Xinyan Chen

OpenCoF. OpenCoF: Learning to Reason Through Video Generation

UGR. [KDD'26] Uncertainty-aware Generative Recommendation

PolicyAlign. Python

ATLAS. One Discrete Word for Visual Reasoning Overtakes Agentic and Latent Methods

Flow-Factory. A unified framework for easy reinforcement learning in Flow-Matching models

Thinking-while-Generating. The first Interleaved framework for textual reasoning within the visual generation process

MME-CoF. Are Video Models Ready as Zero-shot Reasoners?

USTC-Course-Materials-Sharing. This repository shares undergraduate course materials for the Electronic Information Engineering program at the University of Science and Technology of China (USTC).

3D-GSRD. [NeurIPS 2025] 3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding

zotero-arxiv-daily. Recommend new arxiv papers of your interest daily according to your Zotero libarary.

VisionThink. [NeurIPS 2025] Efficient Reasoning Vision Language Models

MINT-CoT. [NeurIPS 2025] MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning

mathverse-cuhk.github.io. JavaScript

T2I-R1. [NeurIPS 2025] T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

EasyR1. EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Awesome-LLM-Strawberry. A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

awesome-LLM-resources. 🧑‍🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

EmpathyAgent. Python

MME-CoT. MME-CoT: Benchmarking Chain-of-Thought in LMMs for Reasoning Quality, Robustness, and Efficiency

Image-Generation-CoT. [CVPR 2025] The First Investigation of CoT Reasoning (RL, TTS, Reflection) in Image Generation

SOTA-paper-rating.io. A tiny paper rating web

AutoPresent. Code for the paper "AutoPresent: Designing Structured Visuals From Scratch" (CVPR 2025)

DeTikZify. Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ.

VisionZip. Official repository for VisionZip (CVPR 2025)

IPR-RLDF. Python

ProSA. [EMNLP 2024 Findings] ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs

learning_research. 本人的科研经验

guided-diffusion. Python

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.