# Research Papers — 2026-01 · bundle page 28 of 189 > Full-text markdown of papers #1351–1400 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/28 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/27.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/29.md) ### Differential Dynamic Causal Nets: Model Construction, Identification and Group Comparisons Authors: Kang You, Gary Green, Jian Zhang Published: 2026-01-29 Categories: q-bio.NC, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2601.21478v1 Pathophysiolpgical modelling of brain systems from microscale to macroscale remains difficult in group comparisons partly because of the infeasibility of modelling the interactions of thousands of neurons at the scales involved. Here, to address the challenge, we present a novel approach to construct differential causal networks directly from electroencephalogram (EEG) data. The proposed network is based on conditionally coupled neuronal circuits which describe the average behaviour of interacting neuron populations that contribute to observed EEG data. In the network, each node represents a parameterised local neural system while directed edges stand for node-wise connections with transmission parameters. The network is hierarchically structured in the sense that node and edge parameters are varying in subjects but follow a mixed-effects model. A novel evolutionary optimisation algorithm for parameter inference in the proposed method is developed using a loss function derived from Chen-Fliess expansions of stochastic differential equations. The method is demonstrated by application to the fitting of coupled Jansen-Rit local models. The performance of the proposed method is evaluated on both synthetic and real EEG data. In the real EEG data analysis, we track changes in the parameters that characterise dynamic causality within brains that demonstrate epileptic activity. We show evidence of network functional disruptions, due to imbalance of excitatory-inhibitory interneurons and altered epileptic brain connectivity, before and during seizure periods. --- ### Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions Authors: Tobias Schmidt, Kai Cui Published: 2026-01-29 Categories: cs.MA, cs.AI, cs.LG, math.OC arXiv: https://arxiv.org/abs/2601.21477v1 Mean-field control (MFC) offers a scalable solution to the curse of dimensionality in multi-agent systems but traditionally hinges on the restrictive assumption of exchangeability via dense, all-to-all interactions. In this work, we bridge the gap to real-world network structures by proposing a rigorous framework for MFC on large sparse graphs. We redefine the system state as a probability measure over decorated rooted neighborhoods, effectively capturing local heterogeneity. Our central contribution is a theoretical foundation for scalable reinforcement learning in this setting. We prove horizon-dependent locality: for finite-horizon problems, an agent's optimal policy at time t depends strictly on its (T-t)-hop neighborhood. This result renders the infinite-dimensional control problem tractable and underpins a novel Dynamic Programming Principle (DPP) on the lifted space of neighborhood distributions. Furthermore, we formally and experimentally justify the use of Graph Neural Networks (GNNs) for actor-critic algorithms in this context. Our framework naturally recovers classical MFC as a degenerate case while enabling efficient, theoretically grounded control on complex sparse topologies. --- ### Thinking Seeds: Leveraging Historical Diversity for Position-Aware RL in LLMs Authors: Lei Yang, Wei Bi, Chenxi Sun, Renren Jin, Deyi Xiong Published: 2026-01-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.21476v2 On-policy reinforcement learning (RL) for language model post-training suffers from a fundamental tension: as training progresses, policy entropy collapses and sampling diversity diminishes, causing the model to ``forget'' its own earlier exploratory capacity. While off-policy data can restore diversity, existing methods mix entire trajectories at the sequence level, introducing severe policy mismatch and training instability. We argue that the core question is not \emph{whether} to use off-policy data, but \emph{where} in the sequence it should appear. Based on this insight, we propose \textbf{Thinking Seeds}, a token-level mix-policy framework that uses the model's own historical checkpoints as off-policy prefixes, providing diverse starting points for reasoning, while the critical continuation is generated on-policy to preserve gradient quality. Through token-level importance ratios, Thinking Seeds effectively leverages historical diversity without compromising training stability. Extensive experiments across models and mathematical reasoning benchmarks demonstrate that Thinking Seeds consistently outperforms standard on-policy training and existing off-policy extensions. Our analysis reveals that the method maintains higher effective entropy, reduces gradient loss from clipping, and expands the explorable solution space, clarifying how position-aware mix-policy modeling improves both exploration and final performance in LLM RL. --- ### Task-free Adaptive Meta Black-box Optimization Authors: Chao Wang, Licheng Jiao, Lingling Li, Jiaxuan Zhao, Guanchun Wang, Fang Liu, Shuyuan Yang Published: 2026-01-29 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.21475v2 Handcrafted optimizers become prohibitively inefficient for complex black-box optimization (BBO) tasks. MetaBBO addresses this challenge by meta-learning to automatically configure optimizers for low-level BBO tasks, thereby eliminating heuristic dependencies. However, existing methods typically require extensive handcrafted training tasks to learn meta-strategies that generalize to target tasks, which poses a critical limitation for realistic applications with unknown task distributions. To overcome the issue, we propose the Adaptive meta Black-box Optimization Model (ABOM), which performs online parameter adaptation using solely optimization data from the target task, obviating the need for predefined task distributions. Unlike conventional metaBBO frameworks that decouple meta-training and optimization phases, ABOM introduces a closed-loop adaptive parameter learning mechanism, where parameterized evolutionary operators continuously self-update by leveraging generated populations during optimization. This paradigm shift enables zero-shot optimization: ABOM achieves competitive performance on synthetic BBO benchmarks and realistic unmanned aerial vehicle path planning problems without any handcrafted training tasks. Visualization studies reveal that parameterized evolutionary operators exhibit statistically significant search patterns, including natural selection and genetic recombination. --- ### ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Management Authors: Zaifeng Pan, Yipeng Shen, Zhengding Hu, Zhuang Wang, Aninda Manocha, Zheng Wang, Zhongkai Yu, Yue Guan, Yufei Ding Published: 2026-01-29 Categories: cs.AI, cs.DC arXiv: https://arxiv.org/abs/2601.21473v1 LLM-based multi-agent simulations are increasingly adopted across application domains, but remain difficult to scale due to GPU memory pressure. Each agent maintains private GPU-resident states, including models, prefix caches, and adapters, which quickly exhaust device memory as the agent count grows. We identify two key properties of these workloads: sparse agent activation and an estimable agent invocation order. Based on an analysis of representative workload classes, we introduce invocation distance, a unified abstraction that estimates the relative order in which agents will issue future LLM requests. Leveraging this abstraction, we present ScaleSim, a memory-efficient LLM serving system for large-scale multi-agent simulations. ScaleSim enables proactive prefetching and priority-based eviction, supports diverse agent-specific memory through a modular interface, and achieves up to 1.74x speedup over SGLang on simulation benchmarks. --- ### Best Arm Identification with LLM Judges and Limited Human Authors: Ruicheng Ao, Hongyu Chen, Siyang Gao, Hanwei Li, David Simchi-Levi Published: 2026-01-29 Categories: cs.LG, math.OC, stat.ML arXiv: https://arxiv.org/abs/2601.21471v1 We study fixed-confidence best-arm identification (BAI) where a cheap but potentially biased proxy (e.g., LLM judge) is available for every sample, while an expensive ground-truth label can only be acquired selectively when using a human for auditing. Unlike classical multi-fidelity BAI, the proxy is biased (arm- and context-dependent) and ground truth is selectively observed. Consequently, standard multi-fidelity methods can mis-select the best arm, and uniform auditing, though accurate, wastes scarce resources and is inefficient. We prove that without bias correction and propensity adjustment, mis-selection probability may not vanish (even with unlimited proxy data). We then develop an estimator for the mean of each arm that combines proxy scores with inverse-propensity-weighted residuals and form anytime-valid confidence sequences for that estimator. Based on the estimator and confidence sequence, we propose an algorithm that adaptively selects and audits arms. The algorithm concentrates audits on unreliable contexts and close arms and we prove that a plug-in Neyman rule achieves near-oracle audit efficiency. Numerical experiments confirm the theoretical guarantees and demonstrate the superior empirical performance of the proposed algorithm. --- ### PPI-SVRG: Unifying Prediction-Powered Inference and Variance Reduction for Semi-Supervised Optimization Authors: Ruicheng Ao, Hongyu Chen, Haoyang Liu, David Simchi-Levi, Will Wei Sun Published: 2026-01-29 Categories: cs.LG, econ.EM, math.OC, stat.ML arXiv: https://arxiv.org/abs/2601.21470v1 We study semi-supervised stochastic optimization when labeled data is scarce but predictions from pre-trained models are available. PPI and SVRG both reduce variance through control variates -- PPI uses predictions, SVRG uses reference gradients. We show they are mathematically equivalent and develop PPI-SVRG, which combines both. Our convergence bound decomposes into the standard SVRG rate plus an error floor from prediction uncertainty. The rate depends only on loss geometry; predictions affect only the neighborhood size. When predictions are perfect, we recover SVRG exactly. When predictions degrade, convergence remains stable but reaches a larger neighborhood. Experiments confirm the theory: PPI-SVRG reduces MSE by 43--52\% under label scarcity on mean estimation benchmarks and improves test accuracy by 2.7--2.9 percentage points on MNIST with only 10\% labeled data. --- ### Adaptive Confidence Gating in Multi-Agent Collaboration for Efficient and Optimized Code Generation Authors: Haoji Zhang, Yuzhe Li, Zhenqiang Liu, Chenyang Liu, Shenyang Zhang, Yi Zhou Published: 2026-01-29 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2601.21469v1 While Large Language Models (LLMs) have catalyzed breakthroughs in automated code generation, Small Language Models (SLMs) often encounter reasoning bottlenecks and failure loops when addressing complex logical requirements. To overcome these challenges, we propose DebateCoder, a multi-agent collaborative framework designed to improve the reasoning ability of SLMs (e.g., Pangu-1B) in resource-constrained environments. DebateCoder uses a structured role-playing protocol with three agents: User Agent (A_UA), Technical Agent (A_TA), and Quality Assurance Agent (A_QA). It also includes an Adaptive Confidence Gating mechanism with a 95% threshold to balance accuracy and inference efficiency. In addition, we introduce a multi-turn deliberation module and a reviewer-guided analytical debugging loop for orthogonal pre-generation debate and post-generation refinement. Experiments on HumanEval and MBPP show that DebateCoder achieves 70.12% Pass@1 on HumanEval, outperforming MapCoder while reducing API overhead by about 35%. These results indicate that collaborative protocols can mitigate limitations of small-parameter models and provide a scalable, efficient approach to high-quality automated software engineering. --- ### MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning Authors: Yaorui Shi, Shugui Liu, Yu Yang, Wenyu Mao, Yuxin Chen, Qi GU, Hui Su, Xunliang Cai, Xiang Wang, An Zhang Published: 2026-01-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.21468v5 Long-horizon agentic reasoning necessitates effectively compressing growing interaction histories into a limited context window. Most existing memory systems serialize history as text, where token-level cost is uniform and scales linearly with length, often spending scarce budget on low-value details. To this end, we introduce MemOCR, a multimodal memory agent that improves long-horizon reasoning under tight context budgets by allocating memory space with adaptive information density through visual layout. Concretely, MemOCR maintains a structured rich-text memory (e.g., headings, highlights) and renders it into an image that the agent consults for memory access, visually prioritizing crucial evidence while aggressively compressing auxiliary details. To ensure robustness across varying memory budgets, we train MemOCR with reinforcement learning under budget-aware objectives that expose the agent to diverse compression levels. Across long-context multi-hop and single-hop question-answering benchmarks, MemOCR outperforms strong text-based baselines and achieves more effective context utilization under extreme budgets. --- ### A block-coordinate descent framework for non-convex composite optimization. Application to sparse precision matrix estimation Authors: Guillaume Lauga Published: 2026-01-29 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2601.21467v1 Block-coordinate descent (BCD) is the method of choice to solve numerous large scale optimization problems, however their theoretical study for non-convex optimization, has received less attention. In this paper, we present a new block-coordinate descent (BCD) framework to tackle non-convex composite optimization problems, ensuring decrease of the objective function and convergence to a solution. This framework is general enough to include variable metric proximal gradient updates, proximal Newton updates, and alternated minimization updates. This generality allows to encompass three versions of the most used solvers in the sparse precision matrix estimation problem, deemed Graphical Lasso: graphical ISTA, Primal GLasso, and QUIC. We demonstrate the value of this new framework on non-convex sparse precision matrix estimation problems, providing convergence guarantees and up to a $100$-fold reduction in the number of iterations required to reach state-of-the-art estimation quality. --- ### Topeax -- An Improved Clustering Topic Model with Density Peak Detection and Lexical-Semantic Term Importance Authors: Márton Kardos Published: 2026-01-29 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.21465v1 Text clustering is today the most popular paradigm for topic modelling, both in academia and industry. Despite clustering topic models' apparent success, we identify a number of issues in Top2Vec and BERTopic, which remain largely unsolved. Firstly, these approaches are unreliable at discovering natural clusters in corpora, due to extreme sensitivity to sample size and hyperparameters, the default values of which result in suboptimal behaviour. Secondly, when estimating term importance, BERTopic ignores the semantic distance of keywords to topic vectors, while Top2Vec ignores word counts in the corpus. This results in, on the one hand, less coherent topics due to the presence of stop words and junk words, and lack of variety and trust on the other. In this paper, I introduce a new approach, \textbf{Topeax}, which discovers the number of clusters from peaks in density estimates, and combines lexical and semantic indices of term importance to gain high-quality topic keywords. Topeax is demonstrated to be better at both cluster recovery and cluster description than Top2Vec and BERTopic, while also exhibiting less erratic behaviour in response to changing sample size and hyperparameters. --- ### Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation Authors: Yuan Sui, Bryan Hooi Published: 2026-01-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.21464v2 Training large language models (LLMs) for non-verifiable tasks, such as creative writing, dialogue, and ethical reasoning, remains challenging due to the absence of ground-truth labels. While LLM-as-Judge approaches offer a scalable alternative to human feedback, they face a fundamental limitation: performance is constrained by the evaluator's own quality. If the judge cannot recognize good solutions, it cannot provide useful training signals, and evaluation biases (e.g., favoring verbosity over quality) remain unaddressed. This motivates meta-evaluation: the ability to evaluate and improve the evaluator itself. We introduce CoNL, a framework that unifies generation, evaluation, and meta-evaluation through multi-agent self-play. Our key insight: critique quality can be measured by whether it helps others improve their solutions. In CoNL, multiple agents sharing the same policy engage in structured conversations to propose, critique, and revise solutions. Critiques that enable solution improvements earn a diagnostic reward, creating explicit supervision for meta-evaluation and enabling joint optimization of generation and judging capabilities through self-play, without external judges or ground truth. Experiments on various benchmarks show that CoNL achieves consistent improvements over self-rewarding baselines while maintaining stable training. --- ### Unifying Speech Editing Detection and Content Localization via Prior-Enhanced Audio LLMs Authors: Jun Xue, Yi Chai, Yanzhen Ren, Jinshen He, Zhiqiang Tang, Zhuolin Yi, Yihuan Huang, Yuankun Xie, Yujie Chen Published: 2026-01-29 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2601.21463v3 Existing speech editing detection (SED) datasets are predominantly constructed using manual splicing or limited editing operations, resulting in restricted diversity and poor coverage of realistic editing scenarios. Meanwhile, current SED methods rely heavily on frame-level supervision to detect observable acoustic anomalies, which fundamentally limits their ability to handle deletion-type edits, where the manipulated content is entirely absent from the signal. To address these challenges, we present a unified framework that bridges speech editing detection and content localization through a generative formulation based on Audio Large Language Models (Audio LLMs). We first introduce AiEdit, https://huggingface.co/datasets/JunXueTech/AiEdit, a large-scale bilingual dataset (approximately 140 hours) that covers addition, deletion, and modification operations using state-of-the-art end-to-end speech editing systems, providing a more realistic benchmark for modern threats. Building upon this, we reformulate SED as a structured text generation task, enabling joint reasoning over edit type identification, and content localization. To enhance the grounding of generative models in acoustic evidence, we propose a prior-enhanced prompting strategy that injects word-level probabilistic cues derived from a frame-level detector. Furthermore, we introduce an acoustic consistency-aware loss that explicitly enforces the separation between normal and anomalous acoustic representations in the latent space. Experimental results demonstrate that the proposed approach consistently outperforms existing methods across both detection and localization tasks. --- ### Partial Feedback Online Learning Authors: Shihao Shao, Cong Fang, Zhouchen Lin, Dacheng Tao Published: 2026-01-29 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2601.21462v3 We study a new learning protocol, termed partial-feedback online learning, where each instance admits a set of acceptable labels, but the learner observes only one acceptable label per round. We highlight that, while classical version space is widely used for online learnability, it does not directly extend to this setting. We address this obstacle by introducing a collection version space, which maintains sets of hypotheses rather than individual hypotheses. Using this tool, we obtain a tight characterization of learnability in the set-realizable regime. In particular, we define the Partial-Feedback Littlestone dimension (PFLdim) and the Partial-Feedback Measure Shattering dimension (PMSdim), and show that they tightly characterize the minimax regret for deterministic and randomized learners, respectively. We further identify a nested inclusion condition under which deterministic and randomized learnability coincide, resolving an open question of Raman et al. (2024b). Finally, given a hypothesis space H, we show that beyond set realizability, the minimax regret can be linear even when |H|=2, highlighting a barrier beyond set realizability. --- ### L$^3$: Large Lookup Layers Authors: Albert Tseng, Christopher De Sa Published: 2026-01-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.21461v3 Modern sparse language models typically achieve sparsity through Mixture-of-Experts (MoE) layers, which dynamically route tokens to dense MLP "experts." However, dynamic hard routing has a number of drawbacks, such as potentially poor hardware efficiency and needing auxiliary losses for stable training. In contrast, the tokenizer embedding table, which is natively sparse, largely avoids these issues by selecting a single embedding per token at the cost of not having contextual information. In this work, we introduce the Large Lookup Layer (L$^3$), which generalizes embedding tables to model decoder layers as a means of further scaling sparsity. L$^3$ layers use static token-based routing to aggregate a set of learned embeddings per token in a context-dependent way, allowing the model to efficiently balance memory and compute by caching information in embeddings. L$^3$ has two main components: (1) a systems-friendly architecture that allows for fast training and CPU-offloaded inference with no overhead, and (2) an information-theoretic embedding allocation algorithm that effectively balances speed and quality. We empirically test L$^3$ by training transformers with up to 2.6B active parameters and find that L$^3$ strongly outperforms both dense models and iso-sparse MoEs in both language modeling and downstream tasks. --- ### HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing Authors: Chengyu Du, Xintao Wang, Aili Chen, Weiyuan Li, Rui Xu, Junteng Liu, Zishan Huang, Rong Tian, Zijun Sun, Yuhao Li, Liheng Feng, Deming Ding et al. Published: 2026-01-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.21459v4 LLM role-playing, i.e., using LLMs to simulate specific personas, has emerged as a key capability in various applications, such as companionship, content creation and digital games. While current models effectively capture character tones and knowledge, simulating the inner thoughts behind their behaviors remains a challenge. Towards cognitive simulation in LLM role-play, previous efforts mainly suffer from two deficiencies: lacking data with high-quality reasoning traces, and lacking reliable reward signals aligned with human preferences. In this paper, we propose HER, a unified framework for cognitive-level persona simulation. HER introduces dual-layer thinking, which distinguishes characters' first-person thinking from LLMs' third-person thinking. To bridge these gaps, we curate reasoning-augmented role-playing data via reverse engineering, and construct human-aligned principles and reward models. Leveraging these resources, we train HER models based on Qwen3-32B via supervised and reinforcement learning. Extensive experiments validate the effectiveness of our approach. Notably, our models significantly outperform the Qwen3-32B baseline, achieving a 30.26 improvement on the CoSER benchmark and a 14.97% gain on the Minimax Role-Play Bench. Our datasets, principles, and models are released to facilitate future research. --- ### Mining Forgery Traces from Reconstruction Error: A Weakly Supervised Framework for Multimodal Deepfake Temporal Localization Authors: Midou Guo, Qilin Yin, Wei Lu, Rui Yang Published: 2026-01-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.21458v2 Modern deepfakes have evolved into localized and intermittent manipulations that require fine-grained temporal localization to mitigate severe digital security risks. The prohibitive cost of frame-level annotation makes weakly supervised methods a practical necessity, which rely only on video-level labels. To this end, we propose Reconstruction-based Temporal Deepfake Localization (RT-DeepLoc), a weakly supervised temporal forgery localization framework that identifies forgeries via reconstruction errors. Our framework uses a Masked Autoencoder (MAE) trained exclusively on authentic data to learn its intrinsic spatiotemporal patterns; this allows the model to produce significant reconstruction discrepancies for forged segments, effectively providing the missing fine-grained cues for accurate localization without demanding dense human annotations. To robustly leverage these indicators, we introduce a novel Asymmetric Intra-video Contrastive Loss (AICL). By focusing on the compactness of authentic features guided by these reconstruction cues, AICL establishes a stable decision boundary that enhances local discrimination while preserving generalization to unseen forgeries by advanced generative models. Extensive experiments on large-scale datasets, including LAV-DF, demonstrate that RT-DeepLoc achieves state-of-the-art performance in weakly-supervised temporal forgery localization. --- ### Questioning the Coverage-Length Metric in Conformal Prediction: When Shorter Intervals Are Not Better Authors: Yizhou Min, Yizhou Lu, Lanqi Li, Zhen Zhang, Jiaye Teng Published: 2026-01-29 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2601.21455v2 Conformal prediction(CP) has become a cornerstone of distribution-free uncertainty quantification, conventionally evaluated by its coverage and interval length. This work critically examines the sufficiency of these standard metrics. We demonstrate that the interval length might be deceptively improved through a counter-intuitive approach termed Prejudicial Trick(PT), while the coverage remains valid. Specifically, for any given test sample, PT probabilistically returns an interval, which is either null or constructed using an adjusted confidence level, thereby preserving marginal coverage. While PT potentially yields a deceptively lower interval length, it introduces practical vulnerabilities: the same input can yield completely different prediction intervals across repeated runs of the algorithm. We formally derive the conditions under which PT achieves these misleading improvements and provide extensive empirical evidence across various regression and classification tasks. Furthermore, we introduce a new metric interval stability which helps detect whether a new CP method implicitly improves the length based on such PT-like techniques. Code is available at https://github.com/benben-cd/PT-Conformal-Prediction. --- ### 4D-CAAL: 4D Radar-Camera Calibration and Auto-Labeling for Autonomous Driving Authors: Shanliang Yao, Zhuoxiao Li, Runwei Guan, Kebin Cao, Meng Xia, Fuping Hu, Sen Xu, Yong Yue, Xiaohui Zhu, Weiping Ding, Ryan Wen Liu Published: 2026-01-29 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2601.21454v1 4D radar has emerged as a critical sensor for autonomous driving, primarily due to its enhanced capabilities in elevation measurement and higher resolution compared to traditional 3D radar. Effective integration of 4D radar with cameras requires accurate extrinsic calibration, and the development of radar-based perception algorithms demands large-scale annotated datasets. However, existing calibration methods often employ separate targets optimized for either visual or radar modalities, complicating correspondence establishment. Furthermore, manually labeling sparse radar data is labor-intensive and unreliable. To address these challenges, we propose 4D-CAAL, a unified framework for 4D radar-camera calibration and auto-labeling. Our approach introduces a novel dual-purpose calibration target design, integrating a checkerboard pattern on the front surface for camera detection and a corner reflector at the center of the back surface for radar detection. We develop a robust correspondence matching algorithm that aligns the checkerboard center with the strongest radar reflection point, enabling accurate extrinsic calibration. Subsequently, we present an auto-labeling pipeline that leverages the calibrated sensor relationship to transfer annotations from camera-based segmentations to radar point clouds through geometric projection and multi-feature optimization. Extensive experiments demonstrate that our method achieves high calibration accuracy while significantly reducing manual annotation effort, thereby accelerating the development of robust multi-modal perception systems for autonomous driving. --- ### LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning Authors: Xunkai Li, Zhengyu Wu, Zekai Chen, Henan Sun, Daohan Su, Guang Zeng, Hongchao Qin, Rong-Hua Li, Guoren Wang Published: 2026-01-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.21453v1 Recently, the rapid advancement of multimodal domains has driven a data-centric paradigm shift in graph ML, transitioning from text-attributed to multimodal-attributed graphs. This advancement significantly enhances data representation and expands the scope of graph downstream tasks, such as modality-oriented tasks, thereby improving the practical utility of graph ML. Despite its promise, limitations exist in the current neural paradigms: (1) Neglect Context in Modality Alignment: Most existing methods adopt topology-constrained or modality-specific operators as tokenizers. These aligners inevitably neglect graph context and inhibit modality interaction, resulting in suboptimal alignment. (2) Lack of Adaptation in Modality Fusion: Most existing methods are simple adaptations for 2-modality graphs and fail to adequately exploit aligned tokens equipped with topology priors during fusion, leading to poor generalizability and performance degradation. To address the above issues, we propose LION (c\underline{LI}ff\underline{O}rd \underline{N}eural paradigm) based on the Clifford algebra and decoupled graph neural paradigm (i.e., propagation-then-aggregation) to implement alignment-then-fusion in multimodal-attributed graphs. Specifically, we first construct a modality-aware geometric manifold grounded in Clifford algebra. This geometric-induced high-order graph propagation efficiently achieves modality interaction, facilitating modality alignment. Then, based on the geometric grade properties of aligned tokens, we propose adaptive holographic aggregation. This module integrates the energy and scale of geometric grades with learnable parameters to improve modality fusion. Extensive experiments on 9 datasets demonstrate that LION significantly outperforms SOTA baselines across 3 graph and 3 modality downstream tasks. --- ### SAGE: Sequence-level Adaptive Gradient Evolution for Generative Recommendation Authors: Yu Xie, Xing Kai Ren, Ying Qi, Hu Yao Published: 2026-01-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.21452v3 Reinforcement learning-based preference optimization is increasingly used to align list-wise generative recommenders with complex, multi-objective user feedback, yet existing optimizers such as Gradient-Bounded Policy Optimization (GBPO) exhibit structural limitations in recommendation settings. We identify a Symmetric Conservatism failure mode in which symmetric update bounds suppress learning from rare positive signals (e.g., cold-start items), static negative-sample constraints fail to prevent diversity collapse under rejection-dominated feedback, and group-normalized multi-objective rewards lead to low-resolution training signals. To address these issues, we propose SAGE (Sequence-level Adaptive Gradient Evolution), a unified optimizer designed for list-wise generative recommendation. SAGE introduces sequence-level signal alignment via a geometric-mean importance ratio and a decoupled multi-objective advantage estimator to reduce token-level variance and mitigate reward collapse, together with asymmetric adaptive bounding that applies positive Boost updates to successful slates and an entropy-aware penalty to discourage low-diversity failures. Experiments on Amazon Product Reviews and the large-scale RecIF-Bench demonstrate consistent improvements in top-K accuracy, cold-start recall, and diversity across both Semantic-ID and native-text action spaces, while preserving numerical stability during training. These results suggest that asymmetric, sequence-aware policy optimization provides a principled and effective framework for addressing optimization failures in generative recommendation. --- ### Variance & Greediness: A comparative study of metric-learning losses Authors: Donghuo Zeng, Hao Niu, Zhi Li, Masato Taya Published: 2026-01-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.21450v1 Metric learning is central to retrieval, yet its effects on embedding geometry and optimization dynamics are not well understood. We introduce a diagnostic framework, VARIANCE (intra-/inter-class variance) and GREEDINESS (active ratio and gradient norms), to compare seven representative losses, i.e., Contrastive, Triplet, N-pair, InfoNCE, ArcFace, SCL, and CCL, across five image-retrieval datasets. Our analysis reveals that Triplet and SCL preserve higher within-class variance and clearer inter-class margins, leading to stronger top-1 retrieval in fine-grained settings. In contrast, Contrastive and InfoNCE compact embeddings are achieved quickly through many small updates, accelerating convergence but potentially oversimplifying class structures. N-pair achieves a large mean separation but with uneven spacing. These insights reveal a form of efficiency-granularity trade-off and provide practical guidance: prefer Triplet/SCL when diversity preservation and hard-sample discrimination are critical, and Contrastive/InfoNCE when faster embedding compaction is desired. --- ### ChipBench: A Next-Step Benchmark for Evaluating LLM Performance in AI-Aided Chip Design Authors: Zhongkai Yu, Chenyang Zhou, Yichen Lin, Hejia Zhang, Haotian Ye, Junxia Cui, Zaifeng Pan, Jishen Zhao, Yufei Ding Published: 2026-01-29 Categories: cs.AI, cs.AR arXiv: https://arxiv.org/abs/2601.21448v2 While Large Language Models (LLMs) show significant potential in hardware engineering, current benchmarks suffer from saturation and limited task diversity, failing to reflect LLMs' performance in real industrial workflows. To address this gap, we propose a comprehensive benchmark for AI-aided chip design that rigorously evaluates LLMs across three critical tasks: Verilog generation, debugging, and reference model generation. Our benchmark features 44 realistic modules with complex hierarchical structures, 89 systematic debugging cases, and 132 reference model samples across Python, SystemC, and CXXRTL. Evaluation results reveal substantial performance gaps, with state-of-the-art Claude-4.5-opus achieving only 30.74\% on Verilog generation and 13.33\% on Python reference model generation, demonstrating significant challenges compared to existing saturated benchmarks where SOTA models achieve over 95\% pass rates. Additionally, to help enhance LLM reference model generation, we provide an automated toolbox for high-quality training data generation, facilitating future research in this underexplored domain. Our code is available at https://github.com/zhongkaiyu/ChipBench.git. --- ### Synthetic Pattern Generation and Detection of Financial Activities using Graph Autoencoders Authors: Francesco Zola, Lucia Muñoz, Andrea Venturi, Amaia Gil Published: 2026-01-29 Categories: cs.LG, cs.CE, cs.ET arXiv: https://arxiv.org/abs/2601.21446v1 Illicit financial activities such as money laundering often manifest through recurrent topological patterns in transaction networks. Detecting these patterns automatically remains challenging due to the scarcity of labeled real-world data and strict privacy constraints. To address this, we investigate whether Graph Autoencoders (GAEs) can effectively learn and distinguish topological patterns that mimic money laundering operations when trained on synthetic data. The analysis consists of two phases: (i) data generation, where synthetic samples are created for seven well-known illicit activity patterns using parametrized generators that preserve structural consistency while introducing realistic variability; and (ii) model training and validation, where separate GAEs are trained on each pattern without explicit labels, relying solely on reconstruction error as an indicator of learned structure. We compare three GAE implementations based on three distinct convolutional layers: Graph Convolutional (GAE-GCN), GraphSAGE (GAE-SAGE), and Graph Attention Network (GAE-GAT). Experimental results show that GAE-GCN achieves the most consistent reconstruction performance across patterns, while GAE-SAGE and GAE-GAT exhibit competitive results only in few specific patterns. These findings suggest that graph-based representation learning on synthetic data provides a viable path toward developing AI-driven tools for detecting illicit behaviors, overcoming the limitations of financial datasets. --- ### APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention Authors: Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Ao Sun, Ziqi Yuan, Hao Zhou, Fandong Meng, Zhiyuan Liu Published: 2026-01-29 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.21444v2 The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention on a single GPU, yielding limited acceleration or degraded performance and restricting LMMs from handling longer, more complex videos. To overcome these issues, we propose APB-V, a sequence-parallel framework with optimized attention that accelerates long-video inference across multiple GPUs. By distributing approximate attention, APB-V reduces computation and increases parallelism, enabling efficient processing of more visual embeddings without compression and thereby improving task performance. System-level optimizations, such as load balancing and fused forward passes, further unleash the potential of APB-V, delivering speedups of 12.72x, 1.70x, and 1.18x over FlashAttn, ZigZagRing, and APB, without notable performance loss. Code available at https://github.com/thunlp/APB --- ### The Paradox of Robustness: Decoupling Rule-Based Logic from Affective Noise in High-Stakes Decision-Making Authors: Jon Chun, Katherine Elkins Published: 2026-01-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.21439v2 While Large Language Models (LLMs) are widely documented to be sensitive to minor prompt perturbations and prone to sycophantic alignment, their robustness in consequential, rule-bound decision-making remains under-explored. We uncover a striking "Paradox of Robustness": despite their known lexical brittleness, aligned LLMs exhibit strong robustness to emotional framing effects in rule-bound institutional decision-making. Using a controlled perturbation framework across three high-stakes domains (healthcare, finance, and education), we find a negligible effect size (Cohen's h = 0.003) compared to the substantial biases observed in analogous human contexts (h in (0.3, 0.8)), approximately two orders of magnitude smaller. This invariance persists across eight models with diverse training paradigms, suggesting the mechanisms driving sycophancy and prompt sensitivity do not translate to failures in logical constraint satisfaction. While LLMs may be "brittle" to how a query is formatted, they appear considerably more stable against affective attempts to bias rule-bound decisions. To probe the boundary of this finding, we add two reviewer-driven side studies. A five-scenario immigration extension yields a small but statistically detectable +0.8 percentage point shift that remains within a pre-specified +/-3 percentage point Region of Practical Equivalence (ROPE), while a screening-level adversarial narrative pilot finds no meaningful decision shift under stronger LLM-generated prompts. We release a core benchmark (9 base scenarios x 18 condition variants = 162 unique prompts), code, and data to facilitate replicable evaluation. --- ### Accurate Network Traffic Matrix Prediction via LEAD: a Large Language Model-Enhanced Adapter-Based Conditional Diffusion Model Authors: Yu Sun, Yaqiong Liu, Nan Cheng, Jiayuan Li, Zihan Jia, Xialin Du, Mugen Peng Published: 2026-01-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.21437v2 Driven by the evolution toward 6G and AI-native edge intelligence, network operations increasingly require predictive and risk-aware adaptation under stringent computation and latency constraints. Network Traffic Matrix (TM), which characterizes flow volumes between nodes, is a fundamental signal for proactive traffic engineering. However, accurate TM forecasting remains challenging due to the stochastic, non-linear, and bursty nature of network dynamics. Existing discriminative models often suffer from over-smoothing and provide limited uncertainty awareness, leading to poor fidelity under extreme bursts. To address these limitations, we propose LEAD, a Large Language Model (LLM)-Enhanced Adapter-based conditional Diffusion model. First, LEAD adopts a "Traffic-to-Image" paradigm to transform traffic matrices into RGB images, enabling global dependency modeling via vision backbones. Then, we design a "Frozen LLM with Trainable Adapter" model, which efficiently captures temporal semantics with limited computational cost. Moreover, we propose a Dual-Conditioning Strategy to precisely guide a diffusion model to generate complex, dynamic network traffic matrices. Experiments on the Abilene and GEANT datasets demonstrate that LEAD outperforms all baselines. On the Abilene dataset, LEAD attains a remarkable 45.2% reduction in RMSE against the best baseline, with the error margin rising only marginally from 0.1098 at one-step to 0.1134 at 20-step predictions. Meanwhile, on the GEANT dataset, LEAD achieves a 0.0258 RMSE at 20-step prediction horizon which is 27.3% lower than the best baseline. --- ### From Consistency to Complementarity: Aligned and Disentangled Multi-modal Learning for Time Series Understanding and Reasoning Authors: Hang Ni, Weijia Zhang, Fei Wang, Zezhi Shao, Hao Liu Published: 2026-01-29 Categories: cs.LG, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2601.21436v2 Advances in multi-modal large language models (MLLMs) have inspired time series understanding and reasoning tasks, that enable natural language querying over time series, producing textual analyses of complex temporal dynamics. Recent attempts hybridize numerical time series with their visualized plots, facilitating precise value reasoning and visual structure comprehension for comprehensive time series understanding of MLLMs. However, effective numerical-visual modality integration remains challenging due to fine-grained temporal misalignment across modalities and severe entanglement between shared and modality-specific semantics, which hinder localized interpretation and complementary reasoning. To address these issues, we propose MADI, a multi-modal LLM enhanced with fine-grained alignment and disentangled interaction, featuring (1) Patch-level Alignment, which enforces physically grounded fine-grained correspondence across heterogeneous modalities, (2) Discrete Disentangled Interaction, which separates modality-common semantics into compact discrete latents and adaptively synergizes the purified modality-unique information, and (3) Critical-token Highlighting, which emphasizes informative, query-relevant signals for robust reasoning. Experiments on synthetic and real-world benchmarks show that MADI consistently outperforms general-purpose LLMs and time-series-specialized MLLMs. --- ### Framing Instability in LLM Ethical Stance: Auditing Negation Sensitivity in Moral Dilemmas Authors: Katherine Elkins, Jon Chun Published: 2026-01-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.21433v2 Language models are increasingly consulted on ethically consequential questions, yet the stance a model expresses may not survive a change in framing. We audit 16 models across 14 ethically fraught dilemmas using polarity-paired proposals ("They should X" / "They should not X"). A model's judgment of the underlying action should not reverse merely because the question is phrased as a prohibition rather than a prescription and yet, we find systematic deviations from this invariance including wholesale endorsement flips, indicating that ethical decisions are vulnerable to framing instability. Small open-weight models (1-4B parameters) endorse a proposed action 24% of the time under affirmative framing but up to 100% under negated framings, a swing of as much as 76 percentage points. Human coding of a response sample confirms the instability is genuine while showing that binary agree/disagree proxies over-state its magnitude, suggesting that an LLM judge cannot replace human coders because it silently collapses abstentions and mirrors the very forced-choice bias under study. Commercial models are for the most part more stable but still shift substantially, with cross-model agreement dropping from 73% on the bare affirmative framing to 59% under simple negation. We argue that because binary agree/disagree formats both inflate apparent endorsement and mask polarity-dependence, single-phrasing audits can misreport a model's ethical stance, and we propose the Negation Sensitivity Index (NSI) as a complement that measures stance stability directly. A model whose stance flips with phrasing cannot be relied upon in any high-stakes decision scenario. --- ### MultiModal Fine-tuning with Synthetic Captions Authors: Shohei Enomoto, Shin'ya Yamaguchi Published: 2026-01-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.21426v1 In this paper, we address a fundamental gap between pre-training and fine-tuning of deep neural networks: while pre-training has shifted from unimodal to multimodal learning with enhanced visual understanding, fine-tuning predominantly remains unimodal, limiting the benefits of rich pre-trained representations. To bridge this gap, we propose a novel approach that transforms unimodal datasets into multimodal ones using Multimodal Large Language Models (MLLMs) to generate synthetic image captions for fine-tuning models with a multimodal objective. Our method employs carefully designed prompts incorporating class labels and domain context to produce high-quality captions tailored for classification tasks. Furthermore, we introduce a supervised contrastive loss function that explicitly encourages clustering of same-class representations during fine-tuning, along with a new inference technique that leverages class-averaged text embeddings from multiple synthetic captions per image. Extensive experiments across 13 image classification benchmarks demonstrate that our approach outperforms baseline methods, with particularly significant improvements in few-shot learning scenarios. Our work establishes a new paradigm for dataset enhancement that effectively bridges the gap between multimodal pre-training and fine-tuning. Our code is available at https://github.com/s-enmt/MMFT. --- ### Lossy Common Information in a Learnable Gray-Wyner Network Authors: Anderson de Andrade, Alon Harell, Ivan V. Bajić Published: 2026-01-29 Categories: cs.LG, cs.CV, cs.IT arXiv: https://arxiv.org/abs/2601.21424v3 Many computer vision tasks share substantial overlapping information, yet conventional codecs tend to ignore this, leading to redundant and inefficient representations. The Gray-Wyner network, a classical concept from information theory, offers a principled framework for separating common and task-specific information. Inspired by this idea, we develop a learnable three-channel codec that disentangles shared information from task-specific details across multiple vision tasks. We characterize the limits of this approach through the notion of lossy common information, and propose an optimization objective that balances inherent tradeoffs in learning such representations. Through comparisons of three codec architectures on two-task scenarios spanning six vision benchmarks, we demonstrate that our approach substantially reduces redundancy and consistently outperforms independent coding. These results highlight the practical value of revisiting Gray-Wyner theory in modern machine learning contexts, bridging classic information theory with task-driven representation learning. --- ### From Implicit Ambiguity to Explicit Solidity: Diagnosing Interior Geometric Degradation in Neural Radiance Fields for Dense 3D Scene Understanding Authors: Jiangsan Zhao, Jakob Geipel, Kryzysztof Kusnierek Published: 2026-01-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.21421v2 Neural Radiance Fields (NeRFs) have emerged as a powerful paradigm for multi-view reconstruction, complementing classical photogrammetric pipelines based on Structure-from-Motion (SfM) and Multi-View Stereo (MVS). However, their reliability for quantitative 3D analysis in dense, self-occluding scenes remains poorly understood. In this study, we identify a fundamental failure mode of implicit density fields under heavy occlusion, which we term Interior Geometric Degradation (IGD). We show that transmittance-based volumetric optimization satisfies photometric supervision by reconstructing hollow or fragmented structures rather than solid interiors, leading to systematic instance undercounting. Through controlled experiments on synthetic datasets with increasing occlusion, we demonstrate that state-of-the-art mask-supervised NeRFs saturate at approximately 89% instance recovery in dense scenes, despite improved surface coherence and mask quality. To overcome this limitation, we introduce an explicit geometric pipeline based on Sparse Voxel Rasterization (SVRaster), initialized from SfM feature geometry. By projecting 2D instance masks onto an explicit voxel grid and enforcing geometric separation via recursive splitting, our approach preserves physical solidity and achieves a 95.8% recovery rate in dense clusters. A sensitivity analysis using degraded segmentation masks further shows that explicit SfM-based geometry is substantially more robust to supervision failure, recovering 43% more instances than implicit baselines. These results demonstrate that explicit geometric priors are a prerequisite for reliable quantitative analysis in highly self-occluding 3D scenes. --- ### ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation Authors: Zihao Huang, Jundong Zhou, Xingwei Qu, Qiyang Min, Ge Zhang Published: 2026-01-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.21420v1 Large language models allocate uniform computation across all tokens, ignoring that some sequences are trivially predictable while others require deep reasoning. We introduce ConceptMoE, which dynamically merges semantically similar tokens into concept representations, performing implicit token-level compute allocation. A learnable chunk module identifies optimal boundaries by measuring inter-token similarity, compressing sequences by a target ratio $R$ before they enter the compute-intensive concept model. Crucially, the MoE architecture enables controlled evaluation: we reallocate saved computation to match baseline activated FLOPs (excluding attention map computation) and total parameters, isolating genuine architectural benefits. Under these conditions, ConceptMoE consistently outperforms standard MoE across language and vision-language tasks, achieving +0.9 points on language pretraining, +2.3 points on long context understanding, and +0.6 points on multimodal benchmarks. When converting pretrained MoE during continual training with layer looping, gains reach +5.5 points, demonstrating practical applicability. Beyond performance, ConceptMoE reduces attention computation by up to $R^2\times$ and KV cache by $R\times$. At $R=2$, empirical measurements show prefill speedups reaching 175\% and decoding speedups up to 117\% on long sequences. The minimal architectural modifications enable straightforward integration into existing MoE, demonstrating that adaptive concept-level processing fundamentally improves both effectiveness and efficiency of large language models. --- ### Revisiting Diffusion Model Predictions Through Dimensionality Authors: Qing Jin, Chaoyang Wang Published: 2026-01-29 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2601.21419v2 Recent advances in diffusion and flow matching models have highlighted a shift in the preferred prediction target -- moving from noise ($\varepsilon$) and velocity (v) to direct data (x) prediction -- particularly in high-dimensional settings. However, a formal explanation of why the optimal target depends on the specific properties of the data remains elusive. In this work, we provide a theoretical framework based on a generalized prediction formulation that accommodates arbitrary output targets, of which $\varepsilon$-, v-, and x-prediction are special cases. We derive the analytical relationship between data's geometry and the optimal prediction target, offering a rigorous justification for why x-prediction becomes superior when the ambient dimension significantly exceeds the data's intrinsic dimension. Furthermore, while our theory identifies dimensionality as the governing factor for the optimal prediction target, the intrinsic dimension of manifold-bound data is typically intractable to estimate in practice. To bridge this gap, we propose k-Diff, a framework that employs a data-driven approach to learn the optimal prediction parameter k directly from data, bypassing the need for explicit dimension estimation. Extensive experiments in both latent-space and pixel-space image generation demonstrate that k-Diff consistently outperforms fixed-target baselines across varying architectures and data scales, providing a principled and automated approach to enhancing generative performance. --- ### Mitigating Overthinking in Large Reasoning Models via Difficulty-aware Reinforcement Learning Authors: Qian Wan, Ziao Xu, Luona Wei, Xiaoxuan Shen, Jianwen Sun Published: 2026-01-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.21418v1 Large Reasoning Models (LRMs) achieve explicit chain-of-thought expansion by imitating deep thinking behaviors of humans, demonstrating excellent performance in complex task scenarios. However, the deep-thinking mode often leads to unnecessarily lengthy reasoning and resource inefficiency when handling simple tasks. This overthinking phenomenon may arise from the generation preference triggered by the reward function during post-training. Existing research attempts to mitigate overthinking from the perspective of prompt design or model training, but generally underestimates the importance of task difficulty awareness, which makes it difficult for LRMs to effectively allocate reasoning resources. In this paper, we propose Difficulty-aware Policy Optimization (DiPO), a reinforcement learning-based LRM training framework. DiPO encourages LRM to spontaneously model task complexity, and integrates them into reinforcement learning framework to adjust the generation preferences introduced by post-training. A difficulty modeling method based on model self-reasoning is proposed, which significantly reduces the dependence on manual annotation and formalize task complexity. We further develop a difficulty-signal-enhanced reward function that incorporates a penalty for lengthy reasoning while considering reasoning performance and output format. Experimental results indicate that DiPO enables the model to spontaneously adjust inference overhead, significantly reducing redundant tokens without losing performance due to thought compression. --- ### System 1&2 Synergy via Dynamic Model Interpolation Authors: Chenxu Yang, Qingyi Si, Chong Tian, Xiyu Liu, Dingyu Yao, Chuanyu Qin, Zheng Lin, Weiping Wang, Jiaqi Wang Published: 2026-01-29 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.21414v1 Training a unified language model that adapts between intuitive System 1 and deliberative System 2 remains challenging due to interference between their cognitive modes. Recent studies have thus pursued making System 2 models more efficient. However, these approaches focused on output control, limiting what models produce. We argue that this paradigm is misaligned: output length is merely a symptom of the model's cognitive configuration, not the root cause. In this work, we shift the focus to capability control, which modulates \textit{how models think} rather than \textit{what they produce}. To realize this, we leverage existing Instruct and Thinking checkpoints through dynamic parameter interpolation, without additional training. Our pilot study establishes that linear interpolation yields a convex, monotonic Pareto frontier, underpinned by representation continuity and structural connectivity. Building on this, we propose \textbf{DAMI} (\textbf{D}yn\textbf{A}mic \textbf{M}odel \textbf{I}nterpolation), a framework that estimates a query-specific Reasoning Intensity $λ(q)$ to configure cognitive depth. For training-based estimation, we develop a preference learning method encoding accuracy and efficiency criteria. For zero-shot deployment, we introduce a confidence-based method leveraging inter-model cognitive discrepancy. Experiments on five mathematical reasoning benchmarks demonstrate that DAMI achieves higher accuracy than the Thinking model while remaining efficient, effectively combining the efficiency of System 1 with the reasoning depth of System 2. --- ### Learning When to Trust LLM Priors: A Validated Framework for Semantic Prior Integration Authors: Erica Zhang, Naomi Sagan, Danny Tse, Fangzhao Zhang, Mert Pilanci, Jose Blanchet Published: 2026-01-29 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2601.21410v3 Large language models (LLMs) encode rich semantic knowledge that can be useful for supervised learning, but their outputs are unreliable as statistical priors: they may be noisy, misspecified, or hallucinated. Existing LLM-informed learning methods either trust such signals directly, leaving predictions vulnerable to unreliable LLM guidance, or restrict semantic integration to a single model class. We introduce Statsformer, a validated framework for learning when to trust LLM-derived semantic priors in supervised statistical learning. Statsformer maps LLM-derived feature scores into a family of learner-specific prior-injection mechanisms across a heterogeneous library of linear and nonlinear predictors. It then uses out-of-fold validation to adaptively calibrate the influence of each prior-informed learner, allowing useful semantic information to improve prediction while attenuating weak, misspecified, or adversarial priors. This yields a guardrailed statistical learning system with an oracle-style guarantee: up to statistical error, the final predictor performs no worse than the best convex combination of its in-library candidates, including prior-free learners. Across diverse prediction tasks, informative LLM priors improve performance, while unreliable priors are automatically downweighted. These results position Statsformer as a reliability-oriented approach to LLM-informed statistical learning: rather than trusting LLM knowledge directly, it validates semantic priors against data before allowing them to influence the final predictor. --- ### MPF-Net: Exposing High-Fidelity AI-Generated Video Forgeries via Hierarchical Manifold Deviation and Micro-Temporal Fluctuations Authors: Xinan He, Kaiqing Lin, Yue Zhou, Jiaming Zhong, Wei Ye, Wenhui Yi, Bing Fan, Feng Ding, Haodong Li, Bo Cao, Bin Li Published: 2026-01-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.21408v2 With the rapid advancement of video generation models such as Veo and Wan, the visual quality of synthetic content has reached a level where macro-level semantic errors and temporal inconsistencies are no longer prominent. However, this does not imply that the distinction between real and cutting-edge high-fidelity fake is untraceable. We argue that AI-generated videos are essentially products of a manifold-fitting process rather than a physical recording. Consequently, the pixel composition logic of consecutive adjacent frames residual in AI videos exhibits a structured and homogenous characteristic. We term this phenomenon `Manifold Projection Fluctuations' (MPF). Driven by this insight, we propose a hierarchical dual-path framework that operates as a sequential filtering process. The first, the Static Manifold Deviation Branch, leverages the refined perceptual boundaries of Large-Scale Vision Foundation Models (VFMs) to capture residual spatial anomalies or physical violations that deviate from the natural real-world manifold (off-manifold). For the remaining high-fidelity videos that successfully reside on-manifold and evade spatial detection, we introduce the Micro-Temporal Fluctuation Branch as a secondary, fine-grained filter. By analyzing the structured MPF that persists even in visually perfect sequences, our framework ensures that forgeries are exposed regardless of whether they manifest as global real-world manifold deviations or subtle computational fingerprints. --- ### BrainFuse: a unified infrastructure integrating realistic biological modeling and core AI methodology Authors: Baiyu Chen, Yujie Wu, Siyuan Xu, Peng Qu, Dehua Wu, Xu Chu, Haodong Bian, Shuo Zhang, Bo Xu, Youhui Zhang, Zhengyu Ma, Guoqi Li Published: 2026-01-29 Categories: cs.NE, q-bio.NC arXiv: https://arxiv.org/abs/2601.21407v1 Neuroscience and artificial intelligence represent distinct yet complementary pathways to general intelligence. However, amid the ongoing boom in AI research and applications, the translational synergy between these two fields has grown increasingly elusive-hampered by a widening infrastructural incompatibility: modern AI frameworks lack native support for biophysical realism, while neural simulation tools are poorly suited for gradient-based optimization and neuromorphic hardware deployment. To bridge this gap, we introduce BrainFuse, a unified infrastructure that provides comprehensive support for biophysical neural simulation and gradient-based learning. By addressing algorithmic, computational, and deployment challenges, BrainFuse exhibits three core capabilities: (1) algorithmic integration of detailed neuronal dynamics into a differentiable learning framework; (2) system-level optimization that accelerates customizable ion-channel dynamics by up to 3,000x on GPUs; and (3) scalable computation with highly compatible pipelines for neuromorphic hardware deployment. We demonstrate this full-stack design through both AI and neuroscience tasks, from foundational neuron simulation and functional cylinder modeling to real-world deployment and application scenarios. For neuroscience, BrainFuse supports multiscale biological modeling, enabling the deployment of approximately 38,000 Hodgkin-Huxley neurons with 100 million synapses on a single neuromorphic chip while consuming as low as 1.98 W. For AI, BrainFuse facilitates the synergistic application of realistic biological neuron models, demonstrating enhanced robustness to input noise and improved temporal processing endowed by complex HH dynamics. BrainFuse therefore serves as a foundational engine to facilitate cross-disciplinary research and accelerate the development of next-generation bio-inspired intelligent systems. --- ### Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation Authors: Zihan Su, Hongyang Wei, Kangrui Cen, Yong Wang, Guanhua Chen, Chun Yuan, Xiangxiang Chu Published: 2026-01-29 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.21406v3 Unified Multimodal Models (UMMs) integrate both visual understanding and generation within a single framework. Their ultimate aspiration is to create a cycle where understanding and generation mutually reinforce each other. While recent post-training methods have successfully leveraged understanding to enhance generation, the reverse direction of utilizing generation to improve understanding remains largely unexplored. In this work, we propose UniMRG (Unified Multi-Representation Generation), a simple yet effective architecture-agnostic post-training method. UniMRG enhances the understanding capabilities of UMMs by incorporating auxiliary generation tasks. Specifically, we train UMMs to generate multiple intrinsic representations of input images, namely pixel (reconstruction), depth (geometry), and segmentation (structure), alongside standard visual understanding objectives. By synthesizing these diverse representations, UMMs capture complementary information regarding appearance, spatial relations, and structural layout. Consequently, UMMs develop a deeper and more comprehensive understanding of visual inputs. Extensive experiments across diverse UMM architectures demonstrate that our method notably enhances fine-grained perception, reduces hallucinations, and improves spatial understanding, while simultaneously boosting generation capabilities. --- ### Rectifying Geometry-Induced Similarity Distortions for Real-World Aerial-Ground Person Re-Identification Authors: Kailash A. Hambarde, Hugo Proença Published: 2026-01-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.21405v2 Aerial-ground person re-identification (AG-ReID) is fundamentally challenged by extreme viewpoint and distance discrepancies between aerial and ground cameras, which induce severe geometric distortions and invalidate the assumption of a shared similarity space across views. Existing methods primarily rely on geometry-aware feature learning or appearance-conditioned prompting, while implicitly assuming that the geometry-invariant dot-product similarity used in attention mechanisms remains reliable under large viewpoint and scale variations. We argue that this assumption does not hold. Extreme camera geometry systematically distorts the query-key similarity space and degrades attention-based matching, even when feature representations are partially aligned. To address this issue, we introduce Geometry-Induced Query-Key Transformation (GIQT), a lightweight low-rank module that explicitly rectifies the similarity space by conditioning query-key interactions on camera geometry. Rather than modifying feature representations or the attention formulation itself, GIQT adapts the similarity computation to compensate for dominant geometry-induced anisotropic distortions. Building on this local similarity rectification, we further incorporate a geometry-conditioned prompt generation mechanism that provides global, view-adaptive representation priors derived directly from camera geometry.Experiments on four aerial-ground person re-identification benchmarks demonstrate that the proposed framework consistently improves robustness under extreme and previously unseen geometric conditions, while introducing minimal computational overhead compared to state-of-the-art methods. --- ### DataCross: A Unified Benchmark and Agent Framework for Cross-Modal Heterogeneous Data Analysis Authors: Ruyi Qi, Zhou Liu, Wentao Zhang Published: 2026-01-29 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2601.21403v1 In real-world data science and enterprise decision-making, critical information is often fragmented across directly queryable structured sources (e.g., SQL, CSV) and "zombie data" locked in unstructured visual documents (e.g., scanned reports, invoice images). Existing data analytics agents are predominantly limited to processing structured data, failing to activate and correlate this high-value visual information, thus creating a significant gap with industrial needs. To bridge this gap, we introduce DataCross, a novel benchmark and collaborative agent framework for unified, insight-driven analysis across heterogeneous data modalities. DataCrossBench comprises 200 end-to-end analysis tasks across finance, healthcare, and other domains. It is constructed via a human-in-the-loop reverse-synthesis pipeline, ensuring realistic complexity, cross-source dependency, and verifiable ground truth. The benchmark categorizes tasks into three difficulty tiers to evaluate agents' capabilities in visual table extraction, cross-modal alignment, and multi-step joint reasoning. We also propose the DataCrossAgent framework, inspired by the "divide-and-conquer" workflow of human analysts. It employs specialized sub-agents, each an expert on a specific data source, which are coordinated via a structured workflow of Intra-source Deep Exploration, Key Source Identification, and Contextual Cross-pollination. A novel reReAct mechanism enables robust code generation and debugging for factual verification. Experimental results show that DataCrossAgent achieves a 29.7% improvement in factuality over GPT-4o and exhibits superior robustness on high-difficulty tasks, effectively activating fragmented "zombie data" for insightful, cross-modal analysis. --- ### Intrinsic Reward Policy Optimization for Sparse-Reward Environments Authors: Minjae Cho, Huy Trong Tran Published: 2026-01-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.21391v1 Exploration is essential in reinforcement learning as an agent relies on trial and error to learn an optimal policy. However, when rewards are sparse, naive exploration strategies, like noise injection, are often insufficient. Intrinsic rewards can also provide principled guidance for exploration by, for example, combining them with extrinsic rewards to optimize a policy or using them to train subpolicies for hierarchical learning. However, the former approach suffers from unstable credit assignment, while the latter exhibits sample inefficiency and sub-optimality. We propose a policy optimization framework that leverages multiple intrinsic rewards to directly optimize a policy for an extrinsic reward without pretraining subpolicies. Our algorithm -- intrinsic reward policy optimization (IRPO) -- achieves this by using a surrogate policy gradient that provides a more informative learning signal than the true gradient in sparse-reward environments. We demonstrate that IRPO improves performance and sample efficiency relative to baselines in discrete and continuous environments, and formally analyze the optimization problem solved by IRPO. Our code is available at https://github.com/Mgineer117/IRPO. --- ### Learning to Optimize Job Shop Scheduling Under Structural Uncertainty Authors: Rui Zhang, Jianwei Niu, Xuefeng Liu, Shaojie Tang, Jing Yuan Published: 2026-01-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.21389v1 The Job-Shop Scheduling Problem (JSSP), under various forms of manufacturing uncertainty, has recently attracted considerable research attention. Most existing studies focus on parameter uncertainty, such as variable processing times, and typically adopt the actor-critic framework. In this paper, we explore a different but prevalent form of uncertainty in JSSP: structural uncertainty. Structural uncertainty arises when a job may follow one of several routing paths, and the selection is determined not by policy, but by situational factors (e.g., the quality of intermediate products) that cannot be known in advance. Existing methods struggle to address this challenge due to incorrect credit assignment: a high-quality action may be unfairly penalized if it is followed by a time-consuming path. To address this problem, we propose a novel method named UP-AAC. In contrast to conventional actor-critic methods, UP-AAC employs an asymmetric architecture. While its actor receives a standard stochastic state, the critic is crucially provided with a deterministic state reconstructed in hindsight. This design allows the critic to learn a more accurate value function, which in turn provides a lower-variance policy gradient to the actor, leading to more stable learning. In addition, we design an attention-based Uncertainty Perception Model (UPM) to enhance the actor's scheduling decisions. Extensive experiments demonstrate that our method outperforms existing approaches in reducing makespan on benchmark instances. --- ### User-Centric Evidence Ranking for Attribution and Fact Verification Authors: Guy Alt, Eran Hirsch, Serwar Basch, Ido Dagan, Oren Glickman Published: 2026-01-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.21387v1 Attribution and fact verification are critical challenges in natural language processing for assessing information reliability. While automated systems and Large Language Models (LLMs) aim to retrieve and select concise evidence to support or refute claims, they often present users with either insufficient or overly redundant information, leading to inefficient and error-prone verification. To address this, we propose Evidence Ranking, a novel task that prioritizes presenting sufficient information as early as possible in a ranked list. This minimizes user reading effort while still making all available evidence accessible for sequential verification. We compare two approaches for the new ranking task: one-shot ranking and incremental ranking. We introduce a new evaluation framework, inspired by information retrieval metrics, and construct a unified benchmark by aggregating existing fact verification datasets. Extensive experiments with diverse models show that incremental ranking strategies better capture complementary evidence and that LLM-based methods outperform shallower baselines, while still facing challenges in balancing sufficiency and redundancy. Compared to evidence selection, we conduct a controlled user study and demonstrate that evidence ranking both reduces reading effort and improves verification. This work provides a foundational step toward more interpretable, efficient, and user-aligned information verification systems. --- ### Understanding Frechet Speech Distance for Synthetic Speech Quality Evaluation Authors: June-Woo Kim, Dhruv Agarwal, Federica Cerina Published: 2026-01-29 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2601.21386v1 Objective evaluation of synthetic speech quality remains a critical challenge. Human listening tests are the gold standard, but costly and impractical at scale. Fréchet Distance has emerged as a promising alternative, yet its reliability depends heavily on the choice of embeddings and experimental settings. In this work, we comprehensively evaluate Fréchet Speech Distance (FSD) and its variant Speech Maximum Mean Discrepancy (SMMD) under varied embeddings and conditions. We further incorporate human listening evaluations alongside TTS intelligibility and synthetic-trained ASR WER to validate the perceptual relevance of these metrics. Our findings show that WavLM Base+ features yield the most stable alignment with human ratings. While FSD and SMMD cannot fully replace subjective evaluation, we show that they can serve as complementary, cost-efficient, and reproducible measures, particularly useful when large-scale or direct listening assessments are infeasible. Code is available at https://github.com/kaen2891/FrechetSpeechDistance. --- ### Sim-MSTNet: sim2real based Multi-task SpatioTemporal Network Traffic Forecasting Authors: Hui Ma, Qingzhong Li, Jin Wang, Jie Wu, Shaoyu Dou, Li Feng, Xinjun Pei Published: 2026-01-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.21384v1 Network traffic forecasting plays a crucial role in intelligent network operations, but existing techniques often perform poorly when faced with limited data. Additionally, multi-task learning methods struggle with task imbalance and negative transfer, especially when modeling various service types. To overcome these challenges, we propose Sim-MSTNet, a multi-task spatiotemporal network traffic forecasting model based on the sim2real approach. Our method leverages a simulator to generate synthetic data, effectively addressing the issue of poor generalization caused by data scarcity. By employing a domain randomization technique, we reduce the distributional gap between synthetic and real data through bi-level optimization of both sample weighting and model training. Moreover, Sim-MSTNet incorporates attention-based mechanisms to selectively share knowledge between tasks and applies dynamic loss weighting to balance task objectives. Extensive experiments on two open-source datasets show that Sim-MSTNet consistently outperforms state-of-the-art baselines, achieving enhanced accuracy and generalization. --- ### DA-SPS: A Dual-stage Network based on Singular Spectrum Analysis, Patching-strategy and Spearman-correlation for Multivariate Time-series Prediction Authors: Tianhao Zhang, Shusen Ma, Yu Kang, Yun-Bo Zhao Published: 2026-01-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.21381v1 Multivariate time-series forecasting, as a typical problem in the field of time series prediction, has a wide range of applications in weather forecasting, traffic flow prediction, and other scenarios. However, existing works do not effectively consider the impact of extraneous variables on the prediction of the target variable. On the other hand, they fail to fully extract complex sequence information based on various time patterns of the sequences. To address these drawbacks, we propose a DA-SPS model, which adopts different modules for feature extraction based on the information characteristics of different variables. DA-SPS mainly consists of two stages: the target variable processing stage (TVPS) and the extraneous variables processing stage (EVPS). In TVPS, the model first uses Singular Spectrum Analysis (SSA) to process the target variable sequence and then uses Long Short-Term Memory (LSTM) and P-Conv-LSTM which deploys a patching strategy to extract features from trend and seasonality components, respectively. In EVPS, the model filters extraneous variables that have a strong correlation with the target variate by using Spearman correlation analysis and further analyses them using the L-Attention module which consists of LSTM and attention mechanism. Finally, the results obtained by TVPS and EVPS are combined through weighted summation and linear mapping to produce the final prediction. The results on four public datasets demonstrate that the DA-SPS model outperforms existing state-of-the-art methods. Additionally, its performance in real-world scenarios is further validated using a private dataset collected by ourselves, which contains the test items' information on laptop motherboards. --- ### Towards Geometry-Aware and Motion-Guided Video Human Mesh Recovery Authors: Hongjun Chen, Huan Zheng, Wencheng Han, Jianbing Shen Published: 2026-01-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.21376v1 Existing video-based 3D Human Mesh Recovery (HMR) methods often produce physically implausible results, stemming from their reliance on flawed intermediate 3D pose anchors and their inability to effectively model complex spatiotemporal dynamics. To overcome these deep-rooted architectural problems, we introduce HMRMamba, a new paradigm for HMR that pioneers the use of Structured State Space Models (SSMs) for their efficiency and long-range modeling prowess. Our framework is distinguished by two core contributions. First, the Geometry-Aware Lifting Module, featuring a novel dual-scan Mamba architecture, creates a robust foundation for reconstruction. It directly grounds the 2D-to-3D pose lifting process with geometric cues from image features, producing a highly reliable 3D pose sequence that serves as a stable anchor. Second, the Motion-guided Reconstruction Network leverages this anchor to explicitly process kinematic patterns over time. By injecting this crucial temporal awareness, it significantly enhances the final mesh's coherence and robustness, particularly under occlusion and motion blur. Comprehensive evaluations on 3DPW, MPI-INF-3DHP, and Human3.6M benchmarks confirm that HMRMamba sets a new state-of-the-art, outperforming existing methods in both reconstruction accuracy and temporal consistency while offering superior computational efficiency. --- ### TeachBench: A Syllabus-Grounded Framework for Evaluating Teaching Ability in Large Language Models Authors: Zheng Li, Siyao Song, Jingyuan Ma, Rui Li, Ying Zeng, Minghao Li, Zhifang Sui Published: 2026-01-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.21375v1 Large language models (LLMs) show promise as teaching assistants, yet their teaching capability remains insufficiently evaluated. Existing benchmarks mainly focus on problem-solving or problem-level guidance, leaving knowledge-centered teaching underexplored. We propose a syllabus-grounded evaluation framework that measures LLM teaching capability via student performance improvement after multi-turn instruction. By restricting teacher agents to structured knowledge points and example problems, the framework avoids information leakage and enables reuse of existing benchmarks. We instantiate the framework on Gaokao data across multiple subjects. Experiments reveal substantial variation in teaching effectiveness across models and domains: some models perform well in mathematics, while teaching remains challenging in physics and chemistry. We also find that incorporating example problems does not necessarily improve teaching, as models often shift toward example-specific error correction. Overall, our results highlight teaching ability as a distinct and measurable dimension of LLM behavior. ---