Ziyang Wang

EgoMemReason. Python

m3docrag. Python

EgoLife. [CVPR 2025] EgoLife: Towards Egocentric Life Assistant

ActiveVideoPerception. Official Code for paper "Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding""

TOMATO. Python

DeepVideoDiscovery. **Deep Video Discovery (DVD)** is a deep-research style question answering agent designed for understanding extra-long videos.

Awesome-Video-LMM-Post-Training. 🔥🔥🔥 Latest Papers, Codes and Datasets on Video-LMM Post-Training

VerIPO. Long-Reasoning Video-R1 Model with Iterative Policy Optimization

rsq. Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"

Long-RL. Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

Video-Holmes. [ECCV 2026] Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?

Video-RTS. Code for EMNLP25 paper "Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning"

SILVR. Official Implementation for "SiLVR : A Simple Language-based Video Reasoning Framework"

LaCT. Code release for paper "Test-Time Training Done Right"

pdf-ocr-processor. A powerful PDF processing tool that uses Mistral AI's OCR capabilities to extract text and images from PDF documents. Features include batch processing, automatic PDF splitting for large files, and organized output structure. Perfect for document digitization and content extraction.

M3D. M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models

LLaVA-Med. Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

OpenVLThinker. OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement

MAgICoRE. Python

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

R1-Video-fixbug. [Blog 1] Recording a bug of grpo_trainer in some R1 projects

Open-R1-Video. ✨First Open-Source R1-like Video-LLM [2025/02/18]

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

OpenRLHF. An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

LLaVA-NeXT. Python

PruneVid. [ACL 2025] PruneVid: Visual Token Pruning for Efficient Video Large Language Models

vid-TLDR. Official implementation of CVPR 2024 paper "vid-TLDR: Training Free Token merging for Light-weight Video Transformer".

video-ReTaKe. Official implementation of paper ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding

VideoRepair. Code for "VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement [ACL 2026 Findings]"

VL-T5. PyTorch code for "Unifying Vision-and-Language Tasks via Text Generation" (ICML 2021)

VL_adapter. PyTorch code for "VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks" (CVPR2022)

LongVU. [ICML 2025] Official PyTorch implementation of LongVU

ZiyangW2000.github.io. SCSS

tvbench. TVBench: Redesigning Video-Language Evaluation

Grounded-SAM-2. Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

VTimeLLM. [CVPR'2024 Highlight] Official PyTorch implementation of the paper "VTimeLLM: Empower LLM to Grasp Video Moments".

EgoSchema. Python

lmms-eval. One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

LongLLaVA. LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture

LongMamba. Some preliminary explorations of Mamba's context scaling.

VideoLLaMB. [ICCV 2025] Official Repository of VideoLLaMB: Long Video Understanding with Recurrent Memory Bridges

HERMES. [ICCV'25] HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics

VideoTree. Playground Code for paper "VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos"

Flash-VStream. This is the official implementation of ICCV 2025 "Flash-VStream: Efficient Real-Time Understanding for Long Video Streams"

ToMe. A method to increase the speed and lower the memory footprint of existing vision transformers.

LongVA. Long Context Transfer from Language to Vision

Video-MME. ✨✨[CVPR 2025] Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Ctrl-Adapter. Official implementation of Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model (ICLR 2025 Oral)

EasyContext. Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

LongVideoBench. [Neurips 24' D&B] Official Dataloader and Evaluation Scripts for LongVideoBench.

LLoVi. Official implementation for "A Simple LLM Framework for Long-Range Video Question-Answering"

VideoAgent. Python

TimeSformer. The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"

X-CLIP. An official implementation for "X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval"

Awesome_Long_Form_Video_Understanding. Awesome papers & datasets specifically focused on long-term videos.

FrozenBiLM. [NeurIPS 2022] Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

DiagrammerGPT. Official code repository for: DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning (COLM 2024)

NExT-QA. NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR'21)

MC-ViT. Implementation of the model: "(MC-ViT)" from the paper: "Memory Consolidation Enables Long-Context Video Understanding"

MAGDi. The code implementation of MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models. Paper: https://arxiv.org/abs/2402.01620

soft_self_consistency. Code for ACL 2024 paper "Soft Self-Consistency Improves Language Model Agents"

crg. PyTorch code for "Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training"

CREMA. [ICLR 2025] CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion

RACCooN. (EMNLP 2025 Main) RACCooN: A Versatile Instructional Video Editing Framework with Auto-Generated Narratives

VideoTree. Code for CVPR25 paper "VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos"

open-eqa. OpenEQA Embodied Question Answering in the Era of Foundation Models

ReConcile. Python

lifelong-memory. Code for LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos

VideoRecap. Python

DAM. Official code for DAM: Dynamic Adapter Merging for Continual Video QA Learning

Awesome-LLMs-for-Video-Understanding. 🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.

qaego4d. Code and Dataset for the CVPRW Paper "Where did I leave my keys? — Episodic-Memory-Based Question Answering on Egocentric Videos"

LLoVi. Official implementation for "A Simple LLM Framework for Long-Range Video Question-Answering"

DoraemonGPT. Official repository of DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models

Video-ChatGPT. [ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.

DAPM. A Pytorch implementation of Diffusion-Based Probabilistic Uncertainty Estimation for Active Domain Adaptation

PDVC. End-to-End Dense Video Captioning with Parallel Decoding (ICCV 2021)

VidChapters. [NeurIPS 2023 D&B] VidChapters-7M: Video Chapters at Scale

fromage. 🧀 Code and models for the ICML 2023 paper "Grounding Language Models to Images for Multimodal Inputs and Outputs".

VideoDirectorGPT. official implementation of VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning (COLM 2024)

VPGen. Visual Programming for Text-to-Image Generation and Evaluation (NeurIPS 2023)

VPEval. VPEval Codebase from Visual Programming for Text-to-Image Generation and Evaluation (NeurIPS 2023)

CLIP4Clip. An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

ICCV-2023-25-Papers. ICCV 2023-2025 Papers: Discover cutting-edge research from ICCV 2023-25, the leading computer vision conference. Stay updated on the latest in computer vision and deep learning, with code included. ⭐ support visual intelligence development!

UCoFiA. Pytorch Code for "Unified Coarse-to-Fine Alignment for Video-Text Retrieval" (ICCV 2023)

l2p-pytorch. PyTorch Implementation of Learning to Prompt (L2P) for Continual Learning @ CVPR22

ai-deadlines. :alarm_clock: AI conference deadline countdowns

CODA-Prompt. PyTorch code for the CVPR'23 paper: "CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning"

MoPRL. [TCSVT] Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection

SeViLA. [NeurIPS 2023] Self-Chained Image-Language Model for Video Localization and Question Answering

champagne. An official codebase for paper ":champagne: CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos (ICCV 23)"

gill. 🐟 Code and models for the NeurIPS 2023 paper "Generating Images with Multimodal Language Models".

CAMoE. Python

VidIL. Pytorch code for Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

VindLU. Python

ts2_net. [ECCV 2022] A pytorch implementation for TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval

Cross-Modal-Adapter. [Pattern Recognition 2025] Cross-Modal Adapter for Vision-Language Retrieval

A-InfoNCE. [ECCV 2022] "Adversarial Contrastive Learning via Asymmetric InfoNCE"