Lists (15)
Stars
Enjoy the magic of Diffusion models!
slime is an LLM post-training framework for RL Scaling.
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & TIS & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…
A curated collection of papers, datasets, and resources on Scientific Datasets and Large Language Models (LLMs)
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
🤖 24/7 AI agent that maximizes Claude Code Pro usage via Slack. Auto-processes tasks, manages isolated workspaces, creates Git commits/PRs, and optimizes day/night usage thresholds.
Cambrian-S: Towards Spatial Supersensing in Video
Benchmarking Multi-Step Spatial Reasoning in MLLMs with LEGO-based VQA & generation tasks.
Official Competition Toolkit for The 2025 RoboSense Challenge
OCR model that handles complex tables, forms, handwriting with full layout.
TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics
Krea Realtime 14B. An open-source realtime AI video model.
Native Multimodal Models are World Learners
"AI-Trader: Can AI Beat the Market?" Live Trading Bench: https://ai4trade.ai Tech Report Link: https://arxiv.org/abs/2512.10971
Search Self-Play: Pushing the Frontier of Agent Capability without Supervision
The loss landscape of Large Language Models resemble basin!
Official Implementation of Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution
Collects papers on autonomous driving E2E learning and VLM/VLA, with organized research branches and trends in these fields.
Official PyTorch code for ICLR 2025 paper "Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Models"
Code for ACL 2025 Main paper "Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning".