1 citations · 1 across the 1 of their papers we have counts for
2 papers
cs.CV2026
VisConf: Quality-Aware Consensus for Best-of-N in Vision-Language Model Reasoning
Muhammad Usman, Muhammad Qasim Ayub, Usman Ahad +1
Best-of-N methods improve text-only LLM reasoning by sampling multiple trajectories before selecting an answer. For Vision-Language Models (VLMs), answer frequency and model confid…
cs.SE2024★ 1 cited
Toward Automated Validation of Language Model Synthesized Test Cases using Semantic Entropy
Hamed Taherkhani, Jiho Shin, Muhammad Ammar Tahir +3
Modern Large Language Model (LLM)-based programming agents often rely on test execution feedback to refine their generated code. These tests are synthetically generated by LLMs. Ho…