4 60 88

Kyle Tuft

Chilangosta

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

Chain-of-Thought Tokens are Computer Program Variables

upvoted a paper 3 days ago

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

upvoted a paper 5 days ago

ReVision: High-Quality, Low-Cost Video Generation with Explicit 3D Physics Modeling for Complex Motion and Interaction

View all activity

Organizations

None yet

Chilangosta's activity

upvoted a paper 1 day ago

Chain-of-Thought Tokens are Computer Program Variables

Paper • 2505.04955 • Published 4 days ago • 6

upvoted a paper 3 days ago

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

Paper • 2505.04512 • Published 5 days ago • 32

upvoted a paper 5 days ago

ReVision: High-Quality, Low-Cost Video Generation with Explicit 3D Physics Modeling for Complex Motion and Interaction

Paper • 2504.21855 • Published 11 days ago • 12

upvoted an article 8 days ago

Article

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Apr 15, 2024

• 179

upvoted 2 papers 9 days ago

KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution

Paper • 2505.00497 • Published 11 days ago • 14

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

Paper • 2505.00703 • Published 10 days ago • 39

upvoted a paper 17 days ago

Make-A-Character 2: Animatable 3D Character Generation From a Single Image

Paper • 2501.07870 • Published Jan 14 • 1

upvoted a collection 26 days ago

VL-Rethinker

Collection

SoTA VLM for Reasoning • 7 items • Updated 6 days ago • 4

upvoted a paper 26 days ago

VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

Paper • 2504.08837 • Published Apr 10 • 42

upvoted a paper 28 days ago

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

Paper • 2504.08736 • Published about 1 month ago • 47

upvoted 2 papers about 1 month ago

Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources

Paper • 2504.00595 • Published Apr 1 • 36

ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model

Paper • 2503.21144 • Published Mar 27 • 25

upvoted 4 papers about 2 months ago

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

Paper • 2503.11576 • Published Mar 14 • 104

upvoted 4 papers 2 months ago

EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer

Paper • 2503.07027 • Published Mar 10 • 29

VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control

Paper • 2503.05639 • Published Mar 7 • 24

EgoLife: Towards Egocentric Life Assistant

Paper • 2503.03803 • Published Mar 5 • 43

Token-Efficient Long Video Understanding for Multimodal LLMs

Paper • 2503.04130 • Published Mar 6 • 94