Wei Liu

lefutonku's activity

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

upvoted 3 papers 6 days ago

Few-Step Distillation for Text-to-Image Generation: A Practical Guide

Paper • 2512.13006 • Published 12 days ago • 7

RF-DETR: Neural Architecture Search for Real-Time Detection Transformers

Paper • 2511.09554 • Published Nov 12 • 7

Next-Embedding Prediction Makes Strong Vision Learners

Paper • 2512.16922 • Published 9 days ago • 79

upvoted 2 papers 7 days ago

WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

Paper • 2512.14614 • Published 11 days ago • 64

In Pursuit of Pixel Supervision for Visual Pre-training

Paper • 2512.15715 • Published 10 days ago • 8

upvoted 2 papers 8 days ago

DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

Paper • 2512.15713 • Published 10 days ago • 15

EgoX: Egocentric Video Generation from a Single Exocentric Video

Paper • 2512.08269 • Published 18 days ago • 111

upvoted 7 papers 10 days ago

E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training

Paper • 2512.10950 • Published 16 days ago • 1

Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

Paper • 2512.11130 • Published 16 days ago • 4

Soft Adaptive Policy Optimization

Paper • 2511.20347 • Published Nov 25 • 41

LitePT: Lighter Yet Stronger Point Transformer

Paper • 2512.13689 • Published 12 days ago • 6

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Paper • 2509.22186 • Published Sep 26 • 139

Memory in the Age of AI Agents

Paper • 2512.13564 • Published 12 days ago • 112

Towards Scalable Pre-training of Visual Tokenizers for Generation

Paper • 2512.13687 • Published 12 days ago • 96

upvoted a paper 16 days ago

From Pixels to Words -- Towards Native Vision-Language Primitives at Scale

Paper • 2510.14979 • Published Oct 16 • 66

upvoted a collection 17 days ago

DFN Models + Data

Collection

CLIP Models trained using DFN-2B/DFN-5B datasets • 7 items • Updated Aug 25 • 17

upvoted 2 papers 24 days ago

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use

Paper • 2510.05592 • Published Oct 7 • 106

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published 25 days ago • 236

upvoted 2 papers 25 days ago

Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning

Paper • 2511.16043 • Published Nov 20 • 108

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Paper • 2511.22699 • Published 30 days ago • 214