# Research Papers — 2026-02 · bundle page 135 of 210 > Full-text markdown of papers #6701–6750 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/135 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/134.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/136.md) ### CauScale: Neural Causal Discovery at Scale Authors: Bo Peng, Sirui Chen, Jiaguo Tian, Yu Qiao, Chaochao Lu Published: 2026-02-09 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2602.08629v2 Causal discovery is essential for advancing data-driven fields such as scientific AI and data analysis, yet existing approaches face significant time- and space-efficiency bottlenecks when scaling to large graphs. To address this challenge, we present CauScale, a neural architecture designed for efficient causal discovery that scales inference to graphs with up to 1000 nodes. CauScale improves time efficiency via a reduction unit that compresses data embeddings and improves space efficiency by adopting tied attention weights to avoid maintaining axis-specific attention maps. To keep high causal discovery accuracy, CauScale adopts a two-stream design: a data stream extracts relational evidence from high-dimensional observations, while a graph stream integrates statistical graph priors and preserves key structural signals. CauScale successfully scales to 500-node graphs during training, where prior work fails due to space limitations. Across testing data with varying graph scales and causal mechanisms, CauScale achieves 99.6% mAP on in-distribution data and 84.4% on out-of-distribution data, while delivering 4-13,000 times inference speedups over prior methods. Our project page is at https://github.com/OpenCausaLab/CauScale. --- ### Revisiting (CLS) and Patch Token Interaction in Vision Transformers Authors: Alexis Marouani, Oriane Siméoni, Hervé Jégou, Piotr Bojanowski, Huy V. Vo Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.08626v1 Vision Transformers have emerged as powerful, scalable and versatile representation learners. To capture both global and local features, a learnable (CLS) class token is typically prepended to the input sequence of patch tokens. Despite their distinct nature, both token types are processed identically throughout the model. In this work, we investigate the friction between global and local feature learning under different pre-training strategies by analyzing the interactions between class and patch tokens. Our analysis reveals that standard normalization layers introduce an implicit differentiation between these token types. Building on this insight, we propose specialized processing paths that selectively disentangle the computational flow of class and patch tokens, particularly within normalization layers and early query-key-value projections. This targeted specialization leads to significantly improved patch representation quality for dense prediction tasks. Our experiments demonstrate segmentation performance gains of over 2 mIoU points on standard benchmarks, while maintaining strong classification accuracy. The proposed modifications introduce only an 8% increase in parameters, with no additional computational overhead. Through comprehensive ablations, we provide insights into which architectural components benefit most from specialization and how our approach generalizes across model scales and learning frameworks. --- ### Do Multilingual LLMs have specialized language heads? Authors: Muhammad Naufil Published: 2026-02-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.08625v1 Multilingual large language models (LLMs) have gained significant popularity for their ability to process and generate text across multiple languages. However, deploying these models in production can be inefficient when only a subset of the supported languages is of interest. There has been some research conducted on identifying whether machine translation models have language-specific or language-agnostic heads, however no research has been conducted for multilingual LLMs, to the best of our knowledge, that as we know are capable of performing diverse tasks beyond just translation. This paper explores whether multilingual LLMs have specialized language attention heads for each language, and investigates the possibility of removing language-specific heads for unwanted languages without degrading performance in the targeted languages. Our findings could inform more efficient deployment strategies for multilingual LLMs, enabling reduced model complexity while maintaining high accuracy for targeted languages. --- ### Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs Authors: Yukun Jiang, Hai Huang, Mingjie Li, Yage Zhang, Michael Backes, Yang Zhang Published: 2026-02-09 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2602.08621v1 By introducing routers to selectively activate experts in Transformer layers, the mixture-of-experts (MoE) architecture significantly reduces computational costs in large language models (LLMs) while maintaining competitive performance, especially for models with massive parameters. However, prior work has largely focused on utility and efficiency, leaving the safety risks associated with this sparse architecture underexplored. In this work, we show that the safety of MoE LLMs is as sparse as their architecture by discovering unsafe routes: routing configurations that, once activated, convert safe outputs into harmful ones. Specifically, we first introduce the Router Safety importance score (RoSais) to quantify the safety criticality of each layer's router. Manipulation of only the high-RoSais router(s) can flip the default route into an unsafe one. For instance, on JailbreakBench, masking 5 routers in DeepSeek-V2-Lite increases attack success rate (ASR) by over 4$\times$ to 0.79, highlighting an inherent risk that router manipulation may naturally occur in MoE LLMs. We further propose a Fine-grained token-layer-wise Stochastic Optimization framework to discover more concrete Unsafe Routes (F-SOUR), which explicitly considers the sequentiality and dynamics of input tokens. Across four representative MoE LLM families, F-SOUR achieves an average ASR of 0.90 and 0.98 on JailbreakBench and AdvBench, respectively. Finally, we outline defensive perspectives, including safety-aware route disabling and router training, as promising directions to safeguard MoE LLMs. We hope our work can inform future red-teaming and safeguarding of MoE LLMs. Our code is provided in https://github.com/TrustAIRLab/UnsafeMoE. --- ### Improving Reconstruction of Representation Autoencoder Authors: Siyu Liu, Chujie Qin, Hubery Yin, Qixin Yan, Zheng-Peng Duan, Chen Li, Jing Lyu, Chun-Le Guo, Chongyi Li Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.08620v1 Recent work leverages Vision Foundation Models as image encoders to boost the generative performance of latent diffusion models (LDMs), as their semantic feature distributions are easy to learn. However, such semantic features often lack low-level information (\eg, color and texture), leading to degraded reconstruction fidelity, which has emerged as a primary bottleneck in further scaling LDMs. To address this limitation, we propose LV-RAE, a representation autoencoder that augments semantic features with missing low-level information, enabling high-fidelity reconstruction while remaining highly aligned with the semantic distribution. We further observe that the resulting high-dimensional, information-rich latent make decoders sensitive to latent perturbations, causing severe artifacts when decoding generated latent and consequently degrading generation quality. Our analysis suggests that this sensitivity primarily stems from excessive decoder responses along directions off the data manifold. Building on these insights, we propose fine-tuning the decoder to increase its robustness and smoothing the generated latent via controlled noise injection, thereby enhancing generation quality. Experiments demonstrate that LV-RAE significantly improves reconstruction fidelity while preserving the semantic abstraction and achieving strong generative quality. Our code is available at https://github.com/modyu-liu/LVRAE. --- ### Enhancing Genetic Algorithms with Graph Neural Networks: A Timetabling Case Study Authors: Laura-Maria Cornei, Mihaela-Elena Breabăn Published: 2026-02-09 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.08619v1 This paper investigates the impact of hybridizing a multi-modal Genetic Algorithm with a Graph Neural Network for timetabling optimization. The Graph Neural Network is designed to encapsulate general domain knowledge to improve schedule quality, while the Genetic Algorithm explores different regions of the search space and integrates the deep learning model as an enhancement operator to guide the solution search towards optimality. Initially, both components of the hybrid technique were designed, developed, and optimized independently to solve the tackled task. Multiple experiments were conducted on Staff Rostering, a well-known timetabling problem, to compare the proposed hybridization with the standalone optimized versions of the Genetic Algorithm and Graph Neural Network. The experimental results demonstrate that the proposed hybridization brings statistically significant improvements in both the time efficiency and solution quality metrics, compared to the standalone methods. To the best of our knowledge, this work proposes the first hybridization of a Genetic Algorithm with a Graph Neural Network for solving timetabling problems. --- ### ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation Authors: Dario Fenoglio, Pasquale Polverino, Jacopo Quizi, Martin Gjoreski, Akash Dhasade, Marc Langheinrich Published: 2026-02-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.08617v2 Scaling Federated Learning (FL) to billion-parameter models forces a challenging trade-off between privacy, scalability, and model utility. Existing solutions often tackle these challenges in isolation, sacrificing accuracy, relying on costly cryptographic tools, or introducing communication and optimization inefficiencies that affect convergence. We introduce ERIS, an FL framework centered on Federated Shard Aggregation (FSA), a novel mechanism that partitions each client update into non-overlapping shards whose aggregation is distributed across multiple client-side aggregators. FSA removes the central aggregation bottleneck, limits the information visible to any single observer, and preserves the centralized FL update after reassembly. ERIS can further readily integrate Distributed Shifted Compression (DSC) to reduce transmitted payloads and exposed coordinates. We prove that ERIS preserves convergence under standard assumptions and bounds mutual information leakage by the observable fraction of each update, decreasing with the number of client-side aggregators, and with the compression level when DSC is enabled. Experiments across image and text tasks, including large language models, show that ERIS achieves FedAvg-level utility while substantially reducing communication bottlenecks and improving robustness to membership inference and reconstruction attacks, without relying on heavy cryptography or utility-degrading perturbations. --- ### Breaking the Grid: Distance-Guided Reinforcement Learning in Large Discrete Action Spaces Authors: Heiko Hoppe, Fabian Akkerman, Wouter van Heeswijk, Maximilian Schiffer Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.08616v2 Reinforcement Learning (RL) is increasingly applied to large-scale decision-making problems like logistics, scheduling, and recommender systems, but existing algorithms struggle with the curse of dimensionality in such large discrete action spaces. We propose Distance-Guided Reinforcement Learning (DGRL), combining Sampled Dynamic Neighborhoods and Distance-Based Updates to enable efficient RL in problems with up to $10^{20}$ actions. Unlike prior methods, DGRL performs stochastic volumetric exploration and transforms policy optimization into a stable regression task, decoupling gradient variance from action space cardinality. On structured tasks, DGRL provably guarantees local value improvement. DGRL naturally generalizes to hybrid continuous-discrete action spaces. We demonstrate performance improvements of up to 66% against state-of-the-art benchmarks across regularly and irregularly structured environments, while simultaneously improving convergence speed and computational complexity. --- ### Inspiration Seeds: Learning Non-Literal Visual Combinations for Generative Exploration Authors: Kfir Goldberg, Elad Richardson, Yael Vinker Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.08615v3 While generative models have become powerful tools for image synthesis, they are typically optimized for executing carefully crafted textual prompts, offering limited support for the open-ended visual exploration that often precedes idea formation. In contrast, designers frequently draw inspiration from loosely connected visual references, seeking emergent connections that spark new ideas. We propose Inspiration Seeds, a generative framework that shifts image generation from final execution to exploratory ideation. Given two input images, our model produces diverse, visually coherent compositions that reveal latent relationships between inputs, without relying on user-specified text prompts. Our approach is feed-forward, trained on synthetic triplets of decomposed visual aspects derived entirely through visual means: we use CLIP Sparse Autoencoders to extract editing directions in CLIP latent space and isolate concept pairs. By removing the reliance on language and enabling fast, intuitive recombination, our method supports visual ideation at the early and ambiguous stages of creative work. --- ### Overview and Comparison of AVS Point Cloud Compression Standard Authors: Wei Gao, Wenxu Gao, Xingming Mu, Changhao Peng, Ge Li Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.08613v1 Point cloud is a prevalent 3D data representation format with significant application values in immersive media, autonomous driving, digital heritage protection, etc. However, the large data size of point clouds poses challenges to transmission and storage, which influences the wide deployments. Therefore, point cloud compression plays a crucial role in practical applications for both human and machine perception optimization. To this end, the Moving Picture Experts Group (MPEG) has established two standards for point cloud compression, including Geometry-based Point Cloud Compression (G-PCC) and Video-based Point Cloud Compression (V-PCC). In the meantime, the Audio Video coding Standard (AVS) Workgroup of China also have launched and completed the development for its first generation point cloud compression standard, namely AVS PCC. This new standardization effort has adopted many new coding tools and techniques, which are different from the other counterpart standards. This paper reviews the AVS PCC standard from two perspectives, i.e., the related technologies and performance comparisons. --- ### VocalNet-MDM: Accelerating Streaming Speech LLM via Self-Distilled Masked Diffusion Modeling Authors: Ziyang Cheng, Yuhao Wang, Heyang Liu, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang Published: 2026-02-09 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2602.08607v1 Recent Speech Large Language Models~(LLMs) have achieved impressive capabilities in end-to-end speech interaction. However, the prevailing autoregressive paradigm imposes strict serial constraints, limiting generation efficiency and introducing exposure bias. In this paper, we investigate Masked Diffusion Modeling~(MDM) as a non-autoregressive paradigm for speech LLMs and introduce VocalNet-MDM. To adapt MDM for streaming speech interaction, we address two critical challenges: training-inference mismatch and iterative overhead. We propose Hierarchical Block-wise Masking to align training objectives with the progressive masked states encountered during block diffusion decoding, and Iterative Self-Distillation to compress multi-step refinement into fewer steps for low-latency inference. Trained on a limited scale of only 6K hours of speech data, VocalNet-MDM achieves a 3.7$\times$--10$\times$ decoding speedup and reduces first-chunk latency by 34\% compared to AR baselines. It maintains competitive recognition accuracy while achieving state-of-the-art text quality and speech naturalness, demonstrating that MDM is a promising and scalable alternative for low-latency, efficient speech LLMs. --- ### Constructive conditional normalizing flows Authors: Borjan Geshkovski, Domènec Ruiz-Balet Published: 2026-02-09 Categories: math.OC, cs.LG, math.AP, math.PR arXiv: https://arxiv.org/abs/2602.08606v3 Motivated by applications in conditional sampling, given a probability measure $μ$ and a diffeomorphism $φ$, we consider the problem of simultaneously approximating $φ$ and the pushforward $φ_{\#}μ$ by means of the flow of a continuity equation whose velocity field is a perceptron neural network with piecewise constant weights. We provide an explicit construction based on a polar-like decomposition of the Lagrange interpolant of $φ$. The latter involves a compressible component, given by the gradient of a particular convex function, which can be realized exactly, and an incompressible component, which -- after approximating via permutations -- can be implemented through shear flows intrinsic to the continuity equation. For more regular maps $φ$ -- such as the Knöthe-Rosenblatt rearrangement -- we provide an alternative, probabilistic construction inspired by the Maurey empirical method, in which the number of discontinuities in the weights doesn't scale inversely with the ambient dimension. --- ### OSCAR: Optimization-Steered Agentic Planning for Composed Image Retrieval Authors: Teng Wang, Rong Shan, Jianghao Lin, Junjie Wu, Tianyi Xu, Jianping Zhang, Wenteng Chen, Changwang Zhang, Zhaoxiang Wang, Weinan Zhang, Jun Wang Published: 2026-02-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.08603v2 Composed image retrieval (CIR) requires complex reasoning over heterogeneous visual and textual constraints. Existing approaches largely fall into two paradigms: unified embedding retrieval, which suffers from single-model myopia, and heuristic agentic retrieval, which is limited by suboptimal, trial-and-error orchestration. To this end, we propose OSCAR, an optimization-steered agentic planning framework for composed image retrieval. We are the first to reformulate agentic CIR from a heuristic search process into a principled trajectory optimization problem. Instead of relying on heuristic trial-and-error exploration, OSCAR employs a novel offline-online paradigm. In the offline phase, we model CIR via atomic retrieval selection and composition as a two-stage mixed-integer programming problem, mathematically deriving optimal trajectories that maximize ground-truth coverage for training samples via rigorous boolean set operations. These trajectories are then stored in a golden library to serve as in-context demonstrations for online steering of VLM planner at online inference time. Extensive experiments on three public benchmarks and a private industrial benchmark show that OSCAR consistently outperforms SOTA baselines. Notably, it achieves superior performance using only 10% of training data, demonstrating strong generalization of planning logic rather than dataset-specific memorization. --- ### OSCAR: Optimization-Steered Agentic Planning for Composed Image Retrieval Authors: Teng Wang, Rong Shan, Jianghao Lin, Junjie Wu, Tianyi Xu, Jianping Zhang, Wenteng Chen, Changwang Zhang, Zhaoxiang Wang, Weinan Zhang, Jun Wang Published: 2026-02-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.08603v1 Composed image retrieval (CIR) requires complex reasoning over heterogeneous visual and textual constraints. Existing approaches largely fall into two paradigms: unified embedding retrieval, which suffers from single-model myopia, and heuristic agentic retrieval, which is limited by suboptimal, trial-and-error orchestration. To this end, we propose OSCAR, an optimization-steered agentic planning framework for composed image retrieval. We are the first to reformulate agentic CIR from a heuristic search process into a principled trajectory optimization problem. Instead of relying on heuristic trial-and-error exploration, OSCAR employs a novel offline-online paradigm. In the offline phase, we model CIR via atomic retrieval selection and composition as a two-stage mixed-integer programming problem, mathematically deriving optimal trajectories that maximize ground-truth coverage for training samples via rigorous boolean set operations. These trajectories are then stored in a golden library to serve as in-context demonstrations for online steering of VLM planner at online inference time. Extensive experiments on three public benchmarks and a private industrial benchmark show that OSCAR consistently outperforms SOTA baselines. Notably, it achieves superior performance using only 10% of training data, demonstrating strong generalization of planning logic rather than dataset-specific memorization. --- ### Beyond Scalar Scores: Reinforcement Learning for Error-Aware Quality Estimation of Machine Translation Authors: Archchana Sindhujan, Girish A. Koushik, Shenbin Qian, Diptesh Kanojia, Constantin Orăsan Published: 2026-02-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.08600v1 Quality Estimation (QE) aims to assess the quality of machine translation (MT) outputs without relying on reference translations, making it essential for real-world, large-scale MT evaluation. Large Language Models (LLMs) have shown significant promise in advancing the field of quality estimation of machine translation. However, most of the QE approaches solely rely on scalar quality scores, offering no explicit information about the translation errors that should drive these judgments. Moreover, for low-resource languages where annotated QE data is limited, existing approaches struggle to achieve reliable performance. To address these challenges, we introduce the first segment-level QE dataset for English to Malayalam, a severely resource-scarce language pair in the QE domain, comprising human-annotated Direct Assessment (DA) scores and Translation Quality Remarks (TQR), which are short, contextual, free-form annotator comments that describe translation errors. We further introduce ALOPE-RL, a policy-based reinforcement learning framework that trains efficient adapters based on policy rewards derived from DA score and TQR. Integrating error-aware rewards with ALOPE-RL, enables LLMs to reason about translation quality beyond numeric scores. Despite being trained on a small-scale QE dataset, ALOPE-RL achieves state-of-the-art performance on English to Malayalam QE using compact LLMs (<=4B parameters}) fine-tuned with LoRA and 4-bit quantization, outperforming both larger LLM-based baselines and leading encoder-based QE models. Our results demonstrate that error-aware, policy-based learning can deliver strong QE performance under limited data and compute budgets. We release our dataset, code, and trained models to support future research. --- ### An Attention Mechanism for Robust Multimodal Integration in a Global Workspace Architecture Authors: Roland Bertin-Johannet, Lara Scipio, Leopold Maytié, Rufin VanRullen Published: 2026-02-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.08597v3 Robust multimodal systems must remain effective when some modalities are noisy, degraded, or unreliable. Existing multimodal fusion methods often learn modality selection jointly with representation learning, making it difficult to determine whether robustness comes from the selector itself or from full end-to-end co-adaptation. Motivated by Global Workspace Theory (GWT), we study this question using a lightweight top-down modality selector operating on top of a frozen multimodal global workspace. We evaluate our method on two multimodal datasets of increasing complexity: Simple Shapes and MM-IMDb 1.0, under structured modality corruptions. The selector improves robustness while using far fewer trainable parameters than end-to-end attention baselines, and the learned selection strategy transfers better across downstream tasks, corruption regimes, and even to a previously unseen modality. Beyond explicit corruption settings, on the MM-IMDb 1.0 benchmark, we show that the same mechanism improves the global workspace over its no-attention counterpart and yields decent benchmark performance. --- ### Kissan-Dost: Bridging the Last Mile in Smallholder Precision Agriculture with Conversational IoT Authors: Muhammad Saad Ali, Daanish U. Khan, Laiba Intizar Ahmad, Umer Irfan, Maryam Mustafa, Naveed Anwar Bhatti, Muhammad Hamad Alizai Published: 2026-02-09 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.08593v1 We present Kissan-Dost, a multilingual, sensor-grounded conversational system that turns live on-farm measurements and weather into plain-language guidance delivered over WhatsApp text or voice. The system couples commodity soil and climate sensors with retrieval-augmented generation, then enforces grounding, traceability, and proactive alerts through a modular pipeline. In a 90-day, two-site pilot with five participants, we ran three phases (baseline, dashboard only, chatbot only). Dashboard engagement was sporadic and faded, while the chatbot was used nearly daily and informed concrete actions. Controlled tests on 99 sensor-grounded crop queries achieved over 90 percent correctness with subsecond end-to-end latency, alongside high-quality translation outputs. Results show that careful last-mile integration, not novel circuitry, unlocks the latent value of existing Agri-IoT for smallholders. --- ### TFMLinker: Universal Link Predictor by Graph In-Context Learning with Tabular Foundation Models Authors: Tianyin Liao, Chunyu Hu, Yicheng Sui, Xingxuan Zhang, Peng Cui, Jianxin Li, Ziwei Zhang Published: 2026-02-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.08592v1 Link prediction is a fundamental task in graph machine learning with widespread applications such as recommendation systems, drug discovery, knowledge graphs, etc. In the foundation model era, how to develop universal link prediction methods across datasets and domains becomes a key problem, with some initial attempts adopting Graph Foundation Models utilizing Graph Neural Networks and Large Language Models. However, the existing methods face notable limitations, including limited pre-training scale or heavy reliance on textual information. Motivated by the success of tabular foundation models (TFMs) in achieving universal prediction across diverse tabular datasets, we explore an alternative approach by TFMs, which are pre-trained on diverse synthetic datasets sampled from structural causal models and support strong in-context learning independent of textual attributes. Nevertheless, adapting TFMs for link prediction faces severe technical challenges such as how to obtain the necessary context and capture link-centric topological information. To solve these challenges, we propose TFMLinker (Tabular Foundation Model for Link Predictor), aiming to leverage the in-context learning capabilities of TFMs to perform link prediction across diverse graphs without requiring dataset-specific fine-tuning. Specifically, we first develop a prototype-augmented local-global context module to construct context that captures both graph-specific and cross-graph transferable patterns. Next, we design a universal topology-aware link encoder to capture link-centric topological information and generate link representations as inputs for the TFM. Finally, we employ the TFM to predict link existence through in-context learning. Experiments on 6 graph benchmarks across diverse domains demonstrate the superiority of our method over state-of-the-art baselines without requiring dataset-specific finetuning. --- ### SDFed: Bridging Local Global Discrepancy via Subspace Refinement and Divergence Control in Federated Prompt Learning Authors: Yicheng Di, Wei Yuan, Tieke He, Yuan Liu, Hongzhi Yin Published: 2026-02-09 Categories: cs.LG, cs.DB arXiv: https://arxiv.org/abs/2602.08590v4 Vision-language pretrained models offer strong transferable representations, yet adapting them in privacy-sensitive multi-party settings is challenging due to the high communication cost of federated optimization and the limited local data on clients. Federated prompt learning mitigates this issue by keeping the VLPM backbone frozen and collaboratively training lightweight prompt parameters. However, existing approaches typically enforce a unified prompt structure and length across clients, which is inadequate under practical client heterogeneity in both data distributions and system resources, and may further introduce conflicts between globally shared and locally optimal knowledge. To address these challenges, we propose \textbf{SDFed}, a heterogeneous federated prompt learning framework that bridges Local-Global Discrepancy via Subspace Refinement and Divergence Control. SDFed maintains a fixed-length global prompt for efficient aggregation while allowing each client to learn a variable-length local prompt to better match its data characteristics and capacity. To mitigate local-global conflicts and facilitate effective knowledge transfer, SDFed introduces a subspace refinement method for local prompts and an information retention and divergence control strategy that preserves key local information while maintaining appropriate separability between global and local representations. Extensive experiments on several datasets demonstrate that SDFed consistently improves performance and robustness in heterogeneous federated settings. --- ### FairRARI: A Plug and Play Framework for Fairness-Aware PageRank Authors: Emmanouil Kariotakis, Aritra Konar Published: 2026-02-09 Categories: cs.LG, cs.SI arXiv: https://arxiv.org/abs/2602.08589v1 PageRank (PR) is a fundamental algorithm in graph machine learning tasks. Owing to the increasing importance of algorithmic fairness, we consider the problem of computing PR vectors subject to various group-fairness criteria based on sensitive attributes of the vertices. At present, principled algorithms for this problem are lacking - some cannot guarantee that a target fairness level is achieved, while others do not feature optimality guarantees. In order to overcome these shortcomings, we put forth a unified in-processing convex optimization framework, termed FairRARI, for tackling different group-fairness criteria in a ``plug and play'' fashion. Leveraging a variational formulation of PR, the framework computes fair PR vectors by solving a strongly convex optimization problem with fairness constraints, thereby ensuring that a target fairness level is achieved. We further introduce three different fairness criteria which can be efficiently tackled using FairRARI to compute fair PR vectors with the same asymptotic time-complexity as the original PR algorithm. Extensive experiments on real-world datasets showcase that FairRARI outperforms existing methods in terms of utility, while achieving the desired fairness levels across multiple vertex groups; thereby highlighting its effectiveness. --- ### DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning Authors: Yiming Yang, Zhuoyuan Li, Fanxiang Zeng, Hao Fu, Yue Liu Published: 2026-02-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.08586v4 Multi-agent LLM systems consistently outperform single-agent baselines, yet practitioners still cannot predict which design works for a new task or diagnose why one fails. We argue this gap persists largely because the field lacks a diagnostic framework with measurable primitives and testable predictions. We introduce \textbf{DIANOIA}, a three-channel decomposition of multi-agent reasoning gain into coverage, fidelity, and synthesis, each of which is empirically measurable. From this decomposition, we derive a diagnostic protocol that identifies the bottleneck channels for any given task. We instantiate the protocol as a multi-agent system whose three components mirror the channels: role-diverse proposers for coverage, execution-grounded verification for fidelity, and iterative synthesis. On GSM8K, AIME-2025, MBPP, and BFCL-SP, our method outperforms strong multi-agent baselines under matched token budgets, dominating the Pareto frontier on MBPP at $\sim$$5{\times}$ token savings and reaching $+4.6$pp at matched cost. On every benchmark, the protocol picks the right bottleneck channels; the system we built around it leads across models. We release code, adapters, diagnostic metrics, and a Claude Code skill at https://anonymous.4open.science/r/DIANOIA4MAS. DIANOIA reframes multi-agent design as channel-aware resource allocation: diagnose which channel is the bottleneck for your task, then invest tokens accordingly. --- ### DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning Authors: Yiming Yang, Zhuoyuan Li, Fanxiang Zeng, Hao Fu, Yue Liu Published: 2026-02-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.08586v3 Multi-agent LLM systems consistently outperform single-agent baselines, yet practitioners still cannot predict which design works for a new task or diagnose why one fails. We argue this gap persists largely because the field lacks a diagnostic framework with measurable primitives and testable predictions. We introduce \textbf{DIANOIA}, a three-channel decomposition of multi-agent reasoning gain into coverage, fidelity, and synthesis, each of which is empirically measurable. From this decomposition, we derive a diagnostic protocol that identifies the bottleneck channels for any given task. We instantiate the protocol as a multi-agent system whose three components mirror the channels: role-diverse proposers for coverage, execution-grounded verification for fidelity, and iterative synthesis. On GSM8K, AIME-2025, MBPP, and BFCL-SP, our method outperforms strong multi-agent baselines under matched token budgets, dominating the Pareto frontier on MBPP at $\sim$$5{\times}$ token savings and reaching $+4.6$pp at matched cost. On every benchmark, the protocol picks the right bottleneck channels; the system we built around it leads across models. We release code, adapters, diagnostic metrics, and a Claude Code skill at https://anonymous.4open.science/r/DIANOIA4MAS. DIANOIA reframes multi-agent design as channel-aware resource allocation: diagnose which channel is the bottleneck for your task, then invest tokens accordingly. --- ### Predicting Future Utility: Global Combinatorial Optimization for Task-Agnostic KV Cache Eviction Authors: Ziyao Tang, Pengkun Jiao, Xinhang Chen, Wei Liu, Shiyong Li, Jingjing Chen Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.08585v2 Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference. Current KV cache eviction methods typically rely on instantaneous heuristic metrics, implicitly assuming that score magnitudes are consistent proxies for importance across all heads. However, this overlooks the heterogeneity in predictive fidelity across attention heads. While certain heads prioritize the instantaneous contribution of tokens, others are dedicated to capturing long-horizon utility. In this paper, we propose that optimal budget allocation should be governed by the marginal utility in preserving long-term semantic information. Building on this insight, we propose LU-KV, a novel framework that formulates head-level budget allocation as a global combinatorial optimization problem to maximize the long-horizon marginal contribution of reserved tokens. To solve this non-convex problem, we employ a convex-hull relaxation and a marginal-utility-based greedy solver, achieving near-optimal solutions. Furthermore, we implement a data-driven offline profiling protocol to facilitate the practical deployment of LU-KV. Evaluations on LongBench and RULER benchmarks demonstrate that LU-KV reduces KV cache size by 80% with minimal performance degradation, while also decreasing inference latency and GPU memory footprint. --- ### Conditional Sequence Modeling for Safe Reinforcement Learning Authors: Wensong Bai, Chao Zhang, Qihang Xu, Chufan Chen, Chenhao Zhou, Hui Qian Published: 2026-02-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.08584v1 Offline safe reinforcement learning (RL) aims to learn policies from a fixed dataset while maximizing performance under cumulative cost constraints. In practice, deployment requirements often vary across scenarios, necessitating a single policy that can adapt zero-shot to different cost thresholds. However, most existing offline safe RL methods are trained under a pre-specified threshold, yielding policies with limited generalization and deployment flexibility across cost thresholds. Motivated by recent progress in conditional sequence modeling (CSM), which enables flexible goal-conditioned control by specifying target returns, we propose RCDT, a CSM-based method that supports zero-shot deployment across multiple cost thresholds within a single trained policy. RCDT is the first CSM-based offline safe RL algorithm that integrates a Lagrangian-style cost penalty with an auto-adaptive penalty coefficient. To avoid overly conservative behavior and achieve a more favorable return--cost trade-off, a reward--cost-aware trajectory reweighting mechanism and Q-value regularization are further incorporated. Extensive experiments on the DSRL benchmark demonstrate that RCDT consistently improves return--cost trade-offs over representative baselines, advancing the state-of-the-art in offline safe RL. --- ### SemiNFT: Learning to Transfer Presets from Imitation to Appreciation via Hybrid-Sample Reinforcement Learning Authors: Melany Yang, Yuhang Yu, Diwang Weng, Jinwei Chen, Wei Dong Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.08582v1 Photorealistic color retouching plays a vital role in visual content creation, yet manual retouching remains inaccessible to non-experts due to its reliance on specialized expertise. Reference-based methods offer a promising alternative by transferring the preset color of a reference image to a source image. However, these approaches often operate as novice learners, performing global color mappings derived from pixel-level statistics, without a true understanding of semantic context or human aesthetics. To address this issue, we propose SemiNFT, a Diffusion Transformer (DiT)-based retouching framework that mirrors the trajectory of human artistic training: beginning with rigid imitation and evolving into intuitive creation. Specifically, SemiNFT is first taught with paired triplets to acquire basic structural preservation and color mapping skills, and then advanced to reinforcement learning (RL) on unpaired data to cultivate nuanced aesthetic perception. Crucially, during the RL stage, to prevent catastrophic forgetting of old skills, we design a hybrid online-offline reward mechanism that anchors aesthetic exploration with structural review. % experiments Extensive experiments show that SemiNFT not only outperforms state-of-the-art methods on standard preset transfer benchmarks but also demonstrates remarkable intelligence in zero-shot tasks, such as black-and-white photo colorization and cross-domain (anime-to-photo) preset transfer. These results confirm that SemiNFT transcends simple statistical matching and achieves a sophisticated level of aesthetic comprehension. Our project can be found at https://melanyyang.github.io/SemiNFT/. --- ### retinalysis-vascx: An explainable software toolbox for the extraction of retinal vascular biomarkers Authors: Jose D. Vargas Quiros, Michael J. Beyeler, Sofia Ortin Vela, EyeNED Reading Center, Sven Bergmann, Caroline C. W. Klaver, Bart Liefers, VascX Research Consortium Published: 2026-02-09 Categories: q-bio.TO, cs.CV arXiv: https://arxiv.org/abs/2602.08580v4 Automatic extraction of retinal vascular biomarkers from color fundus images (CFI) is crucial for large-scale studies of the retinal vasculature. We present VascX, an open-source Python toolbox that extracts biomarkers from CFI artery-vein segmentations. VascX starts from vessel segmentation masks, extracts their skeletons, builds undirected and directed vessel graphs, and resolves vessel segments into longer vessels. A comprehensive set of biomarkers is derived, including vascular density, central retinal equivalents (CREs), and tortuosity. Spatially localized biomarkers may be calculated over grids placed relative to the fovea and optic disc. VascX is released via GitHub and PyPI with comprehensive documentation and examples. Our test-retest reproducibility analysis on repeat imaging of the same eye by different devices shows that most VascX biomarkers have moderate to excellent agreement (ICC > 0.5), with important differences in the level of robustness of different biomarkers. Our analyses of biomarker sensitivity to image perturbations and heuristic parameter values support these differences and further characterize VascX biomarkers. Ultimately, VascX provides an explainable and easily modifiable feature-extraction toolbox that complements segmentation to produce reliable retinal vascular biomarkers. Our graph-based biomarker computation stages support reproducible, region-aware measurements suited for large-scale clinical and epidemiological research. By enabling easy extraction of existing biomarkers and rapid experimentation with new ones, VascX supports oculomics research. Its robustness and computational efficiency facilitate scalable deployment in large databases, while open-source distribution lowers barriers to adoption for ophthalmic researchers and clinicians. --- ### retinalysis-vascx: An explainable software toolbox for the extraction of retinal vascular biomarkers Authors: Jose D. Vargas Quiros, Michael J. Beyeler, Sofia Ortin Vela, EyeNED Reading Center, Sven Bergmann, Caroline C. W. Klave, Bart Liefers, VascX Research Consortium Published: 2026-02-09 Categories: q-bio.TO, cs.CV arXiv: https://arxiv.org/abs/2602.08580v3 Automatic extraction of retinal vascular biomarkers from color fundus images (CFI) is crucial for large-scale studies of the retinal vasculature. We present VascX, an open-source Python toolbox that extracts biomarkers from CFI artery-vein segmentations. VascX starts from vessel segmentation masks, extracts their skeletons, builds undirected and directed vessel graphs, and resolves vessel segments into longer vessels. A comprehensive set of biomarkers is derived, including vascular density, central retinal equivalents (CREs), and tortuosity. Spatially localized biomarkers may be calculated over grids placed relative to the fovea and optic disc. VascX is released via GitHub and PyPI with comprehensive documentation and examples. Our test-retest reproducibility analysis on repeat imaging of the same eye by different devices shows that most VascX biomarkers have moderate to excellent agreement (ICC > 0.5), with important differences in the level of robustness of different biomarkers. Our analyses of biomarker sensitivity to image perturbations and heuristic parameter values support these differences and further characterize VascX biomarkers. Ultimately, VascX provides an explainable and easily modifiable feature-extraction toolbox that complements segmentation to produce reliable retinal vascular biomarkers. Our graph-based biomarker computation stages support reproducible, region-aware measurements suited for large-scale clinical and epidemiological research. By enabling easy extraction of existing biomarkers and rapid experimentation with new ones, VascX supports oculomics research. Its robustness and computational efficiency facilitate scalable deployment in large databases, while open-source distribution lowers barriers to adoption for ophthalmic researchers and clinicians. --- ### Modeling Score Approximation Errors in Diffusion Models via Forward SPDEs Authors: Junsu Seo Published: 2026-02-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.08579v1 This study investigates the dynamics of Score-based Generative Models (SGMs) by treating the score estimation error as a stochastic source driving the Fokker-Planck equation. Departing from particle-centric SDE analyses, we employ an SPDE framework to model the evolution of the probability density field under stochastic drift perturbations. Under a simplified setting, we utilize this framework to interpret the robustness of generative models through the lens of geometric stability and displacement convexity. Furthermore, we introduce a candidate evaluation metric derived from the quadratic variation of the SPDE solution projected onto a radial test function. Preliminary observations suggest that this metric remains effective using only the initial 10% of the sampling trajectory, indicating a potential for computational efficiency. --- ### An arithmetic method algorithm optimizing k-nearest neighbors compared to regression algorithms and evaluated on real world data sources Authors: Theodoros Anagnostopoulos, Evanthia Zervoudi, Christos Anagnostopoulos, Apostolos Christopoulos, Bogdan Wierzbinski Published: 2026-02-09 Categories: cs.LG, math.CO, stat.CO arXiv: https://arxiv.org/abs/2602.08577v1 Linear regression analysis focuses on predicting a numeric regressand value based on certain regressor values. In this context, k-Nearest Neighbors (k-NN) is a common non-parametric regression algorithm, which achieves efficient performance when compared with other algorithms in literature. In this research effort an optimization of the k-NN algorithm is proposed by exploiting the potentiality of an introduced arithmetic method, which can provide solutions for linear equations involving an arbitrary number of real variables. Specifically, an Arithmetic Method Algorithm (AMA) is adopted to assess the efficiency of the introduced arithmetic method, while an Arithmetic Method Regression (AMR) algorithm is proposed as an optimization of k-NN adopting the potentiality of AMA. Such algorithm is compared with other regression algorithms, according to an introduced optimal inference decision rule, and evaluated on certain real world data sources, which are publicly available. Results are promising since the proposed AMR algorithm has comparable performance with the other algorithms, while in most cases it achieves better performance than the k-NN. The output results indicate that introduced AMR is an optimization of k-NN. --- ### ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems Authors: Jinnuo Liu, Chuke Liu, Hua Shen Published: 2026-02-09 Categories: cs.MA, cs.CL arXiv: https://arxiv.org/abs/2602.08567v2 Multi-agent large language model (LLM) systems increasingly consist of agents that observe and respond to one another's outputs. While value alignment is typically evaluated for isolated models, how value perturbations propagate through agent interactions remains poorly understood. We present ValueFlow, a perturbation-based framework that measures value drift in multi-agent systems via a 56-value valuation dataset derived from the Schwartz Value Survey, with agent value orientations scored using an LLM-as-a-judge protocol. ValueFlow decomposes value drift into agent-level response behavior and system-level structural effects, captured by two metrics: \b{eta}-susceptibility, an agent's sensitivity to perturbed peer value signals, and system susceptibility (SS), the effect of node-level perturbations on final system outputs.Experiments span across value dimensions, backbones, personas, and topologies, showing that susceptibility varies sharply across values and is strongly shaped by interaction structure, indicating that value alignment in multi-agent systems is a system-level property, not just an agent-level one. ValueFlow thus provides a principled basis for auditing and mitigating value propagation in deployed multi-agent systems. --- ### Agent-Supported Foresight for AI Systemic Risks: AI Agents for Breadth, Experts for Judgment Authors: Leon Fröhling, Alessandro Giaconia, Edyta Paulina Bogucka, Daniele Quercia Published: 2026-02-09 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.08565v1 AI impact assessments often stress near-term risks because human judgment degrades over longer horizons, exemplifying the Collingridge dilemma: foresight is most needed when knowledge is scarcest. To address long-term systemic risks, we introduce a scalable approach that simulates in-silico agents using the strategic foresight method of the Futures Wheel. We applied it to four AI uses spanning Technology Readiness Levels (TRLs): Chatbot Companion (TRL 9, mature), AI Toy (TRL 7, medium), Griefbot (TRL 5, low), and Death App (TRL 2, conceptual). Across 30 agent runs per use, agents produced 86-110 consequences, condensed into 27-47 unique risks. To benchmark the agent outputs against human perspectives, we collected evaluations from 290 domain experts and 7 leaders, and conducted Futures Wheel sessions with 42 experts and 42 laypeople. Agents generated many systemic consequences across runs. Compared with these outputs, experts identified fewer risks, typically less systemic but judged more likely, whereas laypeople surfaced more emotionally salient concerns that were generally less systemic. We propose a hybrid foresight workflow, wherein agents broaden systemic coverage, and humans provide contextual grounding. Our dataset is available at: https://social-dynamics.net/ai-risks/foresight. --- ### M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled Data Authors: Tiantong Wang, Yiyang Duan, Haoyu Chen, Tiantong Wu, Wei Yang Bryan Lim Published: 2026-02-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.08564v1 Training of large-scale models is both computationally intensive and often constrained by the availability of labeled data. Model merging offers a compelling alternative by directly integrating the weights of multiple source models without requiring additional data or extensive training. However, conventional model merging techniques, such as parameter averaging, often suffer from the unintended combination of non-generalizable features, especially when source models exhibit significant weight disparities. Comparatively, model ensembling generally provides more stable and superior performance that aggregates multiple models by averaging outputs. However, it incurs higher inference costs and increased storage requirements. While previous studies experimentally showed the similarities between model merging and ensembling, theoretical evidence and evaluation metrics remain lacking. To address this gap, we introduce Merging-ensembling loss (M-Loss), a novel evaluation metric that quantifies the compatibility of merging source models using very limited unlabeled data. By measuring the discrepancy between parameter averaging and model ensembling at layer and node levels, M-Loss facilitates more effective merging strategies. Specifically, M-Loss serves both as a quantitative criterion of the theoretical feasibility of model merging, and a guide for parameter significance in model pruning. Our theoretical analysis and empirical evaluations demonstrate that incorporating M-Loss into the merging process significantly improves the alignment between merged models and model ensembling, providing a scalable and efficient framework for accurate model consolidation. --- ### Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs Authors: Ahmed Salem, Andrew Paverd, Sahar Abdelnabi Published: 2026-02-09 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2602.08563v1 Large language models (LLMs) are commonly treated as stateless: once an interaction ends, no information is assumed to persist unless it is explicitly stored and re-supplied. We challenge this assumption by introducing implicit memory-the ability of a model to carry state across otherwise independent interactions by encoding information in its own outputs and later recovering it when those outputs are reintroduced as input. This mechanism does not require any explicit memory module, yet it creates a persistent information channel across inference requests. As a concrete demonstration, we introduce a new class of temporal backdoors, which we call time bombs. Unlike conventional backdoors that activate on a single trigger input, time bombs activate only after a sequence of interactions satisfies hidden conditions accumulated via implicit memory. We show that such behavior can be induced today through straightforward prompting or fine-tuning. Beyond this case study, we analyze broader implications of implicit memory, including covert inter-agent communication, benchmark contamination, targeted manipulation, and training-data poisoning. Finally, we discuss detection challenges and outline directions for stress-testing and evaluation, with the goal of anticipating and controlling future developments. To promote future research, we release code and data at: https://github.com/microsoft/implicitMemory. --- ### Automating Computational Reproducibility in Social Science: Comparing Prompt-Based and Agent-Based Approaches Authors: Syed Mehtab Hussain Shah, Frank Hopfgartner, Arnim Bleier Published: 2026-02-09 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2602.08561v3 Reproducing computational research is often assumed to be as simple as rerunning the original code with provided data. In practice, missing packages, fragile file paths, version conflicts, or incomplete logic frequently cause analyses to fail, even when materials are shared. This study investigates whether large language models and AI agents can automate the diagnosis and repair of such failures, making computational results easier to reproduce and verify. We evaluate this using a controlled reproducibility testbed built from five fully reproducible R-based social science studies. Realistic failures were injected, ranging from simple issues to complex missing logic, and two automated repair workflows were tested in clean Docker environments. The first workflow is prompt-based, repeatedly querying language models with structured prompts of varying context, while the second uses agent-based systems that inspect files, modify code, and rerun analyses autonomously. Across prompt-based runs, reproduction success ranged from 31-79 percent, with performance strongly influenced by prompt context and error complexity. Complex cases benefited most from additional context. Agent-based workflows performed substantially better, with success rates of 69-96 percent across all complexity levels. These results suggest that automated workflows, especially agent-based systems, can significantly reduce manual effort and improve reproduction success across diverse error types. Unlike prior benchmarks, our testbed isolates post-publication repair under controlled failure modes, allowing direct comparison of prompt-based and agent-based approaches. --- ### DNS: Data-driven Nonlinear Smoother for Complex Model-free Process Authors: Fredrik Cumlin, Anubhab Ghosh, Saikat Chatterjee Published: 2026-02-09 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2602.08560v1 We propose data-driven nonlinear smoother (DNS) to estimate a hidden state sequence of a complex dynamical process from a noisy, linear measurement sequence. The dynamical process is model-free, that is, we do not have any knowledge of the nonlinear dynamics of the complex process. There is no state-transition model (STM) of the process available. The proposed DNS uses a recurrent architecture that helps to provide a closed-form posterior of the hidden state sequence given the measurement sequence. DNS learns in an unsupervised manner, meaning the training dataset consists of only measurement data and no state data. We demonstrate DNS using simulations for smoothing of several stochastic dynamical processes, including a benchmark Lorenz system. Experimental results show that the DNS is significantly better than a deep Kalman smoother (DKS) and an iterative data-driven nonlinear state estimation (iDANSE) smoother. --- ### FLAG-4D: Flow-Guided Local-Global Dual-Deformation Model for 4D Reconstruction Authors: Guan Yuan Tan, Ngoc Tuan Vu, Arghya Pal, Sailaja Rajanala, Raphael Phan C. -W., Mettu Srinivas, Chee-Ming Ting Published: 2026-02-09 Categories: cs.CV, cs.GT arXiv: https://arxiv.org/abs/2602.08558v1 We introduce FLAG-4D, a novel framework for generating novel views of dynamic scenes by reconstructing how 3D Gaussian primitives evolve through space and time. Existing methods typically rely on a single Multilayer Perceptron (MLP) to model temporal deformations, and they often struggle to capture complex point motions and fine-grained dynamic details consistently over time, especially from sparse input views. Our approach, FLAG-4D, overcomes this by employing a dual-deformation network that dynamically warps a canonical set of 3D Gaussians over time into new positions and anisotropic shapes. This dual-deformation network consists of an Instantaneous Deformation Network (IDN) for modeling fine-grained, local deformations and a Global Motion Network (GMN) for capturing long-range dynamics, refined through mutual learning. To ensure these deformations are both accurate and temporally smooth, FLAG-4D incorporates dense motion features from a pretrained optical flow backbone. We fuse these motion cues from adjacent timeframes and use a deformation-guided attention mechanism to align this flow information with the current state of each evolving 3D Gaussian. Extensive experiments demonstrate that FLAG-4D achieves higher-fidelity and more temporally coherent reconstructions with finer detail preservation than state-of-the-art methods. --- ### Rho-Perfect: Correlation Ceiling For Subjective Evaluation Datasets Authors: Fredrik Cumlin Published: 2026-02-09 Categories: cs.LG, eess.AS, stat.ML arXiv: https://arxiv.org/abs/2602.08552v1 Subjective ratings contain inherent noise that limits the model-human correlation, but this reliability issue is rarely quantified. In this paper, we present $ρ$-Perfect, a practical estimation of the highest achievable correlation of a model on subjectively rated datasets. We define $ρ$-Perfect to be the correlation between a perfect predictor and human ratings, and derive an estimate of the value based on heteroscedastic noise scenarios, a common occurrence in subjectively rated datasets. We show that $ρ$-Perfect squared estimates test-retest correlation and use this to validate the estimate. We demonstrate the use of $ρ$-Perfect on a speech quality dataset and show how the measure can distinguish between model limitations and data quality issues. --- ### GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model Editing Authors: Shih-Fang Chen, Jun-Cheng Chen, I-Hong Jhuo, Yen-Yu Lin Published: 2026-02-09 Categories: cs.CV, cs.AI, cs.LG, cs.MM, eess.IV arXiv: https://arxiv.org/abs/2602.08550v3 Human perception for effective object tracking in 2D video streams arises from the implicit use of prior 3D knowledge and semantic reasoning. In contrast, most generic object tracking (GOT) methods primarily rely on 2D features of the target and its surroundings, while neglecting 3D geometric cues, making them susceptible to partial occlusion, distractors, and variations in geometry and appearance. To address this limitation, we introduce GOT-Edit, an online cross-modality model editing approach that integrates geometry-aware cues into a generic object tracker from a 2D video stream. Our approach leverages features from a pre-trained Visual Geometry Grounded Transformer to infer geometric cues from only a few 2D images. To address the challenge of seamlessly combining geometry and semantics, GOT-Edit performs online model editing. By leveraging null-space constraints during model updates, it incorporates geometric information while preserving semantic discrimination, yielding consistently better performance across diverse scenarios. Extensive experiments on multiple GOT benchmarks demonstrate that GOT-Edit achieves superior robustness and accuracy, particularly under occlusion and clutter, establishing a new paradigm for combining 2D semantics with 3D geometric reasoning for generic object tracking. The project page is available at https://chenshihfang.github.io/GOT-EDIT. --- ### How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location Authors: Xuanliang Zhang, Dingzirui Wang, Keyan Xu, Qingfu Zhu, Wanxiang Che Published: 2026-02-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.08548v1 While Large Language Models (LLMs) are increasingly deployed for table-related tasks, the internal mechanisms enabling them to process linearized two-dimensional structured tables remain opaque. In this work, we investigate the process of table understanding by dissecting the atomic task of cell location. Through activation patching and complementary interpretability techniques, we delineate the table understanding mechanism into a sequential three-stage pipeline: Semantic Binding, Coordinate Localization, and Information Extraction. We demonstrate that models locate the target cell via an ordinal mechanism that counts discrete delimiters to resolve coordinates. Furthermore, column indices are encoded within a linear subspace that allows for precise steering of model focus through vector arithmetic. Finally, we reveal that models generalize to multi-cell location tasks by multiplexing the identical attention heads identified during atomic location. Our findings provide a comprehensive explanation of table understanding within Transformer architectures. --- ### GISA: A Benchmark for General Information-Seeking Assistant Authors: Yutao Zhu, Xingshuo Zhang, Maosen Zhang, Jiajie Jin, Liancheng Zhang, Xiaoshuai Song, Kangzhi Zhao, Wencong Zeng, Ruiming Tang, Han Li, Ji-Rong Wen, Zhicheng Dou Published: 2026-02-09 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2602.08543v2 The advancement of large language models (LLMs) has significantly accelerated the development of search agents capable of autonomously gathering information through multi-turn web interactions. Various benchmarks have been proposed to evaluate such agents. However, existing benchmarks often construct queries backward from answers, producing unnatural tasks misaligned with real-world needs. Moreover, these benchmarks tend to focus on either locating specific information or aggregating information from multiple sources, while relying on static answer sets prone to data contamination. To bridge these gaps, we introduce GISA, a benchmark for General Information-Seeking Assistants comprising 373 human-crafted queries that reflect authentic information-seeking scenarios. GISA features four structured answer formats (item, set, list, and table), enabling deterministic evaluation. It integrates both deep reasoning and broad information aggregation within unified tasks, and includes a live subset with periodically updated answers to resist memorization. Notably, GISA provides complete human search trajectories for every query, offering gold-standard references for process-level supervision and imitation learning. Experiments on mainstream LLMs and commercial search products reveal that even the best-performing model achieves only 19.30\% exact match score, with performance notably degrading on tasks requiring complex planning and comprehensive information gathering. These findings highlight substantial room for future improvement. --- ### Incremental (k, z)-Clustering on Graphs Authors: Emilio Cruciani, Sebastian Forster, Antonis Skarlatos Published: 2026-02-09 Categories: cs.DS, cs.LG arXiv: https://arxiv.org/abs/2602.08542v3 Given a weighted undirected graph, a number of clusters $k$, and an exponent $z$, the goal in the $(k, z)$-clustering problem on graphs is to select $k$ vertices as centers that minimize the sum of the distances raised to the power $z$ of each vertex to its closest center. In the dynamic setting, the graph is subject to adversarial edge updates, and the goal is to maintain explicitly an exact $(k, z)$-clustering solution in the induced shortest-path metric. While efficient dynamic $k$-center approximation algorithms on graphs exist (Cruciani et al. SODA 2024), to the best of our knowledge, no prior work provides similar results for the dynamic $(k,z)$-clustering problem. As the main result of this paper, we develop a randomized incremental $(k, z)$-clustering algorithm that maintains with high probability a constant-factor approximation in a graph undergoing edge insertions with a total update time of $\tilde O(k m^{1+o(1)}+ k^{1+\frac{1}λ} m)$, where $λ\geq 1$ is an arbitrary fixed constant. Our incremental algorithm consists of two stages. In the first stage, we maintain a constant-factor bicriteria approximate solution of size $\tilde{O}(k)$ with a total update time of $m^{1+o(1)}$ over all adversarial edge insertions. This first stage is an intricate adaptation of the bicriteria approximation algorithm by Mettu and Plaxton (Machine Learning 2004) to incremental graphs. One of our key technical results is that the radii in their algorithm can be assumed to be non-decreasing while the approximation ratio remains constant, a property that may be of independent interest. In the second stage, we maintain a constant-factor approximate $(k,z)$-clustering solution on a dynamic weighted instance induced by the bicriteria approximate solution. For this subproblem, we employ a dynamic spanner algorithm together with a static $(k,z)$-clustering algorithm. --- ### TIBR4D: Tracing-Guided Iterative Boundary Refinement for Efficient 4D Gaussian Segmentation Authors: He Wu, Xia Yan, Yanghui Xu, Liegang Xia, Jiazhou Chen Published: 2026-02-09 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2602.08540v1 Object-level segmentation in dynamic 4D Gaussian scenes remains challenging due to complex motion, occlusions, and ambiguous boundaries. In this paper, we present an efficient learning-free 4D Gaussian segmentation framework that lifts video segmentation masks to 4D spaces, whose core is a two-stage iterative boundary refinement, TIBR4D. The first stage is an Iterative Gaussian Instance Tracing (IGIT) at the temporal segment level. It progressively refines Gaussian-to-instance probabilities through iterative tracing, and extracts corresponding Gaussian point clouds that better handle occlusions and preserve completeness of object structures compared to existing one-shot threshold-based methods. The second stage is a frame-wise Gaussian Rendering Range Control (RCC) via suppressing highly uncertain Gaussians near object boundaries while retaining their core contributions for more accurate boundaries. Furthermore, a temporal segmentation merging strategy is proposed for IGIT to balance identity consistency and dynamic awareness. Longer segments enforce stronger multi-frame constraints for stable identities, while shorter segments allow identity changes to be captured promptly. Experiments on HyperNeRF and Neu3D demonstrate that our method produces accurate object Gaussian point clouds with clearer boundaries and higher efficiency compared to SOTA methods. --- ### Trajectory Stitching for Solving Inverse Problems with Flow-Based Models Authors: Alexander Denker, Moshe Eliasof, Zeljko Kereta, Carola-Bibiane Schönlieb Published: 2026-02-09 Categories: eess.IV, cs.LG arXiv: https://arxiv.org/abs/2602.08538v1 Flow-based generative models have emerged as powerful priors for solving inverse problems. One option is to directly optimize the initial latent code (noise), such that the flow output solves the inverse problem. However, this requires backpropagating through the entire generative trajectory, incurring high memory costs and numerical instability. We propose MS-Flow, which represents the trajectory as a sequence of intermediate latent states rather than a single initial code. By enforcing the flow dynamics locally and coupling segments through trajectory-matching penalties, MS-Flow alternates between updating intermediate latent states and enforcing consistency with observed data. This reduces memory consumption while improving reconstruction quality. We demonstrate the effectiveness of MS-Flow over existing methods on image recovery and inverse problems, including inpainting, super-resolution, and computed tomography. --- ### Causal Schrödinger Bridges: Constrained Optimal Transport on Structural Manifolds Authors: Rui Wu, Li YongJun Published: 2026-02-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.08535v4 Generative modeling typically seeks the path of least action via deterministic flows (ODE). While effective for in-distribution tasks, we argue that these deterministic paths become brittle under causal interventions, which often require transporting probability mass across low-density regions ("off-manifold") where the vector field is ill-defined. This leads to numerical instability and the pathology of anticipatory control. In this work, we introduce the Causal Schrodinger Bridge (CSB), a framework that reformulates counterfactual inference as Entropic Optimal Transport. By leveraging diffusion processes (SDEs), CSB enables probability mass to robustly "tunnel" through support mismatches while strictly enforcing structural admissibility. We prove the Structural Decomposition Theorem, showing that the global high-dimensional bridge factorizes exactly into local, robust transitions. This theorem provides a principled resolution to the Information Bottleneck that plagues monolithic architectures in high dimensions. We empirically validate CSB on a full-rank causal system (d=10^5, intrinsic rank 10^5), where standard structure-blind MLPs fail to converge (MSE ~0.31). By physically implementing the structural decomposition, CSB achieves high-fidelity transport (MSE ~0.06) in just 73.73 seconds on a single GPU. This stands in stark contrast to structure-agnostic O(d^3) baselines, estimated to require over 6 years. Our results demonstrate that CSB breaks the Curse of Dimensionality through structural intelligence, offering a scalable foundation for high-stakes causal discovery in 10^5-node systems. Code is available at: https://github.com/cochran1/causal-schrodinger-bridge --- ### Dialogue Model Optimization via Agent Game and Adaptive Tree-based GRPO Authors: Kun Peng, Conghui Tan, Yu Liu, Guohua Tang, Zhongqian Sun, Wei Yang, Zining Zhu, Lei Jiang, Yanbing Liu, Hao Peng Published: 2026-02-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.08533v2 Open-ended dialogue agents aim to deliver engaging, personalized interactions by adapting to users' traits, but existing methods face critical limitations: over-reliance on pre-collected user data, and short-horizon biases in reinforcement learning (RL) that neglect long-term dialogue value. To address these, we propose a novel long-horizon RL framework integrating online personalization with Adaptive Tree-based Group Relative Policy Optimization (AT-GRPO). Adopting a two-agent game paradigm, a user agent constructs dynamic environments via style mimicry (learning user-specific conversational traits) and active termination (predicting turn-level termination probabilities as immediate rewards), forming an iterative cycle that drives the dialogue agent to deepen interest exploration. AT-GRPO reinterprets dialogue trajectories as trees and introduces adaptive observation ranges. Unlike full tree expansion that incurs exponential overhead, it limits each node to aggregate rewards from a stage-aware range: larger ranges support early-stage topic exploration, while smaller ranges facilitate late-stage dialogue maintenance. This design reduces rollout budgets from exponential to polynomial in the dialogue length, while preserving long-term reward capture. Extensive experiments show our framework's superior performance, sample efficiency, and robustness. --- ### Thegra: Graph-based SLAM for Thermal Imagery Authors: Anastasiia Kornilova, Ivan Moskalenko, Arabella Gromova, Gonzalo Ferrer, Alexander Menshchikov Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.08531v1 Thermal imaging provides a practical sensing modality for visual SLAM in visually degraded environments such as low illumination, smoke, or adverse weather. However, thermal imagery often exhibits low texture, low contrast, and high noise, complicating feature-based SLAM. In this work, we propose a sparse monocular graph-based SLAM system for thermal imagery that leverages general-purpose learned features -- the SuperPoint detector and LightGlue matcher, trained on large-scale visible-spectrum data to improve cross-domain generalization. To adapt these components to thermal data, we introduce a preprocessing pipeline to enhance input suitability and modify core SLAM modules to handle sparse and outlier-prone feature matches. We further incorporate keypoint confidence scores from SuperPoint into a confidence-weighted factor graph to improve estimation robustness. Evaluations on public thermal datasets demonstrate that the proposed system achieves reliable performance without requiring dataset-specific training or fine-tuning a desired feature detector, given the scarcity of quality thermal data. Code will be made available upon publication. --- ### Automatic regularization parameter choice for tomography using a double model approach Authors: Chuyang Wu, Samuli Siltanen Published: 2026-02-09 Categories: cs.CV, math.OC arXiv: https://arxiv.org/abs/2602.08528v2 Image reconstruction in X-ray tomography is an ill-posed inverse problem, particularly with limited available data. Regularization is thus essential, but its effectiveness hinges on the choice of a regularization parameter that balances data fidelity against a priori information. We present a novel method for automatic parameter selection based on the use of two distinct computational discretizations of the same problem. A feedback control algorithm dynamically adjusts the regularization strength, driving an iterative reconstruction toward the smallest parameter that yields sufficient similarity between reconstructions on the two grids. The effectiveness of the proposed approach is demonstrated using real tomographic data. --- ### GeoFocus: Blending Efficient Global-to-Local Perception for Multimodal Geometry Problem-Solving Authors: Linger Deng, Yuliang Liu, Wenwen Yu, Zujia Zhang, Jianzhong Ju, Zhenbo Luo, Xiang Bai Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.08524v1 Geometry problem-solving remains a significant challenge for Large Multimodal Models (LMMs), requiring not only global shape recognition but also attention to intricate local relationships related to geometric theory. To address this, we propose GeoFocus, a novel framework comprising two core modules. 1) Critical Local Perceptor, which automatically identifies and emphasizes critical local structure (e.g., angles, parallel lines, comparative distances) through thirteen theory-based perception templates, boosting critical local feature coverage by 61% compared to previous methods. 2) VertexLang, a compact topology formal language, encodes global figures through vertex coordinates and connectivity relations. By replacing bulky code-based encodings, VertexLang reduces global perception training time by 20% while improving topology recognition accuracy. When evaluated in Geo3K, GeoQA, and FormalGeo7K, GeoFocus achieves a 4.7% accuracy improvement over leading specialized models and demonstrates superior robustness in MATHVERSE under diverse visual conditions. Project Page -- https://github.com/dle666/GeoFocus --- ### Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model Reasoning Authors: Xinhai Sun Published: 2026-02-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.08520v3 Modern large language models (LLMs) are often evaluated and deployed under a one-shot, greedy inference protocol, especially in professional settings that require deterministic behavior. This regime can systematically under-estimate a fixed model's true capability: many errors arise not from missing knowledge, but from premature commitment under internal ambiguity. We introduce Reinforcement Inference, an entropy-aware inference-time control strategy that uses the model's own uncertainty to selectively invoke a second, more deliberate reasoning attempt, enabling stronger performance without any retraining. On 12,032 MMLU-Pro questions across 14 subjects, using DeepSeek-v3.2 with deterministic decoding in a zero-shot setting, Reinforcement Inference improves accuracy from 60.72% to 84.03%, while only incurring 61.06% additional inference calls. A 100% re-asking ablation reaches 84.35%, indicating that uncertainty-aware selection captures most of the attainable improvement with substantially less compute. Moreover, a prompt-only ablation underperforms the baseline, suggesting that the gains are not explained by generic prompting alone. Beyond providing a practical inference-time upgrade, our results suggest a broader entropy-aware paradigm for measuring and expanding model capability: because modern decoder-based models generate outputs autoregressively, entropy and related confidence measures arise naturally as first-class control signals during generation. The resulting gap between one-pass greedy inference and uncertainty-conditioned deliberation offers a diagnostic lens on an LLM's latent reasoning horizon and motivates future training objectives that explicitly constrain correctness--confidence alignment. --- ### Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering Authors: Yunhui Liu, Pengyu Qiu, Yu Xing, Yongchao Liu, Peng Du, Chuntao Hong, Jiajun Zheng, Tao Zheng, Tieke He Published: 2026-02-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.08519v1 Attributed Graph Clustering (AGC) is a fundamental unsupervised task that integrates structural topology and node attributes to uncover latent patterns in graph-structured data. Despite its significance in industrial applications such as fraud detection and user segmentation, a significant chasm persists between academic research and real-world deployment. Current evaluation protocols suffer from the small-scale, high-homophily citation datasets, non-scalable full-batch training paradigms, and a reliance on supervised metrics that fail to reflect performance in label-scarce environments. To bridge these gaps, we present PyAGC, a comprehensive, production-ready benchmark and library designed to stress-test AGC methods across diverse scales and structural properties. We unify existing methodologies into a modular Encode-Cluster-Optimize framework and, for the first time, provide memory-efficient, mini-batch implementations for a wide array of state-of-the-art AGC algorithms. Our benchmark curates 12 diverse datasets, ranging from 2.7K to 111M nodes, specifically incorporating industrial graphs with complex tabular features and low homophily. Furthermore, we advocate for a holistic evaluation protocol that mandates unsupervised structural metrics and efficiency profiling alongside traditional supervised metrics. Battle-tested in high-stakes industrial workflows at Ant Group, this benchmark offers the community a robust, reproducible, and scalable platform to advance AGC research towards realistic deployment. The code and resources are publicly available via GitHub (https://github.com/Cloudy1225/PyAGC), PyPI (https://pypi.org/project/pyagc), and Documentation (https://pyagc.readthedocs.io). ---