Another Blueprint In The Wall: How to Ask Frontier AI Like a Kid?
Paper • 2609.14803 • Published • 7
Chris Concannon
choncan
AI & ML interests
None yet
Recent Activity
upvoted a paper about 7 hours ago
Another Blueprint In The Wall: How to Ask Frontier AI Like a Kid? upvoted a paper about 7 hours ago
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement upvoted a paper about 7 hours ago
HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent HarnessOrganizations
None yet
upvoted 8
papers about 7 hours ago
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
Paper • 2609.11873 • Published • 88
HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness
Paper • 2609.15195 • Published • 17
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
Paper • 2609.17523 • Published • 20
StepAudio 3 Music Technical Report
Paper • 2609.16034 • Published • 76
StepAudio 3 Realtime Technical Report
Paper • 2609.14005 • Published • 101
AI for Games in the Foundation Model Era
Paper • 2609.16679 • Published • 113
Continual Learning Mechanisms Compose for Long-Horizon Memorization
Paper • 2609.06986 • Published • 291
upvoted 9
papers 1 day ago
AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems
Paper • 2609.08572 • Published • 96
Programmable World Model
Paper • 2609.10540 • Published • 109
Show-Harness: Just a VLM Agent Can Play Robots
Paper • 2609.10522 • Published • 160
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem
Paper • 2609.07064 • Published • 141
DataFlex-RL: An Evaluation Platform for RLVR Data Policies
Paper • 2609.06107 • Published • 125
Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation
Paper • 2609.11115 • Published • 207
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models
Paper • 2609.08418 • Published • 144
SenseNova-U1.5: Towards Native Unified Visual Intelligence
Paper • 2609.11929 • Published • 261
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction
Paper • 2609.10715 • Published • 319
upvoted 3
papers 7 days ago
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
Paper • 2609.04172 • Published • 98
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM
Paper • 2609.04098 • Published • 83
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
Paper • 2609.03430 • Published • 186