[NeurIPS 2025 Spotlight] StreamForest: Efficient Online Video Understanding with Persistent Event Memory

This repo contains evaluation code for the paper "MileBench: Benchmarking MLLMs in Long Context"

🔥🔥First-ever hour scale video understanding models

A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

[ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding

Free ChatGPT&DeepSeek API Key，免费ChatGPT&DeepSeek API。免费接入DeepSeek API和GPT4 API，支持 gpt | deepseek | claude | gemini | grok 等排名靠前的常用大模型。

Official repository of MMDU dataset

Code of "MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation"

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

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)

A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

A curated list of large VLM-based VLA models for robotic manipulation.

A Self-Training Framework for Vision-Language Reasoning

[ICML 2024] Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning

CVPR2024: Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models

This repository introduce a comprehensive paper list, datasets, methods and tools for memory research.

Official PyTorch Code for Anchor Token Guided Prompt Learning Methods: [ICCV 2025] ATPrompt and [Arxiv 2511.21188] AnchorOPT

This is the official code repository for the paper: Towards General Continuous Memory for Vision-Language Models.

LongBench v2 and LongBench (ACL 25'&24')

Official PyTorch Implementation of EMoE: Unlocking Emergent Modularity in Large Language Models [main conference @ NAACL2024]

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

Retrieval and Retrieval-augmented LLMs

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

Doing simple retrieval from LLM models at various context lengths to measure accuracy

StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses (NeurIPS 2024)