Jie Feng

JJ-TMT's activity

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

upvoted an article 3 days ago

view article

Article

SmolLM3: smol, multilingual, long-context reasoner

By and 22 others •

9 days ago

• 543

upvoted 2 papers 6 days ago

T-LoRA: Single Image Diffusion Model Customization Without Overfitting

Paper • 2507.05964 • Published 9 days ago • 103

Scaling RL to Long Videos

Paper • 2507.07966 • Published 7 days ago • 129

upvoted 3 papers 9 days ago

Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs

Paper • 2506.07240 • Published Jun 8 • 6

DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

Paper • 2507.04447 • Published 11 days ago • 40

MemOS: A Memory OS for AI System

Paper • 2507.03724 • Published 13 days ago • 117

upvoted a paper 11 days ago

Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation

Paper • 2506.21876 • Published 20 days ago • 27

upvoted 2 papers 13 days ago

Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers

Paper • 2506.23918 • Published 17 days ago • 77

AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training

Paper • 2507.01663 • Published 15 days ago • 5

upvoted 2 papers 14 days ago

LongAnimation: Long Animation Generation with Dynamic Global-Local Memory

Paper • 2507.01945 • Published 15 days ago • 73

Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation

Paper • 2506.19852 • Published 23 days ago • 38

upvoted 3 papers 16 days ago

RoboScape: Physics-informed Embodied World Model

Paper • 2506.23135 • Published 18 days ago • 5

MMSearch-R1: Incentivizing LMMs to Search

Paper • 2506.20670 • Published 22 days ago • 60

UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding

Paper • 2506.23219 • Published 18 days ago • 7

upvoted a paper 19 days ago

SynCity: Training-Free Generation of 3D Worlds

Paper • 2503.16420 • Published Mar 20 • 26

upvoted 2 papers 20 days ago

WorldVLA: Towards Autoregressive Action World Model

Paper • 2506.21539 • Published 21 days ago • 39

MADrive: Memory-Augmented Driving Scene Modeling

Paper • 2506.21520 • Published 21 days ago • 36

upvoted a paper 22 days ago

Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System

Paper • 2506.19433 • Published 23 days ago • 3

upvoted 2 papers 23 days ago

RLPR: Extrapolating RLVR to General Domains without Verifiers

Paper • 2506.18254 • Published 24 days ago • 32

OmniGen2: Exploration to Advanced Multimodal Generation

Paper • 2506.18871 • Published 24 days ago • 73