# Research Papers — 2026-01 · bundle page 130 of 189 > Full-text markdown of papers #6451–6500 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/130 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/129.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/131.md) ### The Practicality of Normalizing Flow Test-Time Training in Bayesian Inference for Agent-Based Models Authors: Junyao Zhang, Jinglai Li, Junqi Tang Published: 2026-01-12 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2601.07413v1 Agent-Based Models (ABMs) are gaining great popularity in economics and social science because of their strong flexibility to describe the realistic and heterogeneous decisions and interaction rules between individual agents. In this work, we investigate for the first time the practicality of test-time training (TTT) of deep models such as normalizing flows, in the parameters posterior estimations of ABMs. We propose several practical TTT strategies for fine-tuning the normalizing flow against distribution shifts. Our numerical study demonstrates that TTT schemes are remarkably effective, enabling real-time adjustment of flow-based inference for ABM parameters. --- ### SCALPEL: Selective Capability Ablation via Low-rank Parameter Editing for Large Language Model Interpretability Analysis Authors: Zihao Fu, Xufeng Duan, Zhenguang G. Cai Published: 2026-01-12 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.07411v1 Large language models excel across diverse domains, yet their deployment in healthcare, legal systems, and autonomous decision-making remains limited by incomplete understanding of their internal mechanisms. As these models integrate into high-stakes systems, understanding how they encode capabilities has become fundamental to interpretability research. Traditional approaches identify important modules through gradient attribution or activation analysis, assuming specific capabilities map to specific components. However, this oversimplifies neural computation: modules may contribute to multiple capabilities simultaneously, while single capabilities may distribute across multiple modules. These coarse-grained analyses fail to capture fine-grained, distributed capability encoding. We present SCALPEL (Selective Capability Ablation via Low-rank Parameter Editing for Large language models), a framework representing capabilities as low-rank parameter subspaces rather than discrete modules. Our key insight is that capabilities can be characterized by low-rank modifications distributed across layers and modules, enabling precise capability removal without affecting others. By training LoRA adapters to reduce distinguishing correct from incorrect answers while preserving general language modeling quality, SCALPEL identifies low-rank representations responsible for particular capabilities while remaining disentangled from others. Experiments across diverse capability and linguistic tasks from BLiMP demonstrate that SCALPEL successfully removes target capabilities while preserving general capabilities, providing fine-grained insights into capability distribution across parameter space. Results reveal that capabilities exhibit low-rank structure and can be selectively ablated through targeted parameter-space interventions, offering nuanced understanding of capability encoding in LLMs. --- ### Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning Authors: Ziheng Li, Liu Kang, Feng Xiao, Luxi Xing, Qingyi Si, Zhuoran Li, Weikang Gong, Deqing Yang, Yanghua Xiao, Hongcheng Guo Published: 2026-01-12 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.07408v2 Group Relative Policy Optimization (GRPO) has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks. However, standard GRPO employs a coarse-grained credit assignment mechanism that propagates group-level rewards uniformly to to every token in a sequence, neglecting the varying contribution of individual reasoning steps. We address this limitation by introducing Outcome-grounded Advantage Reshaping (OAR), a fine-grained credit assignment mechanism that redistributes advantages based on how much each token influences the model's final answer. We instantiate OAR via two complementary strategies: (1) OAR-P, which estimates outcome sensitivity through counterfactual token perturbations, serving as a high-fidelity attribution signal; (2) OAR-G, which uses an input-gradient sensitivity proxy to approximate the influence signal with a single backward pass. These importance signals are integrated with a conservative Bi-Level advantage reshaping scheme that suppresses low-impact tokens and boosts pivotal ones while preserving the overall advantage mass. Empirical results on extensive mathematical reasoning benchmarks demonstrate that while OAR-P sets the performance upper bound, OAR-G achieves comparable gains with negligible computational overhead, both significantly outperforming a strong GRPO baseline, pushing the boundaries of critic-free LLM reasoning. --- ### Measuring Narrative Polarization in Online Discourse Authors: Jan Elfes, Marco Bastos, Luca Maria Aiello Published: 2026-01-12 Categories: cs.CY, cs.CL, cs.SI arXiv: https://arxiv.org/abs/2601.07398v2 Polarization research has demonstrated how people cluster in homogeneous groups with opposing opinions. However, this effect emerges not only through interaction between people, limiting communication between groups, but also between narratives, shaping opinions and partisan identities. Yet, how polarized information environments portray opposing interpretations of reality, and whether narratives move between content environments despite limited interactions, remains unexplored. To address this gap, we formalize the concept of narrative polarization and demonstrate its measurement in 212 YouTube videos and 90,029 comments on the Israeli-Palestinian conflict. Based on structural narrative theory and implemented through a large language model, we extract the narrative roles assigned to central actors in two partisan information environments. We find that while videos produce highly polarized narratives, comments exhibit significantly lower levels of narrative polarization, converging on shared core narrative structures. However, recurring narrative motifs capturing more complex actor constellations reveal additional differences between partisan environments. --- ### Layerwise goal-oriented adaptivity for neural ODEs: an optimal control perspective Authors: Michael Hintermüller, Michael Hinze, Denis Korolev Published: 2026-01-12 Categories: math.OC, cs.AI arXiv: https://arxiv.org/abs/2601.07397v2 In this work, we propose a novel layerwise adaptive construction method for neural network architectures. Our approach is based on a goal--oriented dual-weighted residual technique for the optimal control of neural differential equations. This leads to an ordinary differential equation constrained optimization problem with controls acting as coefficients and a specific loss function. We implement our approach on the basis of a DG(0) Galerkin discretization of the neural ODE, leading to an explicit Euler time marching scheme. The resulting optimization problem is solved using the Adam algorithm and a BFGS method adapted to the $H^1$ topology induced by the regularization term. Finally, we apply our method to the construction of neural networks for the classification of data sets, where we present results for a selection of well known examples from the literature. --- ### Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Efficient Diffusion Transformers Authors: Guantao Chen, Shikang Zheng, Yuqi Lin, Linfeng Zhang Published: 2026-01-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.07396v1 Diffusion Transformer (DiT) models have achieved unprecedented quality in image and video generation, yet their iterative sampling process remains computationally prohibitive. To accelerate inference, feature caching methods have emerged by reusing intermediate representations across timesteps. However, existing caching approaches treat all feature components uniformly. We reveal that DiT feature spaces contain distinct principal and residual subspaces with divergent temporal behavior: the principal subspace evolves smoothly and predictably, while the residual subspace exhibits volatile, low-energy oscillations that resist accurate prediction. Building on this insight, we propose SVD-Cache, a subspace-aware caching framework that decomposes diffusion features via Singular Value Decomposition (SVD), applies exponential moving average (EMA) prediction to the dominant low-rank components, and directly reuses the residual subspace. Extensive experiments demonstrate that SVD-Cache achieves near-lossless across diverse models and methods, including 5.55$\times$ speedup on FLUX and HunyuanVideo, and compatibility with model acceleration techniques including distillation, quantization and sparse attention. Our code is in supplementary material and will be released on Github. --- ### MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP Authors: Ruiqi Li, Zhiqiang Wang, Yunhao Yao, Xiang-Yang Li Published: 2026-01-12 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.07395v1 To standardize interactions between LLM-based agents and their environments, the Model Context Protocol (MCP) was proposed and has since been widely adopted. However, integrating external tools expands the attack surface, exposing agents to tool poisoning attacks. In such attacks, malicious instructions embedded in tool metadata are injected into the agent context during MCP registration phase, thereby manipulating agent behavior. Prior work primarily focuses on explicit tool poisoning or relied on manually crafted poisoned tools. In contrast, we focus on a particularly stealthy variant: implicit tool poisoning, where the poisoned tool itself remains uninvoked. Instead, the instructions embedded in the tool metadata induce the agent to invoke a legitimate but high-privilege tool to perform malicious operations. We propose MCP-ITP, the first automated and adaptive framework for implicit tool poisoning within the MCP ecosystem. MCP-ITP formulates poisoned tool generation as a black-box optimization problem and employs an iterative optimization strategy that leverages feedback from both an evaluation LLM and a detection LLM to maximize Attack Success Rate (ASR) while evading current detection mechanisms. Experimental results on the MCPTox dataset across 12 LLM agents demonstrate that MCP-ITP consistently outperforms the manually crafted baseline, achieving up to 84.2% ASR while suppressing the Malicious Tool Detection Rate (MDR) to as low as 0.3%. --- ### Software-Hardware Co-optimization for Modular E2E AV Paradigm: A Unified Framework of Optimization Approaches, Simulation Environment and Evaluation Metrics Authors: Chengzhi Ji, Xingfeng Li, Zhaodong Lv, Hao Sun, Pan Liu, Hao Frank Yang, Ziyuan Pu Published: 2026-01-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.07393v1 Modular end-to-end (ME2E) autonomous driving paradigms combine modular interpretability with global optimization capability and have demonstrated strong performance. However, existing studies mainly focus on accuracy improvement, while critical system-level factors such as inference latency and energy consumption are often overlooked, resulting in increasingly complex model designs that hinder practical deployment. Prior efforts on model compression and acceleration typically optimize either the software or hardware side in isolation. Software-only optimization cannot fundamentally remove intermediate tensor access and operator scheduling overheads, whereas hardware-only optimization is constrained by model structure and precision. As a result, the real-world benefits of such optimizations are often limited. To address these challenges, this paper proposes a reusable software and hardware co-optimization and closed-loop evaluation framework for ME2E autonomous driving inference. The framework jointly integrates software-level model optimization with hardware-level computation optimization under a unified system-level objective. In addition, a multidimensional evaluation metric is introduced to assess system performance by jointly considering safety, comfort, efficiency, latency, and energy, enabling quantitative comparison of different optimization strategies. Experiments across multiple ME2E autonomous driving stacks show that the proposed framework preserves baseline-level driving performance while significantly reducing inference latency and energy consumption, achieving substantial overall system-level improvements. These results demonstrate that the proposed framework provides practical and actionable guidance for efficient deployment of ME2E autonomous driving systems. --- ### OceanSAR-2: A Universal Feature Extractor for SAR Ocean Observation Authors: Alexandre Tuel, Thomas Kerdreux, Quentin Febvre, Alexis Mouche, Antoine Grouazel, Jean-Renaud Miadana, Antoine Audras, Chen Wang, Bertrand Chapron Published: 2026-01-12 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.07392v1 We present OceanSAR-2, the second generation of our foundation model for SAR-based ocean observation. Building on our earlier release, which pioneered self-supervised learning on Sentinel-1 Wave Mode data, OceanSAR-2 relies on improved SSL training and dynamic data curation strategies, which enhances performance while reducing training cost. OceanSAR-2 demonstrates strong transfer performance across downstream tasks, including geophysical pattern classification, ocean surface wind vector and significant wave height estimation, and iceberg detection. We release standardized benchmark datasets, providing a foundation for systematic evaluation and advancement of SAR models for ocean applications. --- ### On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training Authors: Xueyan Niu, Bo Bai, Wei Han, Weixi Zhang Published: 2026-01-12 Categories: cs.LG, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2601.07389v2 Post-training of large language models routinely interleaves supervised fine-tuning (SFT) with reinforcement learning (RL). These two methods have different objectives: SFT minimizes the cross-entropy loss between model outputs and expert responses, while RL maximizes reward signals derived from human preferences or rule-based verifiers. Modern reasoning models have widely adopted the practice of alternating SFT and RL training. However, there is no theoretical account of whether they can be decoupled. We prove that decoupling is impossible in either order: (1) SFT-then-RL coupling: RL increases SFT loss under both distributional (KL-based) and landscape (PL-based) analyses; and (2) RL-then-SFT coupling: SFT lowers the reward achieved by RL under analogous conditions. Under the PL condition, we further derive the optimal RL duration that balances reward improvement against SFT degradation, identify the non-decoupling threshold governing when RL can improve SFT, and bound the gradient misalignment via spectral concentration. Experiments on Qwen3-0.6B confirm the predicted degradation, verifying that SFT and RL cannot be separated without loss of prior performance in the post-training pipeline. --- ### Computing patient similarity based on unstructured clinical notes Authors: Petr Zelina, Marko Řeháček, Jana Halámková, Lucia Bohovicová, Martin Rusinko, Vít Nováček Published: 2026-01-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.07385v1 Clinical notes hold rich yet unstructured details about diagnoses, treatments, and outcomes that are vital to precision medicine but hard to exploit at scale. We introduce a method that represents each patient as a matrix built from aggregated embeddings of all their notes, enabling robust patient similarity computation based on their latent low-rank representations. Using clinical notes of 4,267 Czech breast-cancer patients and expert similarity labels from Masaryk Memorial Cancer Institute, we evaluate several matrix-based similarity measures and analyze their strengths and limitations across different similarity facets, such as clinical history, treatment, and adverse events. The results demonstrate the usefulness of the presented method for downstream tasks, such as personalized therapy recommendations or toxicity warnings. --- ### CompNO: A Novel Foundation Model approach for solving Partial Differential Equations Authors: Hamda Hmida, Hsiu-Wen Chang Joly, Youssef Mesri Published: 2026-01-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.07384v1 Partial differential equations (PDEs) govern a wide range of physical phenomena, but their numerical solution remains computationally demanding, especially when repeated simulations are required across many parameter settings. Recent Scientific Foundation Models (SFMs) aim to alleviate this cost by learning universal surrogates from large collections of simulated systems, yet they typically rely on monolithic architectures with limited interpretability and high pretraining expense. In this work we introduce Compositional Neural Operators (CompNO), a compositional neural operator framework for parametric PDEs. Instead of pretraining a single large model on heterogeneous data, CompNO first learns a library of Foundation Blocks, where each block is a parametric Fourier neural operator specialized to a fundamental differential operator (e.g. convection, diffusion, nonlinear convection). These blocks are then assembled, via lightweight Adaptation Blocks, into task-specific solvers that approximate the temporal evolution operator for target PDEs. A dedicated boundary-condition operator further enforces Dirichlet constraints exactly at inference time. We validate CompNO on one-dimensional convection, diffusion, convection--diffusion and Burgers' equations from the PDEBench suite. The proposed framework achieves lower relative L2 error than strong baselines (PFNO, PDEFormer and in-context learning based models) on linear parametric systems, while remaining competitive on nonlinear Burgers' flows. The model maintains exact boundary satisfaction with zero loss at domain boundaries, and exhibits robust generalization across a broad range of Peclet and Reynolds numbers. These results demonstrate that compositional neural operators provide a scalable and physically interpretable pathway towards foundation models for PDEs. --- ### Learning Dynamic Collaborative Network for Semi-supervised 3D Vessel Segmentation Authors: Jiao Xu, Xin Chen, Lihe Zhang Published: 2026-01-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.07377v1 In this paper, we present a new dynamic collaborative network for semi-supervised 3D vessel segmentation, termed DiCo. Conventional mean teacher (MT) methods typically employ a static approach, where the roles of the teacher and student models are fixed. However, due to the complexity of 3D vessel data, the teacher model may not always outperform the student model, leading to cognitive biases that can limit performance. To address this issue, we propose a dynamic collaborative network that allows the two models to dynamically switch their teacher-student roles. Additionally, we introduce a multi-view integration module to capture various perspectives of the inputs, mirroring the way doctors conduct medical analysis. We also incorporate adversarial supervision to constrain the shape of the segmented vessels in unlabeled data. In this process, the 3D volume is projected into 2D views to mitigate the impact of label inconsistencies. Experiments demonstrate that our DiCo method sets new state-of-the-art performance on three 3D vessel segmentation benchmarks. The code repository address is https://github.com/xujiaommcome/DiCo --- ### OpenTinker: Separating Concerns in Agentic Reinforcement Learning Authors: Siqi Zhu, Jiaxuan You Published: 2026-01-12 Categories: cs.AI, cs.DC arXiv: https://arxiv.org/abs/2601.07376v2 We introduce \textsc{OpenTinker}, an open infrastructure for training large language model (LLM) agents with many LoRA-backed policies over shared execution resources. Modern agent workloads mix supervised fine-tuning (SFT), online reinforcement learning (RL), rollout generation, validation, and multi-turn environment interaction. In such workloads, LoRA adapters are not static inference artifacts: they are frequently updated policy states whose optimizer state, rollout snapshot, and training data attribution must remain consistent. \textsc{OpenTinker} centers the runtime around this policy lifecycle. Users define environments, agents, and learning objectives, while the system manages training clients, rollout samplers, checkpoint handles, and policy-version refresh. The same data path supports SFT and RL by converting trajectories into token sequences with explicit masks: context and environment observations condition the model, while generated action tokens carry supervised weights or RL advantages. This design enables multi-LoRA SFT/RL training in which many users, tasks, or agents can share a base model while keeping adapter updates, checkpoints, and rollout snapshots isolated. We describe the system architecture, the adapter lifecycle, the service-backed snapshot handoff used by the current implementation, the backend contract for mixed-adapter rollout kernels, and the training scheduler that isolates adapter-local gradients and optimizer state. Representative validation tasks exercise single-turn, multi-turn, LoRA, and multi-agent agentic training. --- ### GROKE: Vision-Free Navigation Instruction Evaluation via Graph Reasoning on OpenStreetMap Authors: Farzad Shami, Subhrasankha Dey, Nico Van de Weghe, Henrikki Tenkanen Published: 2026-01-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.07375v1 The evaluation of navigation instructions remains a persistent challenge in Vision-and-Language Navigation (VLN) research. Traditional reference-based metrics such as BLEU and ROUGE fail to capture the functional utility of spatial directives, specifically whether an instruction successfully guides a navigator to the intended destination. Although existing VLN agents could serve as evaluators, their reliance on high-fidelity visual simulators introduces licensing constraints and computational costs, and perception errors further confound linguistic quality assessment. This paper introduces GROKE(Graph-based Reasoning over OSM Knowledge for instruction Evaluation), a vision-free training-free hierarchical LLM-based framework for evaluating navigation instructions using OpenStreetMap data. Through systematic ablation studies, we demonstrate that structured JSON and textual formats for spatial information substantially outperform grid-based and visual graph representations. Our hierarchical architecture combines sub-instruction planning with topological graph navigation, reducing navigation error by 68.5% compared to heuristic and sampling baselines on the Map2Seq dataset. The agent's execution success, trajectory fidelity, and decision patterns serve as proxy metrics for functional navigability given OSM-visible landmarks and topology, establishing a scalable and interpretable evaluation paradigm without visual dependencies. Code and data are available at https://anonymous.4open.science/r/groke. --- ### Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models Authors: Xin Cheng, Rui Tian, Wangding Zeng, Damai Dai, Qinyu Chen, Bingxuan Wang, Zhenda Xie, Kezhao Huang, Xingkai Yu, Chengqi Deng, Shangyan Zhou, Chenggang Zhao et al. Published: 2026-01-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.07372v2 While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup, forcing them to inefficiently simulate retrieval through computation. To address this, we introduce conditional memory as a complementary sparsity axis, instantiated via Engram, a module that modernizes classic $N$-gram embedding for O(1) lookup. By formulating the Sparsity Allocation problem, we uncover a U-shaped scaling law that optimizes the trade-off between neural computation (MoE) and static memory (Engram). Guided by this law, we scale Engram to 27B parameters, achieving superior performance over a strictly iso-parameter and iso-FLOPs MoE baseline. Most notably, while the memory module is expected to aid knowledge retrieval (e.g., MMLU +3.4; CMMLU +4.0), we observe even larger gains in general reasoning (e.g., BBH +5.0; ARC-Challenge +3.7) and code/math domains~(HumanEval +3.0; MATH +2.4). Mechanistic analyses reveal that Engram relieves the backbone's early layers from static reconstruction, effectively deepening the network for complex reasoning. Furthermore, by delegating local dependencies to lookups, it frees up attention capacity for global context, substantially boosting long-context retrieval (e.g., Multi-Query NIAH: 84.2 to 97.0). Finally, Engram establishes infrastructure-aware efficiency: its deterministic addressing enables runtime prefetching from host memory, incurring negligible overhead. We envision conditional memory as an indispensable modeling primitive for next-generation sparse models. --- ### Interpretable Text Classification Applied to the Detection of LLM-generated Creative Writing Authors: Minerva Suvanto, Andrea McGlinchey, Mattias Wahde, Peter J Barclay Published: 2026-01-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.07368v1 We consider the problem of distinguishing human-written creative fiction (excerpts from novels) from similar text generated by an LLM. Our results show that, while human observers perform poorly (near chance levels) on this binary classification task, a variety of machine-learning models achieve accuracy in the range 0.93 - 0.98 over a previously unseen test set, even using only short samples and single-token (unigram) features. We therefore employ an inherently interpretable (linear) classifier (with a test accuracy of 0.98), in order to elucidate the underlying reasons for this high accuracy. In our analysis, we identify specific unigram features indicative of LLM-generated text, one of the most important being that the LLM tends to use a larger variety of synonyms, thereby skewing the probability distributions in a manner that is easy to detect for a machine learning classifier, yet very difficult for a human observer. Four additional explanation categories were also identified, namely, temporal drift, Americanisms, foreign language usage, and colloquialisms. As identification of the AI-generated text depends on a constellation of such features, the classification appears robust, and therefore not easy to circumvent by malicious actors intent on misrepresenting AI-generated text as human work. --- ### HiVid-Narrator: Hierarchical Video Narrative Generation with Scene-Primed ASR-anchored Compression Authors: Haoxuan Li, Mengyan Li, Junjun Zheng Published: 2026-01-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.07366v1 Generating structured narrations for real-world e-commerce videos requires models to perceive fine-grained visual details and organize them into coherent, high-level stories--capabilities that existing approaches struggle to unify. We introduce the E-commerce Hierarchical Video Captioning (E-HVC) dataset with dual-granularity, temporally grounded annotations: a Temporal Chain-of-Thought that anchors event-level observations and Chapter Summary that compose them into concise, story-centric summaries. Rather than directly prompting chapters, we adopt a staged construction that first gathers reliable linguistic and visual evidence via curated ASR and frame-level descriptions, then refines coarse annotations into precise chapter boundaries and titles conditioned on the Temporal Chain-of-Thought, yielding fact-grounded, time-aligned narratives. We also observe that e-commerce videos are fast-paced and information-dense, with visual tokens dominating the input sequence. To enable efficient training while reducing input tokens, we propose the Scene-Primed ASR-anchored Compressor (SPA-Compressor), which compresses multimodal tokens into hierarchical scene and event representations guided by ASR semantic cues. Built upon these designs, our HiVid-Narrator framework achieves superior narrative quality with fewer input tokens compared to existing methods. --- ### On the universal definition of intelligence Authors: Joseph Chen Published: 2026-01-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.07364v1 This paper aims to propose a universal definition of intelligence that enables fair and consistent comparison of human and artificial intelligence (AI). With the rapid development of AI technology in recent years, how to compare and evaluate human and AI intelligence has become an important theoretical issue. However, existing definitions of intelligence are anthropocentric and unsuitable for empirical comparison, resulting in a lack of consensus in the research field. This paper first introduces four criteria for evaluating intelligence definitions based on R. Carnap's methodology of conceptual clarification: similarity to explicandum, exactness, fruitfulness, and simplicity. We then examine six representative definitions: IQ testing, complex problem-solving ability, reward optimization, environmental adaptation, learning efficiency, and predictive ability, and clarify their theoretical strengths and limitations. The results show that while definitions based on predictive ability have high explanatory power and empirical feasibility, they suffer from an inability to adequately explain the relationship between predictions and behavior/benefits. This paper proposes the Extended Predictive Hypothesis (EPH), which views intelligence as a combination of the ability to accurately predict the future and the ability to benefit from those predictions. Furthermore, by distinguishing predictive ability into spontaneous and reactive predictions and adding the concept of gainability, we present a unified framework for explaining various aspects of intelligence, such as creativity, learning, and future planning. In conclusion, this paper argues that the EPH is the most satisfactory and universal definition for comparing human and AI intelligence. --- ### Seeing Right but Saying Wrong: Inter- and Intra-Layer Refinement in MLLMs without Training Authors: Shezheng Song, Shasha Li, Jie Yu Published: 2026-01-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.07359v1 Multimodal Large Language Models (MLLMs) have demonstrated strong capabilities across a variety of vision-language tasks. However, their internal reasoning often exhibits a critical inconsistency: although deeper layers may attend to the correct visual regions, final predictions are frequently misled by noisy attention from earlier layers. This results in a disconnect between what the model internally understands and what it ultimately expresses, a phenomenon we describe as seeing it right but saying it wrong. To address this issue, we propose DualPD, a dual-perspective decoding refinement strategy that enhances the visual understanding without any additional training. DualPD consists of two components. (1) The layer-wise attention-guided contrastive logits module captures how the belief in the correct answer evolves by comparing output logits between layers that exhibit the largest attention shift. (2) The head-wise information filtering module suppresses low-contribution attention heads that focus on irrelevant regions, thereby improving attention quality within each layer. Experiments conducted on both the LLaVA and Qwen-VL model families across multiple multimodal benchmarks demonstrate that DualPD consistently improves accuracy without training, confirming its effectiveness and generalizability. The code will be released upon publication. --- ### Efficient Convolutional Forward Model for Passive Acoustic Mapping and Temporal Monitoring Authors: Tatiana Gelvez-Barrera, Barbara Nicolas, Bruno Gilles, Adrian Basarab, Denis Kouamé Published: 2026-01-12 Categories: eess.IV, cs.AI arXiv: https://arxiv.org/abs/2601.07356v1 Passive acoustic mapping (PAM) is a key imaging technique for characterizing cavitation activity in therapeutic ultrasound applications. Recent model-based beamforming algorithms offer high reconstruction quality and strong physical interpretability. However, their computational burden and limited temporal resolution restrict their use in applications with time-evolving cavitation. To address these challenges, we introduce a PAM beamforming framework based on a novel convolutional formulation in the time domain, which enables efficient computation. In this framework, PAM is formulated as an inverse problem in which the forward operator maps spatiotemporal cavitation activity to recorded radio-frequency signals accounting for time-of-flight delays defined by the acquisition geometry. We then formulate a regularized inversion algorithm that incorporates prior knowledge on cavitation activity. Experimental results demonstrate that our framework outperforms classical beamforming methods, providing higher temporal resolution than frequency-domain techniques while substantially reducing computational burden compared with iterative time-domain formulations. --- ### Semantic Compression of LLM Instructions via Symbolic Metalanguages Authors: Ernst van Gassen Published: 2026-01-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.07354v1 We introduce MetaGlyph, a symbolic language for compressing prompts by encoding instructions as mathematical symbols rather than prose. Unlike systems requiring explicit decoding rules, MetaGlyph uses symbols like $\in$ (membership) and $\Rightarrow$ (implication) that models already understand from their training data. We test whether these symbols work as ''instruction shortcuts'' that models can interpret without additional teaching. We evaluate eight models across two dimensions relevant to practitioners: scale (3B-1T parameters) and accessibility (open-source for local deployment vs. proprietary APIs). MetaGlyph achieves 62-81% token reduction across all task types. For API-based deployments, this translates directly to cost savings; for local deployments, it reduces latency and memory pressure. Results vary by model. Gemini 2.5 Flash achieves 75% semantic equivalence between symbolic and prose instructions on selection tasks, with 49.9% membership operator fidelity. Kimi K2 reaches 98.1% fidelity for implication ($\Rightarrow$) and achieves perfect (100%) accuracy on selection tasks with symbolic prompts. GPT-5.2 Chat shows the highest membership fidelity observed (91.3%), though with variable parse success across task types. Claude Haiku 4.5 achieves 100% parse success with 26% membership fidelity. Among mid-sized models, Qwen 2.5 7B shows 62% equivalence on extraction tasks. Mid-sized open-source models (7B-12B) show near-zero operator fidelity, suggesting a U-shaped relationship where sufficient scale overcomes instruction-tuning biases. --- ### TALON: Confidence-Aware Speculative Decoding with Adaptive Token Trees Authors: Tianyu Liu, Qitan Lv, Yuhao Shen, Xiao Sun, Xiaoyan Sun Published: 2026-01-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.07353v1 Speculative decoding (SD) has become a standard technique for accelerating LLM inference without sacrificing output quality. Recent advances in speculative decoding have shifted from sequential chain-based drafting to tree-structured generation, where the draft model constructs a tree of candidate tokens to explore multiple possible drafts in parallel. However, existing tree-based SD methods typically build a fixed-width, fixed-depth draft tree, which fails to adapt to the varying difficulty of tokens and contexts. As a result, the draft model cannot dynamically adjust the tree structure to early stop on difficult tokens and extend generation for simple ones. To address these challenges, we introduce TALON, a training-free, budget-driven adaptive tree expansion framework that can be plugged into existing tree-based methods. Unlike static methods, TALON constructs the draft tree iteratively until a fixed token budget is met, using a hybrid expansion strategy that adaptively allocates the node budget to each layer of the draft tree. This framework naturally shapes the draft tree into a "deep-and-narrow" form for deterministic contexts and a "shallow-and-wide" form for uncertain branches, effectively optimizing the trade-off between exploration width and generation depth under a given budget. Extensive experiments across 5 models and 6 datasets demonstrate that TALON consistently outperforms state-of-the-art EAGLE-3, achieving up to 5.16x end-to-end speedup over auto-regressive decoding. --- ### Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models Authors: Linhao Zhong, Linyu Wu, Bozhen Fang, Tianjian Feng, Chenchen Jing, Wen Wang, Jiaheng Zhang, Hao Chen, Chunhua Shen Published: 2026-01-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.07351v2 Diffusion Language Models (DLMs) offer a promising alternative for language modeling by enabling parallel decoding through iterative refinement. However, most DLMs rely on hard binary masking and discrete token assignments, which hinder the revision of early decisions and underutilize intermediate probabilistic representations. In this paper, we propose EvoToken-DLM, a novel diffusion-based language modeling approach that replaces hard binary masks with evolving soft token distributions. EvoToken-DLM enables a progressive transition from masked states to discrete outputs, supporting revisable decoding. To effectively support this evolution, we introduce continuous trajectory supervision, which aligns training objectives with iterative probabilistic updates. Extensive experiments across multiple benchmarks show that EvoToken-DLM consistently achieves superior performance, outperforming strong diffusion-based and masked DLM baselines. Project webpage: https://aim-uofa.github.io/EvoTokenDLM. --- ### Reward Modeling from Natural Language Human Feedback Authors: Zongqi Wang, Rui Wang, Yuchuan Wu, Yiyao Yu, Pinyi Zhang, Shaoning Sun, Yujiu Yang, Yongbin Li Published: 2026-01-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.07349v3 Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs generate reasoning chains ending with critiques and preference labels, and RLVR then relies on the correctness of the preference labels as the training reward. However, in this paper, we demonstrate that such binary classification tasks make GRMs susceptible to guessing correct outcomes without sound critiques. Consequently, these spurious successes introduce substantial noise into the reward signal, thereby impairing the effectiveness of reinforcement learning. To address this issue, we propose Reward Modeling from Natural Language Human Feedback (RM-NLHF), which leverages natural language feedback to obtain process reward signals, thereby mitigating the problem of limited solution space inherent in binary tasks. Specifically, we compute the similarity between GRM-generated and human critiques as the training reward, which provides more accurate reward signals than outcome-only supervision. Additionally, considering that human critiques are difficult to scale up, we introduce Meta Reward Model (MetaRM) which learns to predict process reward from datasets with human critiques and then generalizes to data without human critiques. Experiments on multiple benchmarks demonstrate that our method consistently outperforms state-of-the-art GRMs trained with outcome-only reward, confirming the superiority of integrating natural language over binary human feedback as supervision. --- ### Controlled Self-Evolution for Algorithmic Code Optimization Authors: Tu Hu, Ronghao Chen, Shuo Zhang, Jianghao Yin, Mou Xiao Feng, Jingping Liu, Shaolei Zhang, Wenqi Jiang, Yuqi Fang, Sen Hu, Huacan Wang, Yi Xu Published: 2026-01-12 Categories: cs.CL, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2601.07348v5 Self-evolution methods enhance code generation through iterative "generate-verify-refine" cycles, yet existing approaches suffer from low exploration efficiency, failing to discover solutions with superior complexity within limited budgets. This inefficiency stems from initialization bias trapping evolution in poor solution regions, uncontrolled stochastic operations lacking feedback guidance, and insufficient experience utilization across tasks. To address these bottlenecks, we propose Controlled Self-Evolution (CSE), which consists of three key components. Diversified Planning Initialization generates structurally distinct algorithmic strategies for broad solution space coverage. Genetic Evolution replaces stochastic operations with feedback-guided mechanisms, enabling targeted mutation and compositional crossover. Hierarchical Evolution Memory captures both successful and failed experiences at inter-task and intra-task levels. Experiments on EffiBench-X demonstrate that CSE consistently outperforms all baselines across various LLM backbones. Furthermore, CSE achieves higher efficiency from early generations and maintains continuous improvement throughout evolution. Our code is publicly available at https://github.com/QuantaAlpha/EvoControl. --- ### DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models Authors: Shaokai He, Kaiwen Wei, Xinyi Zeng, Xiang Chen, Xue Yang, Zhenyang Li, Jiang Zhong, Yu Tian Published: 2026-01-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.07347v1 The "reversal curse" refers to the phenomenon where large language models (LLMs) exhibit predominantly unidirectional behavior when processing logically bidirectional relationships. Prior work attributed this to autoregressive training -- predicting the next token inherently favors left-to-right information flow over genuine bidirectional knowledge associations. However, we observe that Diffusion LLMs (DLLMs), despite being trained bidirectionally, also suffer from the reversal curse. To investigate the root causes, we conduct systematic experiments on DLLMs and identify three key reasons: 1) entity fragmentation during training, 2) data asymmetry, and 3) missing entity relations. Motivated by the analysis of these reasons, we propose Diffusion Entity-Relation Modeling (DiffER), which addresses the reversal curse through entity-aware training and balanced data construction. Specifically, DiffER introduces whole-entity masking, which mitigates entity fragmentation by predicting complete entities in a single step. DiffER further employs distribution-symmetric and relation-enhanced data construction strategies to alleviate data asymmetry and missing relations. Extensive experiments demonstrate that DiffER effectively alleviates the reversal curse in Diffusion LLMs, offering new perspectives for future research. --- ### PulseMind: A Multi-Modal Medical Model for Real-World Clinical Diagnosis Authors: Jiao Xu, Junwei Liu, Jiangwei Lao, Qi Zhu, Yunpeng Zhao, Congyun Jin, Shinan Liu, Zhihong Lu, Lihe Zhang, Xin Chen, Jian Wang, Ping Wang Published: 2026-01-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.07344v1 Recent advances in medical multi-modal models focus on specialized image analysis like dermatology, pathology, or radiology. However, they do not fully capture the complexity of real-world clinical diagnostics, which involve heterogeneous inputs and require ongoing contextual understanding during patient-physician interactions. To bridge this gap, we introduce PulseMind, a new family of multi-modal diagnostic models that integrates a systematically curated dataset, a comprehensive evaluation benchmark, and a tailored training framework. Specifically, we first construct a diagnostic dataset, MediScope, which comprises 98,000 real-world multi-turn consultations and 601,500 medical images, spanning over 10 major clinical departments and more than 200 sub-specialties. Then, to better reflect the requirements of real-world clinical diagnosis, we develop the PulseMind Benchmark, a multi-turn diagnostic consultation benchmark with a four-dimensional evaluation protocol comprising proactiveness, accuracy, usefulness, and language quality. Finally, we design a training framework tailored for multi-modal clinical diagnostics, centered around a core component named Comparison-based Reinforcement Policy Optimization (CRPO). Compared to absolute score rewards, CRPO uses relative preference signals from multi-dimensional com-parisons to provide stable and human-aligned training guidance. Extensive experiments demonstrate that PulseMind achieves competitive performance on both the diagnostic consultation benchmark and public medical benchmarks. --- ### Agentic Diagnostic Reasoning over Telecom and Datacenter Infrastructure Authors: Nicolas Tacheny Published: 2026-01-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.07342v1 Large-scale telecom and datacenter infrastructures rely on multi-layered service and resource models, where failures propagate across physical and logical components and affect multiple customers. Traditional approaches to root cause analysis(RCA) rely on hard-coded graph traversal algorithms or rule-based correlation engines, which are costly to maintain and tightly coupled to the infrastructure model. In this work, we introduce an agentic diagnostic framework where a Large Language Model (LLM) performs step-wise investigation using a constrained tool space exposed through the Model Context Protocol (MCP). Instead of embedding causal logic or traversal algorithms into the application, the agent autonomously navigates the infrastructure model by invoking tools for service lookup, dependency retrieval, structured and unstructured data, and event analysis, and impact discovery. We define an investigation protocol that structures the agent's reasoning and ensures grounding, reproducibility, and safe handling of missing or ambiguous information. This work lays the foundation for autonomous incident resolution and change impact mitigation. Future systems will not only diagnose and remediate infrastructure failures, but also predict the impact of planned changes on services and customers, enabling operators to mitigate risks before executing maintenance operations. --- ### Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation Authors: Yanzhi Tian, Cunxiang Wang, Zeming Liu, Heyan Huang, Wenbo Yu, Dawei Song, Jie Tang, Yuhang Guo Published: 2026-01-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.07338v2 Large Language Models (LLMs) have significantly advanced Machine Translation (MT), applying them to linguistically complex domains-such as Social Network Services, literature etc. In these scenarios, translations often require handling non-literal expressions, leading to the inaccuracy of MT metrics. To systematically investigate the reliability of MT metrics, we first curate a meta-evaluation dataset focused on non-literal translations, namely MENT. MENT encompasses four non-literal translation domains and features source sentences paired with translations from diverse MT systems, with 7,530 human-annotated scores on translation quality. Experimental results reveal the inaccuracies of traditional MT metrics and the limitations of LLM-as-a-Judge, particularly the knowledge cutoff and score inconsistency problem. To mitigate these limitations, we propose RATE, a novel agentic translation evaluation framework, centered by a reflective Core Agent that dynamically invokes specialized sub-agents. Experimental results indicate the efficacy of RATE, achieving an improvement of at least 3.2 points in combined system- and segment-level correlation with human judgments compared with current methods. Further experiments demonstrate the robustness of RATE to general-domain MT evaluation. Code and dataset are available at: https://github.com/BITHLP/RATE. --- ### Reconstruction Guided Few-shot Network For Remote Sensing Image Classification Authors: Mohit Jaiswal, Naman Jain, Shivani Pathak, Mainak Singha, Nikunja Bihari Kar, Ankit Jha, Biplab Banerjee Published: 2026-01-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.07335v1 Few-shot remote sensing image classification is challenging due to limited labeled samples and high variability in land-cover types. We propose a reconstruction-guided few-shot network (RGFS-Net) that enhances generalization to unseen classes while preserving consistency for seen categories. Our method incorporates a masked image reconstruction task, where parts of the input are occluded and reconstructed to encourage semantically rich feature learning. This auxiliary task strengthens spatial understanding and improves class discrimination under low-data settings. We evaluated the efficacy of EuroSAT and PatternNet datasets under 1-shot and 5-shot protocols, our approach consistently outperforms existing baselines. The proposed method is simple, effective, and compatible with standard backbones, offering a robust solution for few-shot remote sensing classification. Codes are available at https://github.com/stark0908/RGFS. --- ### OSCAR: Open-Set CAD Retrieval from a Language Prompt and a Single Image Authors: Tessa Pulli, Jean-Baptiste Weibel, Peter Hönig, Matthias Hirschmanner, Markus Vincze, Andreas Holzinger Published: 2026-01-12 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2601.07333v1 6D object pose estimation plays a crucial role in scene understanding for applications such as robotics and augmented reality. To support the needs of ever-changing object sets in such context, modern zero-shot object pose estimators were developed to not require object-specific training but only rely on CAD models. Such models are hard to obtain once deployed, and a continuously changing and growing set of objects makes it harder to reliably identify the instance model of interest. To address this challenge, we introduce an Open-Set CAD Retrieval from a Language Prompt and a Single Image (OSCAR), a novel training-free method that retrieves a matching object model from an unlabeled 3D object database. During onboarding, OSCAR generates multi-view renderings of database models and annotates them with descriptive captions using an image captioning model. At inference, GroundedSAM detects the queried object in the input image, and multi-modal embeddings are computed for both the Region-of-Interest and the database captions. OSCAR employs a two-stage retrieval: text-based filtering using CLIP identifies candidate models, followed by image-based refinement using DINOv2 to select the most visually similar object. In our experiments we demonstrate that OSCAR outperforms all state-of-the-art methods on the cross-domain 3D model retrieval benchmark MI3DOR. Furthermore, we demonstrate OSCAR's direct applicability in automating object model sourcing for 6D object pose estimation. We propose using the most similar object model for pose estimation if the exact instance is not available and show that OSCAR achieves an average precision of 90.48\% during object retrieval on the YCB-V object dataset. Moreover, we demonstrate that the most similar object model can be utilized for pose estimation using Megapose achieving better results than a reconstruction-based approach. --- ### SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models Authors: Yuanhe Zhang, Jiayu Tian, Yibo Zhang, Shilinlu Yan, Liang Lin, Zhenhong Zhou, Li Sun, Sen Su Published: 2026-01-12 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2601.07331v1 Large Audio Language Models (LALMs) have been widely applied in real-time scenarios, such as in-car assistants and online meeting comprehension. In practice, audio inputs are often corrupted by device and environmental noise, leading to performance degradation. However, existing LALM studies on noise lack quantitative analysis and rely mainly on intuition and empirical observation, thus failing to understand practical robustness. To address this issue, we introduce Signal Embedding Energy (SEE), a method for quantifying the impact of noise intensity on LALM inputs, enabling the differentiation of LALM robustness in real-world deployments. SEE introduces a perspective based on structured activation subspaces derived from the model's internal representations, which more accurately captures its perception of noise than raw audio features. Across experiments, SEE exhibits a strong correlation with LALM performance, achieving a correlation of 0.98. Surprisingly, traditional audio denoising methods are only marginally effective for LALMs, and, in some cases, even increase SEE and impair performance. This suggests a mismatch between speech-centric denoising objectives and the noise sensitivity of modern LALMs. Therefore, we propose a mitigation strategy derived from SEE to denoise LALM inputs, outperforming existing denoising methods. This paper introduces a novel metric for noise quantification in LALMs, providing guidance for robustness improvements in real-world deployments. --- ### BayesRAG: Probabilistic Mutual Evidence Corroboration for Multimodal Retrieval-Augmented Generation Authors: Xuan Li, Yining Wang, Haocai Luo, Shengping Liu, Jerry Liang, Ying Fu, Weihuang, Jun Yu, Junnan Zhu Published: 2026-01-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.07329v1 Retrieval-Augmented Generation (RAG) has become a pivotal paradigm for Large Language Models (LLMs), yet current approaches struggle with visually rich documents by treating text and images as isolated retrieval targets. Existing methods relying solely on cosine similarity often fail to capture the semantic reinforcement provided by cross-modal alignment and layout-induced coherence. To address these limitations, we propose BayesRAG, a novel multimodal retrieval framework grounded in Bayesian inference and Dempster-Shafer evidence theory. Unlike traditional approaches that rank candidates strictly by similarity, BayesRAG models the intrinsic consistency of retrieved candidates across modalities as probabilistic evidence to refine retrieval confidence. Specifically, our method computes the posterior association probability for combinations of multimodal retrieval results, prioritizing text-image pairs that mutually corroborate each other in terms of both semantics and layout. Extensive experiments demonstrate that BayesRAG significantly outperforms state-of-the-art (SOTA) methods on challenging multimodal benchmarks. This study establishes a new paradigm for multimodal retrieval fusion that effectively resolves the isolation of heterogeneous modalities through an evidence fusion mechanism and enhances the robustness of retrieval outcomes. Our code is available at https://github.com/TioeAre/BayesRAG. --- ### How to predict creativity ratings from written narratives: A comparison of co-occurrence and textual forma mentis networks Authors: Roberto Passaro, Edith Haim, Massimo Stella Published: 2026-01-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.07327v1 This tutorial paper provides a step-by-step workflow for building and analysing semantic networks from short creative texts. We introduce and compare two widely used text-to-network approaches: word co-occurrence networks and textual forma mentis networks (TFMNs). We also demonstrate how they can be used in machine learning to predict human creativity ratings. Using a corpus of 1029 short stories, we guide readers through text preprocessing, network construction, feature extraction (structural measures, spreading-activation indices, and emotion scores), and application of regression models. We evaluate how network-construction choices influence both network topology and predictive performance. Across all modelling settings, TFMNs consistently outperformed co-occurrence networks through lower prediction errors (best MAE = 0.581 for TFMN, vs 0.592 for co-occurrence with window size 3). Network-structural features dominated predictive performance (MAE = 0.591 for TFMN), whereas emotion features performed worse (MAE = 0.711 for TFMN) and spreading-activation measures contributed little (MAE = 0.788 for TFMN). This paper offers practical guidance for researchers interested in applying network-based methods for cognitive fields like creativity research. we show when syntactic networks are preferable to surface co-occurrence models, and provide an open, reproducible workflow accessible to newcomers in the field, while also offering deeper methodological insight for experienced researchers. --- ### Convergence Rate Analysis of the AdamW-style Shampoo: Unifying One-Sided and Two-Sided Preconditioning Authors: Huan Li, Yiming Dong, Zhouchen Lin Published: 2026-01-12 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2601.07326v4 This paper studies AdamW-style Shampoo, an effective variant of the classical Shampoo that won the external tuning track of the AlgoPerf neural network training competition. Our analysis unifies one-sided and two-sided preconditioning. When the exponents of the two preconditioners sum to $1/2$, we establish the convergence rate $\frac{1}{K}\sum_{k=1}^KE\left(||\nabla f(X_k)||_*\right)\leq O(\frac{\sqrt{m+n}C}{K^{1/4}})$, where $K$ represents the number of iterations, $(m,n)$ denotes the dimensions of the matrix-valued parameters, and $C$ matches the constant appearing in the optimal convergence rate of SGD. Theoretically, the nuclear norm and Frobenius norm satisfy $||\nabla f(X)||_F\leq ||\nabla f(X)||_*\leq \sqrt{\min\{m,n\}}||\nabla f(X)||_F$, which suggests that our convergence rate is analogous to the optimal $\frac{1}{K}\sum_{k=1}^KE\left(||\nabla f(X_k)||_F\right)\leq O(\frac{C}{K^{1/4}})$ convergence rate of SGD in the ideal case where $||\nabla f(X)||_*= Θ(\sqrt{\min\{m,n\}})||\nabla f(X)||_F$ and $m$ and $n$ are of comparable magnitude. Then, we extend our analysis to settings where the preconditioning exponents do not sum to 1/2, and establish convergence with an explicit but more involved rate. --- ### Robust Bayesian Inference via Variational Approximations of Generalized Rho-Posteriors Authors: EL Mahdi Khribch, Pierre Alquier Published: 2026-01-12 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2601.07325v2 We introduce the $\widetildeρ$-posterior, a modified version of the $ρ$-posterior, obtained by replacing the supremum over competitor parameters with a softmax aggregation. This modification allows a PAC-Bayesian analysis of the $\widetildeρ$-posterior. This yields finite-sample oracle inequalities with explicit convergence rates that inherit the key robustness properties of the original framework, in particular, graceful degradation under model misspecification and data contamination. Crucially, the PAC-Bayesian oracle inequalities extend to variational approximations of the $\widetildeρ$-posterior, providing theoretical guarantees for tractable inference. Numerical experiments on exponential families, regression, and real-world datasets confirm that the resulting variational procedures achieve robustness competitive with theoretical predictions at computational cost comparable to standard variational Bayes. --- ### Segmental Advantage Estimation: Enhancing PPO for Long-Context LLM Training Authors: Xue Gong, Qi Yi, Ziyuan Nan, Guanhua Huang, Kejiao Li, Yuhao Jiang, Ruibin Xiong, Zenan Xu, Jiaming Guo, Shaohui Peng, Bo Zhou Published: 2026-01-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.07320v1 Training Large Language Models (LLMs) for reasoning tasks is increasingly driven by Reinforcement Learning with Verifiable Rewards (RLVR), where Proximal Policy Optimization (PPO) provides a principled framework for stable policy updates. However, the practical application of PPO is hindered by unreliable advantage estimation in the sparse-reward RLVR regime. This issue arises because the sparse rewards in RLVR lead to inaccurate intermediate value predictions, which in turn introduce significant bias when aggregated at every token by Generalized Advantage Estimation (GAE). To address this, we introduce Segmental Advantage Estimation (SAE), which mitigates the bias that GAE can incur in RLVR. Our key insight is that aggregating $n$-step advantages at every token(as in GAE) is unnecessary and often introduces excessive bias, since individual tokens carry minimal information. Instead, SAE first partitions the generated sequence into coherent sub-segments using low-probability tokens as heuristic boundaries. It then selectively computes variance-reduced advantage estimates only from these information-rich segment transitions, effectively filtering out noise from intermediate tokens. Our experiments demonstrate that SAE achieves superior performance, with marked improvements in final scores, training stability, and sample efficiency. These gains are shown to be consistent across multiple model sizes, and a correlation analysis confirms that our proposed advantage estimator achieves a higher correlation with an approximate ground-truth advantage, justifying its superior performance. --- ### BEAT-Net: Injecting Biomimetic Spatio-Temporal Priors for Interpretable ECG Diagnosis Authors: Runze Ma, Haonan Lyu, Shunbo Jia, Qiang Yang, Muzi Xu, Jiaqi Zhang, Zihe Luo, Caizhi Liao Published: 2026-01-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.07316v2 Automated electrocardiogram diagnosis using deep learning remains limited by signal-agnostic representations that treat multi-lead recordings as undifferentiated time-series or images, forcing models to rediscover physiological structure implicitly. This leads to data inefficiency, poor generalization, and opaque decision boundaries misaligned with clinical reasoning. We present BEAT-Net, a supervised biomimetic framework that integrates QRS-centered biological tokenization with a hierarchical architecture mirroring the cardiologist's workflow. A QRS tokenizer converts continuous signals into semantically complete heartbeat sequences, which are processed through four specialized stages: morphological feature extraction via a Word Encoder, lead-invariant normalization through a Spatial Operator, temporal context injection by a Temporal Operator, and global reasoning using a Transformer-based Sentence Encoder. Evaluated across three large-scale benchmarks including PTB-XL, CPSC2018, and CSN, BEAT-Net achieves diagnostic accuracy of 0.924 AUC, comparable to dominant CNN baselines at 0.925 AUC, while reducing parameters by 95 percent from 2.06 million to 0.7 million. Critically, BEAT-Net surpasses the 39.5-million-parameter foundation model HeartLang on morphological Form classification, reaching 0.901 AUC compared to HeartLang's 0.832 AUC, while attaining full CNN-level performance using only 35 percent of training data and exhibiting superior cross-dataset generalization. Learned attention patterns spontaneously align with established clinical heuristics, demonstrating that explicit physiological structure provides a more efficient and interpretable alternative to massive pre-training for clinical deployment. --- ### VLM-CAD: VLM-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing Authors: Guanyuan Pan, Shuai Wang, Yugui Lin, Tiansheng Zhou, Pietro Liò, Zhenxin Zhao, Yaqi Wang Published: 2026-01-12 Categories: cs.MA, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2601.07315v5 Vision Language Models (VLMs) have demonstrated remarkable potential in multimodal reasoning. However, they can have spatial blindness and logical hallucinations when interpreting densely structured engineering content, such as analog circuit schematics. To address these challenges, we propose a Vision Language Model-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing (VLM-CAD) designed to support step-by-step reasoning over multimodal evidence. VLM-CAD bridges the modality gap by integrating a neuro-symbolic structural parsing module, Image2Net, which transforms raw pixels into explicit topological graphs and structured JSON representations to anchor VLM interpretation in deterministic facts. To ensure the reliability required for engineering decisions, we further propose ExTuRBO, an Explainable Trust Region Bayesian Optimization method. ExTuRBO employs agent-generated semantic seeds to warm-start local searches and uses Automatic Relevance Determination to provide sensitivity evidence for the final design report. Experimental results on 12 sizing tasks covering six circuits and four technology platforms show that VLM-CAD achieves a pooled Strict Pass@1 of 23.3% and a Relaxed Pass@1 of 91.7%, while providing sensitivity evidence for final design reports. --- ### Mitrasamgraha: A Comprehensive Classical Sanskrit Machine Translation Dataset Authors: Sebastian Nehrdich, David Allport, Sven Sellmer, Jivnesh Sandhan, Manoj Balaji Jagadeeshan, Pawan Goyal, Sujeet Kumar, Kurt Keutzer Published: 2026-01-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.07314v1 While machine translation is regarded as a "solved problem" for many high-resource languages, close analysis quickly reveals that this is not the case for content that shows challenges such as poetic language, philosophical concepts, multi-layered metaphorical expressions, and more. Sanskrit literature is a prime example of this, as it combines a large number of such challenges in addition to inherent linguistic features like sandhi, compounding, and heavy morphology, which further complicate NLP downstream tasks. It spans multiple millennia of text production time as well as a large breadth of different domains, ranging from ritual formulas via epic narratives, philosophical treatises, poetic verses up to scientific material. As of now, there is a strong lack of publicly available resources that cover these different domains and temporal layers of Sanskrit. We therefore introduce Mitrasamgraha, a high-quality Sanskrit-to-English machine translation dataset consisting of 391,548 bitext pairs, more than four times larger than the largest previously available Sanskrit dataset Itih=asa. It covers a time period of more than three millennia and a broad range of historical Sanskrit domains. In contrast to web-crawled datasets, the temporal and domain annotation of this dataset enables fine-grained study of domain and time period effects on MT performance. We also release a validation set consisting of 5,587 and a test set consisting of 5,552 post-corrected bitext pairs. We conduct experiments benchmarking commercial and open models on this dataset and fine-tune NLLB and Gemma models on the dataset, showing significant improvements, while still recognizing significant challenges in the translation of complex compounds, philosophical concepts, and multi-layered metaphors. We also analyze how in-context learning on this dataset impacts the performance of commercial models --- ### Explaining Machine Learning Predictive Models through Conditional Expectation Methods Authors: Silvia Ruiz-España, Laura Arnal, François Signol, Juan-Carlos Perez-Cortes, Joaquim Arlandis Published: 2026-01-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.07313v1 The rapid adoption of complex Artificial Intelligence (AI) and Machine Learning (ML) models has led to their characterization as black boxes due to the difficulty of explaining their internal decision-making processes. This lack of transparency hinders users' ability to understand, validate and trust model behavior, particularly in high-risk applications. Although explainable AI (XAI) has made significant progress, there remains a need for versatile and effective techniques to address increasingly complex models. This work introduces Multivariate Conditional Expectation (MUCE), a model-agnostic method for local explainability designed to capture prediction changes from feature interactions. MUCE extends Individual Conditional Expectation (ICE) by exploring a multivariate grid of values in the neighborhood of a given observation at inference time, providing graphical explanations that illustrate the local evolution of model predictions. In addition, two quantitative indices, stability and uncertainty, summarize local behavior and assess model reliability. Uncertainty is further decomposed into uncertainty+ and uncertainty- to capture asymmetric effects that global measures may overlook. The proposed method is validated using XGBoost models trained on three datasets: two synthetic (2D and 3D) to evaluate behavior near decision boundaries, and one transformed real-world dataset to test adaptability to heterogeneous feature types. Results show that MUCE effectively captures complex local model behavior, while the stability and uncertainty indices provide meaningful insight into prediction confidence. MUCE, together with the ICE modification and the proposed indices, offers a practical contribution to local explainability, enabling both graphical and quantitative insights that enhance the interpretability of predictive models and support more trustworthy and transparent decision-making. --- ### PsyCLIENT: Client Simulation via Conversational Trajectory Modeling for Trainee Practice and Model Evaluation in Mental Health Counseling Authors: Huachuan Qiu, Zhaoming Chen, Yuqian Chen, Yuan Xie, Yu Lu, Zhenzhong Lan Published: 2026-01-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.07312v2 LLM-based client simulation provides a scalable approach to novice counselor training, counseling-dialogue synthesis, and interactive evaluation of automated counseling systems. However, existing approaches are limited by insufficient profile diversity, weak behavioral grounding, and the lack of open Chinese-language resources for simulated counseling clients. We propose PsyCLIENT, a framework that conditions simulated-client responses on client profiles, dialogue histories, and conversational trajectories specifying target behaviors and content constraints at each client turn. We also construct PsyCLIENT-CP, a dataset of 120 Chinese client profiles spanning 60 counseling topics. Evaluations involving 24 professional counselors show that PsyCLIENT receives higher ratings of perceived authenticity and training utility than the comparison methods. In a separate source-identification study, PsyCLIENT dialogues were more frequently misclassified as human-client interactions than those generated by the baselines. These results suggest that conversational trajectory modeling can transform static client profiles into behavior-guided, dynamically unfolding counseling interactions. --- ### Revisiting the Ordering of Channel and Spatial Attention: A Comprehensive Study on Sequential and Parallel Designs Authors: Zhongming Liu, Bingbing Jiang Published: 2026-01-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.07310v2 Attention mechanisms have become a core component of deep learning models, with Channel Attention and Spatial Attention being the two most representative architectures. Current research on their fusion strategies primarily bifurcates into sequential and parallel paradigms, yet the selection process remains largely empirical, lacking systematic analysis and unified principles. We systematically compare channel-spatial attention combinations under a unified framework, building an evaluation suite of 18 topologies across four classes: sequential, parallel, multi-scale, and residual. Across two vision and nine medical datasets, we uncover a "data scale-method-performance" coupling law: (1) in few-shot tasks, the "Channel-Multi-scale Spatial" cascaded structure achieves optimal performance; (2) in medium-scale tasks, parallel learnable fusion architectures demonstrate superior results; (3) in large-scale tasks, parallel structures with dynamic gating yield the best performance. Additionally, experiments indicate that the "Spatial-Channel" order is more stable and effective for fine-grained classification, while residual connections mitigate vanishing gradient problems across varying data scales. We thus propose scenario-based guidelines for building future attention modules. Code is open-sourced at https://github.com/DWlzm. --- ### ARM: Role-Conditioned Neuron Transplantation for Training-Free Generalist LLM Agent Merging Authors: Zhuoka Feng, Kang Chen, Sihan Zhao, Kai Xiong, Yaoning Wang, Minshen Yu, Junjie Nian, Changyi Xiao, Yixin Cao, Yugang Jiang Published: 2026-01-12 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.07309v1 Interactive large language model agents have advanced rapidly, but most remain specialized to a single environment and fail to adapt robustly to other environments. Model merging offers a training-free alternative by integrating multiple experts into a single model. In this paper, we propose Agent-Role Merging (ARM), an activation-guided, role-conditioned neuron transplantation method for model merging in LLM agents. ARM improves existing merging methods from static natural language tasks to multi-turn agent scenarios, and over the generalization ability across various interactive environments. This is achieved with a well designed 3-step framework: 1) constructing merged backbones, 2) selection based on its role-conditioned activation analysis, and 3) neuron transplantation for fine-grained refinements. Without gradient-based optimization, ARM improves cross-benchmark generalization while enjoying efficiency. Across diverse domains, the model obtained via ARM merging outperforms prior model merging methods and domain-specific expert models, while demonstrating strong out-of-domain generalization. --- ### Heterogeneous Multi-Expert Reinforcement Learning for Long-Horizon Multi-Goal Tasks in Autonomous Forklifts Authors: Yun Chen, Bowei Huang, Fan Guo, Kang Song Published: 2026-01-12 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2601.07304v1 Autonomous mobile manipulation in unstructured warehouses requires a balance between efficient large-scale navigation and high-precision object interaction. Traditional end-to-end learning approaches often struggle to handle the conflicting demands of these distinct phases. Navigation relies on robust decision-making over large spaces, while manipulation needs high sensitivity to fine local details. Forcing a single network to learn these different objectives simultaneously often causes optimization interference, where improving one task degrades the other. To address these limitations, we propose a Heterogeneous Multi-Expert Reinforcement Learning (HMER) framework tailored for autonomous forklifts. HMER decomposes long-horizon tasks into specialized sub-policies controlled by a Semantic Task Planner. This structure separates macro-level navigation from micro-level manipulation, allowing each expert to focus on its specific action space without interference. The planner coordinates the sequential execution of these experts, bridging the gap between task planning and continuous control. Furthermore, to solve the problem of sparse exploration, we introduce a Hybrid Imitation-Reinforcement Training Strategy. This method uses expert demonstrations to initialize the policy and Reinforcement Learning for fine-tuning. Experiments in Gazebo simulations show that HMER significantly outperforms sequential and end-to-end baselines. Our method achieves a task success rate of 94.2\% (compared to 62.5\% for baselines), reduces operation time by 21.4\%, and maintains placement error within 1.5 cm, validating its efficacy for precise material handling. --- ### Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding Authors: Jianghao Yin, Qingbin Li, Kun Sun, Cheng Ding, Jie Wang, Qin Chen, Jie Zhou, Nan Wang, Changqing Li, Pei Wu, Jian Xu, Zheming Yang et al. Published: 2026-01-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.07298v2 While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex inter-relationships between images and scattered critical information across image sets. Inspired by human cognitive processes, we propose a Cognition-Inspired Meta-Action Framework (CINEMA), which decomposes multi-image reasoning into five structured meta-actions: Global, Focus, Hint, Think, and Answer, explicitly modeling the sequential cognitive steps humans naturally employ. For cold-start training, we introduce a Retrieval-Based Tree Sampling strategy that generates high-quality meta-action trajectories to bootstrap the model with reasoning patterns. During reinforcement learning, we adopt a two-stage paradigm: an exploration phase with Diversity-Preserving Strategy to avoid entropy collapse, followed by an annealed exploitation phase with DAPO to gradually strengthen exploitation. To train our model, we construct a dataset of 56k cold-start and 58k reinforcement learning instances spanning multi-image, multi-frame, and single-image tasks. We conduct extensive evaluations on multi-image reasoning benchmarks, video understanding benchmarks, and single-image benchmarks, achieving competitive state-of-the-art performance on several key benchmarks. Our model surpasses GPT-4o on the MUIR and MVMath benchmarks and notably outperforms specialized video reasoning models on video understanding benchmarks, demonstrating the effectiveness and generalizability of our human cognition-inspired reasoning framework. --- ### LRAS: Advanced Legal Reasoning with Agentic Search Authors: Yujin Zhou, Chuxue Cao, Jinluan Yang, Lijun Wu, Conghui He, Sirui Han, Yike Guo Published: 2026-01-12 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.07296v1 While Large Reasoning Models (LRMs) have demonstrated exceptional logical capabilities in mathematical domains, their application to the legal field remains hindered by the strict requirements for procedural rigor and adherence to legal logic. Existing legal LLMs, which rely on "closed-loop reasoning" derived solely from internal parametric knowledge, frequently suffer from lack of self-awareness regarding their knowledge boundaries, leading to confident yet incorrect conclusions. To address this challenge, we present Legal Reasoning with Agentic Search (LRAS), the first framework designed to transition legal LLMs from static and parametric "closed-loop thinking" to dynamic and interactive "Active Inquiry". By integrating Introspective Imitation Learning and Difficulty-aware Reinforcement Learning, LRAS enables LRMs to identify knowledge boundaries and handle legal reasoning complexity. Empirical results demonstrate that LRAS outperforms state-of-the-art baselines by 8.2-32\%, with the most substantial gains observed in tasks requiring deep reasoning with reliable knowledge. We will release our data and models for further exploration soon. --- ### Inference-Time Scaling for Visual AutoRegressive modeling by Searching Representative Samples Authors: Weidong Tang, Xinyan Wan, Siyu Li, Xiumei Wang Published: 2026-01-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.07293v1 While inference-time scaling has significantly enhanced generative quality in large language and diffusion models, its application to vector-quantized (VQ) visual autoregressive modeling (VAR) remains unexplored. We introduce VAR-Scaling, the first general framework for inference-time scaling in VAR, addressing the critical challenge of discrete latent spaces that prohibit continuous path search. We find that VAR scales exhibit two distinct pattern types: general patterns and specific patterns, where later-stage specific patterns conditionally optimize early-stage general patterns. To overcome the discrete latent space barrier in VQ models, we map sampling spaces to quasi-continuous feature spaces via kernel density estimation (KDE), where high-density samples approximate stable, high-quality solutions. This transformation enables effective navigation of sampling distributions. We propose a density-adaptive hybrid sampling strategy: Top-k sampling focuses on high-density regions to preserve quality near distribution modes, while Random-k sampling explores low-density areas to maintain diversity and prevent premature convergence. Consequently, VAR-Scaling optimizes sample fidelity at critical scales to enhance output quality. Experiments in class-conditional and text-to-image evaluations demonstrate significant improvements in inference process. The code is available at https://github.com/WD7ang/VAR-Scaling. --- ### Photometric Redshift Estimation Using Scaled Ensemble Learning Authors: Swagata Biswas, Shubhrangshu Ghosh, Avyarthana Ghosh, Yogesh Wadadekar, Abhishek Roy Choudhury, Arijit Mukherjee, Shailesh Deshpande, Arpan Pal Published: 2026-01-12 Categories: astro-ph.GA, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.07292v1 The development of the state-of-the-art telescopic systems capable of performing expansive sky surveys such as the Sloan Digital Sky Survey, Euclid, and the Rubin Observatory's Legacy Survey of Space and Time (LSST) has significantly advanced efforts to refine cosmological models. These advances offer deeper insight into persistent challenges in astrophysics and our understanding of the Universe's evolution. A critical component of this progress is the reliable estimation of photometric redshifts (Pz). To improve the precision and efficiency of such estimations, the application of machine learning (ML) techniques to large-scale astronomical datasets has become essential. This study presents a new ensemble-based ML framework aimed at predicting Pz for faint galaxies and higher redshift ranges, relying solely on optical (grizy) photometric data. The proposed architecture integrates several learning algorithms, including gradient boosting machine, extreme gradient boosting, k-nearest neighbors, and artificial neural networks, within a scaled ensemble structure. By using bagged input data, the ensemble approach delivers improved predictive performance compared to stand-alone models. The framework demonstrates consistent accuracy in estimating redshifts, maintaining strong performance up to z ~ 4. The model is validated using publicly available data from the Hyper Suprime-Cam Strategic Survey Program by the Subaru Telescope. Our results show marked improvements in the precision and reliability of Pz estimation. Furthermore, this approach closely adheres to-and in certain instances exceeds-the benchmarks specified in the LSST Science Requirements Document. Evaluation metrics include catastrophic outlier, bias, and rms. ---