MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis
Paper • 2607.27146 • Published • 22
🔄 In a Training Loop
Urro
urroxyz
AI & ML interests
computational linguistics major 🤖🔎ðŸ”
i am autistic. if i come off rude, i probably didn't mean to. please feel free to ask me for clarification.
Recent Activity
commentedon a paper about 22 hours ago
MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis updated a collection about 22 hours ago
WTF GENIUS PAPERS upvoted a paper about 22 hours ago
MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program SynthesisOrganizations
upvoted 5
papers about 22 hours ago
Multi-Head Attention Residuals
Paper • 2607.27230 • Published • 8
Metis: Memory Foundation Model
Paper • 2607.26760 • Published • 252
Flux-OPD: On-Policy Distillation with Evolving Contexts
Paper • 2607.28022 • Published • 39
Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory
Paper • 2607.27919 • Published • 48
upvoted 3
papers 2 days ago
DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space
Paper • 2607.25675 • Published • 60
CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation
Paper • 2607.16955 • Published • 4
CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization
Paper • 2607.25659 • Published • 80
upvoted 3
papers 3 days ago
CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents
Paper • 2607.25431 • Published • 99
Pass the Baton: Trajectory-Relayed On-Policy Distillation
Paper • 2607.26057 • Published • 29
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
Paper • 2607.25091 • Published • 6
upvoted 3
papers 4 days ago
Kimi K3: Open Frontier Intelligence
Paper • 2607.24653 • Published • 423
Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models
Paper • 2607.22098 • Published • 8
Codifying the Judge: Scalable Evaluation via Program Distillation
Paper • 2607.22561 • Published • 8
upvoted a paper 7 days ago
upvoted 4
papers 8 days ago
Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking
Paper • 2607.19747 • Published • 31
Predictive Divergence Masks for LLM RL
Paper • 2607.10848 • Published • 11
K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
Paper • 2605.09635 • Published • 63
Multi-Turn On-Policy Distillation with Prefix Replay
Paper • 2607.04763 • Published • 12
upvoted a paper 9 days ago