GLM-ASR-Nano: A robust, open-source speech recognition model with 1.5B parameters

HunyuanVideo-1.5: A leading lightweight video generation model

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

MiroThinker is open-source agentic models trained for deep research and complex tool use scenarios.

Cook up amazing multimodal AI applications effortlessly with MiniCPM-o

Lidar Localization and Mapping

Minimal reproduction of OneRec

The implementations of paper "Reinforced Preference Optimization for Recommendation" (ReRe).

OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.

Ollama client for iOS, Android, macOS, and Windows that simplifies experimenting with LLMs.

An official implementation of "CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning"

Dexbotic: Open-Source Vision-Language-Action Toolbox

Official implementation of Falcon-TST

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

The absolute trainer to light up AI agents.

Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model

[NeurIPS 2025] Jasmine: Harnessing Diffusion Prior for Self-Supervised Depth Estimation

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

Developed a dynamic pricing model for a ride-sharing service to optimize fares in real-time. Conducted data analysis, engineered supply-demand features, implemented a rule-based strategy, and built…

GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.

Official Repo of "SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization"