An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

(ICLR 2026)Official repository of 'ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing’

[NeurIPS 2025] Official implementation of HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance

[ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incen…

CYaRon: Yet Another Random Olympic-iNformatics test data generator

[NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS

[ICCV 2025] MM-IFEngine: Towards Multimodal Instruction Following

Scalable RL solution for advanced reasoning of language models

MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Train transformer language models with reinforcement learning.

This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs!

Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’

[ICML 2025] SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation

[ICCV 2025] Light-A-Video: Training-free Video Relighting via Progressive Light Fusion

[ICML 2025 Oral] An official implementation of VideoRoPE & VideoRoPE++

official code for "BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning"

📖 A curated list of resources dedicated to hallucination of multimodal large language models (MLLM).

Next-Token Prediction is All You Need

[ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality

Official implement of MIA-DPO

(CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

[NeurIPS 2024] Official PyTorch implementation of LoTLIP: Improving Language-Image Pre-training for Long Text Understanding

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

[CVPR 2025] Official implementation of ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality in a Training-free Way

Code for paper "Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models"

[ICCV-2025] Official implementation of Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data

[ICCV 2025] The official code of the paper "Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate".