Zhen Fang

CostaliyA's activity

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

upvoted a paper about 12 hours ago

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Paper • 2607.27380 • Published 3 days ago • 61

updated a dataset about 13 hours ago

CostaliyA/eva_dev

Viewer • Updated about 1 hour ago • 1 • 12.8k

New activity in CostaliyA/Video-DeepResearch-35B-A3B 1 day ago

Upload w_text_35 checkpoint-721 (16 shards, ~66GB)

#1 opened 1 day ago by

CostaliyA

updated a model 1 day ago

CostaliyA/Video-DeepResearch-35B-A3B

Updated 1 day ago • 16

published 2 models 1 day ago

CostaliyA/Video-DeepResearch-35B-A3B

Updated 1 day ago • 16

CostaliyA/Video-DeepResearch-30B-A3B

Updated 1 day ago

liked a model 1 day ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 4 days ago • 493k • • 9.18k

upvoted a paper 3 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 5 days ago • 407

upvoted an article 4 days ago

view article

Article

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

• 

ResterChed

•

14 days ago

• 187

upvoted a paper 8 days ago

Self Gradient Forcing: Native Long Video Extrapolation

Paper • 2607.20368 • Published 10 days ago • 34

New activity in Orannue/dataset 9 days ago

update 20260720 metadata shards 003-005

#7 opened 9 days ago by

CostaliyA

published a dataset 9 days ago

CostaliyA/eva_dev

Viewer • Updated about 1 hour ago • 1 • 12.8k

upvoted a paper 10 days ago

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

Paper • 2607.17423 • Published 13 days ago • 166

upvoted 2 papers 13 days ago

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published 16 days ago • 103

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

Paper • 2607.14935 • Published 16 days ago • 170

upvoted a paper 22 days ago

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Paper • 2607.07675 • Published 24 days ago • 64

updated a model 24 days ago

CostaliyA/Flow-GRPO-MIX

Updated 24 days ago • 18

published a model 24 days ago

CostaliyA/Flow-GRPO-MIX

Updated 24 days ago • 18

upvoted 2 papers about 1 month ago

In-Context World Modeling for Robotic Control

Paper • 2606.26025 • Published Jun 25 • 63

DanceOPD: On-Policy Generative Field Distillation

Paper • 2606.27377 • Published Jun 25 • 81