Toward Recursive Self-Improvement in Physical AI
Paper • 2610.29677 • Published • 76
Anthony (Tony) Garrett
kalisanman
·
AI & ML interests
FREE OPEN SOURCE SINGULAIRITY
Recent Activity
upvoted a paper 1 day ago
Toward Recursive Self-Improvement in Physical AI liked a model 2 days ago
fudan-generative-ai/Qwen3.8-27B-REMORY-1.9B upvoted a paper 3 days ago
REMORY: Learning Residual Memory for Context CompactionOrganizations
upvoted a paper 1 day ago
upvoted 18
papers 3 days ago
REMORY: Learning Residual Memory for Context Compaction
Paper • 2610.11287 • Published • 65
SUPRA-TEX: 3D Generation with Super-Aligned Texture
Paper • 2610.22352 • Published • 17
Hybrid Reasoning Agents
Paper • 2610.18861 • Published • 44
TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents
Paper • 2610.22732 • Published • 6
Self-Evolving Agent Harness
Paper • 2610.18813 • Published • 103
Has GPT-6-Astra Achieved Embodied Intelligence?
Paper • 2610.22471 • Published • 482
DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems
Paper • 2610.28522 • Published • 74
RAG-Anything: All-in-One RAG Framework
Paper • 2510.12323 • Published • 87
OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory
Paper • 2610.26860 • Published • 122
What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models
Paper • 2610.23987 • Published • 44
OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use
Paper • 2610.22200 • Published • 106
RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution
Paper • 2610.15772 • Published • 9
Raven: The Harness of Harnesses for Composable Agentic Intelligence
Paper • 2609.33439 • Published • 712
SolarRenderer: Few-Step Generative Reference Rendering
Paper • 2610.28630 • Published • 53
WeVisOne-VL: Unified Visual Perception from Objects to Pixels
Paper • 2610.31329 • Published • 252
Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds
Paper • 2610.28698 • Published • 78
StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions
Paper • 2610.17309 • Published • 81
Harness^2: Recursive Agent Harnessing for an Open World
Paper • 2610.14224 • Published • 124
upvoted a collection 25 days ago