Article
Anatomy of a bug-fixing agent
huggingface
• • 5
Darrow O'Lykos
darrowoflykos
AI & ML interests
None yet
Recent Activity
liked a model about 1 hour ago
tencent/HY-Motion-1.0 liked a model about 4 hours ago
trillionlabs/GravityOCR upvoted an article about 4 hours ago
Anatomy of a bug-fixing agentOrganizations
None yet
upvoted an article about 4 hours ago
upvoted 19
papers about 4 hours ago
Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
Paper • 2609.29429 • Published • 22
Jev in the Wild: A Data-Driven Analysis of the Jev Model's Functionality, Applications and Ecosystem
Paper • 2609.30216 • Published • 10
LastOPD: Taming Collapse in Latent On-Policy Distillation
Paper • 2609.28845 • Published • 19
TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent
Paper • 2609.27277 • Published • 21
Block Sparse Attention with Log-Linear Complexity
Paper • 2609.31093 • Published • 24
Disaggregated Quantization: Specializing LLM Prefill and Decode
Paper • 2609.26333 • Published • 69
KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation
Paper • 2609.33074 • Published • 3
Distillation Defenses Easily Break After Reinforcement Learning
Paper • 2609.35699 • Published • 3
FactorEngram: Factorized N-gram Memory with Basis-Level Gating for Language Models
Paper • 2609.35578 • Published • 3
Pruned CTC for Memory-Efficient Large-Vocabulary ASR Training
Paper • 2609.33645 • Published • 3
RenderRank: Learning to Rerank Text with Compressed Visual Tokens
Paper • 2609.35069 • Published • 7
ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport
Paper • 2609.34899 • Published • 5
Program-Verified Self-Evolution for Vision-Language Models
Paper • 2609.33855 • Published • 12
TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining
Paper • 2609.33419 • Published • 13
Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision
Paper • 2609.35718 • Published • 15
Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models
Paper • 2609.34972 • Published • 18
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents
Paper • 2609.33642 • Published • 25
QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents
Paper • 2609.33848 • Published • 27
Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge
Paper • 2609.34327 • Published • 33