# Research Papers — 2026-01 · bundle page 21 of 189 > Full-text markdown of papers #1001–1050 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/21 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/20.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/22.md) ### A Systematic Literature Review on LLM Defenses Against Prompt Injection and Jailbreaking: Expanding NIST Taxonomy Authors: Pedro H. Barcha Correia, Ryan W. Achjian, Diego E. G. Caetano de Oliveira, Ygor Acacio Maria, Victor Takashi Hayashi, Marcos Lopes, Charles Christian Miers, Marcos A. Simplicio Published: 2026-01-29 Categories: cs.CR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.22240v1 The rapid advancement and widespread adoption of generative artificial intelligence (GenAI) and large language models (LLMs) has been accompanied by the emergence of new security vulnerabilities and challenges, such as jailbreaking and other prompt injection attacks. These maliciously crafted inputs can exploit LLMs, causing data leaks, unauthorized actions, or compromised outputs, for instance. As both offensive and defensive prompt injection techniques evolve quickly, a structured understanding of mitigation strategies becomes increasingly important. To address that, this work presents the first systematic literature review on prompt injection mitigation strategies, comprehending 88 studies. Building upon NIST's report on adversarial machine learning, this work contributes to the field through several avenues. First, it identifies studies beyond those documented in NIST's report and other academic reviews and surveys. Second, we propose an extension to NIST taxonomy by introducing additional categories of defenses. Third, by adopting NIST's established terminology and taxonomy as a foundation, we promote consistency and enable future researchers to build upon the standardized taxonomy proposed in this work. Finally, we provide a comprehensive catalog of the reviewed prompt injection defenses, documenting their reported quantitative effectiveness across specific LLMs and attack datasets, while also indicating which solutions are open-source and model-agnostic. This catalog, together with the guidelines presented herein, aims to serve as a practical resource for researchers advancing the field of adversarial machine learning and for developers seeking to implement effective defenses in production systems. --- ### Geometry without Position? When Positional Embeddings Help and Hurt Spatial Reasoning Authors: Jian Shi, Michael Birsak, Wenqing Cui, Zhenyu Li, Peter Wonka Published: 2026-01-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22231v1 This paper revisits the role of positional embeddings (PEs) within vision transformers (ViTs) from a geometric perspective. We show that PEs are not mere token indices but effectively function as geometric priors that shape the spatial structure of the representation. We introduce token-level diagnostics that measure how multi-view geometric consistency in ViT representation depends on consitent PEs. Through extensive experiments on 14 foundation ViT models, we reveal how PEs influence multi-view geometry and spatial reasoning. Our findings clarify the role of PEs as a causal mechanism that governs spatial structure in ViT representations. Our code is provided in https://github.com/shijianjian/vit-geometry-probes --- ### DAJ: Data-Reweighted LLM Judge for Test-Time Scaling in Code Generation Authors: Peijia Qin, Ruiyi Zhang, Qi Cao, Pengtao Xie Published: 2026-01-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22230v1 Test-time scaling for code generation commonly relies on Best-of-N selection, in which multiple candidate solutions are sampled from a base model, and the best one is selected by an LLM judge. However, training reliable LLM judges is challenging due to severe distribution shifts, including imbalances between easy and hard problems, mismatches between training tasks and evaluation benchmarks, and trajectory mismatch arising from training data generated by cheaper models whose behavior differs from that of inference-time models. We propose DAJ, a reasoning-based LLM judge trained with verifiable rewards under a bi-level data-reweighted learning framework. The proposed framework learns data-importance weights (either domain-level or instance-level) to optimize generalization performance on a held-out meta set aligned with target benchmarks. To the best of our knowledge, this is the first application of data reweighting to LLM-as-a-Judge training for test-time scaling. Our approach automatically emphasizes hard problems, in-distribution samples, and trajectory-aligned data, without relying on hand-crafted heuristics. Empirically, DAJ achieves state-of-the-art performance on LiveCodeBench and BigCodeBench, outperforming strong test-time scaling baselines as well as leading proprietary models. --- ### Lost in Space? Vision-Language Models Struggle with Relative Camera Pose Estimation Authors: Ken Deng, Yifu Qiu, Yoni Kasten, Shay B. Cohen, Yftah Ziser Published: 2026-01-29 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.22228v2 We study whether vision-language models (VLMs) can solve relative camera pose estimation (RCPE) from image pairs, a direct test of multi-view spatial reasoning. We cast RCPE as a discrete verbal classification task and introduce \texttt{VRRPI-Bench}, built from real RGB-D frames with object-centric camera motion, and \texttt{VRRPI-Diag}, which isolates individual motion degrees of freedom. Humans (0.91) and specialized geometric pipelines such as LoFTR (0.99) solve the task reliably, yet the best VLM reaches only 0.66 and most others remain near random. Our analyses show that this gap is not basic spatial competence: strong VLMs are near ceiling on single-image benchmarks, but most remain near random once reasoning must span views. They are unstable under source-target reversal (best 59.7\% consistency) and remain weak even in simplified single-DoF settings, especially on optical-axis motions such as roll and depth translation (GPT-5: 0.46 on roll). These failures are useful: they localize concrete missing capabilities, namely cross-view correspondence, view-consistent reasoning, and projective camera-motion understanding, making RCPE a targeted diagnostic for improving multi-view spatial reasoning in VLMs. --- ### What Lies Beneath: A Call for Distribution-based Visual Question & Answer Datasets Authors: Jill P. Naiman, Daniel J. Evans, JooYoung Seo Published: 2026-01-29 Categories: cs.CV, cs.DL arXiv: https://arxiv.org/abs/2601.22218v1 Visual Question Answering (VQA) has become an important benchmark for assessing how large multimodal models (LMMs) interpret images. However, most VQA datasets focus on real-world images or simple diagrammatic analysis, with few focused on interpreting complex scientific charts. Indeed, many VQA datasets that analyze charts do not contain the underlying data behind those charts or assume a 1-to-1 correspondence between chart marks and underlying data. In reality, charts are transformations (i.e. analysis, simplification, modification) of data. This distinction introduces a reasoning challenge in VQA that the current datasets do not capture. In this paper, we argue for a dedicated VQA benchmark for scientific charts where there is no 1-to-1 correspondence between chart marks and underlying data. To do so, we survey existing VQA datasets and highlight limitations of the current field. We then generate synthetic histogram charts based on ground truth data, and ask both humans and a large reasoning model questions where precise answers depend on access to the underlying data. We release the open-source dataset, including figures, underlying data, distribution parameters used to generate the data, and bounding boxes for all figure marks and text for future research. --- ### Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions Authors: Lingkai Kong, Anagha Satish, Hezi Jiang, Akseli Kangaslahti, Andrew Ma, Wenbo Chen, Mingxiao Song, Lily Xu, Milind Tambe Published: 2026-01-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22211v2 Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical. Existing approaches embed task-specific value functions into constrained optimization programs or learn deterministic structured policies, sacrificing generality and policy expressiveness. We propose a solver-induced \emph{latent spherical flow policy} that brings the expressiveness of modern generative policies to combinatorial RL while guaranteeing feasibility by design. Our method, LSFlow, learns a \emph{stochastic} policy in a compact continuous latent space via spherical flow matching, and delegates feasibility to a combinatorial optimization solver that maps each latent sample to a valid structured action. To improve efficiency, we train the value network directly in the latent space, avoiding repeated solver calls during policy optimization. To address the piecewise-constant and discontinuous value landscape induced by solver-based action selection, we introduce a smoothed Bellman operator that yields stable, well-defined learning targets. Empirically, our approach outperforms state-of-the-art baselines by an average of 20.6\% across a range of challenging combinatorial RL tasks. --- ### Learning to Recommend Multi-Agent Subgraphs from Calling Trees Authors: Xinyuan Song, Liang Zhao Published: 2026-01-29 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2601.22209v1 Multi-agent systems (MAS) increasingly solve complex tasks by orchestrating agents and tools selected from rapidly growing marketplaces. As these marketplaces expand, many candidates become functionally overlapping, making selection not just a retrieval problem: beyond filtering relevant agents, an orchestrator must choose options that are reliable, compatible with the current execution context, and able to cooperate with other selected agents. Existing recommender systems -- largely built for item-level ranking from flat user-item logs -- do not directly address the structured, sequential, and interaction-dependent nature of agent orchestration. We address this gap by \textbf{formulating agent recommendation in MAS as a constrained decision problem} and introducing a generic \textbf{constrained recommendation framework} that first uses retrieval to build a compact candidate set conditioned on the current subtask and context, and then performs \textbf{utility optimization} within this feasible set using a learned scorer that accounts for relevance, reliability, and interaction effects. We ground both the formulation and learning signals in \textbf{historical calling trees}, which capture the execution structure of MAS (parent-child calls, branching dependencies, and local cooperation patterns) beyond what flat logs provide. The framework supports two complementary settings: \textbf{agent-level recommendation} (select the next agent/tool) and \textbf{system-level recommendation} (select a small, connected agent team/subgraph for coordinated execution). To enable systematic evaluation, we construct a unified calling-tree benchmark by normalizing invocation logs from eight heterogeneous multi-agent corpora into a shared structured representation. --- ### Causal Imitation Learning Under Measurement Error and Distribution Shift Authors: Shi Bo, AmirEmad Ghassami Published: 2026-01-29 Categories: cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2601.22206v1 We study offline imitation learning (IL) when part of the decision-relevant state is observed only through noisy measurements and the distribution may change between training and deployment. Such settings induce spurious state-action correlations, so standard behavioral cloning (BC) -- whether conditioning on raw measurements or ignoring them -- can converge to systematically biased policies under distribution shift. We propose a general framework for IL under measurement error, inspired by explicitly modeling the causal relationships among the variables, yielding a target that retains a causal interpretation and is robust to distribution shift. Building on ideas from proximal causal inference, we introduce \texttt{CausIL}, which treats noisy state observations as proxy variables, and we provide identification conditions under which the target policy is recoverable from demonstrations without rewards or interactive expert queries. We develop estimators for both discrete and continuous state spaces; for continuous settings, we use an adversarial procedure over RKHS function classes to learn the required parameters. We evaluate \texttt{CausIL} on semi-simulated longitudinal data from the PhysioNet/Computing in Cardiology Challenge 2019 cohort and demonstrate improved robustness to distribution shift compared to BC baselines. --- ### FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation Authors: S M Ruhul Kabir Howlader, Xiao Chen, Yifei Xie, Lu Liu Published: 2026-01-29 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2601.22204v2 Federated learning (FL) encounters substantial challenges due to heterogeneity, leading to gradient noise, client drift, and partial client participation errors, the last of which is the most pervasive but remains insufficiently addressed in current literature. In this paper, we propose FedAdaVR, a novel FL algorithm aimed at solving heterogeneity issues caused by sporadic client participation by incorporating an adaptive optimiser with a variance reduction technique. This method takes advantage of the most recent stored updates from clients, even when they are absent from the current training round, thereby emulating their presence. Furthermore, we propose FedAdaVR-Quant, which stores client updates in quantised form, significantly reducing the memory requirements (by 50%, 75%, and 87.5%) of FedAdaVR while maintaining highly competitive model performance. We analyse the convergence behaviour of FedAdaVR under general nonconvex conditions and prove that our proposed algorithm can eliminate partial client participation error. Extensive experiments conducted on multiple datasets, under both independent and identically distributed (IID) and non-IID settings, demonstrate that FedAdaVR consistently outperforms state-of-the-art baseline methods. --- ### Beyond Conditional Computation: Retrieval-Augmented Genomic Foundation Models with Gengram Authors: Huinan Xu, Xuyang Feng, Junhong Chen, Junchen Liu, Kaiwen Deng, Kai Ding, Shengning Long, Jiaxue Shuai, Zhaorong Li, Shiping Liu, Guirong Xue, Zhan Xiao Published: 2026-01-29 Categories: q-bio.GN, cs.AI arXiv: https://arxiv.org/abs/2601.22203v1 Current genomic foundation models (GFMs) rely on extensive neural computation to implicitly approximate conserved biological motifs from single-nucleotide inputs. We propose Gengram, a conditional memory module that introduces an explicit and highly efficient lookup primitive for multi-base motifs via a genomic-specific hashing scheme, establishing genomic "syntax". Integrated into the backbone of state-of-the-art GFMs, Gengram achieves substantial gains (up to 14%) across several functional genomics tasks. The module demonstrates robust architectural generalization, while further inspection of Gengram's latent space reveals the emergence of meaningful representations that align closely with fundamental biological knowledge. By establishing structured motif memory as a modeling primitive, Gengram simultaneously boosts empirical performance and mechanistic interpretability, providing a scalable and biology-aligned pathway for the next generation of GFMs. The code is available at https://github.com/zhejianglab/Genos, and the model checkpoint is available at https://huggingface.co/ZhejiangLab/Gengram. --- ### A Survey on Semantic Communication for Vision: Categories, Frameworks, Enabling Techniques, and Applications Authors: Runze Cheng, Yao Sun, Ahmad Taha, Xuesong Liu, David Flynn, Muhammad Ali Imran Published: 2026-01-29 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2601.22202v2 Semantic communication (SemCom) emerges as a transformative paradigm for traffic-intensive visual data transmission, shifting focus from raw data to meaningful content transmission and relieving the increasing pressure on communication resources. However, to achieve SemCom, challenges are faced in accurate semantic quantization for visual data, robust semantic extraction and reconstruction under diverse tasks and goals, transceiver coordination with effective knowledge utilization, and adaptation to unpredictable wireless communication environments. In this paper, we present a systematic review of SemCom for visual data transmission (SemCom-Vision), wherein an interdisciplinary analysis integrating computer vision (CV) and communication engineering is conducted to provide comprehensive guidelines for the machine learning (ML)-empowered SemCom-Vision design. Specifically, this survey first elucidates the basics and key concepts of SemCom. Then, we introduce a novel classification perspective to categorize existing SemCom-Vision approaches as semantic preservation communication (SPC), semantic expansion communication (SEC), and semantic refinement communication (SRC) based on communication goals interpreted through semantic quantization schemes. Moreover, this survey articulates the ML-based encoder-decoder models and training algorithms for each SemCom-Vision category, followed by knowledge structure and utilization strategies. Finally, we discuss potential SemCom-Vision applications. --- ### Adaptive Benign Overfitting (ABO): Overparameterized RLS for Online Learning in Non-stationary Time-series Authors: Luis Ontaneda Mijares, Nick Firoozye Published: 2026-01-29 Categories: q-fin.ST, cs.LG, cs.MS, math.NA, stat.ML arXiv: https://arxiv.org/abs/2601.22200v1 Overparameterized models have recently challenged conventional learning theory by exhibiting improved generalization beyond the interpolation limit, a phenomenon known as benign overfitting. This work introduces Adaptive Benign Overfitting (ABO), extending the recursive least-squares (RLS) framework to this regime through a numerically stable formulation based on orthogonal-triangular updates. A QR-based exponentially weighted RLS (QR-EWRLS) algorithm is introduced, combining random Fourier feature mappings with forgetting-factor regularization to enable online adaptation under non-stationary conditions. The orthogonal decomposition prevents the numerical divergence associated with covariance-form RLS while retaining adaptability to evolving data distributions. Experiments on nonlinear synthetic time series confirm that the proposed approach maintains bounded residuals and stable condition numbers while reproducing the double-descent behavior characteristic of overparameterized models. Applications to forecasting foreign exchange and electricity demand show that ABO is highly accurate (comparable to baseline kernel methods) while achieving speed improvements of between 20 and 40 percent. The results provide a unified view linking adaptive filtering, kernel approximation, and benign overfitting within a stable online learning framework. --- ### Advanced techniques and applications of LiDAR Place Recognition in Agricultural Environments: A Comprehensive Survey Authors: Judith Vilella-Cantos, Mónica Ballesta, David Valiente, María Flores, Luis Payá Published: 2026-01-29 Categories: cs.RO, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2601.22198v1 An optimal solution to the localization problem is essential for developing autonomous robotic systems. Apart from autonomous vehicles, precision agriculture is one of the elds that can bene t most from these systems. Although LiDAR place recognition is a widely used technique in recent years to achieve accurate localization, it is mostly used in urban settings. However, the lack of distinctive features and the unstructured nature of agricultural environments make place recognition challenging. This work presents a comprehensive review of state-of-the-art the latest deep learning applications for agricultural environments and LPR techniques. We focus on the challenges that arise in these environments. We analyze the existing approaches, datasets, and metrics used to evaluate LPR system performance and discuss the limitations and future directions of research in this eld. This is the rst survey that focuses on LiDAR based localization in agricultural settings, with the aim of providing a thorough understanding and fostering further research in this specialized domain. --- ### Neural Signals Generate Clinical Notes in the Wild Authors: Jathurshan Pradeepkumar, Zheng Chen, Jimeng Sun Published: 2026-01-29 Categories: cs.LG, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2601.22197v3 Generating clinical reports that summarize abnormal patterns, diagnostic findings, and clinical interpretations from long-term EEG recordings remains labor-intensive. We present CELM, the first clinical EEG-to-Language foundation model capable of summarizing long-duration, variable-length EEG recordings and performing end-to-end clinical report generation at multiple scales. CELM integrates pretrained EEG foundation models with language models to enable scalable multimodal learning. We curate a large-scale clinical EEG dataset containing 9,922 reports paired with approximately 11,000 hours of EEG recordings from 9,048 patients to train CELM, and release the benchmark with an automated report-structuring pipeline to facilitate future research. Experimental results show that CELM consistently outperforms existing methods across all evaluation settings. Importantly, we further conduct human evaluation with clinical experts, demonstrating that CELM generates reports that are more clinically coherent, diagnostically reliable, and better aligned with expert interpretation. We release our model and benchmark construction pipeline at https://github.com/Jathurshan0330/CELM. --- ### Multitask Learning for Earth Observation Data Classification with Hybrid Quantum Network Authors: Fan Fan, Yilei Shi, Tobias Guggemos, Xiao Xiang Zhu Published: 2026-01-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.22195v1 Quantum machine learning (QML) has gained increasing attention as a potential solution to address the challenges of computation requirements in the future. Earth observation (EO) has entered the era of Big Data, and the computational demands for effectively analyzing large EO data with complex deep learning models have become a bottleneck. Motivated by this, we aim to leverage quantum computing for EO data classification and explore its advantages despite the current limitations of quantum devices. This paper presents a hybrid model that incorporates multitask learning to assist efficient data encoding and employs a location weight module with quantum convolution operations to extract valid features for classification. The validity of our proposed model was evaluated using multiple EO benchmarks. Additionally, we experimentally explored the generalizability of our model and investigated the factors contributing to its advantage, highlighting the potential of QML in EO data analysis. --- ### Practical Evaluation of Quantum Kernel Methods for Radar Micro-Doppler Classification on Noisy Intermediate-Scale Quantum (NISQ) Hardware Authors: Vikas Agnihotri, Jasleen Kaur, Sarvagya Kaushik Published: 2026-01-29 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2601.22194v1 This paper examines the application of a Quantum Support Vector Machine (QSVM) for radarbased aerial target classification using micro-Doppler signatures. Classical features are extracted and reduced via Principal Component Analysis (PCA) to enable efficient quantum encoding. The reduced feature vectors are embedded into a quantum kernel-induced feature space using a fully entangled ZZFeatureMap and classified using a kernel based QSVM. Performance is first evaluated on a quantum simulator and subsequently validated on NISQ-era superconducting quantum hardware, specifically the IBM Torino (133-qubit) and IBM Fez (156-qubit) processors. Experimental results demonstrate that the QSVM achieves competitive classification performance relative to classical SVM baselines while operating on substantially reduced feature dimensionality. Hardware experiments reveal the impact of noise and decoherence and measurement shot count on quantum kernel estimation, and further show improved stability and fidelity on newer Heron r2 architecture. This study provides a systematic comparison between simulator-based and hardware-based QSVM implementations and highlights both the feasibility and current limitations of deploying quantum kernel methods for practical radar signal classification tasks. --- ### SCENE: Semantic-aware Codec Enhancement with Neural Embeddings Authors: Han-Yu Lin, Li-Wei Chen, Hung-Shin Lee Published: 2026-01-29 Categories: eess.IV, cs.CV, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2601.22189v1 Compression artifacts from standard video codecs often degrade perceptual quality. We propose a lightweight, semantic-aware pre-processing framework that enhances perceptual fidelity by selectively addressing these distortions. Our method integrates semantic embeddings from a vision-language model into an efficient convolutional architecture, prioritizing the preservation of perceptually significant structures. The model is trained end-to-end with a differentiable codec proxy, enabling it to mitigate artifacts from various standard codecs without modifying the existing video pipeline. During inference, the codec proxy is discarded, and SCENE operates as a standalone pre-processor, enabling real-time performance. Experiments on high-resolution benchmarks show improved performance over baselines in both objective (MS-SSIM) and perceptual (VMAF) metrics, with notable gains in preserving detailed textures within salient regions. Our results show that semantic-guided, codec-aware pre-processing is an effective approach for enhancing compressed video streams. --- ### RedSage: A Cybersecurity Generalist LLM Authors: Naufal Suryanto, Muzammal Naseer, Pengfei Li, Syed Talal Wasim, Jinhui Yi, Juergen Gall, Paolo Ceravolo, Ernesto Damiani Published: 2026-01-29 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.22159v2 Cybersecurity operations demand assistant LLMs that support diverse workflows without exposing sensitive data. Existing solutions either rely on proprietary APIs with privacy risks or on open models lacking domain adaptation. To bridge this gap, we curate 11.8B tokens of cybersecurity-focused continual pretraining data via large-scale web filtering and manual collection of high-quality resources, spanning 28.6K documents across frameworks, offensive techniques, and security tools. Building on this, we design an agentic augmentation pipeline that simulates expert workflows to generate 266K multi-turn cybersecurity samples for supervised fine-tuning. Combined with general open-source LLM data, these resources enable the training of RedSage, an open-source, locally deployable cybersecurity assistant with domain-aware pretraining and post-training. To rigorously evaluate the models, we introduce RedSage-Bench, a benchmark with 30K multiple-choice and 240 open-ended Q&A items covering cybersecurity knowledge, skills, and tool expertise. RedSage is further evaluated on established cybersecurity benchmarks (e.g., CTI-Bench, CyberMetric, SECURE) and general LLM benchmarks to assess broader generalization. At the 8B scale, RedSage achieves consistently better results, surpassing the baseline models by up to +5.59 points on cybersecurity benchmarks and +5.05 points on Open LLM Leaderboard tasks. These findings demonstrate that domain-aware agentic augmentation and pre/post-training can not only enhance cybersecurity-specific expertise but also help to improve general reasoning and instruction-following. All models, datasets, and code are publicly available. --- ### One-step Latent-free Image Generation with Pixel Mean Flows Authors: Yiyang Lu, Susie Lu, Qiao Sun, Hanhong Zhao, Zhicheng Jiang, Xianbang Wang, Tianhong Li, Zhengyang Geng, Kaiming He Published: 2026-01-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22158v3 Modern diffusion/flow-based models for image generation typically exhibit two core characteristics: (i) using multi-step sampling, and (ii) operating in a latent space. Recent advances have made encouraging progress on each aspect individually, paving the way toward one-step diffusion/flow without latents. In this work, we take a further step towards this goal and propose "pixel MeanFlow" (pMF). Our core guideline is to formulate the network output space and the loss space separately. The network target is designed to be on a presumed low-dimensional image manifold (i.e., x-prediction), while the loss is defined via MeanFlow in the velocity space. We introduce a simple transformation between the image manifold and the average velocity field. In experiments, pMF achieves strong results for one-step latent-free generation on ImageNet at 256x256 resolution (2.22 FID) and 512x512 resolution (2.48 FID), filling a key missing piece in this regime. We hope that our study will further advance the boundaries of diffusion/flow-based generative models. --- ### Discovering Hidden Gems in Model Repositories Authors: Jonathan Kahana, Eliahu Horwitz, Yedid Hoshen Published: 2026-01-29 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2601.22157v1 Public repositories host millions of fine-tuned models, yet community usage remains disproportionately concentrated on a small number of foundation checkpoints. We investigate whether this concentration reflects efficient market selection or if superior models are systematically overlooked. Through an extensive evaluation of over 2,000 models, we show the prevalence of "hidden gems", unpopular fine-tunes that significantly outperform their popular counterparts. Notably, within the Llama-3.1-8B family, we find rarely downloaded checkpoints that improve math performance from 83.2% to 96.0% without increasing inference costs. However, discovering these models through exhaustive evaluation of every uploaded model is computationally infeasible. We therefore formulate model discovery as a Multi-Armed Bandit problem and accelerate the Sequential Halving search algorithm by using shared query sets and aggressive elimination schedules. Our method retrieves top models with as few as 50 queries per candidate, accelerating discovery by over 50x. --- ### Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts Authors: Yingfa Chen, Zhen Leng Thai, Zihan Zhou, Zhu Zhang, Xingyu Shen, Shuo Wang, Chaojun Xiao, Xu Han, Zhiyuan Liu Published: 2026-01-29 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.22156v1 Hybrid Transformer architectures, which combine softmax attention blocks and recurrent neural networks (RNNs), have shown a desirable performance-throughput tradeoff for long-context modeling, but their adoption and studies are hindered by the prohibitive cost of large-scale pre-training from scratch. Some recent studies have shown that pre-trained softmax attention blocks can be converted into RNN blocks through parameter transfer and knowledge distillation. However, these transfer methods require substantial amounts of training data (more than 10B tokens), and the resulting hybrid models also exhibit poor long-context performance, which is the scenario where hybrid models enjoy significant inference speedups over Transformer-based models. In this paper, we present HALO (Hybrid Attention via Layer Optimization), a pipeline for distilling Transformer models into RNN-attention hybrid models. We then present HypeNet, a hybrid architecture with superior length generalization enabled by a novel position encoding scheme (named HyPE) and various architectural modifications. We convert the Qwen3 series into HypeNet using HALO, achieving performance comparable to the original Transformer models while enjoying superior long-context performance and efficiency. The conversion requires just 2.3B tokens, less than 0.01% of their pre-training data --- ### UEval: A Benchmark for Unified Multimodal Generation Authors: Bo Li, Yida Yin, Wenhao Chai, Xingyu Fu, Zhuang Liu Published: 2026-01-29 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2601.22155v1 We introduce UEval, a benchmark to evaluate unified models, i.e., models capable of generating both images and text. UEval comprises 1,000 expert-curated questions that require both images and text in the model output, sourced from 8 real-world tasks. Our curated questions cover a wide range of reasoning types, from step-by-step guides to textbook explanations. Evaluating open-ended multimodal generation is non-trivial, as simple LLM-as-a-judge methods can miss the subtleties. Different from previous works that rely on multimodal Large Language Models (MLLMs) to rate image quality or text accuracy, we design a rubric-based scoring system in UEval. For each question, reference images and text answers are provided to a MLLM to generate an initial rubric, consisting of multiple evaluation criteria, and human experts then refine and validate these rubrics. In total, UEval contains 10,417 validated rubric criteria, enabling scalable and fine-grained automatic scoring. UEval is challenging for current unified models: GPT-5-Thinking scores only 66.4 out of 100, while the best open-source model reaches merely 49.1. We observe that reasoning models often outperform non-reasoning ones, and transferring reasoning traces from a reasoning model to a non-reasoning model significantly narrows the gap. This suggests that reasoning may be important for tasks requiring complex multimodal understanding and generation. --- ### Exploring Reasoning Reward Model for Agents Authors: Kaixuan Fan, Kaituo Feng, Manyuan Zhang, Tianshuo Peng, Zhixun Li, Yilei Jiang, Shuang Chen, Peng Pei, Xunliang Cai, Xiangyu Yue Published: 2026-01-29 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.22154v2 Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to differentiate intermediate reasoning quality, leading to suboptimal training results. In this paper, we introduce Agent Reasoning Reward Model (Agent-RRM), a multi-faceted reward model that produces structured feedback for agentic trajectories, including (1) an explicit reasoning trace , (2) a focused critique that provides refinement guidance by highlighting reasoning flaws, and (3) an overall score that evaluates process performance. Leveraging these signals, we systematically investigate three integration strategies: Reagent-C (text-augmented refinement), Reagent-R (reward-augmented guidance), and Reagent-U (unified feedback integration). Extensive evaluations across 12 diverse benchmarks demonstrate that Reagent-U yields substantial performance leaps, achieving 43.7% on GAIA and 46.2% on WebWalkerQA, validating the effectiveness of our reasoning reward model and training schemes. Code, models, and datasets are all released to facilitate future research. --- ### DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation Authors: Haozhe Xie, Beichen Wen, Jiarui Zheng, Zhaoxi Chen, Fangzhou Hong, Haiwen Diao, Ziwei Liu Published: 2026-01-29 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2601.22153v1 Manipulating dynamic objects remains an open challenge for Vision-Language-Action (VLA) models, which, despite strong generalization in static manipulation, struggle in dynamic scenarios requiring rapid perception, temporal anticipation, and continuous control. We present DynamicVLA, a framework for dynamic object manipulation that integrates temporal reasoning and closed-loop adaptation through three key designs: 1) a compact 0.4B VLA using a convolutional vision encoder for spatially efficient, structurally faithful encoding, enabling fast multimodal inference; 2) Continuous Inference, enabling overlapping reasoning and execution for lower latency and timely adaptation to object motion; and 3) Latent-aware Action Streaming, which bridges the perception-execution gap by enforcing temporally aligned action execution. To fill the missing foundation of dynamic manipulation data, we introduce the Dynamic Object Manipulation (DOM) benchmark, built from scratch with an auto data collection pipeline that efficiently gathers 200K synthetic episodes across 2.8K scenes and 206 objects, and enables fast collection of 2K real-world episodes without teleoperation. Extensive evaluations demonstrate remarkable improvements in response speed, perception, and generalization, positioning DynamicVLA as a unified framework for general dynamic object manipulation across embodiments. --- ### Late Breaking Results: Conversion of Neural Networks into Logic Flows for Edge Computing Authors: Daniel Stein, Shaoyi Huang, Rolf Drechsler, Bing Li, Grace Li Zhang Published: 2026-01-29 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2601.22151v1 Neural networks have been successfully applied in various resource-constrained edge devices, where usually central processing units (CPUs) instead of graphics processing units exist due to limited power availability. State-of-the-art research still focuses on efficiently executing enormous numbers of multiply-accumulate (MAC) operations. However, CPUs themselves are not good at executing such mathematical operations on a large scale, since they are more suited to execute control flow logic, i.e., computer algorithms. To enhance the computation efficiency of neural networks on CPUs, in this paper, we propose to convert them into logic flows for execution. Specifically, neural networks are first converted into equivalent decision trees, from which decision paths with constant leaves are then selected and compressed into logic flows. Such logic flows consist of if and else structures and a reduced number of MAC operations. Experimental results demonstrate that the latency can be reduced by up to 14.9 % on a simulated RISC-V CPU without any accuracy degradation. The code is open source at https://github.com/TUDa-HWAI/NN2Logic --- ### Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions Authors: Xiaoxiao Sun, Mingyang Li, Kun Yuan, Min Woo Sun, Mark Endo, Shengguang Wu, Changlin Li, Yuhui Zhang, Zeyu Wang, Serena Yeung-Levy Published: 2026-01-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22150v3 Large Vision-Language Models (VLMs) often answer classic visual illusions "correctly" on original images, yet persist with the same responses when illusion factors are inverted, even though the visual change is obvious to humans. This raises a fundamental question: do VLMs perceive visual changes or merely recall memorized patterns? While several studies have noted this phenomenon, the underlying causes remain unclear. To move from observations to systematic understanding, this paper introduces VI-Probe, a controllable visual-illusion framework with graded perturbations and matched visual controls (without illusion inducer) that disentangles visually grounded perception from language-driven recall. Unlike prior work that focuses on averaged accuracy, we measure stability and sensitivity using Polarity-Flip Consistency, Template Fixation Index, and an illusion multiplier normalized against matched controls. Experiments across different families reveal that response persistence arises from heterogeneous causes rather than a single mechanism. For instance, GPT-5 exhibits memory override, Claude-Opus-4.1 shows perception-memory competition, while Qwen variants suggest visual-processing limits. Our findings challenge single-cause views and motivate probing-based evaluation that measures both knowledge and sensitivity to controlled visual change. Data and code are available at https://sites.google.com/view/vi-probe/ --- ### DynaWeb: Model-Based Reinforcement Learning of Web Agents Authors: Hang Ding, Peidong Liu, Junqiao Wang, Ziwei Ji, Meng Cao, Rongzhao Zhang, Lynn Ai, Eric Yang, Tianyu Shi, Lei Yu Published: 2026-01-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.22149v2 The development of autonomous web agents, powered by Large Language Models (LLMs) and reinforcement learning (RL), represents a significant step towards general-purpose AI assistants. However, training these agents is severely hampered by the challenges of interacting with the live internet, which is inefficient, costly, and fraught with risks. Model-based reinforcement learning (MBRL) offers a promising solution by learning a world model of the environment to enable simulated interaction. This paper introduces DynaWeb, a novel MBRL framework that trains web agents through interacting with a web world model trained to predict naturalistic web page representations given agent actions. This model serves as a synthetic web environment where an agent policy can dream by generating vast quantities of rollout action trajectories for efficient online reinforcement learning. Beyond free policy rollouts, DynaWeb incorporates real expert trajectories from training data, which are randomly interleaved with on-policy rollouts during training to improve stability and sample efficiency. Experiments conducted on the challenging WebArena and WebVoyager benchmarks demonstrate that DynaWeb consistently and significantly improves the performance of state-of-the-art open-source web agent models. Our findings establish the viability of training web agents through imagination, offering a scalable and efficient way to scale up online agentic RL. --- ### FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale Authors: Ajay Patel, Colin Raffel, Chris Callison-Burch Published: 2026-01-29 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.22146v3 Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstructured text data. To make the resulting model useful to users, it is further trained on a far smaller amount of "instruction-tuning" data comprised of supervised training examples of instructions and responses. To overcome the limited amount of supervised data, we propose a procedure that can transform the knowledge in internet-scale pre-training documents into billions of synthetic instruction and answer training pairs. The resulting dataset, called FineInstructions, uses ~18M instruction templates created from real user-written queries and prompts. These instruction templates are matched to and instantiated with human-written source documents from unstructured pre-training corpora. With "supervised" synthetic training data generated at this scale, an LLM can be pre-trained from scratch solely with the instruction-tuning objective, which is far more in-distribution with the expected downstream usage of LLMs (responding to user prompts). We conduct controlled token-for-token training experiments and find pre-training on FineInstructions outperforms standard pre-training and other proposed synthetic pre-training techniques on standard benchmarks measuring free-form response quality. Our resources can be found at https://huggingface.co/fineinstructions . --- ### JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion Authors: Anthony Chen, Naomi Ken Korem, Gal Zeevi, Tavi Halperin, Matan Ben Yosef, Urska Jelercic, Ofir Bibi, Or Patashnik, Daniel Cohen-Or Published: 2026-01-29 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2601.22143v2 Audio-Visual Foundation Models, which are pretrained to jointly generate sound and visual content, have recently shown an unprecedented ability to model multi-modal generation and editing, opening new opportunities for downstream tasks. Among these tasks, video dubbing could greatly benefit from such priors, yet most existing solutions still rely on complex, task-specific pipelines that struggle in real-world settings. In this work, we introduce a single-model approach that adapts a foundational audio-video diffusion model for video-to-video dubbing via a lightweight LoRA. The LoRA enables the model to condition on an input audio-video while jointly generating translated audio and synchronized facial motion. To train this LoRA, we leverage the generative model itself to synthesize paired multilingual videos of the same speaker. Specifically, we generate multilingual videos with language switches within a single clip, and then inpaint the face and audio in each half to match the language of the other half. By leveraging the rich generative prior of the audio-visual model, our approach preserves speaker identity and lip synchronization while remaining robust to complex motion and real-world dynamics. We demonstrate that our approach produces high-quality dubbed videos with improved visual fidelity, lip synchronization, and robustness compared to existing dubbing pipelines. --- ### Routing the Lottery: Adaptive Subnetworks for Heterogeneous Data Authors: Grzegorz Stefanski, Alberto Presta, Michal Byra Published: 2026-01-29 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.22141v1 In pruning, the Lottery Ticket Hypothesis posits that large networks contain sparse subnetworks, or winning tickets, that can be trained in isolation to match the performance of their dense counterparts. However, most existing approaches assume a single universal winning ticket shared across all inputs, ignoring the inherent heterogeneity of real-world data. In this work, we propose Routing the Lottery (RTL), an adaptive pruning framework that discovers multiple specialized subnetworks, called adaptive tickets, each tailored to a class, semantic cluster, or environmental condition. Across diverse datasets and tasks, RTL consistently outperforms single- and multi-model baselines in balanced accuracy and recall, while using up to 10 times fewer parameters than independent models and exhibiting semantically aligned. Furthermore, we identify subnetwork collapse, a performance drop under aggressive pruning, and introduce a subnetwork similarity score that enables label-free diagnosis of oversparsification. Overall, our results recast pruning as a mechanism for aligning model structure with data heterogeneity, paving the way toward more modular and context-aware deep learning. --- ### Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers Authors: Xin Chen, Feng Jiang, Yiqian Zhang, Hardy Chen, Shuo Yan, Wenya Xie, Min Yang, Shujian Huang Published: 2026-01-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.22139v2 Reasoning-oriented Large Language Models (LLMs) have achieved remarkable progress with Chain-of-Thought (CoT) prompting, yet they remain fundamentally limited by a \emph{blind self-thinking} paradigm: performing extensive internal reasoning even when critical information is missing or ambiguous. We propose Proactive Interactive Reasoning (PIR), a new reasoning paradigm that transforms LLMs from passive solvers into proactive inquirers that interleave reasoning with clarification. Unlike existing search- or tool-based frameworks that primarily address knowledge uncertainty by querying external environments, PIR targets premise- and intent-level uncertainty through direct interaction with the user. PIR is implemented via two core components: (1) an uncertainty-aware supervised fine-tuning procedure that equips models with interactive reasoning capability, and (2) a user-simulator-based policy optimization framework driven by a composite reward that aligns model behavior with user intent. Extensive experiments on mathematical reasoning, code generation, and document editing demonstrate that PIR consistently outperforms strong baselines, achieving up to 32.70\% higher accuracy, 22.90\% higher pass rate, and 41.36 BLEU improvement, while reducing nearly half of the reasoning computation and unnecessary interaction turns. Further reliability evaluations on factual knowledge, question answering, and missing-premise scenarios confirm the strong generalization and robustness of PIR. Model and code are publicly available at: \href{https://github.com/SUAT-AIRI/Proactive-Interactive-R1} --- ### PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training Authors: Shenghao Yang, Zhichao Wang, Oleg Balabanov, N. Benjamin Erichson, Michael W. Mahoney Published: 2026-01-29 Categories: cs.LG, cs.AI, math.NA, math.OC arXiv: https://arxiv.org/abs/2601.22137v1 Matrix functions such as square root, inverse roots, and orthogonalization play a central role in preconditioned gradient methods for neural network training. This has motivated the development of iterative algorithms that avoid explicit eigendecompositions and rely primarily on matrix multiplications, making them well suited for modern GPU accelerators. We present PRISM (Polynomial-fitting and Randomized Iterative Sketching for Matrix functions computation), a general framework for accelerating iterative algorithms for computing matrix functions. PRISM combines adaptive polynomial approximation with randomized sketching: at each iteration, it fits a polynomial surrogate to the current spectrum via a sketched least-squares problem, adapting to the instance at hand with minimal overhead. We apply PRISM to accelerate Newton-Schulz-like iterations for matrix square roots and orthogonalization, which are core primitives in machine learning. Unlike prior methods, PRISM requires no explicit spectral bounds or singular value estimates; and it adapts automatically to the evolving spectrum. Empirically, PRISM accelerates training when integrated into Shampoo and Muon optimizers. --- ### StepShield: When, Not Whether to Intervene on Rogue Agents Authors: Gloria Felicia, Zitha Sasindran, Jinfeng He, Michael Eniolade, Hemant Kumar, Milan Hussain Angati Published: 2026-01-29 Categories: cs.LG, cs.AI, cs.CR, cs.SE arXiv: https://arxiv.org/abs/2601.22136v2 Agent safety benchmarks measure whether a monitor detects harm, not when. Yet timing is the difference between intervention and autopsy. We introduce StepShield, the first benchmark that treats detection timeliness as a first-class metric. On 9,429 incident-grounded code-agent trajectories, we define the Early Intervention Rate (EIR): the fraction of detected rogue trajectories where the alert fires within a k-step window after the divergence point, isolating timing quality from coverage. This metric exposes what we call the Forensics Trap: a pattern-based guardrail with 847 rules achieves 86% recall yet is statistically indistinguishable from random timing on EIR (0.23 vs. 0.24; p = 0.66, one-sided binomial; difference within CI), because over three-quarters of its alerts trigger on benign prefix code before any violation occurs. The 4x EIR gap between rule-based and semantic detectors is completely invisible to accuracy, recall, or F1. Our finding is structural: regex guardrails detect syntax, not intent, and therefore cannot distinguish the moment an agent turns rogue, rendering the entire deployed class of pattern-based monitors unsuited for real-time oversight. No existing method simultaneously achieves high recall, low false-positive rate, and timely intervention, establishing step-level rogue detection as genuinely unsolved. --- ### PI-Light: Physics-Inspired Diffusion for Full-Image Relighting Authors: Zhexin Liang, Zhaoxi Chen, Yongwei Chen, Tianyi Wei, Tengfei Wang, Xingang Pan Published: 2026-01-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22135v1 Full-image relighting remains a challenging problem due to the difficulty of collecting large-scale structured paired data, the difficulty of maintaining physical plausibility, and the limited generalizability imposed by data-driven priors. Existing attempts to bridge the synthetic-to-real gap for full-scene relighting remain suboptimal. To tackle these challenges, we introduce Physics-Inspired diffusion for full-image reLight ($π$-Light, or PI-Light), a two-stage framework that leverages physics-inspired diffusion models. Our design incorporates (i) batch-aware attention, which improves the consistency of intrinsic predictions across a collection of images, (ii) a physics-guided neural rendering module that enforces physically plausible light transport, (iii) physics-inspired losses that regularize training dynamics toward a physically meaningful landscape, thereby enhancing generalizability to real-world image editing, and (iv) a carefully curated dataset of diverse objects and scenes captured under controlled lighting conditions. Together, these components enable efficient finetuning of pretrained diffusion models while also providing a solid benchmark for downstream evaluation. Experiments demonstrate that $π$-Light synthesizes specular highlights and diffuse reflections across a wide variety of materials, achieving superior generalization to real-world scenes compared with prior approaches. --- ### Early and Prediagnostic Detection of Pancreatic Cancer from Computed Tomography Authors: Wenxuan Li, Pedro R. A. S. Bassi, Lizhou Wu, Xinze Zhou, Yuxuan Zhao, Qi Chen, Szymon Plotka, Tianyu Lin, Zheren Zhu, Marisa Martin, Justin Caskey, Shanshan Jiang et al. Published: 2026-01-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22134v1 Pancreatic ductal adenocarcinoma (PDAC), one of the deadliest solid malignancies, is often detected at a late and inoperable stage. Retrospective reviews of prediagnostic CT scans, when conducted by expert radiologists aware that the patient later developed PDAC, frequently reveal lesions that were previously overlooked. To help detecting these lesions earlier, we developed an automated system named ePAI (early Pancreatic cancer detection with Artificial Intelligence). It was trained on data from 1,598 patients from a single medical center. In the internal test involving 1,009 patients, ePAI achieved an area under the receiver operating characteristic curve (AUC) of 0.939-0.999, a sensitivity of 95.3%, and a specificity of 98.7% for detecting small PDAC less than 2 cm in diameter, precisely localizing PDAC as small as 2 mm. In an external test involving 7,158 patients across 6 centers, ePAI achieved an AUC of 0.918-0.945, a sensitivity of 91.5%, and a specificity of 88.0%, precisely localizing PDAC as small as 5 mm. Importantly, ePAI detected PDACs on prediagnostic CT scans obtained 3 to 36 months before clinical diagnosis that had originally been overlooked by radiologists. It successfully detected and localized PDACs in 75 of 159 patients, with a median lead time of 347 days before clinical diagnosis. Our multi-reader study showed that ePAI significantly outperformed 30 board-certified radiologists by 50.3% (P < 0.05) in sensitivity while maintaining a comparable specificity of 95.4% in detecting PDACs early and prediagnostic. These findings suggest its potential of ePAI as an assistive tool to improve early detection of pancreatic cancer. --- ### Pay for Hints, Not Answers: LLM Shepherding for Cost-Efficient Inference Authors: Ziming Dong, Hardik Sharma, Evan O'Toole, Jaya Prakash Champati, Kui Wu Published: 2026-01-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22132v2 Large Language Models (LLMs) deliver state-of-the-art performance on complex reasoning tasks, but their inference costs limit deployment at scale. Small Language Models (SLMs) offer dramatic cost savings yet lag substantially in accuracy. Existing approaches - routing and cascading - treat the LLM as an all-or-nothing resource: either the query bypasses the LLM entirely, or the LLM generates a complete response at full cost. We introduce LLM Shepherding, a framework that requests only a short prefix (a hint) from the LLM and provides it to SLM. This simple mechanism is surprisingly effective for math and coding tasks: even hints comprising 10-30% of the full LLM response improve SLM accuracy significantly. Shepherding generalizes both routing and cascading, and it achieves lower cost under oracle decision-making. We develop a two-stage predictor that jointly determines whether a hint is needed and how many tokens to request. On the widely-used mathematical reasoning (GSM8K, CNK12) and code generation (HumanEval, MBPP) benchmarks, Shepherding reduces costs by 42-94% relative to LLM-only inference. Compared to state-of-the-art routing and cascading baselines, shepherding delivers up to 2.8x cost reduction while matching accuracy. To our knowledge, this is the first work to exploit token-level budget control for SLM-LLM collaboration. --- ### SMOG: Scalable Meta-Learning for Multi-Objective Bayesian Optimization Authors: Leonard Papenmeier, Petru Tighineanu Published: 2026-01-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22131v2 Multi-objective optimization aims to solve problems with competing objectives. Evaluating such problems is often slow or expensive, limiting the budget of evaluations. In many applications, historical data from related optimization tasks is available and can be leveraged via meta-learning to accelerate optimization. Bayesian optimization, as a promising technique for expensive black-box problems, has been extended independently to meta-learning and multi-objective optimization, but methods that simultaneously address both settings remain largely unexplored. We propose SMOG-a scalable and modular meta-learning model based on a multi-output Gaussian process-that explicitly learns correlations between objectives. SMOG builds a structured joint Gaussian process prior across meta- and target tasks and, after conditioning on metadata, yields a closed-form prior for the target task. This construction propagates metadata uncertainty into the target surrogate in a principled way. SMOG supports hierarchical, parallel training, achieving linear scaling with the number of meta-tasks. The resulting surrogate integrates seamlessly with standard multi-objective Bayesian optimization acquisition functions. We demonstrate that our method is consistently competitive, delivering strong data efficiency across representative benchmarks and applications. --- ### World of Workflows: A Benchmark for Bringing World Models to Enterprise Systems Authors: Lakshya Gupta, Litao Li, Yizhe Liu, Sriram Ganapathi Subramanian, Kaheer Suleman, Zichen Zhang, Haoye Lu, Sumit Pasupalak Published: 2026-01-29 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2601.22130v2 Frontier large language models (LLMs) excel as autonomous agents in many domains, yet they remain untested in complex enterprise systems where hidden workflows create cascading effects across interconnected databases. Existing enterprise benchmarks evaluate surface-level agentic task completion similar to general consumer benchmarks, ignoring true challenges in enterprises, such as limited observability, large database state, and hidden workflows with cascading side effects. We introduce World of Workflows (WoW), a realistic ServiceNow-based environment incorporating 4,000+ business rules and 55 active workflows embedded in the system, alongside WoW-bench, a benchmark of 234 tasks evaluating constrained agentic task completion and enterprise dynamics modeling capabilities. We reveal two major takeaways: (1) Frontier LLMs suffer from dynamics blindness, consistently failing to predict the invisible, cascading side effects of their actions, which leads to silent constraint violations, and (2) reliability in opaque systems requires grounded world modeling, where agents must mentally simulate hidden state transitions to bridge the observability gap when high-fidelity feedback is unavailable. For reliable and useful enterprise agents, WoW motivates a new paradigm to explicitly learn system dynamics. We release our GitHub for setting up and evaluating WoW. --- ### SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents Authors: Yifeng Ding, Lingming Zhang Published: 2026-01-29 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.22129v2 Test-time scaling has been widely adopted to enhance the capabilities of Large Language Model (LLM) agents in software engineering (SWE) tasks. However, the standard approach of repeatedly sampling trajectories from scratch is computationally expensive. While recent methods have attempted to mitigate costs using specialized value agents, they can suffer from model miscalibration and fail to generalize to modern agents that synthesize custom bash scripts as tools. In this paper, we introduce SWE-Replay, the first efficient and generalizable test-time scaling technique for modern agents without reliance on potentially noisy value estimates. SWE-Replay optimizes the scaling process by recycling trajectories from prior trials, dynamically choosing to either explore from scratch or exploit archived experience by branching at critical intermediate steps. This selection of intermediate steps is driven by the potential and reasoning significance of repository exploration, rather than external LLM-based quality estimates. Our evaluation shows that, on SWE-Bench Verified, SWE-Replay consistently outperforms naive scaling, reducing costs by up to 17.4% while maintaining or even improving performance by up to 3.8%. Further evaluation on SWE-Bench Pro and Multilingual validates the generalizability of SWE-Replay, establishing it as a robust foundation for efficient test-time scaling of software engineering agents. --- ### The Patient is not a Moving Document: A World Model Training Paradigm for Longitudinal EHR Authors: Irsyad Adam, Zekai Chen, David Laprade, Shaun Porwal, David Laub, Erik Reinertsen, Arda Pekis, Kevin Brown Published: 2026-01-29 Categories: cs.AI, cs.CE, q-bio.QM arXiv: https://arxiv.org/abs/2601.22128v1 Large language models (LLMs) trained with next-word-prediction have achieved success as clinical foundation models. Representations from these language backbones yield strong linear probe performance across biomedical tasks, suggesting that patient semantics emerge from next-token prediction at scale. However, this paradigm treats patients as a document to be summarized rather than a dynamical system to be simulated; a patient's trajectory emerges from their state evolving under interventions and time, requiring models that simulate dynamics rather than predict tokens. To address this, we introduce SMB-Structure, a world model for structured EHR that grounds a joint-embedding prediction architecture (JEPA) with next-token prediction (SFT). SFT grounds our model to reconstruct future patient states in token space, while JEPA predicts those futures in latent space from the initial patient representation alone, forcing trajectory dynamics to be encoded before the next state is observed. We validate across two large-scale cohorts: Memorial Sloan Kettering (23,319 oncology patients; 323,000+ patient-years) and INSPECT (19,402 pulmonary embolism patients). Using a linear probe evaluated at multiple points along the disease trajectory, we demonstrate that our training paradigm learns embeddings that capture disease dynamics not recoverable by autoregressive baselines, enabling SMB-Structure to achieve competitive performance on complex tasks characterized by high patient heterogeneity. Model weights are available at https://huggingface.co/standardmodelbio/SMB-v1-1.7B-Structure. --- ### EditYourself: Audio-Driven Generation and Manipulation of Talking Head Videos with Diffusion Transformers Authors: John Flynn, Wolfgang Paier, Dimitar Dinev, Sam Nhut Nguyen, Hayk Poghosyan, Manuel Toribio, Sandipan Banerjee, Guy Gafni Published: 2026-01-29 Categories: cs.CV, cs.GR, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2601.22127v1 Current generative video models excel at producing novel content from text and image prompts, but leave a critical gap in editing existing pre-recorded videos, where minor alterations to the spoken script require preserving motion, temporal coherence, speaker identity, and accurate lip synchronization. We introduce EditYourself, a DiT-based framework for audio-driven video-to-video (V2V) editing that enables transcript-based modification of talking head videos, including the seamless addition, removal, and retiming of visually spoken content. Building on a general-purpose video diffusion model, EditYourself augments its V2V capabilities with audio conditioning and region-aware, edit-focused training extensions. This enables precise lip synchronization and temporally coherent restructuring of existing performances via spatiotemporal inpainting, including the synthesis of realistic human motion in newly added segments, while maintaining visual fidelity and identity consistency over long durations. This work represents a foundational step toward generative video models as practical tools for professional video post-production. --- ### Creative Image Generation with Diffusion Models Authors: Kunpeng Song, Ahmed Elgammal Published: 2026-01-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.22125v2 Creative image generation has emerged as a compelling area of research, driven by the need to produce novel and high-quality images that expand the boundaries of imagination. In this work, we propose a novel framework for creative generation using diffusion models, where creativity is associated with the inverse probability of an image's existence in the CLIP embedding space. Unlike prior approaches that rely on a manual blending of concepts or exclusion of subcategories, our method calculates the probability distribution of generated images and drives it towards low-probability regions to produce rare, imaginative, and visually captivating outputs. We also introduce pullback mechanisms, achieving high creativity without sacrificing visual fidelity. Extensive experiments on text-to-image diffusion models demonstrate the effectiveness and efficiency of our creative generation framework, showcasing its ability to produce unique, novel, and thought-provoking images. This work provides a new perspective on creativity in generative models, offering a principled method to foster innovation in visual content synthesis. --- ### Toward Federated Large Language Models in Medicine: A Parameter-Efficient Framework for Privacy-Preserving, Multi-Institutional Adaptation Authors: Anran Li, Yuanyuan Chen, Wenjun Long, Yu Yin, Yan Hu, Hyunjae Kim, Weipeng Zhou, Yujia Zhou, Hongyi Peng, Yang Ren, Xuguang Ai, Zhenyue Qin et al. Published: 2026-01-29 Categories: cs.CL, cs.DC arXiv: https://arxiv.org/abs/2601.22124v3 Large language models (LLMs) are increasingly adapted for medical applications, but most are trained using data from a single institution because privacy and governance constraints prevent multi-institutional data sharing. As a result, these models often generalize poorly across heterogeneous healthcare systems. We address this gap by introducing Fed-MedLoRA and Fed-MedLoRA+, a parameter-efficient federated framework for collaborative LLM adaptation across healthcare institutions. Fed-MedLoRA transmits only low-rank adapters rather than full model weights, reducing communication overhead. We also evaluate a privacy-preserving variant that applies Gaussian perturbation to transmitted adapter updates. Fed-MedLoRA+ further incorporates adaptive aggregation to better address cross-site heterogeneity in patient populations, annotation practices, and disease distributions. We evaluate the framework on clinical information extraction across five independent patient cohorts totaling 42,198 entities and 41,570 relations, and compare it with zero-shot and fine-tuned LLMs, domain-specific BERT models, and federated baselines. Across all settings, the proposed methods consistently improve extraction performance and generalize better to heterogeneous cohorts. In a real-world case study using clinical notes from the Yale New Haven Health System, the framework demonstrates strong performance under low-resource new-site deployment. These results suggest that federated, parameter-efficient LLM adaptation is feasible, scalable, and effective for multi-institutional clinical deployment. --- ### Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamics Authors: Winfried Ripken, Michael Plainer, Gregor Lied, Thorben Frank, Oliver T. Unke, Stefan Chmiela, Frank Noé, Klaus-Robert Müller Published: 2026-01-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.22123v4 Simulating the long-time evolution of Hamiltonian systems is limited by the small timesteps required for stable numerical integration. To overcome this constraint, we introduce a framework to learn Hamiltonian Flow Maps by predicting the mean phase-space evolution over a chosen time span, enabling stable large-timestep updates far beyond the stability limits of classical integrators. To this end, we impose a Mean Flow consistency condition for time-averaged Hamiltonian dynamics. Unlike prior approaches, this allows training on independent phase-space samples without access to future states, avoiding expensive trajectory generation. Validated across diverse Hamiltonian systems, our method in particular improves upon molecular dynamics simulations using machine-learned force fields (MLFF). Our models maintain comparable training and inference cost, but support significantly larger integration timesteps while trained directly on widely-available trajectory-free MLFF datasets. --- ### Alpha Discovery via Grammar-Guided Learning and Search Authors: Han Yang, Dong Hao, Zhuohan Wang, Qi Shi, Xingtong Li Published: 2026-01-29 Categories: q-fin.CP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.22119v1 Automatically discovering formulaic alpha factors is a central problem in quantitative finance. Existing methods often ignore syntactic and semantic constraints, relying on exhaustive search over unstructured and unbounded spaces. We present AlphaCFG, a grammar-based framework for defining and discovering alpha factors that are syntactically valid, financially interpretable, and computationally efficient. AlphaCFG uses an alpha-oriented context-free grammar to define a tree-structured, size-controlled search space, and formulates alpha discovery as a tree-structured linguistic Markov decision process, which is then solved using a grammar-aware Monte Carlo Tree Search guided by syntax-sensitive value and policy networks. Experiments on Chinese and U.S. stock market datasets show that AlphaCFG outperforms state-of-the-art baselines in both search efficiency and trading profitability. Beyond trading strategies, AlphaCFG serves as a general framework for symbolic factor discovery and refinement across quantitative finance, including asset pricing and portfolio construction. --- ### Defining Operational Conditions for Safety-Critical AI-Based Systems from Data Authors: Johann Maximilian Christensen, Elena Hoemann, Frank Köster, Sven Hallerbach Published: 2026-01-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.22118v3 Artificial Intelligence (AI) has been on the rise in many domains, including numerous safety-critical applications. However, for complex systems in the real world, defining the underlying environmental conditions in which the AI-based system must operate---the Operational Design Domain (ODD)---is extremely challenging. This often results in an incomplete description of the ODD, which contrasts with the requirements of many domains for certifying AI-based systems. Traditionally, the ODD is created in the early stages of the development process, drawing on sophisticated expert knowledge and related standards. This paper presents a novel method for defining the ODD a posteriori from previously collected data using a multidimensional kernel-based representation. This approach is validated through both synthetic benchmarks and a real-world aviation use case. Moreover, the paper defines similarity of two ODDs if they generate the same outputs up to Lebesgue-null input sets and proves convergence in volume of the calibrated representation under the stated assumptions. The novel, safety-by-design, deterministic kernel-based ODD representation is derived fully automatically, given documented assurance inputs, permutation-stable, bounded by construction, and, under affine-equivariant per-dimension normalization, invariant to the choice of units. Utilizing the proposed ODD representation supports future certification of data-driven, safety-critical AI-based systems. --- ### SINA: A Circuit Schematic Image-to-Netlist Generator Using Artificial Intelligence Authors: Saoud Aldowaish, Yashwanth Karumanchi, Kai-Chen Chiang, Soroosh Noorzad, Morteza Fayazi Published: 2026-01-29 Categories: cs.CV, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2601.22114v1 Current methods for converting circuit schematic images into machine-readable netlists struggle with component recognition and connectivity inference. In this paper, we present SINA, an open-source, fully automated circuit schematic image-to-netlist generator. SINA integrates deep learning for accurate component detection, Connected-Component Labeling (CCL) for precise connectivity extraction, and Optical Character Recognition (OCR) for component reference designator retrieval, while employing a Vision-Language Model (VLM) for reliable reference designator assignments. In our experiments, SINA achieves 96.47% overall netlist-generation accuracy, which is 2.72x higher than state-of-the-art approaches. --- ### Diverse Approaches to Optimal Execution Schedule Generation Authors: Robert de Witt, Mikko S. Pakkanen Published: 2026-01-29 Categories: q-fin.TR, cs.LG arXiv: https://arxiv.org/abs/2601.22113v2 We present the first application of MAP-Elites, a quality-diversity algorithm, to trade execution. Rather than searching for a single optimal policy, MAP-Elites generates a diverse portfolio of regime-specialist strategies indexed by liquidity and volatility conditions. Individual specialists achieve 8-10% performance improvements within their behavioural niches, while other cells show degradation, suggesting opportunities for ensemble approaches that combine improved specialists with the baseline PPO policy. Results indicate that quality-diversity methods offer promise for regime-adaptive execution, though substantial computational resources per behavioural cell may be required for robust specialist development across all market conditions. To ensure experimental integrity, we develop a calibrated Gymnasium environment focused on order scheduling rather than tactical placement decisions. The simulator features a transient impact model with exponential decay and square-root volume scaling, fit to 400+ U.S. equities with $R^2>0.02$ out-of-sample. Within this environment, two Proximal Policy Optimization architectures - both MLP and CNN feature extractors - demonstrate substantial improvements over industry baselines, with the CNN variant achieving 2.13 bps arrival slippage versus 5.23 bps for VWAP on 4,900 out-of-sample orders ($21B notional). These results validate both the simulation realism and provide strong single-policy baselines for quality-diversity methods. --- ### Physics Informed Reconstruction of Four-Dimensional Atmospheric Wind Fields Using Multi-UAS Swarm Observations in a Synthetic Turbulent Environment Authors: Abdullah Tasim, Wei Sun Published: 2026-01-29 Categories: cs.LG, eess.SY, physics.ao-ph arXiv: https://arxiv.org/abs/2601.22111v1 Accurate reconstruction of atmospheric wind fields is essential for applications such as weather forecasting, hazard prediction, and wind energy assessment, yet conventional instruments leave spatio-temporal gaps within the lower atmospheric boundary layer. Unmanned aircraft systems (UAS) provide flexible in situ measurements, but individual platforms sample wind only along their flight trajectories, limiting full wind-field recovery. This study presents a framework for reconstructing four-dimensional atmospheric wind fields using measurements obtained from a coordinated UAS swarm. A synthetic turbulence environment and high-fidelity multirotor simulation are used to generate training and evaluation data. Local wind components are estimated from UAS dynamics using a bidirectional long short-term memory network (Bi-LSTM) and assimilated into a physics-informed neural network (PINN) to reconstruct a continuous wind field in space and time. For local wind estimation, the bidirectional LSTM achieves root-mean-square errors (RMSE) of 0.064 and 0.062 m/s for the north and east components in low-wind conditions, increasing to 0.122 to 0.129 m/s under moderate winds and 0.271 to 0.273 m/s in high-wind conditions, while the vertical component exhibits higher error, with RMSE values of 0.029 to 0.091 m/s. The physics-informed reconstruction recovers the dominant spatial and temporal structure of the wind field up to 1000 m altitude while preserving mean flow direction and vertical shear. Under moderate wind conditions, the reconstructed mean wind field achieves an overall RMSE between 0.118 and 0.154 m/s across evaluated UAS configurations, with the lowest error obtained using a five-UAS swarm. These results demonstrate that coordinated UAS measurements enable accurate and scalable four-dimensional wind-field reconstruction without dedicated wind sensors or fixed infrastructure. --- ### Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining Authors: Shuqi Ke, Giulia Fanti Published: 2026-01-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.22108v2 Continued pretraining is optimized with fixed self-supervised tasks but selected by downstream performance, creating a coarse feedback loop in which practitioners evaluate checkpoints, change data mixtures or objectives, and restart runs, while individual updates remain blind to target capabilities. We ask whether a small set of verifiable downstream examples can provide step-level feedback without directly supervising the learner. We introduce V-pretraining, which decouples a learner trained only with a self-supervised loss from a lightweight task designer that constructs targets or views for unlabeled batches. Given the current learner and batch, V-pretraining scores a candidate construction by predicting the first-order reduction in downstream loss after the induced self-supervised update. The designer maximizes this value; the learner then applies the update with targets or views detached, so downstream labels never update learner parameters. We instantiate V-pretraining as adaptive top-K soft targets for language modeling and learned views or masks for self-supervised vision. Across both modalities, V-pretraining improves target capabilities without degrading generalization. Under wall-clock-matched continued pretraining, it improves GSM8K Pass@1 for Qwen models using 1,024 GSM8K examples only as feedback, including a +7.4 point single-run gain for Qwen2.5-0.5B. In vision, it improves DINOv3 transfer to ADE20K semantic segmentation and NYUv2 depth estimation while preserving ImageNet linear accuracy, suggesting that feedback-guided task construction can improve target capabilities without collapsing general-purpose representations. ---