Stars
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!
[ICML 2025] Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
[KDD 2026] Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?
PyTorch implementation of JiT https://arxiv.org/abs/2511.13720
Running VLA at 30Hz frame rate and 480Hz trajectory frequency
A simple state update rule to enhance length generalization for CUT3R
SGLang is a high-performance serving framework for large language models and multimodal models.
Offical Pytorch Implementation of CVPR2025 GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation
[AAAI-25] Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning.
[CVPR 2025] Code for Segment Any Motion in Videos
[CVPR'25] UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image
[ECCV 2024] LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation
ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation
Visualizing the network of math theories.
ROS package to find a rigid-body transformation between a LiDAR and a camera for "LiDAR-Camera Calibration using 3D-3D Point correspondences"
Automatic Extrinsic Calibration for LiDAR and Camera in Targetless Environments Based on Multi-Feature Edge in One-shot
Learning-based localizability estimation for robust LiDAR localization.
INS-Centric Visual-Inertial Navigation System With LiDAR Enhancement
IMU + X(GNSS, 6DoF Odom) Loosely-Coupled Fusion Localization based on ESKF, IEKF, UKF(UKF/SPKF, JUKF, SVD-UKF) and MAP