SheldonXu

Sheldoooon's activity

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

upvoted a paper 1 day ago

PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models

Paper • 2504.16074 • Published 4 days ago • 29

upvoted 5 papers 8 days ago

SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models

Paper • 2504.11468 • Published 16 days ago • 27

BlockGaussian: Efficient Large-Scale Scene Novel View Synthesis via Adaptive Block-Based Gaussian Splatting

Paper • 2504.09048 • Published 14 days ago • 7

SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL

Paper • 2504.11455 • Published 11 days ago • 12

NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors

Paper • 2504.11427 • Published 11 days ago • 17

Seedream 3.0 Technical Report

Paper • 2504.11346 • Published 11 days ago • 48

upvoted 2 papers 11 days ago

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Paper • 2504.10479 • Published 12 days ago • 241

Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images

Paper • 2504.08727 • Published 15 days ago • 11

upvoted 3 papers 12 days ago

Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

Paper • 2504.08685 • Published 15 days ago • 121

HoloPart: Generative 3D Part Amodal Segmentation

Paper • 2504.07943 • Published 16 days ago • 28

OmniSVG: A Unified Scalable Vector Graphics Generation Model

Paper • 2504.06263 • Published 18 days ago • 151

upvoted 3 papers 19 days ago

EvMic: Event-based Non-contact sound recovery from effective spatial-temporal modeling

Paper • 2504.02402 • Published 23 days ago • 6

Articulated Kinematics Distillation from Video Diffusion Models

Paper • 2504.01204 • Published 25 days ago • 24

SketchVideo: Sketch-based Video Generation and Editing

Paper • 2503.23284 • Published 27 days ago • 23

upvoted 2 papers 24 days ago

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

Paper • 2503.19901 • Published Mar 25 • 39

MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs

Paper • 2503.23022 • Published 28 days ago • 7

upvoted 4 papers 26 days ago

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

Paper • 2503.21732 • Published 30 days ago • 8

Segment Any Motion in Videos

Paper • 2503.22268 • Published 29 days ago • 17

Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging

Paper • 2503.22236 • Published 29 days ago • 11

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks

Paper • 2503.21696 • Published 30 days ago • 22