Stoney Kang

sikang99's activity

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

upvoted a paper about 18 hours ago

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Paper • 2603.17187 • Published 2 days ago • 87

upvoted 3 papers 1 day ago

Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation

Paper • 2603.16669 • Published 2 days ago • 64

SimRecon: SimReady Compositional Scene Reconstruction from Real Videos

Paper • 2603.02133 • Published 17 days ago • 4

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Paper • 2603.12262 • Published 7 days ago • 30

upvoted a paper 4 days ago

VQQA: An Agentic Approach for Video Evaluation and Quality Improvement

Paper • 2603.12310 • Published 7 days ago • 7

upvoted 5 papers 5 days ago

OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams

Paper • 2603.12265 • Published 7 days ago • 12

Mobile-GS: Real-time Gaussian Splatting for Mobile Devices

Paper • 2603.11531 • Published 8 days ago • 9

ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation

Paper • 2603.11421 • Published 8 days ago • 34

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

Paper • 2603.12255 • Published 7 days ago • 89

DVD: Deterministic Video Depth Estimation with Generative Priors

Paper • 2603.12250 • Published 7 days ago • 26

upvoted a paper 7 days ago

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published 9 days ago • 130

upvoted 3 papers 8 days ago

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Paper • 2603.09206 • Published 10 days ago • 51

InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing

Paper • 2603.09877 • Published 9 days ago • 47

Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs

Paper • 2603.09906 • Published 9 days ago • 70

upvoted 2 papers 16 days ago

WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories

Paper • 2603.02049 • Published 17 days ago • 17

VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection

Paper • 2603.00912 • Published 19 days ago • 39

upvoted 4 papers 19 days ago

The Trinity of Consistency as a Defining Principle for General World Models

Paper • 2602.23152 • Published 21 days ago • 198

OmniGAIA: Towards Native Omni-Modal AI Agents

Paper • 2602.22897 • Published 21 days ago • 53

General Agent Evaluation

Paper • 2602.22953 • Published 21 days ago • 11

VGG-T^3: Offline Feed-Forward 3D Reconstruction at Scale

Paper • 2602.23361 • Published 21 days ago • 14