21 papers
Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning
Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer +4
Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing ans…
What If We Allocate Test-Time Compute Adaptively?
Ahsan Bilal, Ahmed Mohsin, Muhammad Umer +4
Test-time compute scaling allocates inference computation uniformly, uses fixed sampling strategies, and applies verification only for reranking. In contrast, we propose a verifier…
General Preference Reinforcement Learning
Muhammad Umer, Muhammad Ahmed Mohsin, Ahsan Bilal +5
Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable rewards drives emergent reason…
Epistemic Uncertainty for Test-Time Discovery
Kainat Riaz, Muhammad Ahmed Mohsin, Ahsan Bilal +5
Automated scientific discovery using large language models relies on identifying genuinely novel solutions. Standard reinforcement learning penalizes high-variance mutations, which…
Canonical Optimization for MIMO MAC Design
Muhammad Umer, Muhammad Ahmed Mohsin, Ahsan Bilal +1
Resource allocation in the multiple-input multiple-output (MIMO) multiple access channel (MAC) is a fundamental problem in multiuser communications, yet it is increasingly treated…
Continuous-Utility Direct Preference Optimization
Muhammad Ahmed Mohsin, Muhammad Umer, Ahsan Bilal +6
Large language model reasoning is often treated as a monolithic capability, relying on binary preference supervision that fails to capture partial progress or fine-grained reasonin…