6 papers
Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
Shihao Zhang, Yunzhi Li, Yuguang Yan +4
Recent text-to-video (T2V) diffusion models rely heavily on auxiliary reward signals (e.g., via reward models or DPO) to align generated content with human aesthetics and improve r…
Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive Rewards
Shihao Zhang, Xiaoman Wang, Yuan Liu +2
Reinforcement learning has recently shown promise in improving large language models for Text-to-SQL generation, yet existing methods typically optimize one-shot rewards defined ov…
From Prediction to Justification: Aligning Sentiment Reasoning with Human Rationale via Reinforcement Learning
Shihao Zhang, Ziwei Wang, Jie Zhou +6
While Aspect-based Sentiment Analysis (ABSA) systems have achieved high accuracy in identifying sentiment polarities, they often operate as "black boxes," lacking the explicit reas…
Improving Deep Regression with Tightness
Shihao Zhang, Yuguang Yan, Angela Yao
For deep regression, preserving the ordinality of the targets with respect to the feature representation improves performance across various tasks. However, a theoretical explanati…
Deep Regression Representation Learning with Topology
Shihao Zhang, kenji kawaguchi, Angela Yao
Most works studying representation learning focus only on classification and neglect regression. Yet, the learning objectives and, therefore, the representation topologies of the t…
Learning to Generate Training Datasets for Robust Semantic Segmentation
Marwane Hariat, Olivier Laurent, Rémi Kazmierczak +4
Semantic segmentation methods have advanced significantly. Still, their robustness to real-world perturbations and object types not seen during training remains a challenge, partic…