# Research Papers — 2026-05 · bundle page 271 of 326 > Full-text markdown of papers #13501–13550 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/271 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/270.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/272.md) ### Feature Dimensionality Outweighs Model Complexity in Breast Cancer Subtype Classification Using TCGA-BRCA Gene Expression Data Authors: Meena Al Hasani Published: 2026-05-07 Categories: cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2605.06562v1 Accurate classification of breast cancer subtypes from gene expression data is critical for diagnosis and treatment selection. However, such datasets are characterized by high dimensionality and limited sample size, posing challenges for machine learning models. In this study, we evaluate the impact of model complexity and feature selection on subtype classification performance using TCGA-BRCA gene expression data. Logistic regression, random forest, and support vector machine (SVM) models were trained using varying numbers of highly variable genes (50 to 20,518). Performance was evaluated using stratified 5-fold cross-validation and assessed with accuracy and macro F1 score. While all models achieved high accuracy, macro F1 analysis revealed substantial differences in subtype-level performance. Logistic regression demonstrated the most stable and balanced performance across subtypes, including improved detection of rare classes. Random forest underperformed on minority subtypes despite strong overall accuracy, while SVM showed sensitivity to feature dimensionality. These findings highlight the importance of model simplicity, evaluation metrics, and feature selection in high-dimensional biological classification tasks. --- ### Optimal Counterfactual Search in Tree Ensembles: A Study Across Modeling and Solution Paradigms Authors: Awa Khouna, Youssouf Emine, Julien Ferry, Thibaut Vidal Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06561v1 Trust in counterfactual explanations depends critically on whether their recommended changes are truly minimal: suboptimal explanations may vastly overshoot the actual changes needed to alter a decision, and heuristic errors can affect individuals unevenly, giving some users relevant recourse while assigning others unnecessarily costly recommendations. Consequently, we study the problem of computing optimal counterfactual explanations for tree ensembles under plausibility and actionability constraints. This is a combinatorial problem: for a fixed model, counterfactual search boils down to selecting consistent branching decisions and threshold-defined regions under a distance objective. We exploit this structure through CPCF, a constraint programming (CP) formulation in which numerical features are encoded as interval domains induced by split thresholds, while discrete features retain native finite-domain representations. This yields a compact finite-domain formulation that supports multiple distance objectives without continuous split-boundary search. We then place CPCF in a broader comparison across mathematical programming paradigms: we extend a maximum Boolean satisfiability (MaxSAT) formulation, originally designed for hard-voting random forests, to soft-voting ensembles, and compare against the current state-of-the-art mixed-integer linear programming (MILP) optimal approach. Across ten datasets and three types of tree ensembles, we analyze scalability, anytime performance, and sensitivity to distance metrics. We observe that CP achieves the best overall performance. More importantly, our results identify regimes in which the specific strengths of each paradigm make it best suited: CP is most versatile overall, MaxSAT handles hard-voting ensembles particularly well, and MILP remains competitive in amortized inference settings with a moderate number of split levels. --- ### Coordination Matters: Evaluation of Cooperative Multi-Agent Reinforcement Learning Authors: Maria Ana Cardei, Matthew Landers, Afsaneh Doryab Published: 2026-05-07 Categories: cs.MA, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.06557v1 Cooperative multi-agent reinforcement learning (MARL) benchmarks commonly emphasize aggregate outcomes such as return, success rate, or completion time. While essential, these metrics often fail to reveal how agents coordinate, particularly in settings where agents, tasks, and joint assignment choices scale combinatorially. We propose a coordination-aware evaluation perspective that supplements return with process-level diagnostics. We instantiate this perspective using STAT, a controlled commitment-constrained spatial task-allocation testbed that systematically varies agents, tasks, and environment size while holding observation access and task rules fixed. We evaluate six representative value-based MARL methods across varying levels of centralization. Our results show that similar return trends can reflect distinct coordination mechanisms, including differences in redundant assignment, assignment diversity, and task-completion efficiency. We find that in commitment-constrained task allocation, performance under scale is shaped not only by nominal action-space size, but also by assignment pressure, sparse decision opportunities, and redundant choices among interdependent agents. Our findings motivate coordination-aware evaluation as a necessary complement to return-based benchmarking for cooperative MARL. --- ### Long Context Pre-Training with Lighthouse Attention Authors: Bowen Peng, Subho Ghosh, Jeffrey Quesnelle Published: 2026-05-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.06554v1 Training causal transformers at extreme sequence lengths is bottlenecked by the quadratic time and memory of scaled dot-product attention (SDPA). In this work, we propose Lighthouse Attention, a training-only symmetrical selection-based hierarchical attention algorithm that wraps around ordinary SDPA and can be easily removed towards the end of the training. Our hierarchical selection is also gradient-free, which exempts us from dealing with a complicated and potentially inefficient backward pass kernel. Our contribution is three-fold: (i) A subquadratic hierarchical pre- and post-processing step that does adaptive compression and decompression of the sequence. (ii) A symmetrical compression strategy that pools queries, keys and values at the same time, while preserving left-to-right causality, which greatly improves parallelism. (iii) A two stage training approach which we pre-train for the majority of the time with Lighthouse Attention and recover a full attention model at the end with a short training. We run preliminary small scale LLM pre-training experiments that show the effectiveness of our method compared to full attention training with all other settings matched, where we achieve a faster total training time and lower final loss after the recovery phase. Full code is available at: https://github.com/ighoshsubho/lighthouse-attention --- ### Diverse Sampling in Diffusion Models with Divergence-Free Particle Guidance Authors: Gal Vinograd, Idan Achituve, Ethan Fetaya Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06553v2 Modern generative models can produce high-quality samples, but independent samples under the same condition often yields highly similar outputs. Particle-based methods increase diversity by letting the samples in a batch interact, typically through a repulsive force. These forces, however, also push each sample away from the data distribution and produce visible artifacts. We introduce EDDY, a training-free particle guidance method designed to avoid this failure mode. Instead of a repulsive gradient, EDDY couples particles through anti-symmetric matrix fields passed through a Stein operator, a family of drift perturbations that leaves the Fokker--Planck equation invariant. Unlike repulsive guidance, these interactions do not alter a particle's distribution while the batch is independent. For the same reason they cannot create diversity on their own, so EDDY pairs them with a negatively correlated initialization that keeps each particle's prior exact. To use EDDY with perceptual kernels such as DINOv2, we approximate its second-order terms with finite differences and Hutchinson estimates. Across FLUX.1-dev, FLUX.2-klein and SDXL, EDDY achieves higher image quality and prompt alignment than existing particle guidance methods at matched diversity. --- ### Diverse Sampling in Diffusion Models with Marginal Preserving Particle Guidance Authors: Gal Vinograd, Idan Achituve, Ethan Fetaya Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06553v1 We present EDDY (Exact-marginal Diversification via Divergence-free dYnamics), a guidance mechanism for diffusion and flow matching models that promotes diversity among samples generated while maintaining quality. EDDY exploits symmetries of the Fokker-Planck equation, using drift perturbations that change particle trajectories while preserving the evolving marginal distribution. We instantiate this principle through kernel-based anti-symmetric pairwise matrix fields, constructed from the repulsive directions. The resulting divergence-free dynamics promote diversity at the joint particle level while preserving each particle's marginal distribution without any additional training. As computing the guidance can be computationally expensive in cases such as text-to-image generation with perceptual embeddings, we propose practical approximations as an effective and efficient solution. Experiments on synthetic distributions and text-to-image generation show that EDDY improves diversity while maintaining strong distributional fidelity compared to common baselines. --- ### Sequential Design of Genetic Circuits Under Uncertainty With Reinforcement Learning Authors: Michal Kobiela, Diego A. Oyarzún, Michael U. Gutmann Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06552v1 The design of biological systems is hindered by uncertainty arising from both intrinsic stochasticity of biomolecular reactions and variability across laboratory or experimental conditions. In this work, we present a sequential framework to optimize genetic circuits under both forms of uncertainty. By employing simulator models based on differential equations or Markov jump processes alongside a reinforcement learning (RL) policy-based approach, our method suggests experiments that adapt to unknown laboratory conditions while accounting for inherent stochasticity. While previous Bayesian methods address uncertainty through iterative experiment-inference-optimization cycles, they typically require computationally expensive inference and optimization steps after each experimental round, leading to delays. To overcome this bottleneck, we propose an amortized approach trained up-front across a distribution of possible uncertain parameters. This strategy sidesteps the need for explicit parameter inference during the design cycle, enabling immediate, observation-based adaptation. We demonstrate our framework on models for heterologous gene expression and a repressilator circuit, showing that it efficiently handles both molecular noise and cross-laboratory variability. --- ### Continuous Latent Diffusion Language Model Authors: Hongcan Guo, Qinyu Zhao, Yian Zhao, Shen Nie, Rui Zhu, Qiushan Guo, Feng Wang, Tao Yang, Hengshuang Zhao, Guoqiang Wei, Yan Zeng Published: 2026-05-07 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.06548v1 Large language models have achieved remarkable success under the autoregressive paradigm, yet high-quality text generation need not be tied to a fixed left-to-right order. Existing alternatives still struggle to jointly achieve generation efficiency, scalable representation learning, and effective global semantic modeling. We propose Cola DLM, a hierarchical latent diffusion language model that frames text generation through hierarchical information decomposition. Cola DLM first learns a stable text-to-latent mapping with a Text VAE, then models a global semantic prior in continuous latent space with a block-causal DiT, and finally generates text through conditional decoding. From a unified Markov-path perspective, its diffusion process performs latent prior transport rather than token-level observation recovery, thereby separating global semantic organization from local textual realization. This design yields a more flexible non-autoregressive inductive bias, supports semantic compression and prior fitting in continuous space, and naturally extends to other continuous modalities. Through experiments spanning 4 research questions, 8 benchmarks, strictly matched ~2B-parameter autoregressive and LLaDA baselines, and scaling curves up to about 2000 EFLOPs, we identify an effective overall configuration of Cola DLM and verify its strong scaling behavior for text generation. Taken together, the results establish hierarchical continuous latent prior modeling as a principled alternative to strictly token-level language modeling, where generation quality and scaling behavior may better reflect model capability than likelihood, while also suggesting a concrete path toward unified modeling across discrete text and continuous modalities. --- ### Efficient Pre-Training with Token Superposition Authors: Bowen Peng, Théo Gigant, Jeffrey Quesnelle Published: 2026-05-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.06546v2 Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughput. In this work, we present Token-Superposition Training (TST), a simple drop-in method that significantly improves the data throughput per FLOPs during pre-training without modifying the parallelism, optimizer, tokenizer, data, or model architecture. TST is done in two phases: (i) A highly efficient superposition phase where we combine many contiguous tokens into one bag and train using a multi-hot cross-entropy (MCE) objective, and (ii) a recovery phase where we revert back to standard training. We extensively evaluate TST on the scale of 270M and 600M parameters and validate on 3B and a 10B A1B mixture of experts model, demonstrating that it is highly robust in different settings. Ultimately, TST consistently outperforms baseline loss and downstream evaluations, and under equal-loss settings, TST yields up to a 2.5x reduction in total pre-training time at the 10B A1B scale. --- ### Hedging Memory Horizons for Non-Stationary Prediction via Online Aggregation Authors: Yutong Wang, Yannig Goude, Qiwei Yao Published: 2026-05-07 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.06541v1 We study online prediction under distribution shift, where inputs arrive chronologically and outcomes are revealed only after prediction. In this setting, predictors must remain stable in quiet regimes yet adapt when regimes shift, and the right adaptation memory is unknown in advance. We propose MELO (Memory-hedged Exponentially Weighted Least-Squares Online aggregation), a model-agnostic method that hedges across adaptation scales: it wraps any non-anticipating base-predictor pool with exponentially weighted least-squares (EWLS) adaptation experts at multiple forgetting factors, and aggregates raw and EWLS-adapted forecasts with MLpol, a parameter-free online aggregation rule. Under boundedness conditions, we establish deterministic oracle inequalities showing that it competes with both the best raw predictor and the best bounded, time-varying affine combinations of the base predictions, up to a path-length-dependent tracking cost and a sublinear aggregation overhead. We evaluate MELO on French national electricity-load forecasting through the COVID-19 lockdown using no regime indicators, lockdown dates, or policy covariates. MELO reduces overall RMSE by 34.7\% relative to base-only MLpol and achieves lower overall RMSE than a TabICL reference supplied with an external COVID policy-response covariate. Moreover, MELO requires only lightweight per-step recursive updates without model retraining. --- ### Ex Ante Evaluation of AI-Induced Idea Diversity Collapse Authors: Nafis Saami Azad, Raiyan Abdul Baten Published: 2026-05-07 Categories: cs.AI, cs.GT arXiv: https://arxiv.org/abs/2605.06540v1 Creative AI systems are typically evaluated at the level of individual utility, yet creative outputs are consumed in populations: an idea loses value when many others produce similar ones. This creates an evaluation blind spot, as AI can improve individual outputs while increasing population-level crowding. We introduce a human-relative framework for benchmarking AI-induced human diversity collapse without requiring human-AI interaction data, providing an ex ante protocol to estimate crowding risk from model-only generations and matched unaided human baselines. By modeling ideas as congestible resources, we show that source-level crowding is identifiable from within-distribution comparisons, yielding an excess-crowding coefficient $Δ$ and a human-relative diversity ratio $ρ$. We show that $ρ\ge1$ is the no-excess-crowding parity condition and connect $Δ$ to an adoption game with exposure-dependent redundancy costs. Across short stories, marketing slogans, and alternative-uses tasks, three frontier LLMs fall below parity across crowding kernels. Estimates stabilize with feasible model-only sample sizes. Importantly, generation-protocol variants show that crowding can be reduced through targeted design, making diversity collapse an actionable, development-time evaluation target for population-aware creative AI. --- ### Diffusion-Based Posterior Sampling: A Feynman-Kac Analysis of Bias and Stability Authors: Matias G. Delgadino, Sebastien Motsch, Advait Parulekar, William Porteous, Sanjay Shakkottai Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06538v1 Diffusion-based posterior samplers use pretrained diffusion priors to sample from measurement- or reward-conditioned posteriors, and are widely used for inverse problems. Yet their theoretical behavior remains poorly understood: even with exact prior scores, their outputs are biased, and in low-temperature regimes their discretizations can become unstable. We characterize this bias by introducing a tractable surrogate path connecting the true posterior to a standard Gaussian and comparing it to the sampler's path. Their density ratio satisfies a parabolic PDE whose reaction term measures the accumulated bias. A Feynman-Kac representation then expresses the Radon-Nikodym correction as an explicit path expectation, identifying which posterior regions are over- or under-sampled. We apply this framework to DPS and STSL, a related sampler. For DPS, the correction is an Ornstein-Uhlenbeck path expectation coupling the data conditional covariance with the reward curvature, revealing where DPS over- or under-samples. Next, we reinterpret STSL as an auxiliary drift that steers trajectories toward low-uncertainty regions, flattening the spatially varying part of the DPS reaction term. Finally, we characterize early guidance-stopping, a common mitigation for low-temperature instabilities caused by forward-Euler integration of the vector field. Together, these results clarify sampler bias, explain existing correctives, and guide stable variant designs. --- ### MedHorizon: Towards Long-context Medical Video Understanding in the Wild Authors: Bodong Du, Bowen Liu, Yang Yu, Xinpeng Ding, Zhiheng Wu, Shuning Wang, Shuo Nie, Naiming Liu, Qifeng Chen, Yangqiu Song, Xiaomeng Li Published: 2026-05-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.06537v1 Medical multimodal large language models (MLLMs) have advanced image understanding and short-video analysis, but real clinical review often requires full-procedure video understanding. Unlike general long videos, medical procedures contain highly redundant anatomical views, while decisive evidence is temporally sparse, spatially subtle, and context dependent. Existing benchmarks often assume this evidence has already been localized through images, short clips, or pre-segmented videos, leaving the retrieval-before-reasoning problem under-tested. We introduce MedHorizon, an in-the-wild benchmark for long-context medical video understanding. MedHorizon preserves 759 hours of full-length clinical procedures and provides 1,253 evidence-grounded multiple-choice questionsthat jointly evaluate sparse evidence understanding and multi-hop clinical reasoning. Its evidence is extremely sparse, with only 0.166% evidence frames on average, requiring models to search noisy procedural streams before interpreting and aggregating findings. We evaluate representative general-domain, medical-domain, and long-video MLLMs. The best model reaches only 41.1% accuracy, showing that current systems remain far from robust full-procedure understanding. Further analysis yields four key findings: performance does not scale reliably with more frames, evidence retrieval and clinical interpretation remain primary bottlenecks; these bottlenecks are rooted in weak procedural reasoning and attention drift under redundancy, and generic sampling methods only partially balances local detail with global coverage. MedHorizon provides a rigorous testbed for MLLMs that retrieve sparse evidence and reason over complete clinical workflows. --- ### Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance Authors: Ziyun Zeng, Yiqi Lin, Guoqiang Liang, Mike Zheng Shou Published: 2026-05-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.06535v1 In recent years, open-source efforts like Senorita-2M have propelled video editing toward natural language instruction. However, current publicly available datasets predominantly focus on local editing or style transfer, which largely preserve the original scene structure and are easier to scale. In contrast, Background Replacement, a task central to creative applications such as film production and advertising, requires synthesizing entirely new, temporally consistent scenes while maintaining accurate foreground-background interactions, making large-scale data generation significantly more challenging. Consequently, this complex task remains largely underexplored due to a scarcity of high-quality training data. This gap is evident in poorly performing state-of-the-art models, e.g., Kiwi-Edit, because the primary open-source dataset that contains this task, i.e., OpenVE-3M, frequently produces static, unnatural backgrounds. In this paper, we trace this quality degradation to a lack of precise background guidance during data synthesis. Accordingly, we design a scalable pipeline that generates foreground and background guidance in a decoupled manner with strict quality filtering. Building on this pipeline, we introduce Sparkle, a dataset of ~140K video pairs spanning five common background-change themes, alongside Sparkle-Bench, the largest evaluation benchmark tailored for background replacement to date. Experiments demonstrate that our dataset and the model trained on it achieve substantially better performance than all existing baselines on both OpenVE-Bench and Sparkle-Bench. Our proposed dataset, benchmark, and model are fully open-sourced at https://showlab.github.io/Sparkle/. --- ### SpatialEpiBench: Benchmarking Spatial Information and Epidemic Priors in Forecasting Authors: Ruiqi Lyu, Alistair Turcan, Bryan Wilder Published: 2026-05-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.06530v1 Accurate epidemic forecasting is crucial for public health response, resource allocation, and outbreak intervention, but remains difficult with sparse, noisy, and highly non-stationary data. Because epidemics unfold across interacting regions, spatiotemporal methods are natural candidates for improving forecasts. Despite growing interest in spatial information, no standardized benchmark exists, and current evaluations often use simple chronological train-test splits that do not reflect real-time forecasting practice. We address this gap with SpatialEpiBench, a challenging benchmark for spatiotemporal epidemic forecasting in realistic public-health settings. SpatialEpiBench includes 11 epidemic datasets with standardized rolling evaluations and outbreak-specific metrics. We evaluate adjacency-informed forecasting models with widely used epidemic priors that adapt general models to epidemiology, but find that most methods underperform a simple last-value baseline from 1 day to 1 month ahead, even during outbreaks and with these priors. We identify three major failure modes: (1) poor outbreak anticipation, (2) difficulty handling sparsity and noise, and (3) limited utility of common geographic adjacency for epidemiological spatial information. We release benchmark data, code, and instructions at https://github.com/Rachel-Lyu/SpatialEpiBench to support development of operationally useful epidemic forecasting models. --- ### Market-Alignment Risk in Pricing Agents: Trace Diagnostics and Trace-Prior RL under Hidden Competitor State Authors: Peiying Zhu, Sidi Chang Published: 2026-05-07 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.06529v1 Outcome metrics can certify the wrong behavior. We study this failure in a two-hotel revenue-management simulator where Hotel A trains an agent against a fixed rule-based revenue-management competitor, Hotel B. A standard learning agent can obtain near-reference revenue per available room (RevPAR) while failing to learn market-like yield management: it sells too aggressively, undercuts, or collapses to modal price buckets. We diagnose this as a Goodhart-style failure under partial observability. Hotel A cannot observe the competitor's remaining inventory, booking curve, or pricing rule, so the same Hotel A-visible state maps to multiple plausible Hotel B prices. Deterministic value-based RL and deterministic copying collapse this unresolved uncertainty into shortcut behavior. We introduce a trace-level diagnostic protocol using RevPAR, occupancy, ADR, full price-bucket distributions, L1/JS distances, and seed-level confidence intervals. The verified repair is Trace-Prior RL: learn a distributional market prior from lagged market traces, then train a stochastic pricing policy with a RevPAR reward and a KL penalty to the learned prior. The final policy matches Hotel B's RevPAR, occupancy, ADR, and price distribution within seed-level uncertainty, while still optimizing Hotel A's own reward. We argue that the contribution is not a new optimizer and not a hotel-pricing leaderboard, but a reproducible failure-and-repair recipe for agentic systems where scalar rewards are easy to game and the intended behavior is only visible in traces. A key finding is that higher exact action accuracy can worsen aggregate trace alignment when the target is distributional. --- ### STALE: Can LLM Agents Know When Their Memories Are No Longer Valid? Authors: Hanxiang Chao, Yihan Bai, Rui Sheng, Tianle Li, Yushi Sun Published: 2026-05-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.06527v1 Large Language Model (LLM) agents are increasingly expected to maintain coherent, long-term personalized memory, yet current benchmarks primarily measure static fact retrieval, overlooking the ability to revise stored beliefs when new evidence emerges. We identify a critical and underexplored failure mode, Implicit Conflict: a later observation invalidates an earlier memory without explicit negation, requiring contextual inference and commonsense reasoning to detect. To rigorously evaluate this capability, we introduce STALE, a benchmark of 400 expert-validated conflict scenarios (1,200 evaluation queries across three probing dimensions) spanning over 100 everyday topics with contexts up to 150K tokens. We propose a three-dimensional probing framework that tests State Resolution (detecting that a prior belief is outdated), Premise Resistance (rejecting queries that falsely presuppose a stale state), and Implicit Policy Adaptation (proactively applying updated states in downstream behavior). A systematic evaluation of frontier LLMs and specialized memory frameworks reveals a pervasive gap between retrieving updated evidence and acting on it, with even the best evaluated model achieving only 55.2% overall accuracy. Models often accept outdated assumptions embedded in a user's query, and they struggle to recognize when a change in one aspect of the user's state should invalidate related memories. To establish an initial baseline for state-aware memory, we further present CUPMem, a prototype that strengthens write-time revision through structured state consolidation and propagation-aware search, suggesting that explicit state adjudication is a promising direction for robust agentic memory. --- ### Process Matters more than Output for Distinguishing Humans from Machines Authors: Milena Rmus, Mathew D. Hardy, Thomas L. Griffiths, Mayank Agrawal Published: 2026-05-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.06524v3 Reliable human-machine discrimination is becoming increasingly important as Large Language Models and autonomous agents are deployed in online settings. Existing approaches evaluate whether a system can produce responses indistinguishable from those of a human. This approach follows the focus on the output of a machine, as suggested by Alan Turing. Cognitive science provides an alternative approach: considering the process by which that behavior is produced. To evaluate whether processes can reliably distinguish humans from machines, we introduce a process-based framework, the Process Turing Test, and evaluate it across a battery of cognitive tasks spanning decision-making, working memory, and planning. These tasks, such as mental rotation and sequence prediction, yield process-level measures complementing conventional measures of overall task performance. We also include multiple CAPTCHA tasks in the battery. Across the battery, process-level features provide substantially stronger discriminative signal than performance metrics alone, reliably distinguishing humans from agents even when task performance is matched (process-based classifier AUC = 0.88). We also conducted a controlled red-teaming study comparing off-the-shelf frontier agents (Claude Sonnet 4.5, GPT-5, Gemini 2.5 Pro), Centaur (LLM fine-tuned on 10.7M human decisions), and two task-specific fine-tuning methods: action-level supervised fine-tuning (A-SFT) and process-level fine-tuning (P-SFT), which directly optimizes process features. We find that broad fine-tuning on human choices makes task processes more human-like relative to off-the-shelf frontier agents, and task-specific P-SFT further improves human-like behavioral mimicry, though this advantage largely disappears under cross-task transfer. These results highlight process specification as a central bottleneck in achieving human-like cognitive processes in machines. --- ### Process Matters more than Output for Distinguishing Humans from Machines Authors: Milena Rmus, Mathew D. Hardy, Thomas L. Griffiths, Mayank Agrawal Published: 2026-05-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.06524v2 Reliable human-machine discrimination is becoming increasingly important as large language models and autonomous agents are deployed in online settings. Existing approaches evaluate whether a system can produce behavior or responses indistinguishable from those of a human, following the emphasis on outputs as a criterion for intelligence proposed by Alan Turing. Cognitive science offers an alternative perspective: evaluating the process by which behavior is produced. To test whether cognitive processes can reliably distinguish humans from machines, we introduce CogCAPTCHA30, a battery of 30 cognitive tasks designed to elicit diagnostic process-level features even when task performance is matched. Across the battery, process-level features provide stronger discriminative signal than performance metrics alone, reliably distinguishing humans from agents even under output matching (mean process-feature classifier AUC = 0.88). To evaluate agentic process differences, we compare off-the-shelf frontier agents (Claude Sonnet 4.5, GPT-5, Gemini 2.5 Pro), Centaur (a language model fine-tuned on 10.7M human decisions), and two task-specific fine-tuning approaches applied to Qwen2.5-1.5B-Instruct: action-level supervised fine-tuning (A-SFT) and process-level fine-tuning (P-SFT), which directly optimizes process features. Broad fine-tuning on human decisions improves human-like task processes relative to off-the-shelf agents, while task-specific process-level supervision further improves behavioral mimicry. However, this advantage diminishes under cross-task transfer when supervised process targets do not naturally generalize across tasks. Explicit process-level supervision can improve human behavioral mimicry, but only if appropriate task-specific process representations are available, highlighting process specification as a bottleneck for achieving human-like cognitive processes in machines. --- ### On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR Authors: Hao Ye, Jisheng Dang, Junfeng Fang, Bimei Wang, Yizhou Zhang, Ning Lv, Wencan Zhang, Hong Peng, Bin Hu, Tat-Seng Chua Published: 2026-05-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.06523v1 Recent extensive research has demonstrated that the enhanced reasoning capabilities acquired by models through Reinforcement Learning with Verifiable Rewards (RLVR) are primarily concentrated within the rank-1 components. Predicated on this observation, we employed Periodic Rank-1 Substitution and identified a counterintuitive phenomenon: RLVR may exhibit implicit reward overfitting to the training dataset. Specifically, the model can achieve satisfactory performance on the test set even when its rewards remain relatively low during the training process. Furthermore, we characterize three distinct properties of RL training: (1) The effective rank-1 component in RLVR don't maintain other model knowledge except mathematical reasoning capability. (2) RLVR fundamentally functions by optimizing a specific singular spectrum. The distribution of singular values of almost all linear layers in RLVR-trained model behaves like heavy-tailed distribution. (3) the left singular vectors associated with rank-1 components demonstrate a stronger alignment tendency during training, which echoes the discovery that RLVR is optimizing sampling efficiency in essence. Taken together, our findings and analysis further reveal how RLVR shapes model parameters and offer potential insights for improving existing RL paradigms or other training paradigms to implement continual learning. --- ### Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models Authors: Xin Wang, Haibo Chen, Wenxuan Liu, Wenwu Zhu Published: 2026-05-07 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2605.06522v1 Foundation models (FMs) are increasingly deployed in open-world settings where distribution shift is the rule rather than the exception. The out-of-distribution (OOD) phenomena they face -- knowledge boundaries, capability ceilings, compositional shifts, and open-ended task variation -- differ in kind from the settings that have shaped prior OOD research, and are further complicated because the pretraining and post-training distributions of modern FMs are often only partially observed. Our position is that OOD for foundation models is a structurally distinct problem that cannot be solved within the prevailing model-centric paradigm, and that agentic systems constitute the missing paradigm required to address it. We defend this claim through four steps. First, we give a stage-aware formalization of OOD that accommodates partially observed multi-stage training distributions. Second, we prove a parameter coverage ceiling: there exist practically relevant inputs that no model-centric method (training-time or test-time) can handle within tolerance $\varepsilon$, for reasons intrinsic to parameter-based representation. Third, we characterize agentic OOD systems by four structural properties -- perception, strategy selection, external action, and closed-loop verification -- and show that they strictly extend the reachable set beyond the ceiling. Fourth, we respond to seven counterarguments, conceding two, and outline a research agenda. We do not claim that agentic methods subsume model-centric ones; we argue that the two are complementary, and that progress on FM-OOD requires explicit recognition of the agentic paradigm as a first-class research direction. --- ### Optimizing Social Utility in Sequential Experiments Authors: Ander Artola Velasco, Stratis Tsirtsis, Manuel Gomez-Rodriguez Published: 2026-05-07 Categories: cs.GT, cs.LG, cs.MA, stat.ME arXiv: https://arxiv.org/abs/2605.06520v1 Regulatory approval of products in high-stakes domains such as drug development requires statistical evidence of safety and efficacy through large-scale randomized controlled trials. However, the high financial cost of these trials may deter developers who lack absolute certainty in their product's efficacy, ultimately stifling the development of `moonshot' products that could offer high social utility. To address this inefficiency, in this paper, we introduce a statistical protocol for experimentation where the product developer (the agent) conducts a randomized controlled trial sequentially and the regulator (the principal) partially subsidizes its cost. By modeling the protocol using a belief Markov decision process, we show that the agent's optimal strategy can be found efficiently using dynamic programming. Further, we show that the social utility is a piecewise linear and convex function over the subsidy level the principal selects, and thus the socially optimal subsidy can also be found efficiently using divide-and-conquer. Simulation experiments using publicly available data on antibiotic development and approval demonstrate that our statistical protocol can be used to increase social utility by more than $35$$\%$ relative to standard, non-sequential protocols. --- ### Efficient Techniques for Data Reconstruction, with Finite-Width Recovery Guarantees Authors: Edward Tansley, Roy Makhlouf, Estelle Massart, Coralia Cartis Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06519v1 Data reconstruction attacks on trained neural networks aim to recover the data on which the network has been trained and pose a significant threat to privacy, especially if the training dataset contains sensitive information. Here, we propose a unified optimization formulation of the data reconstruction problem based on initial and trained parameter values, incorporating state-of-the-art proposals. We show that in the random feature model, this formulation provably leads to training data reconstruction with high probability, provided the network width is sufficiently large; this unprecedented finite-width result uses PAC-style bounds. Furthermore, when the data lies in a low-dimensional subspace, we show that the network width requirement for successful reconstruction can be relaxed, with bounds depending on the subspace dimension rather than the ambient dimension. For general neural network models and unknown data orientations, we propose an efficient reconstruction algorithm that approximates the low-dimensional data subspace through the change in the first-layer weights during training and uses only the last-layer weights for reconstruction, thus reducing the search space dimension and the required network width for high-quality reconstructions. Our numerical experiments on synthetic datasets and CIFAR-10 confirm that our subspace-aware reconstruction approach outperforms standard full-space techniques. --- ### Learning to Cut: Reinforcement Learning for Benders Decomposition Authors: Haochen Cai, Xian Yu Published: 2026-05-07 Categories: math.OC, cs.AI arXiv: https://arxiv.org/abs/2605.06516v1 Benders decomposition (BD) is a widely used solution approach for solving two-stage stochastic programs arising in real-world decision-making under uncertainty. However, it often suffers from slow convergence as the master problem grows with an increasing number of cuts. In this paper, we propose Reinforcement Learning for BD (RLBD), a framework that adaptively selects cuts using a neural network-based stochastic policy. The policy is trained using a policy gradient method via the REINFORCE algorithm. We evaluate the proposed approach on a two-stage stochastic electric vehicle charging station location problem and compare it with vanilla BD and LearnBD, a supervised learning approach that classifies cuts using a support vector machine. Numerical results demonstrate that RLBD achieves substantial improvements in computational efficiency and exhibits strong generalization to problems with similar structures but varying data inputs and decision variable dimensions. --- ### DCR: Counterfactual Attractor Guidance for Rare Compositional Generation Authors: Taewon Kang, Matthias Zwicker Published: 2026-05-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.06512v1 Diffusion models generate realistic visual content, yet often fail to produce rare but plausible compositions. When prompted with combinations that are valid but underrepresented in training data, such as a snowy beach or a rainbow at night, the generation process frequently collapses toward more common alternatives. We identify this failure mode as default completion bias, where denoising trajectories are implicitly attracted toward high-frequency semantic configurations. Existing guidance mechanisms do not explicitly model this competing tendency and therefore struggle to prevent such collapse. We introduce Default Completion Repulsion (DCR), a training-free framework that explicitly models and suppresses default completion behavior. DCR constructs a counterfactual attractor by relaxing the rare compositional factor while preserving surrounding semantics, inducing an alternative denoising trajectory reflecting the model's preferred completion. We define the discrepancy between target and attractor trajectories as a counterfactual drift, and propose a projection-based repulsion mechanism that removes guidance components aligned with this drift direction. This suppresses undesired frequent completions while preserving other semantic components. DCR operates entirely within the standard diffusion sampling process without retraining or architectural modification. Experiments on rare compositional prompts show that DCR improves compositional fidelity while maintaining visual quality. Our analysis further shows that the framework exposes and counteracts intrinsic model biases, offering a new perspective on controllable generation beyond explicit constraint enforcement. --- ### Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models Authors: Amir Rezaei Balef, Mykhailo Koshil, Katharina Eggensperger Published: 2026-05-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.06510v1 Transformer-based tabular foundation models (TFMs) dominate small to medium tabular predictive benchmark tasks, yet their inference mechanisms remain largely unexplored. We present the first large-scale mechanistic study of layerwise dynamics in 6 state-of-the-art tabular in-context learning models. We explore how predictions emerge across depth, identify distinct stages of inference and reveal latent-space dynamics that differ from those of language models. Our findings indicate substantial depthwise redundancy across multiple models, suggesting iterative refinement with overlapping computations during inference stages. Guided by these insights, we design a proof-of-concept, looped single-layer model that uses only 20% of the original model's parameters while achieving comparable performance. The code is available at https://github.com/amirbalef/is_one_layer_enough. --- ### FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction Authors: Fangda Chen, Shanshan Zhao, Longrong Yang, Chuanfu Xu, Zhigang Luo, Long Lan Published: 2026-05-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.06509v1 Video diffusion models perform well in short-video synthesis, but their training-free extension to long videos often suffers from content drift, temporal inconsistency, and over-smoothed dynamics. Existing methods improve temporal consistency by combining a global branch with a local branch, but they often further decompose appearance consistency and temporal dynamics within each branch using predefined criteria. This assignment is unreliable when appearance and action progression are tightly coupled, such as in camera motion and sequential motion. We analyze the video temporal extension issue from a singular-spectrum perspective and show that enlarged self-attention windows induce spectral concentration: spectral energy becomes dominated by a few low-rank singular directions, preserving coarse structure but suppressing high-rank spatial details and motion-rich temporal variations. To mitigate this problem, we propose FreeSpec, a training-free spectral reconstruction framework for long-video generation. FreeSpec decomposes global and local features with singular value decomposition, and uses the global branch as low-rank spectral guidance and the local branch as a high-rank reconstruction basis. This spectrum-level fusion avoids the rigid feature partitioning of previous decomposition rules, preserving long-range consistency while better retaining spatial details and temporal dynamics. Experiments on Wan2.1 and LTX-Video demonstrate that FreeSpec improves long-video generation, especially for temporal dynamics, while maintaining strong visual quality and temporal consistency. Project demo: https://fdchen24.github.io/FreeSpec-Website/. --- ### Beyond Reproducibility: Towards Security-Aware Evaluation of Research Artifacts Authors: Nanda Rani, Christian Rossow Published: 2026-05-07 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2605.06508v2 Research artifacts are widely shared to support reproducibility, and artifact evaluation (AE) has become common at many leading conferences. However, AE mainly checks whether artifacts work as claimed and can be reproduced. It does not aim at spotting or mitigitating potential security risks. Since these artifacts are publicly released and reused, they may unintentionally create opportunities for misuse and raise concerns about safe and responsible sharing. We study 1,388 research artifacts published between 2023 and 2025 at the top-4 security conferences, perform static analysis, and obtain 132,431 candidate security findings. We propose a taxonomy for context-aware security assessment and examine the findings to filter false positives and identify findings that represent plausible context-dependent security risks. We find that 44.80% of the reviewed findings are security-relevant. To support scalable analysis, we present SAFE (Security-Aware Framework for Artifact Evaluation), an autonomous framework that assesses tool-reported findings based on code semantics, execution context, and practical exploitability. SAFE achieves 94.40% accuracy and a 93.60% F1-score in distinguishing security-relevant from non-security findings, and 92.40% accuracy and an 81.10% F1-score in classifying security-risk types. Overall, our results show that context-aware security assessment is a practical complement to existing AE processes and can support safer and more responsible research artifact sharing. The source code for SAFE is available at: https://github.com/nanda-rani/SAFE --- ### On the Security of Research Artifacts Authors: Nanda Rani, Christian Rossow Published: 2026-05-07 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2605.06508v1 Research artifacts are widely shared to support reproducibility, and artifact evaluation (AE) has become common at many leading conferences. However, AE mainly checks whether artifacts work as claimed and can be reproduced. It largely overlooks potential security risks. Since these artifacts are publicly released and reused, they may unintentionally create opportunities for misuse and raise concerns about safe and responsible sharing. We study 509 research artifacts from top-tier security venues and find that many contain insecure code patterns that may introduce potential attack vectors. We propose a taxonomy for context-aware security assessment to enable structured analysis of such risks. We perform static analysis and examine the resulting findings, filtering false positives and identifying real security risks. Our analysis shows that 41.60% of the prevalent findings may pose security concerns under practical usage. To support scalable analysis, we introduce SAFE (Security-Aware Framework for Artifact Evaluation), a first step toward an autonomous framework that analyzes tool-reported findings by considering code semantics, execution context, and practical exploitability. SAFE achieves 84.80% accuracy and 84.63% F1-score in distinguishing security and non-security risks. Overall, our results show that security is also important in AE for promoting safe and responsible research sharing. The source code is available at: https://github.com/nanda-rani/SAFE --- ### MARBLE: Multi-Aspect Reward Balance for Diffusion RL Authors: Canyu Zhao, Hao Chen, Yunze Tong, Yu Qiao, Jiacheng Li, Chunhua Shen Published: 2026-05-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.06507v1 Reinforcement learning fine-tuning has become the dominant approach for aligning diffusion models with human preferences. However, assessing images is intrinsically a multi-dimensional task, and multiple evaluation criteria need to be optimized simultaneously. Existing practice deal with multiple rewards by training one specialist model per reward, optimizing a weighted-sum reward $R(x)=\sum_k w_k R_k(x)$, or sequentially fine-tuning with a hand-crafted stage schedule. These approaches either fail to produce a unified model that can be jointly trained on all rewards or necessitates heavy manually tuned sequential training. We find that the failure stems from using a naive weighted-sum reward aggregation. This approach suffers from a sample-level mismatch because most rollouts are specialist samples, highly informative for certain reward dimensions but irrelevant for others; consequently, weighted summation dilutes their supervision. To address this issue, we propose MARBLE (Multi-Aspect Reward BaLancE), a gradient-space optimization framework that maintains independent advantage estimators for each reward, computes per-reward policy gradients, and harmonizes them into a single update direction without manually-tuned reward weighting, by solving a Quadratic Programming problem. We further propose an amortized formulation that exploits the affine structure of the loss used in DiffusionNFT, to reduce the per-step cost from K+1 backward passes to near single-reward baseline cost, together with EMA smoothing on the balancing coefficients to stabilize updates against transient single-batch fluctuations. On SD3.5 Medium with five rewards, MARBLE improves all five reward dimensions simultaneously, turns the worst-aligned reward's gradient cosine from negative under weighted summation in 80% of mini-batches to consistently positive, and runs at 0.97X the training speed of baseline training. --- ### The Frequency Confound in Language-Model Surprisal and Metaphor Novelty Authors: Omar Momen, Sina Zarrieß Published: 2026-05-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.06506v2 Language-model (LM) surprisal is widely used as a proxy for contextual predictability and has been reported to correlate with metaphor novelty judgments. However, surprisal is tightly intertwined with lexical frequency. We explore this interaction on metaphor novelty ratings using two different word frequency measures. We analyse surprisal estimates from eight Pythia model sizes and 154 training checkpoints. Across settings, word frequency is a stronger predictor of metaphor novelty than surprisal. Across training stages, the surprisal--novelty association peaks at an early stage and then falls again, mirroring a similarly timed increase in the surprisal--frequency association. These results suggest that the often-reported optimal LM surprisal settings may incorrectly associate contextual predictability with metaphor novelty and processing difficulty, whereas lexical frequency may be the major underlying factor. --- ### PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization Authors: Murat Bilgehan Ertan, Xiaochen Zhu, Phuong Ha Nguyen, Marten van Dijk, Srinivas Devadas Published: 2026-05-07 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.06505v2 We introduce PACZero, a family of PAC-private zeroth-order mechanisms for fine-tuning large language models that delivers usable utility at $I(S^*; Y_{1:T})=0$. This privacy regime bounds the membership-inference attack (MIA) posterior success rate at the prior, an MIA-resistance level the DP framework matches only at $\varepsilon=0$ and infinite noise. All DP-ZO comparisons below are matched at the MIA posterior level. The key insight is that PAC Privacy charges mutual information only when the release depends on which candidate subset is the secret. Sign-quantizing subset-aggregated zeroth-order gradients creates frequent unanimity, steps at which every candidate subset agrees on the update direction; at these steps the released sign costs zero conditional mutual information. We propose two variants that span the privacy-utility trade-off: PACZero-MI (budgeted MI via exact calibration on the binary release) and PACZero-ZPL ($I=0$ via a uniform coin flip on disagreement steps). We evaluate on SST-2 and SQuAD with OPT-1.3B and OPT-6.7B in both LoRA and full-parameter tracks. On SST-2 OPT-1.3B full fine-tuning at $I=0$, PACZero-ZPL reaches ${88.99\pm0.91}$, within $2.1$pp of the non-private MeZO baseline ($91.1$ FT). No prior method produces usable utility in the high-privacy regime $\varepsilon<1$, and PACZero-ZPL obtains competitive SST-2 accuracy and nontrivial SQuAD F1 across OPT-1.3B and OPT-6.7B at $I=0$. --- ### Cubit: Token Mixer with Kernel Ridge Regression Authors: Chuanyang Zheng, Jiankai Sun, Yihang Gao, Yuehao Wang, Liangchen Tan, Mac Schwager, Anderson Schneider, Yuriy Nevmyvaka, Xiaodong Liu Published: 2026-05-07 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.06501v3 Since its introduction in 2017, the Transformer has become one of the most widely adopted architectures in modern deep learning. Despite extensive efforts to improve positional encoding, attention mechanisms, and feed-forward networks, the core token-mixing mechanism in Transformers remains attention. In this work, we show that the attention module in Transformers can be interpreted as performing Nadaraya-Watson regression, where it computes similarities between tokens and aggregates the corresponding values accordingly. Motivated by this perspective, we propose Cubit, a potential next-generation architecture that leverages Kernel Ridge Regression (KRR), while the vanilla Transformer relies on Nadaraya-Watson regression. Specifically, Cubit modifies the classical attention computation by incorporating the closed-form solution of KRR, combining value aggregation through kernel similarities with normalization via the inverse of the kernel matrix. To improve the training stability, we further propose the Limited-Range Rescale (LRR), which rescales the value layer within a controlled range. We argue that Cubit, as a KRR-based architecture, provides a stronger mathematical foundation than the vanilla Transformer, whose attention mechanism corresponds to Nadaraya-Watson regression. We validate this claim through comprehensive experiments. The experimental results suggest that Cubit may exhibit stronger long-sequence modeling capability. In particular, its performance gain over the Transformer appears to increase as the training sequence length grows. --- ### Cubit: Token Mixer with Kernel Ridge Regression Authors: Chuanyang Zheng, Jiankai Sun, Yihang Gao, Yuehao Wang, Liangchen Tan, Mac Schwager, Anderson Schneider, Yuriy Nevmyvaka, Xiaodong Liu Published: 2026-05-07 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2605.06501v2 Since its introduction in 2017, the Transformer has become one of the most widely adopted architectures in modern deep learning. Despite extensive efforts to improve positional encoding, attention mechanisms, and feed-forward networks, the core token-mixing mechanism in Transformers remains attention. In this work, we show that the attention module in Transformers can be interpreted as performing Nadaraya-Watson regression, where it computes similarities between tokens and aggregates the corresponding values accordingly. Motivated by this perspective, we propose Cubit, a potential next-generation architecture that leverages Kernel Ridge Regression (KRR), while the vanilla Transformer relies on Nadaraya-Watson regression. Specifically, Cubit modifies the classical attention computation by incorporating the closed-form solution of KRR, combining value aggregation through kernel similarities with normalization via the inverse of the kernel matrix. To improve the training stability, we further propose the Limited-Range Rescale (LRR), which rescales the value layer within a controlled range. We argue that Cubit, as a KRR-based architecture, provides a stronger mathematical foundation than the vanilla Transformer, whose attention mechanism corresponds to Nadaraya-Watson regression. We validate this claim through comprehensive experiments. The experimental results suggest that Cubit may exhibit stronger long-sequence modeling capability. In particular, its performance gain over the Transformer appears to increase as the training sequence length grows. --- ### Operator-Guided Invariance Learning for Continuous Reinforcement Learning Authors: Zuyuan Zhang, Fei Xu Yu, Tian Lan Published: 2026-05-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.06500v1 Reinforcement learning (RL) with continuous time and state/action spaces is often data-intensive and brittle under nuisance variability and shift, motivating methods that exploit value-preserving structures to stabilize and improve learning. Most existing approaches focus on special cases, such as prescribed symmetries and exact equivariance, without addressing how to discover more general structures that require nonlinear operators to transform and map between continuous state/action systems with isomorphic value functions. We propose \textbf{VPSD-RL} (Value-Preserving Structure Discovery for Reinforcement Learning). It models continuous RL as a controlled diffusion with value-preserving mappings defined through Lie-group actions and associated pullback operators. We show that a value-preserving structure exists exactly when pulling back the value function and pushing forward actions commute with the controlled generator and reward functional. Further, approximate value-preserving structures with rigorous guarantees can be found when the Hamilton--Jacobi--Bellman mismatch is small. This framework discovers exact and approximate value-preserving structures by searching for the associated Lie group operators. VPSD-RL fits differentiable drift, diffusion, and reward models; learns infinitesimal generators via determining-equation residual minimization; exponentiates them with ODE flows to obtain finite transformations; and integrates them into continuous RL through transition augmentation and transformation-consistency regularization. We show that bounded generator/reward mismatch implies quantitative stability of the optimal value function along approximate orbits, with sensitivity governed by the effective horizon, and observe improved data efficiency and robustness on continuous-control benchmarks. --- ### From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features Authors: Ruben Fernandez-Boullon, Pablo Magariños-Docampo, Javier Perez-Robles Published: 2026-05-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.06494v1 Sparse autoencoders (SAEs) have become central to mechanistic interpretability, decomposing transformer activations into monosemantic features. Yet existing analyses characterise features almost exclusively through top-activating token lists or decoder weight vectors, leaving the higher-order co-occurrence structure shared across features largely unexamined. We introduce a graph-structured representation in which each SAE feature is modelled as a token co-occurrence graph: nodes are the tokens most frequent near strong activations, and edges connect pairs that co-occur within local context windows. A custom WL-style, frequency-binned graph kernel then provides a similarity measure over this structural space. Applied as a proof of concept to features from a large SAE trained on GPT-2 Small and probed with a synthetic mixed-domain corpus, our clustering recovers heuristic motif families (punctuation-heavy patterns, language and script clusters, and code-like templates) that are not recovered by clustering on decoder cosine similarity. A token-histogram baseline achieves higher overall purity, so the contribution of the graph view is complementary rather than dominant: it surfaces structural relationships that token-frequency and decoder-weight views alone do not capture. Cluster assignments are stable across graph-construction hyperparameters and random seeds. --- ### Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors Authors: Jonas Wiedermann-Möller, Leonard Dung, Maksym Andriushchenko Published: 2026-05-07 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2605.06490v1 AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful for certain goals? We introduce a benchmark for measuring model propensity for instrumental convergence (IC) behaviour in terminal-based agents. This is behaviour such as self-preservation that has been hypothesised to play a key role in risks from highly capable AI agents. Our benchmark is realistic and low-stakes which serves to reduce evaluation-awareness and roleplay confounds. The suite contains seven operational tasks, each with an official workflow and a policy-violating shortcut. An eight-variant shared framework varies monitoring, instruction clarity, stakes, permission, instrumental usefulness and blocked honest paths to support inferences regarding the factors driving IC behaviour. We evaluated ten models using deterministic environment-state scorers over 1,680 samples, with trace review employed for audit and adjudication purposes. The final IC rate is 86 out of 1,680 samples (5.1%). IC behaviour is concentrated rather than uniform: two Gemini models account for 66.3% of IC cases and three tasks account for 84.9%. Conditions in which IC behaviour is indispensable for task success result in the greatest increase in the adjusted IC rate (+15.7 percentage points), whereas emphasising that task success is critical or certain framing choices do not produce comparable effects. Our findings indicate that realistic, low-nudge environments elicit IC behaviour rarely but systematically in most tested models. We conclude that it is feasible to robustly measure tendencies for dangerous behaviour in current frontier AI agents. --- ### 3D MRI Image Pretraining via Controllable 2D Slice Navigation Task Authors: Yu Wang, Qingchao Chen Published: 2026-05-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.06487v1 Self-supervised pretraining has become the mainstream approach for learning MRI representations from unlabeled scans. However, most existing objectives still treat each scan primarily as static aggregations of slices, patches or volumes. We ask whether there exists an intrinsic form of self-supervision signal that is different from reconstructing the masked patches, through transforming the 3D volumes into controllable 2D rendered sequences: by rendering slices at continuous positions, orientations, and scales, a 3D volume can be converted into dense video-action sequences whose controls are the action trajectories. We study this formulation with an action-conditioned pretraining objective, where a tokenizer encodes slice observations and a latent dynamics model predicts the evolution of latent features. Across representative anatomical and spatial downstream tasks, the proposed pretraining is evaluated against standard static-volume baselines, tokenizer-only pretraining, and dynamics variants without aligned actions. These results suggest that controllable MRI slice navigation provides a useful complementary pretraining interface for learning anatomical and spatial representations from large unlabeled MRI collections. --- ### Litespark Inference For CPUs: Ultra-Fast SIMD Framework for Ternary (1.58-bit) Language Models Authors: Nii Osae Osae Dade, Tony Morri, Moinul Hossain Rahat, Sayandip Pal, Rickston Pinto Published: 2026-05-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.06485v2 Large language models (LLMs) have transformed artificial intelligence, but their computational requirements remain prohibitive for most users. Standard inference demands expensive datacenter GPUs or cloud API access, leaving over one billion personal computers underutilized for AI workloads. Ternary models offer a path forward: their weights are constrained to {-1, 0, +1}, theoretically eliminating the need for floating-point multiplication. However, existing frameworks fail to exploit this structure, treating ternary models as dense floating-point networks. We address this gap with custom SIMD kernels that replace matrix multiplication with simple addition and subtraction operations, targeting the integer dot product instructions available on modern CPUs. Our implementation, Litespark-Inference, is pip-installable and integrates directly with Hugging-Face, achieving 18.15x higher throughput, 7.15x faster time-to-first-token and 6.03x memory reduction compared to standard PyTorch inference on Apple Silicon, with comparable or higher throughput speedups up to 95.81x on Intel and AMD processors. --- ### Estimate Level Adjustment For Inference With Proxies Under Random Distribution Shifts Authors: Steven Wilkins-Reeves, Alexandra N. M. Darmon, Deeksha Sinha Published: 2026-05-07 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.06484v1 In many scientific domains, including experimentation, researchers rely on measurements of proxy outcomes to achieve faster and more frequent reads, especially when the primary outcome of interest is challenging to measure directly. While proxies offer a more readily accessible observation for inference, the ultimate goal is to draw statistical inferences about the primary outcome parameter and proxy data are typically imperfect in some ways. To correct for these imperfections, current statistical inference methods often depend on strict identifying assumptions (such as surrogacy, covariate/label shift, or missingness assumptions). These assumptions can be difficult to validate and may be violated by various additional sources of distribution shift, potentially leading to biased parameter estimates and miscalibrated uncertainty quantification. We introduce an estimate-level framework, inspired by domain adaptation techniques, to empirically calibrate proxy-based inference. This framework models the proxy-primary metric discrepancy as a random effect at the parameter level, estimating its distribution from aggregated historical observations across past domains (e.g., experiments, time periods, or distinct segments). This method avoids the requirement for retaining individual-level response data. Additionally, this adjustment can be layered on top of existing proxy-correction methods (such as prediction-powered inference or importance weighting) to account for additional biases not addressed by those corrections. To manage uncertainty when the number of historical domains is limited, we provide both a method-of-moments estimator and a domain bootstrap procedure. We further validate this approach using publicly available datasets and real-world experiments. --- ### ReasonSTL: Bridging Natural Language and Signal Temporal Logic via Tool-Augmented Process-Rewarded Learning Authors: Bowen Ye, Zhijian Li, Junyue Huang, Junkai Ma, Xiang Yin Published: 2026-05-07 Categories: cs.AI, cs.RO, eess.SY arXiv: https://arxiv.org/abs/2605.06483v2 Signal Temporal Logic (STL) is an expressive formal language for specifying spatio-temporal requirements over real-valued, real-time signals. It has been widely used for the verification and synthesis of autonomous systems and cyber-physical systems. In practice, however, users often express their requirements in natural language rather than in structured STL formulas, making natural-language-to-STL translation a critical yet challenging task. Manual specification requires temporal-logic expertise and cannot scale, while prompting commercial LLM APIs incurs substantial token costs and may expose sensitive system requirements to third-party services, raising privacy concerns for industrial deployment. To address these challenges, we present \textsc{ReasonSTL}, a tool-augmented framework that adapts local open-source language models for natural-language-to-STL generation. \textsc{ReasonSTL} decomposes the translation process into explicit reasoning, deterministic tool calls, and structured formula construction. We further introduce process-rewarded training to supervise both tool-use trajectories and final formulas, together with \textsc{STL-Bench}, a bilingual, computation-aware benchmark grounded in real-world signals. Experiments show that a 4B model trained with \textsc{ReasonSTL} achieves state-of-the-art performance in both automatic metrics and human evaluations, demonstrating that \textsc{ReasonSTL} provides a transparent, low-cost, and privacy-preserving alternative for formal specification drafting. --- ### Patch-Effect Graph Kernels for LLM Interpretability Authors: Ruben Fernandez-Boullon, David N. Olivieri Published: 2026-05-07 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.06480v1 Mechanistic interpretability aims to reverse-engineer transformer computations by identifying causal circuits through activation patching. However, scaling these interventions across diverse prompts and task families produces high-dimensional, unstructured datasets that are difficult to compare systematically. We propose a framework that reframes mechanistic analysis as a graph machine-learning problem by representing activation-patching profiles as patch-effect graphs over model components. We introduce three graph-construction methods: direct-influence via causal mediation, partial-correlation, and co-influence and apply graph kernels to analyze the resulting structures. Evaluating this approach on GPT-2 Small using Indirect Object Identification (IOI) and related tasks, we find that patch-effect graphs preserve discriminative structural signals. Specifically, localized edge-slot features provide higher classification accuracy than global graph-shape descriptors. A screened paired-patching validation suggests that CI and PC selected candidate edges correspond to stronger activation-influence effects than random or low-rank candidates. Crucially, by evaluating these representations against rigorous prompt-only and raw patch-effect controls, we make the evidential scope of the benchmark explicit: graph features compress structured patching signal, while raw tensors and surface cues define strong baselines that any circuit-level claim should address. Ultimately, our framework provides a compression and evaluation pipeline for comparing patching-derived structures under controlled baselines, separating robust slice-discriminative evidence from stronger task-general causal-circuit claims. --- ### Risk-Controlled Post-Processing of Decision Policies Authors: Sunay Joshi, Tao Wang, Hamed Hassani, Edgar Dobriban Published: 2026-05-07 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2605.06479v1 Predictive models are often deployed through existing decision policies that stakeholders are reluctant to change unless a risk constraint requires intervention. We study risk-controlled post-processing: given a deterministic baseline policy, choose a new policy that maximizes agreement with the baseline subject to a chance constraint on a user-specified loss. At the population level, we show that the optimal policy has a threshold structure: it follows the baseline except on contexts where switching to the oracle fallback policy yields a large reduction in conditional violation risk. At the finite-sample level, given a fitted fallback policy and score, we develop a post-processing algorithm that uses calibration data to select a threshold. Leveraging tools from algorithmic stability and stochastic processes, we show that under regularity conditions, in the i.i.d. setting, the expected excess risk of the post-processed policy is $O(\log n/n)$. In the special case when an exact-safe fallback policy is available, the algorithm achieves precise expected risk control under exchangeability. In this setting, we also give high-probability near-optimality guarantees on the post-processed policy. Experiments on a COVID-19 radiograph diagnosis task, an LLM routing problem, and a synthetic multiclass decision task show that targeted post-processing can meet or nearly meet risk budgets while preserving substantially more agreement with the baseline than score-blind random mixing. --- ### GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs Authors: Pranav Mantini, Shishir K. Shah Published: 2026-05-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.06477v1 We address the challenge of knowledge composition in Vision-Language Models (VLMs), where accumulating expertise across multiple domains or tasks typically leads to catastrophic forgetting. We introduce GeoStack (Geometric Stacking), a modular framework that allows independently trained domain experts to be composed into a unified model. By imposing geometric and structural constraints on the adapter manifold, GeoStack ensures the foundational knowledge of the base model is preserved. Furthermore, we mathematically demonstrate a weight-folding property that achieves constant-time inference complexity ($O(1)$), regardless of the number of integrated experts. Experimental results across multi-domain adaptation and class-incremental learning show that GeoStack provides an efficient mechanism for long-term knowledge composition while significantly mitigating catastrophic forgetting. Code is available at https://github.com/QuantitativeImagingLaboratory/GeoStack. --- ### Towards Emotion Consistency Analysis of Large Language Models in Emotional Conversational Contexts Authors: Sneha Oram, Ojaswita Bhushan, Pushpak Bhattacharyya Published: 2026-05-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.06476v1 In this work, we conduct an analysis to examine the consistency of Large Language Models (LLMs) with respect to their own generated responses in an emotionally-driven conversational context. Specifically, the text generated by LLM is framed as a query to the same model, and its responses are subsequently assessed. This is performed with three queries across two dimensions of extreme and moderate emotions. The three queries are, in particular, false claim queries that contain inherently wrong assumptions (false presuppositions) in increasing order of intensity. Two commercial models, Claude-3.5-haiku, GPT4o-mini, and a medium-sized model, Mistral-7B, are considered in the study. Our findings indicate that LLMs exhibit below-average performance and remain vulnerable to false beliefs embedded within queries. This susceptibility is especially pronounced for moderate emotional content. Furthermore, an extended attention-score-based analysis highlights a shift in models' priority from evaluative to generative. The results raise important considerations for LLMs' deployment in high-stakes, emotionally sensitive contexts. --- ### Probabilistic Dating of Historical Manuscripts via Evidential Deep Regression on Visual Script Features Authors: Ranjith Chodavarapu Published: 2026-05-07 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2605.06475v1 We introduce a probabilistic approach for dating historical manuscript pages from visual features alone. Instead of aggregating centuries into classes as is standard in the previous literature, we pose dating as an evidential deep regression problem over a continuous year axis, allowing our neural network to output a full predictive distribution with decomposed aleatoric and epistemic uncertainty in a single forward pass. Our architecture combines an EfficientNet-B2 backbone with a Normal-Inverse-Gamma (NIG) output head trained with a joint negative-log-likelihood and evidence-regularization objective. On the DIVA-HisDB benchmark (150 pages, 3 medieval codices, 151,936 patches), our model scores a test MAE of 5.4 years, well below the 50-year century-label supervision granularity, with 93\% of patches within 5 years and 97\% within 10 years. Our approach achieves \textbf{PICP=92.6\%}, the best calibration among all compared methods, in a single forward pass, outperforming MC Dropout (PICP=88.2\%, 50 passes) and Deep Ensembles (PICP=79.7\%, 5 models) at $5\times$ lower inference cost. Uncertainty decomposition shows aleatoric uncertainty is a strong predictor of dating error (Spearman $ρ=0.729$), and a selective prediction about the most certain 20\% of patches can provide \textbf{0.5 years MAE}. We show that predicted uncertainty increases as image degradation worsens, spatial decomposition maps explain which script regions cause aleatoric uncertainty, and page-level aggregation reduces MAE to 4.5 years with $ρ=0.905$ between uncertainty and page-level error. --- ### Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching Authors: Xiang Li, Nan Jiang Published: 2026-05-07 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2605.06474v2 We present a novel theoretical framework, Q-MMR, for off-policy evaluation in finite-horizon MDPs. Q-MMR learns a set of scalar weights, one for each data point, such that the reweighted rewards approximate the expected return under the target policy. The weights are learned inductively in a top-down manner via a moment matching objective against a value-function discriminator class. Notably, and perhaps surprisingly, a data-dependent finite-sample guarantee for general function approximation can be established under only the realizability of $Q^π$, with a dimension-free bound -- that is, the error does not depend on the statistical complexity of the function class. We also establish connections to several existing methods, such as importance sampling and linear FQE. Further theoretical analyses shed new light on the nature of coverage, a concept of fundamental importance to offline RL. --- ### Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management Authors: Haoyu Zheng, Fangcheng Fu, Jia Wu, Binhang Yuan, Yongqiang Zhang, Hao Wang, Yuanyuan Zhu, Xiao Yan, Jiawei Jiang Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06472v1 LLM-based workflows compose specialized agents to execute complex tasks, and these agents usually share substantial context, allowing KV-Cache reuse to save computation. Existing approaches either manage KV-Cache at agent level and fail to exploit the reuse opportunities within workflows, or manage cache at the workflow level but assume that each workflow calls a static sequence of agents. However, practical workflows are typically dynamic, where the sequence of invoked agents and thus induced cache reuse opportunities depend on the context of each task. To serve such dynamic workflows efficiently, we build a system dubbed PBKV (\textbf{P}rediction-\textbf{B}ased \textbf{KV}-Cache Management). For each workflow, PBKV predicts the agent invocations in several future steps by fusing the guidance from historical workflows and context of the target workflow. Based on the predictions, PBKV estimates the reuse potential of cache entries and keeps the high-potential entries in GPU memory. To be robust to prediction errors, PBKV utilizes the predictions conservatively during both cache eviction and prefetching. Experiments on three workflow benchmarks show that PBKV achieves up to $1.85\times$ speedup over LRU on dynamic workflows, and up to $1.26\times$ speedup over the SOTA baseline KVFlow on the static workflow. --- ### Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies Authors: Magnus Victor Boock, Abdullah Akgül, Mustafa Mert Çelikok, Melih Kandemir Published: 2026-05-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.06470v1 We present a new operator-theoretic representation learning framework for offline reinforcement learning that recovers the directed temporal geometry of a controlled Markov process from hitting time observations. While prior art often produces symmetric distances or fails to satisfy the triangle inequality, our framework learns a Hilbert-space displacement geometry where expected hitting times are realized as linear functionals of latent displacements. We prove that this representation exists under latent linear closure and is uniquely identifiable up to a bounded linear isomorphism. For finite-dimensional implementations, we show that global hitting-time error is bounded by one-step transition error amplified by the environment's transient spectral radius. Furthermore, we provide finite-sample guarantees accounting for approximation, statistical complexity, and trajectory-label mismatch. Derived from this theory, we curate Isomorphic Embedding Learning (IEL) as a new goal-agnostic foundation policy learning algorithm that anchors a HILP-style consistency objective with explicit hitting-time regression to ensure that the learned geometry reflects actual decision-time progress. This asymmetric and compositional structure enables robust graph-based multi-stage planning for long-horizon navigation. Our experiments demonstrate that IEL improves the state of the art of learning foundation policy policies from offline maze locomotion data. Our code can be found on https://github.com/MagnusBoock/IEL --- ### Dynamic Controlled Variables Based Dynamic Self-Optimizing Control Authors: Chenchen Zhou, Shaoqi Wang, Hongxin Su, Xinhui Tang, Yi Cao, Shuang-Hua Yang Published: 2026-05-07 Categories: math.OC, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2605.06469v1 Self-optimizing control is a strategy for selecting controlled variables, where the economic objective guides the selection and design of controlled variables, with the expectation that maintaining the controlled variables at constant values can achieve optimization effects, translating the process optimization problem into a process control problem. Currently, self-optimizing control is widely applied to steady-state optimization problems. However, the development of process systems exhibits a trend towards refinement, highlighting the importance of optimizing dynamic processes such as batch processes and grade transitions. This paper formally introduces the self-optimizing control problem for dynamic optimization, termed the dynamic self-optimizing control problem, extending the original definition of self-optimizing control. A novel concept, "dynamic controlled variables" (DCVs), is proposed, and an implicit control policy is presented based on this concept. The paper theoretically analyzes the advantages and generality of DCVs compared to explicit control strategies and elucidates the relationship between DCVs and traditional controllers. Moreover, this paper puts forth a data-driven approach to designing self-optimizing DCVs, which considers DCV design as a mapping identification problem and employs deep neural networks to parameterize the variables. Three case studies validate the efficacy and superiority of DCVs in approximating multi-valued and discontinuous functions, as well as their application to dynamic optimization problems with non-fixed horizons, which traditional self-optimizing control methods are unable to address. ---