OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning
Paper • 2609.39490 • Published • 27
Huang Jie
JadeHuang
AI & ML interests
Multi-Modal LLMs, Agentic AI, Embodied AI and Psychology
Recent Activity
published a dataset 1 day ago
PKU-VaLuE-Lab/EmbodiedCLBench-Native-Harnesses published a dataset 1 day ago
PKU-VaLuE-Lab/EmbodiedCLBench updated a dataset 1 day ago
PKU-VaLuE-Lab/EmbodiedCLBenchOrganizations
upvoted a paper 4 days ago
upvoted a paper 16 days ago
upvoted 3
papers 4 months ago
MMAE: A Massive Multitask Audio Editing Benchmark
Paper • 2606.07229 • Published • 46
VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
Paper • 2606.05259 • Published • 40
M^3Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks
Paper • 2606.05008 • Published • 26
upvoted 4
papers 5 months ago
Language Models Need Sleep
Paper • 2605.26099 • Published • 13
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 268
Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening
Paper • 2502.04903 • Published • 2
TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
Paper • 2605.22355 • Published • 128