[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks
Hongxing Li์ด [arXiv]์ ๊ฒ์ํ โOmniEAR: Benchmarking Agent Reasoning in Embodied Tasksโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.
Recent Posts
[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation
Xiaokun Feng์ด [arXiv]์ ๊ฒ์ํ โOmni-Effects: Unified and Spatially-Controllable Visual Effects Generationโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.
[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] MolmoAct: Action Reasoning Models that can Reason in Space
Shuo Liu์ด [arXiv]์ ๊ฒ์ํ โMolmoAct: Action Reasoning Models that can Reason in Spaceโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.
[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs
Jianguo Li์ด [arXiv]์ ๊ฒ์ํ โMoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMsโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.
[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning
Baihong Yuan์ด [arXiv]์ ๊ฒ์ํ โLess Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoningโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.