# Research Papers — 2026-02 · bundle page 203 of 210 > Full-text markdown of papers #10101–10150 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/203 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/202.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/204.md) ### A Practical Tensor-Network Compression Pipeline for Production-Scale Large Language Models Authors: Sergii Kozyrev, Davyd Maiboroda Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01613v1 Large language models are limited in deployment by GPU memory and inference latency. We present Minima, a production compression pipeline that learns where and how to structurally compress a Transformer and turns that compression into real serving gains. Minima trains a lightweight convolutional predictor to estimate layer- and patch-level sensitivity, applies a mixture of Tucker, tensor-train, and tensor-ring decompositions to low-sensitivity regions, performs a short healing fine-tune, and executes the resulting operators with custom Triton and CUDA kernels. The reduced memory footprint enables speculative decoding with a small draft model and a larger verifier. On Qwen3-32B at an 8k-token context window, Minima reduces peak VRAM from 64 GiB to 40 GiB. For a single active request, throughput increases from 40 tokens per second (baseline) to 50 tokens per second (Minima) and 75 tokens per second (Minima with speculative decoding). Under 50 parallel requests, throughput is 34, 44, and 53 tokens per second respectively, showing that Minima remains effective under high concurrency even when speculative decoding gains compress. We position Minima relative to recent tensor-network, low-rank plus quantization, and cross-layer sharing methods, and argue that it is a practical step toward more aggressive structural compression via shared tensor backbones with tiny per-layer adapters. --- ### What Do Agents Learn from Trajectory-SFT: Semantics or Interfaces? Authors: Weizheng Gu, Chengze Li, Zhuohao Yu, Mengyuan Sun, Zhibang Yang, Wei Wang, Hongrui Jia, Shikun Zhang, Wei Ye Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01611v1 Large language models are increasingly evaluated as interactive agents, yet standard agent benchmarks conflate two qualitatively distinct sources of success: semantic tool-use and interface-specific interaction pattern memorization. Because both mechanisms can yield identical task success on the original interface, benchmark scores alone are not identifiable evidence of environment-invariant capability. We propose PIPE, a protocol-level evaluation augmentation for diagnosing interface reliance by minimally rewriting environment interfaces while preserving task semantics and execution behavior. Across 16 environments from AgentBench and AgentGym and a range of open-source and API-based agents, PIPE reveals that trajectory-SFT substantially amplifies interface shortcutting: trained agents degrade sharply under minimal interface rewrites, while non-trajectory-trained models remain largely stable. We further introduce Interface Reliance (IR), a counterbalanced alias-based metric that quantifies preference for training-time interfaces, and show that interface shortcutting exhibits environment-dependent, non-monotonic training dynamics that remain invisible under standard evaluation. Our code is available at https://anonymous.4open.science/r/What-Do-Agents-Learn-from-Trajectory-SFT-Semantics-or-Interfaces--0831/. --- ### ToPT: Task-Oriented Prompt Tuning for Urban Region Representation Learning Authors: Zitao Guo, Changyang Jiang, Tianhong Zhao, Jinzhou Cao, Genan Dai, Bowen Zhang Published: 2026-02-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.01610v1 Learning effective region embeddings from heterogeneous urban data underpins key urban computing tasks (e.g., crime prediction, resource allocation). However, prevailing two-stage methods yield task-agnostic representations, decoupling them from downstream objectives. Recent prompt-based approaches attempt to fix this but introduce two challenges: they often lack explicit spatial priors, causing spatially incoherent inter-region modeling, and they lack robust mechanisms for explicit task-semantic alignment. We propose ToPT, a two-stage framework that delivers spatially consistent fusion and explicit task alignment. ToPT consists of two modules: spatial-aware region embedding learning (SREL) and task-aware prompting for region embeddings (Prompt4RE). SREL employs a Graphormer-based fusion module that injects spatial priors-distance and regional centrality-as learnable attention biases to capture coherent, interpretable inter-region interactions. Prompt4RE performs task-oriented prompting: a frozen multimodal large language model (MLLM) processes task-specific templates to obtain semantic vectors, which are aligned with region embeddings via multi-head cross-attention for stable task conditioning. Experiments across multiple tasks and cities show state-of-the-art performance, with improvements of up to 64.2\%, validating the necessity and complementarity of spatial priors and prompt-region alignment. The code is available at https://github.com/townSeven/Prompt4RE.git. --- ### Token Pruning for In-Context Generation in Diffusion Transformers Authors: Junqing Lin, Xingyu Zheng, Pei Cheng, Bin Fu, Jingwei Sun, Guangzhong Sun Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01609v1 In-context generation significantly enhances Diffusion Transformers (DiTs) by enabling controllable image-to-image generation through reference examples. However, the resulting input concatenation drastically increases sequence length, creating a substantial computational bottleneck. Existing token reduction techniques, primarily tailored for text-to-image synthesis, fall short in this paradigm as they apply uniform reduction strategies, overlooking the inherent role asymmetry between reference contexts and target latents across spatial, temporal, and functional dimensions. To bridge this gap, we introduce ToPi, a training-free token pruning framework tailored for in-context generation in DiTs. Specifically, ToPi utilizes offline calibration-driven sensitivity analysis to identify pivotal attention layers, serving as a robust proxy for redundancy estimation. Leveraging these layers, we derive a novel influence metric to quantify the contribution of each context token for selective pruning, coupled with a temporal update strategy that adapts to the evolving diffusion trajectory. Empirical evaluations demonstrate that ToPi can achieve over 30\% speedup in inference while maintaining structural fidelity and visual consistency across complex image generation tasks. --- ### Reasoning with Autoregressive-Diffusion Collaborative Thoughts Authors: Mu Yuan, Liekang Zeng, Guoliang Xing, Lan Zhang, Yunhao Liu Published: 2026-02-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.01608v1 Autoregressive and diffusion models represent two complementary generative paradigms. Autoregressive models excel at sequential planning and constraint composition, yet struggle with tasks that require explicit spatial or physical grounding. Diffusion models, in contrast, capture rich spatial structure through high-dimensional generation, but lack the stepwise logical control needed to satisfy complex, multi-stage constraints or to reliably identify and correct errors. We introduce Collaborative Thoughts, a unified collaborative framework that enables autoregressive and diffusion models to reason and generate jointly through a closed-loop interaction. In Collaborative Thoughts, autoregressive models perform structured planning and constraint management, diffusion models instantiate these constraints as intermediate visual thoughts, and a vision-based critic module evaluates whether the visual thoughts satisfy the intended structural and physical requirements. This feedback is then used to iteratively refine subsequent planning and generation steps, mitigating error propagation across modalities. Importantly, Collaborative Thoughts uses the same collaborative loop regardless of whether the task is autoregressive question answering or diffusion-based visual generation. Through representative examples, we illustrate how Collaborative Thoughts can improve the reliability of spatial reasoning and the controllability of generation. --- ### Minimax optimal differentially private synthetic data for smooth queries Authors: Rundong Ding, Yiyun He, Yizhe Zhu Published: 2026-02-02 Categories: math.ST, cs.IT, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.01607v3 Differentially private synthetic data enables the sharing and analysis of sensitive datasets while providing rigorous privacy guarantees for individual contributors. A central challenge is to achieve strong utility guarantees for meaningful downstream analysis. Many existing methods ensure uniform accuracy over broad query classes, such as all Lipschitz functions, but this level of generality often leads to suboptimal rates for statistics of practical interest. Since many common data analysis queries exhibit smoothness beyond what worst-case Lipschitz bounds capture, we ask whether exploiting this additional structure can yield improved utility. We study the problem of generating $(\varepsilon,δ)$-differentially private synthetic data from a dataset of size $n$ supported on the hypercube $(-1,1)^d$, with utility guarantees uniformly for all smooth queries having bounded derivatives up to order $k$. We propose a polynomial-time algorithm that achieves a minimax error rate of $O_{k,d}(n^{-\min \{1, \frac{k}{d}\}})$, up to a $\log(n)$ factor. This characterization uncovers a phase transition at $k=d$. Our results generalize the Chebyshev moment matching framework of (Musco et al., 2025; Wang et al., 2016) and strictly improve the error rates for $k$-smooth queries established in \citep{wang2016differentially}. Moreover, we establish the first minimax lower bound for the utility of $(\varepsilon,δ)$-differentially private synthetic data with respect to $k$-smooth queries, extending the Wasserstein lower bound for $\varepsilon$-differential privacy in (Boedihardjo et al., 2024). --- ### Boosting Maximum Entropy Reinforcement Learning via One-Step Flow Matching Authors: Zeqiao Li, Yijing Wang, Haoyu Wang, Zheng Li, Zhiqiang Zuo Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01606v1 Diffusion policies are expressive yet incur high inference latency. Flow Matching (FM) enables one-step generation, but integrating it into Maximum Entropy Reinforcement Learning (MaxEnt RL) is challenging: the optimal policy is an intractable energy-based distribution, and the efficient log-likelihood estimation required to balance exploration and exploitation suffers from severe discretization bias. We propose \textbf{F}low-based \textbf{L}og-likelihood-\textbf{A}ware \textbf{M}aximum \textbf{E}ntropy RL (\textbf{FLAME}), a principled framework that addresses these challenges. First, we derive a Q-Reweighted FM objective that bypasses partition function estimation via importance reweighting. Second, we design a decoupled entropy estimator that rigorously corrects bias, which enables efficient exploration and brings the policy closer to the optimal MaxEnt policy. Third, we integrate the MeanFlow formulation to achieve expressive and efficient one-step control. Empirical results on MuJoCo show that FLAME outperforms Gaussian baselines and matches multi-step diffusion policies with significantly lower inference cost. Code is available at https://github.com/lzqw/FLAME. --- ### Universal Redundancies in Time Series Foundation Models Authors: Anthony Bao, Venkata Hasith Vattikuti, Jeffrey Lai, William Gilpin Published: 2026-02-02 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.01605v2 Time Series Foundation Models (TSFMs) leverage extensive pretraining to accurately predict unseen time series during inference, without the need for task-specific fine-tuning. Through large-scale evaluations on standard benchmarks, we find that leading transformer-based TSFMs exhibit redundant components in their intermediate layers. We introduce a set of tools for mechanistic interpretability of TSFMs, including ablations of specific components and direct logit attribution on the residual stream. Our findings are consistent across several leading TSFMs with diverse architectures, and across a diverse set of real-world and synthetic time-series datasets. We discover that all models in our study are robust to ablations of entire layers. Furthermore, we develop a theoretical framework framing transformers as kernel regressors, motivating a purely intrinsic strategy for ablating heads based on the stable rank of the per-head projection matrices. Using this approach, we uncover the specific heads responsible for degenerate phenomena widely observed in TSFMs, such as parroting of motifs from the context and seasonality bias. Our study sheds light on the universal properties of this emerging class of architectures for continuous-time sequence modeling. --- ### Universal Redundancies in Time Series Foundation Models Authors: Anthony Bao, Venkata Hasith Vattikuti, Jeffrey Lai, William Gilpin Published: 2026-02-02 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.01605v1 Time Series Foundation Models (TSFMs) leverage extensive pretraining to accurately predict unseen time series during inference, without the need for task-specific fine-tuning. Through large-scale evaluations on standard benchmarks, we find that leading transformer-based TSFMs exhibit redundant components in their intermediate layers. We introduce a set of tools for mechanistic interpretability of TSFMs, including ablations of specific components and direct logit attribution on the residual stream. Our findings are consistent across several leading TSFMs with diverse architectures, and across a diverse set of real-world and synthetic time-series datasets. We discover that all models in our study are robust to ablations of entire layers. Furthermore, we develop a theoretical framework framing transformers as kernel regressors, motivating a purely intrinsic strategy for ablating heads based on the stable rank of the per-head projection matrices. Using this approach, we uncover the specific heads responsible for degenerate phenomena widely observed in TSFMs, such as parroting of motifs from the context and seasonality bias. Our study sheds light on the universal properties of this emerging class of architectures for continuous-time sequence modeling. --- ### Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPO Authors: Shokichi Takakura, Akifumi Wachi, Rei Higuchi, Kohei Miyaguchi, Taiji Suzuki Published: 2026-02-02 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.01603v1 Aligning large language models (LLMs) to diverse human preferences is fundamentally challenging since criteria can often conflict with each other. Inference-time alignment methods have recently gained popularity as they allow LLMs to be aligned to multiple criteria via different alignment algorithms at inference time. However, inference-time alignment is computationally expensive since it often requires multiple forward passes of the base model. In this work, we propose inference-aware meta-alignment (IAMA), a novel approach that enables LLMs to be aligned to multiple criteria with limited computational budget at inference time. IAMA trains a base model such that it can be effectively aligned to multiple tasks via different inference-time alignment algorithms. To solve the non-linear optimization problems involved in IAMA, we propose non-linear GRPO, which provably converges to the optimal solution in the space of probability measures. --- ### Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards Authors: Hieu Trung Nguyen, Bao Nguyen, Wenao Ma, Yuzhi Zhao, Ruifeng She, Viet Anh Nguyen Published: 2026-02-02 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.01601v3 Sampling efficiency is a key bottleneck in reinforcement learning with verifiable rewards. Existing group-based policy optimization methods, such as GRPO, allocate a fixed number of rollouts for all training prompts. This uniform allocation implicitly treats all prompts as equally informative, and could lead to inefficient computational budget usage and impede training progress. We introduce VIP, a Variance-Informed Predictive allocation strategy that allocates a given rollout budget to the prompts in the incumbent batch to minimize the expected gradient variance of the policy update. At each iteration, VIP uses a lightweight Gaussian process model to predict per-prompt success probabilities based on recent rollouts. These probability predictions are translated into variance estimates, which are then fed into a convex optimization problem to determine the optimal rollout allocations under a hard compute budget constraint. Empirical results show that VIP consistently improves sampling efficiency and achieves higher performance than uniform or heuristic allocation strategies in multiple benchmarks. --- ### Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs Authors: Yen-Shan Chen, Zhi Rui Tam, Cheng-Kuang Wu, Yun-Nung Chen Published: 2026-02-02 Categories: cs.CR, cs.CL, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2602.01600v1 Current evaluations of LLM safety predominantly rely on severity-based taxonomies to assess the harmfulness of malicious queries. We argue that this formulation requires re-examination as it assumes uniform risk across all malicious queries, neglecting Execution Likelihood--the conditional probability of a threat being realized given the model's response. In this work, we introduce Expected Harm, a metric that weights the severity of a jailbreak by its execution likelihood, modeled as a function of execution cost. Through empirical analysis of state-of-the-art models, we reveal a systematic Inverse Risk Calibration: models disproportionately exhibit stronger refusal behaviors for low-likelihood (high-cost) threats while remaining vulnerable to high-likelihood (low-cost) queries. We demonstrate that this miscalibration creates a structural vulnerability: by exploiting this property, we increase the attack success rate of existing jailbreaks by up to $2\times$. Finally, we trace the root cause of this failure using linear probing, which reveals that while models encode severity in their latent space to drive refusal decisions, they possess no distinguishable internal representation of execution cost, making them "blind" to this critical dimension of risk. --- ### The Multiple Ticket Hypothesis: Random Sparse Subnetworks Suffice for RLVR Authors: Israel Adewuyi, Solomon Okibe, Vladmir Ivanov Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01599v1 The Lottery Ticket Hypothesis demonstrated that sparse subnetworks can match full-model performance, suggesting parameter redundancy. Meanwhile, in Reinforcement Learning with Verifiable Rewards (RLVR), recent work has shown that updates concentrate on a sparse subset of parameters, which further lends evidence to this underlying redundancy. We study the simplest possible way to exploit this redundancy: training only a randomly selected subset of parameters at extreme sparsities. Empirically, we find that training just 1\% of parameters matches or exceeds full-parameter RLVR finetuning across 3 models and 2 task domains. Moreover, different random masks show minimal overlap ($\leq 0.005$ Jaccard similarity) and yet all succeed, suggesting pretrained models contain many viable sparse subnetworks rather than one privileged set. We term this the Multiple Ticket Hypothesis. We explain this phenomenon through the implicit per-step KL constraint in RLVR, which restricts updates to a low-dimensional subspace, enabling arbitrary sparse masks to succeed. --- ### The Art of Socratic Inquiry: A Framework for Proactive Template-Guided Therapeutic Conversation Generation Authors: Mingwen Zhang, Minqiang Yang, Changsheng Ma, Yang Yu, Hui Bai, Chen Xu, Xiangzhen Kong, Bin Hu Published: 2026-02-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.01598v1 Proactive questioning, where therapists deliberately initiate structured, cognition-guiding inquiries, is a cornerstone of cognitive behavioral therapy (CBT). Yet, current psychological large language models (LLMs) remain overwhelmingly reactive, defaulting to empathetic but superficial responses that fail to surface latent beliefs or guide behavioral change. To bridge this gap, we propose the \textbf{Socratic Inquiry Framework (SIF)}, a lightweight, plug-and-play therapeutic intent planner that transforms LLMs from passive listeners into active cognitive guides. SIF decouples \textbf{when to ask} (via Strategy Anchoring) from \textbf{what to ask} (via Template Retrieval), enabling context-aware, theory-grounded questioning without end-to-end retraining. Complementing SIF, we introduce \textbf{Socratic-QA}, a high-quality dataset of strategy-aligned Socratic sequences that provides explicit supervision for proactive reasoning. Experiments show that SIF significantly enhances proactive questioning frequency, conversational depth, and therapeutic alignment, marking a clear shift from reactive comfort to proactive exploration. Our work establishes a new paradigm for psychologically informed LLMs: not just to respond, but to guide. --- ### UV-M3TL: A Unified and Versatile Multimodal Multi-Task Learning Framework for Assistive Driving Perception Authors: Wenzhuo Liu, Qiannan Guo, Zhen Wang, Wenshuo Wang, Lei Yang, Yicheng Qiao, Lening Wang, Zhiwei Li, Chen Lv, Shanghang Zhang, Junqiang Xi, Huaping Liu Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01594v1 Advanced Driver Assistance Systems (ADAS) need to understand human driver behavior while perceiving their navigation context, but jointly learning these heterogeneous tasks would cause inter-task negative transfer and impair system performance. Here, we propose a Unified and Versatile Multimodal Multi-Task Learning (UV-M3TL) framework to simultaneously recognize driver behavior, driver emotion, vehicle behavior, and traffic context, while mitigating inter-task negative transfer. Our framework incorporates two core components: dual-branch spatial channel multimodal embedding (DB-SCME) and adaptive feature-decoupled multi-task loss (AFD-Loss). DB-SCME enhances cross-task knowledge transfer while mitigating task conflicts by employing a dual-branch structure to explicitly model salient task-shared and task-specific features. AFD-Loss improves the stability of joint optimization while guiding the model to learn diverse multi-task representations by introducing an adaptive weighting mechanism based on learning dynamics and feature decoupling constraints. We evaluate our method on the AIDE dataset, and the experimental results demonstrate that UV-M3TL achieves state-of-the-art performance across all four tasks. To further prove the versatility, we evaluate UV-M3TL on additional public multi-task perception benchmarks (BDD100K, CityScapes, NYUD-v2, and PASCAL-Context), where it consistently delivers strong performance across diverse task combinations, attaining state-of-the-art results on most tasks. --- ### Samba+: General and Accurate Salient Object Detection via A More Unified Mamba-based Framework Authors: Wenzhuo Zhao, Keren Fu, Jiahao He, Xiaohong Liu, Qijun Zhao, Guangtao Zhai Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01593v1 Existing salient object detection (SOD) models are generally constrained by the limited receptive fields of convolutional neural networks (CNNs) and quadratic computational complexity of Transformers. Recently, the emerging state-space model, namely Mamba, has shown great potential in balancing global receptive fields and computational efficiency. As a solution, we propose Saliency Mamba (Samba), a pure Mamba-based architecture that flexibly handles various distinct SOD tasks, including RGB/RGB-D/RGB-T SOD, video SOD (VSOD), RGB-D VSOD, and visible-depth-thermal SOD. Specifically, we rethink the scanning strategy of Mamba for SOD, and introduce a saliency-guided Mamba block (SGMB) that features a spatial neighborhood scanning (SNS) algorithm to preserve the spatial continuity of salient regions. A context-aware upsampling (CAU) method is also proposed to promote hierarchical feature alignment and aggregation by modeling contextual dependencies. As one step further, to avoid the "task-specific" problem as in previous SOD solutions, we develop Samba+, which is empowered by training Samba in a multi-task joint manner, leading to a more unified and versatile model. Two crucial components that collaboratively tackle challenges encountered in input of arbitrary modalities and continual adaptation are investigated. Specifically, a hub-and-spoke graph attention (HGA) module facilitates adaptive cross-modal interactive fusion, and a modality-anchored continual learning (MACL) strategy alleviates inter-modal conflicts together with catastrophic forgetting. Extensive experiments demonstrate that Samba individually outperforms existing methods across six SOD tasks on 22 datasets with lower computational cost, whereas Samba+ achieves even superior results on these tasks and datasets by using a single trained versatile model. Additional results further demonstrate the potential of our Samba framework. --- ### Faster and Better Alignment for Flow Matching Models via Step-aware Advantages Authors: Zhixiong Yue, Feiyang Ye, Zixuan Ni, Sheng Shen, Yu Zhang Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01591v2 Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few-step text-to-image generators. However, existing RL-based approaches for flow matching models typically rely on numerous denoising steps, while suffering from sparse and imprecise reward signals that often lead to suboptimal alignment. To address these limitations, we propose Temperature-Annealed Few-step Sampling with Group Relative Policy Optimization (TAFS-GRPO), a novel framework for training flow matching text-to-image models into efficient few-step generators well aligned with human preferences. Our method iteratively injects adaptive time-dependent noise into one-step clean predictions. By repeatedly annealing the model's sampled outputs, it introduces stochasticity into the sampling process while preserving the semantic integrity of each generated image. Moreover, its step-aware advantage integration mechanism combines GRPO with temperature-annealed sampling to eliminate the need for a differentiable reward function and provide dense, step-specific rewards for stable policy optimization. Extensive experiments demonstrate that TAFS-GRPO achieves strong performance in few-step text-to-image generation and significantly improves the alignment of generated images with human preferences. The code and models of this work will be available to facilitate further research. --- ### Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles Authors: Shaohan Wang, Benfeng Xu, Licheng Zhang, Mingxuan Du, Chiwei Zhu, Xiaorui Wang, Zhendong Mao, Yongdong Zhang Published: 2026-02-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.01590v2 Deep Research Agents (DRAs) have demonstrated remarkable capabilities in autonomous information retrieval and report generation, showing great potential to assist humans in complex research tasks. Current evaluation frameworks primarily rely on LLM-generated references or LLM-derived evaluation dimensions. While these approaches offer scalability, they often lack the reliability of expert-verified content and struggle to provide objective, fine-grained assessments of critical dimensions. To bridge this gap, we introduce Wiki Live Challenge (WLC), a live benchmark that leverages the newest Wikipedia Good Articles (GAs) as expert-level references. Wikipedia's strict standards for neutrality, comprehensiveness, and verifiability serve as a great challenge for DRAs, with GAs representing the pinnacle of which. We curate a dataset of 100 recent Good Articles and propose Wiki Eval, a comprehensive evaluation framework comprising a fine-grained evaluation method with 39 criteria for writing quality and rigorous metrics for factual verifiability. Extensive experiments on various DRA systems demonstrate a significant gap between current DRAs and human expert-level Wikipedia articles, validating the effectiveness of WLC in advancing agent research. We release our benchmark at https://github.com/WangShao2000/Wiki_Live_Challenge --- ### Two-chart Beltrami Optimization for Distortion-Controlled Spherical Bijection with Application to Brain Surface Registration Authors: Zhehao Xu, Lok Ming Lui Published: 2026-02-02 Categories: cs.GR, cs.CV, cs.LG, math.AG arXiv: https://arxiv.org/abs/2602.01589v2 Many genus-0 surface mapping tasks such as landmark alignment, feature matching, and image-driven registration, can be reduced (via an initial spherical conformal map) to optimizing a spherical self-homeomorphism with controlled distortion. However, existing works lack efficient mechanisms to control the geometric distortion of the resulting mapping. To resolve this issue, we formulate this as a Beltrami-space optimization problem, where the angle distortion is encoded explicitly by the Beltrami differential and bijectivity can be enforced through the constraint $\|μ\|_{\infty}<1$. To make this practical on the sphere, we introduce the Spherical Beltrami Differential (SBD), a two-chart representation of quasiconformal self-maps of the unit sphere $\mathbb{S}^2$, together with cross-chart consistency conditions that yield a globally bijective spherical deformation (up to conformal automorphisms). Building on the Spectral Beltrami Network, we develop BOOST, a differentiable optimization framework that updates two Beltrami fields to minimize task-driven losses while regularizing distortion and enforcing consistency along the seam. Experiments on large-deformation landmark matching and intensity-based spherical registration demonstrate improved task performance meanwhile maintaining controlled distortion and robust bijective behavior. We also apply the method to cortical surface registration by aligning sulcal landmarks and matching cortical sulcal depth, achieving comparative or better registration performance without sacrificing geometric validity. --- ### Spectral Text Fusion: A Frequency-Aware Approach to Multimodal Time-Series Forecasting Authors: Huu Hiep Nguyen, Minh Hoang Nguyen, Dung Nguyen, Hung Le Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01588v3 Multimodal time series forecasting is crucial in real-world applications, where decisions depend on both numerical data and contextual signals. The core challenge is to effectively combine temporal numerical patterns with the context embedded in other modalities, such as text. While most existing methods align textual features with time-series patterns one step at a time, they neglect the multiscale temporal influences of contextual information such as time-series cycles and dynamic shifts. This mismatch between local alignment and global textual context can be addressed by spectral decomposition, which separates time series into frequency components capturing both short-term changes and long-term trends. In this paper, we propose SpecTF, a simple yet effective framework that integrates the effect of textual data on time series in the frequency domain. Our method extracts textual embeddings, projects them into the frequency domain, and fuses them with the time series' spectral components using a lightweight cross-attention mechanism. This adaptively reweights frequency bands based on textual relevance before mapping the results back to the temporal domain for predictions. Experimental results demonstrate that SpecTF significantly outperforms state-of-the-art models across diverse multi-modal time series datasets while utilizing considerably fewer parameters. Code is available at https://github.com/hiepnh137/SpecTF. --- ### Provable Defense Framework for LLM Jailbreaks via Noise-Augumented Alignment Authors: Zehua Cheng, Jianwei Yang, Wei Dai, Jiahao Sun Published: 2026-02-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.01587v1 Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the statistical stability of an ensemble. We introduce Certified Semantic Smoothing (CSS) via Stratified Randomized Ablation, a technique that partitions inputs into immutable structural prompts and mutable payloads to derive rigorous lo norm guarantees using the Hypergeometric distribution. To resolve performance degradation on sparse contexts, we employ Noise-Augmented Alignment Tuning (NAAT), which transforms the base model into a semantic denoiser. Extensive experiments on Llama-3 show that our method reduces the Attack Success Rate of gradient-based attacks from 84.2% to 1.2% while maintaining 94.1% benign utility, significantly outperforming character-level baselines which degrade utility to 74.3%. This framework provides a deterministic certificate of safety, ensuring that a model remains robust against all adversarial variants within a provable radius. --- ### HandMCM: Multi-modal Point Cloud-based Correspondence State Space Model for 3D Hand Pose Estimation Authors: Wencan Cheng, Gim Hee Lee Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01586v2 3D hand pose estimation that involves accurate estimation of 3D human hand keypoint locations is crucial for many human-computer interaction applications such as augmented reality. However, this task poses significant challenges due to self-occlusion of the hands and occlusions caused by interactions with objects. In this paper, we propose HandMCM to address these challenges. Our HandMCM is a novel method based on the powerful state space model (Mamba). By incorporating modules for local information injection/filtering and correspondence modeling, the proposed correspondence Mamba effectively learns the highly dynamic kinematic topology of keypoints across various occlusion scenarios. Moreover, by integrating multi-modal image features, we enhance the robustness and representational capacity of the input, leading to more accurate hand pose estimation. Empirical evaluations on three benchmark datasets demonstrate that our model significantly outperforms current state-of-the-art methods, particularly in challenging scenarios involving severe occlusions. These results highlight the potential of our approach to advance the accuracy and reliability of 3D hand pose estimation in practical applications. --- ### A Lightweight Sparse Interaction Network for Time Series Forecasting Authors: Xu Zhang, Qitong Wang, Peng Wang, Wei Wang Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01585v1 Recent work shows that linear models can outperform several transformer models in long-term time-series forecasting (TSF). However, instead of explicitly performing temporal interaction through self-attention, linear models implicitly perform it based on stacked MLP structures, which may be insufficient in capturing the complex temporal dependencies and their performance still has potential for improvement. To this end, we propose a Lightweight Sparse Interaction Network (LSINet) for TSF task. Inspired by the sparsity of self-attention, we propose a Multihead Sparse Interaction Mechanism (MSIM). Different from self-attention, MSIM learns the important connections between time steps through sparsity-induced Bernoulli distribution to capture temporal dependencies for TSF. The sparsity is ensured by the proposed self-adaptive regularization loss. Moreover, we observe the shareability of temporal interactions and propose to perform Shared Interaction Learning (SIL) for MSIM to further enhance efficiency and improve convergence. LSINet is a linear model comprising only MLP structures with low overhead and equipped with explicit temporal interaction mechanisms. Extensive experiments on public datasets show that LSINet achieves both higher accuracy and better efficiency than advanced linear models and transformer models in TSF tasks. The code is available at the link https://github.com/Meteor-Stars/LSINet. --- ### On the Fragility of AI-Based Channel Decoders under Small Channel Perturbations Authors: Haoyu Lei, Mohammad Jalali, Chin Wa Lau, Farzan Farnia Published: 2026-02-02 Categories: cs.IT, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.01582v1 Recent advances in deep learning have led to AI-based error correction decoders that report empirical performance improvements over traditional belief-propagation (BP) decoding on AWGN channels. While such gains are promising, a fundamental question remains: where do these improvements come from, and what cost is paid to achieve them? In this work, we study this question through the lens of robustness to distributional shifts at the channel output. We evaluate both input-dependent adversarial perturbations (FGM and projected gradient methods under $\ell_2$ constraints) and universal adversarial perturbations that apply a single norm-bounded shift to all received vectors. Our results show that recent AI decoders, including ECCT and CrossMPT, could suffer significant performance degradation under such perturbations, despite superior nominal performance under i.i.d. AWGN. Moreover, adversarial perturbations transfer relatively strongly between AI decoders but weakly to BP-based decoders, and universal perturbations are substantially more harmful than random perturbations of equal norm. These numerical findings suggest a potential robustness cost and higher sensitivity to channel distribution underlying recent AI decoding gains. --- ### Nearly Optimal Active Preference Learning and Its Application to LLM Alignment Authors: Yao Zhao, Kwang-Sung Jun Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01581v1 Aligning large language models (LLMs) depends on high-quality datasets of human preference labels, which are costly to collect. Although active learning has been studied to improve sample efficiency relative to passive collection, many existing approaches adopt classical experimental design criteria such as G- or D-optimality. These objectives are not tailored to the structure of preference learning, leaving open the design of problem-specific algorithms. In this work, we identify a simple intuition specific to preference learning that calls into question the suitability of these existing design objectives. Motivated by this insight, we propose two active learning algorithms. The first provides the first instance-dependent label complexity guarantee for this setting, and the second is a simple, practical greedy method. We evaluate our algorithm on real-world preference datasets and observe improved sample efficiency compared to existing methods. --- ### DrawSim-PD: Simulating Student Science Drawings to Support NGSS-Aligned Teacher Diagnostic Reasoning Authors: Arijit Chakma, Peng He, Honglu Liu, Zeyuan Wang, Tingting Li, Tiffany D. Do, Feng Liu Published: 2026-02-02 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2602.01578v1 Developing expertise in diagnostic reasoning requires practice with diverse student artifacts, yet privacy regulations prohibit sharing authentic student work for teacher professional development (PD) at scale. We present DrawSim-PD, the first generative framework that simulates NGSS-aligned, student-like science drawings exhibiting controllable pedagogical imperfections to support teacher training. Central to our approach are apability profiles--structured cognitive states encoding what students at each performance level can and cannot yet demonstrate. These profiles ensure cross-modal coherence across generated outputs: (i) a student-like drawing, (ii) a first-person reasoning narrative, and (iii) a teacher-facing diagnostic concept map. Using 100 curated NGSS topics spanning K-12, we construct a corpus of 10,000 systematically structured artifacts. Through an expert-based feasibility evaluation, K--12 science educators verified the artifacts' alignment with NGSS expectations (>84% positive on core items) and utility for interpreting student thinking, while identifying refinement opportunities for grade-band extremes. We release this open infrastructure to overcome data scarcity barriers in visual assessment research. --- ### Visible Light Positioning With Lamé Curve LEDs: A Generic Approach for Camera Pose Estimation Authors: Wenxuan Pan, Yang Yang, Dong Wei, Zhiyu Zhu, Jintao Wang, Huan Wu, Yao Nie Published: 2026-02-02 Categories: eess.SP, cs.CV arXiv: https://arxiv.org/abs/2602.01577v3 Camera-based visible light positioning (VLP) is a promising technique for accurate and low-cost indoor camera pose estimation (CPE). To reduce the number of required light-emitting diodes (LEDs), advanced methods commonly exploit LED shape features for positioning. Although interesting, they are typically restricted to a single LED geometry, leading to failure in heterogeneous LED-shape scenarios. To address this challenge, this paper investigates Lamé curves as a unified representation of common LED shapes and proposes a generic VLP algorithm using Lamé curve-shaped LEDs, termed LC-VLP. In the considered system, multiple ceiling-mounted Lamé curve-shaped LEDs periodically broadcast their curve parameters via visible light communication, which are captured by a camera-equipped receiver. Based on the received LED images and curve parameters, the receiver can estimate the camera pose using LC-VLP. Specifically, an LED database is constructed offline to store the curve parameters, while online positioning is formulated as a nonlinear least-squares problem and solved iteratively. To provide a reliable initialization, a correspondence-free perspective-n-points (FreePnP) algorithm is further developed, enabling approximate CPE without any pre-calibrated reference points. The performance of LC-VLP is verified by both simulations and experiments. Simulations show that LC-VLP outperforms state-of-the-art methods in both circular- and rectangular-LED scenarios. Compared to a perspective arcs algorithm, LC-VLP can achieve reductions of both over 30% in average position and rotation errors. Experiments further show that LC-VLP can achieve an average position accuracy of less than 4 cm. --- ### Generative Visual Code Mobile World Models Authors: Woosung Koh, Sungjun Han, Segyu Lee, Se-Young Yun, Jamin Shin Published: 2026-02-02 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.01576v2 Mobile Graphical User Interface (GUI) World Models (WMs) offer a promising path for improving mobile GUI agent performance at train- and inference-time. However, current approaches face a critical trade-off: text-based WMs sacrifice visual fidelity, while the inability of visual WMs in precise text rendering led to their reliance on slow, complex pipelines dependent on numerous external models. We propose a novel paradigm: visual world modeling via renderable code generation, where a single Vision-Language Model (VLM) predicts the next GUI state as executable web code that renders to pixels, rather than generating pixels directly. This combines the strengths of both approaches: VLMs retain their linguistic priors for precise text rendering while their pre-training on structured web code enables high-fidelity visual generation. We introduce gWorld (8B, 32B), the first open-weight visual mobile GUI WMs built on this paradigm, along with a data generation framework (gWorld) that automatically synthesizes code-based training data. In extensive evaluation across 4 in- and 2 out-of-distribution benchmarks, gWorld sets a new pareto frontier in accuracy versus model size, outperforming 8 frontier open-weight models over 50.25x larger. Further analyses show that (1) scaling training data via gWorld yields meaningful gains, (2) each component of our pipeline improves data quality, and (3) stronger world modeling improves downstream mobile GUI policy performance. --- ### SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models Authors: Haobo Wang, Weiqi Luo, Xiaojun Jia, Xiaochun Cao Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01574v1 Large vision-language models (VLMs) are vulnerable to transfer-based adversarial perturbations, enabling attackers to optimize on surrogate models and manipulate black-box VLM outputs. Prior targeted transfer attacks often overfit surrogate-specific embedding space by relying on a single reference and emphasizing final-layer alignment, which underutilizes intermediate semantics and degrades transfer across heterogeneous VLMs. To address this, we propose SGHA-Attack, a Semantic-Guided Hierarchical Alignment framework that adopts multiple target references and enforces intermediate-layer consistency. Concretely, we generate a visually grounded reference pool by sampling a frozen text-to-image model conditioned on the target prompt, and then carefully select the Top-K most semantically relevant anchors under the surrogate to form a weighted mixture for stable optimization guidance. Building on these anchors, SGHA-Attack injects target semantics throughout the feature hierarchy by aligning intermediate visual representations at both global and spatial granularities across multiple depths, and by synchronizing intermediate visual and textual features in a shared latent subspace to provide early cross-modal supervision before the final projection. Extensive experiments on open-source and commercial black-box VLMs show that SGHA-Attack achieves stronger targeted transferability than prior methods and remains robust under preprocessing and purification defenses. --- ### When Is Generalized Bayes Bayesian? A Decision-Theoretic Characterization of Loss-Based Updating Authors: Kenichiro McAlinn, Kōsaku Takanashi Published: 2026-02-02 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2602.01573v1 Loss-based updating, including generalized Bayes, Gibbs, and quasi-posteriors, replaces likelihoods by a user-chosen loss and produces a posterior-like distribution via exponential tilt. We give a decision-theoretic characterization that separates \emph{belief posteriors} -- conditional beliefs justified by the foundations of Savage and Anscombe-Aumann under a joint probability mode l-- from \emph{decision posteriors} -- randomized decision rules justified by preferences over decision rules. We make explicit that a loss-based posterior coincides with ordinary Bayes if and only if the loss is, up to scale and a data-only term, negative log-likelihood. We then show that generalized marginal likelihood is not evidence for decision posteriors, and Bayes factors are not well-defined without additional structure. In the decision posterior regime, non-degenerate posteriors require nonlinear preferences over decision rules. Under sequential coherence and separability, these lead to an entropy-penalized variational representation yielding generalized Bayes as the optimal rule. --- ### LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden States Authors: Yeqin Zhang, Yunfei Wang, Jiaxuan Chen, Ke Qin, Yizheng Zhao, Cam-Tu Nguyen Published: 2026-02-02 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2602.01572v2 Sentence representations are foundational to many Natural Language Processing (NLP) applications. While recent methods leverage Large Language Models (LLMs) to derive sentence representations, most rely on final-layer hidden states, which are optimized for next-token prediction and thus often fail to capture global, sentence-level semantics. This paper introduces a novel perspective, demonstrating that attention value vectors capture sentence semantics more effectively than hidden states. We propose Value Aggregation (VA), a simple method that pools token values across multiple layers and token indices. In a training-free setting, VA outperforms other LLM-based embeddings, even matches or surpasses the ensemble-based MetaEOL. Furthermore, we demonstrate that when paired with suitable prompts, the layer attention outputs can be interpreted as aligned weighted value vectors. Specifically, the attention scores of the last token function as the weights, while the output projection matrix ($W_O$) aligns these weighted value vectors with the common space of the LLM residual stream. This refined method, termed Aligned Weighted VA (AlignedWVA), achieves state-of-the-art performance among training-free LLM-based embeddings, outperforming the high-cost MetaEOL by a substantial margin. Finally, we highlight the potential of obtaining strong LLM embedding models through fine-tuning Value Aggregation. --- ### One-Step Diffusion for Perceptual Image Compression Authors: Yiwen Jia, Hao Wei, Yanhui Zhou, Chenyang Ge Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01570v1 Diffusion-based image compression methods have achieved notable progress, delivering high perceptual quality at low bitrates. However, their practical deployment is hindered by significant inference latency and heavy computational overhead, primarily due to the large number of denoising steps required during decoding. To address this problem, we propose a diffusion-based image compression method that requires only a single-step diffusion process, significantly improving inference speed. To enhance the perceptual quality of reconstructed images, we introduce a discriminator that operates on compact feature representations instead of raw pixels, leveraging the fact that features better capture high-level texture and structural details. Experimental results show that our method delivers comparable compression performance while offering a 46$\times$ faster inference speed compared to recent diffusion-based approaches. The source code and models are available at https://github.com/cheesejiang/OSDiff. --- ### DREAMS: A Social Exchange Theory-Informed Modeling of Misinformation Engagement on Social Media Authors: Lin Tian, Marian-Andrei Rizoiu Published: 2026-02-02 Categories: cs.SI, cs.AI arXiv: https://arxiv.org/abs/2602.01567v1 Social media engagement prediction is a central challenge in computational social science, particularly for understanding how users interact with misinformation. Existing approaches often treat engagement as a homogeneous time-series signal, overlooking the heterogeneous social mechanisms and platform designs that shape how misinformation spreads. In this work, we ask: ``Can neural architectures discover social exchange principles from behavioral data alone?'' We introduce \textsc{Dreams} (\underline{D}isentangled \underline{R}epresentations and \underline{E}pisodic \underline{A}daptive \underline{M}odeling for \underline{S}ocial media misinformation engagements), a social exchange theory-guided framework that models misinformation engagement as a dynamic process of social exchange. Rather than treating engagement as a static outcome, \textsc{Dreams} models it as a sequence-to-sequence adaptation problem, where each action reflects an evolving negotiation between user effort and social reward conditioned by platform context. It integrates adaptive mechanisms to learn how emotional and contextual signals propagate through time and across platforms. On a cross-platform dataset spanning $7$ platforms and 2.37M posts collected between 2021 and 2025, \textsc{Dreams} achieves state-of-the-art performance in predicting misinformation engagements, reaching a mean absolute percentage error of $19.25$\%. This is a $43.6$\% improvement over the strongest baseline. Beyond predictive gains, the model reveals consistent cross-platform patterns that align with social exchange principles, suggesting that integrating behavioral theory can enhance empirical modeling of online misinformation engagement. The source code is available at: https://github.com/ltian678/DREAMS. --- ### FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents Authors: Chiwei Zhu, Benfeng Xu, Mingxuan Du, Shaohan Wang, Xiaorui Wang, Zhendong Mao, Yongdong Zhang Published: 2026-02-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.01566v2 Deep research is emerging as a representative long-horizon task for large language model (LLM) agents. However, long trajectories in deep research often exceed model context limits, compressing token budgets for both evidence collection and report writing, and preventing effective test-time scaling. We introduce FS-Researcher, a file-system-based, dual-agent framework that scales deep research beyond the context window via a persistent workspace. Specifically, a Context Builder agent acts as a librarian which browses the internet, writes structured notes, and archives raw sources into a hierarchical knowledge base that can grow far beyond context length. A Report Writer agent then composes the final report section by section, treating the knowledge base as the source of facts. In this framework, the file system serves as a durable external memory and a shared coordination medium across agents and sessions, enabling iterative refinement beyond the context window. Experiments on two open-ended benchmarks (DeepResearch Bench and DeepConsult) show that FS-Researcher achieves state-of-the-art report quality across different backbone models. Further analyses demonstrate a positive correlation between final report quality and the computation allocated to the Context Builder, validating effective test-time scaling under the file-system paradigm. The code and data are open-sourced at https://github.com/Ignoramus0817/FS-Researcher. --- ### Local exponential stability of mean-field Langevin descent-ascent and associated particle system Authors: Geuntaek Seo, Minseop Shin, Pierre Monmarché, Beomjun Choi Published: 2026-02-02 Categories: cs.LG, math.AP, math.OC, math.PR arXiv: https://arxiv.org/abs/2602.01564v2 We study the mean-field Langevin descent-ascent (MFL-DA), a coupled optimization dynamics on the space of probability measures for entropically regularized two-player zero-sum games, together with its associated interacting particle system. For general nonconvex-nonconcave payoffs, Wang and Chizat (COLT 2024) asked whether the original single-timescale MFL-DA converges to the mixed Nash equilibrium and, if so, at what rate. We prove a local affirmative answer in Wasserstein space: if the initial datum is sufficiently close to the mixed Nash equilibrium, then the mean-field dynamics converges to it exponentially fast at a quantitative rate. We further show that the finite-$N$ particle system inherits this stability up to times exponential in $N$, with an $N$-independent exponential rate modulo a finite-particle error floor. Combined with the recent counterexample of Mourrat and Pillaud-Vivien for MFL-DA, which shows that global convergence cannot hold in general, our theorem completes the positive local counterpart of the Wang-Chizat question: the mixed Nash equilibrium has a robust basin of attraction, stable under both the mean-field flow and its finite-particle approximation. --- ### Multimodal UNcommonsense: From Odd to Ordinary and Ordinary to Odd Authors: Yejin Son, Saejin Kim, Dongjun Min, Younjae Yu Published: 2026-02-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.01561v1 Commonsense reasoning in multimodal contexts remains a foundational challenge in artificial intelligence. We introduce Multimodal UNcommonsense(MUN), a benchmark designed to evaluate models' ability to handle scenarios that deviate from typical visual or contextual expectations. MUN pairs visual scenes with surprising or unlikely outcomes described in natural language, prompting models to either rationalize seemingly odd images using everyday logic or uncover unexpected interpretations in ordinary scenes. To support this task, we propose a retrieval-based in-context learning (R-ICL) framework that transfers reasoning capabilities from larger models to smaller ones without additional training. Leveraging a novel Multimodal Ensemble Retriever (MER), our method identifies semantically relevant exemplars even when image and text pairs are deliberately discordant. Experiments show an average improvement of 8.3% over baseline ICL methods, highlighting the effectiveness of R-ICL in low-frequency, atypical settings. MUN opens new directions for evaluating and improving visual-language models' robustness and adaptability in real-world, culturally diverse, and non-prototypical scenarios. --- ### Argument Rarity-based Originality Assessment for AI-Assisted Writing Authors: Keito Inoshita, Michiaki Omura, Tsukasa Yamanaka, Go Maeda, Kentaro Tsuji Published: 2026-02-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.01560v3 This study proposes Argument Rarity-based Originality Assessment (AROA), a framework for automatically evaluating argumentative originality in student essays. AROA defines originality as rarity within a reference corpus and evaluates it through four complementary components: structural rarity, claim rarity, evidence rarity, and cognitive depth, quantified via density estimation and integrated with quality adjustment. Experiments using 1,375 human essays and 1,000 AI-generated essays on two argumentative topics revealed three key findings. First, a strong negative correlation (r = -0.67) between text quality and claim rarity demonstrates a quality-originality trade-off. Second, while AI essays achieved near-perfect quality scores (Q = 0.998), their claim rarity was approximately one-fifth of human levels (AI: 0.037, human: 0.170), indicating that LLMs can reproduce argumentative structure but not semantic originality. Third, the four components showed low mutual correlations (r = 0.06--0.13 between structural and semantic dimensions), confirming that they capture genuinely independent aspects of originality. These results suggest that writing assessment in the AI era must shift from quality to originality. --- ### Combined Flicker-banding and Moire Removal for Screen-Captured Images Authors: Libo Zhu, Zihan Zhou, Zhiyi Zhou, Yiyang Qu, Weihang Zhang, Keyu Shi, Yifan Fu, Yulun Zhang Published: 2026-02-02 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2602.01559v1 Capturing display screens with mobile devices has become increasingly common, yet the resulting images often suffer from severe degradations caused by the coexistence of moiré patterns and flicker-banding, leading to significant visual quality degradation. Due to the strong coupling of these two artifacts in real imaging processes, existing methods designed for single degradations fail to generalize to such compound scenarios. In this paper, we present the first systematic study on joint removal of moiré patterns and flicker-banding in screen-captured images, and propose a unified restoration framework, named CLEAR. To support this task, we construct a large-scale dataset containing both moiré patterns and flicker-banding, and introduce an ISP-based flicker simulation pipeline to stabilize model training and expand the degradation distribution. Furthermore, we design a frequency-domain decomposition and re-composition module together with a trajectory alignment loss to enhance the modeling of compound artifacts. Extensive experiments demonstrate that the proposed method consistently. outperforms existing image restoration approaches across multiple evaluation metrics, validating its effectiveness in complex real-world scenarios. --- ### How Implicit Bias Accumulates and Propagates in LLM Long-term Memory Authors: Yiming Ma, Lixu Wang, Lionel Z. Wang, Hongkun Yang, Haoming Sun, Xin Xu, Jiaqi Wu, Bin Chen, Wei Dong Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01558v1 Long-term memory mechanisms enable Large Language Models (LLMs) to maintain continuity and personalization across extended interaction lifecycles, but they also introduce new and underexplored risks related to fairness. In this work, we study how implicit bias, defined as subtle statistical prejudice, accumulates and propagates within LLMs equipped with long-term memory. To support systematic analysis, we introduce the Decision-based Implicit Bias (DIB) Benchmark, a large-scale dataset comprising 3,776 decision-making scenarios across nine social domains, designed to quantify implicit bias in long-term decision processes. Using a realistic long-horizon simulation framework, we evaluate six state-of-the-art LLMs integrated with three representative memory architectures on DIB and demonstrate that LLMs' implicit bias does not remain static but intensifies over time and propagates across unrelated domains. We further analyze mitigation strategies and show that a static system-level prompting baseline provides limited and short-lived debiasing effects. To address this limitation, we propose Dynamic Memory Tagging (DMT), an agentic intervention that enforces fairness constraints at memory write time. Extensive experimental results show that DMT substantially reduces bias accumulation and effectively curtails cross-domain bias propagation. --- ### Autonomous Question Formation for Large Language Model-Driven AI Systems Authors: Hong Su Published: 2026-02-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.01556v1 Large language model (LLM)-driven AI systems are increasingly important for autonomous decision-making in dynamic and open environments. However, most existing systems rely on predefined tasks and fixed prompts, limiting their ability to autonomously identify what problems should be solved when environmental conditions change. In this paper, we propose a human-simulation-based framework that enables AI systems to autonomously form questions and set tasks by reasoning over their internal states, environmental observations, and interactions with other AI systems. The proposed method treats question formation as a first-class decision process preceding task selection and execution, and integrates internal-driven, environment-aware, and inter-agent-aware prompting scopes to progressively expand cognitive coverage. In addition, the framework supports learning the question-formation process from experience, allowing the system to improve its adaptability and decision quality over time. xperimental results in a multi-agent simulation environment show that environment-aware prompting significantly reduces no-eat events compared with the internal-driven baseline, and inter-agent-aware prompting further reduces cumulative no-eat events by more than 60% over a 20-day simulation, with statistically significant improvements (p < 0.05). --- ### InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs Authors: Lv Tang, Tianyi Zheng, Bo Li, Xingyu Li Published: 2026-02-02 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.01554v2 Unified multimodal large language models (MLLMs) aim to unify image understanding and image generation within a single framework, where a shared visual tokenizer serves as the sole interface that maps high-dimensional images into a limited token budget for downstream multimodal reasoning and synthesis. However, existing shared-token designs are largely architecture-driven and lack an explicit criterion for what information should be preserved to simultaneously support semantic abstraction and visual detail. In this paper, we adopt a capacity-constrained perspective, viewing the shared tokenizer as a compute-bounded learner whose finite representational budget should prioritize reusable structure over hard-to-exploit high-entropy variations and redundancy. Motivated by this view, we propose \textbf{\textit{InfoTok}}, an information-regularized tokenization mechanism grounded in the Information Bottleneck (IB) principle. InfoTok explicitly controls information flow from images to shared tokens to multimodal outputs by imposing mutual-information (MI) constraints that enforce a principled trade-off between compression and task relevance, while also encouraging cross-modal consistency. Because MI is intractable for high-dimensional visual representations, we instantiate InfoTok with practical, differentiable dependence estimators, including a variational IB formulation and a Hilbert Schmidt Independence Criterion (HSIC) based alternative. Integrated into three representative unified MLLMs without introducing any additional training data, InfoTok consistently improves both image understanding and generation performance. These results support information-regularized visual tokenization as a sound basis for token learning in unified MLLMs. --- ### Plain Transformers are Surprisingly Powerful Link Predictors Authors: Quang Truong, Yu Song, Donald Loveland, Mingxuan Ju, Tong Zhao, Neil Shah, Jiliang Tang Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01553v4 Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies. While Graph Neural Networks (GNNs) are the standard solution, state-of-the-art pipelines often rely on explicit structural heuristics or memory-intensive node embeddings -- approaches that struggle to generalize or scale to massive graphs. Emerging Graph Transformers (GTs) offer a potential alternative but often incur significant overhead due to complex structural encodings, hindering their applications to large-scale link prediction. We challenge these sophisticated paradigms with PENCIL, an encoder-only plain Transformer that replaces hand-crafted priors with attention over sampled local subgraphs, retaining the scalability and hardware efficiency of standard Transformers. Through experimental and theoretical analysis, we show that PENCIL extracts richer structural signals than GNNs, implicitly generalizing a broad class of heuristics and subgraph-based expressivity. Empirically, PENCIL outperforms heuristic-informed GNNs and is far more parameter-efficient than ID-embedding--based alternatives, while remaining competitive across diverse benchmarks -- even without node features. Our results challenge the prevailing reliance on complex engineering techniques, demonstrating that simple design choices are potentially sufficient to achieve the same capabilities. Our code is publicly available at https://github.com/quang-truong/pencil. --- ### Plain Transformers are Surprisingly Powerful Link Predictors Authors: Quang Truong, Yu Song, Donald Loveland, Mingxuan Ju, Tong Zhao, Neil Shah, Jiliang Tang Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01553v3 Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies. While Graph Neural Networks (GNNs) are the standard solution, state-of-the-art pipelines often rely on explicit structural heuristics or memory-intensive node embeddings -- approaches that struggle to generalize or scale to massive graphs. Emerging Graph Transformers (GTs) offer a potential alternative but often incur significant overhead due to complex structural encodings, hindering their applications to large-scale link prediction. We challenge these sophisticated paradigms with PENCIL, an encoder-only plain Transformer that replaces hand-crafted priors with attention over sampled local subgraphs, retaining the scalability and hardware efficiency of standard Transformers. Through experimental and theoretical analysis, we show that PENCIL extracts richer structural signals than GNNs, implicitly generalizing a broad class of heuristics and subgraph-based expressivity. Empirically, PENCIL outperforms heuristic-informed GNNs and is far more parameter-efficient than ID-embedding--based alternatives, while remaining competitive across diverse benchmarks -- even without node features. Our results challenge the prevailing reliance on complex engineering techniques, demonstrating that simple design choices are potentially sufficient to achieve the same capabilities. Our code is publicly available at https://github.com/quang-truong/pencil. --- ### S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research Authors: S1-NexusAgent Team Published: 2026-02-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.01550v2 Modern scientific research relies on large-scale data, complex workflows, and specialized tools, which existing LLMs and tool-based agents struggle to handle due to limitations in long-horizon planning, robust goal maintenance, and continual learning from execution. To address these issues, in this work, we propose S1-NexusAgent, a self-evolving agent framework designed for multidisciplinary scientific research. S1-NexusAgent adopts a hierarchical Plan-and-CodeAct execution paradigm, decoupling global scientific planning from subtask-level tool execution through a dual-loop architecture, thereby enabling stable modeling of complex research workflows. The system natively supports the Model Context Protocol (MCP), integrates up to thousands of cross-disciplinary scientific tools, and achieves efficient orchestration of heterogeneous research tools via intention-aware dynamic tool retrieval and hot-plug mechanisms. To address long-context and large-scale data challenges in scientific settings, S1-NexusAgent introduces object-reference-based sparse context management, which enables sub-task context isolation and intermediate result compression. Building on this, a Critic Agent automatically evaluates complete execution trajectories and distills high-quality research paths into reusable Scientific Skills, forming a closed loop for continuous self-evolution, which is valuable for sustainable and long-horizon scientific research. Experiments on authoritative scientific benchmarks involving long-horizon planning and complex specialized tool orchestration, including biomini-eval (biology), ChemBench (chemistry), and MatSciBench (material science), demonstrate that S1-NexusAgent achieves state-of-the-art performance, validating its effectiveness and generalization capability in complex scientific tasks. --- ### Toward Cognitive Supersensing in Multimodal Large Language Model Authors: Boyi Li, Yifan Shen, Yuanzhe Liu, Yifan Xu, Jiateng Liu, Xinzhuo Li, Zhengyuan Li, Jingyuan Zhu, Yunhan Zhong, Fangzhou Lan, Jianguo Cao, James M. Rehg et al. Published: 2026-02-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.01541v1 Multimodal Large Language Models (MLLMs) have achieved remarkable success in open-vocabulary perceptual tasks, yet their ability to solve complex cognitive problems remains limited, especially when visual details are abstract and require visual memory. Current approaches primarily scale Chain-of-Thought (CoT) reasoning in the text space, even when language alone is insufficient for clear and structured reasoning, and largely neglect visual reasoning mechanisms analogous to the human visuospatial sketchpad and visual imagery. To mitigate this deficiency, we introduce Cognitive Supersensing, a novel training paradigm that endows MLLMs with human-like visual imagery capabilities by integrating a Latent Visual Imagery Prediction (LVIP) head that jointly learns sequences of visual cognitive latent embeddings and aligns them with the answer, thereby forming vision-based internal reasoning chains. We further introduce a reinforcement learning stage that optimizes text reasoning paths based on this grounded visual latent. To evaluate the cognitive capabilities of MLLMs, we present CogSense-Bench, a comprehensive visual question answering (VQA) benchmark assessing five cognitive dimensions. Extensive experiments demonstrate that MLLMs trained with Cognitive Supersensing significantly outperform state-of-the-art baselines on CogSense-Bench and exhibit superior generalization on out-of-domain mathematics and science VQA benchmarks, suggesting that internal visual imagery is potentially key to bridging the gap between perceptual recognition and cognitive understanding. We will open-source the CogSense-Bench and our model weights. --- ### FSCA-Net: Feature-Separated Cross-Attention Network for Robust Multi-Dataset Training Authors: Yuehai Chen Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01540v1 Crowd counting plays a vital role in public safety, traffic regulation, and smart city management. However, despite the impressive progress achieved by CNN- and Transformer-based models, their performance often deteriorates when applied across diverse environments due to severe domain discrepancies. Direct joint training on multiple datasets, which intuitively should enhance generalization, instead results in negative transfer, as shared and domain-specific representations become entangled. To address this challenge, we propose the Feature Separation and Cross-Attention Network FSCA-Net, a unified framework that explicitly disentangles feature representations into domain-invariant and domain-specific components. A novel cross-attention fusion module adaptively models interactions between these components, ensuring effective knowledge transfer while preserving dataset-specific discriminability. Furthermore, a mutual information optimization objective is introduced to maximize consistency among domain-invariant features and minimize redundancy among domain-specific ones, promoting complementary shared-private representations. Extensive experiments on multiple crowd counting benchmarks demonstrate that FSCA-Net effectively mitigates negative transfer and achieves state-of-the-art cross-dataset generalization, providing a robust and scalable solution for real-world crowd analysis. --- ### MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety Authors: Xiaoyu Wen, Zhida He, Han Qi, Ziyu Wan, Zhongtian Ma, Ying Wen, Tianhang Zheng, Xingcheng Xu, Chaochao Lu, Qiaosheng Zhang Published: 2026-02-02 Categories: cs.AI, cs.CL, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2602.01539v2 Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due to their \textbf{reliance on static, pre-collected data distributions}. In this paper, we introduce \textbf{MAGIC}, a novel multi-turn multi-agent reinforcement learning framework that formulates LLM safety alignment as an adversarial asymmetric game. Specifically, an attacker agent learns to iteratively rewrite original queries into deceptive prompts, while a defender agent simultaneously optimizes its policy to recognize and refuse such inputs. This dynamic process triggers a \textbf{co-evolution}, where the attacker's ever-changing strategies continuously uncover long-tail vulnerabilities, driving the defender to generalize to unseen attack patterns. Remarkably, we observe that the attacker, endowed with initial reasoning ability, evolves \textbf{novel, previously unseen combinatorial strategies} through iterative RL training, underscoring our method's substantial potential. Theoretically, we provide insights into a more robust game equilibrium and derive safety guarantees. Extensive experiments validate our framework's effectiveness, demonstrating superior defense success rates without compromising the helpfulness of the model. Our code is available at https://github.com/BattleWen/MAGIC. --- ### Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars Authors: Youliang Zhang, Zhengguang Zhou, Zhentao Yu, Ziyao Huang, Teng Hu, Sen Liang, Guozhen Zhang, Ziqiao Peng, Shunkai Li, Yi Chen, Zixiang Zhou, Yuan Zhou et al. Published: 2026-02-02 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.01538v1 Generating talking avatars is a fundamental task in video generation. Although existing methods can generate full-body talking avatars with simple human motion, extending this task to grounded human-object interaction (GHOI) remains an open challenge, requiring the avatar to perform text-aligned interactions with surrounding objects. This challenge stems from the need for environmental perception and the control-quality dilemma in GHOI generation. To address this, we propose a novel dual-stream framework, InteractAvatar, which decouples perception and planning from video synthesis for grounded human-object interaction. Leveraging detection to enhance environmental perception, we introduce a Perception and Interaction Module (PIM) to generate text-aligned interaction motions. Additionally, an Audio-Interaction Aware Generation Module (AIM) is proposed to synthesize vivid talking avatars performing object interactions. With a specially designed motion-to-video aligner, PIM and AIM share a similar network structure and enable parallel co-generation of motions and plausible videos, effectively mitigating the control-quality dilemma. Finally, we establish a benchmark, GroundedInter, for evaluating GHOI video generation. Extensive experiments and comparisons demonstrate the effectiveness of our method in generating grounded human-object interactions for talking avatars. Project page: https://interactavatar.github.io --- ### UniDWM: Towards a Unified Driving World Model via Multifaceted Representation Learning Authors: Shuai Liu, Siheng Ren, Xiaoyao Zhu, Quanmin Liang, Zefeng Li, Qiang Li, Xin Hu, Kai Huang Published: 2026-02-02 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.01536v1 Achieving reliable and efficient planning in complex driving environments requires a model that can reason over the scene's geometry, appearance, and dynamics. We present UniDWM, a unified driving world model that advances autonomous driving through multifaceted representation learning. UniDWM constructs a structure- and dynamic-aware latent world representation that serves as a physically grounded state space, enabling consistent reasoning across perception, prediction, and planning. Specifically, a joint reconstruction pathway learns to recover the scene's structure, including geometry and visual texture, while a collaborative generation framework leverages a conditional diffusion transformer to forecast future world evolution within the latent space. Furthermore, we show that our UniDWM can be deemed as a variation of VAE, which provides theoretical guidance for the multifaceted representation learning. Extensive experiments demonstrate the effectiveness of UniDWM in trajectory planning, 4D reconstruction and generation, highlighting the potential of multifaceted world representations as a foundation for unified driving intelligence. The code will be publicly available at https://github.com/Say2L/UniDWM. --- ### Rotation-free Online Handwritten Character Recognition Using Linear Recurrent Units Authors: Zhe Ling, Sicheng Yu, Danyu Yang Published: 2026-02-02 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.01533v2 Online handwritten character recognition leverages stroke order and dynamic features, which generally provide higher accuracy and robustness compared with offline recognition. However, in practical applications, rotational deformations can disrupt the spatial layout of strokes, substantially reducing recognition accuracy. Extracting rotation-invariant features therefore remains a challenging open problem. In this work, we employ the Sliding Window Path Signature (SW-PS) to capture local structural features of characters, and introduce the lightweight Linear Recurrent Units (LRU) as the classifier. The LRU combine the fast incremental processing capability of recurrent neural networks (RNN) with the efficient parallel training of state space models (SSM), while reliably modelling dynamic stroke characteristics. We conducted recognition experiments with random rotation angle up to $\pm 180^{\circ}$ on three subsets of the CASIA-OLHWDB1.1 dataset: digits, English upper letters, and Chinese radicals. The accuracies achieved after ensemble learning were $99.62\%$, $96.67\%$, and $94.33\%$, respectively. Experimental results demonstrate that the proposed SW-PS+LRU framework consistently surpasses competing models in both convergence speed and test accuracy. ---