Scholar
Anjiang Wei
Google Scholar ID: HoG_nZAAAAAJ
Stanford University
Citations & Impact
Citations
756
H-index
10
i10-index
10
Publications
20
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- “Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces,” ICML 2025 (Oral Presentation)
- “CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis,” COLM 2025
- “SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas,” EMNLP 2025
- “EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checking,” EMNLP 2025
- “SuperCoder: Assembly Program Superoptimization with Large Language Models,” NeurIPS 2025 DL4C Workshop
- “Astra: A Multi-Agent System for GPU Kernel Performance Optimization,” NeurIPS 2025 DL4C Workshop
- “InvBench: Can LLMs Accelerate Program Verification with Invariant Synthesis?,” Preprint
- “VeriCoder: Enhancing LLM-Based RTL Code Generation through Functional Correctness Validation,” NeurIPS 2025 DL4C Workshop
- “Mapple: A Domain-Specific Language for Mapping Distributed Heterogeneous Parallel Programs,” Preprint
- “Task-Based Programming for Adaptive Mesh Refinement in Compressible Flow Simulations,” Preprint
- “Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation,” CVPR 2025
- “PBA: Percentile-Based Level Allocation for Multiple-Bits-Per-Cell RRAM,” ICCAD 2023
