1 citations · 2 across the 18 of their papers we have counts for
7 papers · 1 filter
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…
: Stratified Scaling Search for Test-Time in Diffusion Language Models
Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer +6
Test-time scaling investigates whether a fixed diffusion language model (DLM) can generate better outputs when given more inference compute, without additional training. However, n…
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…
On the Fundamental Limits of LLMs at Scale
Muhammad Ahmed Mohsin, Muhammad Umer, Ahsan Bilal +13
Large Language Models (LLMs) have benefited enormously from scaling, yet these gains are bounded by five fundamental limitations: (1) hallucination, (2) context compression, (3) re…
Meta-Reinforcement Learning for Fast and Data-Efficient Spectrum Allocation in Dynamic Wireless Networks
Oluwaseyi Giwa, Tobi Awodunmila, Muhammad Ahmed Mohsin +2
The dynamic allocation of spectrum in 5G / 6G networks is critical to efficient resource utilization. However, applying traditional deep reinforcement learning (DRL) is often infea…
ItDPDM: Information-Theoretic Discrete Poisson Diffusion Model
Sagnik Bhattacharya, Abhiram Gorle, Ahsan Bilal +3
Generative modeling of non-negative, discrete data, such as symbolic music, remains challenging due to two persistent limitations in existing methods. Firstly, many approaches rely…