Ruizhe Chen

OptimSyn. A framework for influence-guided synthetic data generation through rubric optimization and reinforcement learning.

science-taste-skills. Two-layer Codex-native science taste skills: a persona layer plus a reusable gate.

Awesome-Agent-Environments. Awesome Agent Environments

Qwen-CodePercept. [CVPR2026] CodePercept: Code-Grounded Visual STEM Perception for MLLM

review-prompts. AI review prompts

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Awesome-Video-Agent. A collection of awesome think with videos papers.

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Ego-R1. [TPAMI 2026] Ego-R1: Agentic Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning

Siamese-Diffusion. [CVPR 2025] Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation

LGGPT. [IJCV 2025] Smaller But Better: Unifying Layout Generation with Smaller Large Language Models

SPECTRUM. [ACM MM 2025 Oral] Capturing More: Learning Multi-Domain Representations for Robust Online Handwriting Verification

Awesome-Generative-Models-for-OCR. [arXiv 25] OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities

unary-feedback. Python

TVG-R1. [EMNLP 2025 Industry] Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning

SynCamMaster. [ICLR'25] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

ReCamMaster. [ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

BiasAlert. A Plug-and-play Tool for Social Bias Detection in LLMs. [EMNLP' 24]

Elysium. [ECCV 2024] Elysium: Exploring Object-level Perception in Videos via MLLM

MT-R1-Zero. [EMNLP'25] Code for paper "MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning"

VideoMind. 🧠 VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning (ICLR 2026)

Video-R1. Video-R1: Reinforcing Video Reasoning in MLLMs [🔥the first paper to explore R1 for video]

nano-mdm. Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun

DiffPO. [ACL 2025]

PAD. [ICLR 2025] Pad: Personalized alignment of llms at decoding-time

Awesome-Personalized-LLMs. The latest progress of Personalized Large Language Models (LLMs).

FairMT-bench. Python

samurai. Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)