Code for paper "Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models".
-
Updated
Sep 28, 2025 - Python
#
omni-modal
Here are 3 public repositories matching this topic...
OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames.
agent reinforcement-learning video-understanding multimodal audio-visual video-question-answering temporal-grounding mllm vision-language-model llm-agent long-video-understanding qwen multimodal-llm icml2026 omni-modal
-
Updated
Jun 18, 2026 - Python
This repo is the official implementation of "Stage-adaptive Token Selection for Efficient Omni-modal LLMs"
efficiency audio-visual mllm token-selection token-compression omni-modal-video-understanding omni-llm omni-modal
-
Updated
Jun 10, 2026 - Python
Improve this page
Add a description, image, and links to the omni-modal topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the omni-modal topic, visit your repo's landing page and select "manage topics."