Jonathan Light

4 papers · 2025–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

ICLR (2) CVPR (1) UAI (1)

Top co-authors

Wei Cheng (3) Yisong Yue (2) Ziniu Hu (2) Haifeng Chen (2) Xujiang Zhao (1) Sophia Stiles (1) Atharva Sehgal (1) Yiyou Sun (1) Weiyang Liu (1) Min Cai (1)

Research topics

Artificial Intelligence (4) Core AI (4) Machine Learning (2) Computer Vision (1) Deep Learning (1) Domain-Specific (1) Learning Types (1) Models (1) Optimization & Theory (1)

Keywords

black-box optimization (1) computer vision (1) decision making (1) model evaluation (1) code generation (1) biomedical imaging (1) majority voting (1) monte carlo tree search (1) tree search (1) evolutionary search (1) workflow optimization (1) game strategy (1) local optimum (1) inference-time scaling (1) multi-agent system (1) best-of-n selection (1) prompt diversity (1) diversity fidelity tradeoff (1) agentic code optimization (1) sampling diversity (1)

Papers

On the Effect of Sampling Diversity in Scaling LLM Inference UAI 2026 Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization CVPR 2026 SFS: Smarter Code Space Search improves LLM Inference Scaling ICLR 2025 Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search ICLR 2025