TIGER-AI-Lab

Official Repo for "TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding" [ACL 2025 oral]

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

Open-source benchmark for browser AI agents on daily tasks.

A version of verl to support diverse tool use [TMLR 2026]

This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]

Code and data for "AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks" [TMLR 2024]

The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark" [NeurIPS 2024]

Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" [ICLR 2024]

official repo for "VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation" [EMNLP2024]

Data and Code for Program of Thoughts [TMLR 2023]

Pixel-Level Reasoning Model trained with RL [NeuIPS25]

ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation [TMLR 2024]

ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations [COLM 2025]

Official repo for "LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs".

Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024 Best Paper]

General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]

Can AI agents rebuild websites through browser exploration?

The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]

Official code for paper "UniIR: Training and Benchmarking Universal Multimodal Information Retrievers" (ECCV 2024)

A one-stop library to standardize the inference and evaluation of all the conditional image generation models. [ICLR 2024]

Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing [ICLR 2026]

Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]

Official Repo for Paper "OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision" [ICLR2025]

Context Forcing: Consistent Autoregressive Video Generation with Long Context [ICML26]

Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]

Code for the paper "Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers" [ICCV 2025]

Self-evolving agentic reward framework for image-editing evaluation — 47.4% on EditReward-Bench from only 100 preference demos, no reward-model training. arXiv 2605.08703.

The official repo for "AceCoder: Acing Coder RL via Automated Test-Case Synthesis" [ACL25]

LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis

This repo contains the code for "MEGA-Bench Scaling Multimodal Evaluation to over 500 Real-World Tasks" [ICLR 2025]

Quick Long Video Understanding [TMLR2025]

Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding" (COLM 2024)

Visual Instruction-guided Explainable Metric. Code for "Towards Explainable Metrics for Conditional Image Synthesis Evaluation" (ACL 2024)

"Few-shot In-context Learning for Knowledge Base Question Answering" [ACL2023]

Automatic Metric for Evaluating Generated Videos

RationalRewards: a reasoning reward model for diffusion RL and test-time prompt tuning

A one-stop library to standardize the inference and evaluation of all the conditional video generation models.