Inspect: A framework for large language model evaluations

Secure, high-performance AI infrastructure in Python.

ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation

Towards Human-Sounding Speech

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

RoboBrain 2.0: Advanced version of RoboBrain. See Better. Think Harder. Do Smarter. 🎉🎉🎉

Empowering RAG with a memory-based data interface for all-purpose applications!

📰 Must-read papers on KV Cache Compression (constantly updating 🤗).

[ICML 2025] FreeMesh: Boosting Mesh Generation with Coordinates Merging

EFFOcc: A Minimal Baseline for EFficient Fusion-based 3D Occupancy Network

Textbook on reinforcement learning from human feedback

🔥🔥First-ever hour scale video understanding models

Image Deblurring using Generative Adversarial Networks

Open-source unified multimodal model

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

An MIT License of YOLOv9, YOLOv7, YOLO-RD

🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

🦀 Low-level 3D Computer Vision library in Rust

Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents

R-KV: Redundancy-aware KV Cache Compression for Reasoning Models

SkyReels V1: The first and most advanced open-source human-centric video foundation model

Skywork-R1V2:Multimodal Hybrid Reinforcement Learning for Reasoning

SkyReels-V2: Infinite-length Film Generative model

Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]

[CVPR 2025] Concept Bottleneck Autoencoder (CB-AE) -- efficiently transform any pretrained (black-box) image generative model into an interpretable generative concept bottleneck model (CBM) with mi…