Posts by Collection

portfolio

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

publications

DevBench: A Comprehensive Benchmark for Software Development

Published in International Conference on Computational Linguistics (COLING), 2025

A benchmark evaluating LLMs across the entire software development lifecycle: design, environment setup, implementation, acceptance testing, and unit testing.

Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation

Published in International Conference on Learning Representations (ICLR), 2025

ProverGen combines LLM generation with symbolic provers to build ProverQA, a scalable and diverse first-order logic reasoning benchmark.

SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution

Published in Findings of the Association for Computational Linguistics: ACL 2025, 2025

An open-source framework for GitHub issue resolution built from a retrieval module and a code editing module, trained on 110K real issues.

Exploring Confidence as a Reward to Advance LLMs Reasoning

Published in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026

Confidence-as-a-Reward (CRew): a training-free reward signal built from a model’s token-level confidence in its final answer.

Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization

Published in Deep Learning for Code (DL4C) Workshop at ICML 2026, 2026

A framework for high-performance GPU kernel generation that pairs an evaluation-driven evolutionary agent with an evolution-oriented post-training recipe.

How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data

Published in International Conference on Machine Learning (ICML), 2026

TESSY interleaves teacher and student models to synthesize SFT data that keeps the teacher’s reasoning ability while matching the student’s style.

EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning

Published in Annual Meeting of the Association for Computational Linguistics (ACL), 2026

A task-agnostic evolutionary pipeline that jointly synthesizes problems, candidate solutions, and verification artifacts for verifiable learning.

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015