Hongje Seong

hongjeseong's activity

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

upvoted 2 papers 3 days ago

PhiZero: A World Model Built Around Physical Language

Paper • 2607.28624 • Published 4 days ago • 158

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

Paper • 2607.27205 • Published 5 days ago • 127

upvoted a paper 4 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 7 days ago • 431

upvoted a paper 7 days ago

Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment

Paper • 2607.13429 • Published 19 days ago • 16

upvoted a paper 12 days ago

GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction

Paper • 2605.23888 • Published May 22 • 17

upvoted 2 papers 18 days ago

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Paper • 2607.11886 • Published 21 days ago • 84

Video Generation Models are General-Purpose Vision Learners

Paper • 2607.09024 • Published 24 days ago • 86

upvoted a paper 24 days ago

PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

Paper • 2607.05373 • Published 28 days ago • 66

upvoted 2 papers 29 days ago

Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling

Paper • 2607.01642 • Published Jul 2 • 39

Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

Paper • 2606.29513 • Published Jun 28 • 53

upvoted a paper about 1 month ago

SAM2Matting: Generalized Image and Video Matting

Paper • 2606.27339 • Published Jun 25 • 12

upvoted 3 papers about 2 months ago

TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction

Paper • 2605.26115 • Published May 25 • 52

GenClaw: Code-Driven Agentic Image Generation

Paper • 2605.30248 • Published May 28 • 41

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published Jun 1 • 142

upvoted 6 papers 2 months ago

VLM3: Vision Language Models Are Native 3D Learners

Paper • 2605.30561 • Published May 28 • 26

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Paper • 2605.30280 • Published May 28 • 146

Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction

Paper • 2605.26230 • Published May 25 • 41

SpatialBench: Is Your Spatial Foundation Model an All-Round Player?

Paper • 2605.27367 • Published May 26 • 72

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

Paper • 2605.27365 • Published May 26 • 146

CubePart: An Open-Vocabulary Part-Controllable 3D Generator

Paper • 2605.28763 • Published May 27 • 14