TIGER Lab

All

56 repositories

VLM2Vec
Public
This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR 2025]
benchmark representation-learning image-retrieval
benchmark representation-learning image-retrieval embedding vlm multimodal rag video-retrieval contrastive-learning mmeb
Python
•
Apache License 2.0
•51•588•25•0•Updated Mar 9, 2026Mar 9, 2026
ImagenWorld
Public
Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks [ICLR 2026]
image generation genai
image generation genai
Python
•
MIT License
•0•27•0•0•Updated Mar 8, 2026Mar 8, 2026
verl-tool
Public
A version of verl to support diverse tool use
agent learning reinforcement
agent learning reinforcement llm
Python
•
MIT License
•75•901•6•0•Updated Mar 2, 2026Mar 2, 2026
OpenResearcher
Public
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
retrieval llm deep-research
retrieval llm deep-research
Python
•45•418•0•0•Updated Feb 27, 2026Feb 27, 2026
VisPhyWorld
Public
VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction
Python
•
MIT License
•0•5•0•0•Updated Feb 25, 2026Feb 25, 2026
MMLU-Pro
Public
The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark" [NeurIPS 2024]
evaluation llm
evaluation llm
Python
•
Apache License 2.0
•54•346•8•0•Updated Feb 20, 2026Feb 20, 2026
EditReward
Public
EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing [ICLR 2026]
evaluation editing diffusion
evaluation editing diffusion
Python
•
MIT License
•4•129•4•0•Updated Feb 6, 2026Feb 6, 2026
Context-Forcing
Public
Consistent Autoregressive Video Generation with Long Context
2•74•2•0•Updated Feb 6, 2026Feb 6, 2026
VisualWebInstruct
Public
The official repo for "VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search" [EMNLP25]
vlm llm
vlm llm
Python
•
MIT License
•1•38•0•0•Updated Feb 1, 2026Feb 1, 2026
VisCoder2
Public
The official code of "VisCoder2: Building Multi-Language Visualization Coding Agents" [ICLR26]
visualization coder llm
visualization coder llm
Python
•0•9•0•0•Updated Jan 28, 2026Jan 28, 2026
BrowserAgent
Public
BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions [TMLR2025]
agent browser llm
agent browser llm
Python
•
MIT License
•3•29•0•0•Updated Jan 13, 2026Jan 13, 2026
StructEval
Public
Evaluating LLMs' abilities to generate structural output [TMLR2025]
benchmark structure evaluation
benchmark structure evaluation
Python
•
Apache License 2.0
•5•22•1•1•Updated Jan 13, 2026Jan 13, 2026
Mantis
Public
Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024 Best Paper]
language video vision
language video vision mantis vlm multimodal lmm fuyu mllm llava-llama3
Python
•
Apache License 2.0
•22•240•4•1•Updated Jan 3, 2026Jan 3, 2026
VideoScore2
Public
Automatic Metric for Evaluating Generated Videos
videos vlm llm
videos vlm llm
Python
•
MIT License
•1•33•5•0•Updated Dec 8, 2025Dec 8, 2025
VideoScore
Public
official repo for "VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation" [EMNLP2024]
language machine-learning
language machine-learning
Python
•
MIT License
•5•113•3•0•Updated Dec 4, 2025Dec 4, 2025
ImagenHub
Public
A one-stop library to standardize the inference and evaluation of all the conditional image generation models. [ICLR 2024]
deep-learning pytorch image-editing
deep-learning pytorch image-editing generative-art image-generation diffusion-models stable-diffusion generative-ai
Python
•
MIT License
•19•178•2•0•Updated Dec 2, 2025Dec 2, 2025
General-Reasoner
Public
General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]
rl reasoning llm
rl reasoning llm
Python
•13•222•2•0•Updated Nov 27, 2025Nov 27, 2025
Pixel-Reasoner
Public
Pixel-Level Reasoning Model trained with RL [NeuIPS25]
reasoning multimodal llm
reasoning multimodal llm
Python
•
MIT License
•11•281•4•0•Updated Nov 6, 2025Nov 6, 2025
QuickCodec
Public
A More Efficient Video Codec
video codec
video codec
Cython
•
BSD 3-Clause "New" or "Revised" License
•0•8•0•0•Updated Nov 2, 2025Nov 2, 2025
QuickVideo
Public
Quick Long Video Understanding [TMLR2025]
video multimodal-learning multimodal
video multimodal-learning multimodal llm
Python
•
MIT License
•6•76•2•0•Updated Oct 27, 2025Oct 27, 2025
Hierarchical-Reasoner
Public
Emergent Hierarchical Reasoning in LLMs/VLMs through Reinforcement Learning
rl reasoning llm
rl reasoning llm
Python
•
MIT License
•3•62•0•0•Updated Oct 24, 2025Oct 24, 2025
Critique-Coder
Public
Training Coder Models with Critique Reinforcement Learning
coder rl llm
coder rl llm
Python
•
MIT License
•0•14•0•0•Updated Oct 1, 2025Oct 1, 2025
VideoEval-Pro
Public
More reliable Video Understanding Evaluation
video evaluation understanding
video evaluation understanding multimodal
Python
•0•14•0•0•Updated Sep 23, 2025Sep 23, 2025
VisCoder
Public
The official code of "VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation" [EMNLP25]
visualization coder llm
visualization coder llm
Python
•
Apache License 2.0
•2•17•0•0•Updated Sep 21, 2025Sep 21, 2025
PixelWorld
Public
The official code of "PixelWorld: Towards Perceiving Everything as Pixels" [TMLR25]
vlm llm
vlm llm
Python
•1•16•1•0•Updated Sep 12, 2025Sep 12, 2025
One-Shot-CFT
Public
The official repo for “Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem” [EMNLP25]
lm critique reasoning
lm critique reasoning
Python
•
Apache License 2.0
•5•34•0•0•Updated Sep 1, 2025Sep 1, 2025
ABC
Public
ABC: Achieving Better Control of Multimodal Embeddings using VLMs [TMLR2025]
information-retrieval multimodal
information-retrieval multimodal
Python
•
MIT License
•2•21•0•0•Updated Aug 21, 2025Aug 21, 2025
Vamba
Public
Code for the paper "Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers" [ICCV 2025]
video vlm llm
video vlm llm
Python
•
MIT License
•11•101•2•0•Updated Jul 28, 2025Jul 28, 2025
TheoremExplainAgent
Public
Official Repo for "TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding" [ACL 2025 oral]
rag manim manim-animations
rag manim manim-animations llm-agents manim-video
Python
•
MIT License
•194•1.5k•9•1•Updated Jul 27, 2025Jul 27, 2025
CritiqueFineTuning
Public
Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]
fine-tuning languagemodel
fine-tuning languagemodel
Python
•
MIT License
•8•180•3•0•Updated Jul 8, 2025Jul 8, 2025