2 papers
cs.LG2026
Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models
Jonathan Williams, Esin Tureci
Looped Language Models (LoopLMs) perform multi-step latent reasoning prior to token generation and outperform conventional LLMs on reasoning benchmarks at smaller parameter budgets…
cs.LG2026
Test-Time Alignment via Hypothesis Reweighting
Yoonho Lee, Jonathan Williams, Henrik Marklund +4
Reward models trained on aggregate preferences often fail to capture individual users' values, but existing adaptation methods such as fine-tuning or long-context conditioning are…