70 citations · 93 across the 17 of their papers we have counts for
4 papers · 1 filter
Unlocking the Critic: Reward-Free Policy Optimization for LLM Post-Training
Hongyang Li, Xiao Li, Caesar Wu +3
Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instability and memory overhead. Even whe…
What Does Post-Training Change in Multilingual Reasoning?
Hongyang Li, Xiao Li, Caesar Wu +2
Open-source reasoning models provide unequal access to reasoning capability across languages. When a model can solve a problem but cannot deliver a complete solution in the user's…
LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation Learning
Mohand Mezmaz, Grégoire Danoy
Machine learning for combinatorial optimization typically relies on neural constructors trained via reinforcement learning on large offline datasets for a fixed problem class-incur…
SkyHOST: A Unified Architecture for Cross-Cloud Hybrid Object and Stream Transfer
Muhammad Arslan Tariq, Grégoire Danoy, Pascal Bouvry
Cloud and big data workloads are increasingly distributing data across multiple cloud providers and regions for rapid decision-making and analytics. Traditional transfer tools are…