Pu Fanyi

pufanyi's activity

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

upvoted a paper 25 days ago

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

Paper • 2607.24904 • Published 27 days ago • 37

upvoted an article 26 days ago

view article

Article

Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community

• 

ResterChed

•

Jul 17

• 197

upvoted 3 papers about 1 month ago

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Paper • 2607.19064 • Published Jul 21 • 77

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Paper • 2607.14935 • Published Jul 16 • 172

Video Generation Models are General-Purpose Vision Learners

Paper • 2607.09024 • Published Jul 10 • 88

upvoted a paper about 2 months ago

Vision as Unified Multimodal Generation

Paper • 2607.06560 • Published Jul 7 • 48

upvoted an article 2 months ago

view article

Article

GLM-5.2: Built for Long-Horizon Tasks

• 

zai-org

•

Jun 17

• 139

upvoted a paper 3 months ago

From Pixels to Words -- Towards Native One-Vision Models at Scale

Paper • 2605.28820 • Published May 27 • 76

upvoted a collection 4 months ago

SenseNova-U1

Collection

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-Unify Architecture • 12 items • Updated 8 days ago • 76

upvoted 5 papers 5 months ago

FileGram: Grounding Agent Personalization in File-System Behavioral Traces

Paper • 2604.04901 • Published Apr 6 • 40

HippoCamp: Benchmarking Contextual Agents on Personal Computers

Paper • 2604.01221 • Published Apr 1 • 30

MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

Paper • 2603.15726 • Published Mar 16 • 187

Demystifing Video Reasoning

Paper • 2603.16870 • Published Mar 17 • 373

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

Paper • 2603.15612 • Published Mar 16 • 152

upvoted an article 6 months ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

sensenova

•

Mar 5

• 176

upvoted 5 papers 6 months ago

ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors

Paper • 2603.04338 • Published Mar 4 • 24

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published Feb 23 • 526

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?

Paper • 2603.03241 • Published Mar 3 • 88

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

Paper • 2602.12279 • Published Feb 12 • 20

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

Paper • 2602.08683 • Published Feb 9 • 52