Harness-Zero: Harness Distillation via Agent-as-Harness
Paper • 2609.24974 • Published • 37
Owen Reed
owenreed
AI & ML interests
Efficient LLM inference, KV cache optimization, quantization, speculative decoding, model pruning
Recent Activity
upvoted a paper 6 days ago
Harness-Zero: Harness Distillation via Agent-as-Harness upvoted a paper 7 days ago
EvoOntology: A Self-Evolving Ontology Layer for Data Agents upvoted a paper 8 days ago
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache CompressionOrganizations
None yet
upvoted a paper 6 days ago
upvoted a paper 7 days ago
upvoted 2
papers 8 days ago
upvoted 2
papers 10 days ago
upvoted a paper 12 days ago
upvoted 3
papers 13 days ago
Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction
Paper • 2609.13285 • Published • 81
How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus
Paper • 2609.15504 • Published • 37
Atria Dawn: The Dawn of Agentic Superintelligence
Paper • 2609.15818 • Published • 432
upvoted a paper 14 days ago
upvoted 6
papers 17 days ago
Programmable World Model
Paper • 2609.10540 • Published • 115
BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference
Paper • 2609.04971 • Published • 43
Language Models Can Control Their Own Attention
Paper • 2609.02737 • Published • 79
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
Paper • 2609.04010 • Published • 114
Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training
Paper • 2609.07108 • Published • 36
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
Paper • 2609.08183 • Published • 327
upvoted 2
papers 23 days ago
upvoted a paper 27 days ago