Wei Liu

lefutonku's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 6 papers 5 days ago

SkVM: Compiling Skills for Efficient Execution Everywhere

Paper • 2604.03088 • Published 28 days ago • 10

GigaWorld-Policy: An Efficient Action-Centered World--Action Model

Paper • 2603.17240 • Published Mar 18 • 26

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Paper • 2604.24764 • Published 7 days ago • 115

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Paper • 2604.24763 • Published 7 days ago • 66

ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning

Paper • 2604.24300 • Published 7 days ago • 64

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

Paper • 2604.22748 • Published 10 days ago • 221

upvoted 5 papers 9 days ago

Vista4D: Video Reshooting with 4D Point Clouds

Paper • 2604.21915 • Published 11 days ago • 12

A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications

Paper • 2503.07137 • Published Mar 10, 2025 • 2

MemOS: A Memory OS for AI System

Paper • 2507.03724 • Published Jul 4, 2025 • 167

DeepSeek-V3 Technical Report

Paper • 2412.19437 • Published Dec 27, 2024 • 84

EasyVideoR1: Easier RL for Video Understanding

Paper • 2604.16893 • Published 16 days ago • 40

upvoted 2 papers 10 days ago

AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model

Paper • 2604.19747 • Published 13 days ago • 38

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

Paper • 2604.20796 • Published 12 days ago • 239

upvoted 7 papers 11 days ago

PersonaVLM: Long-Term Personalized Multimodal LLMs

Paper • 2604.13074 • Published Mar 20 • 45

DFlash: Block Diffusion for Flash Speculative Decoding

Paper • 2602.06036 • Published Feb 5 • 71

Bitnet.cpp: Efficient Edge Inference for Ternary LLMs

Paper • 2502.11880 • Published Feb 17, 2025 • 18

PyTorch Distributed: Experiences on Accelerating Data Parallel Training

Paper • 2006.15704 • Published Jun 28, 2020 • 8

Multi-module GRPO: Composing Policy Gradients and Prompt Optimization for Language Model Programs

Paper • 2508.04660 • Published Aug 6, 2025 • 3

CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation

Paper • 2604.19636 • Published 13 days ago • 87

MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping

Paper • 2604.08364 • Published 25 days ago • 100