Omni-modal models can answer questions about video, but their predictions rarely show which participant, event, or interval supports an answer. Moreover, answer-level supervision alone does not teach...
Recent advances have enabled unified omni-modal models in understanding audio, vision, and language. However, existing benchmarks, training data, and learning methods largely treat the modalities inde...
arXiv:2606. 24797v1 Announce Type: cross Abstract: Recent advances in Video Large Language Models (Video-LLMs) have yielded promising performance on video question answering (VideoQA).
EvaOmni is a new evidence‑grounded benchmark for audio‑visual reasoning, comprising 392 videos and 1,027 human‑annotated question‑answer pairs that span 15 capabilities and three difficulty levels. The benchmark requires models to provide both an answer and the supporting audio‑visual evidence intervals, and introduces Coverage Grounded (C.G.) and Bottleneck Grounded (B.G.) scores to evaluate evidence identification and temporal localization. Across 24 Omni LLMs, Gemini3.7‑Flash achieved the highest overall accuracy, yet its B.G. scores reveal significant room for improvement in grounded reasoning.
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.
Event-Causal RAG (EC‑RAG) is a lightweight retrieval‑augmented framework designed for reasoning over ultra‑long and streaming videos. It segments video streams into semantically complete events using a dual visual‑audio sentinel mechanism, representing each event as a State‑Event‑State (SES) structure that captures pre‑event, event, and post‑event states. During question answering, bidirectional graph retrieval accesses relevant predecessor and successor events from a dual vector‑graph memory, and answers are generated using both this structured memory and the corresponding video evidence. The authors also introduce ECV‑1H, an hour‑scale long‑video QA benchmark with over 150 hours of untrimmed video and 1,251 human‑annotated QA pairs, where EC‑RAG achieves significant accuracy gains across multiple video foundation models while maintaining efficient streaming memory usage on a single RTX 5090 GPU.
arXiv:2606. 01485v1 Announce Type: cross Abstract: We describe our submission to the VRR Challenge @ CVPR 2026, built on the \emph{ImplicitQA} / \emph{VRR-QA} benchmark~\cite{implicitqa}: multiple-choice video question answering in which answers are deliberately \emph{not} observable in any single frame and must be inferred from spatial layout, motion, depth, viewpoint, causality, and social context across discontinuous frames of creative video.
Video-FLAIR is a training framework that teaches a model to choose the most suitable reasoning mode—perceptual, compositional, or deliberative—for each multimodal query using reinforcement learning. During training, the model generates responses under all three modes for the same prompt, and a composite reward system selects the best response based on correctness, grounding, and cost, discouraging unsupported deliberation. This adaptive approach improves accuracy on benchmarks such as MathVista, Video-Holmes, and Video-MMMU while dramatically reducing token usage compared to always-thinking baselines.
arXiv:2606. 11209v1 Announce Type: cross Abstract: Visual question answering increasingly requires multi-step reasoning.
arXiv:2601. 07761v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) face a fundamental dilemma in video reasoning: they are caught between the prohibitive computational costs of verbose reasoning and the hallucination risks of efficient, ungrounded approaches.
arXiv:2607. 02959v1 Announce Type: cross Abstract: We introduce VSeek, an agentic framework that transforms long-video question answering (LVQA) from a passive, single-pass perception task into a multi-turn retrieval process.
arXiv:2609.39378v1 Announce Type: new Abstract: Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical constraints while tracking evolvin...