Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation
Paper • 2610.13521 • Published • 252
Daniel Brown
cobalttrail
AI & ML interests
None yet
Recent Activity
upvoted a paper 10 days ago
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction liked a model 13 days ago
abenzerps/Qwen-Image-2.1-Uncensored-QuantizedOrganizations
None yet
upvoted a paper 5 days ago
upvoted a paper 10 days ago
upvoted 5
papers about 1 month ago
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
Paper • 2609.20511 • Published • 143
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
Paper • 2609.18708 • Published • 85
Continual Learning Mechanisms Compose for Long-Horizon Memorization
Paper • 2609.06986 • Published • 369
Atria Dawn: The Dawn of Agentic Superintelligence
Paper • 2609.15818 • Published • 417
Scaling Automatic Research Agents via World Models
Paper • 2608.12564 • Published • 483
upvoted 4
papers about 2 months ago
LatentPress: Context Compression Beyond Text and Vision
Paper • 2609.01507 • Published • 83
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
Paper • 2608.26730 • Published • 133
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Paper • 2609.02749 • Published • 467
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
Paper • 2609.00111 • Published • 347
upvoted 8
papers 2 months ago
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation
Paper • 2608.17426 • Published • 160
SoftVTBench: A Deformation-Aware Visuo-Tactile Dataset and Benchmark for Deformable-Object Manipulation
Paper • 2608.18701 • Published • 15
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination
Paper • 2608.14391 • Published • 285
Self-Supervised Visual On-Policy Distillation
Paper • 2608.14144 • Published • 168
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries
Paper • 2608.05604 • Published • 71
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution
Paper • 2608.00677 • Published • 263
Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution
Paper • 2608.07645 • Published • 28
A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization
Paper • 2608.08156 • Published • 9
upvoted a paper 3 months ago