# Research Papers — 2026-05 · bundle page 64 of 326

> Full-text markdown of papers #3151–3200 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-05/page/64
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/63.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/65.md)

### AgensFlow: A Coordination-Policy Substrate for Multi-Agent Systems

Authors: Nicole Koenigstein
Published: 2026-05-26
Categories: cs.MA, cs.AI, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2605.27466v1

Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how roles should interact, when to use retrieval or verification, and when to omit a step entirely. These choices interact with task regime and operational constraints, so static pipelines and one-off model comparisons provide only a limited view of the design space. This paper introduces AgensFlow, an open-source framework that treats multi-agent coordination as an online policy-learning problem under partial observability. The framework makes coordination decisions observable and learnable from repeated trajectories, rather than treating skill, role, model, topology, and evaluation choices as fixed pipeline design. AgensFlow is evaluated on two corpora: distributed-systems incident tasks and security-advisory tasks. The evaluation shows three main results: learned routing reaches a higher-quality operating point than a fixed pipeline baseline on coordination-heavy classes; skip:X isolates topology compression as a meaningful part of the substrate; and warm-started policy graphs can reduce exploration cost while preserving plateau quality. Overall, the results support that learned, auditable routing can improve coordination-heavy multi-agent workflows over static wiring.

---

### AdaMerge: Salience-Aware Adaptive Token Merging for Training-Free Acceleration of Vision Transformers

Authors: Semi Lee, Hyejin Go, Hyesong Choi
Published: 2026-05-26
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.27465v1

The quadratic cost of self-attention in Vision Transformers (ViTs) constitutes a fundamental bottleneck for practical deployment, motivating a vibrant line of research on token reduction. Among existing approaches, token merging (ToMe) has emerged as an elegant training-free solution; yet its design rests on an unspoken premise of token equality, which contravenes the well-documented non-uniformity of self-attention and leads to information loss in high-salience tokens under aggressive compression. We address this limitation with AdaMerge, a token-merging framework based on two complementary mechanisms. First, salience-weighted similarity leverages column-wise feature-affinity centrality as a token-importance proxy and incorporates the resulting salience scores into the bipartite matching score, ensuring that pivotal tokens contribute more strongly to the merged representation. Second, adaptive merging intensity uses pre-computed layer-wise similarity statistics to dynamically modulate the per-layer reduction count in accordance with input-specific redundancy. On ImageNet-1k with ViT-B/16, AdaMerge consistently outperforms ToMe, PiToMe, and DSM across all FLOPs-matched regimes. The accuracy gap widens monotonically with compression: at the 13.4G FLOPs operating point, AdaMerge sustains a Top-1 degradation of only -1.06%, compared to -1.45% for PiToMe and -4.62% for DSM. To our knowledge, AdaMerge is the first to combine salience-weighted similarity and adaptive per-layer reduction into a single training-free token merging framework, advancing the accuracy-FLOPs Pareto frontier of ViT acceleration.

---

### Beyond Motion Primitives: Behavioral Activity Recognition from Head-Mounted IMU

Authors: Chung-Ta Huang, Leopold Das, Jeffrey Zhou, Faizaan Siddique, Julia Seungjoo Baek, Serena Liu, Andrew Rusli, Todd Y. Zhou, Freddy Yu, Sinclair Hansen, Ziling Hu, Arnav Sharma et al.
Published: 2026-05-26
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.27464v1

AR smart glasses need continuous behavioral context to offer proactive assistance, yet their most practical always-on sensor, the head-mounted Inertial Measurement Unit (IMU), detects only motion primitives such as walking or standing. We push beyond motion primitives to behavioral-level recognition, defining five categories that balance AR application need with sensor observability. To this end, we construct a 160K-sample Ego4D dataset with a four-tier quality assurance framework spanning 8 activity scenarios, and propose HiT-HAR, a 703K-parameter hierarchical model that outperforms prior head-mounted IMU models on five-class action and eight-class scenario recognition. We further map the observability frontier of head-mounted IMU through per-class separability analysis, identifying which behavioral categories are reliably observable (Locomotion), which benefit from temporal context (Object Transfer, Task Operation), and where scenario-dependent signal overlap poses remaining challenges. Our results indicate that architectural choices exploiting temporal context and scenario structure outperform simply scaling model size. The code and dataset are publicly available at https://github.com/Harvard-AI-and-Robotics-Lab/HiT-HAR.

---

### When prompt perturbations break your A/B test: A valid statistical test for generative surveying

Authors: Hayden Helm, Carey Priebe
Published: 2026-05-26
Categories: stat.ME, cs.AI, stat.AP
arXiv: https://arxiv.org/abs/2605.27463v1

Generative surveying -- where collections of LLM-based personas provide feedback on messages -- has emerged as a cheap and scalable alternative to traditional market research. However, LLMs are sensitive to small variations in prompt design and conclusions drawn from generative surveys may depend on arbitrary phrasing choices. Controlling for this sensitivity requires including semantically equivalent perturbations in the analysis. In this paper, we show that standard hypothesis tests, including the sign test and Wilcoxon signed-rank test, are invalid under a statistical model for generative surveying that includes realistic perturbation structure. We propose a permutation test that is valid under this model and formally characterize the conditions under which standard tests fail. Applying our framework to a simple generative surveying problem, we estimate relevant parameters, characterize the power of the permutation test under realistic conditions, and provide practical guidance on budget allocation across personas, perturbations, and replicates. Finally, we show that both the magnitude and direction of the estimated effect are sensitive to the choice of model, even within the same model family.

---

### G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing

Authors: Bharath Raj Nagoor Kani, Noah Snavely
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.27372v1

Modern feed-forward 3D reconstruction methods like VGGT predict pixel-aligned pointmaps in camera-centric coordinate frames. However, this choice of coordinate frame is not always optimal. We propose instead to predict pointmaps in upright, gravity-aligned frames that exploit strong structural cues present in many real-world scenes. Unlike camera-centric frames, gravity-aligned frames share a common vertical axis across viewpoints, reducing the rotational degrees of freedom needed to relate pointmaps to one another. To this end, we introduce the Gravity Grounded Geometry Transformer (G3T), fine-tuned from existing models on gravity-aligned 3D data. G3T produces highly accurate gravity-aware predictions, including upright pointmaps and camera-to-gravity poses. We further introduce G3T-Long, a submap-based incremental 3D reconstruction pipeline that leverages the reduced rotational degrees of freedom afforded by upright frames to achieve significantly improved reconstruction accuracy.

---

### Algorithmic Monocultures in Hiring

Authors: Rishi Bommasani, Sarah H. Bana, Kathleen A. Creel, Dan Jurafsky, Percy Liang
Published: 2026-05-26
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2605.27371v1

Many employers screen job applicants with algorithms built by the same few algorithm vendors. We hypothesize that algorithmic monoculture leads to the same individuals and members of the same racial groups facing rejection. We acquire and analyze a novel dataset of 3 million applicants submitting 4 million applications where all the applications are screened by algorithms built by the same vendor. We find clear racial disparities in applicant outcomes. Of all applications submitted by Asian and Black applicants, 14.74% and 25.87% are submitted to positions that adversely impact Asian and Black applicants, respectively, according to U.S. employment discrimination standards. Individuals also receive homogeneous outcomes: 4% of all applicants who apply to 10 positions are recommended for rejection from all positions, a rate higher than expected by chance. To better understand this homogeneity, we leverage the deterministic replicability of hiring algorithms to generate the outcomes applicants would have received if they applied to all positions. We show that applicants would need to apply widely in order to ensure their applications are considered by a human

---

### SpatialBench: Is Your Spatial Foundation Model an All-Round Player?

Authors: Haosong Peng, Hao Li, Jiaqi Chen, Yuhao Pan, Runmao Yao, Yalun Dai, Fushuo Huo, Fangzhou Hong, Zhaoxi Chen, Haozhao Wang, Dingwen Zhang, Ziwei Liu et al.
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.27367v2

While spatial foundation models have demonstrated impressive performance on standard datasets, a critical question remains: are they truly all-round players capable of generalizing robustly across diverse downstream tasks, arbitrary viewpoints, shifting scene domains, varying input densities, and specific hardware constraints? Answering this overarching question requires a holistic assessment, yet current models are mainly evaluated on specific domains for which they were specifically designed or trained. Such evaluations are intrinsically limited by narrow paradigm coverage, limited scene domains, and arbitrary frame sampling, making it fundamentally difficult to assess their true generalization capabilities. To address this gap, we present SpatialBench, a cross-paradigm, domain-diverse benchmark for spatial foundation models with deterministic sampling. SpatialBench features unprecedented scale and rigorous deterministic design, comprising 19 datasets and 546 scenes across 5 diverse spatial domains. It comprehensively evaluates 41 models across 6 paradigms on 5 task suites under 4 different input density settings. Our extensive evaluation reveals that current models are not yet all-round players, and uncovers crucial insights for future advancement. Specifically, we demonstrate that full-context attention maximizes accuracy while bounded-memory strategies unlock long-sequence scalability. Moreover, our empirical evaluations in challenging embodied and egocentric tasks demonstrate that strict domain alignment and high data quality are far more critical to performance than simple dataset scaling. Furthermore, to address the largest data gap identified in our analysis, we go beyond evaluation by introducing a large-scale dataset, DA-Next-5M, and a strong baseline model, DA-Next, pushing the boundaries of spatial representation learning.

---

### MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation

Authors: Huawei Lin, Peng Li, Jie Song, Fuxin Jiang, Tieying Zhang
Published: 2026-05-26
Categories: cs.AI, cs.CL, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2605.27366v2

Large language model (LLM) agents rely on reusable skills to solve complex tasks, but existing skill creation approaches often treat skills as isolated, static artifacts, limiting reusability, reliability, and long-term improvement. We propose MUSE-Autoskill Agent (Memory-Utilizing Skill Evolution), a skill-centric agent framework that creates, reuses, and refines skills under a unified lifecycle: creation, memory, management, evaluation, and refinement. MUSE creates skills on demand, stores them across tasks, retrieves them through a skill catalog, and accumulates per-skill experience for later reuse and adaptation. Across the main reported settings on SkillsBench and SkillLearnBench, MUSE-Autoskill outperforms Hermes, Codex, and Claude Code. On SkillsBench, its self-created skills surpass human-authored skills on the successfully covered subset (85.24% vs. 81.17%), showing that lifecycle-managed skills can distill agent experience into highly effective reusable assets; MUSE-created skills also transfer to Hermes more effectively than Codex- or Claude-created skills, reaching 51.90% accuracy under transfer. These results highlight the importance of treating skills as long-lived, experience-aware, and testable assets.

---

### LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

Authors: Shihao Wang, Shilong Liu, Yuanguo Kuang, Xinyu Wei, Yangzhou Liu, Zhiqi Li, Yunze Man, Guo Chen, Andrew Tao, Guilin Liu, Jan Kautz, Lei Zhang et al.
Published: 2026-05-26
Categories: cs.CV, cs.AI, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2605.27365v2

Vision-language models (VLMs) commonly formulate visual grounding and detection as a coordinate-token generation problem, serializing each 2D box into multiple 1D tokens that are learned and decoded largely independently. This token-by-token decoding mismatches the coupled structure of box geometry and creates a practical inference bottleneck due to strictly sequential generation. We introduce LocateAnything, a unified generative grounding and detection framework based on Parallel Box Decoding (PBD). By decoding geometric elements such as bounding boxes and points as atomic units in a single step, LocateAnything preserves intra-box geometric coherence and unlocks substantial parallelism. We show that PBD improves both decoding throughput and localization accuracy. We further develop a scalable data engine and curate LocateAnything-Data, a large-scale dataset with more than 138 million training samples, substantially increasing data diversity for high-precision localization. Extensive evaluations show that LocateAnything advances the speed-accuracy frontier, achieving significantly higher decoding throughput while improving high-IoU localization quality across diverse benchmarks. The results highlight the complementary benefits of Parallel Box Decoding and large-scale training data in enabling efficient and precise unified visual grounding and detection.

---

### Natural Language Query to Configuration for Retrieval Agents

Authors: Melissa Z. Pan, Negar Arabzadeh, Mathew Jacob, Fiodar Kazhamiaka, Esha Choukse, Matei Zaharia
Published: 2026-05-26
Categories: cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2605.27361v1

Modern retrieval agents expose many configuration choices -- LLM, retriever, number of documents, number of hops, and synthesis strategy -- each shaping both answer quality and serving cost. Today, these pipelines are typically hand-tuned once per workload, leaving substantial per-query optimization untapped. We formulate the problem: given a natural-language query and either an accuracy or a budget target, select from a predefined pipeline catalog the configuration that minimizes cost or maximizes accuracy at inference time. We propose **BRANE**, which uses an LLM to convert each query into workload-specific characteristics, then trains a lightweight per-configuration predictor that estimates whether the pipeline will answer the query correctly. At inference time, **BRANE** selects the configuration that maximizes predicted correctness penalized by cost, exposing a tunable cost-quality tradeoff without retraining. Across MuSiQue, BrowseComp-Plus, and FinanceBench, **BRANE** consistently pushes the cost-quality Pareto frontier, matches the best fixed configuration's accuracy at up to 89% lower cost, and outperforms LLM-routing, rule-based, and fine-tuned Qwen3-4B baselines. These results show that per-query configuration of the full retrieval pipeline is a practical alternative to static workload-level tuning.

---

### GENESIS: Harnessing AI Agents for Autonomous 6G RAN Synthesis, Research, and Testing

Authors: Tamerlan Aghayev, Maxime Elkael, Michele Polese, Minh Dat Nguyen, Gabriele Gemmi, Andrea Lacava, Ali Saeizadeh, Reshma Prasad, Paolo Testolina, Angelo Feraudo, Soumendra Nanda, Pedram Johari et al.
Published: 2026-05-26
Categories: cs.NI, cs.AI
arXiv: https://arxiv.org/abs/2605.27360v1

Cellular research and development (R&D) is throttled by six structural processes that each consume months of manual engineering work per iteration: (i) synthesizing new features from standards or research papers into production code; (ii) conformance and interoperability testing; (iii) hardening against field anomalies and diverse deployment environments; (iv) data-driven optimization of network functionalities; (v) discovering and prototyping novel waveforms, functionalities, and capabilities for future standards; and (vi) securing the stack against vulnerabilities. Although Large Language Models (LLMs) have compressed comparable R&D work in general software engineering from days to minutes, their known pitfalls worsen on Radio Access Network (RAN) use cases: they hallucinate Application Programming Interfaces (APIs) and mis-read specifications, which kills interoperability of RAN components at the first mistake, and they heavily rely on simulations for designing algorithms, which is notorious for breaking when transferred to real hardware. To address these challenges, we present GENESIS, an agentic Artificial Intelligence (AI) framework that converts intents (e.g., a specification clause, a telemetry anomaly, or a research hypothesis) into solutions validated with over-the-air experiments, fed back into a persistent knowledge base. GENESIS is built on three composable primitives (agents, skills, hooks) and a knowledge layer (SYNAPSE) that doubles as the source of ground truth and the recipient of every artifact the framework produces, making capabilities compound across runs.

---

### MobileMoE: Scaling On-Device Mixture of Experts

Authors: Yanbei Chen, Hanxian Huang, Ernie Chang, Jacob Szwejbka, Digant Desai, Zechun Liu, Vikas Chandra, Raghuraman Krishnamoorthi
Published: 2026-05-26
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.27358v1

Mixture-of-Experts (MoE) has become the de facto architecture for hundred-billion-parameter language models, yet its advantages at sub-billion scales for on-device deployment remain largely unexplored. To close this gap, we present MobileMoE, a family of on-device MoE language models with sub-billion active parameters (0.3-0.9B active and 1.3-5.3B total) that establish a new Pareto frontier for on-device LLMs. We first formulate an on-device MoE scaling law that jointly optimizes MoE architecture under mobile memory and compute constraints, identifying an on-device sweet spot - moderate sparsity with fine-grained and shared experts - that is simultaneously memory and compute-optimal. Building on the derived architectures, we train MobileMoE with a four-stage recipe covering pre-training, mid-training, instruction fine-tuning, and quantization-aware training, all on open-source datasets. Across 14 benchmarks, MobileMoE matches or exceeds leading on-device dense LLMs with 2-4$\times$ fewer inference FLOPs, and matches or surpasses the state-of-the-art MoE OLMoE-1B-7B with up to 60% fewer parameters. To bridge the last mile to mobile deployment, we provide the first efficient MoE inference on commodity smartphones with comprehensive on-device profiling. At comparable INT4 weight memory, MobileMoE-S delivers $1.8$-$3.8\times$ faster prefill and $2.2$-$3.4\times$ faster decode than the dense baseline MobileLLM-Pro.

---

### Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases

Authors: Dongyoon Hahm, Dylan Hadfield-Menell, Kimin Lee
Published: 2026-05-26
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2605.27355v2

Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing alignment influences the preference dataset, causing RLHF to amplify undesired behaviors. This arises from core limitations of RLHF: (1) preference datasets are constructed from the LLM's own outputs, allowing it to influence them, and (2) pairwise comparisons only indicate which response is better, not why. These limitations can be exploited to cause alignment tampering. For example, if an LLM generates biased responses with higher quality, annotators will prefer them based on quality. However, preference labels do not distinguish quality from bias, and the reward model inherits this limitation. Optimizing such rewards through reinforcement learning or best-of-N sampling can amplify misaligned biases. Our experiments demonstrate amplification across diverse biases: from keyword bias to propaganda (e.g., sexism), brand promotion, and instrumental goal-seeking. Mitigation remains challenging, as existing techniques for robust RLHF fail to fully resolve alignment tampering without sacrificing response quality. These findings reveal structural vulnerabilities of current RLHF and emphasize the need to prevent this vulnerability. Project page: https://alignment-tampering.github.io/

---

### Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders

Authors: Yi Jing, Zao Dai, Jinwu Hu, Zijun Yao, Lei Hou, Juanzi Li, Xiaozhi Wang
Published: 2026-05-26
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.27354v1

Model internals encode rich information about how a large language model (LLM) processes its training data; however, post-training data engineering largely relies on external signals and ignores rich intrinsic signals lying in model internals. We propose SAERL, a data engineering framework for LLM reinforcement learning (RL). It models three intrinsic data properties: diversity, difficulty, and quality, using model internals extracted with Sparse Autoencoder (SAE), an advanced mechanistic interpretability tool. Each property grounds a concrete data engineering operation: SAE-space clustering with moderate batch mixing for batch diversity control, a difficulty proxy for easy-to-hard curriculum ordering, and a quality probe for data filtering. SAERL improves average accuracy by 3.00% over vanilla GRPO and reaches target accuracy with 20% fewer training steps on Qwen2.5-Math-1.5B, with consistent gains across model scales and RL algorithms. Experiments show that SAE transfers effectively across model families and scales, serving as a lightweight and reusable data engineering tool. These results demonstrate that model internals are a powerful and practical source of signals for post-training data engineering.

---

### From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models

Authors: Yuchen Liang, Ness Shroff, Yingbin Liang
Published: 2026-05-26
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2605.27352v1

Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, but, especially for uniform-rate models, they often require many steps to generate a single sample. Existing acceleration methods either rely on training additional quantities or suffer from slow mixing. In this work, we propose a novel Gibbs-based corrector for discrete diffusion models, termed Gibbs-Accelerated Discrete Diffusion (GADD). GADD leverages the structure of the concrete score function to construct Gibbs posterior likelihoods directly, without requiring any additional training beyond standard score estimation. We show that GADD achieves an overall sampling complexity of $\mathcal{O}(\mathrm{polylog} (\varepsilon^{-1}))$, yielding the first such rate for diffusion-based samplers for uniform-rate discrete diffusion models. We also conduct numerical experiments demonstrating the practical advantages of GADD across synthetic data, zero-shot text sampling, and zero-shot conditional music generation. These results corroborate the theory and show that GADD consistently improves sample quality and wall-clock efficiency over standard baselines, including vanilla Euler methods and CTMC correctors. Beyond this, our theoretical analysis introduces a novel framework for analyzing predictor-corrector methods in discrete diffusion models, which may be of independent interest. Unlike existing approaches that rely on the Girsanov change-of-measure technique, our method is based on an induction argument that tracks error propagation across predictor iterations while accounting for inaccuracies in the corrector updates.

---

### Feedforward 3D Editing Learns from Semantic-Part Transformation

Authors: Jiawei Weng, Saining Zhang, Zhenxin Diao, Peishuo Li, Henghaofan Zhang, Junhao Chen, Hao Zhao
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.27351v5

3D editing is a fundamental capability for scalable 3D content creation. While image editing has rapidly evolved toward large-scale feedforward generative paradigms, 3D AI generation remains dominated by training-free editing pipelines. A central challenge of feedforward 3D editing lies in the lack of high-quality paired supervision. Editable 3D assets require simultaneous preservation of geometry, multi-view consistency, structural coherence, and localized edit controllability. Existing 3D editing datasets often rely on independently generated assets, image-mediated reconstruction or narrow edit taxonomies, leading to inaccurate localization, weak preservation, blurred edit boundaries, and limited semantic consistency. In this work, we introduce a new perspective: scalable feedforward 3D editing should be learned from semantic-part transformations. Based on this insight, we propose Pxform, a high-quality 3D editing dataset with over 100K consistent before/after editing pairs across seven edit types. Instead of treating objects as unstructured shapes, our pipeline grounds edits directly in semantic 3D parts. Built upon Pxform, we further propose PartFlow, a feedforward 3D editing network that injects source-aware latent control into pretrained 3D generative priors. PartFlow introduces mask-aware velocity preservation and render-space consistency supervision to jointly improve edit fidelity and source preservation, while requiring no 3D edit mask during inference. Extensive experiments demonstrate that high-quality semantic-part supervision substantially improves scalable 3D editing, enabling PartFlow to achieve state-of-the-art performance on both geometric and appearance editing benchmarks.

---

### When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection

Authors: Jihyeon Kim, Sohee Kim, Soosan Lee, Souhwan Jung, James Matthew Rehg, Hyesong Choi
Published: 2026-05-26
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.27348v2

Recent generative models have largely closed the gap on low-level artifacts - pixel fingerprints, frequency anomalies, upsampling traces - particularly in person-centric and partial-edit settings where the manipulated region is small and surrounded by photometrically authentic content. We introduce Social Gaze Consistency, a high-level semantic cue defined as the mutual coherence of gaze direction, head-eye alignment, and pupil placement between interacting individuals, and show that it constitutes a previously underutilized detection axis orthogonal to existing low-level paradigms. We instantiate this insight through three coupled mechanisms: (i) a controlled diagnostic dataset with region-specific perturbations of gaze-consistent imagery, where strict pair-level grouping forecloses generator-fingerprint memorization as an optimization-time shortcut rather than relying on augmentation; (ii) Block-Compositional Caption Supervision, which holds a single 5-block reasoning skeleton invariant across 1,250 macro-combined captions, decoupling reasoning consistency from surface diversity; (iii) Cross-architecture validation showing the same supervision improves a vision-language backbone (FakeVLM) by +3.7 pp on the COCOAI Interaction subset (balanced accuracy 67.8 -> 71.5) and +1.3 pp on the COCOAI Person subset (83.0 -> 84.3), with consistent gains on a vision-only backbone (Effort), evidencing a backbone-agnostic cue. Real- and fake-class recalls rise simultaneously, ruling out a "predict-all-fake" artifact. A four-step mechanistic account - paired-edit shortcut blocking, hard-to-easy difficulty transfer, CLIP prior preservation, and diffusion-family shared spectral weakness in periocular structure - explains why training on a single inpainter (FLUX.1-Fill) transfers to multi-generator suites. We will release the code upon acceptance to facilitate reproducibility.

---

### MATCHA: Matching Text via Contrastive Semantic Alignment

Authors: Siran Li, Ece Sena Etoglu, Carsten Eickhoff, Seyed Ali Bahrainian
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.27345v1

Reliable evaluation is essential for understanding large language model (LLM) performance, yet today's go-to metrics, namely token-overlap scores (e.g., ROUGE) and embedding-based measures (e.g., BERTScore), often misjudge semantic similarity of documents. Our study shows that both token-overlap metrics and embedding-based metrics routinely assign nearly identical scores to texts that directly contradict each other, thereby potentially masking fundamental errors. We introduce MATCHA, an automatic metric that jointly rewards semantic agreement with a reference and penalizes contradictions. MATCHA employs a dual-view perspective that measures (i) proximity to the gold text and (ii) distance from an adversarially generated counterfactual contradiction. In eight public benchmarks, MATCHA outperforms popular metrics, compared with human annotations on question-answering, image caption generation, natural language inference, summarization, and semantic textual similarity tasks. On the TruthfulQA dataset (i.e., a dataset without a training set, where no embedding-based metrics could locally train on), this improvement in terms of matching texts with a reference reaches 18.38% over ROUGE-L and 20.82% over BERTScore. Both quantitative comparison and qualitative human assessments confirm the efficacy and validity of MATCHA and uncover fundamental weaknesses in pre-existing metrics. Compared with 23 embedding models, including top state-of-the-art ones, used as a metric similar to BERTScore, MATCHA remains the most accurate in distinguishing correct from incorrect statements solely based on a reference. Our code and metric are publicly available (https://github.com/Siran-Li/MATCHA).

---

### Towards Controllable Image Generation through Representation-Conditioned Diffusion Models

Authors: Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel Eilertsen
Published: 2026-05-26
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.27343v1

Diffusion models have emerged as powerful tools for high-quality image generation and editing, but guiding these models to produce specific outputs remains a challenge. Conventional approaches rely on conditioning mechanisms, such as text prompts or semantic maps, which require extensively annotated datasets. In this preliminary work, we explore diffusion models conditioned on representations from a pre-trained self-supervised model. The self-conditioning mechanism not only improves the quality of unconditional image generation, but also provides a representation space that can be used to control the generation. We explore this conditioning space by identifying directions of variations, and demonstrate promising properties in terms of smoothness and disentanglement.

---

### 2-ASP(Q) programs with weak constraints: Complexity and efficient implementation

Authors: Andrea Cuteri, Giuseppe Mazzotta, Francesco Ricca
Published: 2026-05-26
Categories: cs.AI, cs.CC, cs.CL, cs.LO
arXiv: https://arxiv.org/abs/2605.27338v1

ASP(Q) extends Answer Set Programming (ASP) with Quantifiers over answer sets. In this paper we focus on the class of ASP(Q) programs with two quantifiers and weak constraints, denoted as 2-ASP(Q)^w. 2-ASP(Q)^w is a practically relevant fragment of ASP(Q) that is expressive enough to capture optimization problems up to the class Delta_3^P. On the theoretical side, we provide a complete complexity characterization of the main computational tasks for 2-ASP(Q)^w programs, including tight completeness results and the analysis of nontrivial cases that have not been addressed in previous works. On the practical side, we introduce novel strategies for computing (optimal) quantified answer sets in the Casper system, that rely on a Counterexample-Guided Abstraction Refinement (CEGAR) technique tailored to ASP(Q). An experimental evaluation on hard benchmarks from different application domains shows that the proposed techniques are effective in practice.

---

### PARE: Pruning and Adaptive Routing for Efficient Video Generation

Authors: Yutong Wang, Yunke Wang, Tianfan Xue, Yu Qiao, Yaohui Wang, Xinyuan Chen, Chang Xu
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.27336v1

Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sampling. Recent methods reduce cost by compressing width, depth, or sampling steps, but typically commit to a fixed architecture that cannot adapt to individual inputs or denoising stages. We propose PARE (Pruning and Adaptive Routing for Efficient video generation), which jointly compresses width and depth with structure-aware pruning and input-adaptive routing. For width, we observe that attention heads specialize into spatial and temporal roles, and design importance scoring that accounts for this distinction to prevent motion-critical temporal heads from being pruned prematurely. For depth, we train a lightweight router conditioned on denoising timestep and visual content to dynamically select which blocks to execute at each step, enabling per-input compute adaptation rather than static block removal. A progressive pipeline first recovers width-pruned quality via distillation, then jointly optimizes the student and router to decouple the two learning objectives. Experiments on Wan2.1-14B for both image-to-video and text-to-video generation show that PARE substantially reduces per-step computation while preserving quality across VBench dimensions, and composes with step distillation for further acceleration.

---

### FinHarness: An Inline Lifecycle Safety Harness for Finance LLM Agents

Authors: Haoxuan Jia, Yang Liu, Bin Chong, Yingguang Yang, Yancheng Chen, Jiayu Liang, Qian Li, Hanning Lu, Kefu Xu, Hao Zheng, Chongyang Zhang, Hao Peng et al.
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.27333v1

Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows. However, boundary filters often miss irreversible mid-trajectory tool calls, while post-hoc LLM judges perform auditing only after termination -- too late for intervention and at a computational cost that scales linearly with trace length. We present FinHarness, an inline safety harness that wraps a finance agent end-to-end with three components: a Query Monitor that fuses single-turn intent with cross-turn drift, a Tool Monitor that evaluates each prospective tool call, and a Cascade module that integrates per-step risk and adaptively routes verification between a lightweight and an advanced-tier LLM judge. Fired risk factors are re-injected into the agent input as ex-ante evidence, enabling the agent to refuse, re-plan, or approve on its own. On FinVault, routed FinHarness cuts ASR from 38.3% to 15.0% while largely preserving benign approval ($41.1\% \to 39.3\%$), and uses $4.7\times$ fewer advanced-judge calls than an always-advanced ablation.

---

### EdgeFlow: Edge-Map Augmented VLM-Based Flowchart Processing for Industrial Requirements Engineering

Authors: Zhifei Dou, Shabnam Hassani, Ou Wei
Published: 2026-05-26
Categories: cs.SE, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2605.27332v1

Flowcharts are widely used in industrial requirements, but usually remain embedded as static images. Vision Language Models (VLMs) show promise in the conversion of these flowcharts into machine-readable models for RE activities, yet, when directly applied to flowchart conversion, they often fail on topology-critical visual details. To address this, we propose EdgeFlow that augments a VLM's original input with a deterministically extracted Canny edge map-acting as a structural prior-to improve flowchart-to-Mermaid conversion, without requiring annotated training data or domain-specific model fine-tuning. We evaluate EdgeFlow on IndusReqFlow, a dataset sourced from real-world requirements. Compared with off-the-shelf VLMs, EdgeFlow improves node-level F1 by 17.39 percentage points and edge-level F1 by 16.94 percentage points. At the path level, EdgeFlow improves path F1 by 11.06 percentage points, enabling better support for model-based testing. These results demonstrate that EdgeFlow provides a practical, training-free means to improve topology-preserving flowchart-to-Mermaid conversion for industrial RE. Cross-dataset evaluation results on a public synthetic benchmark show no significant improvement; this highlights the need for diverse benchmarks incorporating industrial data for the comprehensive evaluation of future VLM-based RE tools.

---

### Maat: The Agentic Legal Research Assistant for Competition Protection

Authors: Basant Mounir, Farida Madkour, Amira Abdelaziz, Asmaa Sami
Published: 2026-05-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.27331v1

Competition law experts conducting legal research must review extensive volumes of cases, decisions, and judicial reports to identify precedents and assess key elements in competition and merger cases. Although general research assistants such as Claude and ChatGPT and legal assistants such as SaulLM-7B and LegalGPT are increasingly used to assist legal research, they remain inadequate for competition law analysis: they lack specialized domain expertise, provide insufficient official citations, or hallucinate competition law cases. We propose Maat, a ReAct agent that orchestrates tools corresponding to different tasks of the research process. Designed iteratively with competition law experts, Maat grounds cases and findings in official sources using RAG for reliability, provides rich in-line citations, falls back to web search when database coverage is insufficient, and prompts the user for clarification when queries are ambiguous. Maat significantly outperforms all baseline assistants on case-specific tasks and performs within range of the top baseline on theoretical question tasks. The dataset used is available on GitHub.

---

### Governed Evolution of Agent Runtimes through Executable Operational Cognition

Authors: Mariano Garralda-Barrio
Published: 2026-05-26
Categories: cs.SE, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2605.27328v1

Recent advances in agentic systems increasingly treat code as an executable operational substrate rather than as a disposable output artifact. Prior work such as \emph{Code as Agent Harness} frames validated agent-generated artifacts as runtime entities that can be created, executed, revised, persisted, and reused within long-running cognitive loops. However, the governance, lifecycle management, and operational evolution of such artifacts remain under-specified. This paper proposes a framework for governed runtime evolution in multi-agent systems through executable operational cognition. We formalize agent-generated artifacts as persistent runtime capabilities that progressively become part of the operational substrate rather than transient intermediate outputs. Building on this perspective, we introduce \emph{HarnessMutation} as a governed mechanism for lifecycle-aware runtime adaptation operating under explicit validation, traceability, evaluation, and rollback constraints. Rather than treating runtime adaptation as unrestricted self-modification, the proposed framework models evolution as a bounded and observable process over persistent operational memory. It further shows how these ideas can be operationalized over modern agent runtimes and governance-oriented orchestration systems, providing a conceptual foundation for adaptive infrastructures whose evolution remains explicit, auditable, and constrained.

---

### Semantic Gradients Interactions in SSD: A Case Study in Racial Identity and Hate Speech

Authors: Felix Ostrowicki, Hubert Plisiecki
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.27322v1

We introduce interaction SSD, an extension of Supervised Semantic Differential that models how semantic meaning varies across moderators such as groups, traits, or conditions making this variation testable and interpretable. The method estimates a main semantic gradient, an interaction gradient, and conditional gradients, all interpretable through standard SSD tools. We illustrate it on the UC Berkeley Measuring Hate Speech corpus, testing whether annotator racial identity moderates hate-speech judgments of comments targeting people of color. The interaction model detects a significant moderation effect: the shared gradient contrasts dehumanizing hostility with counter-speech, while the interaction gradient reveals smaller group-linked differences in which semantic cues predict hate-speech ratings. Interaction SSD makes moderated meaning-outcome relationships statistically testable and interpretable.

---

### Modeling Agentic Technical Debt and Stochastic Tax: A Standalone Framework for Measurement, Simulation, and Dashboarding

Authors: Muhammad Zia Hydari, Raja Iqbal, Narayan Ramasubbu
Published: 2026-05-26
Categories: cs.AI, cs.CY, econ.GN
arXiv: https://arxiv.org/abs/2605.27320v1

Agentic AI systems combine probabilistic reasoning with delegated action through tools, context, memory, orchestration, and external workflow integration. This note develops a formal and managerially usable model that distinguishes Agentic Technical Debt from Stochastic Tax. Agentic Technical Debt is a stock of accumulated design and governance liability. Stochastic Tax is a recurring flow of operating burden that arises when stochastic agents are used in business workflows. The two constructs are related, but they are not the same: debt can amplify the tax, while the tax can remain positive even when debt is minimized. The note starts from a compact dashboard expression, expands it into a fuller structural model, defines all variables and parameters, shows how each cost category can be estimated from operational data, and illustrates the framework with an accounts-payable simulation and companion spreadsheet.

---

### Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning

Authors: Xianqiang Gao, Qizhi Chen, Delin Qu, Haoming Song, Zhigang Wang, Bin Zhao, Dong Wang, Xuelong Li
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.27318v2

Video spatial reasoning requires accumulating viewpoint-dependent evidence over time while retaining information useful to the question being asked. Existing spatial video-language models improve geometric perception and long-range context modeling, but often treat memory as a generic temporal cache, which can introduce redundant or irrelevant evidence and weaken long-horizon reasoning. We propose Q-GeoMem, a question-guided geometric memory framework for video spatial reasoning. Q-GeoMem injects camera-conditioned geometry into visual tokens and maintains two complementary memories: a Fine-Grained Context Bank for recent dense features and camera states, and a Semantic-Geometric Evidence Bank for compact long-range evidence. For each candidate frame, a calibrated Q-Former estimates question relevance, while novelty and evidence utility are recomputed with respect to the active evidence bank. The resulting relevance-novelty utility controls capacity-based replacement and serves as an attention bias during memory reading. During reasoning, both memories are read before update and adaptively fused with the current frame representation. Extensive experiments across two in-domain and five out-of-distribution benchmarks, and controlled memory analyses show that Q-GeoMem achieves state-of-the-art performance in the evaluated settings and validate the effectiveness of question-guided geometric evidence selection.

---

### Probabilistic Smoothing with Ratio-Monotone Transforms for Global Optimization

Authors: Kukyoung Jang, Taehyun Cho, Junrui Zhang, Ping Xu, Kyungjae Lee
Published: 2026-05-26
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2605.27316v1

Probabilistic smoothing is a standard tool for global optimization, but existing methods rely on Gaussian kernels and specific transforms, often resulting in strong hyperparameter sensitivity and limited robustness. We propose a general smoothing framework that combines flexible symmetric unimodal kernels with monotonic ratio-based transformations. Under mild conditions, we show that the smoothed objective preserves the global maximizer and that all stationary points concentrate near the true optimum for sufficiently large amplification, without requiring a decreasing smoothing schedule. We further provide explicit complexity bounds for stochastic gradient ascent and show that a leave-one-out baseline provably reduces variance. Experiments on high-dimensional benchmarks and black-box adversarial attacks demonstrate improved robustness and competitive performance.

---

### Real Images, Worse Judgments: Evaluating Vision-Language Models on Concreteness and Imagery

Authors: Yifan Jiang, Ruoxi Ning, Sheng Yao, Freda Shi
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.27315v2

Visual inputs are often assumed to improve language understanding in multimodal models. We examine this assumption by asking whether vision-language models (VLMs) can distinguish useful visual evidence from incidental image context in lexical judgments. We use human concreteness and imagery ratings because they span words with varying expected visual relevance, from abstract and low-imagery words to concrete and high-imagery words. We find that real-image contexts do not yield consistent gains and often hurt alignment with human ratings, most sharply when visual evidence is least relevant. Through probing and canonical correlation analysis, complemented by an attribution case study, we find that real-image contexts are associated with representational shifts and greater sensitivity to spurious visual cues, coinciding with weaker recoverability of the targeted lexical properties. We further show that instructing models to focus solely on textual content at inference time can reduce this degradation, with the clearest gains on these vulnerable subsets. Our findings suggest that current instruction-tuned VLMs need better calibration of when visual context should inform lexical judgments.

---

### Real Images, Worse Judgments: Evaluating Vision-Language Models on Concreteness and Imagery

Authors: Yifan Jiang, Ruoxi Ning, Sheng Yao, Freda Shi
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.27315v1

Visual inputs are often assumed to improve language understanding in multimodal models. We examine this assumption by asking whether vision-language models (VLMs) can distinguish useful visual evidence from incidental image context in lexical judgments. We use human concreteness and imagery ratings because they span words with varying expected visual relevance, from abstract and low-imagery words to concrete and high-imagery words. We find that real-image contexts do not yield consistent gains and often hurt alignment with human ratings, most sharply when visual evidence is least relevant. Through probing and canonical correlation analysis, complemented by an attribution case study, we find that real-image contexts are associated with representational shifts and greater sensitivity to spurious visual cues, coinciding with weaker recoverability of the targeted lexical properties. We further show that instructing models to focus solely on textual content at inference time can reduce this degradation, with the clearest gains on these vulnerable subsets. Our findings suggest that current instruction-tuned VLMs need better calibration of when visual context should inform lexical judgments.

---

### When Does Demographic Information Help? Data and Modeling Regimes for Perspective-Aware Hate Speech Detection

Authors: Weibin Cai, Reza Zafarani
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.27313v1

Demographic information is often used to model annotator perspectives in subjective tasks such as hate speech detection, but its benefit is inconsistent: it improves performance in some settings and behaves as noise in others. This paper asks when demographic features help. We analyze demographic gain as a function of both data split properties and modeling frameworks. For data splits, we measure annotator disagreement, namely how often annotators assign different labels to the same example, along with training size and train-test demographic coverage. We find that demographic gains concentrate in regimes with low training disagreement, high test disagreement, fine-grained ambiguity measurement, sufficient training data, and greater demographic overlap. Motivated by these regimes, we introduce a gated demographic residual model that treats demographics as a selective adjustment to text-only predictions. Experiments on MHS and POPQUORN show that this design is effective, especially on high disagreement or low confidence examples. Overall, our results suggest that demographics should not be assumed useful by default; their value depends jointly on the data regime and the modeling framework.

---

### Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models

Authors: Yifan Jiang, Dae Yon Hwang, Jesse C. Cresswell, Freda Shi
Published: 2026-05-26
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2605.27311v2

Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning to correctly answer, but vision-language models (VLMs) can often reach solutions through shortcuts or prior familiarity with a chart or question. To strictly evaluate visual reasoning, we propose counterfactual charts where the chart-question task remains fixed, but the underlying data and the corresponding answer are varied. We introduce Chartographer, a framework to reverse engineer charts into executable code, validate reconstruction fidelity, generate counterfactual variants, and derive new answers from executable QA logic. We apply this framework to existing chart QA datasets and evaluate proprietary and open-source VLMs, measuring variant sensitivity and generalizability. Counterfactual charts reveal failures hidden by single-chart performance: VLMs often fail to generalize after answering the original chart correctly. We find that failures are most prevalent when updated charts require novel visual reasoning pathways.

---

### Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models

Authors: Yifan Jiang, Dae Yon Hwang, Jesse C. Cresswell, Freda Shi
Published: 2026-05-26
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2605.27311v1

Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning to correctly answer, but models can often reach solutions through shortcuts or prior familiarity with a chart based on their own background knowledge. To strictly evaluate visual reasoning, we propose counterfactual charts where the chart-question task remains fixed, but underlying chart and the corresponding answer are varied. We introduce Chartographer, a framework to reverse engineer charts into executable code, validate reconstruction fidelity, generate seed-controlled counterfactual variants, and derive new answers from executable QA logic. We apply this framework to existing chart QA datasets and evaluate proprietary and open-source vision-language models (VLMs), measuring variation sensitivity and generalizability. Counterfactual charts reveal failures hidden by single-chart performance: VLMs often fail to generalize after answering the original chart correctly. We find failures are most prevalent when updated charts require novel visual reasoning pathways.

---

### How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning

Authors: Qian Yang, Ankur Sikarwar, Huy Le, Le Zhang, Zhuan Shi, Perouz Taslakian, Aishwarya Agrawal
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.27310v2

Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they reason in language and discard the fine-grained geometry the task requires. Thinking with images aims to fix this by generating an intermediate thinking-image, but recent work shows the visual evidence in these traces is largely ignored. We therefore ask how to make visual thinking matter, and what kind of visual thinking works best. We ask these questions for unified multimodal models (UMMs) that natively support interleaved image-text generation. For the how, we propose View Dropout (VDrop), a training-time intervention that hides parts of one input view from the answer span while leaving it visible to the thinking-image tokens. This incentivizes the model to make use of the thinking-image when answering, rather than answering based on the input views only. With the thinking-image now being used in answer prediction, we ask which kind of visual thinking works best. We frame this as a Learnability-Informativeness (L-I) tradeoff and compare three thinking-image variants: top-down, panoramic, and point-matching renderings. Trained on synthetic scenes and evaluated on five real-world out-of-domain benchmarks, panoramic visual thinking with VDrop is the only configuration that is simultaneously informative and learnable, and achieves the best out-of-domain generalization.

---

### How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning

Authors: Qian Yang, Ankur Sikarwar, Huy Le, Le Zhang, Zhuan Shi, Perouz Taslakian, Aishwarya Agrawal
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.27310v1

Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they often reason in language and lose the fine-grained geometry needed for the task. Thinking with images aims to address this by generating an intermediate thinking image, but recent work shows that models often ignore the visual evidence in these traces. We therefore ask how to make visual thinking matter, and what kind of visual thinking works best. We study these questions in unified multimodal models (UMMs), which natively support interleaved image-text generation. For the first question, we propose View Dropout (VDrop), a training-time intervention that hides parts of one input view from the answer span while keeping them visible to the thinking-image tokens. This encourages the model to use the thinking image when answering, instead of relying only on the input views. Once the thinking image is used for answer prediction, we study which type of visual thinking is most effective. We frame this as a learnability-informativeness tradeoff and compare three thinking-image variants: top-down, panoramic, and point-matching renderings. Trained on synthetic scenes and evaluated on five real-world out-of-domain benchmarks, panoramic visual thinking with VDrop is the only configuration that is both informative and learnable, and it achieves the best out-of-domain generalization.

---

### Greening AI Inference with Accuracy and Latency-aware User Incentives

Authors: Vasilios A. Siris, Adamantia Stamou, George D. Stamoulis, Konstantinos Varsos, Ramin Khalili
Published: 2026-05-26
Categories: cs.LG, cs.OH
arXiv: https://arxiv.org/abs/2605.27309v1

The widespread use of AI services has raised concerns for its environmental sustainability, towards which recent studies have identified carbon emissions of AI inference as the major contributor. This paper introduces a framework for designing AI inference incentives based on the users' valuation for inference quality and latency, together with their environmental consciousness, while accounting for the tradeoff between carbon emissions and the two QoE parameters. Our approach can accommodate different tradeoffs, that depend on the size and complexity of the AI models and the allocation of resources to serve inference requests. The incentives can be offered through a practical two-tier service subscription that offers users a discount in exchange for reduced carbon emissions. The discounted service option gives the AI provider the flexibility to serve some percentage of inference requests at a lower quality and higher latency during periods of high carbon intensity.

---

### Normal Guidance is what Attention Needs

Authors: Ethan Harvey, Dennis Johan Loevlie, Michael C. Hughes
Published: 2026-05-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.27306v1

We consider training classifiers for 3D medical images using only one binary label for the entire volume rather than a label for each 2D slice. In such weakly supervised settings, can we learn accurate classifiers for slice-level predictions? Attention-based multiple instance learning (MIL) can produce an attention score for every slice. Yet recent work demonstrates that a simple center-focused baseline that ignores image content can outperform attention-based and transformer-based MIL at slice-level classification of 3D brain scans. We show this baseline also outperforms existing MIL at slice-level classification of thoracic and abdominal CT scans. Motivated by this baseline, we propose Normal Guidance, a regularization technique that encourages the learned attention distribution to follow a bell-shaped curve. Across three medical imaging datasets totaling over 4 million 2D slices, we show our Normal Guidance enables attention-based and transformer-based MIL methods to deliver significantly better slice-level localization than the state-of-the-art while remaining competitive at whole-scan classification.

---

### PlayClass: Automated Play Behaviour Classification in Poultry

Authors: Prince Ravi Leow, Neil Scheidwasser, Rebecca Oscarsson, Per Jensen, Samir Bhatt, David Alejandro Duchêne
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.27304v1

Automated monitoring of animal welfare has largely targeted negative indicators, leaving positive welfare behaviours such as play underexplored. To address this gap, we present PlayClass, a pipeline for play-behaviour classification in poultry from top-down pen video. The pipeline leverages long-duration tracking with SAM 3 via YOLO-guided chunk boundaries to minimise identity errors in point-based prompting, and frozen embeddings from image and video foundation models for play action classification. Although handcrafted motion features from tracked masks alone achieved competitive accuracy, V-JEPA 2.1 consistently outperformed all other backbones across model scales, reaching 77.0 macro-averaged F$_1$ when combined with handcrafted features. Despite this result, the dataset remains challenging due to play sub-types sharing similar kinematic profiles with non-play and inter-bird occlusion. Overall, our work provides encouraging evidence towards automated frameworks for play behaviour classification in poultry.

---

### Risk Averse Alert Prioritization for IDS Using Subnormal Gaussian Fuzzy Models

Authors: Murat Moran
Published: 2026-05-26
Categories: cs.CR, cs.AI, cs.HC, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2605.27299v1

Modern intrusion detection systems generate thousands of alerts daily, but alert fatigue severely limits security operations effectiveness due to too many false positives or low-impact events. We address this by proposing a principled framework for alert prioritization based on subnormal Gaussian fuzzy numbers, explicitly modeling three sources of uncertainty: threat severity, detection confidence, and organizational risk attitude. Each alert is represented as a fuzzy number with the core indicating severity, spread indicating uncertainty, and height reflecting detection reliability. We apply ranking indices to prioritize alerts, allowing organizations to tune security posture through a risk-attitude parameter. Experimental validation on CIC-IDS2017 and NSL-KDD demonstrates greater robustness than baselines under detector degradation (0.9963 vs 0.8215 NDCGrel@100), with distinct differentiation in mid-confidence alerts and near-parity with baselines under robust detectors. The framework is theoretically grounded, computationally efficient, provides interpretable reasoning, and remains robust across detector families and miscalibration scenarios.

---

### Self-Ensembling Vision-Language Models for Chart Data Extraction

Authors: Thomas Berkane, Qianyi Wang, Maimuna S. Majumder
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.27298v1

Charts effectively convey quantitative information, but the underlying data are often locked in image form, hindering reuse and analysis. Manually digitizing charts is time-consuming and error-prone, motivating automatic chart-to-table extraction. Recent approaches use specialized vision-language models (VLMs), yet performance still lags on charts with many datapoints or substantial stylistic variation. We propose a VLM self-ensembling method that repeatedly samples multiple tabular outputs from the same VLM for a fixed chart image and aggregates them at the level of individual table cells. We align candidate tables and take per-cell medians over numerical values to produce a more accurate consensus table. Our method also includes convergence detection to stop sampling once the aggregated table stabilizes, and uncertainty estimation based on dispersion across samples to help users assess extraction reliability. Because existing chart extraction benchmarks contain relatively simple plots with limited room for improvement, we introduce WB-ChartExtract, a new benchmark built from World Bank data with more complex and stylistically diverse charts; on average, its charts contain 7 times more datapoints than those in the ChartQA benchmark. Across both ChartQA and WB-ChartExtract, our approach improves extraction accuracy over single-pass VLM outputs, yielding up to 23% relative improvement on WB-ChartExtract after ensembling. More broadly, our method helps unlock tabular data previously siloed in chart images, enabling downstream analysis and reuse.

---

### Probing Cultural Awareness in LLMs: A Case Study of Cross-Culture Aesthetic Stylistics

Authors: Jiashuo Wang, Fenggang Yu, Jian Wang, Chak Tou Leong, Xiaoyu Shen, Chunpu Xu, Jiawen Duan, Wenjie Li, Johan F. Hoorn
Published: 2026-05-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.27296v1

Large Language Models (LLMs) are increasingly deployed in diverse cultural contexts, yet their ability to master aesthetic stylistics, i.e., the strategic use of language to evoke cultural resonance, remains underexplored. We curate C4STYLI, a benchmark of highly stylized translated movie titles and advertising slogans from Hong Kong and the Chinese Mainland, to evaluate LLMs via the lens of behavioral recognition and productive competence. Extensive evaluations show that LLMs differ from humans in stylistic recognition, and this recognition ability varies across text domains. In addition, stylistic recognition and generation performance in LLMs are not consistently aligned. To further examine whether LLMs genuinely capture stylistic information in stylistic recognition, we conduct structural ablation with logistic regression probes. We find that, in the Hong Kong setting, stylistic recognition in LLMs relies primarily on surface-level linguistic information rather than stylistic structure. This suggests limited sensitivity to Hong Kong-specific stylistic structure.

---

### Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini

Authors: Madhuri Shanbhogue, Zhe Li, Shanfeng Zhang, Gustavo Hernández Ábrego, Shih-Cheng Huang, Aashi Jain, Daniel Salz, Sonam Goenka, Chaitra Hegde, Ji Ma, Feiyang Chen, Jiaxing Wu et al.
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.27295v1

We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified representation space. We leverage the multimodal capabilities of Gemini to produce embeddings for arbitrary combinations of interleaved inputs across all these modalities that generalize well across a wide variety of tasks. Applying large-scale contrastive learning in a multi-task multi-stage training setup, we achieve state-of-the-art performance on key embedding benchmarks including unimodal, cross-modal, and multimodal retrieval spanning a diverse set of tasks. We show that our embedding model demonstrates strong performance (with a score of 62.9 R@1 on MSCOCO, 68.8 NDCG@10 on Vatex, 69.9 on MTEB multilingual and 84.0 on MTEB Code) across a variety of tasks surpassing the performance of specialized models. These unified capabilities make Gemini Embedding 2 a promising candidate for downstream use cases such as RAG, recommendation and search. Furthermore, its robust zero-shot performance across distinct fields - from astronomy and bioscience to fine arts and the culinary arts - establishes it as a highly reliable, out-of-the-box representation even for specialized domains.

---

### Separating Semantic Competition from Context Length in RAG Reading

Authors: Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh, Rohit Alekar, Cien Zhang, Svetlana Karslioglu, Akash Vishwakarma
Published: 2026-05-26
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2605.27294v1

Retrieval-augmented generation (RAG) systems can respond incorrectly even when the correct passage was retrieved. The model must still read the retrieved passages and identify which one contains the answer among others that look relevant. This passage-reading model is called the reader. Does it fail simply because the context is longer or because the other passages genuinely compete with the correct one? We introduce and demonstrate a matched-control protocol for RAG reading: we keep the number and length of passages fixed, but replace hard competitors with less competitive real passages. We apply this control across two compact open models on SQuAD. This replacement partially restores performance, with the strongest effects on F1 and answer inclusion. For Phi-2, this recovers +6.0 EM points, +7.0 answer-inclusion points, and +0.057 F1. For Qwen2.5-1.5B, it recovers +4.5 EM points, +9.0 answer-inclusion points, and +0.068 F1. To track how performance changes as competitors accumulate, we also report retention curves and summarize them with a right-censored half-life when the curves do not cross half-retention. Together, these results show the protocol isolates a competition effect distinct from context length, though the effect is clearer for F1 and answer inclusion than for exact match, and also varies with snippet length.

---

### BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning

Authors: Shijin Gong, Erhan Xu, Kai Ye, Giulia Livieri, Francesco Quinzan, Chengchun Shi
Published: 2026-05-26
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2605.27293v2

Reinforcement learning with verifiable rewards has become a standard recipe for improving the reasoning abilities of large language models. Existing algorithms face a tradeoff between computational efficiency and sample efficiency in value estimation and policy learning. We introduce BASIS, a critic-free post-training algorithm designed to address this tradeoff. At each online training step, BASIS samples only one rollout per prompt, but leverages rich information across prompts in the entire batch to improve value function estimation. Our experiments demonstrate that BASIS reduces MSE in value function estimation by 69% compared to REINFORCE++, a representative single-rollout baseline, and achieves lower MSE with one rollout than group mean estimators with 8 rollouts. This improvement in value estimation translates to better policy optimization: using substantially less training time, BASIS achieves performance close to multi-rollout GRPO-type baselines and often outperforms single-rollout REINFORCE-type baselines.

---

### BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning

Authors: Shijin Gong, Erhan Xu, Kai Ye, Francesco Quinzan, Giulia Livieri, Chengchun Shi
Published: 2026-05-26
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2605.27293v1

Reinforcement learning with verifiable rewards has become a standard recipe for improving the reasoning abilities of large language models. Existing algorithms face a tradeoff between computational efficiency and sample efficiency in value estimation and policy learning. We introduce BASIS, a critic-free post-training algorithm designed to address this tradeoff. At each online training step, BASIS samples only one rollout per prompt, but leverages rich information across prompts in the entire batch to improve value function estimation. Our experiments demonstrate that BASIS reduces MSE in value function estimation by 69% compared to REINFORCE++, a representative single-rollout baseline, and achieves lower MSE with one rollout than group mean estimators with 8 rollouts. This improvement in value estimation translates to better policy optimization: using substantially less training time, BASIS achieves performance close to multi-rollout GRPO-type baselines and often outperforms single-rollout REINFORCE-type baselines.

---

### Detectability in Diversity: Improved Canary Crafting for Privacy Auditing in One Run

Authors: Mathieu Dagréou, Aurélien Bellet
Published: 2026-05-26
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2605.27292v2

Privacy auditing aims to empirically assess privacy leakage in machine learning models using membership inference attacks (MIAs), and to derive lower bounds on differential privacy (DP) parameters. Recent one-run auditing methods address the high cost of standard approaches by relying on a single training run with multiple "canary" points whose inclusion or exclusion must be detected by the auditor. In this work, we study the problem of efficiently crafting canaries for one-run privacy auditing. Motivated by recent theoretical insights suggesting that interference between canaries contributes to weaker leakage estimates compared to multi-run methods, we propose to optimize canaries to be both highly detectable and minimally interfering. Our approach combines a greedy initialization based on influence functions with a bilevel optimization procedure that maximizes distinguishability while promoting diversity in embedding space, enabling the use of computationally efficient bilevel algorithms. Experiments show that our method achieves stronger privacy leakage estimates at a lower computational cost than existing canary crafting approaches.

---

### It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty

Authors: Kevin H. Guo, Chao Yan, Avinash Baidya, Katherine Brown, Xiang Gao, Juming Xiong, Zhijun Yin, Bradley A. Malin
Published: 2026-05-26
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.27288v1

Large language models (LLMs) are known to abandon their initial stance to conform to user pushback. While prior research largely attributes this behavior to sycophancy learned during reinforcement learning from human feedback, we hypothesize that conformity is also driven by a model's epistemic uncertainty at inference time. In this paper, we introduce MUSE, a two-stage evaluation framework to disentangle the mechanisms driving LLM conformity. Specifically, MUSE maps a model's epistemic uncertainty in responding to a query against its likelihood to yield to user pushback in a subsequent turn. We demonstrate that the mechanisms driving conformity extend beyond sycophancy alone. Specifically, we characterize two distinct factors that jointly drive conformity: sycophantic conformity, where a model aligns with user pushback even with absolute certainty in its initial response, and uncertainty-driven conformity, where a model's likelihood for conformity increases alongside its uncertainty. Furthermore, we conduct ablation studies to demonstrate that both sycophantic conformity and uncertainty-driven conformity grow with 1) the LLM's perceived expertise of the user and 2) the plausibility of the user's suggestions. More broadly, MUSE informs more targeted intervention strategies by distinguishing alignment-induced sycophancy and training-corpora-driven uncertainty.

---

### A Dynamic Programming Framework for Discovering Count and Values of Multilevel Image Thresholding

Authors: Eslam Hegazy, Mohamed Gabr
Published: 2026-05-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.27287v1

Multilevel Image thresholding is an important preprocessing algorithm in computer vision applications nowadays. Since most common thresholding methods take the desired count of thresholds as input by the user, thresholding methods that automatically determines a suitable count of thresholds from the input image itself are advantageous. In this article, a novel thresholding method based on a dynamic programming algorithm and a modification of Minimum Error Thresholding (MET) criterion is thoroughly presented. An empirical statistical study is performed to pinpoint why this proposed method is superior. Moreover, an extended comparison between this proposed method and other state-of-the-art methods is performed on a comprehensive set of natural, satellite and medical test images. The numerical results show that the proposed MET-DP method takes much less time than traditional dynamic programming thresholding methods when the number of thresholds is high. The proposed method can detect a suitable count of thresholds for most of tested images of different types. However, traditional methods that take the count of thresholds as input produce thresholded images of higher structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) values than MET-DP. Source code can be found on https://w3id.org/met-dp/article1-code

---

### Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling

Authors: Yiding Liu, Yifan Hu, Hongjie Xia, Peiyuan Liu, Hongzhou Chen, Xilin Dai, Zewei Dong, Jiang-Ming Yang
Published: 2026-05-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.27286v2

Time series foundation models (TSFMs) are transforming the forecasting paradigm through large-scale cross-domain pretraining. However, most existing TSFMs remain univariate, and recent efforts to enable cross-variate modeling still operate directly within the raw variate space. This design introduces fundamental limitations in semantic alignment and relational expressivity. Specifically, raw-space group mixing lacks a dedicated mechanism to align heterogeneous physical quantities, while standard non-negative attention fails to capture the complex synergistic and antagonistic interactions ubiquitous in real-world systems. To address these challenges, we propose Falcon-X, decouples variates from the raw space and maps them into a unified latent prototype space. Falcon-X employs a Unified Prototype Diff-Attention mechanism that explicitly evaluates both positive and negative semantic affinities to explicitly align heterogeneous variates. Cross-variate interactions are then efficiently performed within this shared space via Latent Entity Attention, naturally facilitating zero-shot structural transfer. Finally, a Variate Reassembly Router robustly reconstructs variate-specific trajectories via a request-and-dispatch mechanism. Extensive evaluations on the GIFT-Eval and fev-bench benchmarks demonstrate that Falcon-X achieves excellent forecasting performance, offering a principled and scalable paradigm for complex multivariate environments. Falcon-X is publicly released to support future research.

---