• 1
• 0
• 0

FlexPrefill

Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

• 1
• 0
• 0

netobs

Calculate observables from neural network-based VMC (NN-VMC).

• 1
• 1
• 0

fonts

Font files available from ByteDance Fonts

• 1
• 0
• 0

coap

COAP is a memory-efficient training method that reduces computational overhead without sacrificing performance.

• 1
• 1
• 0

Protenix-Dock

An accurate and trainable end-to-end protein-ligand docking framework

• 1
• 4
• 1

arishem

A high performance and lightweight rule engine written by Golang.

• 1
• 0
• 0

Agent-R

• 1
• 0
• 0

1d-tokenizer

This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation

• 1
• 0
• 0

Multi-Reward-Editing

• 2
• 0
• 1

VideoWorld

• 1
• 0
• 0

EchoVideo

• 1
• 0
• 0

StyleSSP

• 1
• 1
• 0

byteff

byteff source code

• 1
• 0
• 0

pysisyphus

Python suite for optimization of stationary points on ground- and excited states PES and determination of reaction paths.

• 1
• 6
• 0

particle-sfm

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild. ECCV 2022.

• 1
• 2
• 2

memory-leak-detector

• 1
• 0
• 0

X-Dyna

[ArXiv 2024] X-Dyna: Expressive Dynamic Human Image Animation

• 1
• 0
• 0

Shot2Story

A new multi-shot video understanding benchmark Shot2Story20K with detailed shot-level captions and comprehensive video summaries.

• 1
• 0
• 0

SchurVINS

• 1
• 0
• 0

Ts_Online_Optimization