Has GPT-6-Astra Achieved Embodied Intelligence?
Paper • 2610.22471 • Published • 165
Yuseung "Phillip" Lee
phillipinseoul
AI & ML interests
Computer Vision
Recent Activity
upvoted a paper 14 days ago
Has GPT-6-Astra Achieved Embodied Intelligence? upvoted a paper about 2 months ago
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement upvoted a paper about 2 months ago
HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent HarnessOrganizations
upvoted a paper 14 days ago
upvoted 4
papers about 2 months ago
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Paper • 2609.14857 • Published • 75
HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness
Paper • 2609.15195 • Published • 21
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Paper • 2609.14858 • Published • 149
FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow
Paper • 2609.03563 • Published • 8
upvoted 10
papers 2 months ago
Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning
Paper • 2608.27549 • Published • 48
GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture
Paper • 2608.15875 • Published • 92
Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs
Paper • 2608.12781 • Published • 35
Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection
Paper • 2608.20169 • Published • 12
Prime Agent: A Self-Improving RLM Harness
Paper • 2608.23552 • Published • 60
EXIMO: VLM Guided Exploration of VLA Policies
Paper • 2608.19891 • Published • 12
EnvHarness: Awakening Static Worlds for Agent Learning
Paper • 2608.19880 • Published • 110
SPADE: Self-Play in Adaptive Synthetic Executable Environments
Paper • 2608.19197 • Published • 51
Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation
Paper • 2608.17512 • Published • 33
Demystifying Agent Skills: Why They Work-Until They Don't
Paper • 2608.14036 • Published • 57
upvoted 5
papers 3 months ago
HarnessEval-W: Agentifying the Evaluation of Visual Worlds
Paper • 2608.16859 • Published • 69
Self-Supervised Visual On-Policy Distillation
Paper • 2608.14144 • Published • 55
PRM-as-a-Judge 1.5: A Toolkit for Robot Process Assessment
Paper • 2608.14284 • Published • 15
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
Paper • 2608.13417 • Published • 60
Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence
Paper • 2608.12743 • Published • 37