collaborators

38 papers

cs.LG2026

Reinforcement Learning for Code Optimization

Pierre Chambon, Kunhao Zheng, Juliette Decugis +2

The paper proposes a reinforcement‑learning framework that learns to optimize program execution speed by addressing measurement noise, sparse rewards, and instability, using a cali…

cs.LG2026

Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity

Loïc Cabannes, Pierre-Emmanuel Mazaré, Gergely Szilvasy +6

Linear attention models allow a fixed state size and a fixed amount of compute per token. However, due to their limited state size, linear attention models fall behind in long-cont…

cs.LG2026

DecompRL: Solving Harder Problems by Learning Modular Code Generation

Juliette Decugis, Fabian Gloeckle, Francis Bach +2

How can Large Language Models (LLMs) solve problems they currently cannot? Repeated sampling scales test-time compute but GPU cost grows linearly with attempts, while reinforcement…

cs.LG2026

Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL

Juliette Decugis, Sean O'Brien, Francis Bach +2

Reinforcement learning post-training dramatically improves LLM reasoning, but suffers from training instability and diversity collapse. Advantage functions offer an appealing fix:…

cs.SE2026

Toward Training Superintelligent Software Agents through Self-Play SWE-RL

Yuxiang Wei, Zhiqing Sun, Emily McMilin +6

While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub i…

cs.LG2026

Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL

Kunhao Zheng, Pierre Chambon, Juliette Decugis +4

Linear interpolation between fine-tuned checkpoints has been shown to trace the Pareto front between competing objectives, but whether extrapolative weight averaging can extend suc…