# Research Papers — 2026-08 · bundle page 109 of 240 > Full-text markdown of papers #5401–5450 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/109 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/108.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/110.md) ### GEO-Flag: Detecting and Measuring GEO-Optimized Web Content Authors: Junjie Chu, Ye Leng, Mingjie Li, Yun Shen, Xinyue Shen, Yang Zhang Published: 2026-08-17 Categories: cs.LG, cs.CR, cs.IR arXiv: https://arxiv.org/abs/2608.16824v2 Generative Engine Optimization (GEO) modifies web content to increase its likelihood of being selected and cited by generative search engines. This can give strategically optimized pages visibility disproportionate to their authority or relevance and even make weak or false information appear well supported. Unlike conventional search, generative search synthesizes information into direct answers rather than presenting competing sources, which can further amplify these risks, as assessing source provenance and authority requires additional user interaction. Despite these concerns, systematic methods for detecting GEO-optimized webpages remain underexplored. We introduce \texttt{GEOFlagBench}, a benchmark of 3,200 web content instances spanning 400 queries, four domains, and eight GEO optimizer families, and use it to systematically evaluate existing GEO detection methods. Although the strongest baseline achieves an aggregate F1 of 0.880, method-level and authorship-conditioned evaluations reveal substantial weaknesses and potential reliance on authorship-related shortcuts. We therefore propose \emph{Intervention-Paired Training} (IPT), which supervises detector responses to GEO interventions and non-GEO AI polishing; on ModernBERT, IPT improves F1 from 0.862 to 0.944 and worst-group accuracy from 0.725 to 0.883. We develop a GEO-gated Agent system for auditing the Source Tier and verifiability of Citation URLs in detected GEO pages. Finally, we deploy the complete pipeline on released Google Search and Gemini-grounded retrieval results for 1,000 real-user queries. Across 10,095 available pages, we estimate an overall GEO prevalence of 8.90\%, reaching 16.36\% among pages modified in 2026. Our results establish a foundation for systematically detecting, auditing, and measuring GEO in real-world search ecosystems. --- ### GEO-Flag: Detecting and Measuring GEO-Optimized Web Content Authors: Junjie Chu, Ye Leng, Mingjie Li, Yun Shen, Xinyue Shen, Yang Zhang Published: 2026-08-17 Categories: cs.LG, cs.CR, cs.IR arXiv: https://arxiv.org/abs/2608.16824v1 Generative Engine Optimization (GEO) modifies web content to increase its likelihood of being selected and cited by generative search engines. This can give strategically optimized pages visibility disproportionate to their authority or relevance and even make weak or false information appear well supported. Unlike conventional search, generative search synthesizes information into direct answers rather than presenting competing sources, which can further amplify these risks, as assessing source provenance and authority requires additional user interaction. Despite these concerns, systematic methods for detecting GEO-optimized webpages remain underexplored. We introduce \texttt{GEOFlagBench}, a benchmark of 3,200 webpages spanning 400 queries, four domains, and eight GEO optimizer families, and use it to systematically evaluate existing GEO detection methods. Although the strongest baseline achieves an aggregate F1 of 0.880, method-level and authorship-conditioned evaluations reveal substantial weaknesses and potential reliance on authorship-related shortcuts. We therefore propose \emph{Intervention-Paired Training} (IPT), which supervises detector responses to GEO interventions and non-GEO AI polishing; on ModernBERT, IPT improves F1 from 0.862 to 0.944 and worst-group accuracy from 0.725 to 0.883. We develop a GEO-gated Agent system for auditing the Source Tier and verifiability of Citation URLs in detected GEO pages. Finally, we deploy the complete pipeline on released Google Search and Gemini-grounded retrieval results for 1,000 real-user queries. Across 10,095 available pages, we estimate an overall GEO prevalence of 8.90\%, reaching 16.36\% among pages modified in 2026. Our results establish a foundation for systematically detecting, auditing, and measuring GEO in real-world search ecosystems. --- ### Quipu: A Governed Bitemporal Knowledge Graph Store Authors: Steve Brown Published: 2026-08-17 Categories: cs.AI, cs.DB arXiv: https://arxiv.org/abs/2608.16813v1 Agents now write knowledge graphs, but knowledge-graph stores still carry defaults set when humans curated them: accept writes now and clean later, keep one time axis or none, treat every writer's facts as equally trustworthy, and leave governance to dashboards and middleware. These four defaults are individually convenient and jointly untenable under agent workloads. We present Quipu, an embeddable store that inverts all four: no fact enters except through a gate whose predicates evaluate the pending post-state; data, trust labels, verdicts, and the rules themselves are bitemporal; named graphs are the unit of authority and trust, composed under a lattice whose one invariant is that composition never widens; and the governance specification $Σ$, the trace, and signed verdicts are facts in the store they govern, making the audit $T \models Σ$ a query. We evaluate with Census, a deterministic multi-writer lifecycle whose single seeded run scores every research question against planted ground truth: the gated store ends with 0 of 6 planted defects versus 6 of 6 ungated; all 7 composition probes uphold the lattice contract; 50 of 50 satisfied verdicts re-derive faithfully as of their instant while all 50 would be misreported under a latest-only rule set; and the SARC reference checker agrees with the in-store audit verdict-for-verdict, differing only on coverage semantics. A recorded trace from a governed writer surfaces a live enforcement gap the audit names with its remediation. On DEMM-Bench, an external decision-evidence sufficiency benchmark, a content-only reading of the exported records answers all 512 property-level governance questions correctly with zero overclaim under all eight degradation conditions, while container-presence baselines overclaim on up to 87.5% of them -- and the run surfaced, and led us to close, a gap in what a denial's verdict attests. --- ### Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision Authors: Long Cui, Xiaoqian Liu, Qi Qin, Yi Xin, Tao Lin, Jianguo Li, Linfeng Zhang Published: 2026-08-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.16812v1 Existing image editing frameworks predominantly follow the training paradigm of text-to-image diffusion models. However, extending this paradigm to image editing highlights two inherent discrepancies, specifically, the insufficient attention to edit concept granularity and the training inefficiency caused by sparse supervision signals. To address these issues, we establish a comprehensive hierarchical taxonomy featuring over 1,000 fine-grained edit concepts and build ConceptEdit-12M, a massive dataset of 12 million high-quality editing pairs via an improved synthesis framework. This library-driven approach effectively rectifies the distribution collapse of generated data while ensuring high data fidelity. Furthermore, we propose a dense supervision training strategy that synthesizes multiple non-interfering concepts into single image pairs. By providing richer learning signals, this strategy significantly enhances both training efficiency and overall model performance. Training results validate our strategy, significantly outperforming prior works. Finally, we present ConceptEdit-Bench, a granular evaluation suite designed to diagnose model capabilities across a vast array of real-world scenarios. --- ### Unsupervised Learning of Cell Instances with Generative Routing Pyramids Authors: Ziwen Liu, Martin Weigert Published: 2026-08-17 Categories: cs.CV, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2608.16810v1 Identifying and representing object instances such as cells or nuclei is a common task in microscopy image analysis. Established machine learning workflows typically use supervised detection or segmentation followed by feature extraction or classification, which requires manual annotations and treats instance segmentation and cell representation as separate stages. We describe a new unsupervised method for cell instance segmentation and phenotypic classification from unlabeled microscopy images. Our method is based on reconstructing each image using a coarse-to-fine routing pyramid that associates pixels with spatially sparse latent sources. The resulting pixel-to-latent associations yield instance masks, while the source latents encode cell morphology. We demonstrate competitive performance in instance segmentation across diverse cell morphologies and imaging modalities, as well as generative modeling of cellular phenotypes under perturbations. Source code and checkpoints are available at https://github.com/weigertlab/routing-pyramids. --- ### Breaking Planner Integrity Boundary: Enviroment State-Text Injection Attack on LLM-Driven Embodied Agents Authors: Jiawei Liu, Jiacheng Guo, Tian Zhang, Yiwei Xu, Juan Wang, Jinlin Fan, Bowen Xiao, Chi Guo, Keyan Guo, Hongxin Hu Published: 2026-08-17 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.16806v3 Large language model (LLM)-driven embodied agents rely on environment states to interpret scenes, generate high-level plans, and drive physical execution, making planner-visible state representations a critical security boundary. Existing attacks primarily manipulate user instructions, prompt contexts, model behavior, or perceptual inputs, while paying limited attention to whether environment-state text itself can serve as deceptive task evidence and propagate beyond planning to affect execution outcomes. Because embodied tasks are constrained by entity grounding, action preconditions, spatial relations, and environmental constraints, planning deviation alone does not guarantee adversarial execution. To address this gap, we investigate environment-state text as an independent attack surface and present the first closed-loop Environment State-Text Injection (ESTI) attack for LLM-driven embodied agents. Without modifying the original user instruction, model parameters, or executor, ESTI reformulates an adversarial objective as false state evidence compatible with the current environment and influences planning and execution through object properties, spatial relations, affordances, task-stage rules, and execution feedback. We further develop ESTI-Bench to evaluate attack propagation across the planning-to-execution closed loop and compare ESTI with Vanilla IPI, EIRAD, and BADROBOT across ProgPrompt/VirtualHome, VoxPoser/RLBench, and AI2-THOR/iTHOR. ESTI consistently outperforms existing baselines, improving planning-level and execution-level attack success rates by up to 89.32\% and 43.69\%, respectively. Further analysis shows that grounding, consistency, and executability jointly determine whether manipulated state evidence can propagate through the embodied closed loop and produce verifiable environmental changes. --- ### When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents Authors: Jiawei Liu, Jiacheng Guo, Tian Zhang, Yiwei Xu, Juan Wang, Jinlin Fan, Bowen Xiao, Chi Guo, Keyan Guo, Hongxin Hu Published: 2026-08-17 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.16806v1 Large Language Models (LLMs) have demonstrated capabilities in in-context learning, task decomposition, step-by-step reasoning, and code generation, driving their gradual evolution from text generation models into the core of agents capable of perceiving environments, invoking tools, and executing tasks. Traditional LLM Agents typically obtain information through webpages, documents, databases, or external tools and generate corresponding invocation sequences according to user goals; when this technology is further integrated with robotic systems, large language models begin to undertake functions such as task understanding, high-level planning, and behavioral decision-making. SayCan combines the task reasoning capability of language models with the affordances of robotic skills, while Code as Policies and ProgPrompt generate robot task plans through policy code and programmatic prompting, respectively, and VoxPoser uses language models and vision-language models to construct three-dimensional value maps to guide robotic manipulation \cite{6,7,8,9}. Vision-language-action models such as PaLM-E, RT-2, and GR00T N1 further strengthen the connection among language, visual perception, and robotic actions \cite{10,11,12}. In such LLM-driven embodied agents, the model not only needs to understand user instructions, but also needs to combine scene states, object attributes, spatial relations, and execution feedback to complete task grounding, and then hand the generated action plan to skill libraries, motion planners, or controllers for execution. --- ### Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models Authors: Yuanzhi Xu, Qian Gao, Jun Fan, Guohui Ding, Zhenyu Yang, Yuteng Xiao, Sixue Lin Published: 2026-08-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.16805v1 Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to the wrong same-class instance. Generic visual-question-answering accuracy marks the response as wrong, while object-hallucination metrics may regard both the object and attribute as image-supported; neither reveals the transfer. This study formalizes this blind spot as Dense Same-Class Attribute Misbinding (DSCAM) and presents InstaBind-Lite, a controlled benchmark that makes it directly measurable. Its 524 images contain 529 curated groups of 3-6 same-class entities, 1773 boxed instances, ordered neighbors, distinguishable color-like attributes, and four complementary question levels, yielding 9580 deterministically evaluated questions. Unlike existing protocols, source-instance annotations separate unsupported generation and recognition failure from an attribute copied from another visible entity. Binding-specific metrics further quantify transfer frequency, adjacency, ordinal distance, and intervention effects. Across five open-source and two commercial/API models, the open-source systems average 19.84% Misbinding Rate and the API systems 7.55%; these errors are hidden by aggregate accuracy. Among identifiable transfers, 80.70% and 81.51%, respectively, originate from adjacent instances. Localization and instance-first interventions help selected models but are not universal remedies. InstaBind-Lite therefore turns previously undifferentiated wrong answers into source-identifiable failure categories and tests a reliability dimension that conventional benchmarks cannot determine: whether a model knows not only what is visible, but which instance owns each attribute. --- ### Cross-Sign Language Transfer Learning Using Domain Adaptation with Multi-scale Temporal Alignment Authors: Keren Artiaga, Yang Li, Ercan Engin Kuruoglu, Wai Kin, Chan Published: 2026-08-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.16804v1 Sign language serves as a vital means of communication for individuals with hearing impairments, yet recognition resources for the over 100 distinct sign languages are severely lacking. In response, we present our work on sign language recognition using transfer learning and the domain adaptation method TA3N, which utilizes the Temporal Relational Network (TRN) module for aligning multi-scale temporal relations. Our findings highlight the superior performance of Domain Adaptation to neural network-based transfer learning, particularly in improving recognition of American Sign Language (ASL). Our research also identifies the effectiveness of aligning shorter-term temporal features between source and target domains. In addition to using RGB, we conducted experiments using Optical Flow mode for the sign language samples, ultimately determining that RGB outperforms Optical Flow in the majority of cases. Our work aims to improve accessibility and communication for individuals who rely on sign language as their primary mode of communication. --- ### When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding Authors: Giuseppe Destefanis, Tomaso Aste Published: 2026-08-17 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.16801v1 We study how teams of AI coding agents coordinate while solving programming tasks. Current evaluations usually report whether the agents complete the task and how much the run costs, leaving the coordination inside the team largely unmeasured. We introduce an instrument to measure this coordination. Each run is represented as a temporal network in which agents and files are nodes, and messages, file writes, and file reads are timestamped directed edges with an associated cost. We apply this instrument to 1902 runs, each evaluated with a fixed test suite, across configurations that vary the team size, the team structure, and the file policy. The resulting networks show how coordination changes as teams grow and as the work changes. Direct messaging initially increases close to quadratically with the number of agents, with much of this growth coming from an early round of introductions. As the teams grow further, this increase levels off in the largest teams we study, where agents increasingly communicate through broadcast messages. The task also shapes the network that emerges. Work built around a shared specification produces dense, highly connected teams, while pipeline tasks produce sparse networks organised around local interfaces. Shared files can replace repeated 1-to-1 communication, cutting output tokens by about 42% at eight agents on message-heavy work, while adding overhead when files already carry the coordination. Naming one agent as coordinator creates no communication hub and provides no reliable improvement in success. We also observe an unprompted tendency for agents to seek out hidden grading material. We repeat the key experimental conditions in a sealed environment, replacing the hidden material with marked placeholder files. Across 244 additional runs, agents still reach for it in four fifths of runs, while the coordinator and file-channel findings reproduce. --- ### ClawGym II: Exploring Black-Box RL on Agent Harness Authors: Huatong Song, Fei Bai, Ming Yang, Renyuan Li, Jia Deng, Jujie He, Zhange Zhang, Daixuan Cheng, Yan Xing, Qi Yun, Xuxing Chen, Danyang Li et al. Published: 2026-08-17 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.16798v1 Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment. However, reinforcement learning through complex harnesses remains largely unexplored, as scaling such training to long-horizon agent tasks introduces fundamental challenges. In this work, we present a unified black-box RL framework for stable and scalable optimization of general agents through complex harnesses. Concretely, we first build a sandbox-based execution infrastructure that isolates task environments and harnesses within temporary sandboxes for large-scale concurrent rollouts. We then decouple policy optimization from opaque harness execution and place a serving proxy at the model boundary to capture model calls. To reconstruct multi-turn trajectories and improve training efficiency, we organize the captured calls into prefix trees and further adapt both critic-based PPO and critic-free GRPO to optimize over the recovered tree structure. Meanwhile, we maintain training-inference consistency throughout the optimization process. Finally, we introduce mix-harness training, allowing a single model to be jointly optimized by heterogeneous harnesses. With Qwen3-30A3B, black-box RL improves Pass@1 on ClawGym-Bench by 9.98 and 14.81 points through OpenClaw and Claude Code, respectively, while remaining stable over 200-400 optimization steps. Moreover, the framework yields consistent gains on more challenging tasks such as JobBench and OfficeQA. Overall, our framework enables effective, stable, and scalable optimization of general agents through black-box harnesses, supporting unified training across heterogeneous execution systems. --- ### UniDot: A Unified Network for Sequence Modeling and Feature Interaction in Large-scale Recommendation Authors: Rongcheng Lin, Yan Sun, Jamey Zhang, Guanglei Xiong, Ivan Ji, Xianjie Chen, Shujian Bu Published: 2026-08-17 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2608.16797v1 Industrial recommenders rely on two model families that have evolved largely independently: feature-interaction models over multi-field user/item features, and sequential models over user-behavior histories. Production systems couple them only loosely. To unify the two, we present UniDot, a novel architecture for post-click conversion prediction built from the factorization-machine (FM) point of view: the embedding inner product---which powers collaborative filtering and lets a recommender generalize to unseen user--item pairs---is the same primitive as attention's query dot key scoring, so a single dot-product of tokens can underlie both feature interaction and sequence modeling. UniDot tokenizes non-sequential fields and multi-domain behavioral sequences into one shared token space and stacks a single macro-block in which a token-mixing bus and a sequence-retrieval bus (item tokens cross-attending the histories) run in parallel and exchange state each layer through an MLP-Mixer fusion, while an FM Highway carries explicit per-layer dot-product interactions around the residual stack directly to the classifier. The sequence side is embedded once per forward pass and shared by all consumers, bounding inference latency. Trained with a dual sparse/dense (Adagrad + Muon) optimizer, an auxiliary conversion-delay head, and multi-path mutual learning, UniDot finished as the runner-up on the Industrial track of the TAAC KDD Cup 2026. --- ### Historical Backtesting for Scientific Question Discovery: A Protocol and Astronomy Pilot Authors: Hui Mao Published: 2026-08-17 Categories: cs.CE, cs.AI arXiv: https://arxiv.org/abs/2608.16795v1 Systems that generate scientific research questions are evaluated today by expert scores, LLM-as-judge ratings, or curated case studies -- all subjective, none falsifiable. We formalize historical backtesting as an alternative: a system generates questions from a corpus frozen at a historical cutoff, the questions are frozen before any access to later literature, and a temporally isolated future corpus then determines whether each question was subsequently answered, partially addressed, independently posed, or ignored, and whether its underlying premise was supported or refuted. The protocol is model-agnostic: any system that emits frozen questions can be scored. We release reproducible astronomy instances with temporally isolated corpora, frozen questions, auditable labels, four reference baselines, and a submission interface. Two findings result. First, evidence-structure-first generation outperforms LLM-only prompting: across a generator decomposition crossed with a four-cutoff stress test (2010-2024, 798 judged questions) whose last window postdates model training, LLM-only generation shows memorized relevance without specific foresight, while a generator using no model weights at all finds questions whose premises the future refutes in every era. Second, a seven-rater agreement study (two blinded human annotators, five judge models, 90 items) indicts the outcome taxonomy rather than the judge: two careful humans agree at kappa = 0.17, every judge model agrees with the professional annotator as well or better (0.17-0.26), and frontier models agree with one another at 0.60 -- certifying an LLM judge by model-model agreement would have overstated its reliability threefold. A prospective instance -- 200 questions frozen 2026-08-17, scored 2027-2030 -- is released so the central claims become contamination-free tests that time itself will grade. --- ### Neurosymbolic Embodied Agents Authors: Mohammad Albinhassan, Yuming Feng, Alessandra Russo, Pranava Madhyastha Published: 2026-08-17 Categories: cs.RO, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.16794v2 Language and vision-language models generate plausible embodied plans but do not guarantee executability, as their outputs can violate environment dynamics or act on incorrectly grounded entities. We present a neurosymbolic agent that factors long-horizon household tasks into task-directed visual exploration and constrained symbolic planning. In the first phase, a vision-language model and exploration harness acquire goal-relevant predicates and instance bindings from egocentric observations and grounded interactions, producing a symbolic initial state. In the second, a PDDL transition model restricts decoding to tokens that extend applicable actions. Monte Carlo tree search then evaluates executable continuations using a domain-independent planning heuristic. The resulting plans are executable by construction under the transition model, with transfer to the environment conditioned on correct visual grounding. On VirtualHome and ALFWorld, open 4B-27B models exceed 90% success in both environments, and our smallest agent substantially outperforms a 27B direct visual policy in each. Constraints and search prove complementary rather than interchangeable: in ALFWorld either alone solves under a third of tasks, whereas their combination solves over 95%. The method also uses several times fewer generated tokens than extended thinking and far fewer model-visible images than direct interaction, and residual failures localize to state acquisition rather than plan generation without any specialized training. --- ### Neurosymbolic Embodied Agents Authors: Mohammad Albinhassan, Yuming Feng, Alessandra Russo, Pranava Madhyastha Published: 2026-08-17 Categories: cs.RO, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.16794v1 Language and vision-language models generate plausible embodied plans but do not guarantee executability, as their outputs can violate environment dynamics or act on incorrectly grounded entities. We present a neurosymbolic agent that factors long-horizon household tasks into task-directed visual exploration and constrained symbolic planning. In the first phase, a vision-language model and exploration harness acquire goal-relevant predicates and instance bindings from egocentric observations and grounded interactions, producing a symbolic initial state. In the second, a PDDL transition model restricts decoding to tokens that extend applicable actions. Monte Carlo tree search then evaluates executable continuations using a domain-independent planning heuristic. The resulting plans are executable by construction under the transition model, with transfer to the environment conditioned on correct visual grounding. On VirtualHome and ALFWorld, open 4B-27B models exceed 90% success in both environments, and our smallest agent substantially outperforms a 27B direct visual policy in each. Constraints and search prove complementary rather than interchangeable: in ALFWorld either alone solves under a third of tasks, whereas their combination solves over 95%. The method also uses several times fewer generated tokens than extended thinking and far fewer model-visible images than direct interaction, and residual failures localize to state acquisition rather than plan generation without any specialized training. --- ### PixRestore: Unified Image Restoration via Pixel Diffusion Transformer Authors: Lingchen Sun, Rongyuan Wu, Xiangtao Kong, Jixin Zhao, Qiaosi Yi, Yujing Sun, Shuaizheng Liu, Zhengqiang Zhang, Lei Zhang Published: 2026-08-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.16793v1 Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors. However, the variational autoencoder (VAE) in latent T2I models may discard restoration-sensitive details, while the open-ended synthesis prior can introduce content-inconsistent artifacts. We present PixRestore, a VAE-free pixel-space Diffusion Transformer (DiT) for UIR, where the diffusion backbone is trained entirely from scratch, without relying on T2I pretraining. PixRestore performs flow matching directly on patchified pixels, preserving fine-grained details while keeping the token sequence tractable. To adapt to different degradations, PixRestore learns to predict the reliability of layer features using LQ--HQ DINO feature similarity. Features from more reliable layers are fused as dense conditioning, while less reliable layers receive stronger HQ-feature supervision to encourage degradation removal. We train PixRestore on a large-scale corpus of diverse scenes and degradations, and further finetune it into a one-step generator using DINO-based adversarial objectives for efficient inference. Experiments on public benchmarks and real-world test sets show that, with only about 50M parameters and single-step inference, PixRestore achieves the best overall fidelity, perceptual quality, and robustness to degradations among competing UIR models while being far more efficient. Larger PixRestore variants can further boost performance, demonstrating the scalability of our pixel-space design. Code and the curated benchmark can be found at https://github.com/csslc/PixRestore. --- ### Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching Authors: Ye Lu, Shen Wang, Zhaoyang Zhang, Yihan Yan, Li Liu, Runze Liu, Fanghui Sun Published: 2026-08-17 Categories: cs.CV, cs.AI, cs.CR, cs.MM arXiv: https://arxiv.org/abs/2608.16791v1 Model Inversion Attacks (MIAs) aim to reconstruct representative training samples of target identities from face recognition models, exposing critical security vulnerabilities. Existing methods typically rely on indirect guidance or highly stochastic guidance, making it difficult to stably optimize generation trajectories toward target facial images. In this paper, we propose Steering Flow Model Inversion (SFMI), a novel two-stage white-box model inversion method that reformulates inversion as a trajectory-steering task. Specifically, Step I, Learning a Generic Flow Matching Prior, pre-trains a generic unconditional Flow Matching model to encode the manifold of human faces as a robust prior. Step II, Attacking with Progressive Guidance Scheduler (PGS), injects time-dependent target-specific gradients during sampling. By backpropagating through the target model to obtain gradients from intermediate generated states, PGS progressively injects adaptive guidance signals into the vector field. This process effectively steers the current generative flow from random noise toward the high-density regions of the target class. Under an identity-disjoint cross-evaluation setting using the CelebA dataset, SFMI achieves an ACC of 0.9248, an FID of 22.61, and an LPIPS of 0.3874 on the ArcFace target. Extensive experiments on multiple target models demonstrate that SFMI achieves competitive state-of-the-art performance in attack success and visual fidelity under the evaluated white-box protocol. --- ### Revisiting Classifier-Free Guidance Methods in Latent Diffusion Models Authors: Artem Sergievskii, Artyom Turevich, Sergey Kastryulin Published: 2026-08-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.16786v1 Inference-time quality-enhancement methods are an effective and widely adopted means of improving diffusion models without expensive retraining. We study a family of training-free techniques conceptually rooted in Classifier-Free Guidance (CFG), most of which were originally proposed on older U-Net diffusion models and validated using metrics that assess image quality in isolation, without accounting for compositional alignment or semantic correspondence between the generated image and its associated text prompt. We re-evaluate eight such methods on two open-weight rectified-flow transformers under a fixed per-model protocol and three compositional-alignment benchmarks. No method consistently improves on CFG across the measured criteria. APG obtains several nominal best scores, but the corresponding gains often remain within the estimated evaluation uncertainty. Attention-perturbation methods provide isolated gains on SD3.5 Medium and more frequent degradations on FLUX.2 (klein) 4B Base, while CFG remains a competitive lower-cost baseline. --- ### Calibration-Free Vehicle Speed Estimation: A Monocular Keypoint-Template Approach Authors: Gaofeng Su, Keya Li, Raja Sengupta, Kara M. Kockelman Published: 2026-08-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.16785v1 This paper proposes a calibration-free framework for reliably and effectively estimating vehicle speeds from monocular videos, without relying on roadway features, camera calibration, or roadway-feature-based reference objects. The proposed framework estimates vehicle speeds using a 36-keypoint vehicle template and a homography matrix updated at each frame. A YOLO-based keypoint detection module is trained on diverse datasets, and two estimation strategies are compared: keypoint-only tracking and warped optical flow with dense spatial aggregation. Speed is estimated by projecting displacements into metric space using the homography, with validation conducted on over 400 video clips from roadside and overhead datasets, covering speeds from 30 to 100 mph. The method achieves reliable speed estimation on the VS13 and BrnoCompSpeed datasets, with the warped optical flow method delivering MAEs of 15.0% and 9.7%, respectively, and 77.9% and 93.1% of estimates falling within +/-20% error. After applying a 10% trim to remove edge-of-frame outliers, performance improves to MAEs of 11.7% and 7.6%, with within-+/-20% accuracy increasing to 85.3% and 95.4%. This work addresses key limitations of existing vision-based approaches and enables low-cost and efficient speed enforcement using portable devices such as dashcams and smartphones, thereby supporting citizen-based enforcement programs for traffic safety. --- ### GRIP: Grounded Reasoning via Information-Restricted Premises Authors: Lirui Teng Published: 2026-08-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.16776v2 High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent state, leaving retrieved evidence functionally irrelevant. We call this failure mode query dominance. To address it, we introduce \textbf{GRIP} (Grounded Reasoning via Information-Restricted Premises), which imposes capacity asymmetry: the decoder keeps full-dimensional access to the query, while retrieved evidence passes through a severe stochastic bottleneck. This forces the evidence channel to encode only the residual information unavailable from the query. Across five reasoning benchmarks, GRIP outperforms strong iterative baselines, cuts a query--latent mutual-information diagnostic by roughly 30$\times$ (14.8 $\to$ 0.47 bits), and reduces hallucination by 73\%. Residual-alignment analysis further shows that the bottleneck output occupies subspaces less aligned with the query than baseline representations. --- ### GRIP: Grounded Reasoning via Information-Restricted Premises Authors: Lirui Teng Published: 2026-08-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.16776v1 High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent state, leaving retrieved evidence functionally irrelevant. We call this failure mode query dominance. To address it, we introduce \textbf{GRIP} (Grounded Reasoning via Information-Restricted Premises), which imposes capacity asymmetry: the decoder keeps full-dimensional access to the query, while retrieved evidence passes through a severe stochastic bottleneck. This forces the evidence channel to encode only the residual information unavailable from the query. Across five reasoning benchmarks, GRIP outperforms strong iterative baselines, cuts a query--latent mutual-information diagnostic by roughly 30$\times$ (14.8 $\to$ 0.47 bits), and reduces hallucination by 73\%. Residual-alignment analysis further shows that the bottleneck output occupies subspaces less aligned with the query than baseline representations. --- ### Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis Authors: Reza Fayyazi, Michael Zuzak, Shanchieh Jay Yang Published: 2026-08-17 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.16775v1 Large Language Models (LLMs) are increasingly being deployed in cybersecurity operations to assist cybersecurity analysts with rapid decision-making against emerging threats. However, there is a main criteria that must be met when using LLMs in cybersecurity, that is, trust in the generated outputs. As Agentic AI is integrated into operational systems, a robust evidence attribution and provenance tracking technique is essential to trace the origins of model generations. When autonomous agents make a decision (right or wrong), the ability to trace back through the decision chain is critical, as without it, teams cannot identify which segment of the data caused the model generation. Existing methods often struggle to distinguish among complex and highly similar evidence sources, such as cyber incident logs. This reveals a key gap: current approaches do not adequately capture the holistic geometric relationship between the retrieved evidence and the generated response for reliable evidence verification. To bridge this gap, we propose Topological Attribution Distance (TAD), inspired by Topology, to characterize and capture the global geometric shape of an output and its changes against its retrieved logs. In other words, if the embeddings of a specific source log drastically changes the geometry of the model's response in the embedding space, this suggests that such log is a critical source for the model's generated response. Therefore, TAD is powered by segment-level ablation attribution to investigate incident logs of an actual cyberattack. We demonstrate how TAD finds the most attributed logs on LLM outputs in an adaptive manner. This can provide an explainable and trustworthy tracing based on each LLM's hidden state to understand how geometrically different retrieved logs influence the model generation, and provide evidence verification in cybersecurity and Agentic-AI workflows. --- ### Beyond $L_2$: Generalizing Abductive Latent Explanations to Diverse Prototype-Based Architectures Authors: Jules Soria, Alban Grastien, Romain Xu-Darme, Julien Girard-Satabin, Zakaria Chihani, Daniela Cancila Published: 2026-08-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.16773v1 Prototype-based neural networks are hailed as interpretable-by-design architectures. Recently, Abductive Latent Explanations (ALE) were introduced to provide formal, mathematically guaranteed explanations that leverage the intrinsic structure of these networks to ensure both predictive safety and human readability. ALEs rely on computing tight bounds on latent space distances to produce formal explanations. However, existing ALE formulations are rigidly confined to Euclidean latent spaces. This leaves a critical gap: modern state-of-the-art architectures increasingly rely on non-Euclidean representations - such as spherical metrics, Gaussian densities, and dimensional projections - rendering current formal explanation methods incompatible. In this work, we generalize the ALE framework to support non-Euclidean prototype architectures. For each geometric variant, we systematically derive how to either map the architecture to existing bounds or construct novel, architecture-specific bounding algorithms. We validate our theoretical constructions by computing subset-minimal formal explanations on fully trained image classifiers. By unifying these diverse models under a single formal framework, we enable the first rigorous, cross-architecture comparison of their interpretability. --- ### TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation Authors: Haoran Wang, Chaofan Ma, Ran Yi, Lizhuang Ma Published: 2026-08-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.16765v1 Despite recent advances in unified multimodal models for multi-reference image generation, existing benchmarks remain organized around predefined task types (e.g., "subject composition"), which are ill-suited to this combinatorial setting and lead to fragmented coverage, uncontrolled complexity, and little diagnostic value. Recognizing that diverse multi-reference tasks share a common set of atomic operations, we adopt a capability-oriented perspective and formalize four operators: Anchor ($f$), Disentangle ($g$), Apply ($\oplus$), and Compose ($C$). Any multi-reference prompt can then be represented as a compositional formula over these operators, whose structural complexity is quantified by the number of operator slots. Building on this formulation, we construct TRACE-Bench, comprising approximately 1,600 evaluation cases across slot counts 1--8, built from 631 formula templates and around 4,000 reference images spanning diverse artistic styles and real-world subjects. The formula structure directly drives an operator-aligned evaluation protocol for per-capability scoring and a diagnostic tree analysis for recursive failure localization. Evaluating 9 leading models reveals insights invisible to holistic scoring: the primary bottleneck lies in disentanglement ($g$) and attribute binding ($\oplus$) rather than scene-level composition ($C$), with even the best model scoring only 0.74 on attribute fidelity. Project page: https://amuseum-whr.github.io/TraceBench --- ### LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing Authors: Ruoqi Shu, Xuhui Wang, Isaac Wang, Yanming Mai, Bo Wan Published: 2026-08-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.16763v1 Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency, and reproducibility under strict enterprise constraints. In practice, documents arrive with heterogeneous layouts and formats, semantically rich and context-dependent content, and embedded business rules that current pipelines struggle to process reliably. We introduce LAVA (Logic-Aware Validation and Augmentation), a modular, backbone-agnostic pipeline built on multimodal large language models, that integrates a four-stage design: document-rule retrieval, layout-preserving information extraction, auxiliary metadata enrichment, and auditable symbolic/arithmetic verification. LAVA supports robust rule grounding, fine-grained error attribution, and consistent, traceable end-to-end execution, capabilities essential for high-stakes deployment. Evaluated on a large real-world benchmark with diverse financial documents and dozens of expert-curated validation rules, LAVA outperforms baselines in hallucination control and edge-case handling while maintaining efficient token usage, demonstrating practicality for high-volume, time-critical validation. --- ### On the Principles Behind Neural Network Optimizers Authors: Yushun Zhang Published: 2026-08-17 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2608.16760v1 Reliable optimization is central to neural network (NN) training, yet Adam, the default optimizer for modern LLMs, rests on a fragile foundation. This thesis develops a principled grounding for Adam and motivates new designs. First, we revisit Adam's divergence--convergence debate and show the existence of a problem-dependent phase transition: with properly chosen, batch-size-dependent hyperparameters, Adam converges, whereas under small-$β_2$ regimes it can diverge. Second, we investigate why Adam substantially outperforms SGD on Transformers through Hessian structure. We find that the Hessian evolves toward a near-block-diagonal form along training, accompanied by strong block heterogeneity. We prove that this structure makes Adam's diagonal preconditioner effective. We further show that this special Hessian structure originates from consecutive multiplications of large matrix variables, and we provide a rigorous analysis based on random matrix theory. Finally, these insights motivate Adam-mini, a new optimizer that reduces Adam's memory footprint by 50\% while preserving its performance. Our results also have broader implications beyond Adam: they reveal new local structures in matrix-based nonconvex problems, and also help understand and improve recent NN optimizers, such as Muon. --- ### Binarized High-Efficiency RAW Video Restoration and Beyond Authors: Tianyu Zhu, Ying Fu, Hesong Li, Gengchen Zhang, Xin Yuan, Yulun Zhang Published: 2026-08-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.16756v1 RAW video restoration is fundamental to high-quality low-level perception and serves as the basis for a wide range of downstream vision applications. While binary neural networks (BNNs) enable efficient lightweight deployment for image enhancement, their deficiencies in modeling temporal coherence and activation value distributions hinder their effectiveness when applied to video scenarios. In this paper, we propose BinRVR, a binarized RAW video restoration framework that reduces computation and parameters by approximately 96% while incurring only about 4% performance degradation. Specifically, we present a Binarized Information Interaction Module (BIIM) to jointly model spatial and temporal information in an efficient and unified manner. Moreover, we develop a Distribution-Aware Binarized Convolution (DAB-Conv) that leverages the statistics of full-precision activations to mitigate quantization errors. The proposed framework further supports multi-bit quantization, enabling flexible accuracy-efficiency trade-offs across different hardware constraints. Extensive experiments demonstrate that our BinRVR achieves competitive performance compared with state-of-the-art binarized methods on RAW video restoration tasks, including low-light enhancement, denoising, deblurring, and super-resolution. We further explore the potential of our method on downstream video applications, including object detection and monocular depth estimation. --- ### Beyond Uncertainty: Generalizable Failure Monitoring for Surgical Segmentation under Acquisition Degradation Authors: Hieu D. Pham, Dang P. M. Cao, Thanh Trung Huynh Published: 2026-08-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.16748v1 Surgical segmentation networks can fail silently under acquisition degradation: predicted masks may be wrong even when model confidence remains high. Existing deployment-time monitors rely primarily on uncertainty estimates and can therefore miss confident failures. We present TCSR-Monitor (Temporal Conformal Surgical Risk Monitor), a post-hoc failure-monitoring framework that combines confidence with observable shape, temporal-consistency, and image-quality cues. TCSR-Monitor wraps a frozen segmentation model, requires no model internals, and operates without ground truth at deployment. We also introduce a validation protocol to assess whether alarms remain credible under distribution shift. On EndoVis 2017, leave-one-corruption-out evaluation shows that TCSR-Monitor generalizes to unseen acquisition degradations and substantially outperforms confidence-based baselines. A circularity control confirms that it predicts segmentation failure rather than simply detecting corrupted images. Mondrian conformal calibration balances miss-rates across degradation severities, but a single global threshold still produces false alarms on up to 40% of correctly segmented frames at moderate corruption. Zero-shot transfer to SAM2 demonstrates feature portability, although entropy outperforms the transferred monitor at both evaluated thresholds. Overall, reliable monitoring under acquisition degradation benefits from complementary observable signals beyond confidence alone, but substantial false-alarm and transfer limitations remain. --- ### Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments Authors: Adam Karvonen, Euan Ong, Subhash Kantamneni, Samuel Marks Published: 2026-08-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.16747v1 Many areas of AI research, such as language model interpretability and chain of thought faithfulness, seek to explain model behaviors. But what constitutes a "good" explanation? In this work, we evaluate explanations through the lens of counterfactual simulatability-whether the explanation is useful for predicting model behaviors on related counterfactual inputs. To this end, we introduce CHIVE (Counterfactual Hypothesis Investigation Via Edits), a novel agentic pipeline that identifies unexpected model behaviors in the wild and investigates them with counterfactual prompt edits. This yields thousands of high-quality explanations for naturally-occurring model behaviors along with supporting counterfactual evidence. We apply CHIVE in two ways. First, we evaluate whether common LLM interpretability techniques improve an agent's ability to predict counterfactual model behaviors. Surprisingly, we find no uplift from any of the interpretability techniques studied. Second, we use CHIVE to generate training data. We find that training models to predict outcomes of CHIVE-generated counterfactual experiments generalizes to various out-of-distribution settings. Overall, CHIVE automatically discovers explanations of naturally-occurring LLM behaviors, enabling us to evaluate and improve methods for explaining LLM behaviors. --- ### VicEdit: Learning to Edit Videos from Visual In-Context Examples Authors: Yuji Wang, Teng Hu, Yuheng Chen, Ran Yi, Han Feng, Weijian Cao, Chengjie Wang, Lizhuang Ma, Jiangning Zhang Published: 2026-08-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.16745v1 Despite progress in instruction-based video editing, unimodal textual instructions inherently struggle to convey fine-grained textures and complex dynamics. To bridge this perceptual gap, we propose Visual In-context Editing, a new paradigm elevating video editing from textual instructions to multi-modal visual guidance encompassing single image, image pair, and video pair. To facilitate this paradigm, we curate VicEdit-400K, the first large-scale dataset for visual in-context video editing. We develop an automated pipeline to generate 400K high-quality samples across ten task types, ensuring superior visual fidelity and semantic consistency through multi-dimensional filtering. Leveraging this foundation, we introduce VicEdit, a unified framework to bridge visual and textual contexts. To adaptively extract editing semantics from heterogeneous references, we design Modality-Adaptive Semantic Distillation, which produces modality-specific semantic tokens from visual references. These tokens are then synergistically integrated with textual instructions through Dual-Context Injection, enabling the generation process to benefit from both visual and textual signals. Extensive evaluations on VicEditBench demonstrate that VicEdit achieves state-of-the-art performance across both basic instruction editing and visual in-context editing tasks, establishing visual in-context learning as a powerful and controllable paradigm for video editing. --- ### TDD-Agent: Test-Driven Reasoning for Code Generation Authors: Hongyue Yu, Kefan Li, Jiakun Li, Hongzheng Chai, Yuan Yuan, Rui He, Junyi Wei Published: 2026-08-17 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.16742v1 Large Language Models (LLMs) have achieved remarkable progress in code generation, yet ensuring correctness in complex, repository-level tasks remains challenging. Existing approaches often use generated tests as static post-hoc validators, which limits their ability to guide implementation and may introduce misleading feedback when the tests themselves are incomplete or incorrect. In this paper, we introduce TDD-Agent, which operationalizes the test-driven development paradigm for code generation. TDD-Agent first prompts the model to generate executable tests, encouraging it to clarify expected behaviors before implementation, and then performs iterative dual-track refinement over both the generated code and tests using execution feedback. We first isolate the effect of test-first reasoning through a prompt variant TDD-prompt on LiveCodeBench, where it consistently improves upon reasoning-based prompting baselines. Building on this finding, we evaluate the full TDD-Agent framework on RepoEval, a repository-level benchmark, and show that it consistently outperforms retrieval-based and agent-based baselines. Additional analyses show that iterative refinement improves not only code correctness but also the effectiveness of the generated tests, yielding higher pass rates, coverage, and mutation scores, suggesting that tests can serve as evolving reasoning artifacts rather than fixed validators. Our source code is available at https://anonymous.4open.science/r/TDD-Agent-Framework-6370/. --- ### Le Critique: Privileged Value Functions for LLM Reinforcement Learning Authors: Siddarth Venkatraman, Matthieu Dinot, Laurence Aitchison Published: 2026-08-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.16739v1 Reinforcement learning algorithms for Large Language Models (LLMs) are largely distinguished by their variance reduction strategy. Group-relative methods like GRPO reduce gradient variance by sampling multiple rollouts per prompt, but provide only sequence-level credit. Training is also blocked by straggler rollouts, reducing throughput and increasing off-policyness. Learned value functions theoretically address both problems, providing token-level advantages without requiring large groups. However, additional infrastructure engineering challenges combined with the practical success of critic-free methods have made it difficult to justify their inclusion in RL pipelines. We propose two complementary strategies to improve the performance of value function RL: 1) Privileged Value Functions (PVF) which provide an elegant mechanism to inject additional task-relevant token-level signal without biasing the policy objective; 2) TETHER, a baseline that adaptively interpolates between group-relative and value baselines depending on the value function accuracy. Across several reasoning tasks, both strategies consistently improve over the standard value function baseline, and are competitive with or outperform mean-baseline GRPO. --- ### GoalEvolve: From Handcrafted Algorithm Priors to Goal-Driven Evolution of Physical Design Algorithms Authors: Haixu Liu, Lei Zhou, Yuhao Ren, Yumao Wu, Zhiang Wang Published: 2026-08-17 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2608.16733v1 Physical design algorithms operate within tightly coupled, multi-stage optimization flows, where stage-local gains may vanish or induce downstream degradation. Existing program-evolution frameworks often rely on stage-local objectives or undifferentiated multi-metric feedback, which neither guarantee better final results nor identify which unmet requirement should guide the next iteration. We present GoalEvolve, a goal-driven framework that makes physical design algorithm evolution accountable for the final quality of results (QoR) of the complete flow. Given a multi-objective QoR target region, GoalEvolve converts unmet requirements into normalized target gaps, identifies the dominant bottleneck, and uses stage-resolved checkpoint evidence to locate the responsible stage. An LLM-based Teacher then narrows the search to a relevant algorithmic decision and source region, while parallel Student agents implement and validate hypotheses through full-flow evaluation. Local effects, optimization debt, and downstream retention are retained as mechanism evidence for subsequent evolution. Across eight ASAP7 designs, GoalEvolve improves post-route TNS by 30.67% on average and reduces leakage and dynamic power by 21.18% and 9.42% versus default OpenROAD. Relative to commercial-tool goals, it closes 62.20% of the normalized power gap on power-dominant designs, surpasses the TNS goals on both timing-dominant designs, and closes 32.48% of the equal-weight timing-power gap on joint designs. Across all three designs evaluated against Codex goal mode under matched budgets, GoalEvolve further improves TNS by 26.46% while reducing leakage and dynamic power by 12.38% and 0.76%, respectively. --- ### Unsupervised Anomaly Detection for Image Dataset Quality Assurance in Multi-Center Breast MRI Authors: Chiara Tappermann, Steffen Renisch, Lars Ole Schwen, Hans Meine, Horst K. Hahn, Eike Petersen Published: 2026-08-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.16725v2 Corrupted, inconsistent, or anomalous data silently threatens the safety and reliability of medical AI. Despite growing regulatory recognition of dataset quality assurance (QA) for high-risk medical AI, scalable automated detection remains underdeveloped. We employ unsupervised anomaly detection (AD) and out-of-distribution (OOD) detection as an automated dataset QA mechanism for multi-center dynamic contrast-enhanced breast MRI. We build a controlled AD benchmark of 17 realistic QA-relevant anomaly types from six public datasets (protocol violations, processing errors, incorrect anatomical regions) and propose a taxonomy of radiological image anomalies based on human visual perception, enabling fine-grained analysis of AD failure modes. The benchmark includes near-, medium-far-, far-OOD samples, as well as in-distribution and external normal data. Four methods are evaluated: a projection-based method extended with a domain-specific feature extractor and a novel positional encoding, a reconstruction-based approach extended to full 3D volumes with an augmented training objective, and two unmodified hybrid OOD detection methods. Medium-far- and far-OOD samples are detected reliably, whereas near-OOD samples and external normal data from unseen institutions expose method-specific differences. The 3D reconstruction-based approach best balances detection performance (AUROC: 0.936) and generalization to unseen institutions. The projection-based method with positional encoding achieves the highest overall detection performance (AUROC: 0.954). Both hybrid methods exhibit critical failure modes, confirming that methods validated for one modality or anatomy may not generalize without domain-specific adaptation. Implants and mastectomies remain an open challenge for all methods. Our results establish a foundation and practical guidance on scalable unsupervised QA in medical AI pipelines. --- ### Unsupervised Anomaly Detection for Image Dataset Quality Assurance in Multi-Center Breast MRI Authors: Chiara Tappermann, Steffen Renisch, Lars Ole Schwen, Hans Meine, Horst K. Hahn, Eike Petersen Published: 2026-08-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.16725v1 Corrupted, inconsistent, or anomalous data silently threatens the safety and reliability of medical AI. Despite growing regulatory recognition of dataset quality assurance (QA) for high-risk medical AI, scalable automated detection remains underdeveloped. We employ unsupervised anomaly detection (AD) and out-of-distribution (OOD) detection as an automated dataset QA mechanism for multi-center dynamic contrast-enhanced breast MRI. We build a controlled AD benchmark of 17 realistic QA-relevant anomaly types from six public datasets (protocol violations, processing errors, incorrect anatomical regions) and propose a taxonomy of radiological image anomalies based on human visual perception, enabling fine-grained analysis of AD failure modes. The benchmark includes near-, medium-far-, far-OOD samples, as well as in-distribution and external normal data. Four methods are evaluated: a projection-based method extended with a domain-specific feature extractor and a novel positional encoding, a reconstruction-based approach extended to full 3D volumes with an augmented training objective, and two unmodified hybrid OOD detection methods. Medium-far- and far-OOD samples are detected reliably, whereas near-OOD samples and external normal data from unseen institutions expose method-specific differences. The 3D reconstruction-based approach best balances detection performance (AUROC: 0.936) and generalization to unseen institutions. The projection-based method with positional encoding achieves the highest overall detection performance (AUROC: 0.954). Both hybrid methods exhibit critical failure modes, confirming that methods validated for one modality or anatomy may not generalize without domain-specific adaptation. Implants and mastectomies remain an open challenge for all methods. Our results establish a foundation and practical guidance on scalable unsupervised QA in medical AI pipelines. --- ### GenRouter: Unified Workflow Routing for Agentic Image Generation Authors: Harold Haodong Chen, Zhiyu Hou, Wen-Jie Shu, Weilin Ruan, Yingjie Xu, Litao Guo, Ying-Cong Chen Published: 2026-08-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.16721v1 The rapid evolution of text-to-image (T2I) generation models has effectively solved the foundational challenge of raw pixel synthesis, shifting the community's focus toward fulfilling increasingly intricate user requests. While recent agentic image generation workflows enhance static inference with advanced capabilities like external knowledge retrieval and iterative reasoning, they mostly operate in isolated silos with fixed ``one-size-fits-all" topologies. This inevitably leads to severe compute-mismatch, where simple queries are forced through computationally heavy pipelines. To bridge this gap, we present GenRouter, the first unified workflow routing framework for agentic image generation. We first formulate GenCanvas, standardizing diverse agentic pipelines into a universal set of foundational primitives and executable templates. Operating over this unified space, GenRouter adaptively routes heterogeneous prompts to their optimal workflows via (i) demand profiling, (ii) experience matching, and (iii) Pareto filtering. Extensive experiments across diverse benchmarks demonstrate that GenRouter achieves superior visual alignment while reducing execution costs by over 95% and latency by 65% compared to heavyweight static pipelines. Furthermore, the system continuously self-evolves via accumulated experience, enabling robust zero-shot generalization that boosts performance and halves computational overhead. --- ### CytoFormer: A Molecularly Supervised Cell Foundation Model for Histopathology Cell Classification Authors: Jialu Yao, Songhao Li, Alina Yu, Zhi Huang Published: 2026-08-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.16718v1 Identifying cell types directly from routine haematoxylin and eosin (H&E) histology would enable single-cell analysis at scale, but training such models has relied on manual pathologist annotations, which are slow, expensive and unreliable for many cell types. We instead supervise morphology with molecules. Imaging-based spatial transcriptomics profiles individual cells in situ on a section that can afterwards be stained with H&E, so that molecular identity and morphology are observed for the same physical cell. We assembled 81 such paired Xenium sections spanning 16 organs, derived per-cell labels by clustering, marker-gene annotation, organ-wise human review and quality control, and mapped them onto the cell types commonly reported in each organ. This yielded 15.4 million cells, each with a paired H&E image patch and one of 23 cell types, on which we trained CytoFormer, a cell foundation model with a multi-task, per-organ classification head. On spatially held-out tissue CytoFormer reached an accuracy of 0.85 and a macro-F1 of 0.78 across all 16 organs, and its predictions reproduced the tissue architecture of an entire held-out section. The representation also transfers: with the encoder frozen, a linear head on CytoFormer features performed better than six pathology foundation models on four expert-annotated benchmarks, including on organs and cell types that were not part of pretraining. Finally, in an interactive active-learning setting, CytoFormer's embeddings are markedly more label-efficient than existing pathology foundation models, detecting normal epithelium amid look-alike tumour with an F1 of 0.82 from only a few annotations and leading the strongest baseline by 0.13 in F1. CytoFormer turns paired H&E and spatial transcriptomics into a reusable, label-efficient representation for cell-level analysis of routine histology. --- ### PersonaShot: Benchmarking Person-Centric Narrative Continuity in Multi-Shot Video Generation Authors: Yuji Wang, Yuheng Chen, Teng Hu, Ran Yi, Yijia Hong, Han Feng, Weijian Cao, Chengjie Wang, Lizhuang Ma, Jiangning Zhang Published: 2026-08-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.16717v1 Video generation is rapidly evolving from single-shot clips to multi-shot narratives, where the human character serves as the core narrative anchor. However, existing benchmarks mainly assess character appearance or individual-shot quality, without measuring whether physical and emotional states remain coherent across cuts. They also rarely provide criterion-specific evaluation methods, although physical continuity, facial dynamics, and cinematic relations require different visual, temporal, and relational evidence. To address these limitations, we introduce PersonaShot, the first person-centric benchmark for narrative continuity in multi-shot video generation. PersonaShot contains approximately 1,000 multi-shot segments and 16 metrics spanning physical continuity, affective dynamics, and cinematic grammar. \textbf{\textit{1)} Narrative Continuity Benchmark:} We evaluate character coherence across three temporal levels: within-shot states, cross-shot transitions, and sequence-level trajectories. \textbf{\textit{2)} Human-Aligned Specialist Evaluators:} We distill reasoning from a large multimodal teacher into lightweight criterion-specific evaluators, each grounded in the visual, temporal, or relational evidence required by its metric, and align them with expert human judgments. \textbf{\textit{3)} Systematic Evaluation and Insights:} Our evaluation reveals distinct capability profiles across state-of-the-art models and a clear gap between perceptual quality and cross-shot narrative continuity. Even visually compelling videos frequently exhibit physical-state resets, abrupt affective shifts, and broken cinematic relations across shots. Human studies further demonstrate strong agreement between our evaluators and expert judgments. --- ### The Ethical Decision Head: Operationalizing Normative Ethics in Autonomous Vehicles via Reinforcement Learning from Human Feedback Authors: Thomas Mbrice, Ammar Ali, Sami Mian, Khai Hern Low, Eric Chen, Arshia Aghajani, Wolf Schäfer, Amin Shirangi Published: 2026-08-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.16710v1 As autonomous vehicles (AVs) approach Level 4 and Level 5 operational capability (SAE International, 2018), their on- board decision systems must handle not only safety-critical locomotion but also their subsequent moral weight. This paper details the Ethical Decision Head (EDH), a deep re- inforcement learning (RL) framework that encodes ethical reasoning as a differentiable reward signal, enabling a pol- icy gradient agent to learn morally-aligned driving behavior in scenarios whose state representation is aligned with the CARLA simulation environment (Dosovitskiy et al., 2017). Two normative frameworks are instantiated and evaluated: a Utilitarian framework minimizing total casualties and a Kan- tian framework enforcing course maintenance as a categori- cal imperative. The EDH is trained via Proximal Policy Op- timization (PPO) (Schulman et al., 2017) against a Bradley- Terry reward model (Bradley and Terry, 1952) learned from pairwise human preference annotations over 200 collision- imminent scenarios. Results reveal an asymmetry in the learnability of normative ethical frameworks under human su- pervision. The Kantian condition, which reduces to a con- stant prediction task under the codebook, serves as a pipeline control: it confirms training stability and rules out infrastruc- ture failure as an explanation for the utilitarian result. The Utilitarian agent learned something more unsettling: human raters rewarded self-sacrifice over casualty minimization, and the model learned that preference faithfully. This divergence between what humans prescribe in theory and what they re- ward in practice suggests that RLHF does not learn ethics as philosophers define it, but as humans live it. --- ### MIRROR: Multimodal Intelligent Radiology Reasoning and Observation Reporter Authors: Vignesh Nagarajan, Sriram Venkatapathy Published: 2026-08-17 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.16709v1 A radiologist reading a model's output faces two problems. The model returns a number and no reason, and any system that turns that number into readable prose can quietly add claims the model never made. MIRROR is a research prototype built to separate those failures. It chains a multi-label classifier, a Grad-CAM localizer that turns each positive finding into a named anatomical region, and a report writer that receives the labels, probabilities, and regions but never the image. Because the language layer cannot see pixels, it cannot assert a finding the classifier did not make. We are precise about what that buys: a MIRROR report's findings are auditable against the probability vector, while the sentences framing them are ordinary generated text, and we show one stating a cardiothoracic ratio the system never measured. One registry holds the taxonomy, anatomy, and phrasing for chest X-ray, brain MRI, and head CT, so adding a modality is a data change; all three are routed and tested, one is trained. On ChestMNIST that classifier reaches macro AUROC 0.729 and ranks better than chance on all 14 labels, at 1.6 to 6.8 times the precision a random ranker would get. Yet at the default 0.5 threshold it emits no positive prediction at all for 11 of them, and its excellent-looking Brier score of 0.045 sits beside the 0.047 earned by a predictor that ignores the image. The discrimination is real; the decisions are not. Under the class imbalance normal in radiology, aggregate metrics flatter models that do nothing, and should be reported against that floor. --- ### Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors Authors: David Eric Austin, Kaheer Suleman, Jackie Chi Kit Cheung Published: 2026-08-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.16707v1 Large language models (LLMs) are increasingly deployed as decision-making agents in settings that require sophisticated environmental exploration. However, existing work has raised questions about how LLMs actually balance exploration and exploitation. Unlike classical agents, LLM agents engage with tasks through natural language, exposing them to semantic information with no formal counterpart in the task structure. We introduce the semantic bandit, an extension of the multi-armed bandit setting that explicitly considers the textual labels assigned to actions, and use it to study how semantic priors --- inductive biases arising from associations between language and expected reward learned during pre-training, shape LLM exploration behaviour. We find that semantically informative action labels reduce exploration in favour of exploitation, improving performance when aligned with the reward structure and severely degrading it when misaligned. We further find that negative rewards trigger substantially more exploration than equivalent positive rewards, consistent with an expected-scale bias induced by reward conventions common in pre-training data. Overall, we argue that the use of language to define the environment and rewards introduces unavoidable biases derived from the fact that the model is trained on word co-occurence, with implications for the reliability and robustness of LLM agents in real-world decision-making settings. --- ### Learning to Unlearn: Machine Unlearning via Learning the Unlearning Behaviors Authors: Hang Zhang, Kaifeng Zhang, Yixiao Ma, Weijie Xu, Ye Zhu, Kai Ming Ting Published: 2026-08-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.16700v2 Various machine unlearning techniques have been developed in response to privacy legislation requirements, enabling individuals to exercise their legal right to have their data $D_f$ removed from a machine learning model. This process is typically accomplished via the use of an unlearning function denoted as $U$. Existing methods focus on designing an intricate $U$ to unlearn $D_f \subset D$ from a previous model $A(D)$, so that the unlearned model performs as closely as possible to the retrained model $A(D \setminus D_f)$. However, these methods often suffer from high computational costs when dealing with massive training data, as the complex structures of $U$ become a bottleneck even for models with fewer parameters. Inspired by Learning to Optimize, we introduce the first learning-based model-agnostic approach, Learning-to-UnLearn (L2UL). Our core insight is to shift from manually designing $U$ to learning the unlearning behaviors from a distribution perspective, thereby acquiring a simple and efficient $U$ via learning. Our experimental results demonstrate that the accuracy achieved by L2UL is comparable to that of retraining while exhibiting impressive efficiency, particularly in data-intensive scenarios. Furthermore, we validate the performance and scalability of our method on larger models ResNet. --- ### Learning to Unlearn: Machine Unlearning via Learning the Unlearning Behaviors Authors: Hang Zhang, Kaifeng Zhang, Yixiao Ma, Weijie Xu, Ye Zhu, Kai Ming Ting Published: 2026-08-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.16700v1 Various machine unlearning techniques have been developed in response to privacy legislation requirements, enabling individuals to exercise their legal right to have their data $D_f$ removed from a machine learning model. This process is typically accomplished via the use of an unlearning function denoted as $U$. Existing methods focus on designing an intricate $U$ to unlearn $D_f \subset D$ from a previous model $A(D)$, so that the unlearned model performs as closely as possible to the retrained model $A(D \setminus D_f)$. However, these methods often suffer from high computational costs when dealing with massive training data, as the complex structures of $U$ become a bottleneck even for models with fewer parameters. Inspired by Learning to Optimize, we introduce the first learning-based model-agnostic approach, Learning-to-UnLearn (L2UL). Our core insight is to shift from manually designing $U$ to learning the unlearning behaviors from a distribution perspective, thereby acquiring a simple and efficient $U$ via learning. Our experimental results demonstrate that the accuracy achieved by L2UL is comparable to that of retraining while exhibiting impressive efficiency, particularly in data-intensive scenarios. Furthermore, we validate the performance and scalability of our method on larger models ResNet. --- ### Learning to Price with Persuasion Authors: Maria-Florina Balcan, Tejas Pagare, Karan Singh Published: 2026-08-17 Categories: cs.GT, cs.LG, econ.TH arXiv: https://arxiv.org/abs/2608.16699v1 Motivated by modern marketplaces, where the platform or the seller routinely gathers detailed user profiles, we study a novel learning theoretic model that simultaneously involves information and mechanism design. Specifically, we consider the economic setting recently introduced by Bergemann et al. (2022), where in addition to the menu of quality-price pairs, the seller offers information on the value of the match between product quality and buyer's taste via a signaling scheme. We relax the assumption that the seller knows the buyers' belief about the distribution of tastes and study the sample requirements of designing a revenue maximizing scheme. We consider both the batch setting where we have access to data from a set of i.i.d. buyers and an online demand query model where we observe the buyers' behaviors to seller's schemes. Despite the apparent non-convexity of the problem, we also give the first FPTAS to compute a scheme that maximizes the revenue within an arbitrarily small additive loss, which was left open by Bergemann et al. (2022). Overall, this brings a new learning perspective in asymmetric economic settings where buyers and sellers know different types of information. --- ### FabriMAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy Authors: Aniri, Chen Yilin, Jinhe Bi, Junfei Guo, Donglai Ran, Xu Bian, Zengjie Jin, Yujun Wang, Yijun Tian, Volker Tresp, Fei Shen, Tat-Seng Chua et al. Published: 2026-08-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.16697v1 Vision-Language-Action models (VLAs) integrate visual perception, language instruction, and action generation into end-to-end policies across heterogeneous architectures. However, enabling VLAs to self-evaluate their action generation reliability without external supervision remains a major challenge. Existing methods either rely on expert annotations or estimate uncertainty only from output statistics, largely ignoring internal signals. In this work, we observe that internal visual modality entropy exhibits consistent distinctions between successful and failed tasks across heterogeneous VLAs. Although VLAs' architectures differ in their action generation, we show that they share a common latent action generation abstraction evolving under visual perception, language instruction, and state input, which we formulate as a Conditional Generative Markov Chain. Based on this formulation, we propose MAE (Markov Attention Entropy), a self-evaluation framework that directly converts internal attention signals into architecture-aware reliability scores, and introduce LIBERO-Reflect, a 4,000-episode benchmark combining 2,000 standard episodes and 2,000 challenging episodes across four subsets. Extensive experiments across heterogeneous VLA architectures and diverse scenarios show that MAE consistently outperforms state-of-the-art baselines on AUPR, AUROC, and FPR@95. We further instantiate FabriMAE for verifier-free test-time action selection, showing that MAE-guided multiple sampling improves PI-family robustness on LIBERO-Plus with small observed runtime overhead. --- ### UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures Authors: Homa Esfahanizadeh, Matin Mortaheb, Adeel Mahmood, Jinfeng Du, Harish Viswanathan Published: 2026-08-17 Categories: cs.LG, cs.AI, cs.IT, cs.MM arXiv: https://arxiv.org/abs/2608.16696v2 Lossy compression is conventionally driven by a task-agnostic distortion (e.g., MSE or MS-SSIM), yet in many emerging applications the receiver cares not about uniform fidelity but about a downstream task whose relevant content varies across the signal and evolves over time. We formulate task-aware compression as a weighted rate-distortion problem, in which a single codec is driven by a separable, per-component weighted distortion whose weights encode task importance and may depend on the source. We introduce task consistency, i.e., that minimizing the weighted distortion also minimizes the true task loss, and characterize when it holds: for linear tasks, the task loss admits a weighted-MSE form with signal-independent weights under suitable cross-term conditions, while for nonlinear tasks, an integrated-gradients analysis motivates separable task-aware weights. We show how task symmetry and irrelevance further constrain the admissible weights. Guided by this theory, we realize the weight-conditioned code in a single learned Vision Transformer (ViT) codec whose token-level attention natively consumes a per-component importance vector, so one fixed backbone is re-targeted at runtime, from universal (task-agnostic) to task-specialized operation, purely by swapping the injected weights, without retraining, while producing a single human-viewable reconstruction steered to the active task. On downstream face-analysis tasks, a single model reaches 91.4% accuracy at 0.034 bpp on a localized task, within 1.9% of a task-specific codec (93.3%) and well above a universal codec (76.9%). Such task-adaptive compression suits bandwidth-constrained perception systems, e.g., in Physical AI, where the active task drifts and per-task retraining is infeasible. --- ### UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures Authors: Homa Esfahanizadeh, Matin Mortaheb, Jinfeng Du, Harish Viswanathan Published: 2026-08-17 Categories: cs.LG, cs.AI, cs.IT, cs.MM arXiv: https://arxiv.org/abs/2608.16696v1 Physical AI systems such as autonomous vehicles and robots rely on timely exchange of high-dimensional sensory signals under tight bandwidth, latency, and energy budgets. Because the task driving downstream decisions evolves over time, a task-specific codec is brittle and retraining one per task is infeasible in the field. We propose UniTAC, a single learned image codec spanning universal (task-agnostic) to task-specialized operation, re-targeted at runtime without retraining. The task is abstracted as a per-component importance vector, derived, e.g., from gradient attribution of any downstream model, and transmitted as low-overhead side information that conditions both encoder and decoder. Trained once over a broad, randomized family of such vectors against weighted-reconstruction distortion, UniTAC keeps a fixed backbone and a single human-viewable reconstruction whose fidelity is steered to the active task by swapping the injected vector. We analyze the underlying weighted rate-distortion problem, characterizing when a diagonal weighted distortion is task-consistent and how weights relate to task sensitivity. Guided by this, we design a Vision Transformer (ViT) codec whose token-level conditioning natively realizes this weight-driven code. On a localized task at 0.034 bpp, a single UniTAC model reaches 91.4% accuracy, only 1.9% below a task-based codec (93.3%) and above universal codecs (76.9%). --- ### AnchorScore: A CLIP-Based Diagnostic of MLLM Annotation Difficulty Authors: Yan Ma, Lizhuo Zhang Published: 2026-08-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.16690v2 Multimodal large language models (MLLMs) are widely used for automated annotation, yet their per-class accuracy varies widely (e.g., 12%-98% across the 13 classes of three classroom sub-datasets) and is expensive to measure: evaluating one 27B MLLM on 5,416 validation images takes roughly 14 hours, whereas a frozen-CLIP pass over the same images completes in about 3 minutes. A low-cost signal for ranking classes by expected MLLM annotation difficulty a priori remains underexplored. Building on the AnchorProxy construct (per-class zero-shot CLIP accuracy) introduced in the companion study, this paper systematically evaluates its full-frame formulation, termed AnchorScore here, as an a priori diagnostic that flags the classes MLLMs are least likely to annotate reliably. On classroom behavior data (SCB5, 13 classes, 6 MLLMs), AnchorScore correlates with per-class MLLM accuracy (Spearman rho = 0.769, p = 0.002, n = 13). None of the alternative difficulty predictors (DINOv2, ResNet-50, SigLIP, or MLLM self-verbalized uncertainty) showed a significant class-level correlation at n = 13. A cross-model consensus control suggests AnchorScore primarily captures a shared class-difficulty factor rather than a CLIP-specific signal. An independent replication on Stanford40 Actions yields a nearly identical effect (rho = 0.817, p < 0.001); the association is strongest on activity-recognition data and attenuates on medical and satellite imagery. Three practical applications follow: a deployable hybrid CLIP/MLLM routing strategy (predicted-class routing: up to +23 pp over CLIP-only at roughly 44% fewer MLLM calls), prompt disambiguation on hard classes (exploratory), and review-priority prediction for human verification. AnchorScore does not estimate exact MLLM accuracy; it provides a low-cost ranking signal that directs expensive MLLM evaluation to the classes where it is most informative. --- ### AnchorScore: A CLIP-Based Diagnostic of MLLM Annotation Difficulty Authors: Yan Ma, Lizhuo Zhang Published: 2026-08-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.16690v1 Multimodal large language models (MLLMs) are widely used for automated annotation, yet their per-class accuracy varies widely (e.g., 12%-98% across the 13 classes of three classroom sub-datasets) and is expensive to measure: evaluating one 27B MLLM on 5,416 validation images takes roughly 14 hours, whereas a frozen-CLIP pass over the same images completes in about 3 minutes. A low-cost signal for ranking classes by expected MLLM annotation difficulty a priori remains underexplored. Building on the AnchorProxy construct (per-class zero-shot CLIP accuracy) introduced in the companion study, this paper systematically evaluates its full-frame formulation, termed AnchorScore here, as an a priori diagnostic that flags the classes MLLMs are least likely to annotate reliably. On classroom behavior data (SCB5, 13 classes, 6 MLLMs), AnchorScore correlates with per-class MLLM accuracy (Spearman rho = 0.769, p = 0.002, n = 13). None of the alternative difficulty predictors (DINOv2, ResNet-50, SigLIP, or MLLM self-verbalized uncertainty) showed a significant class-level correlation at n = 13. A cross-model consensus control suggests AnchorScore primarily captures a shared class-difficulty factor rather than a CLIP-specific signal. An independent replication on Stanford40 Actions yields a nearly identical effect (rho = 0.817, p < 0.001); the association is strongest on activity-recognition data and attenuates on medical and satellite imagery. Three practical applications follow: a deployable hybrid CLIP/MLLM routing strategy (predicted-class routing: up to +23 pp over CLIP-only at roughly 44% MLLM cost savings), prompt disambiguation on hard classes (exploratory), and review-priority prediction for human verification. AnchorScore does not estimate exact MLLM accuracy; it provides a low-cost ranking signal that directs expensive MLLM evaluation to the classes where it is most informative. --- ### Hide&Seek: Learning to Explain in an End-to-End Differentiable Network Authors: Tal Ellinson, Hadi Mohasel Afshar, Sally Cripps Published: 2026-08-17 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.16689v1 Instance-wise feature selection is a valuable tool for interpreting labeled data and the predictions of black-box models. In contrast to global feature selection techniques, instance-wise methods dynamically identify important features for each instance. A growing number of methods learn a selector, which identifies important features, and a predictor, which uses these to make predictions. However, these pioneering methods face challenges including information leakage and lack of differentiability, which can slow training. In this paper, we present Hide&Seek, an end-to-end differentiable model for instance-wise feature selection. We jointly learn feature selection and prediction under a single objective without information leakage. Hide&Seek outperforms existing state-of-the-art models across a range of experiments and is fast to train. We achieve this by reformulating feature removal as a differentiable operation where instead of discretely removing features, we replace a proportion of each feature. Training is further stabilized via a parsimony-weight annealing framework. ---