755 citations · 797 across the 16 of their papers we have counts for
7 papers · 1 filter
Compiling Expert Procedures into Verified Programs: When a Small Model Is Enough
Vishvesh Bhat, Asad Aali, Muhammad Ahmed Mohsin
In procedural tool-use domains, how much of the gap between base models is procedure rather than capability? We build an explicit program from a teacher's traces and run it in fron…
Benchmarking the Benchmarks: A Validity Audit of Tool-Calling Evaluation
Vishvesh Bhat, Jay Vaghasiya, Muhammad Ahmed Mohsin +1
Tool-calling benchmarks are increasingly used to rank language-model agents, yet their scores are often treated as ground truth without validating the evaluators themselves. We pre…
MAVEN: Improving Generalization in Agentic Tool Calling
Omkar Ghugarkar, Vishvesh Bhat, Muhammad Ahmed Mohsin +1
Generalization across agentic tool-calling environments remains a central challenge for reliable agentic reasoning systems. Although large language models achieve strong results on…
: 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…
Clinical Note Bloat Reduction for Efficient LLM Use
Jordan L. Cahoon, Chloe Stanwyck, Asad Aali +6
Background: Clinical notes contain extensive duplicated text from templates, copy-paste, and auto-populated fields ("note bloat"), diluting clinical signal, limiting longitudinal c…
Gradient-Stable Attention Heads Signal LLM Correctness
Sophie Ostmeier, Brian Axelrod, Maya Varma +6
Large language models (LLMs) often generate plausible yet incorrect answers, posing risks in safety-critical settings such as medicine. Human evaluation is expensive, and LLM-as-ju…
Training-Free Adaptation of New-Generation LLMs using Legacy Clinical Models
Sasha Ronaghi, Chloe Stanwyck, Asad Aali +4
Adapting language models to the clinical domain through continued pretraining and instruction tuning requires costly retraining for each new model generation. We propose Cross-Arch…