# Research Papers — 2025-10 · bundle page 202 of 217

> Full-text markdown of papers #10051–10100 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/202
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/201.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/203.md)

### Extreme value forecasting using relevance-based data augmentation with deep learning models

Authors: Junru Hua, Rahul Ahluwalia, Rohitash Chandra
Published: 2025-10-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.02407v1

Data augmentation with generative adversarial networks (GANs) has been popular for class imbalance problems, mainly for pattern classification and computer vision-related applications. Extreme value forecasting is a challenging field that has various applications from finance to climate change problems. In this study, we present a data augmentation framework for extreme value forecasting. In this framework, our focus is on forecasting extreme values using deep learning models in combination with data augmentation models such as GANs and synthetic minority oversampling technique (SMOTE). We use deep learning models such as convolutional long short-term memory (Conv-LSTM) and bidirectional long short-term memory (BD-LSTM) networks for multistep ahead prediction featuring extremes. We investigate which data augmentation models are the most suitable, taking into account the prediction accuracy overall and at extreme regions, along with computational efficiency. We also present novel strategies for incorporating data augmentation, considering extreme values based on a relevance function. Our results indicate that the SMOTE-based strategy consistently demonstrated superior adaptability, leading to improved performance across both short- and long-horizon forecasts. Conv-LSTM and BD-LSTM exhibit complementary strengths: the former excels in periodic, stable datasets, while the latter performs better in chaotic or non-stationary sequences.

---

### Optimal Post-processing of Synthetic Data for Pearson Correlation Matching

Authors: Oussama Ounissi, Nicklas Jävergård, Assaad Zeghina, Adrian Muntean
Published: 2025-10-02
Categories: stat.ME, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.02405v3

Preserving correlation in synthetic data is of interest in several applications. Existing approaches mainly address correlation preservation during the generation procedure. Here, we instead consider it as a postprocessing problem. Given original and synthetic tabular data, we seek the smallest change to the synthetic dataset that restores the Pearson correlation matrix of the original data. Under suitable assumptions, we derive a unique explicit solution to the minimization problem. We also provide a bound on the size of the correction in terms of the initial correlation error. On the numerical side, across several datasets and generation methods, the proposed approach largely preserves marginal distributions, t-SNE geometry, and classification performance. The method is generator-independent and can be applied after synthesis without modifying the generation procedure.

---

### FOCUS: Optimal Control for Multi-Entity World Modeling in Text-to-Image Generation

Authors: Eric Tillmann Bill, Enis Simsar, Thomas Hofmann
Published: 2025-10-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.02315v2

Text-to-image (T2I) models excel on single-entity prompts but struggle with multi-entity scenes, often exhibiting attribute leakage, identity entanglement, and subject omissions. We present a principled theoretical framework that steers sampling toward multi-subject fidelity by casting flow matching (FM) as stochastic optimal control (SOC), yielding a single hyperparameter controlled trade-off between fidelity and object-centric state separation / binding consistency. Within this framework, we derive two architecture-agnostic algorithms: (i) a training-free test-time controller that perturbs the base velocity with a single-pass update, and (ii) Adjoint Matching, a lightweight fine-tuning rule that regresses a control network to a backward adjoint signal. The same formulation unifies prior attention heuristics, extends to diffusion models via a flow--diffusion correspondence, and provides the first fine-tuning route explicitly designed for multi-subject fidelity. In addition, we also introduce FOCUS (Flow Optimal Control for Unentangled Subjects), a probabilistic attention-binding objective compatible with both algorithms. Empirically, on Stable Diffusion 3.5 and FLUX.1, both algorithms consistently improve multi-subject alignment while maintaining base-model style; test-time control runs efficiently on commodity GPUs, and fine-tuned models generalize to unseen prompts.

---

### StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions

Authors: Bo-Hsu Ke, You-Zhe Xie, Yu-Lun Liu, Wei-Chen Chiu
Published: 2025-10-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.02314v1

3D scene representation methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have significantly advanced novel view synthesis. As these methods become prevalent, addressing their vulnerabilities becomes critical. We analyze 3DGS robustness against image-level poisoning attacks and propose a novel density-guided poisoning method. Our method strategically injects Gaussian points into low-density regions identified via Kernel Density Estimation (KDE), embedding viewpoint-dependent illusory objects clearly visible from poisoned views while minimally affecting innocent views. Additionally, we introduce an adaptive noise strategy to disrupt multi-view consistency, further enhancing attack effectiveness. We propose a KDE-based evaluation protocol to assess attack difficulty systematically, enabling objective benchmarking for future research. Extensive experiments demonstrate our method's superior performance compared to state-of-the-art techniques. Project page: https://hentci.github.io/stealthattack/

---

### Clink! Chop! Thud! -- Learning Object Sounds from Real-World Interactions

Authors: Mengyu Yang, Yiming Chen, Haozheng Pei, Siddhant Agarwal, Arun Balajee Vasudevan, James Hays
Published: 2025-10-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.02313v1

Can a model distinguish between the sound of a spoon hitting a hardwood floor versus a carpeted one? Everyday object interactions produce sounds unique to the objects involved. We introduce the sounding object detection task to evaluate a model's ability to link these sounds to the objects directly involved. Inspired by human perception, our multimodal object-aware framework learns from in-the-wild egocentric videos. To encourage an object-centric approach, we first develop an automatic pipeline to compute segmentation masks of the objects involved to guide the model's focus during training towards the most informative regions of the interaction. A slot attention visual encoder is used to further enforce an object prior. We demonstrate state of the art performance on our new task along with existing multimodal action understanding tasks.

---

### KaVa: Latent Reasoning via Compressed KV-Cache Distillation

Authors: Anna Kuzina, Maciej Pioro, Paul N. Whatmough, Babak Ehteshami Bejnordi
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.02312v2

Large Language Models (LLMs) excel at multi-step reasoning problems with explicit chain-of-thought (CoT), but verbose traces incur significant computational costs and memory overhead, and often carry redundant, stylistic artifacts. Latent reasoning has emerged as an efficient alternative that internalizes the thought process, but it suffers from a critical lack of supervision, limiting its effectiveness on complex, natural-language reasoning traces. In this work we propose KaVa, the first framework that bridges this gap by distilling knowledge directly from a compressed KV-cache of the teacher into a latent-reasoning student via self-distillation, leveraging the representational flexibility of continuous latent tokens to align stepwise KV trajectories. We show that the abstract, unstructured knowledge within compressed KV-cache, which lacks direct token correspondence, can serve as a rich supervisory signal for a latent reasoning student. Empirically, the approach consistently outperforms strong latent baselines, exhibits markedly smaller degradation from equation-only to natural-language traces, and scales to larger backbones while preserving efficiency. These results establish compressed KV-cache distillation as a scalable supervision signal for latent reasoning, combining the accuracy of CoT-trained teachers with the efficiency and deployability of latent inference.

---

### Inferring Dynamic Physical Properties from Video Foundation Models

Authors: Guanqi Zhan, Xianzheng Ma, Weidi Xie, Andrew Zisserman
Published: 2025-10-02
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.02311v2

We study the task of predicting dynamic physical properties from videos. More specifically, we consider physical properties that require temporal information to be inferred: elasticity of a bouncing object, viscosity of a flowing liquid, and dynamic friction of an object sliding on a surface. To this end, we make the following contributions: (i) We collect a new video dataset for each physical property, consisting of synthetic training and testing splits, as well as a real split for real world evaluation. (ii) We explore three ways to infer the physical property from videos: (a) an oracle method where we supply the visual cues that intrinsically reflect the property using classical computer vision techniques; (b) a simple read out mechanism using a visual prompt and trainable prompt vector for cross-attention on pre-trained video generative and self-supervised models; and (c) prompt strategies for Multi-modal Large Language Models (MLLMs). (iii) We show that a video foundation model trained in a generative (DynamiCrafter) or trained in a self-supervised manner (V-JEPA-2) achieve a generally similar performance, though behind that of the oracle, and that MLLMs are currently inferior to the other models, though their performance can be improved through suitable prompting. The dataset, model, and code are available at https://www.robots.ox.ac.uk/~vgg/research/idpp/.

---

### Robust Tangent Space Estimation via Laplacian Eigenvector Gradient Orthogonalization

Authors: Dhruv Kohli, Sawyer J. Robertson, Gal Mishne, Alexander Cloninger
Published: 2025-10-02
Categories: cs.LG, math.DG
arXiv: https://arxiv.org/abs/2510.02308v2

Estimating the tangent spaces of a data manifold is a fundamental problem in geometric data analysis. The standard approach, Local Principal Component Analysis (LPCA), struggles in high-noise setting due to a critical trade-off in choosing the neighborhood size. Selecting an optimal size requires prior knowledge of the geometric and noise characteristics of the data that are often unavailable. In this paper, we propose a spectral method, Laplacian Eigenvector Gradient Orthogonalization (LEGO), that utilizes the global structure of the data to guide local tangent space estimation. Instead of relying solely on local neighborhoods, LEGO estimates the tangent space at each data point by orthogonalizing the gradients of low-frequency eigenvectors of the graph Laplacian. We provide two theoretical justifications of our method. First, a differential geometric analysis on the tubular neighborhood of a manifold shows that gradients of the low-frequency Neumann eigenfunctions of the tube align closely with the manifold's tangent bundle, while an eigenfunction with high gradient in directions orthogonal to the manifold lie deeper in the spectrum. Second, a random matrix theoretic analysis also demonstrates that low-frequency eigenvectors are robust to sub-Gaussian noise. These results allow us to derive the asymptotic scaling and stability of the estimated eigenvector gradients. Numerical experiments demonstrate that LEGO yields tangent space estimates that are significantly more robust to noise than those from LPCA, resulting in marked improvements in downstream tasks such as manifold learning, boundary detection, and local intrinsic dimension estimation.

---

### NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generation

Authors: Ruozhen He, Moayed Haji-Ali, Ziyan Yang, Vicente Ordonez
Published: 2025-10-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.02307v2

Text-to-image diffusion models often degrade when sampled at resolutions outside the final training resolution set. Prior work has largely emphasized higher resolution generation, enabling pretrained diffusion models to extrapolate beyond the resolutions seen during training. In this work, we instead target lower-resolution generation, performing inference at reduced resolution to significantly cut computational cost. We show that network conditioning of the noise level induces a train-test mismatch that directly degrades low-resolution generation: the same scheduled noise level can correspond to a different perceptual corruption level at lower resolutions, mis-calibrating the denoiser timestep and noise embedding. To this end, we propose NoiseShift, a training-free recalibration method that keeps the original noise sampling schedule unchanged and instead re-indexes the noise conditioning of the denoiser to restore local forward-reverse consistency. Using a lightweight coarse-to-fine calibration on a small set of image-text pairs, NoiseShift learns a resolution-specific mapping from scheduler noise to conditioning noise, reducing train-test mismatch and improving lower-resolution generation quality. When NoiseShift is applied to Stable Diffusion 3 (SD3), Stable Diffusion 3.5 (SD3.5), and Flux-Dev, generation quality at low resolutions improves consistently. Particularly, SD3 generation at 128x128 resolution gets an improved FID score from 203 to 171, and SD3.5 gets an improved FID score from 310 to 277 on LAION-COCO. Even Flux-Dev which already implements a complementary time-shifting strategy gets a modest boost from NoiseShift with an improved FID score from 120 to 113 at 64x64 resolution. More importantly, NoiseShift achieves such improvements with minimal implementation changes and no additional inference overhead.

---

### Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation

Authors: Raphael Tang, Crystina Zhang, Wenyan Li, Carmen Lai, Pontus Stenetorp, Yao Lu
Published: 2025-10-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.02306v1

In arena-style evaluation of large language models (LLMs), two LLMs respond to a user query, and the user chooses the winning response or deems the "battle" a draw, resulting in an adjustment to the ratings of both models. The prevailing approach for modeling these rating dynamics is to view battles as two-player game matches, as in chess, and apply the Elo rating system and its derivatives. In this paper, we critically examine this paradigm. Specifically, we question whether a draw genuinely means that the two models are equal and hence whether their ratings should be equalized. Instead, we conjecture that draws are more indicative of query difficulty: if the query is too easy, then both models are more likely to succeed equally. On three real-world arena datasets, we show that ignoring rating updates for draws yields a 1-3% relative increase in battle outcome prediction accuracy (which includes draws) for all four rating systems studied. Further analyses suggest that draws occur more for queries rated as very easy and those as highly objective, with risk ratios of 1.37 and 1.35, respectively. We recommend future rating systems to reconsider existing draw semantics and to account for query properties in rating updates.

---

### Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive

Authors: Tyler Farghly, Peter Potaptchik, Samuel Howard, George Deligiannidis, Jakiw Pidstrigach
Published: 2025-10-02
Categories: cs.LG, cs.AI, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.02305v1

Diffusion models have achieved state-of-the-art performance, demonstrating remarkable generalisation capabilities across diverse domains. However, the mechanisms underpinning these strong capabilities remain only partially understood. A leading conjecture, based on the manifold hypothesis, attributes this success to their ability to adapt to low-dimensional geometric structure within the data. This work provides evidence for this conjecture, focusing on how such phenomena could result from the formulation of the learning problem through score matching. We inspect the role of implicit regularisation by investigating the effect of smoothing minimisers of the empirical score matching objective. Our theoretical and empirical results confirm that smoothing the score function -- or equivalently, smoothing in the log-density domain -- produces smoothing tangential to the data manifold. In addition, we show that the manifold along which the diffusion model generalises can be controlled by choosing an appropriate smoothing.

---

### Knowledge Distillation Detection for Open-weights Models

Authors: Qin Shi, Amber Yijia Zheng, Qifan Song, Raymond A. Yeh
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.02302v1

We propose the task of knowledge distillation detection, which aims to determine whether a student model has been distilled from a given teacher, under a practical setting where only the student's weights and the teacher's API are available. This problem is motivated by growing concerns about model provenance and unauthorized replication through distillation. To address this task, we introduce a model-agnostic framework that combines data-free input synthesis and statistical score computation for detecting distillation. Our approach is applicable to both classification and generative models. Experiments on diverse architectures for image classification and text-to-image generation show that our method improves detection accuracy over the strongest baselines by 59.6% on CIFAR-10, 71.2% on ImageNet, and 20.0% for text-to-image generation. The code is available at https://github.com/shqii1j/distillation_detection.

---

### Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models

Authors: Runqian Wang, Yilun Du
Published: 2025-10-02
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.02300v3

We introduce Equilibrium Matching (EqM), a generative modeling framework built from an equilibrium dynamics perspective. EqM discards the non-equilibrium, time-conditional dynamics in traditional diffusion and flow-based generative models and instead learns the equilibrium gradient of an implicit energy landscape. Through this approach, we can adopt an optimization-based sampling process at inference time, where samples are obtained by gradient descent on the learned landscape with adjustable step sizes, adaptive optimizers, and adaptive compute. EqM surpasses the generation performance of diffusion/flow models empirically, achieving an FID of 1.90 on ImageNet 256$\times$256. EqM is also theoretically justified to learn and sample from the data manifold. Beyond generation, EqM is a flexible framework that naturally handles tasks including partially noised image denoising, OOD detection, and image composition. By replacing time-conditional velocities with a unified equilibrium landscape, EqM offers a tighter bridge between flow and energy-based models and a simple route to optimization-driven inference.

---

### Interactive Training: Feedback-Driven Neural Network Optimization

Authors: Wentao Zhang, Yang Young Lu, Yuntian Deng
Published: 2025-10-02
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.02297v1

Traditional neural network training typically follows fixed, predefined optimization recipes, lacking the flexibility to dynamically respond to instabilities or emerging training issues. In this paper, we introduce Interactive Training, an open-source framework that enables real-time, feedback-driven intervention during neural network training by human experts or automated AI agents. At its core, Interactive Training uses a control server to mediate communication between users or agents and the ongoing training process, allowing users to dynamically adjust optimizer hyperparameters, training data, and model checkpoints. Through three case studies, we demonstrate that Interactive Training achieves superior training stability, reduced sensitivity to initial hyperparameters, and improved adaptability to evolving user needs, paving the way toward a future training paradigm where AI agents autonomously monitor training logs, proactively resolve instabilities, and optimize training dynamics.

---

### Continual Personalization for Diffusion Models

Authors: Yu-Chien Liao, Jr-Jen Chen, Chi-Pin Huang, Ci-Siang Lin, Meng-Lin Wu, Yu-Chiang Frank Wang
Published: 2025-10-02
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.02296v1

Updating diffusion models in an incremental setting would be practical in real-world applications yet computationally challenging. We present a novel learning strategy of Concept Neuron Selection (CNS), a simple yet effective approach to perform personalization in a continual learning scheme. CNS uniquely identifies neurons in diffusion models that are closely related to the target concepts. In order to mitigate catastrophic forgetting problems while preserving zero-shot text-to-image generation ability, CNS finetunes concept neurons in an incremental manner and jointly preserves knowledge learned of previous concepts. Evaluation of real-world datasets demonstrates that CNS achieves state-of-the-art performance with minimal parameter adjustments, outperforming previous methods in both single and multi-concept personalization works. CNS also achieves fusion-free operation, reducing memory storage and processing time for continual personalization.

---

### VideoNSA: Native Sparse Attention Scales Video Understanding

Authors: Enxin Song, Wenhao Chai, Shusheng Yang, Ethan Armand, Xiaojun Shan, Haiyang Xu, Jianwen Xie, Zhuowen Tu
Published: 2025-10-02
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.02295v2

Video understanding in multimodal language models remains limited by context length: models often miss key transition frames and struggle to maintain coherence across long time scales. To address this, we adapt Native Sparse Attention (NSA) to video-language models. Our method, VideoNSA, adapts Qwen2.5-VL through end-to-end training on a 216K video instruction dataset. We employ a hardware-aware hybrid approach to attention, preserving dense attention for text, while employing NSA for video. Compared to token-compression and training-free sparse baselines, VideoNSA achieves improved performance on long-video understanding, temporal reasoning, and spatial benchmarks. Further ablation analysis reveals four key findings: (1) reliable scaling to 128K tokens; (2) an optimal global-local attention allocation at a fixed budget; (3) task-dependent branch usage patterns; and (4) the learnable combined sparse attention help induce dynamic attention sinks. Project Page: https://enxinsong.com/VideoNSA-web/, Code: https://github.com/Espere-1119-Song/VideoNSA

---

### F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data

Authors: Ziyin Zhang, Zihan Liao, Hang Yu, Peng Di, Rui Wang
Published: 2025-10-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.02294v1

We introduce F2LLM - Foundation to Feature Large Language Models, a suite of state-of-the-art embedding models in three sizes: 0.6B, 1.7B, and 4B. Unlike previous top-ranking embedding models that require massive contrastive pretraining, sophisticated training pipelines, and costly synthetic training data, F2LLM is directly finetuned from foundation models on 6 million query-document-negative tuples curated from open-source, non-synthetic datasets, striking a strong balance between training cost, model size, and embedding performance. On the MTEB English leaderboard, F2LLM-4B ranks 2nd among models with approximately 4B parameters and 7th overall, while F2LLM-1.7B ranks 1st among models in the 1B-2B size range. To facilitate future research in the field, we release the models, training dataset, and code, positioning F2LLM as a strong, reproducible, and budget-friendly baseline for future works.

---

### From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens

Authors: Hala Sheta, Eric Huang, Shuyu Wu, Ilia Alenabi, Jiajun Hong, Ryker Lin, Ruoxi Ning, Daniel Wei, Jialin Yang, Jiawei Zhou, Ziqiao Ma, Freda Shi
Published: 2025-10-02
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2510.02292v1

We introduce VLM-Lens, a toolkit designed to enable systematic benchmarking, analysis, and interpretation of vision-language models (VLMs) by supporting the extraction of intermediate outputs from any layer during the forward pass of open-source VLMs. VLM-Lens provides a unified, YAML-configurable interface that abstracts away model-specific complexities and supports user-friendly operation across diverse VLMs. It currently supports 16 state-of-the-art base VLMs and their over 30 variants, and is extensible to accommodate new models without changing the core logic. The toolkit integrates easily with various interpretability and analysis methods. We demonstrate its usage with two simple analytical experiments, revealing systematic differences in the hidden representations of VLMs across layers and target concepts. VLM-Lens is released as an open-sourced project to accelerate community efforts in understanding and improving VLMs.

---

### Test-Time Anchoring for Discrete Diffusion Posterior Sampling

Authors: Litu Rout, Andreas Lugmayr, Yasamin Jafarian, Srivatsan Varadharajan, Constantine Caramanis, Sanjay Shakkottai, Ira Kemelmacher-Shlizerman
Published: 2025-10-02
Categories: cs.LG, cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2510.02291v2

While continuous diffusion models have achieved remarkable success, discrete diffusion offers a unified framework for jointly modeling text and images. Beyond unification, discrete diffusion provides faster inference, finer control, and principled training-free guidance, making it well-suited for posterior sampling. Existing approaches to posterior sampling using discrete diffusion face severe challenges: derivative-free guidance yields sparse signals, continuous relaxations limit applicability, and split Gibbs samplers suffer from the curse of dimensionality. To overcome these limitations, we introduce Anchored Posterior Sampling (APS), built on two key innovations: quantized expectation for gradient-like guidance in discrete embedding space, and anchored remasking for adaptive decoding. APS achieves state-of-the-art performance among discrete diffusion samplers on both linear and nonlinear inverse problems across the standard image benchmarks. We demonstrate the generality of APS through training-free stylization and text-guided editing. We further apply APS to a large-scale diffusion language model, showing consistent improvement in question answering.

---

### MultiModal Action Conditioned Video Generation

Authors: Yichen Li, Antonio Torralba
Published: 2025-10-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.02287v1

Current video models fail as world model as they lack fine-graiend control. General-purpose household robots require real-time fine motor control to handle delicate tasks and urgent situations. In this work, we introduce fine-grained multimodal actions to capture such precise control. We consider senses of proprioception, kinesthesia, force haptics, and muscle activation. Such multimodal senses naturally enables fine-grained interactions that are difficult to simulate with text-conditioned generative models. To effectively simulate fine-grained multisensory actions, we develop a feature learning paradigm that aligns these modalities while preserving the unique information each modality provides. We further propose a regularization scheme to enhance causality of the action trajectory features in representing intricate interaction dynamics. Experiments show that incorporating multimodal senses improves simulation accuracy and reduces temporal drift. Extensive ablation studies and downstream applications demonstrate the effectiveness and practicality of our work.

---

### Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks

Authors: Ruohao Guo, Afshin Oroojlooy, Roshan Sridhar, Miguel Ballesteros, Alan Ritter, Dan Roth
Published: 2025-10-02
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.02286v2

Despite recent rapid progress in AI safety, current large language models remain vulnerable to adversarial attacks in multi-turn interaction settings, where attackers strategically adapt their prompts across conversation turns and pose a more critical yet realistic challenge. Existing approaches that discover safety vulnerabilities either rely on manual red-teaming with human experts or employ automated methods using pre-defined templates and human-curated attack data, with most focusing on single-turn attacks. However, these methods did not explore the vast space of possible multi-turn attacks, failing to consider novel attack trajectories that emerge from complex dialogue dynamics and strategic conversation planning. This gap is particularly critical given recent findings that LLMs exhibit significantly higher vulnerability to multi-turn attacks compared to single-turn attacks. We propose DialTree, an on-policy reinforcement learning framework integrated with tree search that autonomously discovers diverse multi-turn attack strategies by treating the dialogue as a sequential decision-making problem, enabling systematic exploration without manually curated data. Through extensive experiments, our approach not only achieves more than 44.2% higher ASR across 12 target models compared to previous state-of-the-art approaches, but also effectively uncovers new attack strategies by learning optimal dialogue policies that maximize attack success across multiple turns.

---

### Learning to Generate Rigid Body Interactions with Video Diffusion Models

Authors: David Romero, Ariana Bermudez, Viacheslav Iablochnikov, Hao Li, Fabio Pizzati, Ivan Laptev
Published: 2025-10-02
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.02284v4

Recent video generation models have achieved remarkable progress and are now deployed in film, social media production, and advertising. Beyond their creative potential, such models also hold promise as world simulators for robotics and embodied decision making. Despite strong advances, current approaches still struggle to generate physically plausible object interactions and lack object-level control mechanisms. To address these limitations, we introduce KineMask, an approach for video generation that enables realistic rigid body control, interactions, and effects. Given a single image and a specified object velocity, our method generates videos with inferred motions and future object interactions. We propose a two-stage training strategy that gradually removes future motion supervision via object masks. Using this strategy we train video diffusion models (VDMs) on synthetic scenes of simple interactions and demonstrate significant improvements and generalization to rigid body and hand-object interactions in real scenes. Furthermore, KineMask integrates low-level motion control with high-level textual conditioning via predicted scene descriptions, leading to support for synthesis of complex dynamical phenomena. Our experiments show that KineMask generalizes to different VDMs and achieves strong improvements over recent models of comparable size. Ablation studies further highlight the complementary roles of low- and high-level conditioning in VDMs.

---

### Self-Forcing++: Towards Minute-Scale High-Quality Video Generation

Authors: Justin Cui, Jie Wu, Ming Li, Tao Yang, Xiaojie Li, Rui Wang, Andrew Bai, Yuanhao Ban, Cho-Jui Hsieh
Published: 2025-10-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.02283v1

Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending generation to long videos. Recent work has explored autoregressive formulations for long video generation, typically by distilling from short-horizon bidirectional teachers. Nevertheless, given that teacher models cannot synthesize long videos, the extrapolation of student models beyond their training horizon often leads to pronounced quality degradation, arising from the compounding of errors within the continuous latent space. In this paper, we propose a simple yet effective approach to mitigate quality degradation in long-horizon video generation without requiring supervision from long-video teachers or retraining on long video datasets. Our approach centers on exploiting the rich knowledge of teacher models to provide guidance for the student model through sampled segments drawn from self-generated long videos. Our method maintains temporal consistency while scaling video length by up to 20x beyond teacher's capability, avoiding common issues such as over-exposure and error-accumulation without recomputing overlapping frames like previous methods. When scaling up the computation, our method shows the capability of generating videos up to 4 minutes and 15 seconds, equivalent to 99.9% of the maximum span supported by our base model's position embedding and more than 50x longer than that of our baseline model. Experiments on standard benchmarks and our proposed improved benchmark demonstrate that our approach substantially outperforms baseline methods in both fidelity and consistency. Our long-horizon videos demo can be found at https://self-forcing-plus-plus.github.io/

---

### VidGuard-R1: AI-Generated Video Detection and Explanation via Reasoning MLLMs and RL

Authors: Kyoungjun Park, Yifan Yang, Juheon Yi, Shicheng Zheng, Yifei Shen, Dongqi Han, Caihua Shan, Muhammad Muaz, Lili Qiu
Published: 2025-10-02
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.02282v3

The rapid proliferation of AI-generated video necessitates robust detection tools that offer both high accuracy and human-interpretable explanations. While existing MLLM-based detectors rely on supervised fine-tuning (SFT) or direct preference optimization (DPO), these methods are often bottlenecked by static, pre-labeled datasets that fail to capture the evolving, multi-step physical inconsistencies of modern generative models. To bridge this gap, we introduce VidGuard-R1, the first video authenticity detector to utilize group relative policy optimization (GRPO). Moving beyond passive preference matching, VidGuard-R1 employs a reinforcement learning framework that encourages the model to explore and rank multiple reasoning paths. By introducing specialized reward models for temporal stability and diffusion-aware complexity, we incentivize the model to discover 'physics-grounded' artifacts. Our contributions include: (1) a curated dataset of 140,000 challenging real/fake video pairs; (2) a GRPO-based training paradigm that achieves state-of-the-art zero-shot performance; and (3) a reasoning-first architecture that provides precise, verifiable rationales for its forensic judgments. Project website: https://vidguard-r1.github.io/.

---

### Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation

Authors: Mykyta Ielanskyi, Kajetan Schweighofer, Lukas Aichberger, Sepp Hochreiter
Published: 2025-10-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.02279v2

Hallucinations are a common issue that undermine the reliability of large language models (LLMs). Recent studies have identified a specific subset of hallucinations, known as confabulations, which arise due to predictive uncertainty of LLMs. To detect confabulations, various methods for estimating predictive uncertainty in natural language generation (NLG) have been developed. These methods are typically evaluated by correlating uncertainty estimates with the correctness of generated text, with question-answering (QA) datasets serving as the standard benchmark. However, commonly used approximate correctness functions have substantial disagreement between each other and, consequently, in the ranking of the uncertainty estimation methods. This allows one to inflate the apparent performance of uncertainty estimation methods. We propose using several alternative risk indicators for risk correlation experiments that improve robustness of empirical assessment of UE algorithms for NLG. For QA tasks, we show that marginalizing over multiple LLM-as-a-judge variants leads to reducing the evaluation biases. Furthermore, we explore structured tasks as well as out of distribution and perturbation detection tasks which provide robust and controllable risk indicators. Finally, we propose to use an Elo rating of uncertainty estimation methods to give an objective summarization over extensive evaluation settings.

---

### Metropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Modeling

Authors: Fedor Velikonivtsev, Oleg Platonov, Ekaterina Alimaskina, Gleb Bazhenov, Liudmila Prokhorenkova
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.02278v2

Modeling traffic dynamics is a critical challenge for urban computing, with applications from real-time traffic management to infrastructure planning. However, progress in this area is fundamentally constrained by a lack of large-scale public datasets that capture the subtle properties of real city road networks. Existing benchmarks are often limited by their small scale, reliance on sparse highway traffic sensors, absence of true road connectivity information, and lack of information about road properties. To address this issue, we introduce datasets representing fine-grained road networks of two major cities, which are unique in their scale (up to 100,000 road segments), use of real road connectivity, presence of time series measurements for both traffic speed and volume at a 5-minute resolution, and inclusion of rich static road attributes. These datasets enable in-depth analysis of spatiotemporal traffic patterns and can serve as benchmarks for various ML applications. As a practical demonstration of the utility of our datasets and the challenges they present, we use them for the task of traffic forecasting. The size of the real-world road networks in our datasets reveals significant scalability issues in current traffic forecasting models. To address them, we propose a simple and efficient baseline that not only scales to large road graphs but also achieves forecasting performance competitive with other established spatiotemporal models. We hope that the proposed datasets will serve as a foundational resource for a broad range of research in traffic modeling, urban computing, and smart city development.

---

### BioX-Bridge: Model Bridging for Unsupervised Cross-Modal Knowledge Transfer across Biosignals

Authors: Chenqi Li, Yu Liu, Timothy Denison, Tingting Zhu
Published: 2025-10-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.02276v2

Biosignals offer valuable insights into the physiological states of the human body. Although biosignal modalities differ in functionality, signal fidelity, sensor comfort, and cost, they are often intercorrelated, reflecting the holistic and interconnected nature of human physiology. This opens up the possibility of performing the same tasks using alternative biosignal modalities, thereby improving the accessibility, usability, and adaptability of health monitoring systems. However, the limited availability of large labeled datasets presents challenges for training models tailored to specific tasks and modalities of interest. Unsupervised cross-modal knowledge transfer offers a promising solution by leveraging knowledge from an existing modality to support model training for a new modality. Existing methods are typically based on knowledge distillation, which requires running a teacher model alongside student model training, resulting in high computational and memory overhead. This challenge is further exacerbated by the recent development of foundation models that demonstrate superior performance and generalization across tasks at the cost of large model sizes. To this end, we explore a new framework for unsupervised cross-modal knowledge transfer of biosignals by training a lightweight bridge network to align the intermediate representations and enable information flow between foundation models and across modalities. Specifically, we introduce an efficient strategy for selecting alignment positions where the bridge should be constructed, along with a flexible prototype network as the bridge architecture. Extensive experiments across multiple biosignal modalities, tasks, and datasets show that BioX-Bridge reduces the number of trainable parameters by 88--99\% while maintaining or even improving transfer performance compared to state-of-the-art methods.

---

### Diffusion^2: Turning 3D Environments into Radio Frequency Heatmaps

Authors: Kyoungjun Park, Yifan Yang, Changhan Ge, Lili Qiu, Shiqi Jiang
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.02274v2

Modeling radio frequency (RF) signal propagation is essential for understanding the environment, as RF signals offer valuable insights beyond the capabilities of RGB cameras, which are limited by the visible-light spectrum, lens coverage, and occlusions. It is also useful for supporting wireless diagnosis, deployment, and optimization. However, accurately predicting RF signals in complex environments remains a challenge due to interactions with obstacles such as absorption and reflection. We introduce Diffusion^2, a diffusion-based approach that uses 3D point clouds to model the propagation of RF signals across a wide range of frequencies, from Wi-Fi to millimeter waves. To effectively capture RF-related features from 3D data, we present the RF-3D Encoder, which encapsulates the complexities of 3D geometry along with signal-specific details. These features undergo multi-scale embedding to simulate the actual RF signal dissemination process. Our evaluation, based on synthetic and real-world measurements, demonstrates that Diffusion^2 accurately estimates the behavior of RF signals in various frequency bands and environmental conditions, with an error margin of just 1.9 dB and 27x faster than existing methods, marking a significant advancement in the field. Refer to https://rfvision-project.github.io/ for more information.

---

### Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective

Authors: Wen Yang, Junhong Wu, Chong Li, Chengqing Zong, Jiajun Zhang
Published: 2025-10-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.02272v1

Recent advancements in Reinforcement Post-Training (RPT) have significantly enhanced the capabilities of Large Reasoning Models (LRMs), sparking increased interest in the generalization of RL-based reasoning. While existing work has primarily focused on investigating its generalization across tasks or modalities, this study proposes a novel cross-linguistic perspective to investigate reasoning generalization. This raises a crucial question: $\textit{Does the reasoning capability achieved from English RPT effectively transfer to other languages?}$ We address this by systematically evaluating English-centric LRMs on multilingual reasoning benchmarks and introducing a metric to quantify cross-lingual transferability. Our findings reveal that cross-lingual transferability varies significantly across initial model, target language, and training paradigm. Through interventional studies, we find that models with stronger initial English capabilities tend to over-rely on English-specific patterns, leading to diminished cross-lingual generalization. To address this, we conduct a thorough parallel training study. Experimental results yield three key findings: $\textbf{First-Parallel Leap}$, a substantial leap in performance when transitioning from monolingual to just a single parallel language, and a predictable $\textbf{Parallel Scaling Law}$, revealing that cross-lingual reasoning transfer follows a power-law with the number of training parallel languages. Moreover, we identify the discrepancy between actual monolingual performance and the power-law prediction as $\textbf{Monolingual Generalization Gap}$, indicating that English-centric LRMs fail to fully generalize across languages. Our study challenges the assumption that LRM reasoning mirrors human cognition, providing critical insights for the development of more language-agnostic LRMs.

---

### InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents

Authors: Yaxin Du, Yuanshuo Zhang, Xiyuan Yang, Yifan Zhou, Cheng Wang, Gongyi Zou, Xianghe Pang, Wenhao Wang, Menglan Chen, Shuo Tang, Zhiyu Li, Feiyu Xiong et al.
Published: 2025-10-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.02271v2

Information seeking is a fundamental requirement for humans. However, existing LLM agents rely heavily on open-web search, which exposes two fundamental weaknesses: online content is noisy and unreliable, and many real-world tasks require precise, domain-specific knowledge unavailable from the web. The emergence of the Model Context Protocol (MCP) now allows agents to interface with thousands of specialized tools, seemingly resolving this limitation. Yet it remains unclear whether agents can effectively leverage such tools -- and more importantly, whether they can integrate them with general-purpose search to solve complex tasks. Therefore, we introduce InfoMosaic-Bench, the first benchmark dedicated to multi-source information seeking in tool-augmented agents. Covering six representative domains (medicine, finance, maps, video, web, and multi-domain integration), InfoMosaic-Bench requires agents to combine general-purpose search with domain-specific tools. Tasks are synthesized with InfoMosaic-Flow, a scalable pipeline that grounds task conditions in verified tool outputs, enforces cross-source dependencies, and filters out shortcut cases solvable by trivial lookup. This design guarantees both reliability and non-triviality. Experiments with 14 state-of-the-art LLM agents reveal three findings: (i) web information alone is insufficient, with GPT-5 achieving only 38.2% accuracy and 67.5% pass rate; (ii) domain tools provide selective but inconsistent benefits, improving some domains while degrading others; and (iii) 22.4% of failures arise from incorrect tool usage or selection, highlighting that current LLMs still struggle with even basic tool handling.

---

### microCLIP: Unsupervised CLIP Adaptation via Coarse-Fine Token Fusion for Fine-Grained Image Classification

Authors: Sathira Silva, Eman Ali, Chetan Arora, Muhammad Haris Khan
Published: 2025-10-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.02270v1

Unsupervised adaptation of CLIP-based vision-language models (VLMs) for fine-grained image classification requires sensitivity to microscopic local cues. While CLIP exhibits strong zero-shot transfer, its reliance on coarse global features restricts its performance on fine-grained classification tasks. Prior efforts inject fine-grained knowledge by aligning large language model (LLM) descriptions with the CLIP $\texttt{(CLS)}$ token; however, this approach overlooks spatial precision. We propose $\textbf{microCLIP}$, a self-training framework that jointly refines CLIP's visual and textual representations using fine-grained cues. At its core is Saliency-Oriented Attention Pooling (SOAP) within a lightweight TokenFusion module, which builds a saliency-guided $\texttt{(FG)}$ token from patch embeddings and fuses it with the global $\texttt{(CLS)}$ token for coarse-fine alignment. To stabilize adaptation, we introduce a two-headed LLM-derived classifier: a frozen classifier that, via multi-view alignment, provides a stable text-based prior for pseudo-labeling, and a learnable classifier initialized from LLM descriptions and fine-tuned with TokenFusion. We further develop Dynamic Knowledge Aggregation, which convexly combines fixed LLM/CLIP priors with TokenFusion's evolving logits to iteratively refine pseudo-labels. Together, these components uncover latent fine-grained signals in CLIP, yielding a consistent $2.90\%$ average accuracy gain across 13 fine-grained benchmarks while requiring only light adaptation. Our code is available at https://github.com/sathiiii/microCLIP.

---

### Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning

Authors: Tianchong Jiang, Jingtian Ji, Xiangshan Tan, Jiading Fang, Anand Bhattad, Vitor Guizilini, Matthew R. Walter
Published: 2025-10-02
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2510.02268v1

We study view-invariant imitation learning by explicitly conditioning policies on camera extrinsics. Using Plucker embeddings of per-pixel rays, we show that conditioning on extrinsics significantly improves generalization across viewpoints for standard behavior cloning policies, including ACT, Diffusion Policy, and SmolVLA. To evaluate policy robustness under realistic viewpoint shifts, we introduce six manipulation tasks in RoboSuite and ManiSkill that pair "fixed" and "randomized" scene variants, decoupling background cues from camera pose. Our analysis reveals that policies without extrinsics often infer camera pose using visual cues from static backgrounds in fixed scenes; this shortcut collapses when workspace geometry or camera placement shifts. Conditioning on extrinsics restores performance and yields robust RGB-only control without depth. We release the tasks, demonstrations, and code at https://ripl.github.io/know_your_camera/ .

---

### NeuroSwift: A Lightweight Cross-Subject Framework for fMRI Visual Reconstruction of Complex Scenes

Authors: Shiyi Zhang, Dong Liang, Yihang Zhou
Published: 2025-10-02
Categories: cs.CV, cs.HC
arXiv: https://arxiv.org/abs/2510.02266v2

Reconstructing visual information from brain activity via computer vision technology provides an intuitive understanding of visual neural mechanisms. Despite progress in decoding fMRI data with generative models, achieving accurate cross-subject reconstruction of visual stimuli remains challenging and computationally demanding. This difficulty arises from inter-subject variability in neural representations and the brain's abstract encoding of core semantic features in complex visual inputs. To address these challenges, we propose NeuroSwift, which integrates complementary adapters via diffusion: AutoKL for low-level features and CLIP for semantics. NeuroSwift's CLIP Adapter is trained on Stable Diffusion generated images paired with COCO captions to emulate higher visual cortex encoding. For cross-subject generalization, we pretrain on one subject and then fine-tune only 17 percent of parameters (fully connected layers) for new subjects, while freezing other components. This enables state-of-the-art performance with only one hour of training per subject on lightweight GPUs (three RTX 4090), and it outperforms existing methods.

---

### How to Combat Reactive and Dynamic Jamming Attacks with Reinforcement Learning

Authors: Yalin E. Sagduyu, Tugba Erpek, Kemal Davaslioglu, Sastry Kompella
Published: 2025-10-02
Categories: cs.LG, cs.AI, cs.NI, eess.SP
arXiv: https://arxiv.org/abs/2510.02265v1

This paper studies the problem of mitigating reactive jamming, where a jammer adopts a dynamic policy of selecting channels and sensing thresholds to detect and jam ongoing transmissions. The transmitter-receiver pair learns to avoid jamming and optimize throughput over time (without prior knowledge of channel conditions or jamming strategies) by using reinforcement learning (RL) to adapt transmit power, modulation, and channel selection. Q-learning is employed for discrete jamming-event states, while Deep Q-Networks (DQN) are employed for continuous states based on received power. Through different reward functions and action sets, the results show that RL can adapt rapidly to spectrum dynamics and sustain high rates as channels and jamming policies change over time.

---

### Paving the Way Towards Kinematic Assessment Using Monocular Video: A Preclinical Benchmark of State-of-the-Art Deep-Learning-Based 3D Human Pose Estimators Against Inertial Sensors in Daily Living Activities

Authors: Mario Medrano-Paredes, Carmen Fernández-González, Francisco-Javier Díaz-Pernas, Hichem Saoudi, Javier González-Alonso, Mario Martínez-Zarzuela
Published: 2025-10-02
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.02264v1

Advances in machine learning and wearable sensors offer new opportunities for capturing and analyzing human movement outside specialized laboratories. Accurate assessment of human movement under real-world conditions is essential for telemedicine, sports science, and rehabilitation. This preclinical benchmark compares monocular video-based 3D human pose estimation models with inertial measurement units (IMUs), leveraging the VIDIMU dataset containing a total of 13 clinically relevant daily activities which were captured using both commodity video cameras and five IMUs. During this initial study only healthy subjects were recorded, so results cannot be generalized to pathological cohorts. Joint angles derived from state-of-the-art deep learning frameworks (MotionAGFormer, MotionBERT, MMPose 2D-to-3D pose lifting, and NVIDIA BodyTrack) were evaluated against joint angles computed from IMU data using OpenSim inverse kinematics following the Human3.6M dataset format with 17 keypoints. Among them, MotionAGFormer demonstrated superior performance, achieving the lowest overall RMSE ($9.27°\pm 4.80°$) and MAE ($7.86°\pm 4.18°$), as well as the highest Pearson correlation ($0.86 \pm 0.15$) and the highest coefficient of determination $R^{2}$ ($0.67 \pm 0.28$). The results reveal that both technologies are viable for out-of-the-lab kinematic assessment. However, they also highlight key trade-offs between video- and sensor-based approaches including costs, accessibility, and precision. This study clarifies where off-the-shelf video models already provide clinically promising kinematics in healthy adults and where they lag behind IMU-based estimates while establishing valuable guidelines for researchers and clinicians seeking to develop robust, cost-effective, and user-friendly solutions for telehealth and remote patient monitoring.

---

### RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems

Authors: Yuxiao Qu, Anikait Singh, Yoonho Lee, Amrith Setlur, Ruslan Salakhutdinov, Chelsea Finn, Aviral Kumar
Published: 2025-10-02
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.02263v1

Reasoning requires going beyond pattern matching or memorization of solutions to identify and implement "algorithmic procedures" that can be used to deduce answers to hard problems. Doing so requires realizing the most relevant primitives, intermediate results, or shared procedures, and building upon them. While RL post-training on long chains of thought ultimately aims to uncover this kind of algorithmic behavior, most reasoning traces learned by large models fail to consistently capture or reuse procedures, instead drifting into verbose and degenerate exploration. To address more effective reasoning, we introduce reasoning abstractions: concise natural language descriptions of procedural and factual knowledge that guide the model toward learning successful reasoning. We train models to be capable of proposing multiple abstractions given a problem, followed by RL that incentivizes building a solution while using the information provided by these abstractions. This results in a two-player RL training paradigm, abbreviated as RLAD, that jointly trains an abstraction generator and a solution generator. This setup effectively enables structured exploration, decouples learning signals of abstraction proposal and solution generation, and improves generalization to harder problems. We also show that allocating more test-time compute to generating abstractions is more beneficial for performance than generating more solutions at large test budgets, illustrating the role of abstractions in guiding meaningful exploration.

---

### From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding

Authors: Guangyu Sun, Archit Singhal, Burak Uzkent, Mubarak Shah, Chen Chen, Garin Kessler
Published: 2025-10-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.02262v2

Video Large Language Models (VLMs) have achieved strong performance on various vision-language tasks, yet their practical use is limited by the massive number of visual tokens produced from raw video frames, which quickly exhausts the model's context window. Existing solutions mitigate this issue by selecting a sparse set of frames, but such frame-wise selection discards essential temporal dynamics in long-form videos, leading to suboptimal reasoning about motion and event continuity. In this work, we systematically examine the role of temporal information and show that extending selection from isolated key frames to temporally coherent key clips improves video understanding. To maintain a fixed computational budget while accommodating the larger token footprint of clips, we introduce frame resolution as a controllable factor in frame selection, enabling a trade-off between spatial resolution and clip length. Building on this idea, we propose an adaptive clip length module that dynamically balances these factors to ensure a constant token count per video. Experiments on three long-form video benchmarks demonstrate that our training-free approach, F2C, outperforms uniform sampling by up to 8.1%, 5.6%, and 10.3% on Video-MME, LongVideoBench, and MLVU, respectively. These results highlight the importance of preserving temporal coherence in frame selection and provide a practical pathway for scaling VLMs to real-world video understanding applications. Project webpage is available at https://guangyusun.com/f2c .

---

### Transformers Discover Molecular Structure Without Graph Priors

Authors: Tobias Kreiman, Yutong Bai, Fadi Atieh, Elizabeth Weaver, Eric Qu, Aditi S. Krishnapriyan
Published: 2025-10-02
Categories: cs.LG, cond-mat.mtrl-sci, physics.chem-ph, q-bio.BM
arXiv: https://arxiv.org/abs/2510.02259v3

Computational simulations play a central role in scientific discovery, and machine learning (ML) has emerged as a promising alternative to traditional physics-based modeling. However, scientific modeling requires physically meaningful predictions, raising a fundamental question for data-driven methods: to what extent can physical inductive biases-that is, prior assumptions about the structure of the physical world-emerge by learning from data alone? In this work, we study atomistic modeling, a representative field in the computational sciences where ML architectures have historically embedded strong physical inductive biases-such as geometric locality and graph structure. We develop a systematic understanding of how physical patterns can alternatively be discovered directly from data by training a model without domain-specific priors, including any manually defined atomistic pairwise interactions. We find that the model autonomously recovers key physical structure, such as learned interatomic interaction strengths that mirror classical electrostatics and interaction cutoffs consistent with traditional physical models. We further demonstrate predictable neural scaling law behavior with increased data and compute, and find accuracy on certain metrics competitive with physics-informed architectures. Our results clarify the boundary between engineered inductive biases and learnable physical structure, suggesting that general-purpose architectures can serve as principled baselines for scientific modeling by learning fundamental physical structure directly from data.

---

### DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing

Authors: Zihan Zhou, Shilin Lu, Shuli Leng, Shaocong Zhang, Zhuming Lian, Xinlei Yu, Adams Wai-Kin Kong
Published: 2025-10-02
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.02253v3

Drag-based image editing has long suffered from distortions in the target region, largely because the priors of earlier base models, Stable Diffusion, are insufficient to project optimized latents back onto the natural image manifold. With the shift from UNet-based DDPMs to more scalable DiT with flow matching (e.g., SD3.5, FLUX), generative priors have become significantly stronger, enabling advances across diverse editing tasks. However, drag-based editing has yet to benefit from these stronger priors. This work proposes the first framework to effectively harness FLUX's rich prior for drag-based editing, dubbed DragFlow, achieving substantial gains over baselines. We first show that directly applying point-based drag editing to DiTs performs poorly: unlike the highly compressed features of UNets, DiT features are insufficiently structured to provide reliable guidance for point-wise motion supervision. To overcome this limitation, DragFlow introduces a region-based editing paradigm, where affine transformations enable richer and more consistent feature supervision. Additionally, we integrate pretrained open-domain personalization adapters (e.g., IP-Adapter) to enhance subject consistency, while preserving background fidelity through gradient mask-based hard constraints. Multimodal large language models (MLLMs) are further employed to resolve task ambiguities. For evaluation, we curate a novel Region-based Dragging benchmark (ReD Bench) featuring region-level dragging instructions. Extensive experiments on DragBench-DR and ReD Bench show that DragFlow surpasses both point-based and region-based baselines, setting a new state-of-the-art in drag-based image editing. Code and dataset are available at https://github.com/Edennnnnnnnnn/DragFlow.

---

### Scaling Agents for Computer Use

Authors: Gonzalo Gonzalez-Pumariega, Vincent Tu, Chih-Lun Lee, Jiachen Yang, Ang Li, Xin Eric Wang
Published: 2025-10-02
Categories: cs.AI, cs.CL, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.02250v2

Computer-use agents (CUAs) hold promise for automating everyday digital tasks, but their performance on long-horizon, complex problems remains unreliable. Single-rollout execution is brittle, with small errors compounding over time and leading to high variance in outcomes. While prior work has attempted to scale within a single rollout, such approaches have yielded limited gains. Scaling over multiple rollouts offers a more promising alternative but doing so effectively is challenging due to the difficulty of evaluating and selecting among long-horizon agent behaviors. We introduce Behavior Judge (BJudge), which addresses this challenge by representing agent executions as behavior narratives and comparing candidate behaviors at this level, substantially improving robustness and success rates. Using multiple rollouts, BJudge establishes a new state of the art (SoTA) in OSWorld at 72.6%, significantly outperforming prior methods and surpassing human-level performance at 72.36%, with comprehensive ablations validating key design choices. We further demonstrate strong generalization results to different operating systems on WindowsAgentArena and AndroidWorld. Crucially, our results highlight the strong effectiveness of scaling CUAs, when you do it right: effective scaling requires structured trajectory understanding and selection, and BJudge provides a practical framework to achieve this.

---

### Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation

Authors: Yi Bin, Tianyi Jiang, Yujuan Ding, Kainian Zhu, Fei Ma, Jingkuan Song, Yang Yang, Heng Tao Shen
Published: 2025-10-02
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.02249v2

Large Language Models (LLMs) have demonstrated remarkable reasoning abilities on complex problems using long Chain-of-Thought (CoT) reasoning. However, they often suffer from overthinking, meaning generating unnecessarily lengthy reasoning steps for simpler problems. This issue may degrade the efficiency of the models and make them difficult to adapt the reasoning depth to the complexity of problems. To address this, we introduce a novel metric Token Entropy Cumulative Average (TECA), which measures the extent of exploration throughout the reasoning process. We further propose a novel reasoning paradigm named "Explore Briefly, Then Decide", with an associated Cumulative Entropy Regulation (CER) mechanism. This paradigm leverages TECA to help the model dynamically determine the optimal point to conclude its thought process and provide a final answer, thus achieving efficient reasoning. Experimental results across diverse mathematical benchmarks show that our approach substantially mitigates overthinking without sacrificing problem solving ability. With our thinking paradigm, the average response length decreases by up to 71% on simpler datasets, demonstrating the effectiveness of our method in creating a more efficient and adaptive reasoning process.

---

### ExGRPO: Learning to Reason from Experience

Authors: Runzhe Zhan, Yafu Li, Zhi Wang, Xiaoye Qu, Dongrui Liu, Jing Shao, Derek F. Wong, Yu Cheng
Published: 2025-10-02
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.02245v2

Reinforcement learning from verifiable rewards (RLVR) is an emerging paradigm for improving the reasoning ability of large language models. However, standard on-policy training discards rollout experiences after a single update, leading to computational inefficiency and instability. While prior work on RL has highlighted the benefits of reusing past experience, the role of experience characteristics in shaping learning dynamics of large reasoning models remains underexplored. In this paper, we are the first to investigate what makes a reasoning experience valuable and identify rollout correctness and entropy as effective indicators of experience value. Based on these insights, we propose ExGRPO (Experiential Group Relative Policy Optimization), a framework that organizes and prioritizes valuable experiences, and employs a mixed-policy objective to balance exploration with experience exploitation. Experiments on five backbone models (1.5B-8B parameters) show that ExGRPO consistently improves reasoning performance on mathematical/general benchmarks, with an average gain of +3.5/7.6 points over on-policy RLVR. Moreover, ExGRPO stabilizes training on both stronger and weaker models where on-policy methods fail. These results highlight principled experience management as a key ingredient for efficient and scalable RLVR.

---

### AccurateRAG: A Framework for Building Accurate Retrieval-Augmented Question-Answering Applications

Authors: Linh The Nguyen, Chi Tran, Dung Ngoc Nguyen, Van-Cuong Pham, Hoang Ngo, Dat Quoc Nguyen
Published: 2025-10-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.02243v2

We introduce AccurateRAG -- a novel framework for constructing high-performance question-answering applications based on retrieval-augmented generation (RAG). Our framework offers a pipeline for development efficiency with tools for raw dataset processing, fine-tuning data generation, text embedding & LLM fine-tuning, output evaluation, and building RAG systems locally. Experimental results show that our framework outperforms previous strong baselines and obtains new state-of-the-art question-answering performance on benchmark datasets.

---

### Study on LLMs for Promptagator-Style Dense Retriever Training

Authors: Daniel Gwon, Nour Jedidi, Jimmy Lin
Published: 2025-10-02
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2510.02241v1

Promptagator demonstrated that Large Language Models (LLMs) with few-shot prompts can be used as task-specific query generators for fine-tuning domain-specialized dense retrieval models. However, the original Promptagator approach relied on proprietary and large-scale LLMs which users may not have access to or may be prohibited from using with sensitive data. In this work, we study the impact of open-source LLMs at accessible scales ($\leq$14B parameters) as an alternative. Our results demonstrate that open-source LLMs as small as 3B parameters can serve as effective Promptagator-style query generators. We hope our work will inform practitioners with reliable alternatives for synthetic data generation and give insights to maximize fine-tuning results for domain-specific applications.

---

### RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

Authors: Sicheng Feng, Kaiwen Tuo, Song Wang, Lingdong Kong, Jianke Zhu, Huan Wang
Published: 2025-10-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.02240v2

Fine-grained visual reasoning remains a core challenge for multimodal large language models (MLLMs). The recently introduced ReasonMap highlights this gap by showing that even advanced MLLMs struggle with spatial reasoning in structured and information-rich settings such as transit maps, a task of clear practical and scientific importance. However, standard reinforcement learning (RL) on such tasks is impeded by sparse rewards and unstable optimization. To address this, we first construct ReasonMap-Plus, an extended dataset that introduces dense reward signals through Visual Question Answering (VQA) tasks, enabling effective cold-start training of fine-grained visual understanding skills. Next, we propose RewardMap, a multi-stage RL framework designed to improve both visual understanding and reasoning capabilities of MLLMs. RewardMap incorporates two key designs. First, we introduce a difficulty-aware reward design that incorporates detail rewards, directly tackling the sparse rewards while providing richer supervision. Second, we propose a multi-stage RL scheme that bootstraps training from simple perception to complex reasoning tasks, offering a more effective cold-start strategy than conventional Supervised Fine-Tuning (SFT). Experiments on ReasonMap and ReasonMap-Plus demonstrate that each component of RewardMap contributes to consistent performance gains, while their combination yields the best results. Moreover, models trained with RewardMap achieve an average improvement of 3.47% across 6 benchmarks spanning spatial reasoning, fine-grained visual reasoning, and general tasks beyond transit maps, underscoring enhanced visual understanding and reasoning capabilities.

---

### Drop-Muon: Update Less, Converge Faster

Authors: Kaja Gruntkowska, Yassine Maziane, Zheng Qu, Peter Richtárik
Published: 2025-10-02
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2510.02239v1

Conventional wisdom in deep learning optimization dictates updating all layers at every step-a principle followed by all recent state-of-the-art optimizers such as Muon. In this work, we challenge this assumption, showing that full-network updates can be fundamentally suboptimal, both in theory and in practice. We introduce a non-Euclidean Randomized Progressive Training method-Drop-Muon-a simple yet powerful framework that updates only a subset of layers per step according to a randomized schedule, combining the efficiency of progressive training with layer-specific non-Euclidean updates for top-tier performance. We provide rigorous convergence guarantees under both layer-wise smoothness and layer-wise $(L^0, L^1)$-smoothness, covering deterministic and stochastic gradient settings, marking the first such results for progressive training in the stochastic and non-smooth regime. Our cost analysis further reveals that full-network updates are not optimal unless a very specific relationship between layer smoothness constants holds. Through controlled CNN experiments, we empirically demonstrate that Drop-Muon consistently outperforms full-network Muon, achieving the same accuracy up to $1.4\times$ faster in wall-clock time. Together, our results suggest a shift in how large-scale models can be efficiently trained, challenging the status quo and offering a highly efficient, theoretically grounded alternative to full-network updates.

---

### PUL-Inter-slice Defender: An Anomaly Detection Solution for Distributed Slice Mobility Attacks

Authors: Ricardo Misael Ayala Molina, Hyame Assem Alameddine, Makan Pourzandi, Chadi Assi
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.02236v1

Network Slices (NSs) are virtual networks operating over a shared physical infrastructure, each designed to meet specific application requirements while maintaining consistent Quality of Service (QoS). In Fifth Generation (5G) networks, User Equipment (UE) can connect to and seamlessly switch between multiple NSs to access diverse services. However, this flexibility, known as Inter-Slice Switching (ISS), introduces a potential vulnerability that can be exploited to launch Distributed Slice Mobility (DSM) attacks, a form of Distributed Denial of Service (DDoS) attack. To secure 5G networks and their NSs against DSM attacks, we present in this work, PUL-Inter-Slice Defender; an anomaly detection solution that leverages Positive Unlabeled Learning (PUL) and incorporates a combination of Long Short-Term Memory Autoencoders and K-Means clustering. PUL-Inter-Slice Defender leverages the Third Generation Partnership Project (3GPP) key performance indicators and performance measurement counters as features for its machine learning models to detect DSM attack variants while maintaining robustness in the presence of contaminated training data. When evaluated on data collected from our 5G testbed based on the open-source free5GC and UERANSIM, a UE/ Radio Access Network (RAN) simulator; PUL-Inter-Slice Defender achieved F1-scores exceeding 98.50% on training datasets with 10% to 40% attack contamination, consistently outperforming its counterpart Inter-Slice Defender and other PUL based solutions combining One-Class Support Vector Machine (OCSVM) with Random Forest and XGBoost.

---

### Enhanced Arabic-language cyberbullying detection: deep embedding and transformer (BERT) approaches

Authors: Ebtesam Jaber Aljohani, Wael M. S. Yafoo
Published: 2025-10-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.02232v1

Recent technological advances in smartphones and communications, including the growth of such online platforms as massive social media networks such as X (formerly known as Twitter) endangers young people and their emotional well-being by exposing them to cyberbullying, taunting, and bullying content. Most proposed approaches for automatically detecting cyberbullying have been developed around the English language, and methods for detecting Arabic-language cyberbullying are scarce. Methods for detecting Arabic-language cyberbullying are especially scarce. This paper aims to enhance the effectiveness of methods for detecting cyberbullying in Arabic-language content. We assembled a dataset of 10,662 X posts, pre-processed the data, and used the kappa tool to verify and enhance the quality of our annotations. We conducted four experiments to test numerous deep learning models for automatically detecting Arabic-language cyberbullying. We first tested a long short-term memory (LSTM) model and a bidirectional long short-term memory (Bi-LSTM) model with several experimental word embeddings. We also tested the LSTM and Bi-LSTM models with a novel pre-trained bidirectional encoder from representations (BERT) and then tested them on a different experimental models BERT again. LSTM-BERT and Bi-LSTM-BERT demonstrated a 97% accuracy. Bi-LSTM with FastText embedding word performed even better, achieving 98% accuracy. As a result, the outcomes are generalize

---

### The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models

Authors: Phuc Minh Nguyen, Chinh D. La, Duy M. H. Nguyen, Nitesh V. Chawla, Binh T. Nguyen, Khoa D. Doan
Published: 2025-10-02
Categories: cs.AI, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2510.02230v1

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key method for improving Large Language Models' reasoning capabilities, yet recent evidence suggests it may paradoxically shrink the reasoning boundary rather than expand it. This paper investigates the shrinkage issue of RLVR by analyzing its learning dynamics and reveals two critical phenomena that explain this failure. First, we expose negative interference in RLVR, where learning to solve certain training problems actively reduces the likelihood of correct solutions for others, leading to the decline of Pass@$k$ performance, or the probability of generating a correct solution within $k$ attempts. Second, we uncover the winner-take-all phenomenon: RLVR disproportionately reinforces problems with high likelihood, correct solutions, under the base model, while suppressing other initially low-likelihood ones. Through extensive theoretical and empirical analysis on multiple mathematical reasoning benchmarks, we show that this effect arises from the inherent on-policy sampling in standard RL objectives, causing the model to converge toward narrow solution strategies. Based on these insights, we propose a simple yet effective data curation algorithm that focuses RLVR learning on low-likelihood problems, achieving notable improvement in Pass@$k$ performance. Our code is available at https://github.com/mail-research/SELF-llm-interference.

---

### xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity

Authors: Maximilian Beck, Kajetan Schweighofer, Sebastian Böck, Sebastian Lehner, Sepp Hochreiter
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.02228v2

Scaling laws play a central role in the success of Large Language Models (LLMs), enabling the prediction of model performance relative to compute budgets prior to training. While Transformers have been the dominant architecture, recent alternatives such as xLSTM offer linear complexity with respect to context length while remaining competitive in the billion-parameter regime. We conduct a comparative investigation on the scaling behavior of Transformers and xLSTM along the following lines, providing insights to guide future model design and deployment. First, we study the scaling behavior for xLSTM in compute-optimal and over-training regimes using both IsoFLOP and parametric fit approaches on a wide range of model sizes (80M-7B) and number of training tokens (2B-2T). Second, we examine the dependence of optimal model sizes on context length, a pivotal aspect that was largely ignored in previous work. Finally, we analyze inference-time scaling characteristics. Our findings reveal that in typical LLM training and inference scenarios, xLSTM scales favorably compared to Transformers. Notably, xLSTM models consistently Pareto-dominate Transformer models, delivering lower cross-entropy loss for the same compute budget.

---