Agent-to-Sim Learning Interactive Behavior from Casual Videos.

More relighting!

Large Concept Models: Language modeling in a sentence representation space

Code for BLT research paper

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Extended LaTeX template for CVPR/ICCV papers

Bringing BERT into modernity via both architecture changes and scaling

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

Holistic Adaptation of SAM from 2D to 3D for Promptable Medical Image Segmentation

[CVPR 2024 Extension] 160K volumes (42M slices) datasets, new segmentation datasets, 31M-1.2B pre-trained models, various pre-training recipes, 50+ downstream tasks implementation

Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline

Let's finetune video generation models!

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

Optimizing inference proxy for LLMs

Unified KV Cache Compression Methods for Auto-Regressive Models

Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"

Official implementation of the paper "Watermark Anything with Localized Messages"

🙌 OpenHands: Code Less, Make More

Domain-Controlled Prompt Learning （AAAI2024）

A pre-built agent for TableGPT2.

Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"

AlphaFold 3 inference pipeline.

Large Reasoning Models

The repository for the paper titled "Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks"