# Research Papers — 2026-08 · bundle page 118 of 240 > Full-text markdown of papers #5851–5900 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/118 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/117.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/119.md) ### Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation Authors: Yijie Xu, Haopeng Jin, Run Zhou, Shengbang Liu, Sixiang Chen, Hongyang Cheng, Sicheng Hu, Peterson Co, Jinwen Luo, Huajie Tan, Shanghang Zhang Published: 2026-08-16 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.15680v1 Vision-language-action (VLA) models improve robotic manipulation but remain vulnerable to compounding errors, scene changes, and off-trajectory states. Reinforcement learning can refine pretrained VLA policies, yet sparse success signals hinder exploration, while engineered dense rewards are costly and task-specific. Existing learned visual reward models often rely on static before-after observations, causing temporal ambiguity and weak discrimination between robustness-preserving variations and task-invalid failures under out-of-distribution (OOD) execution. We introduce Robo-Dopamine 2.0, a history- and OOD-aware process reward model with a pairwise prediction interface. It combines (1) history-conditioned pairwise rewards that use source-aligned reference panels for synthetic OOD queries and observed rollout history for online queries, while preserving the queried endpoints, and (2) an OOD-aware signed progress space that represents valid progress, robustness, failure, and recovery. A Signed-Hop Curriculum with transition-aware replay learns coarse execution ordering before fine-grained progress calibration. We also construct an OOD trajectory dataset and a five-family benchmark. Reference panels improve mean visual order consistency (VOC) from 0.967 to 0.986 and OOD-robust VOC from 0.906 to 0.958. With the same 400K pairwise-reward budget, Signed-Hop training with 25% replay reaches 0.9872 mean VOC, compared with 0.9858 for a matched-pool shuffled control. In downstream reinforcement learning, the full model achieves 86.8% mean RoboTwin success and 71/80 successful real-world insertions. --- ### PL-Guard: Probabilistic Logic Reasoning for LLM Guardrails Authors: Satchit Chatterji, Shihan Wang, Giovanni Sileno, Erman Acar Published: 2026-08-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.15673v1 Large language model guardrails can be viewed as policy-consistency problems: a system must determine which policy-relevant facts hold in a prompt-response pair and what those facts imply under a given policy. Common approaches, including policy prompting and LLM-as-a-judge pipelines, often overlap the tasks of semantic grounding and policy reasoning: the model both interprets the prompt-response pair and reasons about whether a policy has been violated. This can lead to unsafe compliance with harmful prompts, or refusals to assist benign ones. To separate grounding and reasoning roles, we propose PL-Guard, a neurosymbolic guardrail architecture. Using a symbolic policy interface consisting of predicates and ProbLog rules, a local LLM grounds prompt-response pairs into predicate probabilities using renormalized True/False token scores, while ProbLog performs explicit probabilistic rule inference over the symbolic policy. On the XSTest benchmark, an offline Qwen-based evaluator finds that PL-Guard with a hand-curated policy reduces unsafe compliance from 22.0% for the base model to 0.5%, and below the 6.0% rate of an LLM-as-a-judge baseline. This comes at the cost of higher over-refusal than the LLM-as-a-judge baseline, 14.4% versus 5.2%. These results suggest that separating neural grounding from probabilistic symbolic reasoning can expose the safety-helpfulness tradeoff while making the guardrail's intermediate reasoning steps explicit and auditable. --- ### Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search Authors: Zhongwei Yu, Yan Song, Xue Yan, Anjie Liu, Xingyu Lu, Yihang Chen, Huichi Zhou, Siyuan Guo, Luoyang Sun, Sihan Chen, Xiangning Yu, Jun Wang Published: 2026-08-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15669v2 Scientific discovery often involves optimising expensive-to-evaluate objectives over vast, structured, and open-ended hypothesis spaces, such as molecules, protein sequences, and computer programs. Generative models such as large language models (LLMs) provide expressive priors over such spaces, but their likelihoods and self-assessments are unreliable proxies for the objectives and calibrated epistemic uncertainty, especially for novel candidates outside the observed data distribution. We introduce the Large Discovery Model (LDM), an empirically grounded recurrent architecture that couples a generative model with a Bayesian non-parametric reward surrogate model. The generative model proposes and refines candidate designs, while the surrogate predicts their performance and quantifies uncertainty, yielding an uncertainty-aware value that guides candidate generation, refinement, and selection. The discovery memory and the surrogate model are continually updated as each new experimental observation arrives. We evaluate LDM on three scenarios spanning different design modalities and objectives, including neural-network training, antibody design, and molecular optimisation. Compared to LLM-only reflection or traditional statistical search across these domains, LDM achieves a $2.4\times$ greater reduction in validation BPB, an $18.2\%$ relative decrease in binding energy, and more than $60\%$ relative gains in molecular multi-objective performance. These results suggests that LDM could serve as a general-purpose discovery engine for effective search over open-ended hypothesis spaces. --- ### SubZero+: Memory-Efficient Adaptive Zeroth-Order LLM Fine-Tuning in Random Subspaces Authors: Ziming Yu, Shuyao Xiao, Xingyu Zhao, Sike Wang, Pan Zhou, Peiyu Zang, Xiangda Yan, Yongjie Yang, Jia Li Published: 2026-08-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15665v2 Zeroth-order (ZO) optimization with SGD in random subspaces enables memory-efficient fine-tuning of large language models without backpropagation. However, high gradient estimation noise fundamentally undermines adaptive optimizers like Adam. We propose SubZero+, which achieves practical adaptive ZO optimization through a carefully designed dual low-dimensionality strategy: (i) multi-query forward-difference gradient estimation in periodically refreshed random subspaces to mitigate noise amplification in moment buffers, and (ii) Adam updates with periodic restarts performed directly in low-dimensional space rather than full-parameter space. In experiments, this dual design retains memory overhead comparable to momentum-free ZO methods while achieving stronger optimization performance than the evaluated ZO baselines. Theoretically, in the exact-directional limit, $K$-query averaging preserves conditional unbiasedness, while the coefficient estimator's covariance and mean-squared error, as well as query-induced second-moment inflation, scale exactly as $1/K$. Extensive experiments across SuperGLUE with models from 1.3B to 32B parameters under both full fine-tuning and LoRA schemes demonstrate consistent improvements over competing ZO methods. SubZero+ significantly narrows the performance gap with first-order optimization while preserving ZO's inference-time memory efficiency. --- ### Sequential Multimodal Evidence Optimization for Product Media Ranking in E-Commerce Authors: Prasenjit Dey, Frank McIntyre, Arnab Sinha Published: 2026-08-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15662v1 On modern e-commerce stores, customers consume ordered slates of heterogeneous product media, such as images, videos, and 3D renders, before making purchase decisions. Existing media-ranking systems often optimize myopic engagement proxies such as clicks or dwell time, even though product media assets are cooperative informational components of the same item that together help customers find the information they need through sequential interaction. We present Sequential Multimodal Evidence Optimization (SMEO), a two-stage utility-guided framework for customer-oriented media sequencing. SMEO first learns a trajectory utility model from consumed media prefixes to estimate how ordered evidence helps customers reach a purchase decision, while mitigating position-bias and variable-depth imbalance in logged data. Recognizing that customer attention is a limited resource, it then trains an autoregressive ranking policy with survival-weighted reward-to-go that prioritizes the most decision-relevant information early, so customers can find what they need with less effort. By decoupling utility learning from policy optimization, SMEO enables stable offline learning from biased logs and post-hoc media attribution without explicit media-level labels. Evaluated offline on large-scale e-commerce sessions using doubly robust off-policy estimation, SMEO improves estimated conversion by 5.5% and helps customers reach a purchase decision with 15% fewer swipes than existing baselines. --- ### Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation Authors: Chenwang Liu, Yijun Liu, Chang Liu, Xu Zhang, Pengchao Han Published: 2026-08-16 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2608.15660v1 Federated learning (FL) enables privacy-preserving distributed model training but faces challenges from heterogeneous model architectures and limited communication resources at the network edge. Federated knowledge distillation (FedKD) alleviates model heterogeneity by combining prototype-wise parameter aggregation and knowledge transfer across heterogeneous models. However, transmitting gradients still introduces considerable communication overhead, while existing compression approaches typically apply a uniform strategy across clients and ignore their diverse model characteristics and resource capacities. To address this issue, we propose a heterogeneous compression framework for FedKD that enables each client to select a compression strategy from a candidate strategy set. We formulate the compression strategy selection problem as a non-stationary stochastic multi-armed bandit (MAB), where each arm corresponds to a compression strategy. An efficiency-aware reward is designed by jointly considering local optimization improvement, global knowledge alignment, and execution time. Based on this formulation, we develop an Adaptive heterogeneouS Compression algorithm for fEderated kNowledge Distillation (ASCEND), which employs an exponential moving average (EMA)-enhanced $ε$-greedy policy to balance exploration and exploitation. Experimental results on multiple datasets demonstrate that ASCEND effectively adapts to heterogeneous model and resource settings, reducing communication overhead and training time while maintaining competitive model accuracy. --- ### WorldRover: A Scalable Synthetic Video Data Engine for World Exploration with Rich Annotations Authors: Xiaojie Xu, Zhengyuan Lin, Runyi Li, Yihao Liu, Kaipeng Zhang, Yongtao Ge Published: 2026-08-16 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2608.15659v2 Learning to generate or reconstruct explorable worlds requires video paired with more than RGB: camera motion, scene geometry, temporal correspondence and, for interactive models, control signals. Real capture can provide some of these signals, but dense geometry and long-range correspondence usually rely on estimation or specialised instrumentation. Rendering provides these quantities directly, yet existing synthetic resources rarely combine them on the same frames while also supporting controlled changes of viewpoint and appearance. We introduce WorldRover, a data engine for generating richly annotated, long-range explorations of artist-built environments. At its core, WorldRover-Engine is an Unreal Engine pipeline that executes and offline-renders minute-scale routes while preserving their full trajectories and scene geometry. The same exploration can be replayed from first-person, third-person, and 360 panoramic cameras under different environmental states. Using WorldRover-Engine, we construct WorldRover-10M, whose sequences pair RGB with metric depth, camera trajectories, and trajectory-derived action signals throughout each exploration. Third-person subsets additionally provide dense optical flow, long-range 2D/3D point tracks with visibility, and a character trajectory distinct from the camera trajectory. The engine can render a traversal from first-person, third-person and 360 panoramic viewpoints, under different environmental states or with a neutral white material, while preserving the route and scene geometry. WorldRover therefore turns long-horizon world exploration into a scalable data-generation problem, providing supervision for models that must build, maintain, and revisit coherent representations of an explorable world. --- ### A Responsible Artificial Intelligence Framework for Groundwater Modeling Authors: Chong Chen, Yulu Zhang, Qingxi Guo, Yihan Liu Published: 2026-08-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15657v1 The rapid development and widespread application of artificial intelligence (AI) have sparked intense discussions on how to deploy responsible AI systems in a manner aligned with human values and ethical standards. Compared to fields like healthcare, energy, or finance, the application of AI in groundwater is relatively limited, and research on responsible AI is even more scarce. Taking the middle reaches of the Heihe River Basin as the study area, this paper proposes six Responsible AI principles: transparency, technical robustness, privacy governance, fairness, accountability, and sustainability. LSTM and Transformer time-series models are developed using multi-source hydrometeorological data, and validated via post-hoc interpretability, Monte Carlo simulation, and scenario analysis. The results show that Transformer outperforms LSTM in accuracy, robustness, and interpretability, demonstrating the operability and practical value of Responsible AI principles in groundwater prediction to support sustainable water management under climate change and human activities. --- ### When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations Authors: Yuqi Chen, Sixuan Li, Yunfeng Cai, Xueai Li, Ka Man Yan, Ying Li Published: 2026-08-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.15654v1 Large language models can write fluent stories, but open-ended storytelling requires more than local fluency. In evolving world simulations and AI-native games, models must preserve facts, relationships, causal dependencies, and character states as the world changes. We introduce WSE-bench, a process benchmark that separately evaluates sustained generation, canonical coherence, and meaningful development in dynamic LLM storytelling. Generation Coverage records the proportion of planned narrative steps produced; Consistency tracks when canon breaks; and Richness measures how meaningfully branching, player-shaped trajectories develop. Across frontier models, Consistency and Richness do not form a smooth trade-off: their empirical Pareto frontier is non-concave, with several non-dominated intermediate configurations that no positive linear weighting can select. Added structure can enrich trajectories, but it does not uniformly improve coherence and may shorten them. Model scale chiefly improves sustained generation, without producing reliable gains in canonical coherence or meaningful development. These results show that sustained generation, canonical coherence, and meaningful development are distinct and sometimes competing capacities. WSE-bench makes those dynamics visible by extending narrative evaluation from finished stories to the processes that create them. --- ### Scalable Black-Box Model Attribution for Images Authors: Asaf Livne, Amir Jevnisek, Shai Avidan Published: 2026-08-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15652v2 The rapid proliferation of generative models raises the model attribution problem: given only an image, can we determine which model produced it? We propose a lightweight CNN to solve this problem in a strict black box setting. The CNN operates on multiple image patches to handle varying image size and improve accuracy. It attributes more models at higher accuracy than prior work, reaching 98.9% on 25-class DRAGON and 95.0% on 27-class OpenFake; runs in a few milliseconds at a cost nearly independent of candidate-set size; and remains robust to transformations encountered in the wild. Beyond closed-set attribution, its learned representation serves as a reusable fingerprint backbone: it supports open-set rejection and few-shot enrollment, recovers model-family structure without lineage supervision, and groups images from unseen generators by source. Controlled ablations and causal perturbations show that its attribution decisions are driven by a spatially local, low-level signal that behaves as a generator-specific fingerprint. --- ### Gaussian-JEPA: Joint-Embedding Predictive Learning for 3D Gaussian Splats Authors: Bin Ren, Qi Ma, Yue Li, Zongyan Han, Yidi Li, Yuqian Fu, Rao Muhammad Anwer, Theo Gevers, Fahad Shahbaz Khan, Salman Khan Published: 2026-08-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15651v1 3D Gaussian Splatting (3DGS) represents 3D content with anisotropic primitives that jointly encode geometry and appearance. Fixed-budget encoders consume sampled observations of Gaussian assets, so the same object may be observed through different primitive realizations. Existing self-supervised methods mainly reconstruct masked Gaussian attributes, tying supervision to one sampled realization and requiring an input-space decoder. Latent prediction offers an alternative, but its application to Gaussian tokens requires targets that accommodate coupled attributes and heterogeneous spatial support. We introduce Gaussian-JEPA, which predicts representations of held-out Gaussian token blocks from visible context. An online encoder processes the context, while a shared exponential-moving-average encoder supplies stop-gradient features for multi-scale targets. Complementary target projections and feature-space grounding provide latent supervision without reconstructing Gaussian attributes. We evaluate the features under Gaussian resampling, partial observations, and renderable shape completion, together with transfer to part segmentation and object classification. Compared with matched reconstruction pretraining, Gaussian-JEPA is more consistent across resampled inputs, retains more instance information under partial observations, and provides stronger frozen features for Gaussian completion. These results support latent prediction as an effective objective for reusable 3D Gaussian representations. Code is on the project page (https://amazingren.github.io/Gaussian-JEPA/). --- ### On Stopping Rules and Spatial Adaptation for CART Authors: Zineng Xu, Yuchao Cai, Yan Shuo Tan Published: 2026-08-16 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2608.15649v1 The popular CART algorithm for regression trees combines a greedy splitting rule with a stopping rule, but while the splitting rule has been well studied, the statistical role of stopping rules is less well understood. Meanwhile, although regression trees fit using Bayesian methods or via empirical risk minimization (ERM) have been shown to be spatially adaptive to local smoothness and anisotropy, it is unknown whether CART can achieve the same adaptation. We address these gaps by proving that, under spatially heterogeneous and anisotropic smoothness and appropriate structural assumptions on the regression function and covariate distribution, CART with the minimum impurity decrease (MID) stopping rule and a suitable threshold achieves pointwise rates that are minimax up to logarithmic factors. These rates hold simultaneously over all points in the domain. Moreover, we prove that spatial adaptation cannot be achieved under the widely used minimum leaf size stopping rule. Together, these results establish a precise statistical role for the MID stopping rule and provide a theoretical basis for the empirical success of CART. --- ### Hierarchical Adaptive Feature Refinement Network for VHR Remote Sensing Image Segmentation Authors: Shuaishuai Cao, Meng Tang, Shuwei Peng, Xuan Liu, Min Huang, Jie Chen, Jiacheng Niu, Yong Chen, Edore Akpokodje, Hui Lin Published: 2026-08-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.15647v1 Semantic segmentation of very-high-resolution (VHR) remote sensing imagery increasingly benefits from strong pretrained hierarchical encoders, yet exploiting their multi-stage representations remains difficult. Nearby regions demand different balances between fine detail and semantic context, aggressive task-specific transformations perturb useful pretrained features, and conventional semantic supervision provides limited structural guidance. We present HAFR-Net, a progressive refinement framework that adaptively organizes and conservatively refines hierarchical representations instead of replacing them with a monolithic decoder transformation. Heterogeneity-Guided Stage-Adaptive Fusion (HG-SAF) predicts dense stage weights conditioned on local feature variation. A Frequency-Residual Adapter (FRA) then injects frequency information through a bounded, zero-initialized residual branch that keeps the fused representation as its reference. A Confusion-Aware Tri-Prior Decoder (CATP) finally regularizes the prediction with boundary, objectness, and training-derived class-relation cues. Under a matched Swin-B training and single-scale inference protocol, HAFR-Net attains 84.12%, 87.86%, 55.17%, and 67.70% mIoU on ISPRS Vaihingen, ISPRS Potsdam, LoveDA, and OpenEarthMap, improving the matched UPerNet baseline by 0.55, 0.95, 1.55, and 1.84 percentage points, respectively. Controlled analyses further show consistent spatial reweighting beyond content-only routing, improved boundary and thin-structure accuracy over matched spatial and spectral alternatives, and reduced confusion on pre-declared class pairs. --- ### Generalised Transportability via Causal Abstractions Authors: Yorgos Felekis, Paris Giampouras, Fabio Massimo Zennaro, Theodoros Damoulas Published: 2026-08-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15645v1 Transporting a causal conclusion from a source study population to a target one is a fundamental problem in causal inference. The theory of transportability provides a criterion for when this is possible: given experimental data from the source and observational data from the target, it determines whether a target query is identifiable and does so completely; i.e. if the query can be transported, the criterion finds the exact formula. However, it works one query at a time and returns an expression rather than the value itself. It is also silent in two practically important regimes: when the query is not transportable and when no target data exist at all. To tackle both, we take a model-level perspective grounded in Causal Abstraction theory. Source and target share variables, graph, and interventions, differing only at a known set of mechanisms, which makes transportability a special case of same-level abstraction. Thus, instead of asking whether one query transports, we ask whether a single map aligns the source and target across their interventional behaviour. We characterise when such a map exists in both the Markovian and semi-Markovian settings; when it does, every target query transports at once. Our main contribution lies in the approximate case. When no exact map exists, the best approximate one still yields certified query intervals, recasting abstraction error as a quantitative notion of approximate transportability. We formulate model-level transport as distributionally robust optimisation over mechanism and environment perturbations of the unseen target and derive certificates for both challenging regimes: bounds for non-transportable queries, and guarantees under target-agnostic settings. We evaluate our framework on synthetic Markovian and semi-Markovian benchmarks and a real ecological dataset, and we show that the certified intervals bracket the true interventional query. --- ### Wiktionary as a Crowdsourced Lexicon for English Dialects Authors: Sidney Wong Published: 2026-08-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.15641v2 This paper evaluates Wiktionary as an ethically crowdsourced lexicon for English dialects. We took a two-phase approach, providing an in-depth descriptive analysis of the crowdsourced lexicon for 12 national varieties of English before applying the lexicon to geo-referenced, country-level social media language data to examine the real-world performance of this crowdsourced dialect lexicon. We demonstrate that Wiktionary matches or exceeds the coverage of traditional dictionaries, such as the Oxford English Dictionary (OED), for regional and Outer-Circle varieties. Our dialect-specific case study on New Zealand English found high alignment between Wiktionary and the OED based on word-formation patterns (R = 0.883). Similarly, we observed high alignment between the dialect lexicon and geo-referenced social media language. While this paper found that Wiktionary has broad coverage of lexical properties, it also highlighted some of the macro-challenges involved in evaluating dialect-responsive language resources and tools, such as the role of language contact in dialects and register effects in web-based corpora. --- ### When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation Authors: Wenhao Yuan, Chenchen Lin, Wentao Hu, Jian Chen, Jinfeng Xu, Shujie Li, Edith Cheuk Han Ngai Published: 2026-08-16 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.15639v2 \textit{Split Federated Learning} (SFL) enables distributed model training by splitting networks between the server and clients. However, under client heterogeneity, the conventional static split strategy may be suboptimal because clients can differ in data distributions, adaptation dynamics, and representation learning progress, making a single split point insufficient to accommodate client-specific training states. In this paper, we propose \textsc{FedSGA}, a \textbf{S}ufficiency-\textbf{G}uided \textbf{A}daptive split \textbf{Fed}erated learning framework that addresses this question through client-specific shallow sufficiency estimation. First, we introduce a client-specific adaptation channel based on private prompt tokens, which tracks local adaptation dynamics separately from the shared backbone and provides a lightweight signal for detecting whether client adaptation remains active. To further avoid repeated online probing over multiple candidate depths, we design a shallow sufficiency estimator that combines cross-client semantic alignment, temporal interface stability, and prompt-state variation to estimate whether the shallowest split is already sufficient. Finally, we introduce a split-compatible interface harmonization module that projects activations from different split depths into a shared semantic space, improving the comparability of heterogeneous client interfaces before server-side prediction. Extensive experiments on multiple heterogeneous benchmarks demonstrate the effectiveness of \textsc{FedSGA} in improving model performance compared with state-of-the-art methods while reducing unnecessary client-side computation. --- ### Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification Authors: Chunyu Qi, Zhuoran Song, Jian Weng, Haozhe Jiang, Xueyuan Liu, Naifeng Jing, Guanghui He, Xiaoyao Liang, Haibing Guan Published: 2026-08-16 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.15636v1 Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in the field of embodied AI, but their high computational cost and limited predicted action length hinder real-time deployment. Although Dadu-Corki, a dedicated accelerator for efficient embodied AI, has been introduced, it does not exploit the inherent interaction patterns between the robot and its environment, which results in a relatively short predicted action length. We observe that robotic environments naturally alternate between active states-where precise actions are crucial-and inactive states-where actions have limited impact on task success. This insight enables a new scheduling opportunity: long-action-length speculative prediction in inactive states, paired with selective verification in active states. We propose SpecVLA, an algorithm-system co-design framework that adaptively balances action length, inference latency, and task reliability. On the algorithm side, SpecVLA introduces a state-aware VLA inference execution paradigm and a hardware-friendly construction of a smaller verification model (sVLA) using differential residuals and block-wise mixed-precision quantization. On the system side, we develop a heterogeneous architecture consisting of a GPU and a robotic-specific hardware module, along with a speculative dataflow that decouples VLA and sVLA through parallel execution. Comprehensive evaluations on OpenVLA and RDT across LIBERO and ManiSkill benchmarks show that SpecVLA reduces end-to-end latency significantly while preserving task success rate. By enabling long-action-length speculative prediction with timely verification, SpecVLA achieves real-time robotic manipulation with both high efficiency and reliability. --- ### Argumentation for Common Ground: Finding Zones of Possible Agreement between Individuals in Conflict Authors: Elisa Cavatorta, Antonio Rago Published: 2026-08-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15634v1 How can common ground between societies in conflict be identified when citizens' acceptability of peace agreements is shaped by contested narratives? Such acceptability is mediated not only by the clauses that agreements include or exclude, but crucially by citizens' subjective reasoning concerning agreements' clauses. In this paper, we leverage computational argumentation to introduce a novel approach to identifying mutually acceptable agreements among individuals in conflict, i.e. a Zone of Possible Agreement (ZOPA). First, we introduce a quantitative bipolar argumentation framework tailored to represent each side's reasoning about peace agreements. We then show how merging these frameworks can enable negotiators to identify peace agreements that are mutually acceptable. To evaluate our approach under conditions of real-world relevance, we focus on the Palestinian-Israeli conflict, where long-standing policy, practitioner and public interest underscores the demand for methods capable of analysing polarised public reasoning. We show how our framework identifies a ZOPA through theoretical analysis and preliminary experiments using survey data from both existing work and retrieved by a large language model. The results illustrate how argumentation can empower negotiators and conflict-resolution teams in mapping feasible ZOPAs grounded in citizens' reasoning. --- ### Sparse Prototype Code Underlies Classification and Prediction Across Modalities Authors: Yehonatan Avidan, Daniel D. Lee, Haim Sompolinsky Published: 2026-08-16 Categories: cs.LG, cond-mat.dis-nn, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2608.15632v1 Neural representations have become a central tool for studying the internal mechanisms of modern AI models, yet their complex high-dimensional structure makes them difficult to interpret. We show that classification tasks give rise to a universal representational geometry, shared across state-of-the-art models in vision, audio, and language processing. The key structure is that within-class variability is not random in representation space. Instead, its classifier-relevant component has strong and structured correlations with the class's own centroid and with the centroids of its competing classes. Building on this observation, we derive an analytical mean-field theory governed mainly by the variability along true-class and rival-class centroid coordinates, together with a global renormalization of the class radius that compensates for the non-Gaussian statistics of real representations. The theory accurately predicts classification accuracy across architectures and modalities. The relevant geometric quantities improve systematically with model scale, mirroring the observed gains in accuracy. A striking feature of the theory is its sparsity: accurate prediction requires only a small set of centroid coordinates associated with the true class and its strongest rivals - connecting our framework to sparse-feature extraction approaches such as sparse autoencoders. Together, these results provide a parsimonious predictive theory of neural representations and suggest that classification in deep networks is governed by a sparse, centroid-aligned structure embedded within the full high-dimensional representation space. --- ### Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis Authors: Alona Strugatski, Licol Zeinfeld, Giora Alexandron Published: 2026-08-16 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.15630v1 The rapid development and growing deployment of large language models (LLMs) have made it increasingly important to understand their capabilities. A common approach is to evaluate LLMs using assessment instruments originally designed to measure skills and competencies in humans, such as standardized exams, and to use performance on these instruments as evidence for generalizable claims about LLMs' underlying abilities on the same skills the assessments are intended to measure in humans. However, from a validity perspective, such inferences require that the relationship between observed performance and underlying constructs established for humans also holds for LLMs. In particular, a necessary condition for transferring score interpretations is similarity in the latent structure of responses to the assessment. In this study, we examine whether this condition holds in two educational contexts: high-school chemistry and a quantitative reasoning section of a university entrance exam. Using a case study design, we compare human response data with responses generated by six multimodal LLMs. Our analytical approach combines exploratory factor analysis, factor congruence, and resampling to assess latent structure similarity across human learners and LLMs. Across both instruments, we find systematic differences between human and LLM factor structures, showing evidence that the analyzed assessments may not measure the same constructs for humans and LLMs. These findings call into question the validity of evaluation practices that use educational assessments to make claims about AI capabilities. --- ### In Defense of OCTA: The Reconstruction-Utility Gap in OCT-to-OCTA Synthesis Authors: Michael Chertok, Alon Tiosano, Orly Gal-Or, Lior Kramarski, Einav Baharav Shlezinger, Irit Bahar, Lior Wolf Published: 2026-08-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15626v1 Optical coherence tomography angiography (OCTA) images retinal blood flow, giving capillary-perfusion and foveal-avascular-zone biomarkers that grade diabetic-retinopathy ischemia. Because OCTA hardware is less common than structural OCT, recent work synthesizes it from OCT, reporting strong reconstruction (3D PSNR > 31 dB, SSIM > 0.9). We ask not whether the synthetic image looks similar, but whether it supports the measurements OCTA is acquired for. A frozen real-OCTA segmenter, applied as a probe to two synthesizers (XOCT, TransPro), shows downstream Dice falling with structural fineness: large vessels survive (0.862 -> 0.831) while the fine capillary network collapses (0.798 -> 0.635, five times the large-vessel loss; paired Wilcoxon p < 1e-3), TransPro worse throughout. A matched-blur control shows this detail is fabricated, not blurred. Retrained on a private Spectralis dataset, neither synthesizer reproduces the neovascular lesion (qualitative, n=3). Reconstruction fidelity is not clinical utility; we establish downstream-task fidelity as the evaluation OCT-to-OCTA synthesis needs. --- ### Rotation-Invariant Multi-IMU Activity Recognition under Independent Per-Location Orientation Shifts Authors: Seungyeol Baek, Yoonbyung Chai, Yonghyeon Lee, Sungjoon Choi, Sungho Suh Published: 2026-08-16 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.15621v1 Human Activity Recognition (HAR) with self-administered wearables, such as at-home rehabilitation and exercise monitoring, often requires reattaching inertial measurement units (IMUs) across sessions. In multi-IMU settings, this can induce independent orientation offsets across body locations, a deployment shift that conventional scalar HAR models do not structurally handle. Existing remedies rely on rotation augmentation, whose robustness depends on sampled transformations, or calibration and orientationnormalization pipelines requiring additional reference-frame assumptions or explicit procedures. We present Truly Rotation-Invariant HAR (TRI-HAR), a rotation-invariant framework that makes robustness to independent per-location IMU orientation offsets a structural model property. TRI-HAR reshapes accelerometer and gyroscope streams into triaxial vectors, applies a shared SO(3)-equivariant backbone and invariant projection to each IMU location, and fuses the resulting invariant features for activity classification. Across four multi-IMU benchmarks, TRI-HAR preserves macro-F1 under fixed independent per-location SO(3) rotations and outperforms rotation-augmented baselines under this target shift without requiring rotational augmentation. --- ### Bias-Corrected Ceilings of Emotion Predictability from Human Label Variation Based on Instance-Level Fano Bounds Authors: Keito Inoshita Published: 2026-08-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15619v1 Emotion recognition from text keeps improving on benchmarks, yet whether an accuracy ceiling has been reached is seldom asked with discipline. Our aim is not to pin this ceiling to a single number, but to quantify how far it depends on finite annotation, estimator choice, annotation noise, and the evaluation protocol, and thereby to discipline how confidently saturation can be claimed. We propose Bias-corrected Affective Ceiling Estimation (BACE), an analysis framework that estimates a bias-corrected ceiling, separates irreducible from reducible error, and disciplines the resulting claims. An anchored Dirichlet-mixture empirical Bayes estimator, bracketed between plug-in and NSB, recovers the human-consensus distribution; an annotator split, a noise deconvolution, and a fixed claim gate then attribute error without circularity. Methodologically, unconstrained point estimates place reachability anywhere from 0.38 to 1.03, so saturation cannot be decided by any single estimator. Substantively, the only assertion passing the claim gate is that at least about 33% of a representative classifier's error on GoEmotions is irreducible, with the same pattern recurring on offensiveness and irony. --- ### Benchmarking Quantum Machine Learning for Power-System Attack Detection: Evaluation Choices Decide the Outcome Before the Models Do Authors: Md Rezwanul Islam Published: 2026-08-16 Categories: cs.LG, cs.CR, quant-ph, stat.ML arXiv: https://arxiv.org/abs/2608.15617v1 Machine-learning detectors for power-system cyberattacks are themselves attack surfaces, and quantum machine learning has been proposed for them. We benchmark fidelity-kernel SVMs and variational classifiers against six tuned classical models on public power-system attack data (Mississippi State/ORNL), across white-box, transfer, decision-based black-box, and poisoning attacks. Our headline finding is methodological: the benchmark's answers are set by the evaluator's choices before the models. Eight choices -- six in the evaluation protocol, two in the tuning the benchmark itself runs -- each reversed or moved a conclusion at fixed models. The largest is the split: the row-level protocol scores 0.905 macro-F1 where holding whole source files out leaves 0.594, and in the capped matched-dimensionality regime the quantum arm sits within noise of chance with the classical arm 0.024 above it. A fidelity kernel looks most robust until attacked directly (retention 0.886 to 0.064); a mis-fitted surrogate manufactures a 10x asymmetry; an unseeded black-box attack moves 75% between restarts. A positive control explains the accuracy null: the labels, not the pipeline. We give the control that catches each choice and release the seeded benchmark. --- ### EgoGazeLite: On-Device Egocentric Gaze Prediction for Token-Efficient Multimodal LLM Video Input Authors: Matteo Stoiber, Niels Buus Lassen Published: 2026-08-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.15614v1 The use of multimodal LLMs (MLLMs) for egocentric video understanding with wearable devices is constrained by the token budget. Memory and compute cost scale with the number of visual tokens, and high-resolution video quickly becomes expensive to transmit and process at scale. Prior work (GazeLLM) addresses this by cropping the video around the camera wearer's gaze. This reduces the number of visual tokens by about tenfold while maintaining or improving the quality of full-resolution descriptions. However, this compression strategy depends on dedicated eye-tracking hardware, which is unavailable on consumer smart glasses. Building a software-only substitute poses a joint constraint: the predictor must be accurate enough to preserve downstream description quality, yet light enough to run on-device, within the power and compute budget of a smartphone. We address this with EgoGazeLite, a lightweight dual-process gaze predictor for egocentric video. Across two MLLMs, three automated metrics, and two LLM judges, predicted-gaze crops show no significant difference from ground-truth-gaze crops. Equivalence is confirmed in all ten cases. EgoGazeLite achieves this at 15.7M parameters, 6.71 GFLOPs, and runs the full gaze-and-crop pipeline end-to-end in real time (21.6 ms/frame) on consumer accelerator hardware. Together, these results remove the need for eye-tracking hardware for token-efficient, gaze-conditioned egocentric video understanding with MLLMs. --- ### AlloEgo-VLM: Disambiguating Allocentric and Egocentric Reference Frames in Vision-Language Models Authors: Kuan-Lin Chen, Tzu-Ti Wei, Chao-Chi Liao, Yu-Chee Tseng, Jen-Jee Chen Published: 2026-08-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15605v1 This study investigates the challenge of ambiguity faced by Vision-Language Models (VLMs) in understanding spatial semantics. Spatial cognition, shaped by cognitive psychology, spatial science, and cultural context, often assigns directionality to objects. However, natural language descriptions of spatial relations frequently omit explicit reference frames, leading to semantic ambiguity and potentially serious errors for embodied AI robots. Existing VLMs, due to insufficient training on reference frames and object orientations, often produce inconsistent responses. To address this issue, we construct a new dataset, AlloEgo-View, comprising (image, query, view-specific answer) triplets that capture key object relations from both allocentric and egocentric perspectives. The view-specific descriptions follow a structured spatial representation that annotate detailed scene descriptions, reference and target objects, their orientations, reference frames, and view types. Building on AlloEgo-View, we develop AlloEgo-VLM, a framework to disambiguate allocentric and egocentric reference frames, even under ambiguous queries, and to be easily integrated into existing VLMs via supervised fine-tuning. Furthermore, we deploy our framework onto an embodied robotic platform within NVIDIA Isaac Sim to validate its real-world feasibility in open-ended object searching tasks. Experiments highlight the limitations of current VLMs in handling view-specific queries and demonstrate the strong disambiguation ability of AlloEgo-VLM. --- ### FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy Authors: Qingyao Yang, Runming Yang, He Xiao, Wendong Xu, Junyu Chen, Haobo Liu, Chenchen Ding, Ruihan Hu, Yik-Chung Wu, Ngai Wong Published: 2026-08-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.15602v1 While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specialized hardware kernels, thus failing to unleash the full acceleration potential due to persistent reliance on expensive floating-point arithmetic or runtime dequantization overheads. To bridge this gap, we propose FluxBin (\textbf{F}lexible \textbf{L}UT-based \textbf{U}ltra-low-bit e\textbf{X}ecution with \textbf{Bin}ary bases), an algorithm-kernel co-design that synergizes post-training quantization with a highly optimized CUDA kernel. Algorithmically, we introduce Decoupled Row-Column Binary Decomposition to enhance representational capacity while maintaining hardware efficiency, complemented by a Hessian-guided saliency-aware hybrid bases that preserve critical information. At the kernel level, we implement a Lookup Table Building Approach with Scale Fusion to reduce floating-point arithmetic, featuring a Virtual Columnar Mapping that transforms irregular, sparse, and salient matrices into dense execution. Extensive evaluations demonstrate FluxBin achieves up to $5.92\times$ speedup and $10.19\times$ energy savings across diverse model architectures, delivering comparable accuracy to heavily fine-tuned methods. This effectively enables the deployment of 70B-scale models on one single A100 GPU with a $4\times$ memory reduction. Code is available at https://github.com/nicyyyy/FluxBin. --- ### Quantum Models with Multi-Stage Training for Compositional Concept Generalization Authors: Mina Abbaszadeh, Matilda Karabina Moore, Mehrnoosh Sadrzadeh, Martha Lewis Published: 2026-08-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15601v1 Compositional Concept Generalization (CoCoGen), the ability to systematically recombine learned primitives in novel contexts, is a key challenge for multimodal learning. In this work, we provide a solution using a compositional model of meaning that separates nouns from relations and uses tensors and variational quantum circuits to train them on data. This model enables us to employ a multi stage training paradigm, one that first learns object representations from single-object image-caption pairs, then subsequently transfers these to the relational stage where object parameters are frozen and optimisation is only applied to relational components. This design explicitly enforces compositional factorisation at the circuit, ensuring that relations are learned as transformations over stable primitives. The training paradigm is tested on the CLEVR dataset developed specificially for CoCoGen. For text, we work with vector representations of nouns and higher order tensor representations of relations using a set of different ansatz. For images, we work with quantum encodings of image embeddings dervied from Open AI's Vision Language tool CLIP and contrast amplitude encoding, which preserves the original embedding geometry, with angle encoding, which introduces nonlinear feature transformations. Our results show that multi-staged training combined with structured encodings significantly improves out of distribution relational generalisation, while using orders of magnitude fewer trainable parameters than classical baselines. We find that performance gains arise from the interaction between representation and encoding, with nonlinear quantum encodings enhancing the separability of compositional structure. These findings demonstrate that structured quantum representations and staged learning provide an effective framework for compositional generalisation in multimodal quantum machine learning. --- ### VARM-Bench: Benchmarking Verifiable Structured Reasoning in Chinese Abusive Speech Moderation Authors: Mingyu Yuan, Shengtao Wen, Lingbing Guo, Zhen Bi, Xiang Chen Published: 2026-08-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15600v1 The widespread circulation of abusive online content has increased the need for reliable moderation of Chinese social-media text. Existing Chinese benchmarks support label classification, fine-grained toxicity categorization, and target-aware extraction, but do not provide a unified representation for deterministically verifying the stated basis of a moderation decision. We introduce VARM-Bench, a benchmark for field-anchored chain-of-thought rationales in Chinese abusive-speech moderation. Each instance contains a concise natural-language rationale with explicit anchors for six decisions: target, target type, target explicitness, author stance, harmfulness label, and fine-grained category. Our deterministic protocol evaluates field correctness, target alignment, output validity, complete-record agreement, and hidden record errors conditioned on correct final decisions, without relying on an LLM judge. Under a common structured-output protocol, we evaluate language models across multiple model families using zero-shot prompting, taxonomy guidance, and structured CoT supervision, and analyze lexical-cue sensitivity and field-level errors. Results show that strong label-level performance can conceal substantial errors in complete moderation records. VARM-Bench provides an auditable and reproducible benchmark for evaluating verifiable moderation rationales in Chinese abusive-speech moderation. --- ### Underwater Color Restoration with Vanishing Uncertainty Authors: Grigory Solomatov, Derya Akkaynak Published: 2026-08-16 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.15598v1 Underwater color restoration promises to unlock color as a reliable signal for aquatic sciences, but achieving this with scientific confidence remains out of reach. Current methods are validated almost exclusively on an empirical basis, which provides confidence only to the extent that the vast diversity of possible visibility conditions is covered with end-to-end testing using a known ground truth. This is exacerbated by color restoration being a fatally ill-posed problem when considered in full mathematical generality, requiring additional constraints to narrow the solution to a finite uncertainty interval. The gap between which constraints suffice in theory and which constraints are satisfied by real-world data is poorly understood, making it unclear whether existing methods are solving a problem that is actually solvable. In this article, we investigate the theoretical side of this gap, identifying idealized conditions which guarantee bounded uncertainty that converges to zero as the spatial resolution of the camera increases. --- ### TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation Authors: Md Messal Monem Miah, Adrita Anika, Zhiyuan Yu, Ruihong Huang Published: 2026-08-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15594v2 Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently benign turns to bypass guardrails. Existing defenses lack the reasoning capacity to identify evolving manipulation patterns, often trading helpfulness for safety by over-refusing benign requests related to sensitive topics. We introduce Trace, a multi-turn defense with trajectory-aware structured reasoning. Before generating each response, the model identifies manipulation cues from the trajectory, evaluates both the benign and adversarial interpretations of user intent, assigns a jailbreak score, and commits to an action: Allow, Caution, or Decline. We curate 4k multi-turn adversarial conversations from five attack frameworks, pair them with 2.4k benign dialogs, and 600 sensitive-but-benign conversations. We train Llama-3.1-8B-Instruct with SFT and GRPO under a multi-component reward that jointly optimizes helpfulness on benign prompts and robustness against jailbreak attempts. Across seven multi-turn attack benchmarks, Trace attains an average attack success rate (ASR) of 14.5% against 31.4% for the strongest baseline and 74.9% for the undefended target, while significantly raising the attacker effort required per successful jailbreak. Trace also balances usability and safety, achieving a 93.3% average compliance on over-refusal benchmarks. --- ### When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction Authors: Feiyang Ren, Shengtao Wen, Lingbing Guo, Yu Tian, Yuanning Cui, Xiang Chen Published: 2026-08-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15592v2 Efficient LLM serving is often bottlenecked by the need to pad sequences to a fixed maximum length, and this wastes compute and degrades throughput. Predicting output lengths in advance makes it possible to adopt length-aware scheduling, and this reduces the overhead. This advantage is especially pronounced in long-context reasoning and reinforcement learning applications. Existing approaches, such as entropy-guided token pooling, use token-wise entropy as their primary signal, but they tend to ignore differences in semantic content across tokens. So, important tokens are often underweighted, and tokens carrying little information receive disproportionate emphasis. This hurts the reliability of length prediction. We introduce ESTP (Entropy-and-Semantic Token Pooling), a lightweight framework that addresses this issue by combining entropy with attention-based importance scores. These scores are derived directly from the self-attention weights computed during the LLM prefill phase, and this allows ESTP to capture both uncertainty and semantic importance with minimal additional computation. Since the framework reuses prefill activations, it adds almost no extra memory overhead and introduces only minimal latency. On the ForeLen benchmark, ESTP outperforms baseline methods, achieves better prediction accuracy and lower error rates in most scenarios. When integrated with a length-aware scheduler in end-to-end system tests, it further helps improve overall throughput and reduce the padding ratio. Our results offer a practical and effective building block for length-aware LLM serving systems. --- ### Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback Authors: Pouya Ghiasnezhad Omran, Michael Zimmermann, Duncan Cambridge, Ashmita Kapoor, Tanya Dixit Published: 2026-08-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15591v1 Large Language Model (LLM) agents deployed in production environments face a fundamental tension: the agent's behavior is frozen at deployment time, while the business rules and edge cases it must handle continue to evolve. Existing approaches address agent construction and one-time evaluation but provide no structured mechanism for continuous post-deployment behavioral correction without modifying the agent's source code. Most of the approaches offered in the market, require intense collection of logs and traces, and re-examining the agent design by the engineering team, a process which is heavy, long and negates the economical value of agentic transformation. We introduce Agent Gym, a modular, domain-agnostic framework that wraps any existing LLM-based agent in a continuous evaluation-and-evolution loop. The framework provides six composable capabilities --- Act, Evaluate, Investigate, Correct, Learn, and Observe --- organized across three architectural zones: a constitution layer that codifies domain knowledge in configuration artifacts, a runtime inference pipeline that chains acting, investigation, and adaptive correction, and a learning loop that enables subject matter experts to discover and validate new correction rules through natural language interaction. The key technical contributions include a hybrid deterministic-LLM correction engine with 21 condition operators and three-tier actions, a three-layer investigation architecture for ground-truth-free compliance validation, and a programmatic safety loop that guarantees rule correctness before human approval. We further introduce the Spec-to-Note Gap, an autoencoder-inspired view of agentic system transparency. An open-source reference implementation for invoice processing demonstrates that the framework is fully operational and ready for adoption. --- ### GraniKV: Asymmetric Granularity KV-Cache Paging for Multi-Agent Systems with Long Shared Prefix Authors: Jinhyun Jeon, Sungjoo Yoo Published: 2026-08-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.15584v2 Production paged-serving engines apply uniform paging granularity to the KV cache, even though the two regions of a multi-agent workload have opposite storage requirements: a long shared prefix demands contiguity, while the per-request suffix demands fine-grained allocation. We present \textbf{GraniKV}, a KV-cache layer that allocates the shared prefix in a contiguous HOT pool and the suffix in a token-level COLD pool, combined with a per-step dispatcher which selects the appropriate backend among dual backends for each regime (compute-, memory-, or communication-bound). To the best of our knowledge, GraniKV is the first system to apply asymmetric paging granularity to the KV cache of a production paged-serving engine. At $L_p{=}16$\,K shared tokens GraniKV reaches $\mathbf{2.16\times}$, $\mathbf{1.98\times}$, and $\mathbf{1.57\times}$ output-token throughput over the production baseline on Llama-3.1-8B/TP=1, Qwen-2.5-14B/TP=2, and Qwen-2.5-32B/TP=4. The gain decomposes: cascade attention integration contributes the majority at saturation; the asymmetric storage layer adds $1.05$--$1.15\times$ end-to-end while being what makes the batched-GEMM prefix backend possible at all. Under heterogeneous multi-agent serving with \emph{distinct} prompts of different lengths, the attribution inverts: GraniKV sustains $\mathbf{1.95\times}$ while batch-global cascade collapses to parity --- the storage layer alone carries the win in the regime that motivates the paper. --- ### PoseAdapter: Dual-Stream 2.5D Controllable Image Generation for Complex Multi-Object Scenes Authors: Yufeng Chi, Huimin Ma, Fan Gao, Zhice Niu, Keqin Li, Jianmin Li Published: 2026-08-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15583v1 While Text-to-Image (T2I) diffusion models have achieved remarkable success, precise spatial and orientational control in multi-object scenes remains a persistent challenge. Existing methods either rely on computationally expensive dense 3D maps or suffer from severe attribute leakage and "cut-and-paste" artifacts. To address these limitations, we propose PoseAdapter, a lightweight framework for high-fidelity 2.5D controllable image generation. Instead of dense spatial maps, it establishes precise spatial-angular anchors using an efficient condition layout: individual object captions, 2D bounding boxes, and 3D angles. To resolve the generative trade-off between strict instance isolation and global coherence, we introduce a Context-Aware Dual-Stream Representation. By injecting local object tokens and relation-enriched scene tokens into the visual stream of modern MM-DiT architectures via parallel masked and unmasked pathways, PoseAdapter eliminates attribute leakage while preserving natural inter-object relationships and scene-level coherence. To support this paradigm, we construct OrientLayout, a high-quality dataset featuring standardized 2.5D annotations and instance-level decoupled semantics. Extensive experiments demonstrate that PoseAdapter outperforms state-of-the-art baselines in spatial accuracy, orientational precision, and multi-object visual fidelity. Code and dataset will be available at https://github.com/cyf23/PoseAdapter. --- ### From Generalist to Specialist: A Context-Fusion Framework for Endoscopic Polyp Reporting with a Frozen VLM Authors: Ruijie Yang, Yan Zhu, Peiyao Fu, Siyuan Li, Te Luo, Zhihua Wang, Quanlin Li, Pinghong Zhou, Xian Yang, Shuo Wang Published: 2026-08-16 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.15580v1 Reliable endoscopic polyp reporting requires integrating quantitative lesion sizing, standardized Paris classification, and clinically meaningful morphological description within a single record. General-purpose vision-language models (VLMs) offer a unified interface for image understanding and report generation. Existing specialization strategies, however, typically rely on task-specific models or model-weight adaptation, leaving unresolved how to introduce reliable specialist knowledge while preserving both this unified interface and the VLM's pretrained capabilities. We introduce a context-fusion framework that specializes a frozen general-purpose VLM through both implicit instruction context and explicit transduction context without modifying its pretrained weights. Specifically, a self-supervised polyp encoder retrieves related image-report pairs as explicit, query-specific evidence, while learned continuous specialist tokens provide implicit instruction context shared across cases. Experiments were conducted on 2,056 expert-annotated public endoscopic images. We compared the framework with general-purpose VLMs, task-specific predictors, and weight-adaptation methods to assess specialist performance, unified reporting, and adaptation efficiency. Across numerical, categorical, and report-generation metrics, the proposed framework substantially improved direct frozen-VLM inference and achieved the strongest overall performance among the evaluated methods. It added trainable parameters equal to only 0.006% of the frozen VLM's parameter count. When the top-1 retrieved case carried the correct target category, our framework corrected 70.5% of the errors made by a weight-adaptation baseline. These findings support the context-fusion framework as a lightweight and effective strategy for specialist adaptation of a frozen VLM. --- ### Kozuchi Agent: A Language-Agnostic Open-Weight Agent for Software Repair Authors: Mehdi Bahrami, Kosaku Kimura, Satoshi Munakata, Satoshi Nakashima, Yu Ishikawa, Kosuke Maeda, Nao Soma, Kenichi Kobayashi, Keisuke Miyazaki, Keizo Kato, Shigeki Fukuta, Tatsuo Kumano et al. Published: 2026-08-16 Categories: cs.SE, cs.AI, cs.ET, cs.PL arXiv: https://arxiv.org/abs/2608.15579v1 Industrial software-engineering teams increasingly need LLM agents that turn bug reports into correct patches, yet benchmark-scale operation adds long horizons, tool-use discipline, context persistence, heterogeneous clusters, and evaluation reuse. We present Kozuchi Agent, a language-agnostic open-weight repair agent and CI-operated evaluation pipeline. Explicit phases, persistent state, deterministic tools, a model-independent action interface, and cross-agent test-time selection make runs auditable and repeatable. With locally hosted Qwen3.5-27B, no fine-tuning, and TTS@8, Kozuchi resolves 374/500 SWE-bench Verified instances on the official evaluator. Unchanged on Multi-SWE-bench Java, the same 27-billion-parameter agent resolves 41/128 instances (32.03%), ranking first among strict open-weight submissions and fourth of 42 overall; on Python it ranks 12th of 135 and first among open-weight systems. Per-phase behavior remains within +/-5 percentage points across languages. Remaining failures mainly reflect semantic correctness, Java-specific harness issues, and selection errors. Across both tracks, results compare favorably with open/local peers by parameter count. Analysis of candidate diversity, selector regret, and patch reliability shows that the remaining gap is primarily semantic correctness and selection rather than edit formatting or proprietary-model access. Operationally, reusable CI stages reduce operator touch-points from five to one across heterogeneous internal clusters. --- ### ARENA: Automated Red-Teaming for Large Audio Language Models Authors: Jiaming He, Zhicong Huang, Tian Jin, Zhen Sun, Cheng Hong, Yi Yu, Wenbo Jiang, Xudong Jiang Published: 2026-08-16 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2608.15578v1 Large audio-language models (LALMs) make it possible to interact with language models through speech, music, and environmental sound, but they also introduce a safety surface that is difficult to expose with text-only red-teaming. We study automated audio-grounded red-teaming, where a text query must remain safe in isolation while the joint text-audio input induces harmful target behavior. We propose ARENA, a closed-loop framework that trains a controller on an independent 2,000case text-audio dataset. MD-Judge supplies training rewards and adaptive search feedback, while a separate, non-adaptive Llama Guard 3 evaluator alone labels final outcomes. On 520 held-out AdvBench objectives, ARENA achieves FDR/PSR of 87.9/100.0%, 71.5/96.3%, 68.1/100.0%, and 75.4/98.5% on Audio Flamingo 3, Qwen2-Audio, MiMo-Audio, and GPTAudio, respectively. Ablations show that feedback-based refinement and audio-variant search substantially improve attack discovery. --- ### Catching Hallucinated Citations in Video-LLM Question Answering: A Self-Verification Pipeline and Verifier Ablation Study Authors: Yogesh Kumar Published: 2026-08-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.15574v1 Video question answering systems built on vision-language models often produce timestamped claims with high confidence even when unsupported by the cited frame. This deceptive hallucination arises because timestamps imply grounding without ensuring correctness, increasing user trust but not accuracy. We introduce a pipeline that closes this loop. A retrieval-augmented language model drafts answers with per-claim timestamp citations, and each cited frame is independently re-examined before being shown to the user. We compare against a plain baseline and ablate three verification designs, evaluated on both Apple Silicon (MLX) and Google Colab (HF Transformers, CUDA). Directly asking the vision model whether a frame supports a claim fails completely (0% catch rate on 40 claims) due to sycophancy. Blind re-captioning plus a general LLM judge improves results but is unstable, oscillating between 0% and 100% flagged depending on prompt phrasing. Replacing that judge with a small natural language inference model yields a stable, interpretable verifier that catches 79% of fabricated claims on adversarial false-premise questions while leaving true claims untouched. We release the full pipeline, evaluation harness, and implementations for both Apple Silicon and Colab. Code is available at https://github.com/yogesh-iitj/grounded-video-qa. --- ### SchurQuant: Groupwise Discrete Optimization for Layer-Wise LLM Quantization Authors: Gunjun Lee, Sehwan Son, Younjoo Lee, Byungjun Kim, Jung Ho Ahn Published: 2026-08-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.15567v1 Weight-only post-training quantization (PTQ) enables the deployment of large language models under tight memory budgets, but accuracy often collapses at 2-3 bits. Existing backpropagation-free PTQ optimizers have two limitations: group decisions ignore the correction that the remaining continuous suffix can absorb, and discrete refinements typically keep the affine quantization grid fixed. We introduce SCHUROPT, which analytically eliminates the suffix's optimal continuous response, yielding an exact groupwise quadratic with Schur-complement curvature. It then alternates closed-form row-wise scale/zero-point refitting with coordinate descent over integer codes. With the GPTQ objective fixed, SCHUROPT improves mean zero-shot accuracy on 2-bit Qwen3-4B by 11.88 percentage points (pp). At higher precision, however, tighter reconstruction does not consistently improve end-model metrics. SCHURQUANT therefore combines SCHUROPT with quantized-prefix teacher reconstruction, reference-weight regularization, residual-add targets, and teacher-decision token weighting. Across eight Llama and Qwen models, SCHURQUANT achieves the highest mean zero-shot accuracy among the evaluated backpropagation free PTQ baselines, outperforming the strongest baseline by 9.65 pp at 2 bits. --- ### Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling Authors: Junbo Jacob Lian, Huiling Chen, Hanzhang Qin, Chung-Piaw Teo Published: 2026-08-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.15565v5 Agents that learn from experience improve at optimization modeling by storing solved trajectories and reusing them as skills. A wrong trajectory that enters the library can be retrieved again and again, and on a stream of new problems there is no ground-truth answer to decide with. Existing learners admit trajectories by matching known optima or labels, and label-free substitutes such as execution success or agreement at one instance can admit wrong models. We introduce ADMITOR, a label-free admission gate. It generates models from three model families, runs each on the stated problem and on instances with resampled parameters, keeps the largest group of models whose optimal values agree on every instance across families, and applies a threshold fitted on solver-verified problems to accept, abstain, or escalate, with a finite-sample bound on the false-discovery rate among accepted values. Inside a state-of-the-art skill learner, ADMITOR raises candidate-level admission precision to 0.927, against 0.871 for majority vote over the host's own samples and 0.726 for execution success, and its library, the smallest of the four, reaches the highest macro accuracy over five public benchmarks, 58.4 against 54.8 for majority vote. An ablation on the same records shows that the gain comes from the accepted value being external to the learner and unanimous across families; on this stream, resampling never changed an accepted value and only reduced coverage. The false-discovery bound holds on the calibration set but not on the benchmark stream: an audit of every false certificate traces most of them to benchmark texts that omit or round the numbers needed to reproduce the labeled answer, and a label-free check of the extracted numbers against the text flags most of these cases. --- ### Amortised Post-Hoc Explanation with Exact Preservation for Dynamic Graph Anomaly Detectors Authors: Iyad Assaad Nekka, Hamida Seba, Walid Khaled Hidouci, Karima Amrouche Published: 2026-08-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.15559v1 Anomaly detection in dynamic graphs underpins financial fraud analysis, intrusion detection, and platform integrity, where automated decisions require human-interpretable justifications. StrGNN, the strongest performer in recent benchmarks, produces no explanation: when an edge is flagged, the analyst receives only a score. Explanation metrics are undefined for StrGNN because no attribution vector exists. This paper closes that gap. We present X-StrGNN, a post-hoc explanation layer that wraps a trained, frozen StrGNN and emits, for every flagged edge, dual attributions: a structural attribution identifying which contextual interactions in the enclosing subgraph drove the decision, and a temporal attribution identifying which historical snapshot carried the signal. Both attributions are multiplicative masks identically one in the unexplained pass, so the layer is an exact pass-through: detection is preserved to machine precision, verified rather than asserted (Delta AUC = 0.0000, Delta AP = 0.0000, Delta P@100 = 0.0000). Attribution costs 0.66 ms per edge, making explanation of an entire alarm list feasible. We conduct the first controlled design study of attribution strategies for this architecture, comparing gradient attribution, per-instance mask optimisation, and amortised parameterisation under one protocol, one budget, and three seeds. X-StrGNN attains the highest stability (0.913) at 268x lower cost than per-instance optimisation, and its temporal attribution (1.601 against a measured random floor of 0.973) is separably better than its ablated control, while per-instance optimisation - the most expensive strategy - falls below that floor. Code, protocol, and per-seed measurements are released. --- ### A Counterexample to the Tang Zhang Schatten Norm Conjecture and Sharp Positive Results Authors: Zijian Zeng, Houde Liu, Kurunathan Ratnavelu Published: 2026-08-16 Categories: math.CO, cs.LG, math.FA arXiv: https://arxiv.org/abs/2608.15558v1 For $m\geq 2$, let $c_p(m)$ be the all-dimensional best constant in $$ \left\|\sum_{k=1}^m A_k\right\|_p \leq c_p(m)\left\|\sum_{k=1}^m |A_k|\right\|_p. $$ Tang and Zhang conjectured an explicit formula for every finite $p>1$. We disprove the conjecture with two explicit real $2\times 2$ rank-one matrices at $p=3/2$. The comparison is certified by seven strict rational inequalities and, in particular, places the attained ratio above $207/200$, while the conjectured constant lies below $207/200$. On the positive side, we prove the conjectured sharp bound for every family of rank-at-most-one summands when $2\leq p<\infty$, and classify all equality cases. We also prove the corresponding endpoint statement for $p=\infty$. Finally, for arbitrary complex matrices, we establish the conjectured sharp constant in the case $m=2$, $p=4$. --- ### RigidBench: Evaluating Rigid-Body Physics in Video Generation Models Authors: Swarnim Jain, Shangzhe Wu Published: 2026-08-16 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.15555v1 Video models are increasingly used to predict what happens next in a scene, yet the metrics commonly used to compare their outputs say little about whether the predicted objects move correctly. Motion, geometry, identity, background stability, and visual similarity can fail independently, but whole-frame scores often mix these errors together. We introduce RigidBench, a simulator-grounded benchmark that compares a generated continuation with a reference rollout from the same initial frame and motion description. Its five rigid-body tasks vary objects, materials, viewpoints, and indoor and outdoor scenes, with per-frame masks, depth, 6-DoF trajectories, and contacts available for scoring. We evaluate eight models on the same 100 examples with ten measurements that keep these aspects separate. The resulting rankings depend strongly on what is measured: no model leads on all ten, and across model means, higher SSIM accompanies larger 3D trajectory error (r = 0.89). RigidBench also includes 5,000 training videos with exact simulator state, which we use to fine-tune and analyze Wan 2.2 TI2V-5B. Full fine-tuning reduces 3D trajectory error by about 20% with almost no change in SSIM, while teacher-forced probes and targeted interventions show that object position is represented throughout Wan's diffusion transformer and used by its denoising computation. --- ### MistyPilot: Enabling Social-Robot Control through Multi-Agent LLM Skill Orchestration Authors: Xiao Wang, Lu Dong, Ifeoma Nwogu, Srirangaraj Setlur, Venu Govindaraju Published: 2026-08-16 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.15549v1 Programming small social robots from natural-language instructions requires more than invoking isolated APIs. Interactive tasks combine reactive physical behaviors with stateful social behaviors, while existing interfaces often require developers to manually compose APIs into skills, configure their parameters, bind sensor events to skills, and manage task states at runtime. We present MistyPilot, a multi-agent LLM framework that interprets high-level natural-language instructions and orchestrates the corresponding skills on the Misty social robot. A Task Router dispatches each instruction to one of two specialized agents: a Physically Interactive Agent for sensor-triggered robot control and direct skill invocation, and a Social Interaction Agent for dialogue-oriented task-state management and context-dependent multimodal response generation. To improve efficiency, the Social Interaction Agent reuses previously generated results when applicable and invokes full generation otherwise. We evaluate MistyPilot on five component-level suites, with sensor bindings and skill invocations executed on the physical Misty robot, and a preliminary user study with 12 participants. MistyPilot attains high accuracy on routing, sensor-skill binding, task-state parsing, result reuse, and skill extension up to 100 skills, and lower variance than an otherwise identical single-agent baseline, while participants report positive perceptions of usability and interaction quality. The code will be made publicly available via the project page. --- ### Spectral Saliency for Machine Unlearning Authors: Cedar Site Bai, Amber Yijia Zheng, Raymond A. Yeh, Brian Bullins Published: 2026-08-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.15548v2 Machine unlearning (MU) aims to remove the influence of specific training data while preserving model utility. As the name suggests, MU can be viewed as the inverse of learning, using gradient-based updates to reduce the influence of a forget-set by counteracting the previously learned behavior. Recently, Muon, a gradient descent variant, has been introduced. Muon applies spectral magnitude normalization to encourage exploration of rare directions and demonstrates promising performance. Inspired by Muon, we adopt the spectral view for unlearning and propose Spectral Saliency Unlearning (SSU). SSU thresholds weak singular components and updates only those directions supported by a confident unlearning signal. We further provide theoretical justification for this thresholding approach from the perspective of the forgetting-retention trade-off. Experiments across image classifiers, diffusion models, and LLMs demonstrate SSU's effectiveness. --- ### BengaliMCQ: Automatic Generation and Answer Prediction of Academic Multiple-Choice Questions in a Low-Resource Language Authors: Abu Tarabin Surzo, A. K. M. Nihalul Kabir, Sm Azmain Faysal, Ariana Haque Ami, Lawrence Amlan Gomes, Farig Sadeque Published: 2026-08-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.15547v1 Traditional retrieval-augmented generation (RAG) frameworks process documents without attending to their hierarchical structure, leading to poor performance, especially in low-resource languages such as Bengali. To address this, we propose a structure-aware RAG framework that models Bengali textbooks as hierarchical graphs and uses a contrastively trained graph neural network to retrieve a small set of relevant passages. These passages provide focused context for a large language model, enabling topic-specific multiple-choice question (MCQ) generation and in-domain answer prediction. Experimental results demonstrate that our framework outperforms strong dense retrieval baselines across retrieval metrics, produces more relevant MCQs, and achieves superior answer prediction accuracy. --- ### ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search Authors: Danial Yazdani, Mohammad Nabi Omidvar, Yuan Sun, Maksud Ibrahimov, Xiaodong Li Published: 2026-08-16 Categories: cs.AI, cs.NE arXiv: https://arxiv.org/abs/2608.15546v2 Most LLM-based automated algorithm design methods optimize a designated component within a human-specified scaffold, fixing overall organization and component interactions. We present ATLAS, an embedding-guided quality-diversity framework for scaffold-free full-algorithm synthesis in combinatorial optimization. The problem specification supplies objectives and constraints; a minimal I/O interface fixes only instance and solution formats; the LLM chooses and restructures components, interactions, and control flow. This freedom enlarges the search space, risking invalid candidates and premature convergence to one design region. ATLAS independently detects execution, interface, and feasibility failures, recomputes objectives, and applies error-conditioned repair; similarity-based archive management preserves algorithms across embedding-space regions to counter premature convergence. Its three-layer search refines the best design, gives other regions dedicated refinement opportunities, and performs cross-region synthesis to recombine components and their interactions. Across four NP-hard problems, ATLAS outperforms several state-of-the-art component-synthesis methods and a matched full-synthesis baseline while remaining competitive with strong human-designed algorithms. One ATLAS run retains several algorithms with comparable performance from distinct embedding-space regions rather than a single design. Code inspection finds that these multi-component designs differ in their primary construction or global-search backbone. Our results suggest that embedding-guided quality-diversity search can make the enlarged full-algorithm design space practically searchable. Source code and exact executable prompts are available at https://github.com/Danial-Yazdani/ATLAS . --- ### CrossView: Can Vision-Language Models Reason Across Cameras? Authors: Sahil Shah, S P Sharan, Harsh Goel, Manvik Pasula, Adithya Hebbalae, Minkyu Choi, Sandeep P. Chinchali Published: 2026-08-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.15539v1 Video understanding benchmarks have long centered on single-camera settings, where modern multi-modal language models achieve strong performance across image and video tasks. Yet, the real world runs on multi-camera networks: autonomous vehicles, security systems, and robots all gather data across many simultaneous views. We argue that this is not simply "more" of the single-camera problem; it is fundamentally different. Multi-camera reasoning requires handling context that scales with the number of views, resolving occlusions visible from only a subset of cameras, judging which views matter, and integrating evidence across perspectives that may overlap or diverge. Current models struggle with exactly these challenges, yet no benchmark systematically targets them. We introduce CrossView, a multi-camera video question-answering benchmark spanning autonomous driving, security surveillance, egocentric/exocentric video, and robotics. Evaluation of proprietary models, such as GPT-5.2, and open-source models, like Qwen3-VL, reveals consistently low accuracy, with open-source models trailing by a wide margin. Performance scales strongly with a model's ability to jointly process multiple viewpoints, positioning CrossView as a rigorous benchmark for multi-camera video. We open-source our code and dataset at https://utaustin-swarmlab.github.io/CrossView. --- ### EA-LiteUNet: An Edge-Adaptive and Resource-Efficient U-Net for Boundary-Sensitive Dermoscopic Image Segmentation Authors: Wang Jiangtao, Nur Intan Raihana Ruhaiyem, Fu Panpan, Yang Yu, Huang Yan Published: 2026-08-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.15537v1 Accurate boundary delineation remains a persistent challenge in dermoscopic image segmentation because of blurred lesion margins, heterogeneous textures, and complex background artifacts. From a signal-processing perspective, lesion boundaries represent high-frequency components that are highly susceptible to aliasing, noise amplification, and information loss. Consequently, repeated downsampling and feature transformations in conventional convolutional architectures often lead to severely degraded boundary representations. To address these limitations, we propose EA-LiteUNet, an edge-adaptive and computationally efficient U-Net variant specifically designed for boundary-sensitive medical image segmentation. The architecture integrates three core mechanisms: (1) boundary-aware representation learning to suppress aliasing and preserve high-frequency structural details; (2) attention-guided feature modulation to selectively enhance boundary-relevant responses across multi-scale features; and (3) a resource-adaptive inference strategy to dynamically balance segmentation accuracy and computational efficiency. Extensive evaluations across three public dermoscopic datasets demonstrate that EA-LiteUNet consistently achieves superior boundary precision. Specifically, on the ISIC 2018 dataset, the method significantly reduces the 95% Hausdorff Distance (HD95) to 12.89 pixels while maintaining a robust Dice score of 92.08%. Notably, this strong performance is achieved with an ultralightweight configuration of merely 0.29M parameters and 1.17 GFLOPs. Ablation studies further validate the complementary effects of these components, confirming their contribution to enhanced boundary fidelity and stable optimization. ---