9 citations · 15 across the 18 of their papers we have counts for
19 papers
Law And Order: Tax Law Autoformalization
Sophia Simeng Han, Yoshiki Takashima, Anjiang Wei +2
Legal systems are increasingly implemented through software, yet scalable methods for translating legal texts into accurate symbolic representations remain underdeveloped. We study…
Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
Lin Shi, Haowei Lin, Zixuan Zhu +123
Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a…
HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL
Zhi Li, Songkun Yan, Jie Cao +4
Calibrating distributed hydrologic models is a critical bottleneck across operational water resources management - streamflow prediction, reservoir operation, drought monitoring, i…
AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
Genghan Zhang, Shaowei Zhu, Anjiang Wei +6
We present AccelOpt, a self-improving large language model (LLM) agentic system that autonomously optimizes kernels for emerging AI acclerators, eliminating the need for expert-pro…
Equivalence Checking of ML GPU Kernels
Benjamin Driscoll, Kshitij Dubey, Anjiang Wei +3
With the rapid progress of deep learning and large language models (LLMs), companies spend enormous sums executing GPU kernels. These kernels have become prime targets for aggressi…
Quokka: Accelerating Program Verification with LLMs via Invariant Synthesis
Anjiang Wei, Tianran Sun, Tarun Suresh +3
Program verification relies on loop invariants, yet automatically discovering strong invariants remains a long-standing challenge. We investigate whether large language models (LLM…
Astra: A Multi-Agent System for GPU Kernel Performance Optimization
Anjiang Wei, Tianran Sun, Yogesh Seenichamy +5
GPU kernel optimization has long been a central challenge at the intersection of high-performance computing and machine learning. Efficient kernels are crucial for accelerating lar…
Task-Based Programming for Adaptive Mesh Refinement in Compressible Flow Simulations
Anjiang Wei, Hang Song, Mert Hidayetoglu +3
High-order solvers for compressible flows are vital in scientific applications. Adaptive mesh refinement (AMR) is a key technique for reducing computational cost by concentrating r…
Mapple: A Domain-Specific Language for Mapping Distributed Programs
Anjiang Wei, Rohan Yadav, Hang Song +3
Optimizing parallel programs for distributed systems is a complex task, often requiring significant code modifications. Task-based programming systems improve modularity by separat…
SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas
Anjiang Wei, Yuheng Wu, Yingjia Wan +6
We introduce SATBench, a benchmark for evaluating the logical reasoning capabilities of large language models (LLMs) through logical puzzles derived from Boolean satisfiability (SA…
SuperCoder: Assembly Program Superoptimization with Large Language Models
Anjiang Wei, Tarun Suresh, Huanmi Tan +4
Superoptimization is the task of transforming a program into a faster one, and ideally the very fastest possible one, while preserving its input-output behavior. In this work, we i…
Can Code Language Models Learn Clarification-Seeking Behaviors?
Jie JW Wu, Manav Chaudhary, Davit Abrahamyan +3
Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, a gap remains between their output and the problem-solving strategies of h…
VeriCoder: Enhancing LLM-Based RTL Code Generation through Functional Correctness Validation
Anjiang Wei, Huanmi Tan, Tarun Suresh +5
Recent advances in Large Language Models (LLMs) have sparked growing interest in applying them to Electronic Design Automation (EDA) tasks, particularly Register Transfer Level (RT…
CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis
Anjiang Wei, Tarun Suresh, Jiannan Cao +6
Inductive program synthesis, or programming by example, requires synthesizing functions from input-output examples that generalize to unseen inputs. While large language model agen…
EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checking
Anjiang Wei, Jiannan Cao, Ran Li +8
As large language models (LLMs) become integral to code-related tasks, a central question emerges: Do LLMs truly understand program semantics? We introduce EquiBench, a new benchma…
Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation
Yuhui Zhang, Yuchang Su, Yiming Liu +9
The rapid development of vision language models (VLMs) demands rigorous and reliable evaluation. However, current visual question answering (VQA) benchmarks often depend on open-en…
Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces
Anjiang Wei, Allen Nie, Thiago S. F. X. Teixeira +4
Modern scientific discovery increasingly relies on high-performance computing for complex modeling and simulation. A key challenge in improving parallel program performance is effi…
Fuzzing Deep-Learning Libraries via Automated Relational API Inference
Yinlin Deng, Chenyuan Yang, Anjiang Wei +1
A growing body of research has been dedicated to DL model testing. However, there is still limited work on testing DL libraries, which serve as the foundations for building, traini…
Free Lunch for Testing: Fuzzing Deep-Learning Libraries from Open Source
Anjiang Wei, Yinlin Deng, Chenyuan Yang +1
Deep learning (DL) systems can make our life much easier, and thus are gaining more and more attention from both academia and industry. Meanwhile, bugs in DL systems can be disastr…