Models
Datasets
Spaces
Docs
Enterprise
Pricing
Log In
Sign Up

Jifei Song's picture

1

Jifei Song

seindlut

21world's profile picture

·

AI & ML interests

None yet

Organizations

seindlut 's collections 9

Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models

Paper • 2508.00819 • Published Aug 1 • 62

MMSearch-R1: Incentivizing LMMs to Search

Paper • 2506.20670 • Published Jun 25 • 64

3D Reconstruction

Dreamland: Controllable World Creation with Simulator and Generative Models

Paper • 2506.08006 • Published Jun 9 • 7

Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning

Paper • 2506.13654 • Published Jun 16 • 43

AniMaker: Automated Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation

Paper • 2506.10540 • Published Jun 12 • 37

FaSTA^*: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing

Paper • 2506.20911 • Published Jun 26 • 41

Dynamic View Synthesis as an Inverse Problem

Paper • 2506.08004 • Published Jun 9 • 5
Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition

Paper • 2506.17201 • Published Jun 20 • 57
WorldVLA: Towards Autoregressive Action World Model

Paper • 2506.21539 • Published Jun 26 • 40

SpatialLM: Training Large Language Models for Structured Indoor Modeling

Paper • 2506.07491 • Published Jun 9 • 50
Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details

Paper • 2506.16504 • Published Jun 19 • 31
3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

Paper • 2507.23478 • Published Jul 31 • 15

LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning

Paper • 2506.10082 • Published Jun 11 • 8

Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models

Paper • 2508.00819 • Published Aug 1 • 62

FaSTA^*: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing

Paper • 2506.20911 • Published Jun 26 • 41

MMSearch-R1: Incentivizing LMMs to Search

Paper • 2506.20670 • Published Jun 25 • 64

Dynamic View Synthesis as an Inverse Problem

Paper • 2506.08004 • Published Jun 9 • 5
Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition

Paper • 2506.17201 • Published Jun 20 • 57
WorldVLA: Towards Autoregressive Action World Model

Paper • 2506.21539 • Published Jun 26 • 40

3D Reconstruction

Dreamland: Controllable World Creation with Simulator and Generative Models

Paper • 2506.08006 • Published Jun 9 • 7

SpatialLM: Training Large Language Models for Structured Indoor Modeling

Paper • 2506.07491 • Published Jun 9 • 50
Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details

Paper • 2506.16504 • Published Jun 19 • 31
3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

Paper • 2507.23478 • Published Jul 31 • 15

Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning

Paper • 2506.13654 • Published Jun 16 • 43

LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning

Paper • 2506.10082 • Published Jun 11 • 8

AniMaker: Automated Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation

Paper • 2506.10540 • Published Jun 12 • 37

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs