What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document Paper • 2610.04128 • Published Oct 2 • 9
Privacy Failure in Split-LLM Training, The Returned Gradient Nullifies the Decoys Paper • 2609.04382 • Published Sep 3 • 6
Covenant-72B: Pre-Training a 72B LLM with Trustless Peers Over-the-Internet Paper • 2603.08163 • Published Mar 9 • 5
DCAS: Decoupling CLI Agent Scaffolding to Internalize Planning across Scaffolds Paper • 2608.06113 • Published Aug 6 • 18
DCAS: Decoupling CLI Agent Scaffolding to Internalize Planning across Scaffolds Paper • 2608.06113 • Published Aug 6 • 18
SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch Paper • 2607.27167 • Published Jul 29 • 20
MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis Paper • 2607.27146 • Published Jul 29 • 30
SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch Paper • 2607.27167 • Published Jul 29 • 20
MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis Paper • 2607.27146 • Published Jul 29 • 30
Incentivizing Permissionless Distributed Learning of LLMs Paper • 2505.21684 • Published May 27, 2025 • 1
Substance Beats Style: Why Beginning Students Fail to Code with LLMs Paper • 2410.19792 • Published Oct 15, 2024
AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans Paper • 2509.21891 • Published Sep 26, 2025
PhD Knowledge Not Required: A Reasoning Challenge for Large Language Models Paper • 2502.01584 • Published Feb 3, 2025 • 9
NNsight and NDIF: Democratizing Access to Foundation Model Internals Paper • 2407.14561 • Published Jul 18, 2024 • 34
Activation Steering for Robust Type Prediction in CodeLLMs Paper • 2404.01903 • Published Apr 2, 2024 • 2
Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions Paper • 2312.12450 • Published Dec 11, 2023 • 2
Type Prediction With Program Decomposition and Fill-in-the-Type Training Paper • 2305.17145 • Published May 25, 2023