# Research Papers — 2026-01 · bundle page 27 of 189

> Full-text markdown of papers #1301–1350 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/27
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/26.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/28.md)

### Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration

Authors: Luwei Tu, Jiawei Wu, Xing Luo, Zhi Jin
Published: 2026-01-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.21592v2

All-in-One Image Restoration (AiOIR) faces the fundamental challenge in reconciling conflicting optimization objectives across heterogeneous degradations. Existing methods are often constrained by coarse-grained control mechanisms or fixed mapping schedules, yielding suboptimal adaptation. To address this, we propose an Uncertainty-Aware Diffusion Bridge Model (UDBM), which innovatively reformulates AiOIR as a stochastic transport problem steered by pixel-wise uncertainty. By introducing a relaxed diffusion bridge formulation which replaces the strict terminal constraint with a relaxed constraint, we model the uncertainty of degradations while theoretically resolving the drift singularity inherent in standard diffusion bridges. Furthermore, we devise a dual modulation strategy: the noise schedule aligns diverse degradations into a shared high-entropy latent space, while the path schedule adaptively regulates the transport trajectory motivated by the viscous dynamics of entropy regularization. By effectively rectifying the transport geometry and dynamics, UDBM achieves state-of-the-art performance across diverse restoration tasks within a single inference step.

---

### Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening

Authors: Xiaotong Ji, Rasul Tutunov, Matthieu Zimmer, Haitham Bou Ammar
Published: 2026-01-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.21590v1

Reinforcement learning (RL) post-training is a dominant approach for improving the reasoning performance of large language models (LLMs), yet growing evidence suggests that its gains arise primarily from distribution sharpening rather than the acquisition of new capabilities. Recent work has shown that sampling from the power distribution of LLMs using Markov chain Monte Carlo (MCMC) can recover performance comparable to RL post-training without relying on external rewards; however, the high computational cost of MCMC makes such approaches impractical for widespread adoption. In this work, we propose a theoretically grounded alternative that eliminates the need for iterative MCMC. We derive a novel formulation showing that the global power distribution can be approximated by a token-level scaled low-temperature one, where the scaling factor captures future trajectory quality. Leveraging this insight, we introduce a training-free and verifier-free algorithm that sharpens the base model's generative distribution autoregressively. Empirically, we evaluate our method on math, QA, and code tasks across four LLMs, and show that our method matches or surpasses one-shot GRPO without relying on any external rewards, while reducing inference latency by over 10x compared to MCMC-based sampling.

---

### Heterogeneity-Aware Knowledge Sharing for Graph Federated Learning

Authors: Wentao Yu, Sheng Wan, Shuo Chen, Bo Han, Chen Gong
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21589v1

Graph Federated Learning (GFL) enables distributed graph representation learning while protecting the privacy of graph data. However, GFL suffers from heterogeneity arising from diverse node features and structural topologies across multiple clients. To address both types of heterogeneity, we propose a novel graph Federated learning method via Semantic and Structural Alignment (FedSSA), which shares the knowledge of both node features and structural topologies. For node feature heterogeneity, we propose a novel variational model to infer class-wise node distributions, so that we can cluster clients based on inferred distributions and construct cluster-level representative distributions. We then minimize the divergence between local and cluster-level distributions to facilitate semantic knowledge sharing. For structural heterogeneity, we employ spectral Graph Neural Networks (GNNs) and propose a spectral energy measure to characterize structural information, so that we can cluster clients based on spectral energy and build cluster-level spectral GNNs. We then align the spectral characteristics of local spectral GNNs with those of cluster-level spectral GNNs to enable structural knowledge sharing. Experiments on six homophilic and five heterophilic graph datasets under both non-overlapping and overlapping partitioning settings demonstrate that FedSSA consistently outperforms eleven state-of-the-art methods.

---

### A Study of Crosslinguistic Influence in Language Models

Authors: Abderrahmane Issam, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
Published: 2026-01-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.21587v2

The sequential acquisition of languages inevitably leads to Crosslinguistic Influence (CLI), where the syntactic properties of a first language (L1) impact the processing of a second language (L2). While modern language models exhibit robust cross-lingual transfer, the exact mechanisms governing how language dominance, relative proficiency, and typological distance dictate structural interference warrant deeper investigation. In this work, we systematically investigate CLI in artificial learners by training simultaneous and sequential bilingual models across 15 typologically diverse L1s and varying the Step of Exposure (SoE), defined as the specific training step at which the L2 is introduced. Utilizing crosslinguistic structural priming, we decouple latent CLI into distinct positive and negative transfer rates. Our evaluations reveal a critical computational tradeoff: while increased L1 dominance (higher SoE) strongly amplifies the correlation between structural transfer and syntactic distance, diminished L2 proficiency bottlenecks the model's capacity for positive transfer, leaving it highly vulnerable to persistent negative interference from distant L1s. Mechanistically, we demonstrate that L1 typological proximity physically dictates the cross-lingual overlap of L2 syntactic neurons. Furthermore, we uncover that explicit priming induces a dynamic layer-wise migration of grammatical resolution to the terminal layers of the network. Through targeted causal ablations, we confirm that deep-layer attention mechanisms exclusively drive this crosslinguistic transfer by routing the L1 structural prior into the final prediction. Ultimately, our findings demonstrate that CLI in language models is not an arbitrary artifact of capacity constraints, but a structured phenomenon fundamentally governed by the interplay of language dominance and proficiency.

---

### CORDS: Continuous Representations of Discrete Structures

Authors: Tin Hadži Veljković, Erik Bekkers, Michael Tiemann, Jan-Willem van de Meent
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21583v2

Many learning problems require predicting sets of objects when the number of objects is not known beforehand. Examples include object detection, molecular modeling, and scientific inference tasks such as astrophysical source detection. Existing methods often rely on padded representations or must explicitly infer the set size, which often poses challenges. We present a novel strategy for addressing this challenge by casting prediction of variable-sized sets as a continuous inference problem. Our approach, CORDS (Continuous Representations of Discrete Structures), provides an invertible mapping that transforms a set of spatial objects into continuous fields: a density field that encodes object locations and count, and a feature field that carries their attributes over the same support. Because the mapping is invertible, models operate entirely in field space while remaining exactly decodable to discrete sets. We evaluate CORDS across molecular generation and regression, object detection, simulation-based inference, and a mathematical task involving recovery of local maxima, demonstrating robust handling of unknown set sizes with competitive accuracy.

---

### Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves

Authors: Jonas Knupp, Jan Hendrik Metzen, Jeremias Bohn, Georg Groh, Kristian Kersting
Published: 2026-01-29
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.21582v1

Depth-recurrence facilitates latent reasoning by sharing parameters across depths. However, prior work lacks combined FLOP-, parameter-, and memory-matched baselines, underutilizes depth-recurrence due to partially fixed layer stacks, and ignores the bottleneck of constant hidden-sizes that restricts many-step latent reasoning. To address this, we introduce a modular framework of depth-recurrent attention mixtures (Dreamer), combining sequence attention, depth attention, and sparse expert attention. It alleviates the hidden-size bottleneck through attention along depth, decouples scaling dimensions, and allows depth-recurrent models to scale efficiently and effectively. Across language reasoning benchmarks, our models require 2 to 8x fewer training tokens for the same accuracy as FLOP-, parameter-, and memory-matched SOTA, and outperform ca. 2x larger SOTA models with the same training tokens. We further present insights into knowledge usage across depths, e.g., showing 2 to 11x larger expert selection diversity than SOTA MoEs.

---

### Evaluating Prediction Uncertainty Estimates from BatchEnsemble

Authors: Morten Blørstad, Herman Jangsett Mostein, Nello Blaser, Pekka Parviainen
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21581v1

Deep learning models struggle with uncertainty estimation. Many approaches are either computationally infeasible or underestimate uncertainty. We investigate \textit{BatchEnsemble} as a general and scalable method for uncertainty estimation across both tabular and time series tasks. To extend BatchEnsemble to sequential modeling, we introduce GRUBE, a novel BatchEnsemble GRU cell. We compare the BatchEnsemble to Monte Carlo dropout and deep ensemble models. Our results show that BatchEnsemble matches the uncertainty estimation performance of deep ensembles, and clearly outperforms Monte Carlo dropout. GRUBE achieves similar or better performance in both prediction and uncertainty estimation. These findings show that BatchEnsemble and GRUBE achieve similar performance with fewer parameters and reduced training and inference time compared to traditional ensembles.

---

### KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices

Authors: Wuyang Zhou, Yuxuan Gu, Giorgos Iacovides, Danilo Mandic
Published: 2026-01-29
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.21579v2

The success of Hyper-Connections (HC) in neural networks (NN) has also highlighted issues related to training instability and restricted scalability. The Manifold-Constrained Hyper-Connections (mHC) mitigate these challenges by projecting the residual connection space onto a Birkhoff polytope, however, it faces two issues: 1) its iterative Sinkhorn-Knopp (SK) algorithm does not always yield exactly doubly stochastic residual matrices; 2) mHC incurs a prohibitive $O(n^3C)$ parameter complexity with $n$ as the width of the residual stream and $C$ as the feature dimension. The recently proposed mHC-lite reparametrizes the residual matrix via the Birkhoff-von-Neumann theorem to guarantee double stochasticity, but also faces a factorial explosion in its parameter complexity, $O \left( nC \cdot n! \right)$. To address both challenges, we propose KromHC, which uses the Kronecker products of smaller doubly stochastic matrices to parametrize the residual matrix in mHC. By enforcing manifold constraints across the factor residual matrices along each mode of the tensorized residual stream, KromHC guarantees exact double stochasticity of the residual matrices while reducing parameter complexity to only $O(n^2C)$. Experiments show that KromHC matches or even outperforms other state-of-the-art (SOTA) mHC variants, while requiring significantly fewer trainable parameters. The code is at https://github.com/wz1119/KromHC.

---

### Collaborative Parameter Learning: Mitigating Forgetting via Parameter-Level Gradient Analysis

Authors: Mutian Yang, Zisen Zhan, Yutong Chen, Haolin Li, Kaiwen Wang, Kaili Zheng, Yuguang Wang, Qi Wang, Jiandong Gao, Ji Wu
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21577v2

Catastrophic forgetting during knowledge injection impairs the ability of large language models to acquire new knowledge without overwriting previously mastered knowledge. Recent studies analyze forgetting from a gradient similarity perspective and mitigate forgetting through vector projection. However, these methods primarily characterize gradient similarity at the aggregate direction level, leaving the parameter wise contributions to forgetting underexplored. In this paper, we decompose gradient similarity into parameter wise contributions and identify two types of parameters during forgetting: Conflicting Parameters, whose updates contribute to forgetting and typically account for 50 percent to 75 percent of parameters, and Collaborative Parameters, whose updates mitigate forgetting and account for 25 percent to 50 percent. Based on this analysis, we propose Collaborative Parameter Learning, CPL, a parameter wise training rule that freezes Conflicting Parameters and updates only Collaborative Parameters. Experiments comparing CPL with seven baseline methods show that CPL learns 20.2% to 48.2% more questions with negligible forgetting, while reducing peak VRAM by approximately 3 GB per billion model parameters and computation time by 16.5 percent. Extensive evaluations on parameter consumption, out of set generalization, cross prompt generalization, multimodal tasks, open ended question answering, and multilingual settings demonstrate that CPL effectively mitigates forgetting across diverse scenarios.

---

### Chain Of Thought Compression: A Theoretical Analysis

Authors: Juncai Li, Ru Li, Yuxiang Zhou, Boxiang Ma, Jeff Z. Pan
Published: 2026-01-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.21576v2

Chain-of-Thought (CoT) has unlocked advanced reasoning abilities of Large Language Models (LLMs) with intermediate steps, yet incurs prohibitive computational costs due to generation of extra tokens. Recent studies empirically show that compressing reasoning steps into latent states, or implicit CoT compression, offers a token-efficient alternative. However, the mechanism behind CoT compression remains unclear. In this paper, we provide the first theoretical analysis of the difficulty of learning to internalize intermediate reasoning steps. By introducing Order-r Interaction, we prove that the learning signal for high-order logical dependencies exponentially decays to solve irreducible problem, where skipping intermediate steps inevitably leads to high-order interaction barriers. To empirically validate this, we introduce NatBool-DAG, a challenging benchmark designed to enforce irreducible logical reasoning and eliminate semantic shortcuts. Guided by our theoretical findings, we propose ALiCoT (Aligned Implicit CoT), a novel framework that overcomes the signal decay by aligning latent token distributions with intermediate reasoning states. Experimental results demonstrate that ALiCoT successfully unlocks efficient reasoning: it achieves a 54.4x speedup while maintaining performance comparable to explicit CoT.

---

### Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networks

Authors: Jinhao Li, Yuhao Sun, Zhiyuan Ma, Hao He, Xinche Zhang, Xing Chen, Jin Li, Sen Song
Published: 2026-01-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.21572v1

Recurrent spiking neural networks (RSNNs) are a promising substrate for energy-efficient control policies, but training them for high-dimensional, long-horizon reinforcement learning remains challenging. Population-based, gradient-free optimization circumvents backpropagation through non-differentiable spike dynamics by estimating gradients. However, with finite populations, high variance of these estimates can induce harmful and overly aggressive update steps. Inspired by trust-region methods in reinforcement learning that constrain policy updates in distribution space, we propose \textbf{Signal-Adaptive Trust Regions (SATR)}, a distributional update rule that constrains relative change by bounding KL divergence normalized by an estimated signal energy. SATR automatically expands the trust region under strong signals and contracts it when updates are noise-dominated. We instantiate SATR for Bernoulli connectivity distributions, which have shown strong empirical performance for RSNN optimization. Across a suite of high-dimensional continuous-control benchmarks, SATR improves stability under limited populations and reaches competitive returns against strong baselines including PPO-LSTM. In addition, to make SATR practical at scale, we introduce a bitset implementation for binary spiking and binary weights, substantially reducing wall-clock training time and enabling fast RSNN policy search.

---

### Shaping capabilities with token-level data filtering

Authors: Neil Rathi, Alec Radford
Published: 2026-01-29
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.21571v2

Current approaches to reducing undesired capabilities in language models are largely post hoc, and can thus be easily bypassed by adversaries. A natural alternative is to shape capabilities during pretraining itself. On the proxy task of removing medical capabilities, we show that the simple intervention of filtering pretraining data is highly effective, robust, and inexpensive at scale. Inspired by work on data attribution, we show that filtering tokens is more effective than filtering documents, achieving the same hit to undesired capabilities at a lower cost to benign ones. Training models spanning two orders of magnitude, we then demonstrate that filtering gets more effective with scale: for our largest models, token filtering leads to a 7000x compute slowdown on the forget domain. We also show that models trained with token filtering can still be aligned on the forget domain. Along the way, we introduce a methodology for labeling tokens with sparse autoencoders and distilling cheap, high-quality classifiers. We also demonstrate that filtering can be robust to noisy labels with sufficient pretraining compute.

---

### From Digital to Physical: Digital Agents as Autonomous Coaches for Physical Intelligence

Authors: Zixing Lei, Genjia Liu, Yuanshuo Zhang, Qipeng Liu, Yuzhu Cai, Sixiang Chen, Jixian Wu, Yunhong Wang, Weixin Li, Chuan Wen, Bo Zhao, Shanghang Zhang et al.
Published: 2026-01-29
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2601.21570v2

The field of Embodied AI is witnessing a rapid evolution toward general-purpose robotic systems, fueled by high-fidelity simulation and large-scale data collection. However, this scaling capability remains severely bottlenecked by a reliance on labor-intensive manual oversight from intricate reward shaping to hyperparameter tuning across heterogeneous backends. Inspired by LLMs' success in software automation and science discovery, we introduce \textsc{EmboCoach-Bench}, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies. Spanning 32 expert-curated RL and IL tasks, our framework posits executable code as the universal interface. We move beyond static generation to assess a dynamic closed-loop workflow, where agents leverage environment feedback to iteratively draft, debug, and optimize solutions, spanning improvements from physics-informed reward design to policy architectures such as diffusion policies. Extensive evaluations yield three critical insights: (1) autonomous agents can qualitatively surpass human-engineered baselines by 26.5\% in average success rate; (2) agentic workflow with environment feedback effectively strengthens policy development and substantially narrows the performance gap between open-source and proprietary models; and (3) agents exhibit self-correction capabilities for pathological engineering cases, successfully resurrecting task performance from near-total failures through iterative simulation-in-the-loop debugging. Ultimately, this work establishes a foundation for self-evolving embodied intelligence, accelerating the paradigm shift from labor-intensive manual tuning to scalable, autonomous engineering in embodied AI field.

---

### Bridging Functional and Representational Similarity via Usable Information

Authors: Antonio Almudévar, Alfonso Ortega
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21568v2

We present a unified framework for quantifying the similarity between representations through the lens of \textit{usable} information, offering a rigorous theoretical and empirical synthesis across three key dimensions. First, addressing functional similarity, we establish a formal link between stitching performance and conditional mutual information. We further reveal that stitching is inherently asymmetric, demonstrating that robust functional comparison necessitates a bidirectional analysis rather than a unidirectional mapping. Second, concerning representational similarity, we find that reconstruction-based metrics and standard tools (e.g., CKA, RSA) act as estimators of usable information under specific constraints. Crucially, we show that similarity is relative to the capacity of the predictive family: representations that appear distinct to a rigid observer may be identical to a more expressive one. Third, we demonstrate that representational similarity is sufficient but not necessary for functional similarity. We unify these concepts through a task-granularity hierarchy: similarity on a complex task guarantees similarity on any coarser derivative, establishing representational similarity as the limit of maximum granularity: input reconstruction.

---

### FlexCausal: Flexible Causal Disentanglement via Structural Flow Priors and Manifold-Aware Interventions

Authors: Yutao Jin, Yuang Tao, Junyong Zhai
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21567v1

Causal Disentangled Representation Learning(CDRL) aims to learn and disentangle low dimensional representations and their underlying causal structure from observations. However, existing disentanglement methods rely on a standard mean-field approximation with a diagonal posterior covariance, which decorrelates all latent dimensions. Additionally, these methods often assume isotropic Gaussian priors for exogenous noise, failing to capture the complex, non-Gaussian statistical properties prevalent in real-world causal factors. Therefore, we propose FlexCausal, a novel CDRL framework based on a block-diagonal covariance VAE. FlexCausal utilizes a Factorized Flow-based Prior to realistically model the complex densities of exogenous noise, effectively decoupling the learning of causal mechanisms from distributional statistics. By integrating supervised alignment objectives with counterfactual consistency constraints, our framework ensures a precise structural correspondence between the learned latent subspaces and the ground-truth causal relations. Finally, we introduce a manifold-aware relative intervention strategy to ensure high-fidelity generation. Experimental results on both synthetic and real-world datasets demonstrate that FlexCausal significantly outperforms other methods.

---

### Multi-objective Integer Linear Programming approach for Automatic Software Cognitive Complexity Reduction

Authors: Adriana Novoa-Hurtado, Rubén Saborido, Francisco Chicano, Manuel Giménez-Medina
Published: 2026-01-29
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2601.21565v1

Clear and concise code is necessary to ensure maintainability, so it is crucial that the software is as simple as possible to understand, to avoid bugs and, above all, vulnerabilities. There are many ways to enhance software without changing its functionality, considering the extract method refactoring the primary process to reduce the effort required for code comprehension. The cognitive complexity measure employed in this work is the one defined by SonarSource, which is a company that develops well-known applications for static code analysis. This extraction problem can be modeled as a combinatorial optimization problem. The main difficulty arises from the existence of different criteria for evaluating the solutions obtained, requiring the formulation of the code extraction problem as a multi-objective optimization problem using alternative methods. We propose a multi-objective integer linear programming model to obtain a set of solutions that reduce the cognitive complexity of a given piece of code, such as balancing the number of lines of code and its cognitive complexity. In addition, several algorithms have been developed to validate the model. These algorithms have been integrated into a tool that enables the parameterised resolution of the problem of reducing software cognitive complexity.

---

### Representation Unlearning: Forgetting through Information Compression

Authors: Antonio Almudévar, Alfonso Ortega
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21564v2

Machine unlearning seeks to remove the influence of specific training data from a model, a need driven by privacy regulations and robustness concerns. Existing approaches typically modify model parameters, but such updates can be unstable, computationally costly, and limited by local approximations. We introduce Representation Unlearning, a framework that performs unlearning directly in the model's representation space. Instead of modifying model parameters, we learn a transformation over representations that imposes an information bottleneck: maximizing mutual information with retained data while suppressing information about data to be forgotten. We derive variational surrogates that make this objective tractable and show how they can be instantiated in two practical regimes: when both retain and forget data are available, and in a zero-shot setting where only forget data can be accessed. Experiments across several benchmarks demonstrate that Representation Unlearning achieves more reliable forgetting, better utility retention, and greater computational efficiency than parameter-centric baselines.

---

### SAL: Selective Adaptive Learning for Backpropagation-Free Training with Sparsification

Authors: Fanping Liu, Hua Yang, Jiasi Zou
Published: 2026-01-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.21561v1

Standard deep learning relies on Backpropagation (BP), which is constrained by biologically implausible weight symmetry and suffers from significant gradient interference within dense representations. To mitigate these bottlenecks, we propose Selective Adaptive Learning (SAL), a training method that combines selective parameter activation with adaptive area partitioning. Specifically, SAL decomposes the parameter space into mutually exclusive, sample-dependent regions. This decoupling mitigates gradient interference across divergent semantic patterns and addresses explicit weight symmetry requirements through our refined feedback alignment. Empirically, SAL demonstrates competitive convergence rates, leading to improved classification performance across 10 standard benchmarks. Additionally, SAL achieves numerical consistency and competitive accuracy even in deep regimes (up to 128 layers) and large-scale models (up to 1B parameters). Our approach is loosely inspired by biological learning mechanisms, offering a plausible alternative that contributes to the study of scalable neural network training.

---

### HistoPrism: Unlocking Functional Pathway Analysis from Pan-Cancer Histology via Gene Expression Prediction

Authors: Susu Hu, Qinghe Zeng, Nithya Bhasker, Jakob Nikolas Kather, Stefanie Speidel
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21560v3

Predicting spatial gene expression from H&E histology offers a scalable and clinically accessible alternative to sequencing, but realizing clinical impact requires models that generalize across cancer types and capture biologically coherent signals. Prior work is often limited to per-cancer settings and variance-based evaluation, leaving functional relevance underexplored. We introduce HistoPrism, an efficient transformer-based architecture for pan-cancer prediction of gene expression from histology. To evaluate biological meaning, we introduce a pathway-level benchmark, shifting assessment from isolated gene-level variance to coherent functional pathways. HistoPrism not only surpasses prior state-of-the-art models on highly variable genes , but also more importantly, achieves substantial gains on pathway-level prediction, demonstrating its ability to recover biologically coherent transcriptomic patterns. With strong pan-cancer generalization and improved efficiency, HistoPrism establishes a new standard for clinically relevant transcriptomic modeling from routinely available histology.

---

### ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

Authors: Xiaoyu Tian, Haotian Wang, Shuaiting Chen, Hao Zhou, Kaichi Yu, Yudian Zhang, Jade Ouyang, Junxi Yin, Jiong Chen, Baoyan Guo, Lei Zhang, Junjie Tao et al.
Published: 2026-01-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.21558v2

Large language models (LLMs) are increasingly used as tool-augmented agents for multi-step decision making, yet training robust tool-using agents remains challenging. Existing methods still require manual intervention, depend on non-verifiable simulated environments, rely exclusively on either supervised fine-tuning (SFT) or reinforcement learning (RL), and struggle with stable long-horizon, multi-turn learning. To address these challenges, we introduce ASTRA, a fully automated end-to-end framework for training tool-augmented language model agents via scalable data synthesis and verifiable reinforcement learning. ASTRA integrates two complementary components. First, a pipeline that leverages the static topology of tool-call graphs synthesizes diverse, structurally grounded trajectories, instilling broad and transferable tool-use competence. Second, an environment synthesis framework that captures the rich, compositional topology of human semantic reasoning converts decomposed question-answer traces into independent, code-executable, and rule-verifiable environments, enabling deterministic multi-turn RL. Based on this method, we develop a unified training methodology that integrates SFT with online RL using trajectory-level rewards to balance task completion and interaction efficiency. Experiments on multiple agentic tool-use benchmarks demonstrate that ASTRA-trained models achieve state-of-the-art performance at comparable scales, approaching closed-source systems while preserving core reasoning ability. We release the full pipelines, environments, and trained models at https://github.com/LianjiaTech/astra.

---

### Meta Context Engineering via Agentic Skill Evolution

Authors: Haoran Ye, Xuning He, Vincent Arak, Haonan Dong, Guojie Song
Published: 2026-01-29
Categories: cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2601.21557v2

The operational efficacy of large language models relies heavily on their inference-time context. This has established Context Engineering (CE) as a formal discipline for optimizing these inputs. Current CE methods rely on manually crafted harnesses, such as rigid generation-reflection workflows and predefined context schemas. They impose structural biases and restrict context optimization to a narrow, intuition-bound design space. To address this, we introduce Meta Context Engineering (MCE), a bi-level framework that supersedes static CE heuristics by co-evolving CE skills and context artifacts. In MCE iterations, a meta-level agent refines engineering skills via agentic crossover, a deliberative search over the history of skills, their executions, and evaluations. A base-level agent executes these skills, learns from training rollouts, and optimizes context as flexible files and code. We evaluate MCE across five disparate domains under offline and online settings. MCE demonstrates consistent performance gains, achieving 5.6--53.8% relative improvement over state-of-the-art agentic CE methods (mean of 16.9%), while maintaining superior context adaptability, transferability, and efficiency in both context usage and training.

---

### Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes

Authors: Yang Zhou, Zhenting Sheng, Mingrui Tan, Yuting Song, Jun Zhou, Yu Heng Kwan, Lian Leng Low, Yang Bai, Yong Liu
Published: 2026-01-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.21551v1

Effective clinical history taking is a foundational yet underexplored component of clinical reasoning. While large language models (LLMs) have shown promise on static benchmarks, they often fall short in dynamic, multi-turn diagnostic settings that require iterative questioning and hypothesis refinement. To address this gap, we propose \method{}, a note-driven framework that trains LLMs to conduct structured history taking and diagnosis by learning from widely available medical notes. Instead of relying on scarce and sensitive dialogue data, we convert real-world medical notes into high-quality doctor-patient dialogues using a decision tree-guided generation and refinement pipeline. We then propose a three-stage fine-tuning strategy combining supervised learning, simulated data augmentation, and preference learning. Furthermore, we propose a novel single-turn reasoning paradigm that reframes history taking as a sequence of single-turn reasoning problems. This design enhances interpretability and enables local supervision, dynamic adaptation, and greater sample efficiency. Experimental results show that our method substantially improves clinical reasoning, achieving gains of +16.9 F1 and +21.0 Top-1 diagnostic accuracy over GPT-4o. Our code and dataset can be found at https://github.com/zhentingsheng/Note2Chat.

---

### Training slow silicon neurons to control extremely fast robots with spiking reinforcement learning

Authors: Irene Ambrosini, Ingo Blakowski, Dmitrii Zendrikov, Cristiano Capone, Luna Gava, Giacomo Indiveri, Chiara De Luca, Chiara Bartolozzi
Published: 2026-01-29
Categories: cs.RO, cs.AI, cs.ET
arXiv: https://arxiv.org/abs/2601.21548v1

Air hockey demands split-second decisions at high puck velocities, a challenge we address with a compact network of spiking neurons running on a mixed-signal analog/digital neuromorphic processor. By co-designing hardware and learning algorithms, we train the system to achieve successful puck interactions through reinforcement learning in a remarkably small number of trials. The network leverages fixed random connectivity to capture the task's temporal structure and adopts a local e-prop learning rule in the readout layer to exploit event-driven activity for fast and efficient learning. The result is real-time learning with a setup comprising a computer and the neuromorphic chip in-the-loop, enabling practical training of spiking neural networks for robotic autonomous systems. This work bridges neuroscience-inspired hardware with real-world robotic control, showing that brain-inspired approaches can tackle fast-paced interaction tasks while supporting always-on learning in intelligent machines.

---

### Multi-Modal Time Series Prediction via Mixture of Modulated Experts

Authors: Lige Zhang, Ali Maatouk, Jialin Chen, Karthik Charan Konduri, Leandros Tassiulas, Rex Ying
Published: 2026-01-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.21547v3

Real-world time series exhibit complex and evolving dynamics, making accurate forecasting extremely challenging. Recent multi-modal forecasting methods leverage textual information such as news reports to improve prediction, but most rely on token-level fusion that mixes temporal patches with language tokens in a shared embedding space. However, such fusion can be ill-suited when high-quality time-text pairs are scarce and when time series exhibit substantial variation in characteristics, thus complicating cross-modal alignment. In parallel, mixture-of-experts (MoE) architectures have proven effective for both time series modeling and multi-modal learning, yet many existing MoE-based modality integration methods still depend on token-level fusion. To address this, we propose Expert Modulation, a new mechanism for multi-modal time series prediction that conditions both routing and expert computation on textual signals, enabling direct and efficient cross-modal control over expert behavior. Through theoretical analysis and experiments, our proposed method demonstrates strong improvements in multi-modal time series prediction. The current code implementation is available at https://github.com/BruceZhangReve/MoME

---

### ShardMemo: Scope-Before-Routing for Agentic Memory Retrieval

Authors: Yang Zhao, Chengxiao Dai, Mengying Kou, Yue Xiu, Dusit Niyato
Published: 2026-01-29
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.21545v2

Agentic systems accumulate persistent memory across sessions, tools, and tasks, and a later request must retrieve from it under two distinct constraints: which memories it is permitted to access, and which are relevant under a limited search budget. Existing memory systems handle access scope in two flawed ways: applying scope after retrieval wastes probe budget on inadmissible memories, while treating scope as a learned ranking feature makes a hard constraint depend on router quality. We present SHARD-MEMO, an agentic memory system built on scope-before-routing: metadata predicates first identify the admissible shards, and a learned router then selects a small number of them for shard-local approximate nearest neighbor retrieval. Given the supplied scope predicate and metadata, this separates hard admissibility from learned relevance ranking, so inadmissible shards cannot consume shard-probe budget. We evaluate on LoCoMo, HotpotQA, and ToolBench, covering conversational, long-context, and procedural memory. Under matched supervision and fixed budgets, SHARDMEMO improves over a learned router baseline by roughly +3 F1 on LoCoMo; in end-to-end LoCoMo evaluation it improves over the strongest evaluated memory baseline by up to +6.8 F1, with gains on HotpotQA and ToolBench.

---

### inversedMixup: Data Augmentation via Inverting Mixed Embeddings

Authors: Fanshuang Kong, Richong Zhang, Qiyu Sun, Zhijie Nie, Ting Deng, Chunming Hu
Published: 2026-01-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.21543v3

Mixup generates augmented samples by linearly interpolating inputs and labels with a controllable ratio. However, since it operates at the latent embedding level, the resulting samples are not human-interpretable. In contrast, LLM-based augmentation methods produce sentences via prompts at the token level, yielding readable outputs but offering limited control over the generation process. Inspired by recent advances in LLM inversion, which reconstructs natural language from embeddings and helps bridge the gap between latent embedding space and discrete token space, we propose inversedMixup, a unified framework that combines the controllability of Mixup with the interpretability of LLM-based generation. Specifically, inversedMixup aligns the output embedding space of a task-specific model with the input embedding space of an LLM, so that mixed embeddings can be reconstructed, under a controllable mixing ratio, into human-interpretable sentences. This interpretability provides the first empirical evidence of the manifold intrusion phenomenon in text Mixup. Building on this, we extend inversedMixup into a three-stage data augmentation method, and introduce a simple yet effective strategy to mitigate manifold intrusion during augmentation. Extensive experiments demonstrate the effectiveness and generalizability of our approach in both few-shot and fully supervised scenarios.

---

### Bi-Anchor Interpolation Solver for Accelerating Generative Modeling

Authors: Hongxu Chen, Hongxiang Li, Zhen Wang, Long Chen
Published: 2026-01-29
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.21542v3

Flow Matching (FM) models have emerged as a leading paradigm for high-fidelity synthesis. However, their reliance on iterative Ordinary Differential Equation (ODE) solving creates a significant latency bottleneck. Existing solutions face a dichotomy: training-free solvers suffer from significant performance degradation at low Neural Function Evaluations (NFEs), while training-based one- or few-steps generation methods incur prohibitive training costs and lack plug-and-play versatility. To bridge this gap, we propose the Bi-Anchor Interpolation Solver (BA-solver). BA-solver retains the versatility of standard training-free solvers while achieving significant acceleration by introducing a lightweight SideNet (1-2% backbone size) alongside the frozen backbone. Specifically, our method is founded on two synergistic components: \textbf{1) Bidirectional Temporal Perception}, where the SideNet learns to approximate both future and historical velocities without retraining the heavy backbone; and 2) Bi-Anchor Velocity Integration, which utilizes the SideNet with two anchor velocities to efficiently approximate intermediate velocities for batched high-order integration. By utilizing the backbone to establish high-precision ``anchors'' and the SideNet to densify the trajectory, BA-solver enables large interval sizes with minimized error. Empirical results on ImageNet-256^2 demonstrate that BA-solver achieves generation quality comparable to 100+ NFEs Euler solver in just 10 NFEs and maintains high fidelity in as few as 5 NFEs, incurring negligible training costs. Furthermore, BA-solver ensures seamless integration with existing generative pipelines, facilitating downstream tasks such as image editing.

---

### Vision KAN: Towards an Attention-Free Backbone for Vision with Kolmogorov-Arnold Networks

Authors: Zhuoqin Yang, Jiansong Zhang, Xiaoling Luo, Xu Wu, Zheng Lu, Linlin Shen
Published: 2026-01-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.21541v1

Attention mechanisms have become a key module in modern vision backbones due to their ability to model long-range dependencies. However, their quadratic complexity in sequence length and the difficulty of interpreting attention weights limit both scalability and clarity. Recent attention-free architectures demonstrate that strong performance can be achieved without pairwise attention, motivating the search for alternatives. In this work, we introduce Vision KAN (ViK), an attention-free backbone inspired by the Kolmogorov-Arnold Networks. At its core lies MultiPatch-RBFKAN, a unified token mixer that combines (a) patch-wise nonlinear transform with Radial Basis Function-based KANs, (b) axis-wise separable mixing for efficient local propagation, and (c) low-rank global mapping for long-range interaction. Employing as a drop-in replacement for attention modules, this formulation tackles the prohibitive cost of full KANs on high-resolution features by adopting a patch-wise grouping strategy with lightweight operators to restore cross-patch dependencies. Experiments on ImageNet-1K show that ViK achieves competitive accuracy with linear complexity, demonstrating the potential of KAN-based token mixing as an efficient and theoretically grounded alternative to attention.

---

### ARGORA: Orchestrated Argumentation for Causally Grounded LLM Reasoning and Decision Making

Authors: Youngjin Jin, Hanna Kim, Kwanwoo Kim, Chanhee Lee, Seungwon Shin
Published: 2026-01-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.21533v1

Existing multi-expert LLM systems gather diverse perspectives but combine them through simple aggregation, obscuring which arguments drove the final decision. We introduce ARGORA, a framework that organizes multi-expert discussions into explicit argumentation graphs showing which arguments support or attack each other. By casting these graphs as causal models, ARGORA can systematically remove individual arguments and recompute outcomes, identifying which reasoning chains were necessary and whether decisions would change under targeted modifications. We further introduce a correction mechanism that aligns internal reasoning with external judgments when they disagree. Across diverse benchmarks and an open-ended use case, ARGORA achieves competitive accuracy and demonstrates corrective behavior: when experts initially disagree, the framework resolves disputes toward correct answers more often than it introduces new errors, while providing causal diagnostics of decisive arguments.

---

### On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression

Authors: Xinwei Zhang, Hangcheng Liu, Li Bai, Hao Wang, Qingqing Ye, Tianwei Zhang, Haibo Hu
Published: 2026-01-29
Categories: cs.CR, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.21531v2

Visual token compression is widely used to accelerate large vision-language models (LVLMs) by pruning or merging visual tokens, yet its adversarial robustness remains unexplored. We show that existing encoder-based attacks cannot fully disclose the robustness vulnerabilities of compressed LVLMs, due to an optimization-inference mismatch: perturbations are optimized on the full-token representation, while inference is performed through a token-compression bottleneck. To address this gap, we propose the Compression-AliGnEd attack (CAGE), which aligns perturbation optimization with compression inference without assuming access to the deployed compression mechanism or its token budget. CAGE combines (i) expected feature disruption, which concentrates distortion on tokens likely to survive across plausible budgets, and (ii) rank distortion alignment, which actively aligns token distortions with rank scores to promote the retention of highly distorted evidence. Across diverse representative plug-and-play compression mechanisms and datasets, our results show that CAGE consistently achieves lower robust accuracy than the baseline. This work highlights that robustness assessments ignoring compression can be overly optimistic, calling for compression-aware security evaluation and defenses for efficient LVLMs.

---

### Fast and Geometrically Grounded Lorentz Neural Networks

Authors: Robert van der Klis, Ricardo Chávez Torres, Max van Spengler, Yuhui Ding, Thomas Hofmann, Pascal Mettes
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21529v1

Hyperbolic space is quickly gaining traction as a promising geometry for hierarchical and robust representation learning. A core open challenge is the development of a mathematical formulation of hyperbolic neural networks that is both efficient and captures the key properties of hyperbolic space. The Lorentz model of hyperbolic space has been shown to enable both fast forward and backward propagation. However, we prove that, with the current formulation of Lorentz linear layers, the hyperbolic norms of the outputs scale logarithmically with the number of gradient descent steps, nullifying the key advantage of hyperbolic geometry. We propose a new Lorentz linear layer grounded in the well-known ``distance-to-hyperplane" formulation. We prove that our formulation results in the usual linear scaling of output hyperbolic norms with respect to the number of gradient descent steps. Our new formulation, together with further algorithmic efficiencies through Lorentzian activation functions and a new caching strategy results in neural networks fully abiding by hyperbolic geometry while simultaneously bridging the computation gap to Euclidean neural networks. Code available at: https://github.com/robertdvdk/hyperbolic-fully-connected.

---

### Sustainable Materials Discovery in the Era of Artificial Intelligence

Authors: Sajid Mannan, Rupert J. Myers, Rohit Batra, Rocio Mercado, Lothar Wondraczek, N. M. Anoop Krishnan
Published: 2026-01-29
Categories: cond-mat.mtrl-sci, cs.AI
arXiv: https://arxiv.org/abs/2601.21527v3

Artificial intelligence (AI) has transformed materials discovery, enabling rapid exploration of chemical space through generative models and surrogate screening. Yet current generative AI models for materials discovery, which now drive exploration of vast chemical and structural spaces, optimize candidates exclusively for structural stability and functional properties, with no integration of environmental assessment at any stage of the design loop. Prospective and ex-ante life cycle assessment methods exist and have been applied to emerging technologies, but they operate as standalone downstream analyses, not as active constraints within generative or active-learning pipelines. The result is that environmental feedback, even when produced, arrives after design decisions have been made rather than informing them. The disconnect between atomic-scale design and lifecycle assessment (LCA) reflects fundamental challenges: (i) data scarcity across heterogeneous sources, (ii) scale gaps from atoms to industrial systems, (iii) uncertainty in synthesis pathways, and (iv) the absence of frameworks that co-optimize performance with environmental impact. In this Perspective, we propose integrating upstream ML-assisted materials discovery with downstream LCA into the ML-LCA framework, comprising five components: information extraction for building materials-environment knowledge bases, harmonized databases linking properties to sustainability metrics, multi-scale models bridging atomic properties to lifecycle impacts, ensemble prediction of manufacturing pathways with uncertainty quantification, and uncertainty-aware optimization enabling simultaneous performance-sustainability navigation. Case studies spanning polymers, glass, photoresists, and cement demonstrate both necessity and feasibility while identifying material-specific integration challenges.

---

### KAPSO: A Knowledge-grounded framework for Autonomous Program Synthesis and Optimization

Authors: Alireza Nadafian, Alireza Mohammadshahi, Majid Yazdani
Published: 2026-01-29
Categories: cs.AI, cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2601.21526v2

We introduce KAPSO, a modular framework for autonomous program synthesis and optimization. Given a natural language goal and an evaluation method, KAPSO iteratively performs ideation, code synthesis and editing, execution, evaluation, and learning to improve a runnable artifact toward measurable objectives. Rather than treating synthesis as the endpoint, KAPSO uses synthesis as an operator within a long-horizon optimization loop, where progress is defined by evaluator outcomes. KAPSO targets long-horizon failures common in coding agents, including lost experimental state, brittle debugging, and weak reuse of domain expertise, by integrating three tightly coupled components. First, a git-native experimentation engine isolates each attempt as a branch, producing reproducible artifacts and preserving provenance across iterations. Second, a knowledge system ingests heterogeneous sources, including repositories, internal playbooks, and curated external resources such as documentation, scientific papers, and web search results, and organizes them into a structured representation that supports retrieval over workflows, implementations, and environment constraints. Third, a cognitive memory layer coordinates retrieval and maintains an episodic store of reusable lessons distilled from experiment traces (run logs, diffs, and evaluator feedback), reducing repeated error modes and accelerating convergence. We evaluated KAPSO on MLE-Bench (Kaggle-style ML competitions) and ALE-Bench (AtCoder heuristic optimization), and report end-to-end performance. Code Available at: https://github.com/Leeroo-AI/kapso

---

### LMK > CLS: Landmark Pooling for Dense Embeddings

Authors: Meet Doshi, Aashka Trivedi, Vishwajeet Kumar, Parul Awasthy, Yulong Li, Jaydeep Sen, Radu Florian, Sachindra Joshi
Published: 2026-01-29
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2601.21525v1

Representation learning is central to many downstream tasks such as search, clustering, classification, and reranking. State-of-the-art sequence encoders typically collapse a variable-length token sequence to a single vector using a pooling operator, most commonly a special (CLS) token or mean pooling over token embeddings. In this paper, we identify systematic weaknesses of these pooling strategies: (CLS) tends to concentrate information toward the initial positions of the sequence and can under-represent distributed evidence, while mean pooling can dilute salient local signals, sometimes leading to worse short-context performance. To address these issues, we introduce Landmark (LMK) pooling, which partitions a sequence into chunks, inserts landmark tokens between chunks, and forms the final representation by mean-pooling the landmark token embeddings. This simple mechanism improves long-context extrapolation without sacrificing local salient features, at the cost of introducing a small number of special tokens. We empirically demonstrate that LMK pooling matches existing methods on short-context retrieval tasks and yields substantial improvements on long-context tasks, making it a practical and scalable alternative to existing pooling methods.

---

### Explicit Credit Assignment through Local Rewards and Dependence Graphs in Multi-Agent Reinforcement Learning

Authors: Bang Giang Le, Viet Cuong Ta
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21523v2

To promote cooperation in Multi-Agent Reinforcement Learning, the reward signals of all agents can be aggregated together, forming global rewards that are commonly known as the fully cooperative setting. However, global rewards are usually noisy because they contain the contributions of all agents, which have to be resolved in the credit assignment process. On the other hand, using local reward benefits from faster learning due to the separation of agents' contributions, but can be suboptimal as agents myopically optimize their own reward while disregarding the global optimality. In this work, we propose a method that combines the merits of both approaches. By using a graph of interaction between agents, our method discerns the individual agent contribution in a more fine-grained manner than a global reward, while alleviating the cooperation problem with agents' local reward. We also introduce a practical approach for approximating such a graph. Our experiments demonstrate the flexibility of the approach, enabling improvements over the traditional local and global reward settings.

---

### More Bang for the Buck: Improving the Inference of Large Language Models at a Fixed Budget using Reset and Discard (ReD)

Authors: Sagi Meir, Tommer D. Keidar, Noam Levi, Shlomi Reuveni, Barak Hirshberg
Published: 2026-01-29
Categories: cs.LG, cond-mat.dis-nn, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2601.21522v3

The performance of large language models (LLMs) on verifiable tasks is usually measured by pass@k, the probability of answering a question correctly at least once in k trials. At a fixed budget, a more suitable metric is coverage@cost, the average number of unique questions answered as a function of the total number of attempts. We connect the two metrics and show that the empirically-observed power-law behavior in pass@k leads to a sublinear growth of the coverage@cost (diminishing returns). To solve this problem, we propose Reset-and-Discard (ReD), a query method of LLMs that increases coverage@cost for a given budget, regardless of the pass@k form. Moreover, given a pass@k, we can quantitatively predict the savings in the total number of attempts using ReD. If pass@k is not available for the model, ReD can infer its power-law exponent. Experiments on three LLMs across coding (HumanEval), math (GSM8K), and reasoning (MMLU-Pro) benchmarks demonstrate that ReD substantially reduces the required attempts, tokens, and USD cost to reach a desired coverage, while also offering an efficient way to measure inference power-laws. ReD's advantage is maintained for imperfect verifiers and outperforms the tested allocation baselines.

---

### A Unified SPD Token Transformer Framework for EEG Classification: Systematic Comparison of Geometric Embeddings

Authors: Chi-Sheng Chen, En-Jui Kuo, Guan-Ying Chen, Xinyu Zhang, Fan Zhang
Published: 2026-01-29
Categories: cs.LG, cs.HC
arXiv: https://arxiv.org/abs/2601.21521v1

Spatial covariance matrices of EEG signals are Symmetric Positive Definite (SPD) and lie on a Riemannian manifold, yet the theoretical connection between embedding geometry and optimization dynamics remains unexplored. We provide a formal analysis linking embedding choice to gradient conditioning and numerical stability for SPD manifolds, establishing three theoretical results: (1) BWSPD's $\sqrtκ$ gradient conditioning (vs $κ$ for Log-Euclidean) via Daleckii-Kreĭn matrices provides better gradient conditioning on high-dimensional inputs ($d \geq 22$), with this advantage reducing on low-dimensional inputs ($d \leq 8$) where eigendecomposition overhead dominates; (2) Embedding-Space Batch Normalization (BN-Embed) approximates Riemannian normalization up to $O(\varepsilon^2)$ error, yielding $+26\%$ accuracy on 56-channel ERP data but negligible effect on 8-channel SSVEP data, matching the channel-count-dependent prediction; (3) bi-Lipschitz bounds prove BWSPD tokens preserve manifold distances with distortion governed solely by the condition ratio $κ$. We validate these predictions via a unified Transformer framework comparing BWSPD, Log-Euclidean, and Euclidean embeddings within identical architecture across 1,500+ runs on three EEG paradigms (motor imagery, ERP, SSVEP; 36 subjects). Our Log-Euclidean Transformer achieves state-of-the-art performance on all datasets, substantially outperforming classical Riemannian classifiers and recent SPD baselines, while BWSPD offers competitive accuracy with similar training time.

---

### HERS: Hidden-Pattern Expert Learning for Risk-Specific Vehicle Damage Adaptation in Diffusion Models

Authors: Teerapong Panboonyuen
Published: 2026-01-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.21517v1

Recent advances in text-to-image (T2I) diffusion models have enabled increasingly realistic synthesis of vehicle damage, raising concerns about their reliability in automated insurance workflows. The ability to generate crash-like imagery challenges the boundary between authentic and synthetic data, introducing new risks of misuse in fraud or claim manipulation. To address these issues, we propose HERS (Hidden-Pattern Expert Learning for Risk-Specific Damage Adaptation), a framework designed to improve fidelity, controllability, and domain alignment of diffusion-generated damage images. HERS fine-tunes a base diffusion model via domain-specific expert adaptation without requiring manual annotation. Using self-supervised image-text pairs automatically generated by a large language model and T2I pipeline, HERS models each damage category, such as dents, scratches, broken lights, or cracked paint, as a separate expert. These experts are later integrated into a unified multi-damage model that balances specialization with generalization. We evaluate HERS across four diffusion backbones and observe consistent improvements: plus 5.5 percent in text faithfulness and plus 2.3 percent in human preference ratings compared to baselines. Beyond image fidelity, we discuss implications for fraud detection, auditability, and safe deployment of generative models in high-stakes domains. Our findings highlight both the opportunities and risks of domain-specific diffusion, underscoring the importance of trustworthy generation in safety-critical applications such as auto insurance.

---

### Cascaded Transfer: Learning Many Tasks under Budget Constraints

Authors: Eloi Campagne, Yvenn Amara-Ouali, Yannig Goude, Mathilde Mougeot, Argyris Kalogeratos
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21513v2

In distributed applications, such as energy demand forecasting at the substation level or federated learning, a large number of related tasks must be learned by different models, while the exact task relationships are unknown. We propose the novel Cascaded Transfer Learning (CTL) paradigm in which model parameters cascade hierarchically through tasks organized as a rooted tree, respecting a global training budget. Starting from a source task, the tree specifies the order in which tasks are learned and refined, with the budget allocated along its branches. We design cascade mechanisms based on spanning trees that connect all tasks by minimizing an objective combining pairwise task distances and the available training budget, which yield geometry-aware and depth-bounded transfer graphs. We theoretically characterize how transfer errors accumulate and attenuate along cascade paths: errors introduced at any upstream node are contracted by every downstream refinement, and balanced tree topologies bound this accumulation. Experiments on synthetic and real many-task settings, time-series forecasting and image classification, show that CTL enables more accurate and cost-effective adaptation across large task collections than alternative approaches, with the largest gains at the tightest budgets.

---

### MURAD: A Large-Scale Multi-Domain Unified Reverse Arabic Dictionary Dataset

Authors: Serry Sibaee, Yasser Alhabashi, Nadia Sibai, Yara Farouk, Adel Ammar, Sawsan AlHalawani, Wadii Boulila
Published: 2026-01-29
Categories: cs.CL, cs.CY, cs.DB, cs.IR
arXiv: https://arxiv.org/abs/2601.21512v1

Arabic is a linguistically and culturally rich language with a vast vocabulary that spans scientific, religious, and literary domains. Yet, large-scale lexical datasets linking Arabic words to precise definitions remain limited. We present MURAD (Multi-domain Unified Reverse Arabic Dictionary), an open lexical dataset with 96,243 word-definition pairs. The data come from trusted reference works and educational sources. Extraction used a hybrid pipeline integrating direct text parsing, optical character recognition, and automated reconstruction. This ensures accuracy and clarity. Each record aligns a target word with its standardized Arabic definition and metadata that identifies the source domain. The dataset covers terms from linguistics, Islamic studies, mathematics, physics, psychology, and engineering. It supports computational linguistics and lexicographic research. Applications include reverse dictionary modeling, semantic retrieval, and educational tools. By releasing this resource, we aim to advance Arabic natural language processing and promote reproducible research on Arabic lexical semantics.

---

### LLaMEA-SAGE: Guiding Automated Algorithm Design with Structural Feedback from Explainable AI

Authors: Niki van Stein, Anna V. Kononova, Lars Kotthoff, Thomas Bäck
Published: 2026-01-29
Categories: cs.AI, cs.NE, cs.SE
arXiv: https://arxiv.org/abs/2601.21511v1

Large language models have enabled automated algorithm design (AAD) by generating optimization algorithms directly from natural-language prompts. While evolutionary frameworks such as LLaMEA demonstrate strong exploratory capabilities across the algorithm design space, their search dynamics are entirely driven by fitness feedback, leaving substantial information about the generated code unused. We propose a mechanism for guiding AAD using feedback constructed from graph-theoretic and complexity features extracted from the abstract syntax trees of the generated algorithms, based on a surrogate model learned over an archive of evaluated solutions. Using explainable AI techniques, we identify features that substantially affect performance and translate them into natural-language mutation instructions that steer subsequent LLM-based code generation without restricting expressivity. We propose LLaMEA-SAGE, which integrates this feature-driven guidance into LLaMEA, and evaluate it across several benchmarks. We show that the proposed structured guidance achieves the same performance faster than vanilla LLaMEA in a small controlled experiment. In a larger-scale experiment using the MA-BBOB suite from the GECCO-MA-BBOB competition, our guided approach achieves superior performance compared to state-of-the-art AAD methods. These results demonstrate that signals derived from code can effectively bias LLM-driven algorithm evolution, bridging the gap between code structure and human-understandable performance feedback in automated algorithm design.

---

### The Effectiveness of Style Vectors for Steering Large Language Models: A Human Evaluation

Authors: Diaoulé Diallo, Katharina Dworatzyk, Sophie Jentzsch, Peer Schütt, Sabine Theis, Tobias Hecking
Published: 2026-01-29
Categories: cs.AI, cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2601.21505v1

Controlling the behavior of large language models (LLMs) at inference time is essential for aligning outputs with human abilities and safety requirements. \emph{Activation steering} provides a lightweight alternative to prompt engineering and fine-tuning by directly modifying internal activations to guide generation. This research advances the literature in three significant directions. First, while previous work demonstrated the technical feasibility of steering emotional tone using automated classifiers, this paper presents the first human evaluation of activation steering concerning the emotional tone of LLM outputs, collecting over 7,000 crowd-sourced ratings from 190 participants via Prolific ($n=190$). These ratings assess both perceived emotional intensity and overall text quality. Second, we find strong alignment between human and model-based quality ratings (mean $r=0.776$, range $0.157$--$0.985$), indicating automatic scoring can proxy perceived quality. Moderate steering strengths ($λ\approx 0.15$) reliably amplify target emotions while preserving comprehensibility, with the strongest effects for disgust ($η_p^2 = 0.616$) and fear ($η_p^2 = 0.540$), and minimal effects for surprise ($η_p^2 = 0.042$). Finally, upgrading from Alpaca to LlaMA-3 yielded more consistent steering with significant effects across emotions and strengths (all $p < 0.001$). Inter-rater reliability was high (ICC $= 0.71$--$0.87$), underscoring the robustness of the findings. These findings support activation-based control as a scalable method for steering LLM behavior across affective dimensions.

---

### MAR: Efficient Large Language Models via Module-aware Architecture Refinement

Authors: Junhong Cai, Guiqin Wang, Kejie Zhao, Jianxiong Tang, Xiang Wang, Luziwei Leng, Ran Cheng, Yuxin Ma, Qinghai Guo
Published: 2026-01-29
Categories: cs.AI, cs.CL, cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2601.21503v1

Large Language Models (LLMs) excel across diverse domains but suffer from high energy costs due to quadratic attention and dense Feed-Forward Network (FFN) operations. To address these issues, we propose Module-aware Architecture Refinement (MAR), a two-stage framework that integrates State Space Models (SSMs) for linear-time sequence modeling and applies activation sparsification to reduce FFN costs. In addition, to mitigate low information density and temporal mismatch in integrating Spiking Neural Networks (SNNs) with SSMs, we design the Adaptive Ternary Multi-step Neuron (ATMN) and the Spike-aware Bidirectional Distillation Strategy (SBDS). Extensive experiments demonstrate that MAR effectively restores the performance of its dense counterpart under constrained resources while substantially reducing inference energy consumption. Furthermore, it outperforms efficient models of comparable or even larger scale, underscoring its potential for building efficient and practical LLMs.

---

### Task-Awareness Improves LLM Generations and Uncertainty

Authors: Tim Tomov, Dominik Fuchsgruber, Stephan Günnemann
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21500v2

In many applications of LLMs, natural language responses often have an underlying structure such as representing discrete labels, numerical values, or graphs. Yet, existing decoding and uncertainty estimation methods operate only in language space and largely disregard structural information. We address this by modeling LLM outputs directly in a task-dependent latent structure. By equipping this structure with a dissimilarity measure, we can compute Bayes-optimal responses. These are not selected from sampled generations but are newly synthesized by combining individual responses in the latent space. Across different tasks, Bayes-optimal responses consistently outperform standard decoding methods like beam search. Moreover, quantifying uncertainty via the induced Bayesian risk captures variations in terms of the latent structure and improves alignment with output quality and correctness. Our decision-theoretic framework is applicable to any problem that admits a latent response structure and enables reliable task-aware LLM predictions.

---

### SimGraph: A Unified Framework for Scene Graph-Based Image Generation and Editing

Authors: Thanh-Nhan Vo, Trong-Thuan Nguyen, Tam V. Nguyen, Minh-Triet Tran
Published: 2026-01-29
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.21498v1

Recent advancements in Generative Artificial Intelligence (GenAI) have significantly enhanced the capabilities of both image generation and editing. However, current approaches often treat these tasks separately, leading to inefficiencies and challenges in maintaining spatial consistency and semantic coherence between generated content and edits. Moreover, a major obstacle is the lack of structured control over object relationships and spatial arrangements. Scene graph-based methods, which represent objects and their interrelationships in a structured format, offer a solution by providing greater control over composition and interactions in both image generation and editing. To address this, we introduce SimGraph, a unified framework that integrates scene graph-based image generation and editing, enabling precise control over object interactions, layouts, and spatial coherence. In particular, our framework integrates token-based generation and diffusion-based editing within a single scene graph-driven model, ensuring high-quality and consistent results. Through extensive experiments, we empirically demonstrate that our approach outperforms existing state-of-the-art methods.

---

### The Path of Least Resistance: Guiding LLM Reasoning Trajectories with Prefix Consensus

Authors: Ishan Jindal, Sai Prashanth Akuthota, Jayant Taneja, Sachin Dev Sharma
Published: 2026-01-29
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.21494v2

Large language models achieve strong reasoning performance, but inference strategies such as Self-Consistency (SC) are computationally expensive, as they fully expand all reasoning traces. We introduce PoLR (Path of Least Resistance), the first inference-time method to leverage prefix consistency for compute-efficient reasoning. PoLR clusters short prefixes of reasoning traces, identifies the dominant cluster, and expands all paths in that cluster, preserving the accuracy benefits of SC while substantially reducing token usage and latency. Our theoretical analysis, framed via mutual information and entropy, explains why early reasoning steps encode strong signals predictive of final correctness. Empirically, PoLR consistently matches or exceeds SC across GSM8K, MATH500, AIME24/25, and GPQA-DIAMOND, reducing token usage by up to 60% and wall-clock latency by up to 50%. Moreover, PoLR is fully complementary to adaptive inference methods (e.g., Adaptive Consistency, Early-Stopping SC) and can serve as a drop-in pre-filter, making SC substantially more efficient and scalable without requiring model fine-tuning.

---

### Manifold constrained steepest descent for smooth and closed-set optimization

Authors: Kaiwei Yang, Lexiao Lai
Published: 2026-01-29
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2601.21487v2

We study minimization of smooth functions over feasible sets that have smooth embedded-manifold structure throughout or only on selected regions, using linear minimization oracles (LMOs) to determine search directions under user-chosen norms. Restricting an LMO to a tangent space, however, can require an iterative inner solve. We propose \emph{Manifold Constrained Steepest Descent} (MCSD) and a tangent-projected variant, MCSD-TP, which avoid solving tangent-space LMO subproblems iteratively. The spectral-norm specialization of MCSD on the Stiefel manifold yields \emph{SPEL}, which admits an efficient implementation using matrix-sign computations. Under standard regularity assumptions, both methods attain an \(O(\log T/\sqrt T)\) best-iterate stationarity bound. For closed feasible sets, the hybrid MCSD--PGD combines either smooth method with projected gradient descent; under the corresponding local smoothness condition, every accumulation point is Bouligand stationary. Experiments on Stiefel-constrained PCA, weighted low-rank approximation, and sparse phase retrieval illustrate the proposed methods.

---

### ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment

Authors: Xiuyu Li, Jinkai Zhang, Mingyang Yi, Yu Li, Longqiang Wang, Yue Wang, Ju Fan
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.21484v3

Reinforcement Learning (RL) post-training alignment for language models is effective, but also costly and unstable in practice, owing to its complicated training process. To address this, we propose a training-free inference method to sample directly from the optimal RL policy. The transition probability applied to Masked Language Modeling (MLM) consists of a reference policy model and an energy term. Based on this, our algorithm, Energy-Guided Test-Time Scaling (ETS), estimates the key energy term via online Monte Carlo, with a provable convergence rate. Moreover, to ensure practical efficiency, ETS leverages modern acceleration frameworks alongside tailored importance sampling estimators, substantially reducing inference latency while provably preserving sampling quality. Experiments on MLM (including autoregressive models and diffusion language models) across reasoning, coding, and science benchmarks show that our ETS consistently improves generation quality, validating its effectiveness and design. The code is available at https://github.com/sheriyuo/ETS.

---

### DimStance: Multilingual Datasets for Dimensional Stance Analysis

Authors: Jonas Becker, Liang-Chih Yu, Shamsuddeen Hassan Muhammad, Jan Philip Wahle, Terry Ruas, Idris Abdulmumin, Lung-Hao Lee, Nelson Odhiambo, Lilian Wanzare, Wen-Ni Liu, Tzu-Mi Lin, Zhe-Yu Xu et al.
Published: 2026-01-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.21483v2

Stance detection is an established task that classifies an author's attitude toward a specific target into categories such as Favor, Neutral, and Against. Beyond categorical stance labels, we leverage a long-established affective science framework to model stance along real-valued dimensions of valence (negative-positive) and arousal (calm-active). This dimensional approach captures nuanced affective states underlying stance expressions, enabling fine-grained stance analysis. To this end, we introduce DimStance, the first dimensional stance resource with valence-arousal (VA) annotations. This resource comprises 11,746 target aspects in 7,365 texts across five languages (English, German, Chinese, Nigerian Pidgin, and Swahili) and two domains (politics and environmental protection). To facilitate the evaluation of stance VA prediction, we formulate the dimensional stance regression task, analyze cross-lingual VA patterns, and benchmark pretrained and large language models under regression and prompting settings. Results show competitive performance of fine-tuned LLM regressors, persistent challenges in low-resource languages, and limitations of token-based generation. DimStance provides a foundation for multilingual, emotion-aware, stance analysis and benchmarking.

---

### Hypernetwork-Based Adaptive Aggregation for Multimodal Multiple-Instance Learning in Predicting Coronary Calcium Debulking

Authors: Kaito Shiku, Ichika Seo, Tetsuya Matoba, Rissei Hino, Yasuhiro Nakano, Ryoma Bise
Published: 2026-01-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.21479v1

In this paper, we present the first attempt to estimate the necessity of debulking coronary artery calcifications from computed tomography (CT) images. We formulate this task as a Multiple-instance Learning (MIL) problem. The difficulty of this task lies in that physicians adjust their focus and decision criteria for device usage according to tabular data representing each patient's condition. To address this issue, we propose a hypernetwork-based adaptive aggregation transformer (HyperAdAgFormer), which adaptively modifies the feature aggregation strategy for each patient based on tabular data through a hypernetwork. The experiments using the clinical dataset demonstrated the effectiveness of HyperAdAgFormer. The code is publicly available at https://github.com/Shiku-Kaito/HyperAdAgFormer.

---