Code to load DreamZero model checkpoints and run evaluation on DROID-sim and Genie Sim 3.0

[ICLR'25] Official code for the paper 'MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs'

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

Reinforcement Learning via Self-Distillation (SDPO)

Official PyTorch implementation of One-Minute Video Generation with Test-Time Training

[ICLR 2026] Glance and Focus Reinforcement for Pan-cancer Screening

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Wanna breeze through some papers?

Merlin is a 3D VLM for computed tomography that leverages both structured electronic health records (EHR) and unstructured radiology reports for pretraining.

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

Official codebase for the paper Latent Visual Reasoning

Official JAX implementation of End-to-End Test-Time Training for Long Context

Repo for "Adaptation of Agentic AI"

MemVerse: Multimodal Memory for Lifelong Learning Agents

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

[Medical_NLP ➟ Awesome-AI4Med] medical-related LLMs, Multimodal systems, Datasets, Benchmarks, and more.

这是一份入门AI/LLM大模型的逐步指南，包含教程和演示代码，带你从API走进本地大模型部署和微调，代码文件会提供Kaggle或Colab在线版本，即便没有显卡也可以进行学习。项目中还开设了一个小型的代码游乐场🎡，你可以尝试在里面实验一些有意思的AI脚本。同时，包含李宏毅 (HUNG-YI LEE）2024生成式人工智能导论课程的完整中文镜像作业。

SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

Videodl: A lightweight video downloader written in pure python. (轻量级视频下载器，优先高清无水印，支持抖音，快手，小红书，B站，TikTok，YouTube，FIFA+，优酷，腾讯，爱奇艺，1905电影网，乐视，芒果，咪咕，PPTV，搜狐，Facebook，Twitter，新浪微博，今日头条，网易公开课，全民K歌，CCTV央视…

nnMIL: A generalizable multiple instance learning framework for computational pathology