Yujin Tang

Awesome-Agentic-Time-Series. The paper list of "The Landscape of Agentic Time Series Systems: Architectures, Reliability, and Frontiers."

AMA-Bench. [ICML 26] An evaluation framework assessing long-context retention and long-horizon memory performance for agentic applications (AMA-bench).

mem0. Universal memory layer for AI Agents

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

HippoRAG. [NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.

PlowPilot. TypeScript

PlugMem. ICML 2026 · Plug-and-play long-term memory for LLM agents

alma. ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engineered designs for agentic system.

Awesome-Agent-Memory. [Up-To-Date] [TMLR 2026] Awesome Agent Memory Paper Resource

MemGUI-Bench. [ACM MM 2026] MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments

reasoning-bank-slm. An experiment that applies Google Research's `ReasoningBank` technique to Small Language Models. This experiment hopes to show that the same gains from the ReasoningBank paper also applies to much smaller, less capable models.

Synapse. [ICLR 2024] Trajectory-as-Exemplar Prompting with Memory for Computer Control

agent-workflow-memory. AWM: Agent Workflow Memory

alfworld. ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

webarena. Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"

MemSkill. MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

MPR. The official repository for paper "Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information"

MemoryAgentBench. Open source code for ICLR 2026 Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

visualwebarena. VisualWebArena is a benchmark for multimodal agents.

ai-multi-agent-presentation-builder. Python

LLM_Agent_Memory_Survey.

Mirage. [CVPR 2026] Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens

Huaman-Agent-Memory.

WebShop. [NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents

MemVerse. MemVerse: Multimodal Memory for Lifelong Learning Agents

sft-qwen2.5-omni-thinker. verl: Volcano Engine Reinforcement Learning for LLMs

M3-Agent-Training. Python

ReMe. ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

Agent-Memory-Paper-List. The paper list of "Memory in the Age of AI Agents: A Survey"

VAGEN. World model reasoning RL for multi-turn VLM agents

A-mem. A-MEM: Agentic Memory for LLM Agents

A-mem. The code for NeurIPS 2025 paper "A-Mem: Agentic Memory for LLM Agents"

MemGen. MemGen: Weaving Generative Latent Memory for Self-Evolving Agents

m3-agent. Python

NeurIPS24-Optimus-1. [NeurIPS 2024] Official Implementation for Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks

MWT. Official Repository of End-to-End Implicit Neural Representations for Classification (CVPR 2025)

functa. Python

LinearDiff. Python

test-time-registers. [NeurIPS '25 Spotlight] Official Pytorch implementation of "Vision Transformers Don't Need Trained Registers"

Vit-RGTS. Open source implementation of "Vision Transformers Need Registers"

abxlab. [ICLR'26] A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments

DeepTutor. DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

deit. Official DeiT repository

LLM-Discrete-Tokenization-Survey. [TPAMI 2026] Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey.

Awesome-Token-Compress. A paper list of some recent works about Token Compress for Vit and VLM

Show-o. [ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

ReAct. [ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

PH-Reg. Official code for "Vision Transformers with Self-Distilled Registers" (NeurIPS 2025 Spotlight)

DAP. Official implementation of "Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation".

ShowUI. [CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.

Open-AutoGLM. An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

nepa. PyTorch implementation of NEPA

UnSAM. [NeurIPS 2024] Code release for "Segment Anything without Supervision"

open_clip. An open source implementation of CLIP.

CoVT. [ECCV 2026] Official repo of "Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens"

reconstruction-alignment. [ICLR 2026] Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning.

GUI-Agents-Paper-List. Awesome GUI Agent Paper List

Awesome-GUI-Agent. 💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.

Awesome-3DGS-Applications. 【TPAMI 2026】A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation

GST. Official code of ``2D Gaussians Spatial Transport for Point-supervised Density Regression'' (GST), AAAI 26.

GPSToken. The official code for paper "GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation"

VARC. Python

dinov3. Reference PyTorch implementation and models for DINOv3

lejepa. Python

dHT. Differentiable Hierarchical Visual Tokenization

DeepOCR. A reproduction of the Deepseek-OCR model including training

VLMEvalKit. Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

FOCUS. [ICLR 2026] FOCUS: Efficient Keyframe Selection for Long Video Understanding

Spatial-SSRL. [CVPR 2026] Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"

Awesome-World-Models. A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

VisionSelector. VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs

lmms-engine. A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

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

DeepSeek-OCR. Contexts Optical Compression

LLaVA-OneVision-2. Fully Open Framework for Democratized Multimodal Training

MMVP. Python

NEO. NEO Series: Native Vision-Language Models from First Principles

streaming-vlm. StreamingVLM: Real-Time Understanding for Infinite Video Streams

lm-evaluation-harness. A framework for few-shot evaluation of language models.

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

InternVL. [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

LLaVA-NeXT. Python

cross-modal-information-flow-in-MLLM. This is the official repository for paper: cross-modal information flow in multimodal large language models

LongLive. Long Video Gen Infrastructure

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Keye. Python

MiMo-VL. MiMo-VL

GLM-V. GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

VideoLLaMA3. Frontier Multimodal Foundation Models for Image and Video Understanding

LayerCraft. Official Repo for LayerCraft

lectures. Python

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

LucidFlux. LucidFlux: Caption-Free Photo-Realistic Image Restoration via a Large-Scale Diffusion Transformer, ICLR 2026

RF-Solver-Edit. [🚀ICML 2025] "Taming Rectified Flow for Inversion and Editing" Using FLUX and HunyuanVideo for image and video editing!

KV-Edit. [ICCV 2025] Official implementation for KV-Edit: Training-Free Image Editing for Precise Background Preservation

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

A-Comprehensive-Survey-For-Long-Context-Language-Modeling. A Comprehensive Survey on Long Context Language Modeling

Q-LLM. This is the official repo of "QuickLLaMA: Query-aware Inference Acceleration for Large Language Models"

needle-in-a-haystack. Doing simple retrieval from LLM models at various context lengths to measure accuracy

LLMxMapReduce. Python

Awesome-LLM-Long-Context-Modeling. 📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

RSCP2GAN. Python

slurm-tutorial. SLURM Tutorial

Empirical-Study-of-GPT-4o-Image-Gen. An Empirical Study of GPT-4o Image Generation Capabilities

Janus. Janus-Series: Unified Multimodal Understanding and Generation Models

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models

ICon. ICLR 2025 - official implementation for "I-Con: A Unifying Framework for Representation Learning"

FramePack. Lets make video diffusion practical!

Awesome-VQVAE. A collection of resources and papers on Vector Quantized Variational Autoencoder (VQ-VAE) and its application

Recurrent-Parameter-Generation. The official implementation of Recurrent Diffusion for Large-Scale Parameter Generation.

2d-gaussian-splatting. [SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

Genius. [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework

STC-GS. High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation

Vidu4D. [TPAMI 2025, NeurIPS 2024] Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization

STeP. STeP: a general and scalable framework for solving video inverse problems with spatiotemporal diffusion priors

FAR. Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"

NBP. Official implementation of Next Block Prediction: Video Generation via Semi-Autoregressive Modeling

in-context-learning. Jupyter Notebook

Neural-Network-Diffusion. We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters

VEnhancer. Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

Enhance-A-Video. Enhance-A-Video: Better Generated Video for Free

Dynamic3DGaussians. Python

c3dgs. Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis

Compact-3DGS. The official repository of Compact 3D Gaussian Representation for Radiance Field

3DGS-Benchmarks.

gaussian-splatting. Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

nerf. Code release for NeRF (Neural Radiance Fields)

Awesome-Unified-Multimodal. 📖 This is a repository for organizing papers, codes, and other resources related to unified multimodal models.

DreamScene360. [ECCV 2024] DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting

feature-3dgs. [CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields

Qwen2.5-Omni. Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

Unified-MoE-Compression. The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".

CogVideo. text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

awesome-visual-tokenizer. [WIP🚧] 2025 up-to-date list of resources on visual tokenizers (primarily for visual generation). Give it a star 🌟 if you find it useful.

Awesome-LLM. Awesome-LLM: a curated list of Large Language Model

DreamBooth.github.io. Webpage for DreamBooth

monst3r. Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"

nerfies.github.io. JavaScript

IC-Light. More relighting!

dify. Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

FineParser_CVPR2024. Python

Awesome-Human-Centric-Foundation-Models. Repo for "Human-Centric Foundation Models: Perception, Generation and Agentic Modeling" (https://arxiv.org/abs/2502.08556)

HumanOmni. HumanOmni

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

Sa2VA. Official Repo For Pixel-LLM Codebase: Sa2VA (T-PAMI-26), SAMTok (CVPR-26), VRT (Arxiv-25), SaSaSa2VA (1-st solution for LSVOS)

R-MeeTo. Give us minutes, we give back a faster Mamba. The official implementation of "Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training".

SEED-Voken. SEED-Voken: A Series of Powerful Visual Tokenizers

Autoregressive-Models-in-Vision-Survey. [TMLR 2025🔥] A survey for the autoregressive models in vision.

LLMSurvey. The official GitHub page for the survey paper "A Survey of Large Language Models".

Cosmos-Tokenizer. A suite of image and video neural tokenizers

latex_paper_writing_tips. Tips for Writing a Research Paper using LaTeX

MeToken. Python

awesome-MIT-ai-for-climate-change. 🌍 A curated list of MIT faculty that tackle climate change with machine learning for applying students, undergraduates, or others

Embodied_AI_Paper_List. [Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI

QuadMamba. Official code for [NeurIPS 2024] QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model

Awesome-Prompt-Adapter-Learning-for-VLMs-CLIP. A curated list of awesome prompt/adapter learning methods for vision-language models like CLIP.

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

Awesome-LWMs. A Collection of Awesome Large Weather Models (LWMs) | AI for Earth (AI4Earth) | AI for Science (AI4Science)

Awesome-Scientific-Language-Models. A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (EMNLP'24)

hydra. Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"

alphafold3-pytorch. Implementation of Alphafold 3 from Google Deepmind in Pytorch

x-transformers. A concise but complete full-attention transformer with a set of promising experimental features from various papers

Awesome-Transformer-Attention. An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

Awesome-Visual-Transformer. Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

awesome-3D-gaussian-splatting. Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

LearnTrajDep. code for learning trajectory dependencies for human motion prediction

MambaVision. [CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

OMG-Seg. Official Repo For OMG-LLaVA and OMG-Seg codebase [CVPR-24 and NeurIPS-24]

MG-LLaVA. Official repository for paper MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning(https://arxiv.org/abs/2406.17770).

ttt-lm-pytorch. Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

LLM-Drop. The official implementation of the paper "Uncovering the Redundancy in Transformers via a Unified Study of Layer Dropping (TMLR)".

VidToMe. Official Pytorch Implementation for "VidToMe: Video Token Merging for Zero-Shot Video Editing" (CVPR 2024)

1d-tokenizer. This repo contains the code for 1D tokenizer and generator

Pruner-Zero. [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs

MambaTree. [NeurIPS2024 Spotlight] The official implementation of MambaTree: Tree Topology is All You Need in State Space Model

Vript. Python

caduceus. Bi-Directional Equivariant Long-Range DNA Sequence Modeling

awesome-xlstm. A curated list of xLSTM resources

MLLA. [NeurIPS 2024] Official repository of MLLA

vision-lstm. xLSTM as Generic Vision Backbone

flash-linear-attention. 🚀 Efficient implementations for emerging model architectures

annotated-mamba. Annotated version of the Mamba paper

Latte. [TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation.

Awesome-LLM-Prune. Awesome list for LLM pruning.

awesome-ssm-ml. Reading list for research topics in state-space models

Mamba_State_Space_Model_Paper_List. [Mamba-Survey-2024] Paper list for State-Space-Model/Mamba and it's Applications

awesome-time-series-segmentation-papers. This repository contains a reading list of papers on Time Series Segmentation. This repository is still being continuously improved.

VMamba. VMamba: Visual State Space Models，code is based on mamba

Vim. [ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Vision-Mamba-CIFAR10. Python

PyTorch-VAE. A Collection of Variational Autoencoders (VAE) in PyTorch.

Awesome-LLM-Robotics. A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites

TSFpaper. This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the type of model.

Diffusion. Minimal multi-gpu implementation of Diffusion Models with Classifier-Free Guidance (CFG)

Time-Series-Library. A Library for Advanced Deep Time Series Models for General Time Series Analysis.

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

FontDiffuser. [AAAI2024] FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning

SimpleCVPaperReading. :smile:博客论文列表：分系列整理