Muhammad Umer

activity

20202026

most citedComparative Analysis of Extreme Verification Latency Learning Algorithms

3 citations · 3 across the 6 of their papers we have counts for

collaborators

Showing 2026 · cs.LGShow all

2 papers · 2 filters

cs.LG2026

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…

cs.LG2026

$S^{3}$ : 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…

Epistemic Uncertainty for Test-Time Discovery

S3: Stratified Scaling Search for Test-Time in Diffusion Language Models

$S^{3}$ : Stratified Scaling Search for Test-Time in Diffusion Language Models