activity
20242026
most citedHPE-CogVLM: Advancing Vision Language Models with a Head Pose Grounding Task

1 citations · 1 across the 3 of their papers we have counts for

collaborators

15 papers

cs.LG2026

HindSearch: Trajectory-Level Hindsight Critique for Search-Augmented Reinforcement Learning

Haowei Liu, Jiamian Wang, Hsin-Tai Wu +2

Search-augmented LM agents are typically trained with a binary exact-match reward, which throws away most of what a failed trajectory tells us about why it failed. We introduce Hin…

cs.LG2026

ReliableTableQA:How Much Supervision Does Reliability Annotation Need?

Huei-Chung Hu, Hsin-Tai Wu, Koyo Kobayashi

We introduce ReliableTableQA, a framework for training an LLM to annotate the statistical reliability of tabular QA results, not whether the query is answerable, but whether the co…

cs.CV20261 cited

HPE-CogVLM: Advancing Vision Language Models with a Head Pose Grounding Task

Yu Tian, Tianqi Shao, Tsukasa Demizu +2

Head pose estimation (HPE) requires a sophisticated understanding of 3D spatial relationships to generate precise yaw, pitch, and roll angles. Previous HPE models, primarily CNN-ba…

cs.CL2025

BookAsSumQA: An Evaluation Framework for Aspect-Based Book Summarization via Question Answering

Ryuhei Miyazato, Ting-Ruen Wei, Xuyang Wu +2

Aspect-based summarization aims to generate summaries that highlight specific aspects of a text, enabling more personalized and targeted summaries. However, its application to book…

cs.CL2025

Does Reasoning Introduce Bias? A Study of Social Bias Evaluation and Mitigation in LLM Reasoning

Xuyang Wu, Jinming Nian, Ting-Ruen Wei +3

Recent advances in large language models (LLMs) have enabled automatic generation of chain-of-thought (CoT) reasoning, leading to strong performance on tasks such as math and code.…

cs.CL2025

Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts

Xuyang Wu, Yuan Wang, Hsin-Tai Wu +2

Large vision-language models (LVLMs) have recently achieved significant progress, demonstrating strong capabilities in open-world visual understanding. However, it is not yet clear…