9 papers
Conjecture and Inquiry: Quantifying Software Performance Requirements via Interactive Retrieval-Augmented Preference Elicitation
Shihai Wang, Tao Chen
Since software performance requirements are documented in natural language, quantifying them into mathematical forms is essential for software engineering. Yet, the vagueness in pe…
MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
Baorong Shi, Bo Cui, Boyuan Jiang +17
We present MedXIAOHE, a medical vision-language foundation model designed to advance general-purpose medical understanding and reasoning in real-world clinical applications. MedXIA…
MOOT: a Repository of Many Multi-Objective Optimization Tasks
Tim Menzies, Tao Chen, Yulong Ye +4
Software engineers must make decisions that trade off competing goals (faster vs. cheaper, secure vs. usable, accurate vs. interpretable, etc.). Despite MSR's proven techniques for…
GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
Hongze Tan, Zihan Wang, Jianfei Pan +7
Reinforcement Learning (RL) is pivotal for enhancing Large Language Model (LLM) reasoning, yet mainstream algorithms such as GRPO and DAPO remain constrained by a coarse-grained cr…
CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing
Shanyv Liu, Xuyang Yuan, Tao Chen +5
Graph-based Multi-Agent Systems (MAS) enable complex cyclic workflows but suffer from inefficient static model allocation, where deploying strong models uniformly wastes computatio…
Light over Heavy: Automated Performance Requirements Quantification with Linguistic Inducement
Shihai Wang, Tao Chen
Elicited performance requirements need to be quantified for compliance in different engineering tasks, e.g., configuration tuning and performance testing. Much existing work has re…