20 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…
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…
Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition
Muhammad Ahmed Mohsin, Ahsan Bilal, Muhammad Umer +1
Large language models exhibit sycophancy, the tendency to shift their stated positions toward perceived user preferences or authority cues regardless of evidence. Standard alignmen…