# Research Papers — 2026-02 · bundle page 159 of 210

> Full-text markdown of papers #7901–7950 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/159
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/158.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/160.md)

### NanoNet: Parameter-Efficient Learning with Label-Scarce Supervision for Lightweight Text Mining Model

Authors: Qianren Mao, Yashuo Luo, Ziqi Qin, Junnan Liu, Weifeng Jiang, Zhijun Chen, Zhuoran Li, Likang Xiao, Chuou Xu, Qili Zhang, Hanwen Hao, Jingzheng Li et al.
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06093v1

The lightweight semi-supervised learning (LSL) strategy provides an effective approach of conserving labeled samples and minimizing model inference costs. Prior research has effectively applied knowledge transfer learning and co-training regularization from large to small models in LSL. However, such training strategies are computationally intensive and prone to local optima, thereby increasing the difficulty of finding the optimal solution. This has prompted us to investigate the feasibility of integrating three low-cost scenarios for text mining tasks: limited labeled supervision, lightweight fine-tuning, and rapid-inference small models. We propose NanoNet, a novel framework for lightweight text mining that implements parameter-efficient learning with limited supervision. It employs online knowledge distillation to generate multiple small models and enhances their performance through mutual learning regularization. The entire process leverages parameter-efficient learning, reducing training costs and minimizing supervision requirements, ultimately yielding a lightweight model for downstream inference.

---

### SVRepair: Structured Visual Reasoning for Automated Program Repair

Authors: Jincheng Wang, Liwei Luo, Xiaoxuan Tang, Jingxuan Xu, Sheng Zhou, Dajun Chen, Wei Jiang, Yong Li
Published: 2026-02-05
Categories: cs.SE, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.06090v2

Large language models (LLMs) have recently been applied to Automated Program Repair (APR), yet most existing approaches remain unimodal and fail to use diagnostic signals contained in visual artifacts such as screenshots and control-flow graphs. In practice, many bug reports convey critical information visually (e.g., layout breakage or missing widgets), but directly using such dense visual inputs often causes context loss and noise, making it difficult for MLLMs to ground visual observations into precise fault localization and executable patches. To bridge this semantic gap, we propose \textbf{SVRepair}, a multimodal APR framework with Structured Visual Representation (SVR). SVRepair first fine-tunes a vision-language model, SVR, to uniformly transform heterogeneous visual artifacts into a \emph{semantic scene graph} that captures GUI elements and their structural relations (e.g., hierarchy), providing normalized, code-relevant context for downstream repair. Building on the graph, SVRepair drives a coding agent to localize faults and synthesize patches, and further introduces an iterative visual-artifact segmentation strategy that progressively narrows the input to bug-centered regions to suppress irrelevant context and reduce hallucinations. Across primary repository-level APR benchmarks, SVRepair resolves \textbf{186/517} SWE-Bench M instances (\textbf{35.98\%} over all instances; \textbf{36.47\%} over submitted runs) and \textbf{4/19} visual OmniGIRL instances (\textbf{21.05\%}). On supplementary structured multimodal code reasoning benchmarks, SVRepair reaches \textbf{38.02\%} on MMCode and \textbf{95.73\%} on CodeVision. Code is available at https://github.com/codefuse-ai/CodeFuse-SVR.

---

### Transformer-Based Reinforcement Learning for Autonomous Orbital Collision Avoidance in Partially Observable Environments

Authors: Thomas Georges, Adam Abdin
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06088v1

We introduce a Transformer-based Reinforcement Learning framework for autonomous orbital collision avoidance that explicitly models the effects of partial observability and imperfect monitoring in space operations. The framework combines a configurable encounter simulator, a distance-dependent observation model, and a sequential state estimator to represent uncertainty in relative motion. A central contribution of this work is the use of transformer-based Partially Observable Markov Decision Process (POMDP) architecture, which leverage long-range temporal attention to interpret noisy and intermittent observations more effectively than traditional architectures. This integration provides a foundation for training collision avoidance agents that can operate more reliably under imperfect monitoring environments.

---

### Shared LoRA Subspaces for almost Strict Continual Learning

Authors: Prakhar Kaushik, Ankit Vaidya, Shravan Chaudhari, Rama Chellappa, Alan Yuille
Published: 2026-02-05
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.06043v1

Adapting large pretrained models to new tasks efficiently and continually is crucial for real-world deployment but remains challenging due to catastrophic forgetting and the high cost of retraining. While parameter-efficient tuning methods like low rank adaptation (LoRA) reduce computational demands, they lack mechanisms for strict continual learning and knowledge integration, without relying on data replay, or multiple adapters. We propose Share, a novel approach to parameter efficient continual finetuning that learns and dynamically updates a single, shared low-rank subspace, enabling seamless adaptation across multiple tasks and modalities. Share constructs a foundational subspace that extracts core knowledge from past tasks and incrementally integrates new information by identifying essential subspace directions. Knowledge from each new task is incorporated into this evolving subspace, facilitating forward knowledge transfer, while minimizing catastrophic interference. This approach achieves up to 100x parameter reduction and 281x memory savings over traditional LoRA methods, maintaining performance comparable to jointly trained models. A single Share model can replace hundreds of task-specific LoRA adapters, supporting scalable, asynchronous continual learning. Experiments across image classification, natural language understanding, 3D pose estimation, and text-to-image generation validate its effectiveness, making Share a practical and scalable solution for lifelong learning in large-scale AI systems.

---

### Pseudo-Invertible Neural Networks

Authors: Yamit Ehrlich, Nimrod Berman, Assaf Shocher
Published: 2026-02-05
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.06042v2

The Moore-Penrose Pseudo-inverse (PInv) serves as the fundamental solution for linear systems. In this paper, we propose a natural generalization of PInv to the nonlinear regime in general and to neural networks in particular. We introduce Surjective Pseudo-invertible Neural Networks (SPNN), a class of architectures explicitly designed to admit a tractable non-linear PInv. The proposed non-linear PInv and its implementation in SPNN satisfy fundamental geometric properties. One such property is null-space projection or "Back-Projection", $x' = x + A^\dagger(y-Ax)$, which moves a sample $x$ to its closest consistent state $x'$ satisfying $Ax=y$. We formalize Non-Linear Back-Projection (NLBP), a method that guarantees the same consistency constraint for non-linear mappings $f(x)=y$ via our defined PInv. We leverage SPNNs to expand the scope of zero-shot inverse problems. Diffusion-based null-space projection has revolutionized zero-shot solving for linear inverse problems by exploiting closed-form back-projection. We extend this method to non-linear degradations. Here, "degradation" is broadly generalized to include any non-linear loss of information, spanning from optical distortions to semantic abstractions like classification. This approach enables zero-shot inversion of complex degradations and allows precise semantic control over generative outputs without retraining the diffusion prior.

---

### Pseudo-Invertible Neural Networks

Authors: Yamit Ehrlich, Nimrod Berman, Assaf Shocher
Published: 2026-02-05
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.06042v1

The Moore-Penrose Pseudo-inverse (PInv) serves as the fundamental solution for linear systems. In this paper, we propose a natural generalization of PInv to the nonlinear regime in general and to neural networks in particular. We introduce Surjective Pseudo-invertible Neural Networks (SPNN), a class of architectures explicitly designed to admit a tractable non-linear PInv. The proposed non-linear PInv and its implementation in SPNN satisfy fundamental geometric properties. One such property is null-space projection or "Back-Projection", $x' = x + A^\dagger(y-Ax)$, which moves a sample $x$ to its closest consistent state $x'$ satisfying $Ax=y$. We formalize Non-Linear Back-Projection (NLBP), a method that guarantees the same consistency constraint for non-linear mappings $f(x)=y$ via our defined PInv. We leverage SPNNs to expand the scope of zero-shot inverse problems. Diffusion-based null-space projection has revolutionized zero-shot solving for linear inverse problems by exploiting closed-form back-projection. We extend this method to non-linear degradations. Here, "degradation" is broadly generalized to include any non-linear loss of information, spanning from optical distortions to semantic abstractions like classification. This approach enables zero-shot inversion of complex degradations and allows precise semantic control over generative outputs without retraining the diffusion prior.

---

### Predicting Camera Pose from Perspective Descriptions for Spatial Reasoning

Authors: Xuejun Zhang, Aditi Tiwari, Zhenhailong Wang, Heng Ji
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06041v2

Multi-image spatial reasoning remains challenging for current multimodal large language models (MLLMs). While single-view perception is inherently 2D, reasoning over multiple views requires building a coherent scene understanding across viewpoints. In particular, we study perspective taking, where a model must build a coherent 3D understanding from multi-view observations and use it to reason from a new, language-specified viewpoint. We introduce CAMCUE, a pose-aware multi-image framework that uses camera pose as an explicit geometric anchor for cross-view fusion and novel-view reasoning. CAMCUE injects per-view pose into visual tokens, grounds natural-language viewpoint descriptions to a target camera pose, and synthesizes a pose-conditioned imagined target view to support answering. To support this setting, we curate CAMCUE-DATA with 27,668 training and 508 test instances pairing multi-view images and poses with diverse target-viewpoint descriptions and perspective-shift questions. We also include human-annotated viewpoint descriptions in the test split to evaluate generalization to human language. CAMCUE improves overall accuracy by 9.06% and predicts target poses from natural-language viewpoint descriptions with over 90% rotation accuracy within 20° and translation accuracy within a 0.5 error threshold. This direct grounding avoids expensive test-time search-and-match, reducing inference time from 256.6s to 1.45s per example and enabling fast, interactive use in real-world scenarios.

---

### SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs

Authors: Jintao Tong, Shilin Yan, Hongwei Xue, Xiaojun Tang, Kunyu Shi, Guannan Zhang, Ruixuan Li, Yixiong Zou
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06040v1

Multimodal Large Language Models (MLLMs) have made remarkable progress in multimodal perception and reasoning by bridging vision and language. However, most existing MLLMs perform reasoning primarily with textual CoT, which limits their effectiveness on vision-intensive tasks. Recent approaches inject a fixed number of continuous hidden states as "visual thoughts" into the reasoning process and improve visual performance, but often at the cost of degraded text-based logical reasoning. We argue that the core limitation lies in a rigid, pre-defined reasoning pattern that cannot adaptively choose the most suitable thinking modality for different user queries. We introduce SwimBird, a reasoning-switchable MLLM that dynamically switches among three reasoning modes conditioned on the input: (1) text-only reasoning, (2) vision-only reasoning (continuous hidden states as visual thoughts), and (3) interleaved vision-text reasoning. To enable this capability, we adopt a hybrid autoregressive formulation that unifies next-token prediction for textual thoughts with next-embedding prediction for visual thoughts, and design a systematic reasoning-mode curation strategy to construct SwimBird-SFT-92K, a diverse supervised fine-tuning dataset covering all three reasoning patterns. By enabling flexible, query-adaptive mode selection, SwimBird preserves strong textual logic while substantially improving performance on vision-dense tasks. Experiments across diverse benchmarks covering textual reasoning and challenging visual understanding demonstrate that SwimBird achieves state-of-the-art results and robust gains over prior fixed-pattern multimodal reasoning methods.

---

### DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching

Authors: Yuxing Lu, Yucheng Hu, Xukai Zhao, Jiuxin Cao
Published: 2026-02-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.06039v1

Multi-agent systems built from prompted large language models can improve multi-round reasoning, yet most existing pipelines rely on fixed, trajectory-wide communication patterns that are poorly matched to the stage-dependent needs of iterative problem solving. We introduce DyTopo, a manager-guided multi-agent framework that reconstructs a sparse directed communication graph at each round. Conditioned on the manager's round goal, each agent outputs lightweight natural-language query (need) and \key (offer) descriptors; DyTopo embeds these descriptors and performs semantic matching, routing private messages only along the induced edges. Across code generation and mathematical reasoning benchmarks and four LLM backbones, DyTopo consistently outperforms over the strongest baseline (avg. +6.2). Beyond accuracy, DyTopo yields an interpretable coordination trace via the evolving graphs, enabling qualitative inspection of how communication pathways reconfigure across rounds.

---

### CommCP: Efficient Multi-Agent Coordination via LLM-Based Communication with Conformal Prediction

Authors: Xiaopan Zhang, Zejin Wang, Zhixu Li, Jianpeng Yao, Jiachen Li
Published: 2026-02-05
Categories: cs.RO, cs.AI, cs.CV, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2602.06038v1

To complete assignments provided by humans in natural language, robots must interpret commands, generate and answer relevant questions for scene understanding, and manipulate target objects. Real-world deployments often require multiple heterogeneous robots with different manipulation capabilities to handle different assignments cooperatively. Beyond the need for specialized manipulation skills, effective information gathering is important in completing these assignments. To address this component of the problem, we formalize the information-gathering process in a fully cooperative setting as an underexplored multi-agent multi-task Embodied Question Answering (MM-EQA) problem, which is a novel extension of canonical Embodied Question Answering (EQA), where effective communication is crucial for coordinating efforts without redundancy. To address this problem, we propose CommCP, a novel LLM-based decentralized communication framework designed for MM-EQA. Our framework employs conformal prediction to calibrate the generated messages, thereby minimizing receiver distractions and enhancing communication reliability. To evaluate our framework, we introduce an MM-EQA benchmark featuring diverse, photo-realistic household scenarios with embodied questions. Experimental results demonstrate that CommCP significantly enhances the task success rate and exploration efficiency over baselines. The experiment videos, code, and dataset are available on our project website: https://comm-cp.github.io.

---

### Thinking with Geometry: Active Geometry Integration for Spatial Reasoning

Authors: Haoyuan Li, Qihang Cao, Tao Tang, Kun Xiang, Zihan Guo, Jianhua Han, JiaWang Bian, Hang Xu, Xiaodan Liang
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06037v5

Recent progress in spatial reasoning with Multimodal Large Language Models (MLLMs) increasingly leverages geometric priors from 3D encoders. However, most existing integration strategies remain passive: geometry is exposed as a global stream and fused in an indiscriminate manner, which often induces semantic-geometry misalignment and redundant signals. We propose GeoThinker, a framework that shifts the paradigm from passive fusion to active perception. Instead of feature mixing, GeoThinker enables the model to selectively retrieve geometric evidence conditioned on its internal reasoning demands. GeoThinker achieves this through Spatial-Grounded Fusion applied at carefully selected VLM layers, where semantic visual priors selectively query and integrate task-relevant geometry via frame-strict cross-attention, further calibrated by Importance Gating that biases per-frame attention toward task-relevant structures. Comprehensive evaluation results show that GeoThinker sets a new state-of-the-art in spatial intelligence, achieving a peak score of 72.6 on the VSI-Bench. Furthermore, GeoThinker demonstrates robust generalization and significantly improved spatial perception across complex downstream scenarios, including embodied referring and autonomous driving. Our results indicate that the ability to actively integrate spatial structures is essential for next-generation spatial intelligence. Code can be found at https://github.com/Li-Hao-yuan/GeoThinker.

---

### DFlash: Block Diffusion for Flash Speculative Decoding

Authors: Jian Chen, Yesheng Liang, Zhijian Liu
Published: 2026-02-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.06036v2

Autoregressive large language models (LLMs) deliver strong performance but require inherently sequential decoding, leading to high inference latency and poor GPU utilization. Speculative decoding mitigates this bottleneck by using a fast draft model whose outputs are verified in parallel by the target LLM; however, existing methods still rely on autoregressive drafting, which remains sequential and limits practical speedups. Diffusion LLMs offer a promising alternative by enabling parallel generation, but current diffusion models typically underperform compared with autoregressive models. In this paper, we introduce DFlash, a speculative decoding framework that employs a lightweight block diffusion model for parallel drafting. By generating draft tokens in a single forward pass and conditioning the draft model on context features extracted from the target model, DFlash enables efficient drafting with high-quality outputs and higher acceptance rates. Experiments show that DFlash achieves over 6x lossless acceleration across a range of models and tasks, delivering up to 2.5x higher speedup than the state-of-the-art speculative decoding method EAGLE-3.

---

### InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactions

Authors: Sirui Xu, Samuel Schulter, Morteza Ziyadi, Xialin He, Xiaohan Fei, Yu-Xiong Wang, Liangyan Gui
Published: 2026-02-05
Categories: cs.CV, cs.GR, cs.RO
arXiv: https://arxiv.org/abs/2602.06035v1

Humans rarely plan whole-body interactions with objects at the level of explicit whole-body movements. High-level intentions, such as affordance, define the goal, while coordinated balance, contact, and manipulation can emerge naturally from underlying physical and motor priors. Scaling such priors is key to enabling humanoids to compose and generalize loco-manipulation skills across diverse contexts while maintaining physically coherent whole-body coordination. To this end, we introduce InterPrior, a scalable framework that learns a unified generative controller through large-scale imitation pretraining and post-training by reinforcement learning. InterPrior first distills a full-reference imitation expert into a versatile, goal-conditioned variational policy that reconstructs motion from multimodal observations and high-level intent. While the distilled policy reconstructs training behaviors, it does not generalize reliably due to the vast configuration space of large-scale human-object interactions. To address this, we apply data augmentation with physical perturbations, and then perform reinforcement learning finetuning to improve competence on unseen goals and initializations. Together, these steps consolidate the reconstructed latent skills into a valid manifold, yielding a motion prior that generalizes beyond the training data, e.g., it can incorporate new behaviors such as interactions with unseen objects. We further demonstrate its effectiveness for user-interactive control and its potential for real robot deployment.

---

### V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval

Authors: Dongyang Chen, Chaoyang Wang, Dezhao Su, Xi Xiao, Zeyu Zhang, Jing Xiong, Qing Li, Yuzhang Shang, Shichao Kan
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06034v4

Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However, existing approaches remain largely language-driven, relying on static visual encodings and lacking the ability to actively verify fine-grained visual evidence, which often leads to speculative reasoning in visually ambiguous cases. We propose V-Retrver, an evidence-driven retrieval framework that reformulates multimodal retrieval as an agentic reasoning process grounded in visual inspection. V-Retrver enables an MLLM to selectively acquire visual evidence during reasoning via external visual tools, performing a multimodal interleaved reasoning process that alternates between hypothesis generation and targeted visual verification.To train such an evidence-gathering retrieval agent, we adopt a curriculum-based learning strategy combining supervised reasoning activation, rejection-based refinement, and reinforcement learning with an evidence-aligned objective. Experiments across multiple multimodal retrieval benchmarks demonstrate consistent improvements in retrieval accuracy (with 23.0% improvements on average), perception-driven reasoning reliability, and generalization.

---

### V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval

Authors: Dongyang Chen, Chaoyang Wang, Dezhao Su, Xi Xiao, Zeyu Zhang, Jing Xiong, Qing Li, Yuzhang Shang, Shichao Kan
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06034v2

Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However, existing approaches remain largely language-driven, relying on static visual encodings and lacking the ability to actively verify fine-grained visual evidence, which often leads to speculative reasoning in visually ambiguous cases. We propose V-Retrver, an evidence-driven retrieval framework that reformulates multimodal retrieval as an agentic reasoning process grounded in visual inspection. V-Retrver enables an MLLM to selectively acquire visual evidence during reasoning via external visual tools, performing a multimodal interleaved reasoning process that alternates between hypothesis generation and targeted visual verification.To train such an evidence-gathering retrieval agent, we adopt a curriculum-based learning strategy combining supervised reasoning activation, rejection-based refinement, and reinforcement learning with an evidence-aligned objective. Experiments across multiple multimodal retrieval benchmarks demonstrate consistent improvements in retrieval accuracy (with 23.0% improvements on average), perception-driven reasoning reliability, and generalization.

---

### Can Vision Language Models Learn Intuitive Physics from Interaction?

Authors: Luca M. Schulze Buschoff, Konstantinos Voudouris, Can Demircan, Eric Schulz
Published: 2026-02-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06033v2

Pre-trained vision language models do not have good intuitions about the physical world. Recent work has shown that supervised fine-tuning can improve model performance on simple physical tasks. However, fine-tuned models do not appear to learn robust physical rules that can generalize to new contexts. Based on research in cognitive science, we hypothesize that models need to interact with an environment to properly learn its physical dynamics. We train models that learn through interaction with a simulated environment using reinforcement learning. While learning from interaction allows models to improve their within-task performance, it fails to produce models with generalizable physical intuitions. We find that models trained on one task do not reliably generalize to related tasks, even if the tasks share visual statistics and physical principles, and regardless of whether the models are trained through interaction.

---

### Splat and Distill: Augmenting Teachers with Feed-Forward 3D Reconstruction For 3D-Aware Distillation

Authors: David Shavin, Sagie Benaim
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06032v2

Vision Foundation Models (VFMs) have achieved remarkable success when applied to various downstream 2D tasks. Despite their effectiveness, they often exhibit a critical lack of 3D awareness. To this end, we introduce Splat and Distill, a framework that instills robust 3D awareness into 2D VFMs by augmenting the teacher model with a fast, feed-forward 3D reconstruction pipeline. Given 2D features produced by a teacher model, our method first lifts these features into an explicit 3D Gaussian representation, in a feedforward manner. These 3D features are then ``splatted" onto novel viewpoints, producing a set of novel 2D feature maps used to supervise the student model, ``distilling" geometrically grounded knowledge. By replacing slow per-scene optimization of prior work with our feed-forward lifting approach, our framework avoids feature-averaging artifacts, creating a dynamic learning process where the teacher's consistency improves alongside that of the student. We conduct a comprehensive evaluation on a suite of downstream tasks, including monocular depth estimation, surface normal estimation, multi-view correspondence, and semantic segmentation. Our method significantly outperforms prior works, not only achieving substantial gains in 3D awareness but also enhancing the underlying semantic richness of 2D features. Project page is available at https://davidshavin4.github.io/Splat-and-Distill/

---

### AP-OOD: Attention Pooling for Out-of-Distribution Detection

Authors: Claus Hofmann, Christian Huber, Bernhard Lehner, Daniel Klotz, Sepp Hochreiter, Werner Zellinger
Published: 2026-02-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06031v1

Out-of-distribution (OOD) detection, which maps high-dimensional data into a scalar OOD score, is critical for the reliable deployment of machine learning models. A key challenge in recent research is how to effectively leverage and aggregate token embeddings from language models to obtain the OOD score. In this work, we propose AP-OOD, a novel OOD detection method for natural language that goes beyond simple average-based aggregation by exploiting token-level information. AP-OOD is a semi-supervised approach that flexibly interpolates between unsupervised and supervised settings, enabling the use of limited auxiliary outlier data. Empirically, AP-OOD sets a new state of the art in OOD detection for text: in the unsupervised setting, it reduces the FPR95 (false positive rate at 95% true positives) from 27.84% to 4.67% on XSUM summarization, and from 77.08% to 70.37% on WMT15 En-Fr translation.

---

### PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling

Authors: Kavana Venkatesh, Yinhan He, Jundong Li, Jiaming Cui
Published: 2026-02-05
Categories: cs.MA, cs.LG
arXiv: https://arxiv.org/abs/2602.06030v2

Large language model (LLM)-based multi-agent systems enable expressive agent reasoning but are expensive to scale and poorly calibrated for timestep-aligned state-transition simulation, while classical agent-based models (ABMs) offer interpretability but struggle to integrate rich individual-level signals and non-stationary behaviors. We propose PhysicsAgentABM, which shifts inference to behaviorally coherent agent clusters: state-specialized symbolic agents encode mechanistic transition priors, a multimodal neural transition model captures temporal and interaction dynamics, and uncertainty-aware epistemic fusion yields calibrated cluster-level transition distributions. Individual agents then stochastically realize transitions under local constraints, decoupling population inference from entity-level variability. We further introduce ANCHOR, an LLM agent-driven clustering strategy based on cross-contextual behavioral responses and a novel contrastive loss, reducing LLM calls by up to 6-8 times. Experiments across public health, finance, and social sciences show consistent gains in event-time accuracy and calibration over mechanistic, neural, and LLM baselines. By re-architecting generative ABM around population-level inference with uncertainty-aware neuro-symbolic fusion, PhysicsAgentABM establishes a new paradigm for scalable and calibrated simulation with LLMs.

---

### Curiosity is Knowledge: Self-Consistent Learning and No-Regret Optimization with Active Inference

Authors: Yingke Li, Anjali Parashar, Enlu Zhou, Chuchu Fan
Published: 2026-02-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06029v1

Active inference (AIF) unifies exploration and exploitation by minimizing the Expected Free Energy (EFE), balancing epistemic value (information gain) and pragmatic value (task performance) through a curiosity coefficient. Yet it has been unclear when this balance yields both coherent learning and efficient decision-making: insufficient curiosity can drive myopic exploitation and prevent uncertainty resolution, while excessive curiosity can induce unnecessary exploration and regret. We establish the first theoretical guarantee for EFE-minimizing agents, showing that a single requirement--sufficient curiosity--simultaneously ensures self-consistent learning (Bayesian posterior consistency) and no-regret optimization (bounded cumulative regret). Our analysis characterizes how this mechanism depends on initial uncertainty, identifiability, and objective alignment, thereby connecting AIF to classical Bayesian experimental design and Bayesian optimization within one theoretical framework. We further translate these theories into practical design guidelines for tuning the epistemic-pragmatic trade-off in hybrid learning-optimization problems, validated through real-world experiments.

---

### Context Forcing: Consistent Autoregressive Video Generation with Long Context

Authors: Shuo Chen, Cong Wei, Sun Sun, Ping Nie, Kai Zhou, Ge Zhang, Ming-Hsuan Yang, Wenhu Chen
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06028v1

Recent approaches to real-time long video generation typically employ streaming tuning strategies, attempting to train a long-context student using a short-context (memoryless) teacher. In these frameworks, the student performs long rollouts but receives supervision from a teacher limited to short 5-second windows. This structural discrepancy creates a critical \textbf{student-teacher mismatch}: the teacher's inability to access long-term history prevents it from guiding the student on global temporal dependencies, effectively capping the student's context length. To resolve this, we propose \textbf{Context Forcing}, a novel framework that trains a long-context student via a long-context teacher. By ensuring the teacher is aware of the full generation history, we eliminate the supervision mismatch, enabling the robust training of models capable of long-term consistency. To make this computationally feasible for extreme durations (e.g., 2 minutes), we introduce a context management system that transforms the linearly growing context into a \textbf{Slow-Fast Memory} architecture, significantly reducing visual redundancy. Extensive results demonstrate that our method enables effective context lengths exceeding 20 seconds -- 2 to 10 times longer than state-of-the-art methods like LongLive and Infinite-RoPE. By leveraging this extended context, Context Forcing preserves superior consistency across long durations, surpassing state-of-the-art baselines on various long video evaluation metrics.

---

### Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory

Authors: Haozhen Zhang, Haodong Yue, Tao Feng, Quanyu Long, Jianzhu Bao, Bowen Jin, Weizhi Zhang, Xiao Li, Jiaxuan You, Chengwei Qin, Wenya Wang
Published: 2026-02-05
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.06025v3

Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems rely on offline, query-agnostic memory construction that can be inefficient and may discard query-critical information. Although runtime memory utilization is a natural alternative, prior work often incurs substantial overhead and offers limited explicit control over the performance-cost trade-off. In this work, we present \textbf{BudgetMem}, a runtime agent memory framework for explicit, query-aware performance-cost control. BudgetMem structures memory processing as a set of memory modules, each offered in three budget tiers (i.e., \textsc{Low}/\textsc{Mid}/\textsc{High}). A lightweight router performs budget-tier routing across modules to balance task performance and memory construction cost, which is implemented as a compact neural policy trained with reinforcement learning. Using BudgetMem as a unified testbed, we study three complementary strategies for realizing budget tiers: implementation (method complexity), reasoning (inference behavior), and capacity (module model size). Across LoCoMo, LongMemEval, and HotpotQA, BudgetMem surpasses strong baselines when performance is prioritized (i.e., high-budget setting), and delivers better accuracy-cost frontiers under tighter budgets. Moreover, our analysis disentangles the strengths and weaknesses of different tiering strategies, clarifying when each axis delivers the most favorable trade-offs under varying budget regimes.

---

### Developing a Discrete-Event Simulator of School Shooter Behavior from VR Data

Authors: Christopher A. McClurg, Alan R. Wagner
Published: 2026-02-05
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2602.06023v2

Virtual reality (VR) has emerged as a powerful tool for evaluating school security measures in high-risk scenarios such as school shootings, offering experimental control and high behavioral fidelity. However, assessing new interventions in VR requires recruiting new participant cohorts for each condition, making large-scale or iterative evaluation difficult. These limitations are especially restrictive when attempting to learn effective intervention strategies, which typically require many training episodes. To address this challenge, we develop a data-driven discrete-event simulator (DES) that models shooter movement and in-region actions as stochastic processes learned from participant behavior in VR studies. We use the simulator to examine the impact of a robot-based shooter intervention strategy. Once shown to reproduce key empirical patterns, the DES enables scalable evaluation and learning of intervention strategies that are infeasible to train directly with human subjects. Overall, this work demonstrates a high-to-mid fidelity simulation workflow that provides a scalable surrogate for developing and evaluating autonomous school-security interventions.

---

### Correctness-Optimized Residual Activation Lens (CORAL): Transferrable and Calibration-Aware Inference-Time Steering

Authors: Miranda Muqing Miao, Young-Min Cho, Lyle Ungar
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06022v1

Large language models (LLMs) exhibit persistent miscalibration, especially after instruction tuning and preference alignment. Modified training objectives can improve calibration, but retraining is expensive. Inference-time steering offers a lightweight alternative, yet most existing methods optimize proxies for correctness rather than correctness itself. We introduce CORAL (Correctness-Optimized Residual Activation Lens), a regularized inference-time steering method that captures distributed correctness signals from model internal activations using weight-decay MLP probes. We evaluate CORAL across three 7B-parameter models and find that it consistently improves accuracy by 10\% and expected calibration error (ECE) by 50\% on average. We additionally demonstrate that these gains transfer without retraining to the complete published test sets of four held-out benchmarks (ARC-Challenge, HellaSwag, Math-MC, OpenBookQA), averaging 14\% accuracy improvements and 49\% ECE improvements. Our results support the hypothesis that distributed information in model internals can be extracted using regularized probes when individual neurons are insufficient. CORAL thus provides a compute-efficient, transferable, and calibration-aware approach to improve MCQA performance during inference.

---

### Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge Manifold

Authors: Ye He, Yitong Qiu, Molei Tao
Published: 2026-02-05
Categories: stat.ML, cs.LG, math.NA, math.PR
arXiv: https://arxiv.org/abs/2602.06021v2

We study a data-dependent notion of diffusion-model generalization: when a model does not memorize the training set, where do its generated samples go relative to the geometry induced by the data? To answer this, we introduce a time-dependent family of log-density ridge manifolds constructed from the smoothed empirical distribution, and use it to characterize reverse-time inference. Our main result shows that generated samples evolve by a reach-align-slide mechanism: they first enter a neighborhood of the ridge, then their distance to the ridge is controlled by the normal component of training error, and finally their motion along the ridge is controlled by the tangential component. We further connect this geometric picture to training dynamics through directional decompositions of the learned error, and make this link explicit for random feature models, where architectural bias and optimization error can be separated quantitatively. Experiments on synthetic multimodal data and MNIST latent diffusion support the predicted geometric behavior in both low and high dimensions.

---

### Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks

Authors: Kevin Lu, Jannik Brinkmann, Stefan Huber, Aaron Mueller, Yonatan Belinkov, David Bau, Chris Wendler
Published: 2026-02-05
Categories: cs.LG, q-bio.BM
arXiv: https://arxiv.org/abs/2602.06020v3

How do protein structure prediction models fold proteins? We investigate this question through causal interventions on the folding trunks of ESMFold, OpenFold, and Boltz-1. Across all three models, we find a shared two-stage computational structure. In the first stage, early blocks initialize pairwise biochemical signals: features like charge propagate from sequence into pairwise representations through architecture-specific pathways. In the second stage, late blocks develop pairwise spatial features: distance and contact information accumulate in the pairwise representation. We verify these mechanisms causally by showing that steering charge and distance features induces predictable structural changes. Furthermore, these representations are functionally interchangeable: pairwise states can be linearly aligned and substituted across models. Together, these results suggest that folding trunks with different architectures, inputs, and training procedures converge on a shared representational organization for mapping sequence chemistry into spatial geometry.

---

### Multi-Token Prediction via Self-Distillation

Authors: John Kirchenbauer, Abhimanyu Hans, Brian Bartoldson, Micah Goldblum, Ashwinee Panda, Tom Goldstein
Published: 2026-02-05
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.06019v2

Existing techniques for accelerating language model inference, such as speculative decoding, require training auxiliary speculator models and building and deploying complex inference pipelines. We consider a new approach for converting a pretrained autoregressive language model from a slow single next token prediction model into a fast standalone multi-token prediction model using a simple online distillation objective. The final model retains the exact same implementation as the pretrained initial checkpoint and is deployable without the addition of any auxiliary verifier or other specialized inference code. Our method produces models that decode more than $3\times$ faster at $<5\%$ drop in accuracy on GSM8K relative to the single token decoding performance of the same checkpoint.

---

### MambaVF: State Space Model for Efficient Video Fusion

Authors: Zixiang Zhao, Yukun Cui, Lilun Deng, Haowen Bai, Haotong Qin, Tao Feng, Konrad Schindler
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06017v1

Video fusion is a fundamental technique in various video processing tasks. However, existing video fusion methods heavily rely on optical flow estimation and feature warping, resulting in severe computational overhead and limited scalability. This paper presents MambaVF, an efficient video fusion framework based on state space models (SSMs) that performs temporal modeling without explicit motion estimation. First, by reformulating video fusion as a sequential state update process, MambaVF captures long-range temporal dependencies with linear complexity while significantly reducing computation and memory costs. Second, MambaVF proposes a lightweight SSM-based fusion module that replaces conventional flow-guided alignment via a spatio-temporal bidirectional scanning mechanism. This module enables efficient information aggregation across frames. Extensive experiments across multiple benchmarks demonstrate that our MambaVF achieves state-of-the-art performance in multi-exposure, multi-focus, infrared-visible, and medical video fusion tasks. We highlight that MambaVF enjoys high efficiency, reducing up to 92.25% of parameters and 88.79% of computational FLOPs and a 2.1x speedup compared to existing methods. Project page: https://mambavf.github.io

---

### A Systematic Evaluation of Large Language Models for PTSD Severity Estimation: The Role of Contextual Knowledge and Modeling Strategies

Authors: Panagiotis Kaliosis, Adithya V Ganesan, Oscar N. E. Kjell, Whitney Ringwald, Scott Feltman, Melissa A. Carr, Dimitris Samaras, Camilo Ruggero, Benjamin J. Luft, Roman Kotov, Andrew H. Schwartz
Published: 2026-02-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.06015v2

Large language models (LLMs) are increasingly being used in a zero-shot (generative) fashion to assess mental health conditions, yet we have limited knowledge on what factors affect their accuracy. In this study, we use a clinical dataset of natural language narratives and self-reported PTSD severity scores from 1,437 individuals to comprehensively evaluate the performance of 11 state-of-the-art LLMs. To understand the factors affecting model's assessment accuracy, we systematically varied (i) contextual knowledge prompted to the models like subscale definitions, distribution summary, and interview questions, and (ii) modeling strategies including zero-shot vs few shot, amount of reasoning effort, model sizes, structured subscales vs direct scalar prediction, output rescaling and nine ensemble methods. Our findings indicate that (a) LLMs are most accurate when provided with detailed construct definitions and context of the narrative, even exceeding human raters agreement with self-reported scores; (b) increased reasoning effort leads to better estimation accuracy; (c) performance of open-weight models (Llama, DeepSeek) plateaus beyond 70B parameters while closed-weight (gpt-o3-mini, gpt-5) alternatives improve with newer generations; and (d) best performance is achieved when ensembling a supervised model with the zero-shot LLMs. Beyond agreement with self-reports, LLMs' estimates discriminated PTSD severity from depression, anxiety, and alcohol use, and prospectively predicted future mental healthcare expenditure. Together, these results suggest that contextual knowledge and modeling strategies meaningfully affect accuracy and clinical utility of LLM-based assessments of PTSD severity.

---

### Optimism Stabilizes Thompson Sampling for Adaptive Inference

Authors: Shunxing Yan, Han Zhong
Published: 2026-02-05
Categories: cs.LG, cs.AI, math.OC, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2602.06014v2

Thompson sampling (TS) is widely used for stochastic multi-armed bandits, yet its inferential properties under adaptive data collection are subtle. Classical asymptotic theory for sample means can fail because arm-specific sample sizes are random and coupled with the rewards through the action-selection rule. We study adaptive inference for Thompson sampling with Gaussian randomized indices in $K$-armed stochastic bandits with independent sub-Gaussian reward noises, and identify \emph{optimism} as a key mechanism for restoring \emph{stability}, meaning that each arm's pull count concentrates around a deterministic scale. This stability yields asymptotically valid Wald inference despite adaptive sampling. First, we prove that variance-inflated TS is stable for any $K \ge 2$, including the challenging regime where multiple arms are optimal, with asymptotically uniform allocation over optimal arms and sharp logarithmic pull-count asymptotics for suboptimal arms. This resolves the $K$-armed extension question raised by \citet{halder2025stable}, using new winner-map and Lyapunov-drift techniques to control allocation among multiple optimal arms. Second, we analyze an alternative optimistic modification that keeps the Gaussian index variance unchanged but adds an explicit mean bonus to the index center, and establish a similar stability conclusion. In summary, suitably implemented optimism stabilizes Thompson sampling and enables asymptotically valid Wald inference in multi-armed bandits, while incurring only a mild additional regret cost.

---

### GenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?

Authors: Ruihang Li, Leigang Qu, Jingxu Zhang, Dongnan Gui, Mengde Xu, Xiaosong Zhang, Han Hu, Wenjie Wang, Jiaqi Wang
Published: 2026-02-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.06013v1

The rapid advancement of visual generation models has outpaced traditional evaluation approaches, necessitating the adoption of Vision-Language Models as surrogate judges. In this work, we systematically investigate the reliability of the prevailing absolute pointwise scoring standard, across a wide spectrum of visual generation tasks. Our analysis reveals that this paradigm is limited due to stochastic inconsistency and poor alignment with human perception. To resolve these limitations, we introduce GenArena, a unified evaluation framework that leverages a pairwise comparison paradigm to ensure stable and human-aligned evaluation. Crucially, our experiments uncover a transformative finding that simply adopting this pairwise protocol enables off-the-shelf open-source models to outperform top-tier proprietary models. Notably, our method boosts evaluation accuracy by over 20% and achieves a Spearman correlation of 0.86 with the authoritative LMArena leaderboard, drastically surpassing the 0.36 correlation of pointwise methods. Based on GenArena, we benchmark state-of-the-art visual generation models across diverse tasks, providing the community with a rigorous and automated evaluation standard for visual generation.

---

### AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions

Authors: Xianyang Liu, Shangding Gu, Dawn Song
Published: 2026-02-05
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.06008v1

Large language model (LLM)-based agents are increasingly expected to negotiate, coordinate, and transact autonomously, yet existing benchmarks lack principled settings for evaluating language-mediated economic interaction among multiple agents. We introduce AgenticPay, a benchmark and simulation framework for multi-agent buyer-seller negotiation driven by natural language. AgenticPay models markets in which buyers and sellers possess private constraints and product-dependent valuations, and must reach agreements through multi-round linguistic negotiation rather than numeric bidding alone. The framework supports a diverse suite of over 110 tasks ranging from bilateral bargaining to many-to-many markets, with structured action extraction and metrics for feasibility, efficiency, and welfare. Benchmarking state-of-the-art proprietary and open-weight LLMs reveals substantial gaps in negotiation performance and highlights challenges in long-horizon strategic reasoning, establishing AgenticPay as a foundation for studying agentic commerce and language-based market interaction. Code and dataset are available at the link: https://github.com/SafeRL-Lab/AgenticPay.

---

### Speech Emotion Recognition Leveraging OpenAI's Whisper Representations and Attentive Pooling Methods

Authors: Ali Shendabadi, Parnia Izadirad, Mostafa Salehi, Mahmoud Bijankhan
Published: 2026-02-05
Categories: cs.AI, cs.CL, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2602.06000v1

Speech Emotion Recognition (SER) research has faced limitations due to the lack of standard and sufficiently large datasets. Recent studies have leveraged pre-trained models to extract features for downstream tasks such as SER. This work explores the capabilities of Whisper, a pre-trained ASR system, in speech emotion recognition by proposing two attention-based pooling methods, Multi-head Attentive Average Pooling and QKV Pooling, designed to efficiently reduce the dimensionality of Whisper representations while preserving emotional features. We experiment on English and Persian, using the IEMOCAP and ShEMO datasets respectively, with Whisper Tiny and Small. Our multi-head QKV architecture achieves state-of-the-art results on the ShEMO dataset, with a 2.47% improvement in unweighted accuracy. We further compare the performance of different Whisper encoder layers and find that intermediate layers often perform better for SER on the Persian dataset, providing a lightweight and efficient alternative to much larger models such as HuBERT X-Large. Our findings highlight the potential of Whisper as a representation extractor for SER and demonstrate the effectiveness of attention-based pooling for dimension reduction.

---

### On the Role of Computation in Reinforcement Learning

Authors: Raj Ghugare, Michał Bortkiewicz, Alicja Ziarko, Benjamin Eysenbach
Published: 2026-02-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.05999v4

How does the amount of compute available to a reinforcement learning (RL) policy affect its learning? Can policies using a fixed amount of parameters, still benefit from additional compute? The standard RL framework does not provide a language to answer these questions formally. Empirically, deep RL policies are often parameterized as neural networks with static architectures, conflating the amount of compute and the number of parameters. In this paper, we formalize compute bounded policies and prove that policies which use more compute can solve problems and generalize to longer-horizon tasks that are outside the scope of policies with less compute. Building on prior work in algorithmic learning and model-free planning, we propose a minimal architecture that can use a variable amount of compute. Our experiments complement our theory. On a set 31 different tasks spanning online and offline RL, we show that $(1)$ this architecture achieves stronger performance simply by using more compute, and $(2)$ stronger generalization on longer-horizon test tasks compared to standard feedforward networks or deep residual network using up to 5 times more parameters.

---

### VisRefiner: Learning from Visual Differences for Screenshot-to-Code Generation

Authors: Jie Deng, Kaichun Yao, Libo Zhang
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.05998v1

Screenshot-to-code generation aims to translate user interface screenshots into executable frontend code that faithfully reproduces the target layout and style. Existing multimodal large language models perform this mapping directly from screenshots but are trained without observing the visual outcomes of their generated code. In contrast, human developers iteratively render their implementation, compare it with the design, and learn how visual differences relate to code changes. Inspired by this process, we propose VisRefiner, a training framework that enables models to learn from visual differences between rendered predictions and reference designs. We construct difference-aligned supervision that associates visual discrepancies with corresponding code edits, allowing the model to understand how appearance variations arise from implementation changes. Building on this, we introduce a reinforcement learning stage for self-refinement, where the model improves its generated code by observing both the rendered output and the target design, identifying their visual differences, and updating the code accordingly. Experiments show that VisRefiner substantially improves single-step generation quality and layout fidelity, while also endowing models with strong self-refinement ability. These results demonstrate the effectiveness of learning from visual differences for advancing screenshot-to-code generation.

---

### Causal Inference on Stopped Random Walks in Online Advertising

Authors: Jia Yuan Yu
Published: 2026-02-05
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2602.05997v1

We consider a causal inference problem frequently encountered in online advertising systems, where a publisher (e.g., Instagram, TikTok) interacts repeatedly with human users and advertisers by sporadically displaying to each user an advertisement selected through an auction. Each treatment corresponds to a parameter value of the advertising mechanism (e.g., auction reserve-price), and we want to estimate through experiments the corresponding long-term treatment effect (e.g., annual advertising revenue). In our setting, the treatment affects not only the instantaneous revenue from showing an ad, but also changes each user's interaction-trajectory, and each advertiser's bidding policy -- as the latter is constrained by a finite budget. In particular, each a treatment may even affect the size of the population, since users interact longer with a tolerable advertising mechanism. We drop the classical i.i.d. assumption and model the experiment measurements (e.g., advertising revenue) as a stopped random walk, and use a budget-splitting experimental design, the Anscombe Theorem, a Wald-like equation, and a Central Limit Theorem to construct confidence intervals for the long-term treatment effect.

---

### Orthogonal Self-Attention

Authors: Leo Zhang, James Martens
Published: 2026-02-05
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.05996v1

Softmax Self-Attention (SSA) is a key component of Transformer architectures. However, when utilised within skipless architectures, which aim to improve representation learning, recent work has highlighted the inherent instability of SSA due to inducing rank collapse and poorly-conditioned Jacobians. In this work, we design a novel attention mechanism: Orthogonal Self-Attention (OSA), which aims to bypass these issues with SSA, in order to allow for (non-causal) Transformers without skip connections and normalisation layers to be more easily trained. In particular, OSA parametrises the attention matrix to be orthogonal via mapping a skew-symmetric matrix, formed from query-key values, through the matrix exponential. We show that this can be practically implemented, by exploiting the low-rank structure of our query-key values, resulting in the computational complexity and memory cost of OSA scaling linearly with sequence length. Furthermore, we derive an initialisation scheme for which we prove ensures that the Jacobian of OSA is well-conditioned.

---

### Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps

Authors: Peter Holderrieth, Douglas Chen, Luca Eyring, Ishin Shah, Giri Anantharaman, Yutong He, Zeynep Akata, Tommi Jaakkola, Nicholas Matthew Boffi, Max Simchowitz
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.05993v3

Flow and diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and brittle, a challenge commonly called reward alignment. We argue that efficient reward alignment should be a property of the generative model itself, not an afterthought, and redesign the model for adaptability. We propose "Diamond Maps", stochastic flow map models that enable efficient and accurate alignment to arbitrary rewards at inference time. Diamond Maps amortize many simulation steps into a single-step sampler, like flow maps, while preserving the stochasticity required for optimal reward alignment. This design makes search, Sequential Monte Carlo, and guidance scalable by enabling efficient and consistent estimation of the value function. Our experiments show that Diamond Maps can be learned efficiently via distillation from GLASS Flows, achieve stronger reward alignment performance, and scale better than existing methods. Our results point toward a practical route to generative models that can be rapidly adapted to arbitrary preferences and constraints at inference time.

---

### DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs

Authors: Lizhuo Luo, Shenggui Li, Yonggang Wen, Tianwei Zhang
Published: 2026-02-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.05992v3

Diffusion large language models (dLLMs) have emerged as a promising alternative for text generation, distinguished by their native support for parallel decoding. In practice, block inference is crucial for avoiding order misalignment in global bidirectional decoding and improving output quality. However, the widely-used fixed, predefined block (naive) schedule is agnostic to semantic difficulty, making it a suboptimal strategy for both quality and efficiency: it can force premature commitments to uncertain positions while delaying easy positions near block boundaries. In this work, we analyze the limitations of naive block scheduling and disclose the importance of dynamically adapting the schedule to semantic difficulty for reliable and efficient inference. Motivated by this, we propose Dynamic Sliding Block (DSB), a training-free block scheduling method that uses a sliding block with a dynamic size to overcome the rigidity of the naive block. To further improve efficiency, we introduce DSB Cache, a training-free KV-cache mechanism tailored to DSB. Extensive experiments across multiple models and benchmarks demonstrate that DSB, together with DSB Cache, consistently improves both generation quality and inference efficiency for dLLMs. Code is released at https://github.com/lizhuo-luo/DSB.

---

### Layer-wise LoRA fine-tuning: a similarity metric approach

Authors: Keith Ando Ogawa, Bruno Lopes Yamamoto, Lucas Lauton de Alcantara, Lucas Pellicer, Rosimeire Pereira Costa, Edson Bollis, Anna Helena Reali Costa, Artur Jordao
Published: 2026-02-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.05988v2

Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge through fine-tuning. Parameter-efficient fine-tuning techniques, such as Low-Rank Adaptation (LoRA), aim to reduce the computational cost of this process by freezing the pre-trained model and updating a smaller number of parameters. In comparison to full fine-tuning, these methods achieve over 99\% reduction in trainable parameter count, depending on the configuration. Unfortunately, such a reduction may prove insufficient as LLMs continue to grow in scale. In this work, we address the previous problem by systematically selecting only a few layers to fine-tune using LoRA or its variants. We argue that not all layers contribute equally to the model adaptation. Leveraging this, we identify the most relevant layers to fine-tune by measuring their contribution to changes in internal representations. Our method is orthogonal to and readily compatible with existing low-rank adaptation techniques. We reduce the trainable parameters in LoRA-based techniques by up to 50\%, while maintaining the predictive performance across different models and tasks. Specifically, on encoder-only architectures, this reduction in trainable parameters leads to a negligible predictive performance drop on the GLUE benchmark. On decoder-only architectures, we achieve a small drop or even improvements in the predictive performance on mathematical problem-solving capabilities and coding tasks. Finally, this effectiveness extends to multimodal models, for which we also observe competitive results relative to fine-tuning with LoRA modules in all layers. Code is available at: https://github.com/c2d-usp/Layer-wise-LoRA-with-CKA

---

### RISE-Video: Can Video Generators Decode Implicit World Rules?

Authors: Mingxin Liu, Shuran Ma, Shibei Meng, Xiangyu Zhao, Zicheng Zhang, Shaofeng Zhang, Zhihang Zhong, Peixian Chen, Haoyu Cao, Xing Sun, Haodong Duan, Xue Yang
Published: 2026-02-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.05986v1

While generative video models have achieved remarkable visual fidelity, their capacity to internalize and reason over implicit world rules remains a critical yet under-explored frontier. To bridge this gap, we present RISE-Video, a pioneering reasoning-oriented benchmark for Text-Image-to-Video (TI2V) synthesis that shifts the evaluative focus from surface-level aesthetics to deep cognitive reasoning. RISE-Video comprises 467 meticulously human-annotated samples spanning eight rigorous categories, providing a structured testbed for probing model intelligence across diverse dimensions, ranging from commonsense and spatial dynamics to specialized subject domains. Our framework introduces a multi-dimensional evaluation protocol consisting of four metrics: \textit{Reasoning Alignment}, \textit{Temporal Consistency}, \textit{Physical Rationality}, and \textit{Visual Quality}. To further support scalable evaluation, we propose an automated pipeline leveraging Large Multimodal Models (LMMs) to emulate human-centric assessment. Extensive experiments on 11 state-of-the-art TI2V models reveal pervasive deficiencies in simulating complex scenarios under implicit constraints, offering critical insights for the advancement of future world-simulating generative models.

---

### Geographically-aware Transformer-based Traffic Forecasting for Urban Motorway Digital Twins

Authors: Krešimir Kušić, Vinny Cahill, Ivana Dusparic
Published: 2026-02-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.05983v1

The operational effectiveness of digital-twin technology in motorway traffic management depends on the availability of a continuous flow of high-resolution real-time traffic data. To function as a proactive decision-making support layer within traffic management, a digital twin must also incorporate predicted traffic conditions in addition to real-time observations. Due to the spatio-temporal complexity and the time-variant, non-linear nature of traffic dynamics, predicting motorway traffic remains a difficult problem. Sequence-based deep-learning models offer clear advantages over classical machine learning and statistical models in capturing long-range, temporal dependencies in time-series traffic data, yet limitations in forecasting accuracy and model complexity point to the need for further improvements. To improve motorway traffic forecasting, this paper introduces a Geographically-aware Transformer-based Traffic Forecasting GATTF model, which exploits the geographical relationships between distributed sensors using their mutual information (MI). The model has been evaluated using real-time data from the Geneva motorway network in Switzerland and results confirm that incorporating geographical awareness through MI enhances the accuracy of GATTF forecasting compared to a standard Transformer, without increasing model complexity.

---

### Clifford Kolmogorov-Arnold Networks

Authors: Matthias Wolff, Francesco Alesiani, Christof Duhme, Xiaoyi Jiang
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.05977v2

We introduce Clifford Kolmogorov-Arnold Network (ClKAN), a flexible and efficient architecture for function approximation in arbitrary Clifford Algebra spaces. We propose the use of Randomized Quasi-Monte Carlo grid generation as a solution to the exponential scaling associated with higher-dimensional algebras. Our ClKAN also introduces new batch normalization strategies to deal with variable domain input. ClKAN finds application in scientific discovery and engineering, and is validated in synthetic and physics-inspired tasks.

---

### SAGE: Benchmarking and Improving Retrieval for Deep Research Agents

Authors: Tiansheng Hu, Yilun Zhao, Canyu Zhang, Arman Cohan, Chen Zhao
Published: 2026-02-05
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2602.05975v2

Deep research agents have emerged as powerful systems for addressing complex queries. Meanwhile, LLM-based retrievers have demonstrated strong capability in following instructions or reasoning. This raises a critical question: can LLM-based retrievers effectively contribute to deep research agent workflows? To investigate this, we introduce SAGE, a benchmark for scientific literature retrieval comprising 1,200 queries across four scientific domains, with a 200,000 paper retrieval corpus. We evaluate six deep research agents and find that all systems struggle with reasoning-intensive retrieval. Using DR Tulu as backbone, we further compare BM25 and LLM-based retrievers (i.e., ReasonIR and gte-Qwen2-7B-instruct) as alternative search tools. Surprisingly, BM25 significantly outperforms LLM-based retrievers by approximately 30%, as existing agents generate keyword-oriented sub-queries. To improve performance, we propose a corpus-level test-time scaling framework that uses LLMs to augment documents with metadata and keywords, making retrieval easier for off-the-shelf retrievers. This yields 8% and 2% gains on short-form and open-ended questions, respectively.

---

### Characterizing Human Semantic Navigation in Concept Production as Trajectories in Embedding Space

Authors: Felipe D. Toro-Hernández, Jesuino Vieira Filho, Rodrigo M. Cabral-Carvalho
Published: 2026-02-05
Categories: cs.CL, cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2602.05971v2

Semantic representations can be framed as a structured, dynamic knowledge space through which humans navigate to retrieve and manipulate meaning. To investigate how humans traverse this geometry, we introduce a framework that represents concept production as navigation through embedding space. Using different transformer text embedding models, we construct participant-specific semantic trajectories based on cumulative embeddings and extract geometric and dynamical metrics, including distance to next, distance to centroid, entropy, velocity, and acceleration. These measures capture both scalar and directional aspects of semantic navigation, providing a computationally grounded view of semantic representation search as movement in a geometric space. We evaluate the framework on four datasets across different languages, spanning different property generation tasks: Neurodegenerative, Swear verbal fluency, Property listing task in Italian, and in German. Across these contexts, our approach distinguishes between clinical groups and concept types, offering a mathematical framework that requires minimal human intervention compared to typical labor-intensive linguistic pre-processing methods. Comparison with a non-cumulative approach reveals that cumulative embeddings work best for longer trajectories, whereas shorter ones may provide too little context, favoring the non-cumulative alternative. Critically, different embedding models yielded similar results, highlighting similarities between different learned representations despite different training pipelines. By framing semantic navigation as a structured trajectory through embedding space, bridging cognitive modeling with learned representation, thereby establishing a pipeline for quantifying semantic representation dynamics with applications in clinical research, cross-linguistic analysis, and the assessment of artificial cognition.

---

### Inverse Depth Scaling From Most Layers Being Similar

Authors: Yizhou Liu, Sara Kangaslahti, Ziming Liu, Jeff Gore
Published: 2026-02-05
Categories: cs.LG, cs.AI, math.DS, stat.ML
arXiv: https://arxiv.org/abs/2602.05970v2

Neural scaling laws relate loss to model size in large language models (LLMs), yet depth and width may contribute to performance differently, requiring more detailed studies. Here, we quantify how depth affects loss via analysis of LLMs and toy residual networks. We find loss scales inversely proportional to depth in LLMs, probably due to functionally similar layers reducing error through ensemble averaging rather than compositional learning or discretizing smooth dynamics. This regime is inefficient yet robust and may arise from the architectural bias of residual networks and target functions incompatible with smooth dynamics. The findings suggest that improving LLM efficiency may require architectural innovations to encourage compositional use of depth.

---

### A Hybrid Data-Driven Algorithm for Real-Time Friction Force Estimation in Hydraulic Cylinders

Authors: Mohamad Amin Jamshidi, Mehrbod Zarifi, Zolfa Anvari, Hamed Ghafarirad, Mohammad Zareinejad
Published: 2026-02-05
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2602.05967v1

Hydraulic systems are widely utilized in industrial applications due to their high force generation, precise control, and ability to function in harsh environments. Hydraulic cylinders, as actuators in these systems, apply force and position through the displacement of hydraulic fluid, but their operation is significantly influenced by friction force. Achieving precision in hydraulic cylinders requires an accurate friction model under various operating conditions. Existing analytical models, often derived from experimental tests, necessitate the identification or estimation of influencing factors but are limited in adaptability and computational efficiency. This research introduces a data-driven, hybrid algorithm based on Long Short-Term Memory (LSTM) networks and Random Forests for nonlinear friction force estimation. The algorithm effectively combines feature detection and estimation processes using training data acquired from an experimental hydraulic test setup. It achieves a consistent and stable model error of less than 10% across diverse operating conditions and external load variations, ensuring robust performance in complex situations. The computational cost of the algorithm is 1.51 milliseconds per estimation, making it suitable for real-time applications. The proposed method addresses the limitations of analytical models by delivering high precision and computational efficiency. The algorithm's performance is validated through detailed analysis and experimental results, including direct comparisons with the LuGre model. The comparison highlights that while the LuGre model offers a theoretical foundation for friction modeling, its performance is limited by its inability to dynamically adjust to varying operational conditions of the hydraulic cylinder, further emphasizing the advantages of the proposed hybrid approach in real-time applications.

---

### LSA: Localized Semantic Alignment for Enhancing Temporal Consistency in Traffic Video Generation

Authors: Mirlan Karimov, Teodora Spasojevic, Markus Braun, Julian Wiederer, Vasileios Belagiannis, Marc Pollefeys
Published: 2026-02-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.05966v1

Controllable video generation has emerged as a versatile tool for autonomous driving, enabling realistic synthesis of traffic scenarios. However, existing methods depend on control signals at inference time to guide the generative model towards temporally consistent generation of dynamic objects, limiting their utility as scalable and generalizable data engines. In this work, we propose Localized Semantic Alignment (LSA), a simple yet effective framework for fine-tuning pre-trained video generation models. LSA enhances temporal consistency by aligning semantic features between ground-truth and generated video clips. Specifically, we compare the output of an off-the-shelf feature extraction model between the ground-truth and generated video clips localized around dynamic objects inducing a semantic feature consistency loss. We fine-tune the base model by combining this loss with the standard diffusion loss. The model fine-tuned for a single epoch with our novel loss outperforms the baselines in common video generation evaluation metrics. To further test the temporal consistency in generated videos we adapt two additional metrics from object detection task, namely mAP and mIoU. Extensive experiments on nuScenes and KITTI datasets show the effectiveness of our approach in enhancing temporal consistency in video generation without the need for external control signals during inference and any computational overheads.

---

### Learning to Share: Selective Memory for Efficient Parallel Agentic Systems

Authors: Joseph Fioresi, Parth Parag Kulkarni, Ashmal Vayani, Song Wang, Mubarak Shah
Published: 2026-02-05
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2602.05965v2

Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results. To improve robustness and solution quality, recent approaches deploy multiple agent teams running in parallel to explore diverse reasoning trajectories. However, parallel execution comes at a significant computational cost: when different teams independently reason about similar sub-problems or execute analogous steps, they repeatedly perform substantial overlapping computation. To address these limitations, in this paper, we propose Learning to Share (LTS), a learned shared-memory mechanism for parallel agentic frameworks that enables selective cross-team information reuse while controlling context growth. LTS introduces a global memory bank accessible to all teams and a lightweight controller that decides whether intermediate agent steps should be added to memory or not. The controller is trained using stepwise reinforcement learning with usage-aware credit assignment, allowing it to identify information that is globally useful across parallel executions. Experiments on the AssistantBench and GAIA benchmarks show that LTS significantly reduces overall runtime while matching or improving task performance compared to memory-free parallel baselines, demonstrating that learned memory admission is an effective strategy for improving the efficiency of parallel agentic systems. Project page: https://joefioresi718.github.io/LTS_webpage/

---

### Discrete diffusion samplers and bridges: Off-policy algorithms and applications in latent spaces

Authors: Arran Carter, Sanghyeok Choi, Kirill Tamogashev, Víctor Elvira, Esmeralda S. Whitammer
Published: 2026-02-05
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.05961v3

Sampling from a distribution $p(x) \propto e^{-\mathcal{E}(x)}$ known up to a normalising constant is an important and challenging problem in statistics. Recent years have seen the rise of a new family of amortised sampling algorithms, commonly referred to as diffusion samplers, that enable fast and efficient sampling from an unnormalised density. Such algorithms have been widely studied for continuous-space sampling tasks; however, their application to problems in discrete space remains largely unexplored. Although some progress has been made in this area, discrete diffusion samplers do not take full advantage of ideas commonly used for continuous-space sampling. In this paper, we propose to bridge this gap by introducing off-policy training techniques for discrete diffusion samplers. We show that these techniques improve the performance of discrete samplers on both established and new synthetic benchmarks. Next, we generalise discrete diffusion samplers to the task of bridging between two arbitrary distributions, introducing data-to-energy Schrödinger bridge training for the discrete domain for the first time. Lastly, we showcase the application of the proposed diffusion samplers to data-free posterior sampling in the discrete latent spaces of image generative models.

---