4 papers
TREK: Distill to Explore, Reinforce to Refine
Yuanda Xu, Zhengze Zhou, Kayhan Behdin +10
Group Relative Policy Optimization (GRPO) is effective when the current policy already samples useful reasoning trajectories, but it stalls on hard prompts whose correct solution m…
Precision Tracked Transformer via Kalman Filtering, Kriging and Process Noise
Bo Long, Deepak Agarwal, Jelena Markovic-Voronov +2
The Transformer is the foundational building block of modern AI, yet offers no principled handling of \emph{uncertainty}, which is prevalent in real applications: cold-start tokens…
Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo
Jelena Markovic-Voronov, Wenhui Zhu, Bo Long +5
We introduce a principled probabilistic framework for reward-guided decoding in large language models, addressing the limitations of standard decoding methods that optimize token-l…
Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints
Jelena Markovic-Voronov, Kayhan Behdin, Yuanda Xu +3
We study the problem of routing queries to large language models (LLMs) under cost, GPU resources, and concurrency constraints. Prior per-query routing methods often fail to contro…