# Research Papers — 2026-01 · bundle page 11 of 189

> Full-text markdown of papers #501–550 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-01/page/11
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/10.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/12.md)

### Nested Slice Sampling: Vectorized Nested Sampling for GPU-Accelerated Inference

Authors: David Yallup, Namu Kroupa, Will Handley
Published: 2026-01-30
Categories: stat.CO, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.23252v2

Model comparison and calibrated uncertainty quantification often require integrating over parameters, but scalable inference can be challenging for complex, multimodal targets. Nested Sampling is a robust alternative to standard MCMC, yet its typically sequential structure and hard constraints make efficient accelerator implementations difficult. This paper introduces Nested Slice Sampling (NSS), a GPU-friendly, vectorized formulation of Nested Sampling that uses Hit-and-Run Slice Sampling for constrained updates. A tuning analysis yields a simple near-optimal rule for setting the slice width, improving high-dimensional behavior and making per-step compute more predictable for parallel execution. Experiments on challenging synthetic targets, high dimensional Bayesian inference, and Gaussian process hyperparameter marginalization show that NSS maintains accurate evidence estimates and high-quality posterior samples, and is particularly robust on difficult multimodal problems where current state-of-the-art methods such as tempered SMC baselines can struggle. An open-source implementation is released to facilitate adoption and reproducibility.

---

### Structure Over Scale: Learning Visual Reasoning from Pedagogical Video

Authors: Bishoy Galoaa, Xiangyu Bai, Sarah Ostadabbas
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.23251v2

State-of-the-art vision-language models (VLMs) score impressively on video benchmarks yet stumble on basic visual reasoning tasks involving spatial relations, navigation, and object selection that a preschooler solves easily. We hypothesize that the explicit pedagogical structure, specifically the context-question-pause-answer cycles embedded in children's educational video, provides naturally co-aligned reasoning traces: temporally synchronized visual cues, questions, and answers that emerge only from deliberate pedagogical authoring and cannot be practically reconstructed through manual annotation at scale. To test this, we introduce SoSVQA (Structure over Scale Visual Question Answering), a unified benchmark of 10K question-answer pairs automatically extracted from Dora the Explorer (DoraVQA) and Mickey Mouse Clubhouse (ClubHVQA) with precise timestamp alignment, and fine-tune Qwen2-VL and Qwen3-VL using Group Relative Policy Optimization (GRPO) to leverage the clear correctness signals and structured reasoning traces inherent in educational content. Despite training on just 10K QA pairs from 78 hours of children's television, orders of magnitude less data than GPT and Gemini, our approach delivers generalizable performance gains for Qwen-based VLMs, yielding consistent improvements on NExT-QA (+19.7), Video-MME (+10.6), and MotionBench (+4.9), matching the performance of leading proprietary systems and demonstrating that content structure can compensate for content scale.

---

### Graph Attention Network for Node Regression on Random Geometric Graphs with Erdős--Rényi contamination

Authors: Somak Laha, Suqi Liu, Morgane Austern
Published: 2026-01-30
Categories: stat.ML, cs.IT, cs.LG, cs.SI, math.ST
arXiv: https://arxiv.org/abs/2601.23239v1

Graph attention networks (GATs) are widely used and often appear robust to noise in node covariates and edges, yet rigorous statistical guarantees demonstrating a provable advantage of GATs over non-attention graph neural networks~(GNNs) are scarce. We partially address this gap for node regression with graph-based errors-in-variables models under simultaneous covariate and edge corruption: responses are generated from latent node-level covariates, but only noise-perturbed versions of the latent covariates are observed; and the sample graph is a random geometric graph created from the node covariates but contaminated by independent Erdős--Rényi edges. We propose and analyze a carefully designed, task-specific GAT that constructs denoised proxy features for regression. We prove that regressing the response variables on the proxies achieves lower error asymptotically in (a) estimating the regression coefficient compared to the ordinary least squares (OLS) estimator on the noisy node covariates, and (b) predicting the response for an unlabelled node compared to a vanilla graph convolutional network~(GCN) -- under mild growth conditions. Our analysis leverages high-dimensional geometric tail bounds and concentration for neighbourhood counts and sample covariances. We verify our theoretical findings through experiments on synthetically generated data. We also perform experiments on real-world graphs and demonstrate the effectiveness of the attention mechanism in several node regression tasks.

---

### How well do generative models solve inverse problems? A benchmark study

Authors: Patrick Krüger, Patrick Materne, Werner Krebs, Hanno Gottschalk
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.23238v1

Generative learning generates high dimensional data based on low dimensional conditions, also called prompts. Therefore, generative learning algorithms are eligible for solving (Bayesian) inverse problems. In this article we compare a traditional Bayesian inverse approach based on a forward regression model and a prior sampled with the Markov Chain Monte Carlo method with three state of the art generative learning models, namely conditional Generative Adversarial Networks, Invertible Neural Networks and Conditional Flow Matching. We apply them to a problem of gas turbine combustor design where we map six independent design parameters to three performance labels. We propose several metrics for the evaluation of this inverse design approaches and measure the accuracy of the labels of the generated designs along with the diversity. We also study the performance as a function of the training dataset size. Our benchmark has a clear winner, as Conditional Flow Matching consistently outperforms all competing approaches.

---

### YuriiFormer: A Suite of Nesterov-Accelerated Transformers

Authors: Aleksandr Zimin, Yury Polyanskiy, Philippe Rigollet
Published: 2026-01-30
Categories: cs.LG, cs.AI, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2601.23236v2

We propose a variational framework that interprets transformer layers as iterations of an optimization algorithm acting on token embeddings. In this view, self-attention implements a gradient step of an interaction energy, while MLP layers correspond to gradient updates of a potential energy. Standard GPT-style transformers emerge as vanilla gradient descent on the resulting composite objective, implemented via Lie--Trotter splitting between these two energy functionals. This perspective enables principled architectural design using classical optimization ideas. As a proof of concept, we introduce a Nesterov-style accelerated transformer that preserves the same attention and MLP oracles. The resulting architecture consistently outperforms a nanoGPT baseline on TinyStories and OpenWebText, demonstrating that optimization-theoretic insights can translate into practical gains.

---

### Sequence Diffusion Model for Temporal Link Prediction in Continuous-Time Dynamic Graph

Authors: Nguyen Minh Duc, Viet Cuong Ta
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.23233v1

Temporal link prediction in dynamic graphs is a fundamental problem in many real-world systems. Existing temporal graph neural networks mainly focus on learning representations of historical interactions. Despite their strong performance, these models are still purely discriminative, producing point estimates for future links and lacking an explicit mechanism to capture the uncertainty and sequential structure of future temporal interactions. In this paper, we propose SDG, a novel sequence-level diffusion framework that unifies dynamic graph learning with generative denoising. Specifically, SDG injects noise into the entire historical interaction sequence and jointly reconstructs all interaction embeddings through a conditional denoising process, thereby enabling the model to capture more comprehensive interaction distributions. To align the generative process with temporal link prediction, we employ a cross-attention denoising decoder to guide the reconstruction of the destination sequence and optimize the model in an end-to-end manner. Extensive experiments on various temporal graph benchmarks show that SDG consistently achieves state-of-the-art performance in the temporal link prediction task.

---

### ShotFinder: Imagination-Driven Open-Domain Video Shot Retrieval via Web Search

Authors: Tao Yu, Haopeng Jin, Hao Wang, Shenghua Chai, Yujia Yang, Junhao Gong, Jiaming Guo, Minghui Zhang, Xinlong Chen, Zhenghao Zhang, Yuxuan Zhou, Yufei Xiong et al.
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.23232v4

In recent years, large language models (LLMs) have made rapid progress in information retrieval, yet existing research has mainly focused on text or static multimodal settings. Open-domain video shot retrieval, which involves richer temporal structure and more complex semantics, still lacks systematic benchmarks and analysis. To fill this gap, we introduce ShotFinder, a benchmark that formalizes editing requirements as keyframe-oriented shot descriptions and introduces five types of controllable single-factor constraints: Temporal order, Color, Visual style, Audio, and Resolution. We curate 1,210 high-quality samples from YouTube across 20 thematic categories, using large models for generation with human verification. Based on the benchmark, we propose ShotFinder, a text-driven three-stage retrieval and localization pipeline: (1) query expansion via video imagination, (2) candidate video retrieval with a search engine, and (3) description-guided shot localization. Experiments on multiple closed-source and open-source models reveal a significant gap to human performance, with clear imbalance across constraints: temporal localization is relatively tractable, while color and visual style remain major challenges. These results reveal that open-domain video shot retrieval is still a critical capability that multimodal large models have yet to overcome.

---

### Solving Inverse Problems with Flow-based Models via Model Predictive Control

Authors: George Webber, Alexander Denker, Riccardo Barbano, Andrew J Reader
Published: 2026-01-30
Categories: eess.IV, cs.LG
arXiv: https://arxiv.org/abs/2601.23231v2

Flow-based generative models provide strong unconditional priors for inverse problems, but guiding their dynamics for conditional generation remains challenging. Recent work casts training-free conditional generation in flow models as an optimal control problem; however, solving the resulting trajectory optimisation is computationally and memory intensive, requiring differentiation through the flow dynamics or adjoint solves. We propose MPC-Flow, a model predictive control framework that formulates inverse problem solving with flow-based generative models as a sequence of control sub-problems, enabling practical optimal control-based guidance at inference time. We provide theoretical analysis linking MPC-Flow to the underlying optimal control objective and show how different algorithmic choices yield a spectrum of guidance algorithms, including regimes that avoid backpropagation through the generative model trajectory. We evaluate MPC-Flow on benchmark image restoration tasks, spanning linear and non-linear settings such as in-painting, deblurring, and super-resolution, and demonstrate strong performance and scalability to massive state-of-the-art architectures via training-free guidance of FLUX.2 (32B) in a quantised setting on consumer hardware.

---

### Strongly Polynomial Time Complexity of Policy Iteration for $L_\infty$ Robust MDPs

Authors: Ali Asadi, Krishnendu Chatterjee, Ehsan Goharshady, Mehrdad Karrabi, Alipasha Montaseri, Carlo Pagano
Published: 2026-01-30
Categories: cs.AI, cs.CC
arXiv: https://arxiv.org/abs/2601.23229v2

Markov decision processes (MDPs) are a fundamental model in sequential decision making. Robust MDPs (RMDPs) extend this framework by allowing uncertainty in transition probabilities and optimizing against the worst-case realization of that uncertainty. In particular, $(s, a)$-rectangular RMDPs with $L_\infty$ uncertainty sets form a fundamental and expressive model: they subsume classical MDPs and turn-based stochastic games. We consider this model with discounted payoffs. The existence of polynomial and strongly-polynomial time algorithms is a fundamental problem for these optimization models. For MDPs, linear programming yields polynomial-time algorithms for any arbitrary discount factor, and the seminal work of Ye established strongly--polynomial time for a fixed discount factor. The generalization of such results to RMDPs has remained an important open problem. In this work, we show that a robust policy iteration algorithm runs in strongly-polynomial time for $(s, a)$-rectangular $L_\infty$ RMDPs with a constant (fixed) discount factor, resolving an important algorithmic question.

---

### Scaling Multiagent Systems with Process Rewards

Authors: Ed Li, Junyu Ren, Cat Yan
Published: 2026-01-30
Categories: cs.AI, cs.CL, cs.ET, cs.MA
arXiv: https://arxiv.org/abs/2601.23228v2

While multiagent systems have shown promise for tackling complex tasks via specialization, finetuning multiple agents simultaneously faces two key challenges: (1) credit assignment across agents, and (2) sample efficiency of expensive multiagent rollouts. In this work, we propose finetuning multiagent systems with per-action process rewards from AI feedback (MAPPA) to address both. Through assigning credit to individual agent actions rather than only at task completion, MAPPA enables fine-grained supervision without ground truth labels while extracting maximal training signal from each rollout. We demonstrate our approach on competition math problems and tool-augmented data analysis tasks. On unseen math problems, MAPPA achieves +5.0--17.5pp on AIME and +7.8--17.2pp on AMC. For data analysis tasks, our method improves success rate by +16.7pp while quality metrics improve by up to 47%, validating that per-action supervision can lead to improvements across different multiagent systems on various domains. By addressing these challenges, our work takes a first step toward scaling multiagent systems for complex, long-horizon tasks with minimal human supervision.

---

### Agile Reinforcement Learning through Separable Neural Architecture and Applications

Authors: Rajib Mostakim, Reza T. Batley, Sourav Saha
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.23225v2

Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet go-to function approximators - multilayer perceptrons (MLPs) - are often parameter-inefficient due to an imperfect inductive bias for the smooth structure of many value functions. This mismatch can also hinder sample efficiency and slow policy learning in this capacity-limited regime. Although model compression techniques exist, they operate post-hoc and do not improve learning efficiency. Spline-based architectures such as Kolmogorov-Arnold Networks (KANs) have been shown to offer parameter efficiency but are widely reported to exhibit significant computational overhead, especially at scale. In seeking to address these limitations, this work introduces SPAN (SPline-based Adaptive Networks) for RL. SPAN adapts the KHRONOS framework with a learnable preprocessing layer. SPAN is evaluated across discrete (PPO) and high-dimensional continuous (SAC) control tasks, offline settings (Minari/D4RL) and a real-world datacenter HVAC control application. SPAN achieves a 30-50% improvement in sample efficiency and 1.3-9 times higher success rates across benchmarks compared to MLP baselines. Despite incurring a per-step evaluation overhead of 1.2-1.8x, SPAN's superior convergence reliability yields an expected total training cost 1.3-6.3x lower than MLP baselines when accounting for convergence failures. In the HVAC application, SPAN reduces energy consumption in 9 of 12 months relative to MLP while simultaneously achieving a 1.1-3.4x reduction in thermal comfort violations across the evaluation year, demonstrating generalization to real-world engineering control. Furthermore, SPAN demonstrates superior anytime performance and robustness to hyperparameter variations, suggesting it as a viable, high-performance alternative for learning efficient policies in resource-limited settings.

---

### Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning

Authors: Xiangyu Zeng, Zhiqiu Zhang, Yuhan Zhu, Xinhao Li, Zikang Wang, Changlian Ma, Qingyu Zhang, Zizheng Huang, Kun Ouyang, Tianxiang Jiang, Ziang Yan, Yi Wang et al.
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.23224v2

Existing multimodal large language models for long-video understanding predominantly rely on uniform sampling and single-turn inference, limiting their ability to identify sparse yet critical evidence amid extensive redundancy. We introduce Video-o3, a novel framework that supports iterative discovery of salient visual clues, fine-grained inspection of key segments, and adaptive termination once sufficient evidence is acquired. Technically, we address two core challenges in interleaved tool invocation. First, to mitigate attention dispersion induced by the heterogeneity of reasoning and tool-calling, we propose Task-Decoupled Attention Masking, which isolates per-step concentration while preserving shared global context. Second, to control context length growth in multi-turn interactions, we introduce a Verifiable Trajectory-Guided Reward that balances exploration coverage with reasoning efficiency. To support training at scale, we further develop a data synthesis pipeline and construct Seeker-173K, comprising 173K high-quality tool-interaction trajectories for effective supervised and reinforcement learning. Extensive experiments show that Video-o3 substantially outperforms state-of-the-art methods, achieving 72.1% accuracy on MLVU and 46.5% on Video-Holmes. These results demonstrate Video-o3's strong multi-hop evidence-seeking and reasoning capabilities, and validate the effectiveness of native tool invocation in long-video scenarios.

---

### Are you going to finish that? A Practical Study of the Partial Token Problem

Authors: Hao Xu, Alisa Liu, Jonathan Hayase, Yejin Choi, Noah A. Smith
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.23223v2

Language models (LMs) are trained over sequences of tokens, whereas users interact with LMs via text. This mismatch gives rise to the partial token problem, which occurs when a user ends their prompt in the middle of the expected next-token, leading to distorted next-token predictions. Although this issue has been studied using arbitrary character prefixes, its prevalence and severity in realistic prompts respecting word boundaries remains underexplored. In this work, we identify three domains where token and "word" boundaries often do not line up: languages that do not use whitespace, highly compounding languages, and code. In Chinese, for example, up to 25% of word boundaries do not line up with token boundaries, making even natural, word-complete prompts susceptible to this problem. We systematically construct semantically natural prompts ending with a partial tokens; in experiments, we find that they comprise a serious failure mode: frontier LMs consistently place three orders of magnitude less probability on the correct continuation compared to when the prompt is "backed-off" to be token-aligned. This degradation does not diminish with scale and often worsens for larger models. Finally, we evaluate inference-time mitigations to the partial token problem and validate the effectiveness of recent exact solutions. Overall, we demonstrate the scale and severity of probability distortion caused by tokenization in realistic use cases, and provide practical recommentions for model inference providers.

---

### Region-Normalized DPO for Medical Image Segmentation under Noisy Judges

Authors: Hamza Kalisch, Constantin Seibold, Jens Kleesiek, Ken Herrmann, Frederic Jonske
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.23222v1

While dense pixel-wise annotations remain the gold standard for medical image segmentation, they are costly to obtain and limit scalability. In contrast, many deployed systems already produce inexpensive automatic quality-control (QC) signals like model agreement, uncertainty measures, or learned mask-quality scores which can be used for further model training without additional ground-truth annotation. However, these signals can be noisy and biased, making preference-based fine-tuning susceptible to harmful updates. We study Direct Preference Optimization (DPO) for segmentation from such noisy judges using proposals generated by a supervised base segmenter trained on a small labeled set. We find that outcomes depend strongly on how preference pairs are mined: selecting the judge's top-ranked proposal can improve peak performance when the judge is reliable, but can amplify harmful errors under weaker judges. We propose Region-Normalized DPO (RN-DPO), a segmentation-aware objective which normalizes preference updates by the size of the disagreement region between masks, reducing the leverage of harmful comparisons and improving optimization stability. Across two medical datasets and multiple regimes, RN-DPO improves sustained performance and stabilizes preference-based fine-tuning, outperforming standard DPO and strong baselines without requiring additional pixel annotations.

---

### Optimal Fair Aggregation of Crowdsourced Noisy Labels using Demographic Parity Constraints

Authors: Gabriel Singer, Samuel Gruffaz, Olivier Vo Van, Nicolas Vayatis, Argyris Kalogeratos
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.23221v2

As acquiring reliable ground-truth labels is usually costly, or infeasible, crowdsourcing and aggregation of noisy human annotations is the typical resort. Aggregating subjective labels, though, may amplify individual biases, particularly regarding sensitive features, raising fairness concerns. Nonetheless, fairness in crowdsourced aggregation remains largely unexplored, with no existing convergence guarantees and only limited post-processing approaches for enforcing $\varepsilon$-fairness under demographic parity. We address this gap by analyzing the fairness s of crowdsourced aggregation methods within the $\varepsilon$-fairness framework, for Majority Vote and Optimal Bayesian aggregation. In the small-crowd regime, we derive an upper bound on the fairness gap of Majority Vote in terms of the fairness gaps of the individual annotators. We further show that the fairness gap of the aggregated consensus converges exponentially fast to that of the ground-truth under interpretable conditions. Since ground-truth itself may still be unfair, we generalize a state-of-the-art multiclass fairness post-processing algorithm from the continuous to the discrete setting, which enforces strict demographic parity constraints to any aggregation rule. Experiments on synthetic and real datasets demonstrate the effectiveness of our approach and corroborate the theoretical insights.

---

### Med-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-Training

Authors: Anglin Liu, Ruichao Chen, Yi Lu, Hongxia Xu, Jintai Chen
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.23220v2

Despite recent Multimodal Large Language Models (MLLMs)' linguistic prowess in medical diagnosis, we find even state-of-the-art MLLMs suffer from a critical perceptual deficit: geometric blindness. This failure to ground outputs in objective geometric constraints leads to plausible yet factually incorrect hallucinations, rooted in training paradigms that prioritize linguistic fluency over geometric fidelity. This paper introduces Med-Scout, a novel framework that "cures" this blindness via Reinforcement Learning (RL) that leverages the intrinsic geometric logic latent within unlabeled medical images. Instead of relying on costly expert annotations, Med-Scout derives verifiable supervision signals through three strategic proxy tasks inspired by the systematic reading and reasoning patterns of clinicians: Hierarchical Scale Localization, Topological Jigsaw Reconstruction, and Anomaly Consistency Detection. To rigorously quantify this deficit, we present Med-Scout-Bench, a new benchmark specifically designed to evaluate geometric perception. Extensive evaluations show that Med-Scout significantly mitigates geometric blindness, outperforming leading proprietary and open-source MLLMs by over 40% on our benchmark. Furthermore, this enhanced geometric perception generalizes to broader medical understanding, achieving superior results on radiological and comprehensive medical VQA tasks.

---

### MonoScale: Scaling Multi-Agent System with Monotonic Improvement

Authors: Shuai Shao, Yixiang Liu, Bingwei Lu, Weinan Zhang
Published: 2026-01-30
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2601.23219v2

In recent years, LLM-based multi-agent systems (MAS) have advanced rapidly, using a router to decompose tasks and delegate subtasks to specialized agents. A natural way to expand capability is to scale up the agent pool by continually integrating new functional agents or tool interfaces, but naive expansion can trigger performance collapse when the router cold-starts on newly added, heterogeneous, and unreliable agents. We propose MonoScale, an expansion-aware update framework that proactively generates a small set of agent-conditioned familiarization tasks, harvests evidence from both successful and failed interactions, and distills it into auditable natural-language memory to guide future routing. We formalize sequential augmentation as a contextual bandit and perform trust-region memory updates, yielding a monotonic non-decreasing performance guarantee across onboarding rounds. Experiments on GAIA and Humanity's Last Exam show stable gains as the agent pool grows, outperforming naive scale-up and strong-router fixed-pool baselines.

---

### Tackling air quality with SAPIENS

Authors: Marcella Bona, Nathan Heatley, Jia-Chen Hua, Adriana Lara, Valeria Legaria-Santiago, Alberto Luviano Juarez, Fernando Moreno-Gomez, Jocelyn Richardson, Natan Vilchis, Xiwen Shirley Zheng
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.23215v1

Air pollution is a chronic problem in large cities worldwide and awareness is rising as the long-term health implications become clearer. Vehicular traffic has been identified as a major contributor to poor air quality. In a lot of cities the publicly available air quality measurements and forecasts are coarse-grained both in space and time. However, in general, real-time traffic intensity data is openly available in various forms and is fine-grained. In this paper, we present an in-depth study of pollution sensor measurements combined with traffic data from Mexico City. We analyse and model the relationship between traffic intensity and air quality with the aim to provide hyper-local, dynamic air quality forecasts. We developed an innovative method to represent traffic intensities by transforming simple colour-coded traffic maps into concentric ring-based descriptions, enabling improved characterisation of traffic conditions. Using Partial Least Squares Regression, we predict pollution levels based on these newly defined traffic intensities. The model was optimised with various training samples to achieve the best predictive performance and gain insights into the relationship between pollutants and traffic. The workflow we have designed is straightforward and adaptable to other contexts, like other cities beyond the specifics of our dataset.

---

### Disentangling multispecific antibody function with graph neural networks

Authors: Joshua Southern, Changpeng Lu, Santrupti Nerli, Samuel D. Stanton, Andrew M. Watkins, Franziska Seeger, Frédéric A. Dreyer
Published: 2026-01-30
Categories: q-bio.BM, cs.AI
arXiv: https://arxiv.org/abs/2601.23212v1

Multispecific antibodies offer transformative therapeutic potential by engaging multiple epitopes simultaneously, yet their efficacy is an emergent property governed by complex molecular architectures. Rational design is often bottlenecked by the inability to predict how subtle changes in domain topology influence functional outcomes, a challenge exacerbated by the scarcity of comprehensive experimental data. Here, we introduce a computational framework to address part of this gap. First, we present a generative method for creating large-scale, realistic synthetic functional landscapes that capture non-linear interactions where biological activity depends on domain connectivity. Second, we propose a graph neural network architecture that explicitly encodes these topological constraints, distinguishing between format configurations that appear identical to sequence-only models. We demonstrate that this model, trained on synthetic landscapes, recapitulates complex functional properties and, via transfer learning, has the potential to achieve high predictive accuracy on limited biological datasets. We showcase the model's utility by optimizing trade-offs between efficacy and toxicity in trispecific T-cell engagers and retrieving optimal common light chains. This work provides a robust benchmarking environment for disentangling the combinatorial complexity of multispecifics, accelerating the design of next-generation therapeutics.

---

### A Random Matrix Theory of Masked Self-Supervised Regression

Authors: Arie Wortsman Zurich, Federica Gerace, Bruno Loureiro, Yue M. Lu
Published: 2026-01-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.23208v1

In the era of transformer models, masked self-supervised learning (SSL) has become a foundational training paradigm. A defining feature of masked SSL is that training aggregates predictions across many masking patterns, giving rise to a joint, matrix-valued predictor rather than a single vector-valued estimator. This object encodes how coordinates condition on one another and poses new analytical challenges. We develop a precise high-dimensional analysis of masked modeling objectives in the proportional regime where the number of samples scales with the ambient dimension. Our results provide explicit expressions for the generalization error and characterize the spectral structure of the learned predictor, revealing how masked modeling extracts structure from data. For spiked covariance models, we show that the joint predictor undergoes a Baik--Ben Arous--Péché (BBP)-type phase transition, identifying when masked SSL begins to recover latent signals. Finally, we identify structured regimes in which masked self-supervised learning provably outperforms PCA, highlighting potential advantages of SSL objectives over classical unsupervised methods

---

### Learning to Execute Graph Algorithms Exactly with Graph Neural Networks

Authors: Muhammad Fetrat Qharabagh, Artur Back de Luca, George Giapitzakis, Kimon Fountoulakis
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.23207v2

Understanding what graph neural networks can learn, especially their ability to learn to execute algorithms, remains a central theoretical challenge. In this work, we prove exact learnability results for graph algorithms under bounded-degree and finite-precision constraints. Our approach follows a two-step process. First, we train an ensemble of multi-layer perceptrons (MLPs) to execute the local instructions of a single node. Second, during inference, we use the trained MLP ensemble as the update function within a graph neural network (GNN). Leveraging Neural Tangent Kernel (NTK) theory, we show that local instructions can be learned from a small training set, enabling the complete graph algorithm to be executed during inference without error and with high probability. To illustrate the learning power of our setting, we establish a rigorous learnability result for the LOCAL model of distributed computation. We further demonstrate positive learnability results for widely studied algorithms such as message flooding, breadth-first and depth-first search, and Bellman-Ford.

---

### High-quality generation of dynamic game content via small language models: A proof of concept

Authors: Morten I. K. Munk, Arturo Valdivia, Paolo Burelli
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.23206v2

Large language models (LLMs) offer promise for dynamic game content generation, but they face critical barriers, including narrative incoherence and high operational costs. Due to their large size, they are often accessed in the cloud, limiting their application in offline games. Many of these practical issues are solved by pivoting to small language models (SLMs), but existing studies using SLMs have resulted in poor output quality. We propose a strategy of achieving high-quality SLM generation through aggressive fine-tuning on deliberately scoped tasks with narrow context, constrained structure, or both. In short, more difficult tasks require narrower scope and higher specialization to the training corpus. Training data is synthetically generated via a DAG-based approach, grounding models in the specific game world. Such models can form the basis for agentic networks designed around the narratological framework at hand, representing a more practical and robust solution than cloud-dependent LLMs. To validate this approach, we present a proof-of-concept focusing on a single specialized SLM as the fundamental building block. We introduce a minimal RPG loop revolving around rhetorical battles of reputations, powered by this model. We demonstrate that a simple retry-until-success strategy reaches adequate quality (as defined by an LLM-as-a-judge scheme) with predictable latency suitable for real-time generation. While local quality assessment remains an open question, our results demonstrate feasibility for real-time generation under typical game engine constraints.

---

### TSAQA: Time Series Analysis Question And Answering Benchmark

Authors: Baoyu Jing, Sanhorn Chen, Lecheng Zheng, Boyu Liu, Zihao Li, Jiaru Zou, Tianxin Wei, Zhining Liu, Zhichen Zeng, Ruizhong Qiu, Xiao Lin, Yuchen Yan et al.
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.23204v2

Time series data are integral to critical applications across domains such as finance, healthcare, transportation, and environmental science. While recent work has begun to explore multi-task time series question answering (QA), current benchmarks remain limited to forecasting and anomaly detection tasks. We introduce TSAQA, a novel unified benchmark designed to broaden task coverage and evaluate diverse temporal analysis capabilities. TSAQA integrates six diverse tasks under a single framework ranging from conventional analysis, including anomaly detection and classification, to advanced analysis, such as characterization, comparison, data transformation, and temporal relationship analysis. Spanning 210k samples across 13 domains, the dataset employs diverse formats, including true-or-false (TF), multiple-choice (MC), and a novel puzzling (PZ), to comprehensively assess time series analysis. Zero-shot evaluation demonstrates that these tasks are challenging for current Large Language Models (LLMs): the best-performing commercial LLM, Gemini-2.5-Flash, achieves an average score of only 65.08. Although instruction tuning boosts open-source performance: the best-performing open-source model, LLaMA-3.1-8B, shows significant room for improvement, highlighting the complexity of temporal analysis for LLMs.

---

### Scale-Cascaded Diffusion Models for Super-Resolution in Medical Imaging

Authors: Darshan Thaker, Mahmoud Mostapha, Radu Miron, Shihan Qiu, Mariappan Nadar
Published: 2026-01-30
Categories: eess.IV, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.23201v1

Diffusion models have been increasingly used as strong generative priors for solving inverse problems such as super-resolution in medical imaging. However, these approaches typically utilize a diffusion prior trained at a single scale, ignoring the hierarchical scale structure of image data. In this work, we propose to decompose images into Laplacian pyramid scales and train separate diffusion priors for each frequency band. We then develop an algorithm to perform super-resolution that utilizes these priors to progressively refine reconstructions across different scales. Evaluated on brain, knee, and prostate MRI data, our approach both improves perceptual quality over baselines and reduces inference time through smaller coarse-scale networks. Our framework unifies multiscale reconstruction and diffusion priors for medical image super-resolution.

---

### Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience

Authors: Zhongxiang Sun, Qipeng Wang, Weijie Yu, Jingxuan Yang, Haolang Lu, Jun Xu
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.23188v1

Deep search agents powered by large language models have demonstrated strong capabilities in multi-step retrieval, reasoning, and long-horizon task execution. However, their practical failures often stem from the lack of mechanisms to monitor and regulate reasoning and retrieval states as tasks evolve under uncertainty. Insights from cognitive neuroscience suggest that human metacognition is hierarchically organized, integrating fast anomaly detection with selectively triggered, experience-driven reflection. In this work, we propose Deep Search with Meta-Cognitive Monitoring (DS-MCM), a deep search framework augmented with an explicit hierarchical metacognitive monitoring mechanism. DS-MCM integrates a Fast Consistency Monitor, which performs lightweight checks on the alignment between external evidence and internal reasoning confidence, and a Slow Experience-Driven Monitor, which is selectively activated to guide corrective intervention based on experience memory from historical agent trajectories. By embedding monitoring directly into the reasoning-retrieval loop, DS-MCM determines both when intervention is warranted and how corrective actions should be informed by prior experience. Experiments across multiple deep search benchmarks and backbone models demonstrate that DS-MCM consistently improves performance and robustness.

---

### ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought

Authors: Fanmeng Wang, Haotian Liu, Guojiang Zhao, Hongteng Xu, Zhifeng Gao
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.23184v1

While Chain-of-Thought (CoT) significantly enhances the performance of Large Language Models (LLMs), explicit reasoning chains introduce substantial computational redundancy. Recent latent reasoning methods attempt to mitigate this by compressing reasoning processes into latent space, but often suffer from severe performance degradation due to the lack of appropriate compression guidance. In this study, we propose Rendered CoT-Guided variational Latent Reasoning (ReGuLaR), a simple yet novel latent learning paradigm resolving this issue. Fundamentally, we formulate latent reasoning within the Variational Auto-Encoding (VAE) framework, sampling the current latent reasoning state from the posterior distribution conditioned on previous ones. Specifically, when learning this variational latent reasoning model, we render explicit reasoning chains as images, from which we extract dense visual-semantic representations to regularize the posterior distribution, thereby achieving efficient compression with minimal information loss. Extensive experiments demonstrate that ReGuLaR significantly outperforms existing latent reasoning methods across both computational efficiency and reasoning effectiveness, and even surpasses CoT through multi-modal reasoning, providing a new and insightful solution to latent reasoning. Code: https://github.com/FanmengWang/ReGuLaR.

---

### JobResQA: A Benchmark for LLM Machine Reading Comprehension on Multilingual Résumés and JDs

Authors: Casimiro Pio Carrino, Paula Estrella, Rabih Zbib, Carlos Escolano, José A. R. Fonollosa
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.23183v1

We introduce JobResQA, a multilingual Question Answering benchmark for evaluating Machine Reading Comprehension (MRC) capabilities of LLMs on HR-specific tasks involving résumés and job descriptions. The dataset comprises 581 QA pairs across 105 synthetic résumé-job description pairs in five languages (English, Spanish, Italian, German, and Chinese), with questions spanning three complexity levels from basic factual extraction to complex cross-document reasoning. We propose a data generation pipeline derived from real-world sources through de-identification and data synthesis to ensure both realism and privacy, while controlled demographic and professional attributes (implemented via placeholders) enable systematic bias and fairness studies. We also present a cost-effective, human-in-the-loop translation pipeline based on the TEaR methodology, incorporating MQM error annotations and selective post-editing to ensure an high-quality multi-way parallel benchmark. We provide a baseline evaluations across multiple open-weight LLM families using an LLM-as-judge approach revealing higher performances on English and Spanish but substantial degradation for other languages, highlighting critical gaps in multilingual MRC capabilities for HR applications. JobResQA provides a reproducible benchmark for advancing fair and reliable LLM-based HR systems. The benchmark is publicly available at: https://github.com/Avature/jobresqa-benchmark

---

### FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation

Authors: Siyang He, Qiqi Wang, Xiaoran Liu, Hongnan Ma, Yiwei Shi, Yuerong Song, Ying Zhu, Tianyi Liang, Zengfeng Huang, Ziwei He, Xipeng Qiu
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.23182v2

Despite the non-autoregressive potential of diffusion language models (dLLMs), existing decoding strategies demonstrate positional bias, failing to fully unlock the potential of arbitrary generation. In this work, we delve into the inherent spectral characteristics of dLLMs and present the first frequency-domain analysis showing that low-frequency components in hidden states primarily encode global structural information and long-range dependencies, while high-frequency components are responsible for characterizing local details. Based on this observation, we propose FourierSampler, which leverages a frequency-domain sliding window mechanism to dynamically guide the model to achieve a "structure-to-detail" generation. FourierSampler outperforms other inference enhancement strategies on LLADA and SDAR, achieving relative improvements of 20.4% on LLaDA1.5-8B and 16.0% on LLaDA-8B-Instruct. It notably surpasses similarly sized autoregressive models like Llama3.1-8B-Instruct.

---

### Ensuring Semantics in Weights of Implicit Neural Representations through the Implicit Function Theorem

Authors: Tianming Qiu, Christos Sonis, Hao Shen
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.23181v1

Weight Space Learning (WSL), which frames neural network weights as a data modality, is an emerging field with potential for tasks like meta-learning or transfer learning. Particularly, Implicit Neural Representations (INRs) provide a convenient testbed, where each set of weights determines the corresponding individual data sample as a mapping from coordinates to contextual values. So far, a precise theoretical explanation for the mechanism of encoding semantics of data into network weights is still missing. In this work, we deploy the Implicit Function Theorem (IFT) to establish a rigorous mapping between the data space and its latent weight representation space. We analyze a framework that maps instance-specific embeddings to INR weights via a shared hypernetwork, achieving performance competitive with existing baselines on downstream classification tasks across 2D and 3D datasets. These findings offer a theoretical lens for future investigations into network weights.

---

### TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification

Authors: Haoyun Jiang, Junqi He, Feng Hong, Xinlong Yang, Jianwei Zhang, Zheng Li, Zhengyang Zhuge, Zhiyong Chen, Bo Han, Junyang Lin, Jiangchao Yao
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.23180v1

Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and response sequences grow longer. Speculative decoding (SD) offers a powerful solution, providing significant speed-ups through its lightweight drafting and parallel verification mechanism. While existing work has nearly saturated improvements in draft effectiveness and efficiency, this paper advances SD from a new yet critical perspective: the verification cost. We propose TriSpec, a novel ternary SD framework that, at its core, introduces a lightweight proxy to significantly reduce computational cost by approving easily verifiable draft sequences and engaging the full target model only when encountering uncertain tokens. TriSpec can be integrated with state-of-the-art SD methods like EAGLE-3 to further reduce verification costs, achieving greater acceleration. Extensive experiments on the Qwen3 and DeepSeek-R1-Distill-Qwen/LLaMA families show that TriSpec achieves up to 35\% speedup over standard SD, with up to 50\% fewer target model invocations while maintaining comparable accuracy.

---

### Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization

Authors: Hui Lu, Yi Yu, Yiming Yang, Chenyu Yi, Xueyi Ke, Qixing Zhang, Bingquan Shen, Alex Kot, Xudong Jiang
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.23179v2

Targeted adversarial attacks on closed-source multimodal large language models (MLLMs) have been increasingly explored under black-box transfer, yet prior methods are predominantly sample-specific and offer limited reusability across inputs. We instead study a more stringent setting, Universal Targeted Transferable Adversarial Attacks (UTTAA), where a single perturbation must consistently steer arbitrary inputs toward a specified target across unknown commercial MLLMs. Naively adapting existing sample-wise attacks to this universal setting faces three core difficulties: (i) target supervision becomes high-variance due to target-crop randomness, (ii) token-wise matching is unreliable because universality suppresses image-specific cues that would otherwise anchor alignment, and (iii) few-source per-target adaptation is highly initialization-sensitive, which can degrade the attainable performance. In this work, we propose MCRMO-Attack, which stabilizes supervision via Multi-Crop Aggregation with an Attention-Guided Crop, improves token-level reliability through alignability-gated Token Routing, and meta-learns a cross-target perturbation prior that yields stronger per-target solutions. Across commercial MLLMs, we boost unseen-image attack success rate by +23.7\% on GPT-4o and +19.9\% on Gemini-2.0 over the strongest universal baseline.

---

### MeshGraphNet-Transformer: Scalable Mesh-based Learned Simulation for Solid Mechanics

Authors: Mikel M. Iparraguirre, Iciar Alfaro, David Gonzalez, Elias Cueto
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.23177v4

We present MeshGraphNet-Transformer (MGN-T), a novel architecture that combines the global modeling capabilities of Transformers with the geometric inductive bias of MeshGraphNets, while preserving a mesh-based graph representation. MGN-T overcomes a key limitation of standard MGN, the inefficient long-range information propagation caused by iterative message passing on large, high-resolution meshes. A physics-attention Transformer serves as a global processor, updating all nodal states simultaneously while explicitly retaining node and edge attributes. By directly capturing long-range physical interactions, MGN-T eliminates the need for deep message-passing stacks or hierarchical, coarsened meshes, enabling efficient learning on high-resolution meshes with varying geometries, topologies, and boundary conditions at an industrial scale. We demonstrate that MGN-T successfully handles industrial-scale meshes for impact dynamics, a setting in which standard MGN fails due message-passing under-reaching. The method accurately models self-contact, plasticity, and multivariate outputs, including internal, phenomenological plastic variables. Moreover, MGN-T outperforms state-of-the-art approaches on classical benchmarks, achieving higher accuracy while maintaining practical efficiency, using only a fraction of the parameters required by competing baselines.

---

### Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization

Authors: Luca Della Libera, Cem Subakan, Mirco Ravanelli
Published: 2026-01-30
Categories: cs.LG, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2601.23174v2

Neural audio codecs are at the core of modern conversational speech technologies, converting continuous speech into sequences of discrete tokens that can be processed by LLMs. However, existing codecs typically operate at fixed frame rates, allocating tokens uniformly in time and producing unnecessarily long sequences. In this work, we introduce DyCAST, a Dynamic Character-Aligned Speech Tokenizer that enables variable-frame-rate tokenization through soft character-level alignment and explicit duration modeling. DyCAST learns to associate tokens with character-level linguistic units during training and supports alignment-free inference with direct control over token durations at decoding time. To improve speech resynthesis quality at low frame rates, we further introduce a retrieval-augmented decoding mechanism that enhances reconstruction fidelity without increasing bitrate. Experiments show that DyCAST achieves competitive speech resynthesis quality and downstream performance while using significantly fewer tokens than fixed-frame-rate codecs. Code and checkpoints will be released publicly at https://github.com/lucadellalib/dycast.

---

### Names Don't Matter: Symbol-Invariant Transformer for Open-Vocabulary Learning

Authors: İlker Işık, Wenchao Li
Published: 2026-01-30
Categories: cs.LG, cs.LO, cs.SC
arXiv: https://arxiv.org/abs/2601.23169v2

Current neural architectures lack a principled way to handle interchangeable tokens, i.e., symbols that are semantically equivalent yet distinguishable, such as bound variables. As a result, models trained on fixed vocabularies often struggle to generalize to unseen symbols, even when the underlying semantics remain unchanged. We propose a novel Transformer-based mechanism that is provably invariant to the renaming of interchangeable tokens. Our approach employs parallel embedding streams to isolate the contribution of each interchangeable token in the input, combined with an aggregated attention mechanism that enables structured information sharing across streams. Experimental results confirm the theoretical guarantees of our method and demonstrate substantial performance gains on open-vocabulary tasks that require generalization to novel symbols. Project page: https://bu-depend-lab.github.io/Symbol-Invariant-Transformer/

---

### Hi-Light: A Path to high-fidelity, high-resolution video relighting with a Novel Evaluation Paradigm

Authors: Xiangrui Liu, Haoxiang Li, Yezhou Yang
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.23167v1

Video relighting offers immense creative potential and commercial value but is hindered by challenges, including the absence of an adequate evaluation metric, severe light flickering, and the degradation of fine-grained details during editing. To overcome these challenges, we introduce Hi-Light, a novel, training-free framework for high-fidelity, high-resolution, robust video relighting. Our approach introduces three technical innovations: lightness prior anchored guided relighting diffusion that stabilises intermediate relit video, a Hybrid Motion-Adaptive Lighting Smoothing Filter that leverages optical flow to ensure temporal stability without introducing motion blur, and a LAB-based Detail Fusion module that preserves high-frequency detail information from the original video. Furthermore, to address the critical gap in evaluation, we propose the Light Stability Score, the first quantitative metric designed to specifically measure lighting consistency. Extensive experiments demonstrate that Hi-Light significantly outperforms state-of-the-art methods in both qualitative and quantitative comparisons, producing stable, highly detailed relit videos.

---

### Monotonic Reference-Free Refinement for Autoformalization

Authors: Lan Zhang, Marco Valentino, André Freitas
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.23166v2

While statement autoformalization has advanced rapidly, full-theorem autoformalization remains largely unexplored. Existing iterative refinement methods in statement autoformalization typically improve isolated aspects of formalization, such as syntactic correctness, but struggle to jointly optimize multiple quality dimensions, which is critical for full-theorem autoformalization. We introduce a reference-free iterative monotonic process at inference time for full-theorem autoformalization that leverages complementary feedback from theorem provers and LLM-based judges, without access to ground-truth or existing formalizations and without human intervention. Our approach optimizes a masked composite objective over Formal Validity, Logical Preservation, Mathematical Consistency, and Formal Quality, guided by a responsiveness map that indicates how different LLMs acting as different roles preferentially improve each dimension. We further propose an acceptance policy that guarantees certified monotonic improvement, and provide conditions ensuring convergence and termination. Empirical experiments demonstrate the proposed process enables simultaneous improvement across multiple dimensions, achieving 100.00% formal validity and a 90.27% overall score on miniF2F, and 77.96% formal validity and a 52.45% overall score on ProofNet.

---

### Stochastic Linear Bandits with Parameter Noise

Authors: Daniel Ezer, Alon Peled-Cohen, Yishay Mansour
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.23164v2

We study the stochastic linear bandits with parameter noise model, in which the reward of action $a$ is $a^\top θ$ where $θ$ is sampled i.i.d. We show a regret upper bound of $\widetilde{O} (\sqrt{d T \log (K/δ) σ^2_{\max})}$ for a horizon $T$, general action set of size $K$ of dimension $d$, and where $σ^2_{\max}$ is the maximal variance of the reward for any action. We further provide a lower bound of $\widetildeΩ (d \sqrt{T σ^2_{\max}})$ which is tight (up to logarithmic factors) whenever $\log (K) \approx d$. For more specific action sets, $\ell_p$ unit balls with $p \leq 2$ and dual norm $q$, we show that the minimax regret is $\widetildeΘ (\sqrt{dT σ^2_q)}$, where $σ^2_q$ is a variance-dependent quantity that is always at most $4$. This is in contrast to the minimax regret attainable for such sets in the classic additive noise model, where the regret is of order $d \sqrt{T}$. Surprisingly, we show that this optimal (up to logarithmic factors) regret bound is attainable using a very simple explore-exploit algorithm.

---

### Probing the Trajectories of Reasoning Traces in Large Language Models

Authors: Marthe Ballon, Brecht Verbeken, Vincent Ginis, Andres Algaba
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.23163v1

Large language models (LLMs) increasingly solve difficult problems by producing "reasoning traces" before emitting a final response. However, it remains unclear how accuracy and decision commitment evolve along a reasoning trajectory, and whether intermediate trace segments provide answer-relevant information beyond generic length or stylistic effects. Here, we propose a protocol to systematically probe the trajectories of reasoning traces in LLMs by 1) generating a model's reasoning trace, 2) truncating it at fixed token-percentiles, and 3) injecting each partial trace back into the model (or a different model) to measure the induced distribution over answer choices via next-token probabilities. We apply this protocol to the open-source Qwen3-4B/-8B/-14B and gpt-oss-20b/-120b models across the multiple-choice GPQA Diamond and MMLU-Pro benchmarks. We find that accuracy and decision commitment consistently increase as the percentage of provided reasoning tokens grows. These gains are primarily driven by relevant content in the model generation rather than context length or generic "reasoning style" effects. Stronger models often backtrack successfully from incorrect partial traces, but immediate answers often remain anchored in the weaker model's incorrect response. More broadly, we show that trajectory probing provides diagnostics for efficient and safer deployment of reasoning models as the measurements can inform practical trace-handling and monitoring policies that improve reliability without assuming intermediate tokens are inherently faithful explanations.

---

### DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding

Authors: Jiaming Zhou, Xuxin Cheng, Shiwan Zhao, Yuhang Jia, Cao Liu, Ke Zeng, Xunliang Cai, Yong Qin
Published: 2026-01-30
Categories: cs.SD, cs.CL
arXiv: https://arxiv.org/abs/2601.23161v1

Autoregressive (AR) large audio language models (LALMs) such as Qwen-2.5-Omni have achieved strong performance on audio understanding and interaction, but scaling them remains costly in data and computation, and strictly sequential decoding limits inference efficiency. Diffusion large language models (dLLMs) have recently been shown to make effective use of limited training data, and prior work on DIFFA indicates that replacing an AR backbone with a diffusion counterpart can substantially improve audio understanding under matched settings, albeit at a proof-of-concept scale without large-scale instruction tuning, preference alignment, or practical decoding schemes. We introduce DIFFA-2, a practical diffusion-based LALM for general audio understanding. DIFFA-2 upgrades the speech encoder, employs dual semantic and acoustic adapters, and is trained with a four-stage curriculum that combines semantic and acoustic alignment, large-scale supervised fine-tuning, and variance-reduced preference optimization, using only fully open-source corpora. Experiments on MMSU, MMAU, and MMAR show that DIFFA-2 consistently improves over DIFFA and is competitive to strong AR LALMs under practical training budgets, supporting diffusion-based modeling is a viable backbone for large-scale audio understanding. Our code is available at https://github.com/NKU-HLT/DIFFA.git.

---

### Segment Any Events with Language

Authors: Seungjun Lee, Gim Hee Lee
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.23159v1

Scene understanding with free-form language has been widely explored within diverse modalities such as images, point clouds, and LiDAR. However, related studies on event sensors are scarce or narrowly centered on semantic-level understanding. We introduce SEAL, the first Semantic-aware Segment Any Events framework that addresses Open-Vocabulary Event Instance Segmentation (OV-EIS). Given the visual prompt, our model presents a unified framework to support both event segmentation and open-vocabulary mask classification at multiple levels of granularity, including instance-level and part-level. To enable thorough evaluation on OV-EIS, we curate four benchmarks that cover label granularity from coarse to fine class configurations and semantic granularity from instance-level to part-level understanding. Extensive experiments show that our SEAL largely outperforms proposed baselines in terms of performance and inference speed with a parameter-efficient architecture. In the Appendix, we further present a simple variant of our SEAL achieving generic spatiotemporal OV-EIS that does not require any visual prompts from users in the inference. Check out our project page in https://0nandon.github.io/SEAL

---

### No More, No Less: Least-Privilege Language Models

Authors: Paulius Rauba, Dominykas Seputis, Patrikas Vanagas, Mihaela van der Schaar
Published: 2026-01-30
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2601.23157v2

Least privilege is a core security principle: grant each request only the minimum access needed to achieve its goal. Deployed language models almost never follow it, instead being exposed through a single API endpoint that serves all users and requests. This gap exists not because least privilege would be unhelpful; deployments would benefit greatly from reducing unnecessary capability exposure. The real obstacle is definitional and mechanistic: what does "access" mean inside a language model, and how can we enforce it without retraining or deploying multiple models? We take inspiration from least privilege in computer systems and define a class of models called least-privilege language models, where privilege is reachable internal computation during the forward pass. In this view, lowering privilege literally shrinks the model's accessible function class, as opposed to denying access via learned policies. We formalize deployment-time control as a monitor-allocator-enforcer stack, separating (i) request-time signals, (ii) a decision rule that allocates privilege, and (iii) an inference-time mechanism that selects privilege. We then propose Nested Least-Privilege Networks, a shape-preserving, rank-indexed intervention that provides a smooth, reversible control knob. We show that this knob yields policy-usable privilege-utility frontiers and enables selective suppression of targeted capabilities with limited collateral degradation across various policies. Most importantly, we argue for a new deployment paradigm that challenges the premise that language models can only be controlled at the output level.

---

### Unsupervised Hierarchical Skill Discovery

Authors: Damion Harvey, Geraud Nangue Tasse, Benjamin Rosman, Branden Ingram, Steven James
Published: 2026-01-30
Categories: cs.LG, cs.FL
arXiv: https://arxiv.org/abs/2601.23156v2

We consider the problem of unsupervised skill segmentation and hierarchical structure discovery in reinforcement learning. While recent approaches have sought to segment trajectories into reusable skills or options, most rely on action labels, rewards, or handcrafted annotations, limiting their applicability. We propose a method that segments unlabelled trajectories into skills and induces a hierarchical structure over them using a grammar-based approach. The resulting hierarchy captures both low-level behaviours and their composition into higher-level skills. We evaluate our approach in high-dimensional, pixel-based environments, including Craftax and the full, unmodified version of Minecraft. Using metrics for skill segmentation, reuse, and hierarchy quality, we find that our method consistently produces more structured and semantically meaningful hierarchies than existing baselines. Furthermore, as a proof of concept, we demonstrate that these discovered hierarchies accelerate and stabilise learning on downstream reinforcement learning tasks.

---

### SPICE: Submodular Penalized Information-Conflict Selection for Efficient Large Language Model Training

Authors: Powei Chang, Jinpeng Zhang, Bowen Chen, Chenyu Wang, Chenlu Guo, Yixing Zhang, Yukang Gao, JianXiang Xiang, Yue Gao, Chaoqun Sun, Yiyi Chen, Dongying Kong
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.23155v2

Information-based data selection for instruction tuning is compelling: maximizing the log-determinant of the Fisher information yields a monotone submodular objective, enabling greedy algorithms to achieve a $(1-1/e)$ approximation under a cardinality budget. In practice, however, we identify alleviating gradient conflicts, misalignment between per-sample gradients, is a key factor that slows down the decay of marginal log-determinant information gains, thereby preventing significant loss of information. We formalize this via an $\varepsilon$-decomposition that quantifies the deviation from ideal submodularity as a function of conflict statistics, yielding data-dependent approximation factors that tighten as conflicts diminish. Guided by this analysis, we propose SPICE, a conflict-aware selector that maximizes information while penalizing misalignment, and that supports early stopping and proxy models for efficiency. Empirically, SPICE selects subsets with higher log-determinant information than original criteria, and these informational gains translate into performance improvements: across 8 benchmarks with LLaMA2-7B and Qwen2-7B, SPICE uses only 10% of the data, yet matches or exceeds 6 methods including full-data tuning. This achieves performance improvements with substantially lower training cost.

---

### On Safer Reinforcement Learning for Sedation and Analgesia in Intensive Care

Authors: Joel Romero-Hernandez, Oscar Camara
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.23154v2

Pain management in intensive care usually involves complex trade-offs, since both inadequate and excessive treatment can compromise patient safety. Prior work on reinforcement learning for sedation and analgesia has explored how to optimize these interventions, but has not considered patient survival or partial observability. To investigate the risks of these design choices, we developed an offline deep reinforcement learning framework that suggests hourly medication doses based on recurrent state representations. Using retrospective data from 47,144 ICU stays in the MIMIC-IV database, we trained and evaluated behavior-regularized actor-critic models that prescribe continuous doses of opioids, propofol, benzodiazepines, and dexmedetomidine according to two goals: reduce pain or jointly reduce pain and 30-day post-discharge mortality. Although the two resulting policies were associated with lower pain, clinician agreement with the pain-only policy was positively correlated with mortality ($ρ$=0.119, p<0.0001), while agreement with the joint policy was negatively correlated ($ρ$=-0.316, p<0.0001). We found that such divergence arose from a different response to high levels of comorbidity. This suggests that valuing post-discharge outcomes could be critical for learning safer treatment policies, even if a short-term goal remains the primary objective.

---

### Behemoth: Benchmarking Unlearning in LLMs Using Fully Synthetic Data

Authors: Eugenia Iofinova, Dan Alistarh
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.23153v1

As artificial neural networks, and specifically large language models, have improved rapidly in capabilities and quality, they have increasingly been deployed in real-world applications, from customer service to Google search, despite the fact that they frequently make factually incorrect or undesirable statements. This trend has inspired practical and academic interest in model editing, that is, in adjusting the weights of the model to modify its likely outputs for queries relating to a specific fact or set of facts. This may be done either to amend a fact or set of facts, for instance, to fix a frequent error in the training data, or to suppress a fact or set of facts entirely, for instance, in case of dangerous knowledge. Multiple methods have been proposed to do such edits. However, at the same time, it has been shown that such model editing can be brittle and incomplete. Moreover the effectiveness of any model editing method necessarily depends on the data on which the model is trained, and, therefore, a good understanding of the interaction of the training data distribution and the way it is stored in the network is necessary and helpful to reliably perform model editing. However, working with large language models trained on real-world data does not allow us to understand this relationship or fully measure the effects of model editing. We therefore propose Behemoth, a fully synthetic data generation framework. To demonstrate the practical insights from the framework, we explore model editing in the context of simple tabular data, demonstrating surprising findings that, in some cases, echo real-world results, for instance, that in some cases restricting the update rank results in a more effective update. The code is available at https://github.com/IST-DASLab/behemoth.git.

---

### Manifold-Aware Perturbations for Constrained Generative Modeling

Authors: Katherine Keegan, Lars Ruthotto
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.23151v1

Generative models have enjoyed widespread success in a variety of applications. However, they encounter inherent mathematical limitations in modeling distributions where samples are constrained by equalities, as is frequently the setting in scientific domains. In this work, we develop a computationally cheap, mathematically justified, and highly flexible distributional modification for combating known pitfalls in equality-constrained generative models. We propose perturbing the data distribution in a constraint-aware way such that the new distribution has support matching the ambient space dimension while still implicitly incorporating underlying manifold geometry. Through theoretical analyses and empirical evidence on several representative tasks, we illustrate that our approach consistently enables data distribution recovery and stable sampling with both diffusion models and normalizing flows.

---

### Compressed BC-LISTA via Low-Rank Convolutional Decomposition

Authors: Han Wang, Yhonatan Kvich, Eduardo Pérez, Florian Römer, Yonina C. Eldar
Published: 2026-01-30
Categories: eess.IV, cs.LG
arXiv: https://arxiv.org/abs/2601.23148v1

We study Sparse Signal Recovery (SSR) methods for multichannel imaging with compressed {forward and backward} operators that preserve reconstruction accuracy. We propose a Compressed Block-Convolutional (C-BC) measurement model based on a low-rank Convolutional Neural Network (CNN) decomposition that is analytically initialized from a low-rank factorization of physics-derived forward/backward operators in time delay-based measurements. We use Orthogonal Matching Pursuit (OMP) to select a compact set of basis filters from the analytic model and compute linear mixing coefficients to approximate the full model. We consider the Learned Iterative Shrinkage-Thresholding Algorithm (LISTA) network as a representative example for which the C-BC-LISTA extension is presented. In simulated multichannel ultrasound imaging across multiple Signal-to-Noise Ratios (SNRs), C-BC-LISTA requires substantially fewer parameters and smaller model size than other state-of-the-art (SOTA) methods while improving reconstruction accuracy. In ablations over OMP, Singular Value Decomposition (SVD)-based, and random initializations, OMP-initialized structured compression performs best, yielding the most efficient training and the best performance.

---

### Securing Time Integrity in Energy IoT Against Clock Drift and Y2K38 Failures

Authors: Saeid Jamshidi, Foutse Khomh, Carol Fung, Omar Abdul Wahab, Rolando Herrero
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.23147v3

Time integrity across distributed Internet of Things (IoT) devices is fundamental to reliable sensing, control, and security in energy cyber-physical systems. However, operational energy IoT systems remain vulnerable to clock-drift escalation, time-synchronization manipulation, and catastrophic timestamp discontinuities, e.g., the Year 2038 (Y2K38) Unix epoch overflow. These failures violate timestamp monotonicity, distort temporal ordering, and introduce structured inconsistencies in system observations. Conventional anomaly detection models, which typically assume reliable and uniformly ordered timestamps, are therefore ill-equipped to capture timing-layer failures. This paper introduces STGAT (Spatio-Temporal Graph Attention Network), a clock-dynamics-aware anomaly detection solution that jointly models temporal distortion and inter-device consistency in energy IoT systems. STGAT integrates drift-aware temporal embeddings and temporal self-attention to capture non-uniform and corrupted time evolution within individual device streams, while graph attention models the spatial propagation of timing inconsistencies across interconnected nodes. A Jacobian-regularized latent representation further promotes geometric separation between nominal clock evolution and anomalous temporal deformation caused by drift escalation, synchronization offsets, jitter accumulation, and epoch-overflow events. Experimental evaluation on energy IoT telemetry augmented with controlled timing-layer perturbations shows that STGAT achieves 95.7% accuracy, 94.0% precision, 92.0% recall, 93.0% F1-score, and 0.97 AUC under the primary test setting. STGAT also reduces detection delay to 2.3 time steps, corresponding to a 26% improvement over the closest baseline, while maintaining stable performance under overflow-induced discontinuities, stealthy drift escalation, and temporally induced physical inconsistencies.

---

### THINKSAFE: Self-Generated Safety Alignment for Reasoning Models

Authors: Seanie Lee, Sangwoo Park, Yumin Choi, Gyeongman Kim, Minki Kang, Jihun Yun, Dongmin Park, Jongho Park, Sung Ju Hwang
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.23143v4

Large reasoning models (LRMs) achieve remarkable performance by leveraging reinforcement learning (RL) on reasoning tasks to generate long chain-of-thought (CoT) reasoning. However, this over-optimization often prioritizes compliance, making models vulnerable to harmful prompts. To mitigate this safety degradation, recent approaches rely on external teacher distillation, yet this introduces a distributional discrepancy that degrades native reasoning. We formalize safety realignment as a KL projection onto the safe simplex and prove that the student's own safety-filtered distribution is the unique KL-optimal target, while any external teacher incurs an irreducible excess KL penalty. Guided by this analysis, we propose ThinkSafe, a self-generated alignment framework that restores safety without external teachers. Our key insight is that while compliance suppresses safety mechanisms, models often retain latent knowledge to identify harm. ThinkSafe unlocks this via lightweight refusal steering, which preserves the KL-optimal target while increasing the acceptance rate. Experiments on DeepSeek-R1-Distill and Qwen3 show ThinkSafe significantly improves safety while preserving reasoning proficiency, and achieves superior safety and comparable reasoning to GRPO with roughly an order of magnitude less compute. Code, models, and datasets are available at https://github.com/seanie12/ThinkSafe and https://huggingface.co/Seanie-lee/collections.

---

### Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive Gradients

Authors: Cheng Ge, Caitlyn Heqi Yin, Hao Liang, Jiawei Zhang
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.23135v1

Reinforcement learning (RL) has become a key driver of language model reasoning. Among RL algorithms, Group Relative Policy Optimization (GRPO) is the de facto standard, avoiding the need for a critic by using per-prompt baselines and variance normalization. Yet why and when this normalization helps remains unclear. In this work, we provide an explanation through the lens of local curvature of the sequence-level policy gradient: standard deviation normalization implements an adaptive gradient. Theoretically, under mild conditions, GRPO enjoys a strictly improved convergence rate over unnormalized REINFORCE, with gains characterized by the average within-prompt reward standard deviation across prompts and iterations. Empirically, our analysis on GSM8K and MATH benchmarks reveals three distinct training phases governed by the interplay between feature orthogonality and reward variance: (I) an early acceleration phase where high variance and orthogonality favor adaptive scaling; (II) a relatively stable transition phase; and (III) a late-stage regime where the loss of orthogonality limits further gains. Together, these results provide a principled account of when std normalization helps in GRPO, and offer broader insights into the design of critic-free RL algorithms.

---