Yuseung "Phillip" Lee

phillipinseoul's activity

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

upvoted a paper about 1 hour ago

A Subgoal-driven Framework for Improving Long-Horizon LLM Agents

Paper • 2603.19685 • Published 3 days ago • 5

liked a dataset 3 days ago

nyu-visionx/VSI-590K

Preview • Updated Nov 7, 2025 • 2.1k • 18

upvoted 2 papers 3 days ago

Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models

Paper • 2603.18002 • Published 4 days ago • 9

Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding

Paper • 2603.19235 • Published 3 days ago • 86

upvoted 2 papers 4 days ago

Unified Spatio-Temporal Token Scoring for Efficient Video VLMs

Paper • 2603.18004 • Published 4 days ago • 12

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models

Paper • 2603.17117 • Published 5 days ago • 82

upvoted 5 papers 5 days ago

MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation

Paper • 2603.16861 • Published 5 days ago • 4

Efficient Reasoning on the Edge

Paper • 2603.16867 • Published 5 days ago • 16

MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

Paper • 2603.15726 • Published 6 days ago • 175

WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation

Paper • 2603.16871 • Published 5 days ago • 58

Demystifing Video Reasoning

Paper • 2603.16870 • Published 5 days ago • 348

upvoted 2 papers 6 days ago

Attention Residuals

Paper • 2603.15031 • Published 7 days ago • 139

Grounding World Simulation Models in a Real-World Metropolis

Paper • 2603.15583 • Published 6 days ago • 143

upvoted a paper 7 days ago

VQQA: An Agentic Approach for Video Evaluation and Quality Improvement

Paper • 2603.12310 • Published 10 days ago • 7

upvoted a paper 10 days ago

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

Paper • 2603.12255 • Published 10 days ago • 90

upvoted a paper 11 days ago

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published 12 days ago • 135

upvoted 3 papers 12 days ago

The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness

Paper • 2603.09200 • Published 13 days ago • 5

Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports

Paper • 2603.09896 • Published 12 days ago • 26

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

Paper • 2603.09206 • Published 13 days ago • 52

upvoted a paper 13 days ago

Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces

Paper • 2603.06713 • Published 17 days ago • 16