Xiaokang Liu

hiskiv's activity

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

updated a model about 10 hours ago

hiskiv/cosmos-ckpt

Updated about 10 hours ago

updated a model 3 days ago

hiskiv/VLAST-ckpt

Updated 3 days ago

published a model 13 days ago

hiskiv/VLAST-ckpt

Updated 3 days ago

upvoted a paper 14 days ago

The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation

Paper • 2511.20256 • Published 14 days ago • 26

upvoted a paper about 1 month ago

UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback

Paper • 2511.01678 • Published Nov 3 • 34

published a model about 2 months ago

hiskiv/cosmos-ckpt

Updated about 10 hours ago

updated a model about 2 months ago

hiskiv/cosmos-models

Updated Oct 17 • 7

published a model about 2 months ago

hiskiv/cosmos-models

Updated Oct 17 • 7

updated a dataset about 2 months ago

hiskiv/robot-temp

Viewer • Updated Oct 17 • 480 • 19

published a dataset about 2 months ago

hiskiv/robot-temp

Viewer • Updated Oct 17 • 480 • 19

upvoted 2 papers 2 months ago

Paper2Video: Automatic Video Generation from Scientific Papers

Paper • 2510.05096 • Published Oct 6 • 116

Code2Video: A Code-centric Paradigm for Educational Video Generation

Paper • 2510.01174 • Published Oct 1 • 33

upvoted a paper 5 months ago

Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models

Paper • 2507.07484 • Published Jul 10 • 17

upvoted a paper 6 months ago

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

Paper • 2505.23380 • Published May 29 • 22

upvoted 5 papers 9 months ago

Impossible Videos

Paper • 2503.14378 • Published Mar 18 • 61

TPDiff: Temporal Pyramid Video Diffusion Model

Paper • 2503.09566 • Published Mar 12 • 45

Automated Movie Generation via Multi-Agent CoT Planning

Paper • 2503.07314 • Published Mar 10 • 44

DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles

Paper • 2503.03651 • Published Mar 5 • 16

Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

Paper • 2503.01774 • Published Mar 3 • 44

upvoted a paper 10 months ago

PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data

Paper • 2502.14397 • Published Feb 20 • 41