# Research Papers — 2026-01 · bundle page 5 of 189

> Full-text markdown of papers #201–250 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/5
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/4.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/6.md)

### Scalable Generative Game Engine: Breaking the Resolution Wall via Hardware-Algorithm Co-Design

Authors: Wei Zeng, Xuchen Li, Ruili Feng, Zhen Liu, Fengwei An, Jian Zhao
Published: 2026-01-31
Categories: cs.AI, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2602.00608v1

Real-time generative game engines represent a paradigm shift in interactive simulation, promising to replace traditional graphics pipelines with neural world models. However, existing approaches are fundamentally constrained by the ``Memory Wall,'' restricting practical deployments to low resolutions (e.g., $64 \times 64$). This paper bridges the gap between generative models and high-resolution neural simulations by introducing a scalable \textit{Hardware-Algorithm Co-Design} framework. We identify that high-resolution generation suffers from a critical resource mismatch: the World Model is compute-bound while the Decoder is memory-bound. To address this, we propose a heterogeneous architecture that intelligently decouples these components across a cluster of AI accelerators. Our system features three core innovations: (1) an asymmetric resource allocation strategy that optimizes throughput under sequence parallelism constraints; (2) a memory-centric operator fusion scheme that minimizes off-chip bandwidth usage; and (3) a manifold-aware latent extrapolation mechanism that exploits temporal redundancy to mask latency. We validate our approach on a cluster of programmable AI accelerators, enabling real-time generation at $720 \times 480$ resolution -- a $50\times$ increase in pixel throughput over prior baselines. Evaluated on both continuous 3D racing and discrete 2D platformer benchmarks, our system delivers fluid 26.4 FPS and 48.3 FPS respectively, with an amortized effective latency of 2.7 ms. This work demonstrates that resolving the ``Memory Wall'' via architectural co-design is not merely an optimization, but a prerequisite for enabling high-fidelity, responsive neural gameplay.

---

### Actor-Dual-Critic Dynamics for Zero-sum and Identical-Interest Stochastic Games

Authors: Ahmed Said Donmez, Yuksel Arslantas, Muhammed O. Sayin
Published: 2026-01-31
Categories: cs.LG, cs.GT
arXiv: https://arxiv.org/abs/2602.00606v1

We propose a novel independent and payoff-based learning framework for stochastic games that is model-free, game-agnostic, and gradient-free. The learning dynamics follow a best-response-type actor-critic architecture, where agents update their strategies (actors) using feedback from two distinct critics: a fast critic that intuitively responds to observed payoffs under limited information, and a slow critic that deliberatively approximates the solution to the underlying dynamic programming problem. Crucially, the learning process relies on non-equilibrium adaptation through smoothed best responses to observed payoffs. We establish convergence to (approximate) equilibria in two-agent zero-sum and multi-agent identical-interest stochastic games over an infinite horizon. This provides one of the first payoff-based and fully decentralized learning algorithms with theoretical guarantees in both settings. Empirical results further validate the robustness and effectiveness of the proposed approach across both classes of games.

---

### Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains

Authors: Luca Viano, Ruida Zhou, Yifan Sun, Mahdi Namazifar, Volkan Cevher, Shoham Sabach, Mohammad Ghavamzadeh
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00603v1

The class of direct preference optimization (DPO) algorithms has emerged as a promising approach for solving the alignment problem in foundation models. These algorithms work with very limited feedback in the form of pairwise preferences and fine-tune models to align with these preferences without explicitly learning a reward model. While the form of feedback used by these algorithms makes the data collection process easy and relatively more accurate, its ambiguity in terms of the quality of responses could have negative implications. For example, it is not clear if a decrease (increase) in the likelihood of preferred (dispreferred) responses during the execution of these algorithms could be interpreted as a positive or negative phenomenon. In this paper, we study how to design algorithms that can leverage additional information in the form of rating gap, which informs the learner how much the chosen response is better than the rejected one. We present new algorithms that can achieve faster statistical rates than DPO in presence of accurate rating gap information. Moreover, we theoretically prove and empirically show that the performance of our algorithms is robust to inaccuracy in rating gaps. Finally, we demonstrate the solid performance of our methods in comparison to a number of DPO-style algorithms across a wide range of LLMs and evaluation benchmarks.

---

### Hermes the Polyglot: A Unified Framework to Enhance Expressiveness for Multimodal Interlingual Subtitling

Authors: Chaoqun Cui, Shijing Wang, Liangbin Huang, Qingqing Gu, Zhaolong Huang, Xiao Zeng, Wenji Mao
Published: 2026-01-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.00597v1

Interlingual subtitling, which translates subtitles of visual media into a target language, is essential for entertainment localization but has not yet been explored in machine translation. Although Large Language Models (LLMs) have significantly advanced the general capabilities of machine translation, the distinctive characteristics of subtitle texts pose persistent challenges in interlingual subtitling, particularly regarding semantic coherence, pronoun and terminology translation, and translation expressiveness. To address these issues, we present Hermes, an LLM-based automated subtitling framework. Hermes integrates three modules: Speaker Diarization, Terminology Identification, and Expressiveness Enhancement, which effectively tackle the above challenges. Experiments demonstrate that Hermes achieves state-of-the-art diarization performance and generates expressive, contextually coherent translations, thereby advancing research in interlingual subtitling.

---

### Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks

Authors: Govind Waghmare, Srini Rohan Gujulla Leel, Nikhil Tumbde, Sumedh B G, Sonia Gupta, Srikanta Bedathur
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00596v1

Temporal Graph Neural Networks (TGNNs) aim to capture the evolving structure and timing of interactions in dynamic graphs. Although many models incorporate time through encodings or architectural design, they often compute attention over entangled node and edge representations, failing to reflect their distinct temporal behaviors. Node embeddings evolve slowly as they aggregate long-term structural context, while edge features reflect transient, timestamped interactions (e.g. messages, trades, or transactions). This mismatch results in semantic attention blurring, where attention weights cannot distinguish between slowly drifting node states and rapidly changing, information-rich edge interactions. As a result, models struggle to capture fine-grained temporal dependencies and provide limited transparency into how temporal relevance is computed. This paper introduces KEAT (Kernelized Edge Attention for Temporal Graphs), a novel attention formulation that modulates edge features using a family of continuous-time kernels, including Laplacian, RBF, and learnable MLP variant. KEAT preserves the distinct roles of nodes and edges, and integrates seamlessly with both Transformer-style (e.g., DyGFormer) and message-passing (e.g., TGN) architectures. It achieves up to 18% MRR improvement over the recent DyGFormer and 7% over TGN on link prediction tasks, enabling more accurate, interpretable and temporally aware message passing in TGNNs.

---

### Kanade: A Simple Disentangled Tokenizer for Spoken Language Modeling

Authors: Zhijie Huang, Stephen McIntosh, Daisuke Saito, Nobuaki Minematsu
Published: 2026-01-31
Categories: cs.CL, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2602.00594v2

A good language model starts with a good tokenizer. Tokenization is especially important for speech modeling, which must handle continuous signals that mix linguistic and non-linguistic information. A speech tokenizer should extract phonetics and prosody, suppress linguistically irrelevant information like speaker identity, and enable high-quality synthesis. We present Kanade, a single-layer disentangled speech tokenizer that realizes this ideal. Kanade separates out acoustic constants to create a single stream of tokens that captures rich phonetics and prosody. It does so without the need for auxiliary methods that existing disentangled codecs often rely on. Experiments show that Kanade achieves state-of-the-art speaker disentanglement and lexical availability, while maintaining excellent reconstruction quality.

---

### Pix2Fact: When Vision Is Not Enough -- Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes

Authors: Yifan Jiang, Cong Zhang, Bofei Zhang, Qiaofeng Zheng, Yifan Yang, Bingzhang Wang, Yew-Soon Ong
Published: 2026-01-31
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.00593v4

Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and external knowledge, a synergy overlooked by existing benchmarks that evaluate these abilities in isolation. To fill this void, we introduce Pix2Fact, a visual question-answering benchmark designed to assess expert-level visual perception and knowledge search. Pix2Fact comprises 1,000 high-resolution (4K+) images spanning eight scenarios. Its questions and answers are meticulously crafted by PhD-holding annotators from top global universities across diverse disciplines. Each question requires detailed visual grounding and the integration of external knowledge. Evaluating ten state-of-the-art VLMs, including proprietary models such as Gemini-3.1-Pro and GPT-5.4, we find that Pix2Fact poses a formidable challenge: the most advanced model (Gemini-3.1-Pro) achieves only 51.7% average accuracy, even with access to visual ground truth and search tools. Our analysis attributes this low accuracy to three factors, frequent visual grounding errors even with visual ground truth, shallow search harnessing, and VLM's inability to retrieve long-tail, unstructured local information. This striking gap exposes the limitations of current models in assisting humans with real-world scenarios that demand overwhelming visual comprehension. We believe Pix2Fact will serve as a critical benchmark to drive the next generation of language-vision agents that seamlessly integrate fine-grained perception with robust knowledge search.

---

### DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder

Authors: Jiaran Zhang, Luck Ma, Fanqi Wan, Di Qi, Xu Zhao, Jieyi Hou, Zhe Xie, Mengqiang Ren, Xin Wu, Zhewei Huang, Liangyu Chen, Qi Han et al.
Published: 2026-01-31
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2602.00592v2

Reliable Docker-based environment construction is a dominant bottleneck for scaling execution-grounded training and evaluation of software engineering agents. We introduce DockSmith, a specialized agentic Docker builder designed to address this challenge. DockSmith treats environment construction not only as a preprocessing step, but as a core agentic capability that exercises long-horizon tool use, dependency reasoning, and failure recovery, yielding supervision that transfers beyond Docker building itself. DockSmith is trained on large-scale, execution-grounded Docker-building trajectories produced by a SWE-Factory-style pipeline augmented with a loop-detection controller and a cross-task success memory. Training a 30B-A3B model on these trajectories achieves open-source state-of-the-art performance on Multi-Docker-Eval, with 39.72% Fail-to-Pass and 58.28% Commit Rate. Moreover, DockSmith improves out-of-distribution performance on SWE-bench Verified, SWE-bench Multilingual, and Terminal-Bench 2.0, demonstrating broader agentic benefits of environment construction.

---

### Multimodal Machine Learning for Integrating Heterogeneous Analytical Systems

Authors: Shun Muroga, Hideaki Nakajima, Taiyo Shimizu, Kazufumi Kobashi, Kenji Hata
Published: 2026-01-31
Categories: cond-mat.mtrl-sci, cond-mat.soft, cs.AI, cs.LG, physics.data-an
arXiv: https://arxiv.org/abs/2602.00590v1

Understanding structure-property relationships in complex materials requires integrating complementary measurements across multiple length scales. Here we propose an interpretable "multimodal" machine learning framework that unifies heterogeneous analytical systems for end-to-end characterization, demonstrated on carbon nanotube (CNT) films whose properties are highly sensitive to microstructural variations. Quantitative morphology descriptors are extracted from SEM images via binarization, skeletonization, and network analysis, capturing curvature, orientation, intersection density, and void geometry. These SEM-derived features are fused with Raman indicators of crystallinity/defect states, specific surface area from gas adsorption, and electrical surface resistivity. Multi-dimensional visualization using radar plots and UMAP reveals clear clustering of CNT films according to crystallinity and entanglements. Regression models trained on the multimodal feature set show that nonlinear approaches, particularly XGBoost, achieve the best predictive accuracy under leave-one-out cross-validation. Feature-importance analysis further provides physically meaningful interpretations: surface resistivity is primarily governed by junction-to-junction transport length scales, crystallinity/defect-related metrics, and network connectivity, whereas specific surface area is dominated by intersection density and void size. The proposed multimodal machine learning framework offers a general strategy for data-driven, explainable characterization of complex materials.

---

### SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacement

Authors: Xiangfei Qiu, Xvyuan Liu, Tianen Shen, Xingjian Wu, Hanyin Cheng, Bin Yang, Jilin Hu
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00589v1

Time series forecasting is important in many fields that require accurate predictions for decision-making. Patching techniques, commonly used and effective in time series modeling, help capture temporal dependencies by dividing the data into patches. However, existing patch-based methods fail to dynamically select patches and typically use all patches during the prediction process. In real-world time series, there are often low-quality issues during data collection, such as missing values, distribution shifts, anomalies and white noise, which may cause some patches to contain low-quality information, negatively impacting the prediction results. To address this issue, this study proposes a robust time series forecasting framework called SEER. Firstly, we propose an Augmented Embedding Module, which improves patch-wise representations using a Mixture-of-Experts (MoE) architecture and obtains series-wise token representations through a channel-adaptive perception mechanism. Secondly, we introduce a Learnable Patch Replacement Module, which enhances forecasting robustness and model accuracy through a two-stage process: 1) a dynamic filtering mechanism eliminates negative patch-wise tokens; 2) a replaced attention module substitutes the identified low-quality patches with global series-wise token, further refining their representations through a causal attention mechanism. Comprehensive experimental results demonstrate the SOTA performance of SEER.

---

### The French Drama Revolution: Political Economy and Literary Production, 1700-1900

Authors: Thiago Dumont Oliveira
Published: 2026-01-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.00588v1

This paper investigates the changing nature of French drama between 1700-1900 using Latent Dirichlet Allocation and Jensen-Shannon Divergence. Results indicate that the topical distribution of French drama changed profoundly after the French Revolution, particularly between 1789 and 1850. Bourgeois themes emerged among the most prevalent topics since the late 18th century. To assess the coevolution of drama and economic growth, I plot the yearly prevalence of topics alongside French GDP between 1700-1900, and discuss these changes in light of the political and economic changes prompted by the French Revolution and the industrialization of the country.

---

### Safe Langevin Soft Actor Critic

Authors: Mahesh Keswani, Samyak Jain, Raunak P. Bhattacharyya
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00587v1

Balancing reward and safety in constrained reinforcement learning remains challenging due to poor generalization from sharp value minima and inadequate handling of heavy-tailed risk distribution. We introduce Safe Langevin Soft Actor-Critic (SL-SAC), a principled algorithm that addresses both issues through parameter-space exploration and distributional risk control. Our approach combines three key mechanisms: (1) Adaptive Stochastic Gradient Langevin Dynamics (aSGLD) for reward critics, promoting ensemble diversity and escape from poor optima; (2) distributional cost estimation via Implicit Quantile Networks (IQN) with Conditional Value-at-Risk (CVaR) optimization for tail-risk mitigation; and (3) a reactive Lagrangian relaxation scheme that adapts constraint enforcement based on the empirical CVaR of episodic costs. We provide theoretical guarantees on CVaR estimation error and demonstrate that CVaR-based Lagrange updates yield stronger constraint violation signals than expected-cost updates. On Safety-Gymnasium benchmarks, SL-SAC achieves the lowest cost in 7 out of 10 tasks while maintaining competitive returns, with cost reductions of 19-63% in velocity tasks compared to state-of-the-art baselines.

---

### RAG-GNN: Integrating Retrieved Knowledge with Graph Neural Networks for Precision Medicine

Authors: Hasi Hays, William J. Richardson
Published: 2026-01-31
Categories: q-bio.MN, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.00586v2

Network topology excels at structural predictions but fails to capture functional semantics encoded in biomedical literature. We present RAG-GNN, an end-to-end trainable retrieval-augmented graph neural network framework that integrates GNN representations with dynamically retrieved literature-derived knowledge through a jointly optimized retrieval projection, gated fusion mechanism, and contrastive alignment. In a cancer signaling case study (379 proteins, 3,498 interactions, 14 functional categories), RAG-GNN improves functional clustering from silhouette $= -0.237 \pm 0.065$ (GNN-only) to $-0.144 \pm 0.066$, a consistent improvement of $+0.093 \pm 0.022$ across 10 random seeds, while the learned retrieval achieves mean precision@10 $= 0.242$, a 152\% improvement over the random baseline ($0.096$). Heuristic information decomposition with bootstrap confidence intervals reveals that topology and retrieval encode overwhelmingly shared information (95.6\%), with retrieval improving both intra-cluster cohesion (silhouette) and cluster agreement (ARI $+0.021 \pm 0.015$). Counterfactual experiments confirm that adversarial, absent, and random retrieval all degrade performance, validating that the gated fusion mechanism depends on document content. Benchmarking against eight established embedding methods demonstrates task-specific complementarity: topology-focused methods achieve strong link prediction, while retrieval augmentation consistently improves functional clustering within the controlled GNN-only ablation. DDR1 subnetwork analysis provides confirmatory validation consistent with established synthetic lethality relationships. These results establish that topology-only and retrieval-augmented approaches serve complementary purposes for precision medicine applications.

---

### Exploring Information Seeking Agent Consolidation

Authors: Guochen Yan, Jialong Wu, Zhengwei Tao, Bo Li, Qintong Zhang, Jiahao Xu, Haitao Mi, Yuejian Fang, Qingni Shen, Wentao Zhang, Zhonghai Wu
Published: 2026-01-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.00585v2

Information-seeking agents have emerged as a powerful paradigm for knowledge-intensive tasks, yet today's systems remain specialized for the open web, documents, or local knowledge bases, hindering scalable and cross-domain deployment. We present the first systematic empirical study of consolidating these information-seeking agents into a single foundation agentic model. We compare two paradigms -- \emph{data-level mixing}, which trains a unified model on a mixture of datasets, and \emph{parameter-level merging}, which merges independently trained experts in parameter space -- across 3 training scenarios, evaluating \textbf{26} representative parameter-level methods on \textbf{10} benchmarks. To compare across heterogeneous benchmarks, we introduce a geometric Composite Score and an Imbalance Score that describe overall performance and task skew. Our analysis shows that (i) well-designed parameter-level merging attains parity with data mixing at a fraction of its training cost and is order-agnostic; (ii) parameter-level merging structurally preserves out-of-domain capabilities that data mixing universally forgets; and (iii) cross-scenario stability is strongly tied to consolidation quality. We distil our observations into a method-selection guide and design principles for next-generation merging operators.

---

### MAUGen: A Unified Diffusion Approach for Multi-Identity Facial Expression and AU Label Generation

Authors: Xiangdong Li, Ye Lou, Ao Gao, Wei Zhang, Siyang Song
Published: 2026-01-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.00583v1

The lack of large-scale, demographically diverse face images with precise Action Unit (AU) occurrence and intensity annotations has long been recognized as a fundamental bottleneck in developing generalizable AU recognition systems. In this paper, we propose MAUGen, a diffusion-based multi-modal framework that jointly generates a large collection of photorealistic facial expressions and anatomically consistent AU labels, including both occurrence and intensity, conditioned on a single descriptive text prompt. Our MAUGen involves two key modules: (1) a Multi-modal Representation Learning (MRL) module that captures the relationships among the paired textual description, facial identity, expression image, and AU activations within a unified latent space; and (2) a Diffusion-based Image label Generator (DIG) that decodes the joint representation into aligned facial image-label pairs across diverse identities. Under this framework, we introduce Multi-Identity Facial Action (MIFA), a large-scale multimodal synthetic dataset featuring comprehensive AU annotations and identity variations. Extensive experiments demonstrate that MAUGen outperforms existing methods in synthesizing photorealistic, demographically diverse facial images along with semantically aligned AU labels.

---

### Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecasting

Authors: Xiangfei Qiu, Kangjia Yan, Xvyuan Liu, Xingjian Wu, Jilin Hu
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00582v1

Irregular multivariate time series forecasting (IMTSF) is challenging due to non-uniform sampling and variable asynchronicity. These irregularities violate the equidistant assumptions of standard models, hindering local temporal modeling and rendering classical frequency-domain methods ineffective for capturing global periodic structures. To address this challenge, we propose TFMixer, a joint time-frequency modeling framework for IMTS forecasting. Specifically, TFMixer incorporates a Global Frequency Module that employs a learnable Non-Uniform Discrete Fourier Transform (NUDFT) to directly extract spectral representations from irregular timestamps. In parallel, the Local Time Module introduces a query-based patch mixing mechanism to adaptively aggregate informative temporal patches and alleviate information density imbalance. Finally, TFMixer fuses the time-domain and frequency-domain representations to generate forecasts and further leverages inverse NUDFT for explicit seasonal extrapolation. Extensive experiments on real-world datasets demonstrate the state--of-the-art performance of TFMixer.

---

### Small Shifts, Large Gains: Unlocking Traditional TSP Heuristic Guided-Sampling via Unsupervised Neural Instance Modification

Authors: Wei Huang, Hanchen Wang, Dong Wen, Wenjie Zhang
Published: 2026-01-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.00580v1

The Traveling Salesman Problem (TSP) is one of the most representative NP-hard problems in route planning and a long-standing benchmark in combinatorial optimization. Traditional heuristic tour constructors, such as Farthest or Nearest Insertion, are computationally efficient and highly practical, but their deterministic behavior limits exploration and often leads to local optima. In contrast, neural-based heuristic tour constructors alleviate this issue through guided-sampling and typically achieve superior solution quality, but at the cost of extensive training and reliance on ground-truth supervision, hindering their practical use. To bridge this gap, we propose TSP-MDF, a novel instance modification framework that equips traditional deterministic heuristic tour constructors with guided-sampling capability. Specifically, TSP-MDF introduces a neural-based instance modifier that strategically shifts node coordinates to sample multiple modified instances, on which the base traditional heuristic tour constructor constructs tours that are mapped back to the original instance, allowing traditional tour constructors to explore higher-quality tours and escape local optima. At the same time, benefiting from our instance modification formulation, the neural-based instance modifier can be trained efficiently without any ground-truth supervision, ensuring the framework maintains practicality. Extensive experiments on large-scale TSP benchmarks and real-world benchmarks demonstrate that TSP-MDF significantly improves the performance of traditional heuristics tour constructors, achieving solution quality comparable to neural-based heuristic tour constructors, but with an extremely short training time.

---

### Bridging Degradation Discrimination and Generation for Universal Image Restoration

Authors: JiaKui Hu, Zhengjian Yao, Lujia Jin, Yanye Lu
Published: 2026-01-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00579v1

Universal image restoration is a critical task in low-level vision, requiring the model to remove various degradations from low-quality images to produce clean images with rich detail. The challenges lie in sampling the distribution of high-quality images and adjusting the outputs on the basis of the degradation. This paper presents a novel approach, Bridging Degradation discrimination and Generation (BDG), which aims to address these challenges concurrently. First, we propose the Multi-Angle and multi-Scale Gray Level Co-occurrence Matrix (MAS-GLCM) and demonstrate its effectiveness in performing fine-grained discrimination of degradation types and levels. Subsequently, we divide the diffusion training process into three distinct stages: generation, bridging, and restoration. The objective is to preserve the diffusion model's capability of restoring rich textures while simultaneously integrating the discriminative information from the MAS-GLCM into the restoration process. This enhances its proficiency in addressing multi-task and multi-degraded scenarios. Without changing the architecture, BDG achieves significant performance gains in all-in-one restoration and real-world super-resolution tasks, primarily evidenced by substantial improvements in fidelity without compromising perceptual quality. The code and pretrained models are provided in https://github.com/MILab-PKU/BDG.

---

### SAU: Sparsity-Aware Unlearning for LLMs via Gradient Masking and Importance Redistribution

Authors: Yuze Wang, Yujia Tong, Xuan Liu, Junhao Dong
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00577v3

Large Language Models (LLMs) inevitably memorize sensitive information during training, posing significant privacy risks. Machine unlearning has emerged as a promising solution to selectively remove such information without full retraining. However, existing methods are designed for dense models and overlook model sparsification, an essential technique for efficient LLM deployment. We find that unlearning effectiveness degrades substantially on sparse models. Through empirical analysis, we reveal that this degradation occurs because existing unlearning methods require updating all parameters, yet sparsification prunes substantial weights to zero, fundamentally limiting the model's forgetting capacity. To address this challenge, we propose Sparsity-Aware Unlearning (SAU), which decouples unlearning from sparsification objectives through gradient masking that redirects updates to surviving weights, combined with importance-aware redistribution to compensate for pruned parameters. Extensive experiments demonstrate that SAU significantly outperforms existing methods on sparse LLMs, achieving effective forgetting while preserving model utility.

---

### Data Distribution as a Lever for Guiding Optimizers Toward Superior Generalization in LLMs

Authors: Tushaar Gangavarapu, Jiping Li, Christopher Vattheuer, Zhangyang Wang, Baharan Mirzasoleiman
Published: 2026-01-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.00576v1

Can modifying the training data distribution guide optimizers toward solutions with improved generalization when training large language models (LLMs)? In this work, we theoretically analyze an in-context linear regression model with multi-head linear self-attention, and compare the training dynamics of two gradient based optimizers, namely gradient descent (GD) and sharpness-aware minimization (SAM), the latter exhibiting superior generalization properties but is prohibitively expensive for training even medium-sized LLMs. We show, for the first time, that SAM induces a lower simplicity bias (SB)-the tendency of an optimizer to preferentially learn simpler features earlier in training-and identify this reduction as a key factor underlying its improved generalization performance. Motivated by this insight, we demonstrate that altering the training data distribution by upsampling or augmenting examples learned later in training similarly reduces SB and leads to improved generalization. Our extensive experiments show that our strategy improves the performance of multiple LLMs-including Phi2-2.7B , Llama3.2-1B, Gemma3-1B-PT, and Qwen3-0.6B-Base-achieving relative accuracy gains up to 18% when fine-tuned with AdamW and Muon on mathematical reasoning tasks.

---

### Learning Modal-Mixed Chain-of-Thought Reasoning with Latent Embeddings

Authors: Yifei Shao, Kun Zhou, Ziming Xu, Mohammad Atif Quamar, Shibo Hao, Zhen Wang, Zhiting Hu, Biwei Huang
Published: 2026-01-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.00574v1

We study how to extend chain-of-thought (CoT) beyond language to better handle multimodal reasoning. While CoT helps LLMs and VLMs articulate intermediate steps, its text-only form often fails on vision-intensive problems where key intermediate states are inherently visual. We introduce modal-mixed CoT, which interleaves textual tokens with compact visual sketches represented as latent embeddings. To bridge the modality gap without eroding the original knowledge and capability of the VLM, we use the VLM itself as an encoder and train the language backbone to reconstruct its own intermediate vision embeddings, to guarantee the semantic alignment of the visual latent space. We further attach a diffusion-based latent decoder, invoked by a special control token and conditioned on hidden states from the VLM. In this way, the diffusion head carries fine-grained perceptual details while the VLM specifies high-level intent, which cleanly disentangles roles and reduces the optimization pressure of the VLM. Training proceeds in two stages: supervised fine-tuning on traces that interleave text and latents with a joint next-token and latent-reconstruction objective, followed by reinforcement learning that teaches when to switch modalities and how to compose long reasoning chains. Extensive experiments across 11 diverse multimodal reasoning tasks, demonstrate that our method yields better performance than language-only and other CoT methods. Our code will be publicly released.

---

### When Classes Evolve: A Benchmark and Framework for Stage-Aware Class-Incremental Learning

Authors: Zheng Zhang, Tao Hu, Xueheng Li, Yang Wang, Rui Li, Jie Zhang, Chengjun Xie
Published: 2026-01-31
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.00573v2

Class-Incremental Learning (CIL) aims to sequentially learn new classes while mitigating catastrophic forgetting of previously learned knowledge. Conventional CIL approaches implicitly assume that classes are morphologically static, focusing primarily on preserving previously learned representations as new classes are introduced. In practice, however, instances of the same semantic class may undergo substantial morphological evolution, such as a larva turning into a butterfly. Consequently, a model must both discriminate between classes and adapt to evolving appearances within a single class. To systematically address this challenge, we formalize Stage-Aware CIL (Stage-CIL), a paradigm in which each class is learned progressively through distinct morphological stages. We further introduce Stage-Bench, a 10-domain, two-stage benchmark and protocol for evaluating both inter-class forgetting and stage-level degradation within classes. Finally, we propose STAGE, an evolution-aware reference baseline that disentangles semantic identity from evolution dynamics through a fixed-size memory pool, enabling stage-aware prediction of later morphological forms from earlier representations. Extensive experiments show that conventional CIL reductions and existing continual-learning baselines remain insufficient under Stage-CIL, while STAGE consistently outperforms strong competitors, demonstrating the promise of explicit evolution-aware modeling for this new setting.

---

### GLAD: Generative Language-Assisted Visual Tracking for Low-Semantic Templates

Authors: Xingyu Luo, Yidong Cai, Jie Liu, Jie Tang, Gangshan Wu, Limin Wang
Published: 2026-01-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00570v1

Vision-language tracking has gained increasing attention in many scenarios. This task simultaneously deals with visual and linguistic information to localize objects in videos. Despite its growing utility, the development of vision-language tracking methods remains in its early stage. Current vision-language trackers usually employ Transformer architectures for interactive integration of template, search, and text features. However, persistent challenges about low-semantic images including prevalent image blurriness, low resolution and so on, may compromise model performance through degraded cross-modal understanding. To solve this problem, language assistance is usually used to deal with the obstacles posed by low-semantic images. However, due to the existing gap between current textual and visual features, direct concatenation and fusion of these features may have limited effectiveness. To address these challenges, we introduce a pioneering Generative Language-AssisteD tracking model, GLAD, which utilizes diffusion models for the generative multi-modal fusion of text description and template image to bolster compatibility between language and image and enhance template image semantic information. Our approach demonstrates notable improvements over the existing fusion paradigms. Blurry and semantically ambiguous template images can be restored to improve multi-modal features in the generative fusion paradigm. Experiments show that our method establishes a new state-of-the-art on multiple benchmarks and achieves an impressive inference speed. The code and models will be released at: https://github.com/Confetti-lxy/GLAD

---

### Forget by Uncertainty: Orthogonal Entropy Unlearning for Quantized Neural Networks

Authors: Tian Zhang, Yujia Tong, Junhao Dong, Ke Xu, Yuze Wang, Jingling Yuan
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00567v2

The deployment of quantized neural networks on edge devices, combined with privacy regulations like GDPR, creates an urgent need for machine unlearning in quantized models. However, existing methods face critical challenges: they induce forgetting by training models to memorize incorrect labels, conflating forgetting with misremembering, and employ scalar gradient reweighting that cannot resolve directional conflicts between gradients. We propose OEU, a novel Orthogonal Entropy Unlearning framework with two key innovations: 1) Entropy-guided unlearning provides an unbiased forgetting direction by maximizing prediction uncertainty on forgotten data, avoiding confident misprediction toward any specific class, and 2) Gradient orthogonal projection eliminates interference by projecting forgetting gradients onto the orthogonal complement of retain gradients, providing theoretical guarantees for utility preservation under first-order approximation. Extensive experiments demonstrate that OEU outperforms existing methods in both forgetting effectiveness and retain accuracy.

---

### Unmasking Reasoning Processes: A Process-aware Benchmark for Evaluating Structural Mathematical Reasoning in LLMs

Authors: Xiang Zheng, Weiqi Zhai, Wei Wang, Boyu Yang, Wenbo Li, Ruixiang Luo, Haoxiang Sun, Yucheng Wang, Zhengze Li, Meng Wang, Yuetian Du, Guojie Lin et al.
Published: 2026-01-31
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.00564v2

Recent large language models (LLMs) achieve near-saturation accuracy on many established mathematical reasoning benchmarks, raising concerns about their ability to diagnose genuine reasoning competence. This saturation largely stems from the dominance of template-based computation and shallow arithmetic decomposition in existing datasets, which underrepresent reasoning skills such as multi-constraint coordination, constructive logical synthesis, and spatial inference. To address this gap, we introduce ReasoningMath-Plus, a benchmark of 150 carefully curated problems explicitly designed to evaluate structural reasoning. Each problem emphasizes reasoning under interacting constraints, constructive solution formation, or non-trivial structural insight, and is annotated with a minimal reasoning skeleton to support fine-grained process-level evaluation. Alongside the dataset, we introduce HCRS (Hazard-aware Chain-based Rule Score), a deterministic step-level scoring function, and train a Process Reward Model (PRM) on the annotated reasoning traces. Empirically, while leading models attain relatively high final-answer accuracy (up to 5.8/10), HCRS-based holistic evaluation yields substantially lower scores (average 4.36/10, best 5.14/10), showing that answer-only metrics can overestimate reasoning robustness.

---

### Uncovering Latent Communication Patterns in Brain Networks via Adaptive Flow Routing

Authors: Tianhao Huang, Guanghui Min, Zhenyu Lei, Aiying Zhang, Chen Chen
Published: 2026-01-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.00561v1

Unraveling how macroscopic cognitive phenotypes emerge from microscopic neuronal connectivity remains one of the core pursuits of neuroscience. To this end, researchers typically leverage multi-modal information from structural connectivity (SC) and functional connectivity (FC) to complete downstream tasks. Recent methodologies explore the intricate coupling mechanisms between SC and FC, attempting to fuse their representations at the regional level. However, lacking fundamental neuroscientific insight, these approaches fail to uncover the latent interactions between neural regions underlying these connectomes, and thus cannot explain why SC and FC exhibit dynamic states of both coupling and heterogeneity. In this paper, we formulate multi-modal fusion through the lens of neural communication dynamics and propose the Adaptive Flow Routing Network (AFR-Net), a physics-informed framework that models how structural constraints (SC) give rise to functional communication patterns (FC), enabling interpretable discovery of critical neural pathways. Extensive experiments demonstrate that AFR-Net significantly outperforms state-of-the-art baselines. The code is available at https://anonymous.4open.science/r/DIAL-F0D1.

---

### Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models

Authors: Wenbin Xing, Quanxing Zha, Lizheng Zu, Mengran Li, Ming Li, Junchi Yan
Published: 2026-01-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.00559v1

Current research on video hallucination mitigation primarily focuses on isolated error types, leaving compositional hallucinations, arising from incorrect reasoning over multiple interacting spatial and temporal factors largely underexplored. We introduce OmniVCHall, a benchmark designed to systematically evaluate both isolated and compositional hallucinations in video multimodal large language models (VLLMs). OmniVCHall spans diverse video domains, introduces a novel camera-based hallucination type, and defines a fine-grained taxonomy, together with adversarial answer options (e.g., "All are correct" and "None of the above") to prevent shortcut reasoning. The evaluations of 39 representative VLLMs reveal that even advanced models (e.g., Qwen3-VL and GPT-5) exhibit substantial performance degradation. We propose TriCD, a contrastive decoding framework with a triple-pathway calibration mechanism. An adaptive perturbation controller dynamically selects distracting operations to construct negative video variants, while a saliency-guided enhancement module adaptively reinforces grounded token-wise visual evidences. These components are optimized via reinforcement learning to encourage precise decision-making under compositional hallucination settings. Experimental results show that TriCD consistently improves performance across two representative backbones, achieving an average accuracy improvement of over 10%. The data and code can be find at https://github.com/BMRETURN/OmniVCHall.

---

### A Hierarchical and Attentional Analysis of Argument Structure Constructions in BERT Using Naturalistic Corpora

Authors: Liu Kaipeng, Wu Ling
Published: 2026-01-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.00554v1

This study investigates how the Bidirectional Encoder Representations from Transformers model processes four fundamental Argument Structure Constructions. We employ a multi-dimensional analytical framework, which integrates MDS, t-SNE as dimensionality reduction, Generalized Discrimination Value (GDV) as cluster separation metrics, Fisher Discriminant Ratio (FDR) as linear diagnostic probing, and attention mechanism analysis. Our results reveal a hierarchical representational structure. Construction-specific information emerges in early layers, forms maximally separable clusters in middle layers, and is maintained through later processing stages.

---

### APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigation

Authors: Daoxuan Zhang, Ping Chen, Xiaobo Xia, Xiu Su, Ruichen Zhen, Jianqiang Xiao, Shuo Yang
Published: 2026-01-31
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.00551v1

Aerial Object Goal Navigation, a challenging frontier in Embodied AI, requires an Unmanned Aerial Vehicle (UAV) agent to autonomously explore, reason, and identify a specific target using only visual perception and language description. However, existing methods struggle with the memorization of complex spatial representations in aerial environments, reliable and interpretable action decision-making, and inefficient exploration and information gathering. To address these challenges, we introduce \textbf{APEX} (Aerial Parallel Explorer), a novel hierarchical agent designed for efficient exploration and target acquisition in complex aerial settings. APEX is built upon a modular, three-part architecture: 1) Dynamic Spatio-Semantic Mapping Memory, which leverages the zero-shot capability of a Vision-Language Model (VLM) to dynamically construct high-resolution 3D Attraction, Exploration, and Obstacle maps, serving as an interpretable memory mechanism. 2) Action Decision Module, trained with reinforcement learning, which translates this rich spatial understanding into a fine-grained and robust control policy. 3) Target Grounding Module, which employs an open-vocabulary detector to achieve definitive and generalizable target identification. All these components are integrated into a hierarchical, asynchronous, and parallel framework, effectively bypassing the VLM's inference latency and boosting the agent's proactivity in exploration. Extensive experiments show that APEX outperforms the previous state of the art by +4.2\% SR and +2.8\% SPL on challenging UAV-ON benchmarks, demonstrating its superior efficiency and the effectiveness of its hierarchical asynchronous design. Our source code is provided in \href{https://github.com/4amGodvzx/apex}{GitHub}

---

### Beyond the Node: Clade-level Selection for Efficient MCTS in Automatic Heuristic Design

Authors: Kezhao Lai, Yutao Lai, Hai-Lin Liu
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00549v2

While Monte Carlo Tree Search (MCTS) shows promise in Large Language Model (LLM) based Automatic Heuristic Design (AHD), it suffers from a critical over-exploitation tendency under the limited computational budgets required for heuristic evaluation. To address this limitation, we propose Clade-AHD, an efficient framework that replaces node-level point estimates with clade-level Bayesian beliefs. By aggregating descendant evaluations into Beta distributions and performing Thompson Sampling over these beliefs, Clade-AHD explicitly models uncertainty to guide exploration, enabling more reliable decision-making under sparse and noisy evaluations. Extensive experiments on complex combinatorial optimization problems demonstrate that Clade-AHD consistently outperforms state-of-the-art methods while significantly reducing computational cost. The source code is publicly available at: https://github.com/Mriya0306/Clade-AHD.

---

### Contrastive Domain Generalization for Cross-Instrument Molecular Identification in Mass Spectrometry

Authors: Seunghyun Yoo, Sanghong Kim, Namkyung Yoon, Hwangnam Kim
Published: 2026-01-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.00547v1

Identifying molecules from mass spectrometry (MS) data remains a fundamental challenge due to the semantic gap between physical spectral peaks and underlying chemical structures. Existing deep learning approaches often treat spectral matching as a closed-set recognition task, limiting their ability to generalize to unseen molecular scaffolds. To overcome this limitation, we propose a cross-modal alignment framework that directly maps mass spectra into the chemically meaningful molecular structure embedding space of a pretrained chemical language model. On a strict scaffold-disjoint benchmark, our model achieves a Top-1 accuracy of 42.2% in fixed 256-way zero-shot retrieval and demonstrates strong generalization under a global retrieval setting. Moreover, the learned embedding space demonstrates strong chemical coherence, reaching 95.4% accuracy in 5-way 5-shot molecular re-identification. These results suggest that explicitly integrating physical spectral resolution with molecular structure embedding is key to solving the generalization bottleneck in molecular identification from MS data.

---

### Depth, Not Data: An Analysis of Hessian Spectral Bifurcation

Authors: Shenyang Deng, Boyao Liao, Zhuoli Ouyang, Tianyu Pang, Yaoqing Yang
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00545v3

The eigenvalue distribution of the Hessian matrix plays a crucial role in understanding the optimization landscape of deep neural networks. Prior work has attributed the well-documented ``bulk-and-spike'' spectral structure, where a few dominant eigenvalues are separated from a bulk of smaller ones, to the imbalance in the data covariance matrix. In this work, we challenge this view by demonstrating that such spectral Bifurcation can arise purely from the network architecture, independent of data imbalance. Specifically, we analyze a deep linear network setup and prove that, even when the data covariance is perfectly balanced, the Hessian still exhibits a Bifurcation eigenvalue structure: a dominant cluster and a bulk cluster. Crucially, we establish that the ratio between dominant and bulk eigenvalues scales linearly with the network depth. This reveals that the spectral gap is strongly affected by the network architecture rather than solely by data distribution. Our results suggest that both model architecture and data characteristics should be considered when designing optimization algorithms for deep networks.

---

### Reasoning by Commented Code for Table Question Answering

Authors: Seho Pyo, Jiheon Seok, Jaejin Lee
Published: 2026-01-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.00543v1

Table Question Answering (TableQA) poses a significant challenge for large language models (LLMs) because conventional linearization of tables often disrupts the two-dimensional relationships intrinsic to structured data. Existing methods, which depend on end-to-end answer generation or single-line program queries, typically exhibit limited numerical accuracy and reduced interpretability. This work introduces a commented, step-by-step code-generation framework that incorporates explicit reasoning into the Python program-generation process. The approach decomposes TableQA reasoning into multi-line executable programs with concise natural language comments, thereby promoting clearer reasoning and increasing the likelihood of generating correct code. On the WikiTableQuestions benchmark, the proposed method achieves 70.9\% accuracy using Qwen2.5-Coder-7B-Instruct, surpassing the Repanda baseline (67.6\%). Integrating the proposed framework with a robust end-to-end TableQA model via a lightweight answer-selection mechanism yields further improvements. This combined approach achieves up to 84.3\% accuracy on the WikiTableQuestions benchmark.

---

### NPNet: A Non-Parametric Network with Adaptive Gaussian-Fourier Positional Encoding for 3D Classification and Segmentation

Authors: Mohammad Saeid, Amir Salarpour, Pedram MohajerAnsari, Mert D. Pesé
Published: 2026-01-31
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.00542v1

We present NPNet, a fully non-parametric approach for 3D point-cloud classification and part segmentation. NPNet contains no learned weights; instead, it builds point features using deterministic operators such as farthest point sampling, k-nearest neighbors, and pooling. Our key idea is an adaptive Gaussian-Fourier positional encoding whose bandwidth and Gaussian-cosine mixing are chosen from the input geometry, helping the method remain stable across different scales and sampling densities. For segmentation, we additionally incorporate fixed-frequency Fourier features to provide global context alongside the adaptive encoding. Across ModelNet40/ModelNet-R, ScanObjectNN, and ShapeNetPart, NPNet achieves strong performance among non-parametric baselines, and it is particularly effective in few-shot settings on ModelNet40. NPNet also offers favorable memory use and inference time compared to prior non-parametric methods

---

### One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models

Authors: Zilin Jing, Vincent Jeanselme, Yuta Kobayashi, Simon A. Lee, Chao Pang, Aparajita Kashyap, Yanwei Li, Xinzhuo Jiang, Shalmali Joshi
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00541v2

Clinical events captured in Electronic Health Records (EHR) are irregularly sampled and may consist of a mixture of discrete events and numerical measurements, such as laboratory values or treatment dosages. The sequential nature of EHR, analogous to natural language, has motivated the use of next-token prediction to train prior EHR Foundation Models (FMs) over events. However, this training fails to capture the full structure of EHR. When a given event occurs must be captured, but the event value (abnormal lab) also modulates the likelihood of other clinical events. Most existing EHR FMs do not jointly model this likelihood and are unable to capture the full observation process, impacting downstream capabilities. We propose ORA, a marked time-to-event pretraining objective that jointly models event timing and associated measurements. Across multiple datasets, downstream tasks, and model backbones, this objective consistently yields more generalizable representations than next-token prediction and pretraining losses that ignore continuous measurements. Importantly, the proposed objective yields improvements beyond traditional classification evaluation, including better regression and time-to-event prediction. Beyond introducing a new family of FMs, our ablations suggest a broader takeaway: pretraining objectives that account for EHR structure are critical for expanding downstream capabilities and generalizability.

---

### Surrogate Ensemble in Expensive Multi-Objective Optimization via Deep Q-Learning

Authors: Yuxin Wu, Hongshu Guo, Ting Huang, Yue-Jiao Gong, Zeyuan Ma
Published: 2026-01-31
Categories: cs.NE, cs.LG
arXiv: https://arxiv.org/abs/2602.00540v1

Surrogate-assisted Evolutionary Algorithms~(SAEAs) have shown promising robustness in solving expensive optimization problems. A key aspect that impacts SAEAs' effectiveness is surrogate model selection, which in existing works is predominantly decided by human developer. Such human-made design choice introduces strong bias into SAEAs and may hurt their expected performance on out-of-scope tasks. In this paper, we propose a reinforcement learning-assisted ensemble framework, termed as SEEMOO, which is capable of scheduling different surrogate models within a single optimization process, hence boosting the overall optimization performance in a cooperative paradigm. Specifically, we focus on expensive multi-objective optimization problems, where multiple objective functions shape a compositional landscape and hence challenge surrogate selection. SEEMOO comprises following core designs: 1) A pre-collected model pool that maintains different surrogate models; 2) An attention-based state-extractor supports universal optimization state representation of problems with varied objective numbers; 3) a deep Q-network serves as dynamic surrogate selector: Given the optimization state, it selects desired surrogate model for current-step evaluation. SEEMOO is trained to maximize the overall optimization performance under a training problem distribution. Extensive benchmark results demonstrate SEEMOO's surrogate ensemble paradigm boosts the optimization performance of single-surrogate baselines. Further ablation studies underscore the importance of SEEMOO's design components.

---

### OpenDDI: A Comprehensive Benchmark for DDI Prediction

Authors: Xinmo Jin, Bowen Fan, Xunkai Li, Henan Sun, YuXin Zeng, Zekai Chen, Yuxuan Sun, Jia Li, Qiangqiang Dai, Hongchao Qin, Rong-Hua Li, Guoren Wang
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00539v1

Drug-Drug Interactions (DDIs) significantly influence therapeutic efficacy and patient safety. As experimental discovery is resource-intensive and time-consuming, efficient computational methodologies have become essential. The predominant paradigm formulates DDI prediction as a drug graph-based link prediction task. However, further progress is hindered by two fundamental challenges: (1) lack of high-quality data: most studies rely on small-scale DDI datasets and single-modal drug representations; (2) lack of standardized evaluation: inconsistent scenarios, varied metrics, and diverse baselines. To address the above issues, we propose OpenDDI, a comprehensive benchmark for DDI prediction. Specifically, (1) from the data perspective, OpenDDI unifies 6 widely used DDI datasets and 2 existing forms of drug representation, while additionally contributing 3 new large-scale LLM-augmented datasets and a new multimodal drug representation covering 5 modalities. (2) From the evaluation perspective, OpenDDI unifies 20 SOTA model baselines across 3 downstream tasks, with standardized protocols for data quality, effectiveness, generalization, robustness, and efficiency. Based on OpenDDI, we conduct a comprehensive evaluation and derive 10 valuable insights for DDI prediction while exposing current limitations to provide critical guidance for this rapidly evolving field. Our code is available at https://github.com/xiaoriwuguang/OpenDDI

---

### SADER: Structure-Aware Diffusion Framework with DEterministic Resampling for Multi-Temporal Remote Sensing Cloud Removal

Authors: Yifan Zhang, Qian Chen, Yi Liu, Wengen Li, Jihong Guan
Published: 2026-01-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00536v1

Cloud contamination severely degrades the usability of remote sensing imagery and poses a fundamental challenge for downstream Earth observation tasks. Recently, diffusion-based models have emerged as a dominant paradigm for remote sensing cloud removal due to their strong generative capability and stable optimization. However, existing diffusion-based approaches often suffer from limited sampling efficiency and insufficient exploitation of structural and temporal priors in multi-temporal remote sensing scenarios. In this work, we propose SADER, a structure-aware diffusion framework for multi-temporal remote sensing cloud removal. SADER first develops a scalable Multi-Temporal Conditional Diffusion Network (MTCDN) to fully capture multi-temporal and multimodal correlations via temporal fusion and hybrid attention. Then, a cloud-aware attention loss is introduced to emphasize cloud-dominated regions by accounting for cloud thickness and brightness discrepancies. In addition, a deterministic resampling strategy is designed for continuous diffusion models to iteratively refine samples under fixed sampling steps by replacing outliers through guided correction. Extensive experiments on multiple multi-temporal datasets demonstrate that SADER consistently outperforms state-of-the-art cloud removal methods across all evaluation metrics. The code of SADER is publicly available at https://github.com/zyfzs0/SADER.

---

### Invertible Memory Flow Networks

Authors: Liyu Zerihun, Alexandr Plashchinsky
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00535v1

Long sequence neural memory remains a challenging problem. RNNs and their variants suffer from vanishing gradients, and Transformers suffer from quadratic scaling. Furthermore, compressing long sequences into a finite fixed representation remains an intractable problem due to the difficult optimization landscape. Invertible Memory Flow Networks (IMFN) make long sequence compression tractable through factorization: instead of learning end-to-end compression, we decompose the problem into pairwise merges using a binary tree of "sweeper" modules. Rather than learning to compress long sequences, each sweeper learns a much simpler 2-to-1 compression task, achieving O(log N) depth with sublinear error accumulation in sequence length. For online inference, we distilled into a constant-cost recurrent student achieving O(1) sequential steps. Empirical results validate IMFN on long MNIST sequences and UCF-101 videos, demonstrating compression of high-dimensional data over long sequences.

---

### AIRE-Prune: Asymptotic Impulse-Response Energy for State Pruning in State Space Models

Authors: Apurba Prasad Padhy, Fernando Camacho, Saibal Mukhopadhyay
Published: 2026-01-31
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2602.00534v1

State space models (SSMs) often sacrifice capacity, search space, or stability to offset the memory and compute costs of large state dimensions. We introduce a structured post-training pruning method for SSMs -- AIRE-Prune (Asymptotic Impulse-Response Energy for State PRUN(E)) -- that reduces each layer's state dimension by directly minimizing long-run output-energy distortion. AIRE-Prune assigns every state a closed-form asymptotic impulse-response energy-based score, i.e., the total impulse-response energy it contributes over an infinite horizon (time), and normalizes these scores layer-wise to enable global cross-layer comparison and selection. This extends modal truncation from single systems to deep stacks and aligns pruning with asymptotic response energy rather than worst-case gain. Across diverse sequence benchmarks, AIRE-Prune reveals substantial redundancy in SISO and MIMO SSMs with average pruning of 60.8%, with average accuracy drop of 0.29% without retraining, while significantly lowering compute. Code: https://github.com/falcon-arrow/AIRE-Prune.

---

### Convergent World Representations and Divergent Tasks

Authors: Core Francisco Park
Published: 2026-01-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.00533v1

While neural representations are central to modern deep learning, the conditions governing their geometry and their roles in downstream adaptability remain poorly understood. We develop a framework clearly separating the underlying world, the data generation process and the resulting model representations to study these questions in a controlled setup. 5,075 city coordinates define the world and 7 geometric tasks generate the training data for autoregressive training. We find that different tasks give rise to qualitatively and quantitatively distinct world representation geometries. However, multi-task training drives convergence of world representations: models trained on non-overlapping tasks develop aligned geometric representations, providing controlled evidence for the Multitask Scaling Hypothesis of the Platonic Representation Hypothesis. To study adaptation, we pretrain models on all tasks, then test whether new entities (cities) can be consistently integrated into the representation space via fine-tuning. Surprisingly, we find that despite multi-task pretraining, some tasks, which we call divergent, actively harm the representational integration of new entities and harm generalization. Our results show that training on multiple relational tasks reliably produces convergent world representations, but lurking divergent tasks can catastrophically harm new entity integration via fine-tuning.

---

### Meta-Learning-Assisted Constraint Relaxation for Constrained Black-Box Optimization

Authors: Sijie Ma, Zeyuan Ma, Yue-Jiao Gong, Ran Cheng
Published: 2026-01-31
Categories: cs.NE, cs.LG
arXiv: https://arxiv.org/abs/2602.00532v2

Constraint handling is central to constrained black-box optimization (BBO), where objective improvement and feasibility restoration often provide conflicting search signals. Existing $ε$-relaxation methods are simple and effective, but their relaxation schedules are usually fixed or manually designed for a limited range of problems. To address this limitation, this letter proposes MeCO, a meta-learning-assisted optimizer that learns an adaptive $ε$-relaxation policy for constrained BBO. MeCO couples a SHADE optimizer with a Double Deep Q-Network controller. At each optimization step, the controller observes compact population and constraint features and selects a scalar action, which is decoded into a relaxation vector for the candidate comparison rule. The policy is trained across constrained BBO instances and then deployed on held-out problems without problem-specific tuning. Experiments on the CEC2017 constrained benchmark, 16 UAV path-planning tasks and eight real-world engineering problems provide evidence that MeCO transfers across held-out benchmark functions, higher dimensions, and an application-domain setting. Ablation and behavior analyses further clarify the roles of constraint-related state features, action scaling, reward shaping, and meta-training.

---

### Enhancing Open-Vocabulary Object Detection through Multi-Level Fine-Grained Visual-Language Alignment

Authors: Tianyi Zhang, Antoine Simoulin, Kai Li, Sana Lakdawala, Shiqing Yu, Arpit Mittal, Hongyu Fu, Yu Lin
Published: 2026-01-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00531v1

Traditional object detection systems are typically constrained to predefined categories, limiting their applicability in dynamic environments. In contrast, open-vocabulary object detection (OVD) enables the identification of objects from novel classes not present in the training set. Recent advances in visual-language modeling have led to significant progress of OVD. However, prior works face challenges in either adapting the single-scale image backbone from CLIP to the detection framework or ensuring robust visual-language alignment. We propose Visual-Language Detection (VLDet), a novel framework that revamps feature pyramid for fine-grained visual-language alignment, leading to improved OVD performance. With the VL-PUB module, VLDet effectively exploits the visual-language knowledge from CLIP and adapts the backbone for object detection through feature pyramid. In addition, we introduce the SigRPN block, which incorporates a sigmoid-based anchor-text contrastive alignment loss to improve detection of novel categories. Through extensive experiments, our approach achieves 58.7 AP for novel classes on COCO2017 and 24.8 AP on LVIS, surpassing all state-of-the-art methods and achieving significant improvements of 27.6% and 6.9%, respectively. Furthermore, VLDet also demonstrates superior zero-shot performance on closed-set object detection.

---

### How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use

Authors: Minhua Lin, Enyan Dai, Hui Liu, Xianfeng Tang, Yuliang Yan, Zhenwei Dai, Jingying Zeng, Zhiwei Zhang, Fali Wang, Hongcheng Gao, Chen Luo, Xiang Zhang et al.
Published: 2026-01-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.00528v1

As Large Language Models (LLMs) are increasingly applied in high-stakes domains, their ability to reason strategically under uncertainty becomes critical. Poker provides a rigorous testbed, requiring not only strong actions but also principled, game-theoretic reasoning. In this paper, we conduct a systematic study of LLMs in multiple realistic poker tasks, evaluating both gameplay outcomes and reasoning traces. Our analysis reveals LLMs fail to compete against traditional algorithms and identifies three recurring flaws: reliance on heuristics, factual misunderstandings, and a "knowing-doing" gap where actions diverge from reasoning. An initial attempt with behavior cloning and step-level reinforcement learning improves reasoning style but remains insufficient for accurate game-theoretic play. Motivated by these limitations, we propose ToolPoker, a tool-integrated reasoning framework that combines external solvers for GTO-consistent actions with more precise professional-style explanations. Experiments demonstrate that ToolPoker achieves state-of-the-art gameplay while producing reasoning traces that closely reflect game-theoretic principles.

---

### Physiology as Language: Translating Respiration to Sleep EEG

Authors: Kaiwen Zha, Chao Li, Hao He, Peng Cao, Tianhong Li, Ali Mirzazadeh, Ellen Zhang, Jong Woo Lee, Yoon Kim, Dina Katabi
Published: 2026-01-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.00526v1

This paper introduces a novel cross-physiology translation task: synthesizing sleep electroencephalography (EEG) from respiration signals. To address the significant complexity gap between the two modalities, we propose a waveform-conditional generative framework that preserves fine-grained respiratory dynamics while constraining the EEG target space through discrete tokenization. Trained on over 28,000 individuals, our model achieves a 7% Mean Absolute Error in EEG spectrogram reconstruction. Beyond reconstruction, the synthesized EEG supports downstream tasks with performance comparable to ground truth EEG on age estimation (MAE 5.0 vs. 5.1 years), sex detection (AUROC 0.81 vs. 0.82), and sleep staging (Accuracy 0.84 vs. 0.88), significantly outperforming baselines trained directly on breathing. Finally, we demonstrate that the framework generalizes to contactless sensing by synthesizing EEG from wireless radio-frequency reflections, highlighting the feasibility of remote, non-contact neurological assessment during sleep.

---

### SAGE: Accelerating Vision-Language Models via Entropy-Guided Adaptive Speculative Decoding

Authors: Yujia Tong, Tian Zhang, Yunyang Wan, Kaiwei Lin, Jingling Yuan, Chuang Hu
Published: 2026-01-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00523v1

Speculative decoding has emerged as a promising approach to accelerate inference in vision-language models (VLMs) by enabling parallel verification of multiple draft tokens. However, existing methods rely on static tree structures that remain fixed throughout the decoding process, failing to adapt to the varying prediction difficulty across generation steps. This leads to suboptimal acceptance lengths and limited speedup. In this paper, we propose SAGE, a novel framework that dynamically adjusts the speculation tree structure based on real-time prediction uncertainty. Our key insight is that output entropy serves as a natural confidence indicator with strong temporal correlation across decoding steps. SAGE constructs deeper-narrower trees for high-confidence predictions to maximize speculation depth, and shallower-wider trees for uncertain predictions to diversify exploration. SAGE improves acceptance lengths and achieves faster acceleration compared to static tree baselines. Experiments on multiple benchmarks demonstrate the effectiveness of SAGE: without any loss in output quality, it delivers up to $3.36\times$ decoding speedup for LLaVA-OneVision-72B and $3.18\times$ for Qwen2.5-VL-72B.

---

### MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrieval

Authors: Chaoran Xu, Chengkan Lv, Qiyu Chen, Feng Zhang, Zhengtao Zhang
Published: 2026-01-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00522v1

Zero-shot anomaly detection (ZSAD) often leverages pretrained vision or vision-language models, but many existing methods use prompt learning or complex modeling to fit the data distribution, resulting in high training or inference cost and limited cross-domain stability. To address these limitations, we propose Memory-Retrieval Anomaly Detection method (MRAD), a unified framework that replaces parametric fitting with a direct memory retrieval. The train-free base model, MRAD-TF, freezes the CLIP image encoder and constructs a two-level memory bank (image-level and pixel-level) from auxiliary data, where feature-label pairs are explicitly stored as keys and values. During inference, anomaly scores are obtained directly by similarity retrieval over the memory bank. Based on the MRAD-TF, we further propose two lightweight variants as enhancements: (i) MRAD-FT fine-tunes the retrieval metric with two linear layers to enhance the discriminability between normal and anomaly; (ii) MRAD-CLIP injects the normal and anomalous region priors from the MRAD-FT as dynamic biases into CLIP's learnable text prompts, strengthening generalization to unseen categories. Across 16 industrial and medical datasets, the MRAD framework consistently demonstrates superior performance in anomaly classification and segmentation, under both train-free and training-based settings. Our work shows that fully leveraging the empirical distribution of raw data, rather than relying only on model fitting, can achieve stronger anomaly detection performance. The code will be publicly released at https://github.com/CROVO1026/MRAD.

---

### Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory

Authors: Junhyuk Choi, Sohhyung Park, Chanhee Cho, Hyeonchu Park, Bugeun Kim
Published: 2026-01-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.00521v2

While LLM-as-a-Judge is widely used in automated evaluation, existing validation practices primarily operate at the level of observed outputs, offering limited insight into whether LLM judges themselves function as stable and reliable measurement instruments. To address this limitation, we introduce a two-phase diagnostic framework for assessing reliability of LLM-as-a-Judge, grounded in Item Response Theory (IRT). The framework adopts Graded Response Model (GRM) of IRT and formalizes reliability along two complementary dimensions: (1) intrinsic consistency, defined as the stability of measurement behavior under prompt variations, and (2) human alignment, capturing correspondence with human quality assessments. We empirically examine diverse LLM judges with this framework, and show that leveraging IRT-GRM yields interpretable signals for diagnosing judgments systematically. These signals provide practical guidance for verifying reliablity of LLM-as-a-Judge and identifying potential causes of unreliability.

---

### NEST: Nested Event Stream Transformer for Sequences of Multisets

Authors: Minghui Sun, Haoyu Gong, Xingyu You, Jillian Hurst, Benjamin Goldstein, Matthew Engelhard
Published: 2026-01-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00520v3

Event stream data often exhibit hierarchical structure in which multiple events co-occur, resulting in a sequence of multisets (i.e., bags of events). In electronic health records (EHRs), for example, medical events are grouped into a sequence of clinical encounters with well-defined temporal structure, but the order and timing of events within each encounter may be unknown or unreliable. Most existing foundation models (FMs) for event stream data flatten this hierarchy into a one-dimensional sequence, leading to (i) computational inefficiency associated with dense attention and learning spurious within-set relationships, and (ii) lower-quality set-level representations from heuristic post-training pooling for downstream tasks. Here, we show that preserving the original hierarchy in the FM architecture provides a useful inductive bias that improves both computational efficiency and representation quality. We then introduce Nested Event Stream Transformer (NEST), a FM for event streams comprised of sequences of multisets. Building on this architecture, we formulate Masked Set Modeling (MSM), an efficient paradigm that promotes improved set-level representation learning. Experiments on real-world multiset sequence data show that NEST captures real-world dynamics while improving both pretraining efficiency and downstream performance.

---

### SPARK: Stochastic Propagation via Affinity-guided Random walK for training-free unsupervised segmentation

Authors: Kunal Mahatha, Jose Dolz, Christian Desrosiers
Published: 2026-01-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00516v1

We argue that existing training-free segmentation methods rely on an implicit and limiting assumption, that segmentation is a spectral graph partitioning problem over diffusion-derived affinities. Such approaches, based on global graph partitioning and eigenvector-based formulations of affinity matrices, suffer from several fundamental drawbacks, they require pre-selecting the number of clusters, induce boundary oversmoothing due to spectral relaxation, and remain highly sensitive to noisy or multi-modal affinity distributions. Moreover, many prior works neglect the importance of local neighborhood structure, which plays a crucial role in stabilizing affinity propagation and preserving fine-grained contours. To address these limitations, we reformulate training-free segmentation as a stochastic flow equilibrium problem over diffusion-induced affinity graphs, where segmentation emerges from a stochastic propagation process that integrates global diffusion attention with local neighborhoods extracted from stable diffusion, yielding a sparse yet expressive affinity structure. Building on this formulation, we introduce a Markov propagation scheme that performs random-walk-based label diffusion with an adaptive pruning strategy that suppresses unreliable transitions while reinforcing confident affinity paths. Experiments across seven widely used semantic segmentation benchmarks demonstrate that our method achieves state-of-the-art zero-shot performance, producing sharper boundaries, more coherent regions, and significantly more stable masks compared to prior spectral-clustering-based approaches.

---