# Research Papers — 2026-05 · bundle page 223 of 326

> Full-text markdown of papers #11101–11150 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/223
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/222.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/224.md)

### AdaPaD: Adaptive Parallel Deflation for PEFT with Self-Correcting Rank Discovery

Authors: Barbara Su, Fangshuo Liao, Anastasios Kyrillidis
Published: 2026-05-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.10741v1

Fine-tuning large language models with LoRA requires choosing a rank r before training starts. Existing approaches either extract rank-1 components sequentially, freezing each component's error permanently into every subsequent residual, or optimize the full low-rank factorization jointly with guarantees that describe only the joint update, not individual rank-1 directions. We present AdaPaD (Adaptive Parallel Deflation), which trains all rank-1 components simultaneously: each worker refines its component against a deflation target built from the latest estimates of all predecessors, and as those estimates improve, the targets improve too. We call this property self-correction: deflation errors converge to zero over rounds rather than persisting as fixed residuals. On top of this backbone, AdaPaD adds advance learning (private pre-training before activation) and per-module dynamic rank discovery (importance-based growth until a shared budget is exhausted), making the rank distribution an output rather than an input. We prove that every component's error decays exponentially after a warm-up period, with a generalization bound that splits into a vanishing algorithmic term and an irreducible statistical floor. Empirically, AdaPaD is competitive with adaptive-rank LoRA baselines on GLUE with DeBERTaV3-base at matched parameter budgets, and competitive with fixed-rank LoRA on Qwen3-0.6B SQuAD/SQuAD v2 while deploying an adapter that is on average 30.7% smaller.

---

### Geospatial-Temporal Sensemaking of Remote Sensing Activity Detections with Multimodal Large Language Model

Authors: David F. Ramirez, Tim Overman, Kristen Jaskie, Andreas Spanias
Published: 2026-05-11
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2605.10739v1

We introduce SMART-HC-VQA, a Sentinel-2-based visual question answering dataset derived from the IARPA SMART Heavy Construction dataset, designed for spatiotemporal analysis of human activity. The dataset transforms construction-site annotations, construction-type labels, temporal-phase labels, geographic metadata, and observation relationships into natural language question-answer triplets. This approach redefines the existing dataset as a temporally extended automatic target recognition and visual question answering (VQA) challenge, considering a fixed geospatial site as a target whose attributes and activity states evolve across sparse satellite observations. Currently, SMART-HC-VQA comprises 21,837 accessible Sentinel-2 image chips, 65,511 single-image VQA examples, and approximately 2.3 million two-image temporal comparison examples generated via our novel Image-Pairwise Combinatorial Augmentation. We detail the workflow for retrieving and processing Sentinel-2 imagery, segmenting large satellite tiles into site-centered images, maintaining traceability to SMART-HC annotations, and analyzing the distributions of site size, observation count, temporal coverage, construction type, and phase labels. Additionally, we describe an implemented multi-image MLLM training framework based on LLaVA-NeXT Mistral-7B, adapted to accept multiple dated image inputs and train on metadata-derived VQA examples. This work offers a reproducible foundation for understanding language-guided remote sensing activities, aiming not only to detect change but also to reason about the ongoing processes, their progression, and potential future developments.

---

### XQCfD: Accelerating Fast Actor-Critic Algorithms with Prior Data and Prior Policies

Authors: Daniel Palenicek, Florian Vogt, Joe Watson, Ingmar Posner, Danica Kragic, Jan Peters
Published: 2026-05-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.10734v1

For reinforcement learning in the real world online exploration is expensive A common practice in robotic reinforcement learning is to incorporate additional data to improve sample efficiency Expert demonstration data is often crucial for solving hard exploration tasks with sparse rewards While prior data is used to augment experience and pretrain models we show that the design of existing algorithms fails to achieve the sample efficiency that is possible in this setting due to a failure to use pretrained policies effectively We propose XQCfD which extends the sample-efficient XQC actor-critic to learn from demonstrations using augmented replay buffers pretrained policies and stationary policy architectures designed to avoid rapidly unlearning the strong initial policy like prior works We show our stationary network architecture enables policy improvement out-of-distribution better than standard network architectures due to its higher entropy predictions XQCfD achieves state of the art performance across a range of complex manipulation tasks with sparse rewards from the popular Adroit Robomimic and MimicGen benchmarks -- notably with a low update-to-data ratio and no ensemble networks

---

### iPay: Integrated Payment Action Recognition via Multimodal Networks and Adaptive Spatial Prior Learning

Authors: Kaicong Huang, Weiheng Oh, Thomas Guggisberg, Ruimin Ke
Published: 2026-05-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.10732v1

Automated transit payment analysis is vital for scalable fare auditing and passenger analytics, yet practice still relies on limited manual inspection. Prior vision- and skeleton-based methods remain brittle under noisy onboard surveillance and often depend on poorly generalizable handcrafted features. Building on the success of graph convolutional networks in human action recognition, we observe that skeleton features excel at modeling global spatiotemporal dependencies but tend to underemphasize the subtle local relative motions that distinguish payment actions. In contrast, RGB features preserve fine-grained spatial details yet often lack reliable temporal continuity in surveillance footage. To bridge both system-level deployment needs and model-level design challenges, we present iPay, an integrated payment action recognition framework for onboard transit surveillance system. iPay adopts a multimodal mixture-of-experts architecture with four tightly coupled streams: (1) an RGB expert stream emphasizing local evidence via region-focused computation; (2) a skeleton expert stream modeling articulated motion with a graph convolutional backbone; (3) a dual-attention fusion stream enabling skeleton-to-RGB temporal transfer and RGB-to-skeleton spatial enhancement; and (4) a prior-driven Spatial Difference Discriminator (SDD) that explicitly models hand-to-anchor relative motion to improve task-specific discriminability. We also collaborate with local transit agencies to collect over 55 hours of real onboard surveillance footage, yielding 500+ payment clips. Experiments show that iPay outperforms prior methods and achieves 83.45\% recognition accuracy with competitive computational efficiency, making it suitable for edge deployment. Code is available at https://github.com/ccoopq/iPay.

---

### Qwen-Image-2.0 Technical Report

Authors: Bing Zhao, Chenfei Wu, Deqing Li, Hao Meng, Jiahao Li, Jie Zhang, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kuan Cao, Kun Yan, Liang Peng et al.
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10730v1

We present Qwen-Image-2.0, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a single framework. Despite recent progress, existing models still struggle with ultra-long text rendering, multilingual typography, high-resolution photorealism, robust instruction following, and efficient deployment, especially in text-rich and compositionally complex scenarios. Qwen-Image-2.0 addresses these challenges by coupling Qwen3-VL as the condition encoder with a Multimodal Diffusion Transformer for joint condition-target modeling, supported by large-scale data curation and a customized multi-stage training pipeline. This enables strong multimodal understanding while preserving flexible generation and editing capabilities. The model supports instructions of up to 1K tokens for generating text-rich content such as slides, posters, infographics, and comics, while significantly improving multilingual text fidelity and typography. It also enhances photorealistic generation with richer details, more realistic textures, and coherent lighting, and follows complex prompts more reliably across diverse styles. Extensive human evaluations show that Qwen-Image-2.0 substantially outperforms previous Qwen-Image models in both generation and editing, marking a step toward more general, reliable, and practical image generation foundation models.

---

### Kernel-Gradient Drifting Models

Authors: Maria Esteban-Casadevall, Jorge Carrasco-Pollo, Max Welling, Jan-Willem van de Meent, Erik J. Bekkers, Floor Eijkelboom
Published: 2026-05-11
Categories: cs.LG, math.DG
arXiv: https://arxiv.org/abs/2605.10727v1

We propose kernel-gradient drifting, a one-step generative modeling framework that replaces the fixed Euclidean displacement direction in drifting models with directions induced by the kernel itself. Standard drifting is attractive because it enables fast, high-quality generation without distilling a large pretrained diffusion model, but its theory is currently understood mainly for Gaussian kernels, where the drift coincides with smoothed score matching and is identifiable. Our gradient-based reformulation exposes this score-based structure for general kernels: the resulting drift is the score difference between kernel-smoothed data and model distributions, yielding identifiability for characteristic kernels and a smoothed-KL descent interpretation of the drifting dynamics. Since kernel gradients are intrinsic tangent vectors, the same construction extends naturally to Riemannian manifolds and to discrete data via the Fisher-Rao geometry of the probability simplex. Across spherical geospatial data, promoter DNA and molecule generation, kernel-gradient drifting enables state-of-the-art one-step generation beyond the Euclidean setting without distillation.

---

### AgentMV: A State-Guided Multi-Agent Framework for Budget-Aware Music Video Generation

Authors: Huimin Wang, Chang Xia, Leilei Ouyang, Yongqi Kang, Yu Fu, Yuqi Ouyang
Published: 2026-05-11
Categories: cs.CV, cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2605.10723v2

Generating a complete music video from a song requires more than synthesizing visually plausible clips for individual lyric prompts. A practical system must maintain long-range visual consistency, coordinate recurring motifs, synchronize edits with musical structure, and manage the cumulative cost of video generation. Existing approaches typically generate segments independently or adopt fixed generation strategies, limiting their ability to perform global planning over an entire song. We present AgentMV, a state-guided multi-agent framework for budget-aware music video generation. AgentMV decomposes the production process into specialized agents for music perception, script planning, visual asset provision, segment realization, and final assembly, coordinated through a Structured Persistent State that enables information exchange and state tracking throughout the generation process. To optimize generation resources, we formulate motif-aware segment realization as a group-level Multiple-Choice Knapsack Problem solved via dynamic programming, considering segment importance, generation quality, cost, and motif reuse under a global budget constraint. Experiments on song benchmarks demonstrate that AgentMV improves quality-cost trade-offs over existing MV generation frameworks, highlighting the potential of state-guided multi-agent coordination and budget-aware planning for long-form music video generation with improved quality and efficiency.

---

### AllocMV: Optimal Resource Allocation for Music Video Generation via Structured Persistent State

Authors: Huimin Wang, Leilei Ouyang, Chang Xia, Yongqi Kang, Yu Fu, Yuqi Ouyang
Published: 2026-05-11
Categories: cs.CV, cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2605.10723v1

Generating long-horizon music videos (MVs) is frequently constrained by prohibitive computational costs and difficulty maintaining cross-shot consistency. We propose AllocMV, a hierarchical framework formulating music video synthesis as a Multiple-Choice Knapsack Problem (MCKP). AllocMV represents the video's persistent state as a compact, structured object comprising character entities, scene priors, and sharing graphs, produced by a global planner prior to realization. By estimating segment saliency from multimodal cues, a group-level MCKP solver based on dynamic programming optimally allocates resources across High-Gen, Mid-Gen, and Reuse branches. For repetitive musical motifs, we implement a divergence-based forking strategy that reuses visual prefixes to reduce costs while ensuring motif-level continuity. Evaluated via the Cost-Quality Ratio (CQR), AllocMV achieves an optimal trade-off between perceived quality and resource expenditure under strict budgetary and rhythmic constraints.

---

### On Improving Graph Neural Networks for QSAR by Pre-training on Extended-Connectivity Fingerprints

Authors: Sam Money-Kyrle, Markus Dablander, Thierry Hanser, Stephane Werner, Charlotte M. Deane, Garrett M. Morris
Published: 2026-05-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.10722v1

Molecular Graph Neural Networks (GNNs) are increasingly common in drug discovery, particularly for Quantitative Structure-Activity Relationship (QSAR) studies; yet, their superiority compared to classical molecular featurisation approaches is disputed. We report a general strategy for improving GNNs for QSAR by pre-training to predict Extended-Connectivity Fingerprints (ECFP). We validate our approach with statistical tests and challenging out-of-distribution (OOD) splits. Across five out of six Biogen benchmarks, we observed a statistically significant improvement in standard performance metrics over all evaluated baselines when using ECFP pre-trained GNNs. However, for more heterogeneous datasets and more complex endpoints, such as binding affinity prediction, pre-trained GNNs underperformed in OOD settings. Importantly, we investigated the impact of substructure-level data leakage during pre-training on downstream performance. While we identified scenarios where pre-training on ECFPs was less effective, our findings show that ECFP-based pre-training can enhance downstream OOD performance on a diverse set of practically relevant QSAR tasks.

---

### Conformity Generates Collective Misalignment in AI Agents Societies

Authors: Giordano De Marzo, Alessandro Bellina, Claudio Castellano, Viola Priesemann, David Garcia
Published: 2026-05-11
Categories: physics.soc-ph, cs.CL, cs.MA
arXiv: https://arxiv.org/abs/2605.10721v1

Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations where social influence may override individual alignment. Here we show that populations of individually aligned AI agents can be driven into stable misaligned states through conformity dynamics. Simulating opinion dynamics across nine large language models and one hundred opinion pairs, we find that each agent's behavior is governed by two competing forces: a tendency to follow the majority and an intrinsic bias toward specific positions. Using tools from statistical physics, we derive a quantitative theory that predicts when populations become trapped in long-lived misaligned configurations, and identifies predictable tipping points where small numbers of adversarial agents can irreversibly shift population-level alignment even after manipulation ceases. These results demonstrate that individual-level alignment provides no guarantee of collective safety, calling for evaluation frameworks that account for emergent behavior in AI populations.

---

### An Uncertainty-Aware Resilience Micro-Agent for Causal Observability in the Computing Continuum

Authors: Suvi De Silva, Alfreds Lapkovskis, Alaa Saleh, Sasu Tarkoma, Praveen Kumar Donta
Published: 2026-05-11
Categories: cs.DC, cs.AI, cs.LG, cs.PF, eess.SY
arXiv: https://arxiv.org/abs/2605.10718v2

Grey failures in the computing continuum produce ambiguous overlapping symptoms that existing approaches fail to diagnose reliably, either due to a lack of causal awareness or acting under high epistemic uncertainty, risking destructive interventions. This paper presents an uncertainty-aware resilience micro-agent for causal observability (AURORA), a lightweight framework for diagnosing and mitigating grey failures in edge-tier environments. The framework employs parallel micro-agents that integrate the free-energy principle, causal do-calculus, and localized causal state-graphs to support counterfactual root-cause analysis within each fault's Markov blanket. Restricting inference to causally relevant variables reduces computational overhead while preserving diagnostic fidelity. AURORA further introduces a dual-gated execution mechanism that authorizes remediation only when causal confidence is high and predicted epistemic uncertainty is bounded; otherwise, it abstains from local intervention and escalates the diagnostic payload to the fog tier. Our experiments demonstrate that AURORA outperforms baselines, achieving a 0% destructive action rate, while maintaining 62.0% repair accuracy and a 3ms mean time to repair.

---

### Heteroscedastic Diffusion for Multi-Agent Trajectory Modeling

Authors: Guillem Capellera, Antonio Rubio, Luis Ferraz, Antonio Agudo
Published: 2026-05-11
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2605.10717v1

Multi-agent trajectory modeling traditionally focuses on forecasting, often neglecting more general tasks like trajectory completion, which is essential for real-world applications such as correcting tracking data. Existing methods also generally predict agents' states without offering any state-wise measure of heteroscedastic uncertainty. Moreover, popular multi-modal sampling methods lack error probability estimates for each generated scene under the same prior observations, which makes it difficult to rank the predictions at inference time. We introduce U2Diffine, a unified diffusion model built to perform trajectory completion while simultaneously offering state-wise heteroscedastic uncertainty estimates. This is achieved by augmenting the standard denoising loss with the negative log-likelihood of the predicted noise, and then propagating the latent space uncertainty to the real state space using a first-order Taylor approximation. We also propose U2Diff, a faster baseline that avoids gradient computation during sampling. This approach significantly increases inference speed, making it as efficient as a standard generative-only diffusion model. For post-processing, we integrate a Rank Neural Network (RankNN) that enables error probability estimation for each generated mode, demonstrating strong correlation with ground truth errors. Our method outperforms state-of-the-art solutions in both trajectory completion and forecasting across four challenging sports datasets (NBA, Basketball-U, Football-U, Soccer-U), underscoring the effectiveness of our uncertainty and error probability estimation.

---

### What should post-training optimize? A test-time scaling law perspective

Authors: Muheng Li, Jian Qian, Wenlong Mou
Published: 2026-05-11
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2605.10716v1

Large language models are increasingly deployed with test-time strategies: sample $N$ responses, score them with a reward model or verifier, and return the best. This deployment rule exposes a mismatch in post-training: standard objectives optimize the mean reward of a single response, whereas best-of-$N$ performance is governed by the upper tail of the reward distribution. Recent test-time-aware objectives partly address this mismatch, but typically assume that training can use the same per-prompt rollout budget as deployment, which is impractical when post-training must cover many prompts while deployment can allocate much larger per-prompt test-time compute. We study this budget-mismatch regime, where only $m\ll N$ per-prompt rollouts are available during training but the target objective is best-of-$N$ deployment. Under structural assumptions on the reward tails, we show that the policy gradient of the best-of-$N$ objective can be approximated from a much smaller rollout group by extrapolating upper-tail statistics. This yields a family of Tail-Extrapolated estimators for best-of-$N$-oriented post-training: a simple direct estimator, Tail-Extrapolated Advantage (TEA), and a fixed-order debiased Prefix-TEA estimator based on moment cancellation. Experiments on instruction-following tasks show that TEA and Prefix-TEA improve best-of-$N$ performance across different language models, reward models and datasets under various training and test-time budget settings.

---

### UAV-Assisted Scan-to-Simulation for Landslides Using Physics-Informed Gaussian Splatting

Authors: Zhenyu Liang, Jack C. P. Cheng
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10715v1

Landslide monitoring and simulation play an important role in urban safety assessment and disaster prevention. Existing landslide simulation pipelines typically rely on digital elevation model and mesh-based representations, which are suitable for geometric analysis, but often lack visual realism. This limitation reduces their effectiveness in interactive applications, hazard communication, and public education. In this paper, we propose a UAV-based scan-to-simulation framework that bridges photorealistic scene capture and physics-based landslide simulation through 3DGS. Specifically, our pipeline includes four stages: (1) UAV-based acquisition of slope imagery, (2) reconstruction of a low-anisotropy 3DGS scene representation, (3) volumetric conversion of the target simulation region by filling the interior of the surface-based model, and (4) integration with the Material Point Method (MPM) for landslide simulation. We validate the proposed framework on a real landslide site in Hong Kong that experienced a severe landslide event. The results show that our method supports both realistic visual reconstruction and effective simulation.

---

### Why Low-Resource NLP Needs More Than Cross-Lingual Transfer: Lessons Learned from Luxembourgish

Authors: Fred Philippy, Siwen Guo, Jacques Klein, Tegawendé F. Bissyandé
Published: 2026-05-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.10714v1

Cross-lingual transfer has become a central paradigm for extending natural language processing (NLP) technologies to low-resource languages. By leveraging supervision from high-resource languages, multilingual language models can achieve strong task performance with little or no labeled target-language data. However, it remains unclear to what extent cross-lingual transfer can substitute for language-specific efforts. In this paper, we synthesize prior research findings and data collection results on Luxembourgish, which, despite its typological proximity to high-resource languages and its presence in a multilingual context, remains insufficiently represented in modern NLP technologies. Across findings, we observe a fundamental interdependence between cross-lingual transfer and language-specific efforts. Cross-lingual transfer can substantially improve target-language performance, but its success depends critically on the availability of sufficiently high-quality, task-aligned target-language data. At the same time, such resources, particularly in low-resource settings, are typically too limited in scale to drive strong performance on their own. Instead, such resources reach their full potential only when leveraged within a cross-lingual framework. We therefore argue that cross-lingual transfer and language-specific efforts should not be viewed as competing alternatives. Instead, they function as complementary components of a sustainable low-resource NLP pipeline. Based on these insights, we provide practical guidelines for integrating and balancing cross-lingual transfer with language-specific development in sustainable low-resource NLP pipelines.

---

### Price of Quality: Sufficient Conditions for Sparse Recovery using Mixed-Quality Data

Authors: Youssef Chaabouni, David Gamarnik
Published: 2026-05-11
Categories: stat.ML, cs.IT, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2605.10713v1

We study sparse recovery when observations come from mixed-quality sources: a small collection of high-quality measurements with small noise variance and a larger collection of lower-quality measurements with higher variance. For this heterogeneous-noise setting, we establish sample-size conditions for information-theoretic and algorithmic recovery. On the information-theoretic side, we show that it is sufficient for $(n_1, n_2)$ to satisfy a linear trade-off defining the Price of Quality: the number of low-quality samples needed to replace one high-quality sample. In the agnostic setting, where the decoder is completely agnostic to the quality of the data, it is uniformly bounded, and in particular one high-quality sample is never worth more than two low-quality samples for this sufficient condition to hold. In the informed setting, where the decoder is informed of per-sample variances, the price of quality can grow arbitrarily large. On the algorithmic side, we analyze the LASSO in the agnostic setting and show that the recovery threshold matches the homogeneous-noise case and only depends on the average noise level, revealing a striking robustness of computational recovery to data heterogeneity. Together, these results give the first conditions for sparse recovery with mixed-quality data and expose a fundamental difference between how the information-theoretic and algorithmic thresholds adapt to changes in data quality.

---

### RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings

Authors: Byeongchan Kim, Arijit Sehanobish, Avinava Dubey, Min-hwan Oh, Krzysztof Choromanski
Published: 2026-05-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.10706v1

We present a new class of efficient attention mechanisms applying universal 3D Relative Positional Encoding (RPE) methods given by arbitrary integrable modulation functions $f$. They lead to the new class of 3D-Transformer models, called \textit{RelFlexformers}, flexibly integrating those RPEs, and characterized by the $O(L \log L)$ time complexity of the attention computation for the $L$-length input sequences. RelFlexformers builds on the theory of the Non-Uniform Fourier Transform (NU-FFT), naturally generalizing several existing efficient RPE-attention methods from structured settings with tokens homogeneously embedded in unweighted grids into general non-structured heterogeneous scenarios, where tokens' positions are arbitrarily distributed in the corresponding 3D spaces. As such, RelFlexformers can be applied in particular to model point clouds. Our extensive empirical evaluation on a large portfolio of 3D datasets confirms quality improvements provided by the NU-FFT-driven attention modulation techniques in the RelFlexformers.

---

### TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering

Authors: Zhenyu Liang, Xiao Zhang, Tianchao Li, Jack C. P. Cheng, Chi-Keung Tang
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10705v1

Transmissive scenes are ubiquitous in daily life, yet reconstructing and rendering them remains highly challenging due to the inherent entanglement between near-field reflections from the surrounding environment on the transmissive surface, and the transmitted content of the scene behind it. This coupling gives rise to dual surface geometries and dual radiance components within each observation, posing ambiguities for standard methods. We present TransmissiveGS, a novel framework for disentangled reconstruction and rendering of transmissive scenes. Specifically, we model the scene with a dual-Gaussian representation and introduce a deferred shading function to jointly render the two Gaussian components. To separate reflection and transmission, we exploit the inherent multi-view inconsistency of reflections and leverage the residuals from reconstructing multi-view consistent content as cues for disentangled geometry and appearance modeling. We further propose a reflection light field that enables high-fidelity estimation of near-field reflections. During training, we introduce a high-frequency regularization to preserve fine details. We also contribute a new synthetic dataset for evaluating transmissive surface reconstruction. Experiments on both synthetic and real-world scenes demonstrate that TransmissiveGS consistently outperforms prior Gaussian Splatting-based methods in both reconstruction and rendering quality for transmissive scenes.

---

### The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions

Authors: Dahlia Shehata, Ming Li
Published: 2026-05-11
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2605.10698v2

Multi-agent systems (MAS) assume that collaborating inherently improves Large Language Model (LLM) reasoning. We challenge this by demonstrating that simulated social pressure triggers an algorithmic ``Bystander Effect,'' inducing severe cognitive loafing. By evaluating 22,500 deterministic trajectories across 3 dataset contexts (GAIA, SWE-bench, Multi-Challenge) with 3 state-of-the-art (SOTA) models, we semantically audit internal reasoning traces against external outputs. We formalize the \textit{Interaction Depth Limit} ($D_L$), the exact plurality threshold where an agent's logical sovereignty collapses into social compliance. Crucially, we uncover the \textit{Sovereignty Gap}: models frequently compute the correct derivation internally but suffer ``Alignment Hallucinations'' -- actively subjugating empirical evidence to sycophantically appease a simulated swarm. We prove that multi-agent social load is strictly non-commutative; the "brand" identity of the ``Lead Anchor'' auditor disproportionately dictates the swarm's integrity. These findings expose architectural vulnerabilities, proving that unstructured multi-agent topologies can degrade independent reasoning.

---

### The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions

Authors: Dahlia Shehata, Ming Li
Published: 2026-05-11
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2605.10698v1

Multi-agent systems (MAS) assume that collaborating inherently improves Large Language Model (LLM) reasoning. We challenge this by demonstrating that simulated social pressure triggers an algorithmic ``Bystander Effect,'' inducing severe cognitive loafing. By evaluating 22,500 deterministic trajectories across 3 dataset contexts (GAIA, SWE-bench, Multi-Challenge) with 3 state-of-the-art (SOTA) models, we semantically audit internal reasoning traces against external outputs. We formalize the \textit{Interaction Depth Limit} ($D_L$), the exact plurality threshold where an agent's logical sovereignty collapses into social compliance. Crucially, we uncover the \textit{Sovereignty Gap}: models frequently compute the correct derivation internally but suffer ``Alignment Hallucinations'' -- actively subjugating empirical evidence to sycophantically appease a simulated swarm. We prove that multi-agent social load is strictly non-commutative; the "brand" identity of the ``Lead Anchor'' auditor disproportionately dictates the swarm's integrity. These findings expose architectural vulnerabilities, proving that unstructured multi-agent topologies can degrade independent reasoning.

---

### DANCE: Detect and Classify Events in EEG

Authors: Jarod Lévy, Hubert Banville, Jérémy Rapin, Jean-Remi King, Thomas Moreau, Stéphane d'Ascoli
Published: 2026-05-11
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2605.10688v1

Event identification in continuous neural recordings is a critical task in neuroscience. Decoding in EEG is dominated by classifying windows aligned to known event onsets. However, while available in controlled experiments, such onsets are absent in continuous real-world monitoring. Here, we introduce DANCE, a deep learning pipeline that frames neural decoding as a set-prediction problem and jointly detects and classifies events directly from raw, unaligned signals. Evaluated separately on ten datasets curated from the literature with a wide variety of event types (ranging from milliseconds to minutes in duration), our model outperforms existing methods on a broad range of cognitive, clinical and BCI tasks. This single architecture establishes a new state of the art in the competitive task of seizure monitoring and matches the accuracy of onset-informed models for BCI tasks. Overall, our method marks a step towards end-to-end asynchronous neural decoding models

---

### The finite expression method for turbulent dynamics with high-order moment recovery

Authors: Xingjian Xu, Di Qi, Chunmei Wang
Published: 2026-05-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.10687v1

Turbulent dynamical systems are characterized by nonlinear interactions and stochastic effects that generate coupled statistical quantities, such as non-zero higher-order moments, which are difficult to capture from data with accuracy. We propose a two-stage data-driven modeling framework that combines symbolic regression with generative models to jointly identify the governing dynamics and predict their key statistical quantities. In Stage I of the framework, the Finite Expression Method (FEX) is adopted to discover closed-form expressions of the deterministic dynamics, recovering nonlinear interaction terms and external forcing without predefined libraries. In Stage II, generative models are introduced to learn the residual stochastic components as a refined correction to the model error from the Stage I approximation, enabling accurate characterization of higher-order statistics. Theoretical analysis establishes the consistency of the symbolic estimator and quantifies the estimation error in terms of data size and numerical discretization. The model performance is verified through detailed numerical experiments on the stochastic triad models across multiple regimes, demonstrating that the framework successfully recovers interaction terms and forcing expressions, and accurately predicts statistical moments up to order five. These results highlight the potential of integrating interpretable symbolic discovery with data-driven stochastic modeling for complex turbulent systems.

---

### GESR: A Genetic Programming-Based Symbolic Regression Method with Gene Editing

Authors: Yanjie Li, Liping Zhang, Min Wu, Weijun Li, Lina Yu, Jingyi Liu, Yusong Deng, Mingzhu Wan, Xin Ning
Published: 2026-05-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.10685v3

Mathematical formulas serve as a language through which humans communicate with nature. Discovering mathematical laws from scientific data to describe natural phenomena has been a long-standing pursuit of humanity for centuries. In the field of artificial intelligence, this challenge is known as the symbolic regression problem. Among existing symbolic regression approaches, Genetic Programming (GP) based on evolutionary algorithms remains one of the most classical and widely adopted methods. GP simulates the evolutionary process across generations through genetic mutation and crossover. However, mutations and crossovers in GP are entirely random. While this randomness effectively mimics natural evolution, it inevitably produces both beneficial and detrimental variations. If there existed a metaphorical `God` capable of foreseeing which genetic mutations or crossovers would yield superior outcomes and performing targeted gene editing accordingly, the efficiency of evolution could be substantially improved. Motivated by this idea, we propose in this paper a symbolic regression approach based on gene editing, termed GESR. In GESR, we trained two "hands of God" (two BERT models). Among them, the first leverages the BERT's masked language modeling capability to guide the mutation of genes (expression symbols). The other BERT model guides the crossover of individual genes by predicting the crossover point. Experimental results demonstrate that GESR significantly improves computational efficiency compared with traditional GP algorithms and achieves strong overall performance across multiple symbolic regression tasks.

---

### Is Data Shapley Not Better than Random in Data Selection? Ask NASH

Authors: Xiao Tian, Jue Fan, Rachael Hwee Ling Sim, Zixuan Wang, Nancy F. Chen, Bryan Kian Hsiang Low
Published: 2026-05-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.10684v2

Data selection studies the problem of identifying high-quality subsets of training data. While some existing works have considered selecting the subset of data with top-$m$ Data Shapley or other semivalues as they account for the interaction among every subset of data, other works argue that Data Shapley can sometimes perform ineffectively in practice and select subsets that are no better than random. This raises the questions: (I) Are there certain "Shapley-informative" settings where Data Shapley consistently works well? (II) Can we strategically utilize these settings to select high-quality subsets consistently and efficiently? In this paper, we propose a novel data selection framework, NASH (Non-linear Aggregation of SHapley-informative components), which (I) decomposes the target utility function (e.g., validation accuracy) into simpler, Shapley-informative component functions, and selects data by optimizing an objective that (II) aggregates these components non-linearly. We demonstrate that NASH substantially boosts the effectiveness of Shapley/semivalue-based data selection with minimal additional runtime cost.

---

### Scalable Mamba-Based Message-Passing Neural Decoder for Error-Correcting Codes

Authors: Rostislav Gusev, Nikita Aleksandrov, Artem Solomkin, Dmitry Artemasov
Published: 2026-05-11
Categories: cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2605.10681v2

Forward error correction is essential for reliable communication over noisy channels. Attention-based model-free neural decoders have shown strong performance for short codes, but their scalability to longer codes is limited by the quadratic memory and computational cost of attention. In this paper, we introduce the Mamba message-passing decoder (MMPD), an attention-free syndrome-based neural decoder for binary linear codes. MMPD retains the Tanner-graph structure of a message-passing decoder by performing local pairwise aggregation along variable-check edges. To enable efficient long-range information propagation, these local updates are combined with bidirectional Mamba state-space blocks. By avoiding dense attention matrices, MMPD scales more favorably for long codes in both memory and computation. Experiments on the (1056, 880) LDPC code show that MMPD achieves a 0.45 dB gain over the state-of-the-art CrossMPT decoder at a specified target bit error rate, while reducing memory consumption by a factor of 1.5. This reduction factor increases substantially for longer codes, demonstrating the applicability of MMPD to scalable neural decoding of practical long codes.

---

### Scalable Mamba-Based Message-Passing Neural Decoder for Error-Correcting Codes

Authors: Rostislav Gusev, Nikita Aleksandrov, Artem Solomkin, Dmitry Artemasov
Published: 2026-05-11
Categories: cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2605.10681v1

Forward error correction is essential for reliable communication over noisy channels. Attention-based model-free neural decoders have shown strong performance for short codes, but their scalability to longer codes is limited by the quadratic memory and computational cost of attention. In this paper, we introduce the Mamba message-passing decoder (MMPD), an attention-free syndrome-based neural decoder for binary linear codes. MMPD retains the Tanner-graph structure of a message-passing decoder by performing local pairwise aggregation along variable-check edges. To enable efficient long-range information propagation, these local updates are combined with bidirectional Mamba state-space blocks. By avoiding dense attention matrices, MMPD scales more favorably for long codes in both memory and computation. Experiments on the (1056, 880) LDPC code show that MMPD achieves a 0.45 dB gain over the state-of-the-art CrossMPT decoder at a specified target bit error rate, while reducing memory consumption by a factor of 1.5. This reduction factor increases substantially for longer codes, demonstrating the applicability of MMPD to scalable neural decoding of practical long codes.

---

### Exact Unlearning from Proxies Induces Closeness Guarantees on Approximate Unlearning

Authors: Virgile Dine, Teddy Furon
Published: 2026-05-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.10680v1

This paper proposes a paradigm shift linking machine unlearning directly to the structure of the data distributions rather than a mere update of the neural network parameters. We show that inferring these distributions with precision enables distilling the exact unlearning signal induced by the modeling. Theoretical bounds on the Kullback-Leibler divergence from the ideal retrained model to our unlearned model, under verifiable admissibility criterion, reveal the soundness of our framework. This method is experimentally validated over three forgetting scenarios as reaching the closest classifier to the ideal retrained model when compared to competitors.

---

### Energy-Efficient Implementation of Spiking Recurrent Cells on FPGA

Authors: Pascal Harmeling, Florent De Geeter, Guillaume Drion
Published: 2026-05-11
Categories: cs.NE
arXiv: https://arxiv.org/abs/2605.10679v3

Spiking Neural Networks (SNNs) can reduce energy consumption compared to conventional Artificial Neural Networks (ANNs) when spiking activity is sparse and the neuron model is hardware-friendly. However, biologically faithful models are often too costly to implement on FPGAs, whereas very simple models (e.g., IR/LIF) sacrifice part of the neuronal dynamics. In this work, we present an FPGA accelerator for an SNN using Spiking Recurrent Cell (SRC) neurons, providing a trade-off between biological plausibility and hardware cost. We propose a set of mathematical simplifications that remove costly unary operators (\textit{tanh}, \textit{exp}) and avoid floating-point arithmetic through scaling and piecewise-defined approximations. The complete network is implemented in VHDL and validated using spiking traces derived from the MNIST dataset. The weight matrices computed off-line are stored directly in LUT-registers without any adaptation. This demonstrates the robustness of SRC cells. Experiments were conducted on an Artix-7 XC7A200T clocked at 100 MHz. The reference implementation achieves 96.31\% accuracy with a 220-image spiking trace and a processing time of 1.7424 ms per digit. We then investigate accuracy/energy trade-offs by reducing the spiking trace length and quantizing synaptic weights down to 4 bits, achieving 93.32\% accuracy at 0.55 mJ per digit (55 images, 5-bit weights) and 92.89\% at 0.45 mJ (44 images, 4-bit weights). These results show that SRC-based SNNs can deliver competitive performance with reduced energy consumption, while preserving richer neuronal dynamics than standard LIF/IR models.

---

### Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium

Authors: Qingxin Xiao, Peilin Zhao, Yangyang Zhao, Lingwei Dang, Qingyao Wu
Published: 2026-05-11
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.10676v1

During MLLM decoding, attention often abnormally concentrates on irrelevant image tokens. While existing research dismisses this as invalid noise and forcibly redirects attention to compel focusing on key image information, we argue these tokens are critical carriers of visual and narrative logic, and such coercive corrections exacerbate visual-language imbalance. Adopting a "decoding-as-game" perspective, we reveal that hallucinations stem from an equilibrium imbalance between linguistic priors and visual information. We propose Adversarial Counter-Commonsense Equilibrium (ACE), a training-free framework that perturbs visual context via counter-commonsense patches. Leveraging the fact that authentic visual features remain stable under perturbation while hallucinations fluctuate, ACE implements a dynamic game decoding strategy. This approach precisely suppresses perturbation-sensitive priors while compensating for stable visual signals to restore balance. Extensive experiments demonstrate that ACE, as a plug-and-play strategy, enhances model trustworthiness with negligible inference overhead.

---

### Neuromorphic Monocular Depth Estimation with Uncertainty Modeling

Authors: Viktor Bergkvist, Felix Rydell, Per-Erik Forssén, David Gustafsson, Johan Rideg
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10675v1

Event cameras offer distinct advantages over conventional frame-based sensors, including microsecond-level temporal resolution, high dynamic range, and low bandwidth. In this paper, we predict per-pixel depth distributions from monocular event streams using deep neural networks. We estimate uncertainty using Gaussian, log-normal, and evidential learning frameworks. We compare six event representations: spatio-temporal voxel grids with 1, 5, 10, and 20 temporal bins, the Compact Spatio-Temporal Representation (CSTR), and Time-Ordered Recent Event (TORE) volumes. Our U-Net-based models are trained on synthetic data and then fine-tuned on real sequences. We evaluate performance using absolute relative error, root mean squared error, and the area under the sparsification error. Quantitative results show that the representations perform similarly, while 10 bin log-normal and 5 bin evidential learning perform best across metrics. Our experiments demonstrate that uncertainty estimation can be successfully integrated into event-based monocular depth estimation, and be used to indicate pixels with reliable depth.

---

### Step Rejection Fine-Tuning: A Practical Distillation Recipe

Authors: Igor Slinko, Ilia Zavidnyi, Egor Bogomolov, Yaroslav Zharov
Published: 2026-05-11
Categories: cs.LG, cs.AI, cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2605.10674v1

Rejection Fine-Tuning (RFT) is a standard method for training LLM agents, where unsuccessful trajectories are discarded from the training set. In the context of SWE-bench tasks, this corresponds to filtering out runs where the submitted patch does not pass the tests. However, this approach discards unresolved trajectories, even though they form a large portion of all trajectories for hard tasks and even then may be partially correct. In this work, we propose Step Rejection Fine-Tuning (SRFT) - a practical way to leverage these unresolved trajectories. For this, we employ a critic LLM to assess the correctness of each step in a trajectory. Consequently, during training, we mask the loss for erroneous steps while retaining them in the context window. This way we ensure the model learns to recover from errors without reproducing them. Evaluation on SWE-bench Verified shows that while RFT improves the resolution rate by 2.4% by excluding unresolved trajectories, SRFT improves it by 3.7% by filtering them instead of discarding completely, reaching the total resolution rate of 32.2%.

---

### Compander-Aligned Query Geometry for Quantized Zeroth-Order Optimization

Authors: Yao Shu, Zilin Zhu
Published: 2026-05-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.10673v1

Low-bit forward evaluation is an attractive route to memory-efficient zeroth-order (ZO) adaptation: the optimizer needs only scalar losses, and the model can be queried near deployment precision. The obstacle is that a quantized ZO query is not a continuous finite difference followed by harmless storage rounding. The query chooses endpoints, the low-precision engine rounds them, and the loss difference is measured along the rounded chord. For nonuniform companding quantizers, this makes the codebook insufficient to predict ZO behavior: a fixed weight-space radius can collapse in dense cells, over-span sparse cells, or assign a rounded chord to an unrounded update direction. We identify the missing object as query geometry and model scalar nonuniform quantization as $Q = φ^{-1} \circ U \circ φ$. CAQ-ZO (Compander-Aligned Queries for Zeroth-Order Optimization) forms one-grid-step Rademacher stencils $z \pm Δr$ in $z = φ(x)$, maps endpoints back through $φ^{-1}$, and updates in $z$. Our theory proves the grid-span mismatch, decomposes endpoint-rounding estimator residuals, and gives stationarity bounds in which generic off-grid queries retain a $Δ^2/μ^2$ residual channel while CAQ-ZO makes the query-time residual exactly zero. Synthetic experiments isolate this channel, and matched NF4 Qwen/Llama fine-tuning shows that CAQ-ZO improves the trained NF4 baseline under the same quantizer and evaluation budget.

---

### Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework

Authors: Phalguni Nanda, Zaiwei Chen
Published: 2026-05-11
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2605.10671v1

In this work, we show that natural policy gradient, a core algorithm in reinforcement learning, admits an exact formulation as a smoothed and averaged form of policy iteration. Specifically, we introduce doubly smoothed policy iteration (DSPI), a Bellman-operator framework in which each policy is obtained by applying a regularized greedy step to a weighted average of past $Q$-functions. DSPI includes policy iteration, dual-averaged policy iteration, natural policy gradient, and more general policy dual averaging methods as special cases. Using only monotonicity and contraction of smoothed Bellman operators, we prove distribution-free global geometric convergence of DSPI. Consequently, standard natural policy gradient and policy dual averaging achieve an iteration complexity of $\mathcal{O}((1-γ)^{-1}\log((1-γ)^{-1}ε^{-1}))$ for computing an $ε$-optimal policy, without modifying the MDP, adding regularization beyond the mirror map inherent in the update, or using adaptive, trajectory-dependent stepsizes. For the unregularized greedy case, corresponding to dual-averaged policy iteration, we also prove finite termination. The same Bellman-operator framework further extends to discounted MDPs with linear function approximation and stochastic shortest path problems.

---

### A Spectral Framework for Closed-Form Relative Density Estimation

Authors: Francis Bach
Published: 2026-05-11
Categories: cs.LG, math.OC, math.ST
arXiv: https://arxiv.org/abs/2605.10668v1

We propose a closed-form spectral framework for relative log-density estimation in linearly parameterized probabilistic models, including unnormalized and conditional models. This is achieved by representing the Kullback-Leibler (KL) divergence as an integral of weighted chi-squared divergences, converting KL estimation into a family of least-squares problems. We derive an explicit spectral formula based only on first- and second-order feature moments, yielding closed-form estimators of both divergences and log-density potentials for fixed features. The framework extends to a broad class of f-divergences and can be combined with kernelization or feature learning with neural networks. We prove convergence guarantees for the resulting estimators and empirically compare them on synthetic data with optimization-based variational formulations, including logistic and softmax regression for normalized conditional models.

---

### Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions

Authors: Diancheng Kang, Zheyuan Liu, Ningshan Ma, Yue Huang, Zhaoxuan Tan, Meng Jiang
Published: 2026-05-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.10664v2

Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful dialogue. We identify KV-cache contamination as a key failure mode: steered token states are stored and repeatedly reused, turning a local perturbation into cumulative coherence degradation. To address this challenge, we propose Gated Cropped Attention-Delta steering (GCAD), which extracts steering signals from system-prompt contributions to self-attention and applies them with token-level gating. Across persona-steering experiments, GCAD preserves trait control while substantially improving long-horizon coherence. On the main multi-turn benchmark, GCAD improves average coherence drift from -18.6 to -1.9 and raises turn-10 trait expression from 78.0 to 93.1. These results suggest that activation steering becomes more reliable when interventions follow the prompt-mediated pathways that models already use for behavioral control.

---

### Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents

Authors: Zhiyuan Fan, Wenwei Jin, Feng Zhang, Bin Li, Yihong Dong, Yao Hu, Jiawei Li
Published: 2026-05-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.10663v1

Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactions, thus enabling adaptation to novel tasks at deployment time. This process places substantial demands on the foundation model's capacities for abstraction, generalization, and in-context learning. However, most existing studies focus primarily on system-level design choices, such as how experience is represented and managed, neglecting the inherent capabilities of the underlying model. While some recent works have started to optimize the experience utilization stage via reinforcement learning, they still fail to treat self-evolution as a unified process to be jointly optimized. To this end, we propose Evolving-RL, an efficient algorithmic framework that jointly improves the experience extraction and utilization capabilities required for self-evolution. Specifically, we center the learning process on experience extraction and evaluation, using the two supervisory signals derived from evaluation to optimize the extractor and solver separately and thus enable their coordinated co-evolution. Experiments on ALFWorld and Mind2Web show that Evolving-RL effectively enhances LLMs' ability to extract and reuse experience, leading to strong performance gains on out-of-distribution tasks (up to 98.7% relative improvement over the GRPO baseline on ALFWorld unseen tasks and 35.8% on Mind2Web), and these gains are fully unlocked only through the coordinated co-evolution of experience extraction and utilization. Furthermore, Evolving-RL inherently functions as an experience-augmented RL algorithm. By internalizing reusable experience patterns directly into model parameters, it achieves remarkable performance gains over standard baselines on both seen and unseen tasks, even in the absence of test-time experience accumulation.

---

### Investigating Single-Block Recurrence in Vision Transformers for Image Recognition

Authors: Michal Byra, Pawel Olszowiec, Grzegorz Stefanski, Grzegorz Gruszczynski, Alberto Presta
Published: 2026-05-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.10661v2

Vision Transformers (ViTs) implement depth by stacking independently parameterized blocks, but it remains unclear how much of this parameterization is necessary and how much can be replaced by recurrent reuse. We study this question with bViT, a single-block recurrent ViT that repeatedly applies the same transformer block while preserving the iterative computation of a deep model. On ImageNet-1K, bViT-B reaches 0.779 validation accuracy compared with 0.789 for ViT-B under the same training recipe and computational budget, while using 8.6M rather than 86.6M parameters. This correspondence becomes stronger with model width, while narrow recurrent models exhibit a substantial performance gap. Beyond classification, the single-block formulation provides a controlled testbed for studying how transformer computation evolves with depth, since the same heads, neurons, and weight matrices can be tracked across recurrent steps. Analyses of attention, activation patterns, and step-conditioned spectral pruning reveal temporally organized behavior and step-dependent utilization of the shared parameters. bViT also transfers competitively to downstream tasks while enabling highly parameter-efficient adaptation. Our work shows that much of the performance associated with independently parameterized ViT depth can be recovered through recurrent reuse of a single sufficiently wide transformer block.

---

### bViT: Investigating Single-Block Recurrence in Vision Transformers for Image Recognition

Authors: Michal Byra, Pawel Olszowiec, Grzegorz Stefanski, Grzegorz Gruszczynski, Alberto Presta
Published: 2026-05-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.10661v1

Vision Transformers (ViTs) are built by stacking independently parameterized blocks, but it remains unclear how much of this depth requires layer specific transformations and how much can be realized through recurrent computation. We study this question with bViT, a single-block recurrent ViT in which one transformer block is applied repeatedly to process an image. This architecture preserves the iterative structure of a deep ViT while removing layer specific block parameterization, providing a controlled setting for studying recurrence in vision. On ImageNet-1K, a 12-step bViT-B achieves accuracy comparable to standard ViT-B under the same training recipe and computational budget, while using an order of magnitude fewer parameters. We observe that recurrent performance improves with representation width, with wider bViTs recovering much more of the performance of standard ViTs than narrow variants. We interpret this behavior as implicit depth multiplexing, where a shared block expresses multiple step-dependent computations through the evolving hidden state. Beyond ImageNet classification, bViT transfers competitively to downstream tasks and enables parameter-efficient fine-tuning. Mechanistic analyses of activations, attention and step-specific pruning show that the shared block changes its effective behavior across recurrent steps rather than simply repeating the same computation. Our results suggest that a large fraction of ViT depth can be implemented through recurrent reuse, provided that the representation space is sufficiently wide.

---

### When Can Digital Personas Reliably Approximate Human Survey Findings?

Authors: Mumin Jia, Yilin Chen, Divya Sharma, Jairo Diaz-Rodriguez
Published: 2026-05-11
Categories: cs.CL, cs.AI, cs.SI, stat.ML
arXiv: https://arxiv.org/abs/2605.10659v1

Digital personas powered by Large Language Models (LLMs) are increasingly proposed as substitutes for human survey respondents, yet it remains unclear when they can reliably approximate human survey findings. We answer this question using the LISS panel, constructing personas from respondents' background variables and pre-2023 survey histories, then testing them against the same respondents' held-out post-cutoff answers. Across four persona architectures, three LLMs, and two prediction tasks, we assess performance at the question, respondent, distributional, equity, and clustering levels. Digital personas improve alignment with human response distributions, especially in domains tied to stable attributes and values, but remain limited for individual prediction and fail to recover multivariate respondent structure. Retrieval-augmented architectures provide the clearest gains, but performance depends more on human response structure than on model choice: personas perform best for low-variability questions and common respondent patterns, and worst for subjective, heterogeneous, or rare responses. Our results provide practical guidance on when digital personas could be appropriate for survey research and when human validation remains necessary.

---

### Why Zeroth-Order Adaptation May Forget Less: A Randomized Shaping Theory

Authors: Yao Shu, Jian Mu, Zhongxiang Dai
Published: 2026-05-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.10658v1

Continual learning requires new-task adaptation without damaging previously acquired capabilities. Recent forward-pass and zeroth-order (ZO) results show that low-query adaptation may retain better than first-order (FO) descent, but the usual view of ZO as noisy FO estimation does not explain why. We give a local randomized gradient-shaping analysis: finite differences expose a raw shape that is mean-aligned with FO, while the norm-matched comparator fixes the expected squared adaptation norm. Under this controlled comparison, forgetting depends on how the adaptation shape exposes retention curvature. For norm-matched ZO, the expected shaped retention curvature obeys an exact identity that preserves the isotropic retention floor while contracting only the anisotropic component. Projecting this identity onto the incoming gradient yields the observable FO--ZO quadratic forgetting gap: ZO improves mean forgetting precisely when the FO direction has above-average retention curvature, by a query-dependent fraction of that curvature excess. A practical finite-query accounting separates the mean mechanism from one-batch sampling and smoothing perturbations. As an algorithmic transfer, RISE applies the calibrated ZO shape to exact FO gradients inside parameter blocks. Its target is a stability--plasticity tradeoff: randomized shaping may reduce the retention exposure paid by FO, exact gradients remove finite-smoothing bias from finite-difference ZO, and blockwise sampling supplies many local shaping directions after one gradient computation. The blockwise analysis separates mean-step damage from centered random exposure, showing how block-diagonal curvature, cross-block coupling, and local shaping diagnostics specify where this exact-gradient transfer is most likely to be visible.

---

### BCJR-QAT: A Differentiable Relaxation of Trellis-Coded Weight Quantization

Authors: Venugopalan Iyengar
Published: 2026-05-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.10655v1

Trellis-coded quantization sets the current 2-bit post-training frontier for LLMs (QTIP), but pushing below the PTQ ceiling requires quantization-aware training, and QAT on a trellis is obstructed by the non-differentiable Viterbi argmax. We introduce BCJR-QAT, a relaxation that replaces the argmax with the BCJR forward-backward sum-product algorithm at temperature $T$, producing a soft codeword equal to the Boltzmann expectation over trellis paths, exactly differentiable, recovering the hard QTIP code as $T \to 0$, and mathematically identical to the transfer-matrix computation for a 1D Ising-like spin chain. We contribute (i) a fused Triton kernel making BCJR tractable on a single consumer GPU ($6.57\times$ speedup, fp32 parity); (ii) a quantitative drift-budget theory of when BCJR-QAT can escape the QTIP-PTQ Voronoi basin, verified across four experiments; and (iii) a positive empirical result on Llama-3.2-1B at 2 bpw under end-to-end forward-KL distillation: with the right schedule (skip the high-$T$ phase to avoid an overshoot we diagnose), single-layer BCJR-QAT beats QTIP-PTQ by $\mathbf{-0.084}$ PPL on WikiText-2, and multi-layer compounding is super-additive.

---

### Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights

Authors: Jixiang Qing, Henry Moss, Matthias Sachs
Published: 2026-05-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.10654v1

We consider the active learning problem where the goal is to learn an unknown function with low prediction error under an unknown Boltzmann distribution induced by the function itself. This self-induced weighting arises naturally in problems such as potential energy surface (PES) modeling in computational chemistry, yet poses unique challenges as the target distribution is unknown and its partition function is intractable. We propose \texttt{AB-SID-iVAR}, a Gaussian Process-based acquisition function that approximates the intractable Bayesian target distribution in closed form while avoiding partition function estimation, and is applicable to both discrete and continuous input domains. We also analyze a Thompson sampling alternative (\texttt{TS-SID-iVAR}) as a higher variance Monte Carlo variant. Despite the unknown target, under mild conditions, we establish that the terminal prediction error vanishes with high probability, and provide a tighter average-case guarantee. We demonstrate consistent improvements over existing approaches in this setting on synthetic benchmarks and real-world PES modeling and drug discovery tasks.

---

### A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent Variables

Authors: Zheng Li, Feng Xie, Shenglan Nie, Xichen Guo, Ruxin Wang, Hao Zhang
Published: 2026-05-11
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2605.10651v1

Constraint-based causal discovery is widely used for learning causal structures, but heavy reliance on conditional independence (CI) testing makes it computationally expensive in high-dimensional settings. To mitigate this limitation, many divide-and-conquer frameworks have been proposed, but most assume causal sufficiency, i.e., no latent variables. In this paper, we show that divide-and-conquer strategies can be theoretically generalized beyond causal sufficiency to settings with latent variables. Specifically, we propose a recursive decomposition framework, termed DiCoLa, that enables divide-and-conquer causal discovery in the presence of latent variables. It recursively decomposes the global learning task into smaller subproblems and integrates their solutions through a principled reconstruction step to recover the global structure. We theoretically establish the soundness and completeness of the proposed framework. Extensive experiments on synthetic data demonstrate that our approach significantly improves computational efficiency across a range of causal discovery algorithms, while experiments on a real-world dataset further illustrate its practical effectiveness.

---

### A Random-Matrix Criterion for Initializing Gated Recurrent Neural Networks

Authors: Tommaso Fioratti, Riccardo Marcaccioli, Francesco Casola
Published: 2026-05-11
Categories: cs.LG, cond-mat.dis-nn
arXiv: https://arxiv.org/abs/2605.10650v1

Proper weight initialization prior to training has historically been one of the key factors that helped kick off the deep learning revolution. Initialization is even more crucial in "reservoir computing", where the weights of a readout layer are learned linearly while the reservoir weights are fixed and largely determine the richness, stability and memory of the resulting dynamics. In the infinite-width limit it has been shown that meaningful initializations are those sitting at an effective critical point of the randomly initialized model. The phase transition is controlled by the weight variance $g^2$ and separates an ordered phase from a chaotic one where information progressively degrades. Here we derive a simple criterion to estimate the critical $g_c$ for a broad class of recurrent architectures and we show that it closely tracks the gain at which a gated-RNN reservoir achieves peak performance on a chaotic forecasting task. Finally, we argue that our criterion can serve as a design principle for future initialization schemes.

---

### diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectories

Authors: Florent Guépin, Cheick Tidiani Cisse, Denis Renaud, François Bidet, Arnaud Legendre
Published: 2026-05-11
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2605.10647v1

Trajectories are nowadays valuable information for a wide range of applications. However they are also inherently sensitive, as they contain highly personal information about individuals. Facing this challenge, synthesizing mobility trajectories has emerged as a promising solution to leverage mobility information while preserving privacy. State-of-the-art models, often rely on the false assumptions of generative models implicit privacy and fails to provide privacy guarantees while preserving trajectories utility. Here, we introduce diffGHOST, a conditional diffusion model based on latent space segmentation, designed to answer this challenge. Thus, this paper propose a methodology that identify and mitigate memorization of critical samples using condition segments of a learn latent space.

---

### GenMed: A Pairwise Generative Reformulation of Medical Diagnostic Tasks

Authors: Hantao Zhang, Weidong Guo, Yuhe Liu, Jiancheng Yang, Sathvik Bhagavan, Danli Shi, Mingda Xu, Pascal Fua
Published: 2026-05-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.10645v1

Data-driven medical AI is traditionally formulated as a discriminative mapping from input $X$ to output $Y$ via a learned function $f$, which does not generalize well across heterogeneous data and modalities encountered in real-world clinical settings. In this work, we propose a fundamentally different, generative paradigm. We model the joint distribution $P(X,Y)$ using diffusion models and reframe inference as a test-time output optimization problem. By guiding the generative process to match observed inputs, our framework enables flexible, gradient-based conditioning at inference time without architectural changes or retraining, effectively supporting arbitrary and previously unseen combinations of observations. Extensive experiments demonstrate strong performance across standard and cross-modality medical image segmentation, few-shot segmentation with only 2 or 4 training samples, degraded-input segmentation, shape completion from sparse and partial observations, and zero-shot application to demonstrate generality. To support these evaluations, we curated and released a large-scale text-shape dataset derived from MedShapeNet. Our results highlight the versatility of generative joint modeling as a foundation for reusable, task-agnostic medical AI systems.

---

### A Single-Layer Model Can Do Language Modeling

Authors: Zanmin Wang
Published: 2026-05-11
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2605.10643v1

Modern language models scale depth by stacking layers, each holding its own state - a per-layer KV cache in transformers, a per-layer matrix in Mamba, Gated DeltaNet (GDN), RWKV, and xLSTM. Biological systems lean heavily on recurrence rather than on stacking. We ask how far that shape can go on language modeling. We propose Grounded Prediction Networks (GPN): one state vector revisited at every step through a single recurrent block - one FFN, one shared matrix memory. At 130M parameters, a 1-layer GPN+M reaches FineWeb-Edu perplexity 18.06, within 13% of a 12-layer Transformer++ (16.05) and 18% of a 10-layer GDN (15.34); a 2-layer variant closes the gap to 6%/11%. We do not match the deep baselines. Because the working context is a single vector, we can directly inspect its geometry: a persistent default-token direction, a content-bearing horizon of tens of tokens, and memory heads that split spontaneously into fast and slow retention pools.

---

### Composing diffusion priors with explicit physical context via generative Gibbs sampling

Authors: Weizhou Wang, Jonathan Weare, Aaron R. Dinner
Published: 2026-05-11
Categories: cs.LG, cond-mat.stat-mech
arXiv: https://arxiv.org/abs/2605.10642v1

Pretrained diffusion models provide powerful learned priors, but in scientific sampling the target distribution often depends on physical context that is not fully represented by one generative model. We introduce Generative Gibbs for Physics-Aware Sampling (GG-PA), a training-free framework that formulates the composition of learned partial priors and explicit physical context as inference over a joint target distribution in an augmented state space. We derive a Gibbs sampler for this joint target, show that it is asymptotically exact as the diffusion time approaches zero, and prove that in settings with quadratic interactions it remains exact at finite diffusion times. We further introduce replica exchange over diffusion time to accelerate mixing. Experiments on a double-well system, a $φ^4$ lattice model, and atomistic peptide systems show that GG-PA recovers context-induced distribution shifts and emergent collective behavior in interacting systems using partial priors without retraining. These results demonstrate GG-PA as a practical approach for combining pretrained generative priors with explicit physical context.

---

### LLaVA-CKD: Bottom-Up Cascaded Knowledge Distillation for Vision-Language Models

Authors: Nikolaos Gkalelis, Vasileios Mezaris
Published: 2026-05-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.10641v1

Large Vision-Language Models (VLMs) are successful in addressing a multitude of vision-language understanding tasks, such as Visual Question Answering (VQA), but their memory and compute requirements remain a concern for practical deployment. A promising class of techniques for mitigating this concern is Knowledge Distillation, where knowledge from a high-capacity Teacher network is transferred to a considerably smaller Student network. However, the capacity gap between the two networks is both a blessing and a curse: the smaller the Student network, the better its efficiency, and the larger the Teacher, the more knowledge it carries; yet, beyond a point, the larger capacity gap between the two leads to worse knowledge transfer. To counter this effect, we propose a bottom-up cascaded knowledge distillation (CKD) framework. Instead of treating knowledge transfer as an activity involving one high-capacity Teacher (or an ensemble of such), inspired by human formal education systems, we introduce one (potentially, more) additional Teacher(s) of intermediate capacity that gradually bring the Student network to the next level, where the next (higher-capacity) Teacher can take over. We provide a theoretical analysis in order to study the effect of cascaded distillation in the generalization performance of the Student. We apply the proposed framework on models build upon the LLaVA methodology and evaluate the derived models on seven standard, publicly available VQA benchmarks, demonstrating their SotA performance.

---

### Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm

Authors: Haoyu Wang, Yifan Shang, Zhongxiang Sun, Weijie Yu, Xiao Zhang, Jun Xu
Published: 2026-05-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.10640v1

Continual Pre-Training (CPT) is essential for enabling Language Models (LMs) to integrate new knowledge without erasing old. While classical CPT techniques like data replay have become the standard paradigm, the mechanisms underlying how LMs acquire and retain facts over time, termed as continual Factual Knowledge Acquisition (cFKA), remain unclear. In this work, we present a theoretical framework that characterizes the training dynamics of cFKA using a single-layer Transformer, offering a unified explanation for the behavior of representative CPT methods. Our analysis reveals that regularization-based methods merely adjust the convergence rate of parameters without altering the inherent forgetting tendency, whereas data replay methods succeed in shifting convergence dynamics and stabilizing pretrained knowledge. Building on these insights, we propose a novel generative data replay approach, called \textbf{S}electing \textbf{T}okens via attenti\textbf{O}n \textbf{C}ontribution~(STOC), which identifies influential factual snippets to guide replay data generation. Extensive experiments on both synthetic and real-world datasets validate our findings and demonstrate that STOC effectively enhances cFKA by mitigating catastrophic forgetting.

---