11 papers
Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled Preference Optimization
Xinyu Qiu, Heng Jia, Zhengwen Zeng +4
Parallel test-time scaling typically trains separate generation and verification models, incurring high training and inference costs. We propose Advantage Decoupled Preference Opti…
3DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization
Yuze Hao, Linchao Zhu, Yi Yang
Inverse design aims to design the input variables of a physical system to optimize a specified objective function, typically formulated as a search or optimization problem. However…
DeltaPhi: Physical States Residual Learning for Neural Operators in Data-Limited PDE Solving
Xihang Yue, Yi Yang, Linchao Zhu
The limited availability of high-quality training data poses a major obstacle in data-driven PDE solving, where expensive data collection and resolution constraints severely impact…
Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data
Shuai Zhao, Yunqiu Xu, Linchao Zhu +1
Large language models~(LLMs) are expected to be helpful, harmless, and honest. In different alignment scenarios, such as safety, confidence, and general preference alignment, binar…
MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs
Yunqiu Xu, Linchao Zhu, Yi Yang
While multimodal large language models (MLLMs) have demonstrated extraordinary vision-language understanding capabilities, their abilities to solve instance-level visual-language p…
Protecting Copyrighted Material with Unique Identifiers in Large Language Model Training
Shuai Zhao, Linchao Zhu, Ruijie Quan +1
A primary concern regarding training large language models (LLMs) is whether they abuse copyrighted online text. With the increasing training data scale and the prevalence of LLMs…