Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
A completely decentralized alternative to the current-day web.
A Framework for LLM-based Multi-Agent Reinforced Training and Inference
SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]
Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.