proomt

Search

Search posts, papers, and topics

All posts

Hugging Face Daily PapersHaolin He, Yunfei Chu, Qi Chen2 min readpaperadvanced

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

Summary

OmniVChat defines native audio‑visual dialogue where a model consumes raw audio and video streams and replies in text. The authors build OmniVChat‑Studio, a multi‑agent simulator that generates single‑ and multi‑turn audio‑visual conversations, and use it to create OmniVChat‑Bench, a benchmark covering five dialogue abilities. They also propose OmniVChat‑RL, a reinforcement‑learning reward that b…

  • Native audio‑visual input removes the need for separate speech‑to‑text or captioning pipelines, reducing latency and preserving perceptual cues.
  • OmniVChat‑Studio synthesizes realistic multi‑modal dialogues using multiple agents, enabling large‑scale data generation where real recordings are scarce.
  • OmniVChat‑Bench evaluates five core abilities (e.g., context understanding, visual grounding, multimodal reasoning) with metrics beyond keyword matching.
  • OmniVChat‑RL reward combines task correctness, response latency, and stylistic quality, and can be applied via RL fine‑tuning of existing LLMs.

The work tackles two practical bottlenecks for multimodal assistants: lack of large, high‑quality audio‑visual dialogue data and reliable evaluation metrics. By providing a scalable data synthesis pipeline and a benchmark that captures nuanced multimodal reasoning, the paper offers a reproducible f…

7/10

Related reading

  1. OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning

    OmniHarness introduces a symbolic‑policy framework that extracts reusable procedural knowledge from multimodal LLM‑driven visual generation runs. By decoupling task logic from instance inputs, the system can instantiate, adapt, and compose policies for new visual tasks, using intermediate verification for on‑the‑fly refinement while keeping the underlying model frozen. Self‑directed practice task…

    Hugging Face Daily Papersarxiv.org1 minpaper
  2. CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

    CodeMidas builds RL environments directly from open‑source code: agents explore a repo, infer a spec, generate tests from the original implementation, and filter tasks via execution checks. The pipeline yields 5,545 high‑quality coding tasks across 23 languages and 15 domains. Training the MiMo‑V2.5 agent with GRPO on this dataset improves benchmark scores by 8‑18% (e.g., DeepSWE +11.7%, ProgramB…

    Hugging Face Daily Papersarxiv.org1 minpaper
  3. OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation

    OmniVBench is a new benchmark and the Omni‑R2V Dataset, offering 7 task families, 18 fine‑grained reference‑to‑video generation tasks and a factor‑grounded evaluation checklist of over 12 k items. The dataset provides 340 k industrial‑grade video samples and pipelines for constructing reference‑target pairs, exposing large performance gaps in current R2V models.

    Hugging Face Daily Papersarxiv.org2 minpaper
  4. HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness

    HarnessVLN introduces a zero‑shot, training‑free embodied navigation framework that wraps a multimodal LLM in an "Agent Harness" – a tool‑based protocol that validates planner actions against spatial evidence, tracks progress with hierarchical event memory, and maintains a persistent spatiotemporal graph for recovery. The system works for instruction‑following and object‑goal tasks, achieving 60.…

    Hugging Face Daily Papersarxiv.org1 minpaper
  5. In-Context Robot Learning with VLM Agents

    GPT‑Policy is a framework that lets a large vision‑language model (e.g. GPT‑6 Astra) perform in‑context robot learning: a context compiler extracts visual transitions from demos, the VLM proposes tool actions, and a constrained controller verifies and executes them. Real‑robot experiments show that raw video demos improve success rates even without explicit action labels, and that providing align…

    Hugging Face Daily Papersarxiv.org1 minpaper