# Research Papers — 2026-05 · bundle page 118 of 326 > Full-text markdown of papers #5851–5900 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/118 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/117.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/119.md) ### SMDD-Bench: Can LLMs Solve Real-World Small Molecule Drug Design Tasks? Authors: Kevin Han, Renfei Zhang, Kathy Wei, Hamed Mahdavi, Niloofar Mireshghallah, Amir Barati Farimani Published: 2026-05-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.21740v2 LLM agents have incredible potential for scientific discovery applications. However, the performance of LLM agents on real-world, small molecule drug design (SMDD) tasks across diverse chemistries and targets is unclear. Current evaluation methods are either ad hoc, too simple for real-world discovery, limited in scale, or restricted to single-turn question answering. In effort to standardize the evaluation of LLM agents on small molecule design, we introduce SMDD-Bench, a challenging, multi-turn, long-horizon agentic benchmark consisting of 502 guaranteed-solvable task instances spanning 5 task types: 2D Pharmacophore Identification, Interaction Point Discovery, Scaffold Hopping, Lead Optimization, and Fragment Assembly. SMDD-Bench tasks span a wide region of chemical space and involve 102 unique protein targets. Completely solving the benchmark would require having strong chemical and biological reasoning and 3D intuition, understanding specialized tool use, and displaying planning expertise over a limited number of oracle calls. We benchmark 7 frontier open and closed source LLMs and find even the most performant LLM, GPT5.4, solves only 40.2\% of tasks. We hope SMDD-Bench provides a standardized testbed to invigorate the field towards training and evaluating LLM agents for fully autonomous computational drug design. We host a public leaderboard at smddbench.com . --- ### AttuneBench: A Conversation-Based Benchmark for LLM Emotional Intelligence Authors: Kate M. Lubrano, Faisal Sayed, Ankita Rathod, Akshansh, Craver Corbyn Thomas-Smith, Mark E. Whiting, Karina Nguyen Published: 2026-05-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.21739v2 Emotional intelligence (EI), the ability to perceive, understand, and respond appropriately to others' emotional states, is central to human communication, and increasingly important to assess as LLMs assume conversational roles in everyday life. Existing EI benchmarks rely on synthetic prompts, single-turn cases, or third-party annotation. These approaches do not directly measure how models infer and respond to a participant's emotional state over the course of a real conversation. We introduce AttuneBench, a benchmark grounded in 200 genuine multi-turn human-model conversations in which participants conversed with anonymized LLMs and provided turn-by-turn annotations of their emotional state, the model's behavior, and their preferred responses. Across 11 evaluated models, we find that model rankings on emotion recognition, behavioral classification, preference prediction, and judged response quality are largely independent, indicating that emotionally intelligent behavior decomposes into separable capabilities. Preference alignment and response-quality judgments are substantially more model-discriminating than emotion-label accuracy. These results indicate that emotionally intelligent behavior requires predicting what kind of response a specific user wants in context, a distinction that aggregate scoring can obscure and that single-turn or synthetic formats cannot directly capture across turns. AttuneBench provides a framework for assessing each of these capabilities and for diagnosing model-specific strengths and failure modes in emotionally salient conversation. --- ### Support-aware offline policy selection for advertising marketplaces Authors: Prashant Shekhar, Caroline Howard Published: 2026-05-20 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.21736v1 Logged advertising auctions make offline reserve-price evaluation attractive but risky. Replay tables can identify policies with large apparent yield gains, yet they can also hide weak threshold support, multiple-comparison effects, subgroup harm, and bidder-response uncertainty. Existing replay and off-policy evaluation methods estimate or rank policy values, but they do not directly answer the operational question of whether the available evidence is strong enough to justify validation. This paper develops a support-aware offline decision framework for reserve-policy selection. Rather than outputting a single point-estimate winner, the framework converts logged evidence into a conservative decision object consisting of certified policies, statistically dominated alternatives, and unresolved candidates requiring further validation. The main theoretical result gives a unified finite-catalog guarantee showing that, under simultaneous uncertainty control and conservative support gates, the framework preserves the best gate-passing policy while eliminating only policies with certified regret. Supporting results characterize support-localized replay generalization, establish information-theoretic threshold-resolution limits, and quantify when heterogeneous bidder response can overturn localized replay rankings. Experiments on iPinYou real-time-bidding logs show that the leading reserve rule achieves a 47.66% replay lift in season two, a 40.71% simultaneous lower-bound lift, and a 43.87% frozen out-of-time replay lift in season three. The framework reduces a 19-policy catalog to a two-policy validation shortlist while certifying non-harm across 44 advertiser, exchange, and region segments. The results support the central claim that offline reserve-policy evaluation should produce certified validation decisions rather than point-estimate rankings alone. --- ### I-SAFE: Wasserstein Coherence Metrics for Structural Auditing of Scientific AI Models Authors: Barbara Tarantino, Gennaro Auricchio, Paolo Giudici Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21731v2 Deep learning models are increasingly used in scientific prediction tasks where strong benchmark performance is often interpreted as evidence of scientifically meaningful behavior. This interpretation is fragile, as models may exploit shortcut features, dataset-specific regularities, or distributional biases that are predictive on held-out data but not aligned with domain-relevant structure. To address this limitation, we introduce the \textsc{I-SAFE} (Interventional Secure, Accurate, Fair and Explainable) framework, a post-hoc distributional auditing framework for scientific AI models centered on the Wasserstein Coherence Metric (WCM). Given a trained black-box predictor and an external structural prior encoding domain knowledge about task-relevant input structure, \textsc{I-SAFE} evaluates raw model outputs under structurally guided perturbations of the input. The proposed audit measures output-distribution coherence through three complementary metrics: a Quantile-Based Metric (QBM) for location-level coherence, the WCM for ordinal coherence, and a translation-invariant WCM variant for shape coherence. We instantiate \textsc{I-SAFE} on drug--target interaction (DTI) prediction using the Davis kinase benchmark, KLIFS (Kinase--Ligand Interaction Fingerprints and Structures) binding-pocket annotations, and three sequence-based DTI models: DeepConvDTI, DeepDTA, and TAPB. Although the models operate in a comparable predictive regime, \textsc{I-SAFE} reveals substantially different distributional response profiles, a distinction invisible to accuracy-based evaluation. The framework is model-agnostic and applicable to any domain where inputs admit a structured decomposition and an external prior is available. --- ### BEiTScore: Reference-free Image Captioning Evaluation with an Efficient Cross-Encoder Model Authors: Gonçalo Gomes, Bruno Martins, Chrysoula Zerva Published: 2026-05-20 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.21728v1 Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating long-form and context-rich descriptions. State-of-the-art evaluation metrics involve extensive computational costs associated with the use of Large Language Models (LLMs) as judges, or instead suffer from the limitations of standard CLIP-based encoders, such as strict token limits, lack of fine-grained sensitivity, or lack of compositional generalization by treating captions as ``bags-of-words.'' We propose a new learned metric that tackles the aforementioned challenges, based on a lightweight cross-encoder that is initialized from a visual question-answering model checkpoint, balancing a strong weight initialization with computational efficiency. Our training scheme uses a carefully assembled data mixture for supervised learning, featuring adversarial LLM-based data augmentations to enhance model sensitivity to fine-grained visual-linguistic errors. We also introduce a new benchmark designed to assess detailed captioning evaluation across diverse scenarios. Experimental results demonstrate that the proposed metric achieves state-of-the-art performance while maintaining the efficiency required for large-scale benchmarking, quality-aware decoding, or reward guidance. --- ### Probabilistic Attribution For Large Language Models Authors: Shilpika Shilpika, Carlo Graziani, Bethany Lusch, Venkatram Vishwanath, Michael E. Papka Published: 2026-05-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.21726v1 The generative nature of Large Language Models (LLMs) is reflected in the conditional probabilities they compute to sample each response token given the previous tokens. These probabilities encode the distributional structure that the model learns in training and exploits in inference. In this work, we use these probabilities to situate LLMs within the mathematical theory of stochastic processes. We use this framework to design a model-agnostic probabilistic token attribution measure, using Bayes rule to invert the next-token log-probabilities so as to capture the models internal representation of the distribution over token sequences. The representation is independent of the models computational structure. This representation yields the conditional probability of the response given the prompt, and of the response given the prompt with a token marginalized away. Our attribution score is the log of the ratio of these probabilities. We further compute the entropies of a single prompts token distributions, conditioned on the remaining context. The interplay between entropy and attribution score sheds light on LLM behavior. We evaluate 8 models across 7 prompts and investigate anomalies, token sensitivity, response stability, model stability, and training convergence, thereby improving interpretability and guiding users to focus on uncertain or unstable parts of the generation. --- ### TBP-mHC: full expressivity for manifold-constrained hyper connections through transportation polytopes Authors: Anton Lyubinin Published: 2026-05-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.21724v1 Hyper-Connections (HC) improve residual networks by introducing learnable mixing across multiple residual streams, but unconstrained mixing leads to training instability. Manifold-Constrained Hyper-Connections (mHC) address this by enforcing approximate double stochasticity via Sinkhorn normalization, while mHC-lite ensures exact constraints through convex combinations of permutation matrices at the cost of factorial complexity. KromHC reduces this cost using Kronecker-product parameterizations, but restricts the mixing matrices to a structured submanifold of the Birkhoff polytope . We propose Transportation Birkhoff Polytope (TBP) parameterizations and their Recursive variants (RTBP), which construct exactly doubly stochastic mixing matrices with $(n-1)^2$ degrees of freedom. Our approach avoids iterative normalization and combinatorial explosion while preserving full expressivity of the Birkhoff polytope. Empirical results on language model pre-training' demonstrate competitive performance with improved stability and scalability. --- ### Learning Altruistic Collaboration in Heterogeneous Multi-Team Systems Authors: Riwa Karam, Ruoyu Lin, Brooks A. Butler, Magnus Egerstedt Published: 2026-05-20 Categories: cs.RO, cs.AI, cs.MA, eess.SY arXiv: https://arxiv.org/abs/2605.21723v1 This paper studies heterogeneous multi-team collaboration through dynamic robot allocation, where robots are treated as transferable resources. Leveraging Hamilton's rule from ecology as an altruistic decision-making mechanism, we propose a multi-team collaborative resource allocation framework with heterogeneous capabilities, transfer costs, and capability-dependent contributions. The resulting allocation problem is combinatorial and is shown to be NP-hard. To address scalability, we develop a graph neural network policy under centralized training and decentralized execution that approximates the altruistic allocations based on Hamilton's rule. The model operates over the team interaction graph and predicts robot-level transfer decisions and next robot-to-team assignments. The proposed approach is validated in a firefighting scenario through simulations and experiments, demonstrating that the learned policy achieves near-optimal performance while scaling to larger systems. --- ### MetaDNS: Enhancing Exploration in Discrete Neural Samplers via Well-Tempered Metadynamics Authors: Xiaochen Du, Juno Nam, Jaemoo Choi, Wei Guo, Sathya Edamadaka, Junyi Sha, Elton Pan, Yongxin Chen, Molei Tao, Rafael Gómez-Bombarelli Published: 2026-05-20 Categories: cond-mat.stat-mech, cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2605.21722v1 Sampling from discrete distributions with multiple modes and energy barriers is fundamental to machine learning and computational physics. Recent discrete neural samplers like MDNS suffer from mode collapse and fail to sample high-energy barrier regions between modes, which is critical for free energy estimation and understanding phase transitions. We propose Metadynamics Discrete Neural Sampler (MetaDNS), a general framework integrating well-tempered metadynamics into discrete diffusion or autoregressive samplers. By maintaining an adaptive, history-dependent bias potential along selected low-dimensional coordinates, MetaDNS forces exploration of previously inaccessible regions, enabling free energy reconstruction infeasible with standard neural samplers due to a lack of high-energy samples. On challenging low-temperature benchmarks including Ising, Potts, and the copper-gold binary alloy, MetaDNS reproduces the thermodynamic distribution. Compared to MCMC-based metadynamics, MetaDNS also achieves comparable exploration requiring fewer bias deposition steps. --- ### AVI-HT: Adaptive Vision-IMU Fusion for 3D Hand Tracking Authors: Ziyi Kou, Ankit Kumar, Mia Huang, Taylor Niehues, Vatsal Mehta, Ergys Ristani, Li Guan Published: 2026-05-20 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2605.21714v1 We present AVI-HT, an adaptive visual-IMU fusion approach for tracking 3D hand poses by jointly modeling the egocentric image with on-glove 6-DoF IMU signals. AVI-HT achieves significantly improved accuracy and availability, particularly in hand-object interaction (HOI) scenarios involving heavy visual occlusion. Two complementary ingredients underpin its success: (1) synchronized multi-modal training data pairing on-body vision-IMU sensor streams with ground-truth 3D hand poses from a motion-capture system, and (2) a cross-sensor deep attention mechanism that adaptively modulates the trust assigned to the vision and individual IMU sensors. To evaluate AVI-HT in real-world settings, we conduct extensive experiments on our DexGloveHOI dataset that consists of 100K+ pairwise vision-IMU samples with synchronized 3D annotated poses, in which users manipulate a variety of objects during daily tasks. We compare against multiple single- and multi-modal tracking approaches under two hand models (UmeTrack, MANO). The results show that AVI-HT reduces mean keypoint error by 16.1% and its wrist-aligned variant by 24.2% over the baselines. Ablation studies further reveal the per-finger contribution of IMU sensors across activity types, and the model's sensitivity to IMU noise and temporal misalignment in vision-IMU fusion. --- ### Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews Authors: André V. Duarte, Brian Tufts, Aditya Oke, Fei Fang, Arlindo L. Oliveira, Lei Li Published: 2026-05-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.21713v1 How can we distinguish whether a peer review was written by a human or generated by an AI model? We argue that, in this setting, authorship should not be attributed solely from the textual features of a review, but also from the ideas, judgments, and claims it expresses. To this end, we propose Sem-Detect, an authorship detection method for peer reviews that operationalizes this principle by combining textual features with claim-level semantic analysis. Sem-Detect compares a target review against multiple AI-generated reviews of the same paper, leveraging the observation that different AI models tend to converge on similar points, while human reviewers introduce more unique and diverse ones. As a result, Sem-Detect is able to distinguish fully AI reviews from authentic human-written ones, including those that have been refined using an LLM but still reflect human judgment. Across a dataset of over 20,000 peer reviews from ICLR and NeurIPS conferences, Sem-Detect improves over the strongest baseline by 25.5% in TPR@0.1% FPR in the binary setting. Moreover, in the three-class scenario, we empirically show that LLM refinement preserves the semantic signals of human reviews, which remain distinct from the patterns exhibited by fully AI-generated text; as a result, fewer than 3.5% of LLM-refined human reviews are misclassified as AI-generated. --- ### Broadening Access to Transportation Safety Data with Generative AI: A Schema-Grounded Framework for Spatial Natural Language Queries Authors: Mahdi Azhdari, Eric J. Gonzales Published: 2026-05-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.21712v1 Transportation safety analysis requires integrating crash records, roadway attributes, and geospatial data through GIS-based workflows, but access remains uneven across agencies and community stakeholders. Technical prerequisites create a gap between analytical tools central to safety planning and the practitioners able to use them. Local agencies, school committees, and residents may have safety concerns but limited capacity to retrieve, filter, map, and analyze relevant data. Generative AI offers a way to narrow this divide, but its public-sector use raises questions about reliability, reproducibility, and governance. This paper presents a schema-grounded natural language interface for transportation safety analysis, using a large language model (LLM) to interpret user intent while preserving deterministic, reviewable execution against an authoritative database. User queries are translated into structured semantic frames, validated by a rule-based layer, compiled into a typed directed acyclic graph of spatial operations, and executed against a PostGIS database. This bounded design separates language interpretation from deterministic execution, keeping results reproducible and schema-grounded while removing access barriers. The framework is evaluated using a statewide Massachusetts transportation safety database integrating crash records, roadway attributes, and geospatial layers including schools, bus stops, crosswalks, and municipal boundaries. All queries executed successfully; the validation layer corrects errors in 29% of evaluation queries, reflecting the gap between flexible natural language and strict schema-grounded requirements. The results suggest that combining natural language accessibility with deterministic execution is a practical direction for broadening access to transportation safety data, with implications for trustworthy AI in public-sector planning. --- ### Zero-shot adaptation to order book dynamics Authors: Arip Asadulaev Published: 2026-05-20 Categories: cs.CE, cs.LG arXiv: https://arxiv.org/abs/2605.21707v1 We describe an adaptive market-making architecture that preserves the analytical structure of the Avellaneda--Stoikov framework while introducing a successor measure-style adaptation mechanism. In our paper we keep Avellaneda--Stoikov fast Hamilton--Jacobi--Bellman structure and make it adaptive to changing market regimes and trading objectives. The central idea is to separate market dynamics from the trading objective. The market state determines a low-dimensional set of Avellaneda--Stoikov parameters, while recent realized rewards determine a low-dimensional objective vector. The HJB forward map then converts this objective into optimal bid and ask quotes through a scalarization of future reward features. --- ### Latent-space Attacks for Refusal Evasion in Language Models Authors: Giorgio Piras, Raffaele Mura, Fabio Brau, Maura Pintor, Luca Oneto, Fabio Roli, Battista Biggio Published: 2026-05-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.21706v2 Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representations. Existing methods do so by ablating a refusal direction from model activations, aiming to remove refusal from the model's residual stream. Despite their empirical success, these methods lack a principled account of the latent-space transformation they induce and why it suppresses refusal. In this work, we recast refusal suppression as a latent-space evasion attack against linear probes trained to separate refused from answered prompts. Under this view, prior work's difference-in-means direction naturally defines such a probe, and its ablation is exactly a projection onto its decision boundary, i.e., a minimum-confidence evasion attack. This perspective not only explains the empirical success of prior work but also admits a key limitation: evasion stops at the decision boundary, motivating the need to push representations further into the compliant region, i.e., where the model answers. We leverage this by proposing a Controlled Latent-space Evasion attack that projects representations past the boundary with an optimized confidence. We achieve state-of-the-art attack success rate across 15 instruction-tuned, multimodal, and reasoning models, outperforming existing refusal-ablation baselines and specialized jailbreak attacks. --- ### X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation Authors: Sharath Turuvekere Sreenivas, Adithyakrishna Venkatesh Hanasoge, Mingyu Yang, Ali Taghibakhshi, Saurav Muralidharan, Ashwath Aithal, Pavlo Molchanov Published: 2026-05-20 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.21699v1 Cross-tokenizer knowledge distillation allows a student model to learn from teachers with incompatible vocabularies. Prior work operates on hidden states or logits; the latter is preferred as a drop-in replacement requiring no auxiliary components. Logit-based methods either use only the correct-token probability, missing the full 'dark knowledge' in the teacher's distribution, or operate on the full output distribution, relying on strict token partitioning and/or unprincipled heuristic ranking. We identify two key shortcomings of full-distribution, logit-based methods: (i) an uncommon-token failure, where critical tokens fall into the unmatched subset (e.g., Llama's 1100 multi-digit numerals under digit-splitting Qwen supervision) and are suppressed during training, reducing GSM8k from 12.89 to 2.56 compared to same-tokenizer KD from a weaker teacher; and (ii) over-conservative matching, where strict 1-to-1 matching excludes near-equivalent tokens across surface forms. These failures require distinct remedies: eliminating the partition when critical tokens are misaligned, and refining it when alignment is reliable. We propose X-Token, an approach with two complementary loss formulations targeting these issues. P-KL removes partitioning and aligns the student's distribution with the teacher's via a sparse projection matrix W (initialized from tokenizer-level string rules) to address the uncommon-token failure. H-KL retains the hybrid form while relaxing matching to align each student token with its top-ranked teacher mapping under W. Both objectives share W and extend naturally to multiple teachers. Empirically, on Llama-3.2-1B, X-Token outperforms the current state of the art GOLD by +3.82 average points with a Qwen3-4B teacher and by +0.5 with a Phi-4-Mini teacher. Further, a two-teacher setup (Phi-4-mini + Llama-3B) improves over single-teacher distillation by +1.3 points. --- ### The Impact of AI Usage and Informativeness on Skill Development in Logical Reasoning Authors: Shang Wu, Hongyu Yao, Catarina Belem, Shuyuan Fu, Mark Steyvers, Padhraic Smyth Published: 2026-05-20 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2605.21695v1 Artificial intelligence (AI) is being increasingly integrated into human problem-solving, yet its effects on individual skill development remain unclear. We examine how both AI usage and informativeness can shape learning in the context of a controlled logical reasoning task with on-demand access to AI assistance. We find that greater AI usage is associated with weaker skill development: heavy AI users underperform relative to comparable peers, whereas light AI users perform similarly to matched users who do not use AI. We also find in our study that these patterns are mediated by AI informativeness. Low-information AI neither improves immediate performance nor preserves performance after AI assistance is removed, and is linked to weaker learning overall. On the other hand, high-information AI was found to improve short-run performance without reducing post-AI outcomes on average in our experiments, but with heterogeneous effects. Our findings in general suggest that AI can, depending on context, either complement human skill development by amplifying independent reasoning or can act as a substitute that undermines such reasoning, with the implication that regulating AI access and usage will be important for promoting skill development in the presence of AI assistance. --- ### PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents Authors: Sidnei Barbieri, Ágney Lopes Roth Ferraz, Lourenço Alves Pereira Júnior Published: 2026-05-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2605.21694v2 Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender must decide which model outputs may change the system state, which outputs must be rejected, and how failures should be recorded. We present PocketAgents, a manifest-driven library of autonomous defense agents. Each agent is installed as three data files: a manifest, a prompt, and a runtime context. The shared runtime gives the agent bounded telemetry access and accepts only typed reports whose requested action appears in the manifest. We implemented PocketAgents on top of Perry, a cyber-deception testbed, and evaluated two agents for the Command and Control and Exfiltration tactics in 18 closed-loop trials of a DarkSide-inspired attack on a small enterprise topology. Thirteen trials produced validated network-block actions and contained the attack; four failed schema validation; one produced a valid no-action decision. The experiments show that a typed boundary makes LLM-driven defense measurable, extensible, and attributable. --- ### PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents Authors: Sidnei Barbieri, Ágney Lopes Roth Ferraz, Lourenço Alves Pereira Júnior Published: 2026-05-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2605.21694v1 Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender must decide which model outputs may change the system state, which outputs must be rejected, and how failures should be recorded. We present PocketAgents, a manifest-driven library of autonomous defense agents. Each agent is installed as three data files: a manifest, a prompt, and a runtime context. The shared runtime gives the agent bounded telemetry access and accepts only typed reports whose requested action appears in the manifest. We implemented PocketAgents on top of a cyber arena (Perry), a cyber-deception testbed, and evaluated two agents, Command and Control and Exfiltration, in 18 closed-loop trials of a DarkSide-inspired attack on a small enterprise topology. Thirteen trials produced validated network-block actions and contained the attack; four failed schema validation; one produced a valid no-action decision. The experiments show that a typed boundary makes LLM-driven defense measurable, extensible, and attributable. --- ### Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective Authors: David Perera, Victor Moura, Lais Isabelle Alves dos Santos, Michel F. C. Haddad, Flavio Figueiredo Published: 2026-05-20 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.21692v1 Characterizing precisely the asymptotic generalization error of neural networks using parameters that can be estimated efficiently is a crucial problem in machine learning, which relies heavily on heuristics and practitioners' intuition to make key design choices. In order to mitigate this issue, we introduce the Representation Gap, a metric closely related to the generalization error, but admitting better-behaved asymptotic dynamics. Focusing on equivariant diffusion models and leveraging results from optimal quantization and point-process theory, we derive a precise asymptotic equivalent of the Representation Gap and show that it is governed by a single parameter, the \textit{intrinsic dimension} of the task, which is easy to interpret, efficient to estimate, and can be linked to the equivariances of common neural network architectures. We show that this asymptotic dynamic also extends to a broader range of tasks and training algorithms. Finally, we demonstrate empirically that our asymptotic law and intrinsic dimension estimation are accurate on a wide range of synthetic datasets, where these quantities are known, as well as on more realistic datasets, where we obtain results consistent with the related literature. --- ### Investigating Concept Alignment Using Implausible Category Members Authors: Sunayana Rane, Brenden M. Lake, Thomas L. Griffiths Published: 2026-05-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.21683v1 Developing AI systems with a human-like understanding of everyday concepts is a key step towards developing safe, reliable systems whose behavior makes sense to humans. When probing concept understanding, asking questions about plausible category members (e.g., "Is a car a vehicle?") is likely to recall patterns in the model's vast training data. We pursue an alternative strategy, characterizing the boundaries of conceptual categories by asking about implausible category members (e.g., "Is an olive a vehicle?") to probe the kind of concept-level knowledge we take for granted in fellow humans. We characterize concept boundaries for a set of fundamental concepts by studying AI systems' assignments of objects to superordinate categories from a classic psychological study by Rosch and Mervis, as well as their assignments of the same objects to mismatched superordinate categories. We compare these assignments to those made by human participants on the full range of within-category and cross-category assignment tasks. Our results reveal a range of concepts for which which models differ in meaningful and surprising ways from humans, including treating "words" as belonging to categories like "vehicles" and "clothing," identifying several "vegetable" category members as "fruit," and assigning exemplars from non-weapon categories to the "weapons" category. We also demonstrate how these instances of concept misalignment translate into problematic downstream behavior with implications for AI safety. --- ### HyperBench: Standardizing and Scaling Synthetic Evaluation for Hyperspectral Super-Resolution Authors: Ritik Shah, Marco F. Duarte Published: 2026-05-20 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2605.21671v1 Hyperspectral super-resolution (HSR) reconstructs a high-spatial-resolution hyperspectral image by fusing a low-resolution hyperspectral image (LR-HSI) with a high-resolution multispectral image (HR-MSI). In the absence of real-world paired data, HSR methods are evaluated almost exclusively on synthetic experiments derived from hyperspectral datasets through Wald's protocol. Despite the protocol's widespread adoption, its practical implementation varies markedly across research works, typically relying on a single (usually Gaussian) or very few point spread functions (PSFs), one or two spectral response functions (SRFs), and a couple of spatial downsampling factors. As a result, reported performance figures are difficult to compare across the literature, in addition to being often difficult to reproduce; furthermore, they may not generalize across realistic sensing conditions. We introduce HyperBench, a unified and extensible framework that standardizes synthetic experimentation for HSR. HyperBench supports diverse degradation configurations spanning ten PSFs, four SRFs derived from operational multispectral sensors, configurable spatial downsampling factors, and matched additive white Gaussian noise; its goal is to automate large-scale evaluation and structured logging. By decoupling model development from experimental design, the framework enables reproducible, apples-to-apples cross-method comparison with minimal friction. We use HyperBench to evaluate six recently proposed HSR methods across a 70-configuration sweep on four widely used hyperspectral scenes and observe that the inter-method PSNR spread widens from approximately 5 dB on the easiest PSF to over 13 dB on the hardest - a fragility that is structurally invisible to the prevailing single-configuration evaluation protocol. HyperBench code is available at https://github.com/ritikgshah/HyperBench . --- ### MRecover: A Conditional Generative Model for Recovering Motion-Corrupted MR images Using AI Generated Contrast Authors: Jinghang Li, Tales Santini, Courtney Clark, Bruno de Almeida, Cong Chu, Salem Alkhateeb, Andrea Sajewski, Jacob Berardinelli, Hecheng Jin, Tobias Campos, Jeremy J. Berardo, Joseph Mettenburg et al. Published: 2026-05-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.21669v1 Hippocampal subfield segmentation requires high-resolution T2w turbo spin echo (TSE) MRI, yet this sequence is susceptible to motion artifacts, leading to substantial data loss. We developed a conditional generative model (MRecover) that synthesizes routinely acquired T1w images to create TSE images with autoregressive slice conditioning for volumetric consistency. Trained on 7T MRI data (n=577), the model achieved high in-domain fidelity (n=148, SSIM=0.84, FSIM=0.94) and generalized well to out-of-domain 3T data: subfield volumes from synthesized and the as-acquired images closely matched: (n=416, r=0.87-0.97) and yielded 31.8% more analyzable subjects in the motion-affected ADNI3 dataset after quality control (593 vs 450). The synthesized images also achieved larger effect sizes due to increasing the sample size for diagnostic group differences in hippocampal subfield atrophy (whole hippocampus $ε^2$= 0.121-0.100 vs. 0.086-0.062, left-right hemispheres). Project page: https://jinghangli98.github.io/MRecover/ --- ### Planning, Scheduling, and Behavior in EV Charging Systems: A Critical Survey and Trilemma Framework Authors: Peiyan Xiao, Yuheng Li, Ayan Mukhopadhyay, Sai Krishna Ghanta, Sabur Baidya, Yanhai Xiong Published: 2026-05-20 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2605.21665v1 The rapid growth of electric vehicles is shifting the main constraint on transport electrification from vehicle adoption to the deployment and operation of charging infrastructure. Charging-network design requires decisions across three interdependent layers: Planning, which determines where and how much infrastructure to build; Scheduling, which governs charging dispatch, pricing, and grid interaction; and Behavior, which captures how users choose stations, charging times, and charging durations. Existing studies have advanced each layer substantially, but the literature remains fragmented, and cross-layer interactions are often treated through simplifying assumptions. This survey develops a three-layer Planning-Scheduling-Behavior (PSB) framework to organize EV charging research according to decision horizon, actor objective, and coupling structure. We further identify a fidelity-tractability tradeoff, termed the PSB trilemma: each layer is computationally difficult in isolation, and realistic integration across layers generally requires reducing the fidelity of at least one layer. Reviewing the three pairwise-coupling literatures - Planning-Scheduling, Scheduling-Behavior, and Planning-Behavior - we show that the omitted third layer is typically fixed exogenously or represented by a static aggregate surrogate. These simplifications enable tractability but impose distinct costs: they can obscure long-term investment feedback, temporal grid and emissions dynamics, or heterogeneous user response and equity outcomes. Building on this diagnosis, we identify open challenges in emerging charging technologies, behavioral incentives, equity metrics, and city-scale learning-based methods that balance fidelity, interpretability, and policy relevance. --- ### Hierarchical Variational Policies for Reward-Guided Diffusion Authors: Kushagra Pandey, Farrin Marouf Sofian, Jan Niklas Groeneveld, Felix Draxler, Stephan Mandt Published: 2026-05-20 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.21661v1 Adapting pretrained diffusion models to downstream objectives such as inverse problems often requires expensive test-time guidance or optimization. We propose a principled framework for generating high-quality reward-aligned samples at substantially reduced inference cost. Our approach formulates test-time adaptation as a hierarchical variational model, where control is amortized into a lightweight yet expressive stochastic policy. This formulation naturally supports few-step diffusion sampling: large step sizes enable fast inference, while the learned policy maintains sample quality by providing structured per-step control. The resulting fully amortized sampler achieves a strong quality--speed tradeoff, matching or exceeding recent test-time scaling baselines while requiring significantly less compute. For example, on 4x super-resolution, our method achieves better perceptual quality with more than 5x faster inference compared to the best-performing baseline. We further extend our approach to a semi-amortized regime that combines cheap amortized proposals with limited test-time optimization, achieving state-of-the-art perceptual quality across several challenging inverse problems. --- ### Value-Gradient Hypothesis of RL for LLMs Authors: Arip Asadulaev, Daniil Ognev, Karim Salta, Martin Takac Published: 2026-05-20 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.21654v1 Reinforcement learning substantially improves pretrained language models, but it remains understudied why critic-free methods such as PPO and GRPO work as well as they do, and when they should provide the largest gains. We develop a value-gradient perspective of critic-free RL for LLM post-training. First, under a differentiable rollout and additive-noise parameterization, we show that the actor update is value-gradient-like in expectation: the backward pass propagates costates whose conditional expectation equals the value gradient. Second, for discrete transformer policies, we show that autodifferentiation through attention produces empirical costates that approximate this value signal, with an error controlled by the sampling gap and policy entropy. These results motivate a decomposition of RL impact into value gradient signal and reachable reward headroom, yielding a criterion for when RL should be most effective along a pretraining trajectory. --- ### Amplifying, Not Learning: The Price of Out-of-Distribution Generalization in AI-Text Detection Authors: Alexander Smirnov Published: 2026-05-20 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.21653v2 AI-text detectors gate decisions in education, hiring, and publishing, yet they flag the most fluent, formal human writing as machine-generated: they rate the median formal-native human essay as 99.5% likely AI while clearing genuine high-temperature AI at 10.5%. Deployed detectors share it (chatgpt-detector-roberta flags 56% of formal essays at a 1% false-alarm rate). This is not a calibration bug but the signature of one mechanism: a fine-tuned detector does not learn an AI-versus-human boundary, it amplifies an inherited typicality axis (predictability under a language model) that pre-exists fine-tuning, rescaling it rather than constructing one. Decomposing the detector into this inherited reading and a fine-tuned residual, the inherited part carries the bulk of cross-generator transfer and produces the over-flagging of formal humans, while the residual is generator-specific and does not transfer; a frozen-representation probe fit on ~25 labels per class matches the fully fine-tuned detector on unseen generators (cross-generator AUROC 0.893 vs 0.831). This yields a no-go: because the axis that transfers is the axis that over-flags, no training objective, threshold, concept-erasure, or ensemble we test removes the harm while preserving cross-generator detection, across three architectures, fine-tuned decoders, and zero-shot perplexity detectors. A closed-form, training-free operator relocates and diagnoses the bias (reviving a dead deployed detector, true-positive rate 0 to 0.904 at a 1% false-alarm rate) but, consistent with the no-go, is AUROC-neutral on cross-generator detection: it moves the bias, it cannot erase it. The mechanism is not specific to English prose: the over-flag and the decomposition replicate in Chinese and in code. Detector unfairness is a predictable, structural property of the detection paradigm, the price of out-of-distribution generalization. --- ### Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction Authors: Alexander Smirnov Published: 2026-05-20 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.21653v1 AI text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary. On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures (86-106% of the fine-tuned discrimination ceiling: on RoBERTa-base, raw projection exceeds fine-tuning); on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested. The same axis inverts on non-native ESL writing (AUROC 0.06-0.20) -- a falsifiable prediction unique to the typicality reading. A 24-example frozen probe matches full fine-tuning (0.900 vs 0.895). A closed-form Jacobian predictor parameterises axis-manipulating interventions with R^2 = 1.000 universal, lifts ELECTRA-CE deployment TPR from 0.000 to 0.904 at FPR = 1%, and transfers to three independently-trained third-party RoBERTa detectors at 16/16 oracle-equivalence (57% NYT-FPR reduction on the OpenAI detector). Scope: encoder family; mechanism magnitude HC3-anchored; population-level shared axis with per-text mechanisms varying across architectures. Three operationally distinct probes -- text-surface caps_rate residualisation, geometric signed-epsilon ablation, closed-form text-pair predictor -- agree at cos 0.74/0.81/1.00 across three architectures, confirming observer-invariance. Under matched-TPR-0.90 evaluation, the published intervention zoo (CC, dealign-f2c) is calibration-equivalent across 27 cells (|Delta AUROC| <= 0.0081), and >= 97% of the LoRA->full-FT bias gap on ELECTRA is calibration shift, not learned representation -- the central claim's prediction confirmed. --- ### Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming Authors: Yue Zhou, Erxuan Wu, Yikang Sun, Hongjoo Lee, Yuan Bi, Huixiong Xu, Nassir Navab, Zhongliang Jiang Published: 2026-05-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.21652v2 Vision-Language Models (VLMs) have significantly advanced medical visual question answering, yet their performance in ultrasound remains suboptimal. In clinical practice, sonographers explicitly focus on lesion regions to formulate reports, though diagnostic interpretations sometimes vary due to inherent subjectivity. However, existing VLMs are not explicitly structured to interactively zoom into lesions prior to diagnosis; moreover, they typically treat annotations as unbiased ground truths, failing to account for their inherent subjectivity and ambiguity. In this paper, we propose a framework specifically designed to consider the sonographer's cognitive workflow. We first introduce a structured Zoom-then-Diagnose paradigm, which replicates the interactive search process to enable lesion-focused reasoning. Furthermore, within the Group Relative Policy Optimization (GRPO) framework, we introduce an uncertainty-aware reward derived from stochastic group-wise rollouts to estimate prediction consistency as a proxy for model confidence. Together, these two components encourage the model to reinforce accurate predictions on clear cases while remaining cautious under ambiguity. Experiments across liver, breast, and thyroid datasets show that our framework improves lesion localization by 39.3\%, demonstrating that our model has learned the ability to actively look closer and diagnose. --- ### EntmaxKV: Support-Aware Decoding for Entmax Attention Authors: Gonçalo Duarte, Miguel Couceiro, Marcos V. Treviso Published: 2026-05-20 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.21649v2 Long-context decoding is increasingly limited by KV-cache memory traffic as each generated token attends over a cache whose size grows linearly with context length. Existing sparse decoding methods reduce this cost by selecting subsets of tokens or pages, but are designed for softmax attention, whose dense tails make any truncation discard nonzero probability mass. In contrast, $α$-entmax produces exact zeros, turning sparse decoding from dense-tail approximation into support recovery: if the selected candidates contain the entmax support, sparse decoding remains exact. While recent entmax kernels enable efficient training, they do not address the autoregressive decoding bottleneck, where dense inference still streams the full KV cache before sparsity is known. In this work, we introduce EntmaxKV, an entmax-native sparse decoding framework that exploits sparsity before KV pages are loaded. EntmaxKV combines query-aware page scoring, support-aware candidate selection, and sparse entmax attention. We analyze truncation error through the dropped probability mass $δ$, showing that output error is controlled by $δ$ and vanishes when the entmax support is recovered. We further introduce a Gaussian-aware entmax selector that estimates the entmax threshold from lightweight page statistics, adapting the selected budget to the score distribution. Empirically, EntmaxKV drops less probability mass, retains more support tokens, and achieves lower output error than softmax-based sparse decoding at matched KV budgets. On long-context and language modeling benchmarks, it closely matches full-cache entmax while using a small fraction of the KV cache, achieving up to $2.88\times$ (softmax) and $5.5\times$ (entmax) speedup over full attention baselines as well as over $2\times$ speedup over softmax and entmax top-k at 1M context length. --- ### EntmaxKV: Support-Aware Decoding for Entmax Attention Authors: Gonçalo Duarte, Miguel Couceiro, Marcos V. Treviso Published: 2026-05-20 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.21649v1 Long-context decoding is increasingly limited by KV-cache memory traffic since each generated token attends over a cache whose size grows linearly with context length. Existing sparse decoding methods reduce this cost by selecting subsets of tokens or pages, but are designed for softmax attention, whose dense tails make any truncation discard nonzero probability mass. In contrast, $α$-entmax produces exact zeros, turning sparse decoding from dense-tail approximation into support recovery: if the selected candidates contain the entmax support, sparse decoding remains exact. While recent entmax kernels enable efficient training, they do not address the autoregressive decoding bottleneck, where dense inference still streams the full KV cache before sparsity is known. In this work, we introduce EntmaxKV, an entmax-native sparse decoding framework that exploits sparsity before KV pages are loaded. EntmaxKV combines query-aware page scoring, support-aware candidate selection, and sparse entmax attention. We analyze truncation error through the dropped probability mass $δ$, showing that output error is controlled by $δ$ and vanishes when the entmax support is recovered. We further introduce a Gaussian-aware entmax selector that estimates the entmax threshold from lightweight page statistics, adapting the selected budget to the score distribution. Empirically, EntmaxKV drops less probability mass, retains more support tokens, and achieves lower output error than softmax-based sparse decoding at matched KV budgets. On long-context and language modeling benchmarks, it closely matches full-cache entmax while using a small fraction of the KV cache, achieving up to $3.36\times$ (softmax) and $5.43\times$ (entmax) speedup over full attention baselines at 1M context length. Code available at: https://github.com/deep-spin/entmaxkv. --- ### Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos Authors: Lucas Fernandez Sarmiento Published: 2026-05-20 Categories: cs.LG, cond-mat.dis-nn, cs.NE, stat.ML arXiv: https://arxiv.org/abs/2605.21648v2 We develop a mean-field theory of dropout as a perturbation of critical signal propagation at the edge of chaos, and show that it predicts a simple, no-cost change to standard practice: \emph{front-loaded} dropout schedules cut test loss by \(18\)--\(35\%\) over constant dropout in MLPs and Vision Transformers at fixed budget. The theoretical mechanism is that dropout shifts the perfect-alignment fixed point, making the depth scale for information propagation finite even at critical initialization. We derive critical and crossover scaling laws for correlation decay and establish that smooth activations and kinked, \relu{}-like activations constitute distinct universality classes, with different critical exponents and a universal two-parameter scaling collapse in detuning and dropout strength. The distinction traces to the analytic structure of the correlation map: smooth activations admit a Taylor expansion near perfect alignment, while kinked activations develop a branch point with universal non-analyticity. As a corollary, the framework yields saturated dropout profiles under fixed budget; a regularization-reach argument then selects front-loaded schedules, with accuracy gains as a consistent secondary effect. We also discuss how the same Gaussian-kernel structure extends the theory beyond MLPs toward CNNs and residual architectures. --- ### Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations Authors: Jacek Karolczak, Jerzy Stefanowski Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21646v1 Prototype-based explanations offer an intuitive, example-based approach to support the interpretability of machine learning black box classifiers but often lack feature-level granularity. We introduce a framework that integrates feature importance at two levels to address this gap. First, for local explanations, we propose \textit{alike parts}: a method that uses feature importance scores to highlight the most relevant, shared feature subsets between a classified instance and its nearest prototype, guiding user attention. Second, we augment the global prototype selection objective function with a feature importance term to actively promote diversity in the feature attributions of the selected prototypes. Experiments on six benchmark datasets show that this augmented selection process maintains or, in some cases, increases the prediction fidelity of the surrogate model, suggesting that feature diversity does not compromise model fidelity. --- ### AOP-Wiki EMOD 3.0: Data Model Expansions and Content Evaluation Framework for Using Agentic AI to Improve Integration between AOPs and New Approach Methodologies (NAMs) Authors: Virginia K. Hench, J. Harry Caufield, Sierra A. T. Moxon, Jason M. O'Brien, Stephen W. Edwards Published: 2026-05-20 Categories: cs.AI, cs.DB arXiv: https://arxiv.org/abs/2605.21645v1 Adverse Outcome Pathways (AOP) are logic models that causally link biological mechanisms that can be measured in a lab to adverse outcomes, relevant to chemical regulatory endpoints. AOPs contextualize new approach methodologies (NAMs), in vitro and in silico methods used as alternatives to animal testing and the sequential events in an AOP serve as multi-scale models spanning biological scales. The AOP-Wiki serves as the global repository for AOPs. While the AOP-Wiki has played a central role in AOP expansion over the past decade, constraints within the current data model and application infrastructure limit the AOP-Wiki from supporting continued AOP growth and evolution. Yet, the transformative power of agentic AI has re-invigorated AOP-Wiki data modernization efforts at a time when core AOP principles can be harnessed to inform use of AI for aggregating and structuring AOP-relevant information. Seizing upon this momentum, we present AOP-Wiki EMOD 3.0, the third in a series of evidence model prototypes, which concretely demonstrates data model expansions and our vision for how the AOP-Wiki might be transformed to better serve regulatory science and emergent use of AOPs in biomedical and One Health contexts. We aim to lay a foundation to support computationally-generated AOPs and quantitative AOPs (qAOPs) by focussing on solutions for AOP-Wiki internal quality improvement, evidence structuring to enhance AOP FAIRness and AI-readiness, and improved integration between the AOP framework and NAMs to better serve next generation risk assessment. --- ### Ablate-to-Validate: Are Vision-Language Models Really Using Continuous Thought Tokens? Authors: Tianyi Zhang, Mahtab Bigverdi, Ranjay Krishna Published: 2026-05-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.21642v1 Vision-language models (VLMs) are increasingly augmented with continuous or latent non-textual tokens intended to support "visual thinking." Despite improved task accuracy, this alone does not show that models actually use these tokens for reasoning -- gains may arise from confounds such as added context length, special-token anchoring, or training-time regularization. We formalize a diagnostic principle, Ablate-to-Validate, for testing whether latent-token content is genuinely utilized, and instantiate it as the Token Replacement Test (TRT), a standardized suite of content-replacement ablations. TRT holds the prompt, image, token budget, and decoding fixed while replacing intermediate tokens with zero, random, first-repeat, or oracle alternatives, isolating whether performance depends on token content or merely on token presence. As a controlled testbed, we study relative depth reasoning with LLaVA-13B and Qwen2.5-VL-3B, training models to predict and consume continuous or discrete depth spans across multiple frozen encoders (SigLIP2, CLIP, DINOv2) and token budgets. We additionally apply TRT to three off-the-shelf visual-thinking systems (Mirage, Mull-Tokens, CoVT) on BLINK, VSP, and CV-Bench. Across all settings, accuracy gains are a misleading proxy for latent-token reasoning: VLMs retain most improvement even when token content is corrupted or replaced, revealing a persistent gap between having a latent channel and using it as an information bottleneck. We recommend TRT as a standard diagnostic alongside accuracy for any method introducing continuous thought tokens. --- ### Addressing the Synergy Gap: The Six Elements of the Design Space Authors: Tommaso Turchi, Ben Wilson, Matt Roach, Alan Dix, Alessio Malizia Published: 2026-05-20 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2605.21635v1 AI is now embedded in healthcare, finance, policy, and many other domains, yet genuine human-AI synergy - combined performance that exceeds what either party achieves alone - is uncommon. Meta-analyses show that AI assistance tends to improve human performance compared to working alone, but studies finding true synergy are scarce. We call this persistent shortfall the synergy gap. Most current work treats human-AI combination as an engineering problem and concentrates on interpretability, trust calibration, or interface design. These matter, but they cover only part of what determines whether combination works. Closing the synergy gap, we argue, requires explicit engagement with a wider design space. We map that space through six interconnected elements: sociotechnical context, decision-making frameworks, human decision participants, AI capabilities, interaction, and holistic evaluation. For each element, we describe what it covers, how it shapes the others in practice, and what it implies for design. The result is a shared vocabulary for practitioners building hybrid systems, an analytical lens for researchers studying combination patterns, and a starting point for evaluators interested in the full quality of human-AI decision-making rather than accuracy alone. --- ### VRXU-net: A Deep Learning Approach for Brain Ischemic Stroke Lesion Detection and Segmentation in T1W MRI Authors: Sayed Amir Mousavi Mobarakeh Published: 2026-05-20 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2605.21633v1 When the blood supply to the brain is obstructed by a clot, oxygen delivery to brain tissues becomes insufficient, leading to cellular necrosis. In healthcare settings, accurately identifying and delineating ischemic lesion boundaries is essential for treatment and surgical planning. However, ischemic stroke lesions vary widely in shape, size, and location, and in grayscale MRI modalities such as T1W they may resemble surrounding brain structures. This makes lesion detection and segmentation a challenging task for clinicians. This study introduces a novel VRU-Net architecture, derived from visual features, residual connections, and a U-shaped network, for detecting and segmenting ischemic stroke lesions in 3D magnetic resonance imaging scans. The proposed method first uses a modified VGG model to identify ischemic stroke in separate 2D slices. Then, a U-shaped segmentation model with residual blocks segments the lesion in each slice. This procedure is applied independently to the axial, sagittal, and coronal planes, and the final output is generated by aggregating the three segmentation results. To improve both performance and processing speed, a high-performance classifier is applied before the segmentation model in a sequential framework. This strategy reduces unnecessary segmentation of non-lesion slices and improves overall accuracy. In addition, decomposing 3D images into 2D slices reduces model complexity while allowing information from three anatomical planes to support more accurate lesion localization. The proposed model is trained on the Anatomical Tracings of Lesions After Stroke dataset and outperforms state-of-the-art models in terms of accuracy and Dice coefficient. Moreover, the segmentation output provides feedback that helps the classification model reduce false-positive predictions. --- ### MindLoom: Composing Thought Modes for Frontier-Level Reasoning Data Synthesis Authors: Haiyang Shen, Taian Guo, Xuanzhong Chen, Mugeng Liu, Weichen Bi, Wenchun Jing, Sixiong Xie, Zhuofan Shi, Yudong Han, Chongyang Pan, Siqi Zhong, Jinsheng Huang et al. Published: 2026-05-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.21630v1 Although LLMs have made substantial progress in reasoning, systematically producing frontier-level reasoning data remains difficult. Existing synthesis methods often have limited visibility into the structural factors that govern problem difficulty, which can result in narrow diversity and unstable difficulty control. In this work, we view the difficulty of a reasoning problem as arising from the accumulation of atomic knowledge-reasoning transformations, which we term thought modes. Building on this perspective, we propose MindLoom, a framework for synthesizing frontier-level reasoning data through compositional thought mode engineering. Given a collection of hard problems with verified solutions, MindLoom first decomposes those solutions into thought mode chains that reveal each problem's construction logic. It then trains a retrieval model that matches problem states to compatible thought modes, providing guidance on which reasoning challenges to introduce during synthesis. New problems are composed by iteratively applying retrieved thought modes to seed questions, with distribution-aligned sampling to encourage diverse reasoning coverage. Finally, a rollout-based judging stage labels generated questions by difficulty and supplies judged-correct responses for supervised fine-tuning. We evaluate MindLoom on nine benchmarks covering five STEM disciplines and four mathematical reasoning tasks across multiple model families and sizes. Models fine-tuned on MindLoom-generated data achieves favorable performances over base models, distillation, and external-data baselines across the reported benchmarks. Ablation studies indicate the contribution of each component, and further analysis suggests that MindLoom covers a broad range of reasoning patterns while maintaining useful difficulty control. We have open-sourced our implementation at https://github.com/EachSheep/MindLoom. --- ### Faster Completion, Less Learning: Generative AI Reduced Study Time on Math Problems and the Knowledge They Build Authors: Sina Rismanchian, Hasan Uzun, Jeffrey Matayoshi, Eric Cosyn, Eyad Kurd-Misto Published: 2026-05-20 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2605.21629v3 How much have students' ordinary learning processes shifted in response to generative AI, and how does that affect their durable learning outcomes? Self-report surveys show little change, while small-scale behavioral studies report widespread AI use without the scale or duration to measure learning consequences. We address both questions using a ten-year panel of $3.2$ million ALEKS learning interactions for investigating time-on-task, complemented by ALEKS PPL placement-assessment data for examining proctoring and learning outcomes, with a quasi-experimental design exploiting variation in tasks that are more susceptible to AI (text-based word problems) and less susceptible to AI (interactive graph-based problems). Learning time on AI-susceptible problems declines $2.8\%$ per quarter among college students after ChatGPT's release, cumulating to $26.9\%$ over eleven quarters; high-schoolers show $31.3\%$, middle-schoolers $9.0\%$, and Grade 5 students no detectable change. Among college students, the post-ChatGPT divergence vanishes entirely under proctoring, ruling out broad efficiency gains as the likely explanation. Logistic fixed-effects models on randomly assigned proctored retention items yield a $25\%$ cumulative decline in odds of correct response; the same estimator on non-proctored assessment produces a large opposite-signed increase -- inconsistent with any platform, cohort, or curriculum explanation. These results are among the first large-scale behavioral and outcome evidence that generative AI has altered how students study and the knowledge they build -- the population-level indicator of \emph{cognitive surrender}, with direct implications for educational research, assessment governance, and AI policy. --- ### Distribution-free root cause analysis Authors: Rohan Hore, Aaditya Ramdas Published: 2026-05-20 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2605.21627v1 We study distribution-free root cause analysis in multi-stream data, where an evolving underlying system is observed through multiple data streams that may each undergo distributional changes at unknown timepoints. In such settings, the stream exhibiting the earliest change provides a natural starting point for investigating the underlying cause, which we refer to as the root-cause index. Leveraging conformal $p$-values, we propose a novel framework, Conformal Root Cause Analysis (CROC), which constructs finite-sample valid confidence sets for the root-cause index under minimal assumptions: the data streams are independent, and within each stream the pre- and post-change observations are sampled exchangeably from arbitrary and unknown distributions. We further establish a universality property, showing that any distribution-free method for root cause localization can be represented within the CROC framework. In addition, under mild regularity conditions and principled score design, our method yields asymptotically sharp confidence sets that efficiently isolate the root cause. We further extend CROC to efficiently handle cross-stream dependence when present. Extensive simulations demonstrate accurate localization of the root stream, supporting our theoretical guarantees. --- ### Flat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly Authors: Aditya Chetan, Eric Cai, Peeyush Kushwaha, Bharath Raj Nagoor Kani, Utkarsh Mall, Qianqian Wang, Noah Snavely, Bharath Hariharan Published: 2026-05-20 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.21625v1 The emergence of Large Vision-Language Models (LVLMs) has significantly advanced video understanding capabilities. However, existing benchmarks focus predominantly on coarse-grained tasks such as action segmentation, classification, captioning, and retrieval. Furthermore, these benchmarks often rely on entities that can be easily identified verbally, like household objects, animals, human subjects, etc., limiting their applicability to complex, in-the-wild video scenarios. But, many applications such as furniture assembly, cooking, etc., require step-by-step fine-grained spatio-temporal understanding of the video, which is not sufficiently evaluated in current benchmarks. To address this gap, we introduce Flat-Pack Bench, a novel benchmark centered on furniture assembly tasks. Our benchmark evaluates LVLMs on nuanced tasks, including temporal ordering of assembly actions, temporal localization of assembly state, understanding part mating, and tracking, using multiple-choice questions paired with visual prompts highlighting relevant parts as references for fine-grained questions. Our experiments reveal that state-of-the-art LVLMs struggle significantly with fine-grained spatio-temporal reasoning, highlighting their limitations in effectively leveraging temporal information from videos, limited tracking ability, and understanding of spatial interactions like physical contact. --- ### The Shape of Testimony: A Scalable Framework for Oral History Archive Comparison Authors: Itamar Trainin, Renana Keydar, Amit Pinchevski Published: 2026-05-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.21623v1 Researchers in Holocaust studies have often distinguished between two styles of oral survivor testimony: the USC Shoah Foundation's interviews tend to follow a structured, interviewer-guided format, whereas the Yale Fortunoff Video Archive generally favors a more free-form, open-ended style. This distinction has influenced both scholarly research and the development of later archives. In this study, we critically examine that claim by conducting a large-scale computational analysis of more than 1,600 testimonies from both collections. Leveraging discourse segmentation, topic modeling, and large language model (LLM) based analysis, we quantify the "structuredness" level of testimonies through topic coherence, interviewer-survivor dynamics, and the distribution of question types. Our results generally corroborate the structural differences identified in earlier research, while also revealing significant overlaps between the collections, both within individual interviews and across common narrative patterns. This complicates the simple "structured vs. free-form" dichotomy often applied to these oral histories. Beyond revisiting a foundational claim in Holocaust studies, our work provides a scalable, replicable framework for comparative corpus analysis. As a proof of concept, it suggests broader applications for digital oral history, narrative analysis, and the design of citizen-science annotation platforms. --- ### TO-Agents: A Multi-Agent AI Framework for Subjective Preference-Guided Topology Optimization Authors: Isabella A. Stewart, Hongrui Chen, Faez Ahmed Published: 2026-05-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.21622v2 Topology optimization can generate efficient structures, but designers often must manually translate qualitative intent, such as desired visual style, product experience, or manufacturability into solver settings that are not directly tied to those preferences. We present TO-Agents, a multi-agent AI framework that connects natural-language design intent with iterative topology optimization. The framework converts a human-provided problem description into validated solver inputs, runs a topology optimization solver, renders the resulting 3D topology, and uses multiview vision-language reasoning with an independent judge agent to critique each result and revise solver parameters. We evaluate the framework on two long-horizon design tasks: a cantilever beam benchmark and a phone-stand product design. In both tasks, the designer specifies an aesthetic preference for hierarchically branched structures inspired by natural tree morphologies, and the system performs four revision cycles across ten independent replicates. TO-Agents produces at least one preference-aligned design in 60\% of trials for each case study, corresponding to up to $6 \times$ more successful trials than an ablated pipeline without visual or historical feedback. Judge scores and human evaluations show that the pipeline can identify effective parameter levers, recover from poor revisions, and expand design exploration. A manufacturing agent further post-processes top-ranked designs for additive manufacturing, enabling end-to-end intent-to-prototype design. We also identify failure modes, including overshooting, selective memory, misplaced tools, and incorrect parameter reasoning. These results suggest that agentic topology optimization can shift designers from low-level parameter tuning toward higher-level specification of form and function, while highlighting safeguards needed for reliable autonomous engineering design. --- ### TO-Agents: A Multi-Agent AI Pipeline for Preference-Guided Topology Optimization Authors: Isabella A. Stewart, Hongrui Chen, Faez Ahmed Published: 2026-05-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.21622v1 Topology optimization can generate efficient structures, but designers often must manually translate qualitative intent, such as desired visual style, product experience, or manufacturability into solver settings that are not directly tied to those preferences. We present TO-Agents, a multi-agent AI framework that connects natural-language design intent with iterative topology optimization. The framework converts a human-provided problem description into validated solver inputs, runs a topology optimization solver, renders the resulting 3D topology, and uses multi-view vision-language reasoning with an independent judge agent to critique each result and revise solver parameters. We evaluate the framework on two long-horizon design tasks: a cantilever beam benchmark and a phone-stand product design. In both tasks, the designer specifies an aesthetic preference for hierarchically branched structures inspired by natural tree morphologies, and the system performs four revision cycles across ten independent replicates. TO-Agents produces at least one preference-aligned design in 60% of trials for each case study, corresponding to up to 6x more successful trials than an ablated pipeline without visual or historical feedback. Judge scores and human evaluations show that the pipeline can identify effective parameter levers, recover from poor revisions, and expand design exploration. A manufacturing agent further post-processes top-ranked designs for additive manufacturing, enabling end-to-end intent-to-prototype design. We also identify failure modes, including overshooting, selective memory, misplaced tools, and incorrect parameter reasoning. These results suggest that agentic topology optimization can shift designers from low-level parameter tuning toward higher-level specification of form and function, while highlighting safeguards needed for reliable autonomous engineering design. --- ### $\textit{BlockFormer}$ : Transformer-based inference from interaction maps Authors: Eloïse Touron, Pedro L. C. Rodrigues, Julyan Arbel, Nelle Varoquaux, Michael Arbel Published: 2026-05-20 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2605.21617v2 Inference from interaction maps, such as centromere identification from genome-wide chromosome conformation capture techniques -- notably Hi-C -- can be formulated as a generic inverse problem: infer a set of parameters given a map summarizing pairwise interactions between entities through blocks of variable numbers and sizes. In this work, we introduce a data-driven approach that leverages shared structure between these maps, such as global alignment between localized patterns, while handling the variability in number and size of entities arising in real-world data. Our approach relies on a transformer architecture capable of handling such variability and a custom simulator to generate abundant, yet computationally cheap synthetic data for training. Applied to the problem of centromere localization, the method accurately recovers their genomic positions across a wide range of species of various genome sizes. --- ### ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage Authors: Chang Liu, Noah Fleischmann, Nicolò Altamura, Edward Raff, James Holt, Kristopher Micinski Published: 2026-05-20 Categories: cs.CR, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2605.21615v1 Existing binary corpora typically capture only one or two axes of binary variation: they either provide cross-compiler builds without a temporal axis, or CVE labels for single-build binaries. None combine cross-build diversity, cross-version history, and CVE labels into a queryable structure. We present ASSEMBLAGE-DEEPHISTORY, which consolidates these dimensions into a unified framework where every binary's compilation context, source code, vulnerable functions, and package version are stored as first-class metadata. ASSEMBLAGE-DEEPHISTORY comprises 73,610 binaries spanning 248 open-source projects, compiled across GCC, Clang, and MSVC at multiple optimization levels on Linux and Windows, with multi-year historical builds. Each binary is indexed in a database that links it to its source code, functions, debug info, variant builds, historical versions, and vulnerable functions. Three analyses demonstrate this structure's value: (1) a three-stage LLM benchmark (recognition, strategy-guided detection, and cross-build transfer) to test whether LLMs reason about binary vulnerabilities or pattern-match on build-specific artifacts; (2) a comparison of MalConv embeddings, jTrans function embeddings, and TLSH fuzzy hashes quantifying how same-package versions cluster in each space; and (3) a Bayesian regression decomposing binary similarity into contributions from temporal distance, file changes, and commits. --- ### Exploring the Effectiveness of Using LLMs for Automated Assessment of Student Self Explanations in Programming Education Authors: Arun-Balajiee Lekshmi-Narayanan, Mohammad Hassany, Peter Brusilovsky Published: 2026-05-20 Categories: cs.HC, cs.LG arXiv: https://arxiv.org/abs/2605.21614v1 Worked examples are step-by-step solutions to problems in a specific domain, offered to students to acquire domain-specific problem-solving skills. The effectiveness of worked examples could be enhanced by combining them with self-explanations, which ask students to explain rather than passively study each problem-solving step. The main challenge of this approach is assessing the correctness of the student's explanations. In the prevailing approach, student explanations are judged by their semantic similarity to an instructor's or domain expert's explanation. Given recent advances in LLM-based automated scoring, it remains unclear whether semantic similarity methods are still the most effective technique to automatically score textual student responses like essays or code explanations. Comparing these methods also requires quality datasets that offer distinctive features such as balanced class distributions and domain-specific labeled data for automated scoring tasks. In this paper, we present a rigorous comparison between LLMs and semantic similarity used for automated scoring, framed as a binary classification task. --- ### UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation Authors: Jiayun Wang, Yu Wang, Weijie Gan, Zhenting Wang, Wei Wei Published: 2026-05-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.21611v1 We introduce spatially grounded contextual image generation, a controllable image generation task that reframes the conditioning paradigm. Instead of supplying a reference image and a global text prompt through two separate encoders, one for vision and one for language, UniVL is trained to bind semantics to spatial locations directly from a single unified visual input, where the textual instruction is rendered onto the spatial mask. This removes the need for a standalone text encoder at inference time. The resulting model supports contextual image generation by following user-specified instructions about what should appear where, while substantially reducing computation. To address this task, we propose a framework in which the UniVL encoder, adapted from an optical-character-recognition-pretrained backbone, reads the unified condition optically and produces a UniVL embedding, fVIL, that fuses visual and semantic intent with spatial locations in a single token sequence. A two-stage pipeline first aligns UniVL with the VAE embedding space and then conditions a pretrained diffusion backbone entirely on UniVL embeddings, eliminating the standalone text encoder, such as T5. Although this reframing uses a deliberately minimal text interface, it yields strong empirical gains. On UniVL-ImgGen, a benchmark of 477K mask-annotated images that we construct for training and evaluation, UniVL improves image quality over text-prompted baselines, reducing FID from 14 to 11 and increasing PSNR from 16 to 20. It also eliminates the text encoder entirely, reducing inference TFLOPs by up to 52% and runtime by up to 44%. Additional ablation studies validate the contributions of the proposed components, paving the way for efficient, spatially grounded image generation with a unified conditioning paradigm. --- ### AgForce Enables Antigen-conditioned Generative Antibody Design Authors: Mansoor Ahmed, Murray Patterson Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21610v2 Antibody design methods condition on antigen structure to generate complementarity-determining regions (CDR), yet a systematic evaluation of baseline methods reveals that they largely ignore the antigen input. We identify three failure modes that explain this behavior. Antigen blindness arises because models derive predictions from antibody framework context rather than antigen information, producing nearly identical CDRs regardless of the target. Vocabulary collapse reduces predicted amino acids to three to five per position, far below the ground truth distribution in native sequences. The argmax bottleneck on the cross-entropy loss via greedy decoding acts as a null predictor that sees only position and loop length and recovers almost all the residues irrespective of the model architecture and the target antigen. We propose a novel encoder-decoder architecture called AgForce that uses a graph neural network (GNN) as the encoder and specialized decoders for sequence-structure co-design. Specifically, we apply framework dropout, gated bottlenecks, and hyperbolic cross attention that prevent the antibody shortcut path. In the decoder, a Mixture Density Network (MDN) sequence head with Potts-like pairwise coupling and annealed Multiple Choice Learning (aMCL) replaces the cross-entropy objective with a multi-component distribution. An antigen cycle consistency head routes gradients through the sequence decoder, forcing predicted distributions to encode antigen identity. On the ChiMERa-Bench dataset, AgForce leads the baselines on every interface metric on all three splits (fnat, iRMSD, DockQ, and epitope F1) together with structure and sequence, while achieving roughly a 2x larger effective vocabulary compared to the GNN baselines. --- ### AgForce Enables Antigen-conditioned Generative Antibody Design Authors: Mansoor Ahmed, Murray Patterson Published: 2026-05-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.21610v1 Antibody design methods condition on antigen structure to generate complementarity-determining regions (CDR), yet a systematic evaluation of baseline methods reveals that they largely ignore the antigen input. We identify three failure modes that explain this behavior. Antigen blindness arises because models derive predictions from antibody framework context rather than antigen information, producing nearly identical CDRs regardless of the target. Vocabulary collapse reduces predicted amino acids to three to five per position, far below the ground truth distribution in native sequences. Moreover, any model trained with standard per-position cross-entropy converges to the positional marginal distribution, making it provably unable to produce antigen-specific sequence predictions. We propose a novel encoder-decoder architecture called AgForce, that uses a graph neural network (GNN) as the encoder and specialized decoders for sequence-structure co-design. Specifically, we apply framework dropout, gated bottlenecks, and hyperbolic cross attention that prevent the antibody shortcut path. In the decoder, a Mixture Density Network (MDN) sequence head with Potts-like pairwise coupling and annealed Multiple Choice Learning (aMCL) replaces the cross-entropy objective with a multi-component distribution whose optimal solution differs from the positional marginal. An antigen cycle consistency head routes gradients through the sequence decoder, forcing predicted distributions to encode antigen identity. AgForce achieves the best binding quality and sequence recovery simultaneously on the CHIMERA-Bench dataset, improving amino acid recovery by 8% over the strongest sequence baseline while surpassing the baselines across all interface metrics, and nearly doubling the effective vocabulary of GNN methods. The source code is available at: https://github.com/mansoor181/ag-force.git --- ### CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety Authors: Heajun An, Qi Zhang, Vedanth Achanta, Jin-Hee Cho Published: 2026-05-20 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2605.21609v1 Large language models (LLMs) are increasingly embedded in adolescent digital environments, mediating information seeking, advice, and emotionally sensitive interactions. Yet existing safety mechanisms remain largely grounded in adult-centric norms and operationalize safety through refusal-oriented suppression. While such approaches may reduce immediate policy violations, they can also create conversational dead-ends, limit constructive guidance, and fail to address the developmental vulnerabilities inherent in adolescent-AI interactions. We argue that adolescent LLM safety should be framed not solely as a filtering problem, but as a socio-technical, developmentally aligned transformation problem. To operationalize this perspective, we propose Critique-and-Revise-for-Teenagers (CR4T), a model-agnostic safeguarding framework that selectively reconstructs unsafe or refusal-style outputs into ageappropriate, guidance-oriented responses while preserving benign intent. CR4T combines lightweight risk detection with domain-conditioned rewriting to remove risk-amplifying content, reduce unnecessary conversational shutdown, and introduce developmentally appropriate guidance. Experimental results show that targeted rewriting substantially reduces unsafe and refusal-oriented outcomes while avoiding unnecessary intervention on acceptable interactions. These findings suggest that selective response reconstruction offers a more human-centered alternative to refusal-centric guardrails for adolescent-facing LLM systems. ---