4.4k citations
- Tsinghua UniversityCN71 papers
- Peking UniversityCN66 papers
- Shanghai Jiao Tong UniversityCN61 papers
- Zhejiang UniversityCN50 papers
- Chinese Academy of SciencesCN44 papers
- Hong Kong University of Science and TechnologyHK43 papers
- University of Science and Technology of ChinaCN41 papers
- Southern University of Science and TechnologyCN35 papers
- Huawei Technologies (Canada)CA34 papers
- Chinese University of Hong KongHK33 papers
- University of Hong KongHK31 papers
- Renmin University of ChinaCN29 papers
49 papers · 1 filter
Animus3D: Text-driven 3D Animation via Motion Score Distillation
Qi Sun, Can Wang, Jiaxiang Shang +2
We present Animus3D, a text-driven 3D animation framework that generates motion field given a static 3D asset and text prompt. Previous methods mostly leverage the vanilla Score Di…
Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models
Dayan Pan, Zhaoyang Fu, Jingyuan Wang +3
Large Language Models (LLMs) possess remarkable generalization capabilities but struggle with multi-task adaptation, particularly in balancing knowledge retention with task-specifi…
CHORD: Customizing Hybrid-precision On-device Model for Sequential Recommendation with Device-cloud Collaboration
Tianqi Liu, Kairui Fu, Shengyu Zhang +5
With the advancement of mobile device capabilities, deploying reranking models directly on devices has become feasible, enabling real-time contextual recommendations. When migratin…
ElasticMoE: An Efficient Auto Scaling Method for Mixture-of-Experts Models
Gursimran Singh, Timothy Yu, Haley Li +7
Mixture-of-Experts (MoE) models promise efficient scaling of large language models (LLMs) by activating only a small subset of experts per token, but their parallelized inference p…
DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework
Boyan Li, Chong Chen, Zhujun Xue +2
Large language models (LLMs) have advanced Text-to-SQL, yet existing solutions still fall short of system-level reliability. The limitation is not merely in individual modules -- e…
RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning
Jinrui Liu, Bingyan Nie, Boyu Li +4
Improving the reasoning capabilities of embodied agents is crucial for robots to complete complex human instructions in long-view manipulation tasks successfully. Despite the succe…