OmniReasoning introduces a new benchmark, OmniReasoningBench, that requires both audio and visual evidence for answering 1,150 multiple-choice and open-ended questions across two tasks. The authors also develop OmniQA, a data engine that automatically generates evidence‑grounded QA pairs with time‑stamped clue chains, producing training datasets OmniReasoning‑SFT‑112K and OmniReasoning‑RL‑19K. Finally, they propose Modality‑Factored Self‑Distillation (MFSD), an on‑policy self‑distillation method that assigns token‑level credit by evaluating responses under modality‑specific clue contexts, enabling the OmniReasoning‑30B‑A3B model to achieve significant performance gains on both the new benchmark and existing video benchmarks.
By Junming Lin, Yuxuan Wang, Zhenxin Lei, Yuxin Liu, Ruixun Liu, Yinsong Yan, Ling Wang, Minghao Han, Yunfei Chu, Shun Lei, Xueyao Zhang, Qize Yang, Jin Xu, Yiwu Zhong
arXiv:2609.38930v1 Announce Type: cross
Abstract: In semantic segmentation, a recent line of RankSEG methods directly optimizes Dice/IoU scores at inference time, improving alignment with evaluation...
By Zixun Wang, Ben Dai
arXiv:2609.40356v1 Announce Type: cross
Abstract: Recent video generation is increasingly realistic and controllable, yet video editing remains less developed, particularly for precise local edits th...
By Xinghao Chen, Xiangbo Gao, Jiongze Yu, Yuheng Wu, Zhengzhong Tu
The paper introduces a policy‑conditioned AI‑use detection framework for academic publishing, arguing that traditional AI detection tools misalign with venue rules by merely identifying AI‑generated text. Instead, the proposed system treats the governing policy as an explicit input, generating hypotheses, evidence, calibration, and uncertainty rather than binary verdicts. It outlines how to benchmark compliance, evaluate true positive rates at venue‑specified false positive thresholds, and emphasizes the need for structured disclosure, tool routing, and contestable findings.
By Jairo Diaz-Rodriguez, Mumin Jia
The paper treats multi‑path large language model reasoning as a diversity‑combining problem, analogous to noisy channel observations in wireless communications. It shows that the optimal symmetric linear combiner of latent embeddings is uniform, justifying majority vote in standard self‑consistency while allowing for weighting or pruning when prompt‑template branches are heterogeneous. By reducing path correlation through prompt‑template diversity, the authors propose an Adaptive‑K rule that selects an optimal number of reasoning paths, preserving most of the accuracy achieved with a fixed large number of paths across multiple models and benchmarks.
By Guangsheng Yu, Litianyi Zhang, Qin Wang, Xu Wang, Mingyuan Li, Shaoxiong Ji, Ren Ping Liu, Massimo Piccardi
Personalized image generation has remained narrowly focused on conditional synthesis from curated visual exemplars, rather than capturing who a user is. In practice, however, a user's personal context...
Query-aware keyframe selection enables multimodal large language models (MLLMs) to process long videos using only a small set of question-relevant frames. Existing score-based methods, however, typica...
Looped transformers and Mixture-of-Experts (MoE) offer complementary routes to efficient scaling: recurrence increases computational depth at fixed parameters, while MoE sparsity expands total capacit...
Language agents are expected to solve increasingly complex tasks, creating a growing need for continual improvement. One promising approach is to evolve the agent harness, the software that governs to...
Digital image watermarking is increasingly critical in media contexts, as emerging regulations and industry practices require marking AI-generated content and ensuring traceable sources to prevent man...
Causal action verifiers gate an agent's state-changing tool calls by checking whether each proposed intervention is identifiable against a committed action-state graph, and they issue a certificate th...
Long-context failures of RoPE-based language models can arise from RoPE's intrinsic tradeoff between maintaining stable token preferences and distinguishing nearby positions. Determining which weaknes...
Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neural networks, Kolmogorov Arnold networks, and se...
Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neural networks, Kolmogorov Arnold networks, and se...
Source-Free Universal Domain Adaptation (SF-UniDA) extends Universal Domain Adaptation by removing access to source data at adaptation time while still handling label-set mismatches between domains. D...
Distinguishing periodic from chaotic dynamics in a time series is a fundamental challenge in both physics and engineering. Yet, end-to-end learned architectures must discover both a representation and...
Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains underexplored. In this work, we present Flow Any Scene...
Large forecasting applications often combine statistical, machine-learning, and neural models. These families solve the same problem but differ in fitted state, training procedures, and how they paral...
This paper demonstrate that whether masking-based token pruning helps or hurts worst-group robustness can be predicted before deployment, without labels or fine-tuning. A systematic study of semantic...
Video super-resolution (VSR) is normally judged by PSNR and SSIM on clips that were downsampled bicubically, although in surveillance its purpose is to make faces and licence plates \emph{recognisable...