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...
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.
arXiv:2605.07593v2 Announce Type: replace Abstract: Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory str...
arXiv:2602. 22897v3 Announce Type: replace Abstract: Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world.
Multimodal Large Language Models have demonstrated impressive video understanding, yet their ability to reason over long-form narratives is often masked by visual-centric evaluations and inefficient c...
arXiv:2608. 09435v1 Announce Type: new Abstract: Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time.
Video-HolmesV2 is a new benchmark that tests multimodal large language models on their ability to reason with spatio‑temporal audio‑visual evidence in long videos. It requires models to justify answers with precise evidence, uses a multi‑model cross‑verification pipeline and a spatio‑temporal evidence‑aware metric, and introduces an audio‑text guided token compression framework to reduce long‑context noise. In evaluations, even strong proprietary models score below 60% while the proposed approach outperforms comparable open‑source omni‑models.
Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time. Yet existing audio-language models often represent clips as global acoustic events, while vision-language models lack the spatial audio cues needed to localize and track individual sources.
Long audio-video reasoning is difficult for omnimodal LLMs because the decisive evidence is often sparse, cross-modal, and too expensive to preserve with uniformly high-fidelity inputs. We introduce OmniReasoner, a tool-use post-training framework for Thinking with Long Audio-Video: omni-modal LLMs learn, via supervised fine-tuning and reinforcement learning, to decide whether and where to call a zoom-in tool before answering.
arXiv:2609.23589v1 Announce Type: cross Abstract: Large audio-language models (LALMs) are increasingly used for a broader range of audio reasoning tasks. These models typically incorporate audio repr...
OmniVChat defines a native audio‑visual dialogue task where models receive raw audio and video from a user and produce text responses, eliminating the need for separate text queries or speech recognition. To address data scarcity and evaluation challenges, the authors introduce OmniVChat‑Studio, a multi‑agent engine that synthesizes single‑ and multi‑turn dialogues, and OmniVChat‑Bench, a benchmark assessing models across five dialogue ability categories. They also propose OmniVChat‑RL, a reinforcement‑learning reward that balances reply correctness, efficiency, and style, and demonstrate that training Qwen3‑Omni‑Instruct with this reward on synthesized data improves performance on both synthetic and human‑recorded benchmarks.
The paper introduces Training-Free Omni (TFO), a plug‑and‑play framework that transforms a frozen vision‑language model (VLM) into a speech‑centric omni model without modifying its architecture or requiring multimodal re‑alignment. TFO leverages Whisper to generate confidence‑filtered, timestamped transcripts and routes them through the VLM’s existing language interface, leaving the visual pathway untouched. Evaluations on 56 benchmarks across 21 languages show that TFO matches or surpasses native omni models on audio‑visual tasks, improves audio‑only performance, and preserves strong visual and reasoning capabilities.