Researcher — paper.dinq.me

2026 顶会论文

作者位次 #11/12ICLR 2026Poster· Social Aspects / Fairness, Equity, Justice and Safety

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs

Junxiao Yang · Jinzhe Tu · Haoran Liu · Xiaoce Wang · Chujie Zheng · Zhexin Zhang · Shiyao Cui · Caishun Chen · Tiantian He · Hongning Wang · Yew-Soon Ong · Minlie Huang

社会与人本推理安全OpenReview

作者位次 #6/8ICLR 2026Poster· Applications / Language, Speech and Dialog

FlowSearcher: Synthesizing Memory-Guided Agentic Workflows for Web Information Seeking

Keyi Xiang · Zeyu Feng · Zhuoyi Lin · YUEMING LYU · Boyuan Shi · Yew-Soon Ong · Ivor W. Tsang · Haiyan Yin

检索与知识智能体与工具多模态OpenReview

作者位次 #3/4ICLR 2026Poster· Reinforcement Learning / Batch/Offline

Masked Skill Token Training for Hierarchical Off-Dynamics Transfer

Zeyu Feng · Haiyan Yin · Yew-Soon Ong · Harold Soh

强化学习与后训练OpenReview

作者位次 #10/10ICLR 2026Poster

Tug-of-War No More: Harmonizing Accuracy and Robustness in Vision-Language Models via Stability-Aware Task Vector Merging

Junhao Dong · Xinghua Qu · Cong Zhang · Qi Rong Sua · Nguyen Duc Thai · Wenbo Pan · Xinfeng Li · Tongliang Liu · Piotr Koniusz · Yew-Soon Ong

安全多模态OpenReview

作者位次 #5/5ICLR 2026Poster· Optimization / Everything Else

An Agentic Framework with LLMs for Solving Complex Vehicle Routing Problems

Ni Zhang · Zhiguang Cao · Jianan Zhou · Cong Zhang · Yew-Soon Ong

智能体与工具OpenReview

作者位次 #3/3CVPR 2026Oral· Computer Vision & Pattern Recognition

Learning Latent Concepts for Detecting Out-of-Distribution Objects

Ting Peng · Junhao Dong · Yew-Soon Ong

多模态OpenReview 项目页

作者位次 #4/5CVPR 2026Poster· Computer Vision & Pattern Recognition

Hierarchically Robust Zero-shot Vision-language Models

Junhao Dong · Yifei Zhang · Hao Zhu · Yew-Soon Ong · Piotr Koniusz

多模态OpenReview 项目页

作者位次 #2/3SIGIR 2026Oral· Information Retrieval (Full)

Agentic Spatio-Temporal Grounding via Collaborative Reasoning

Heng Zhao · Yew-Soon Ong · Joey Tianyi Zhou

摘要

Spatio-Temporal Video Grounding (STVG) aims to retrieve the spatio-temporal tube of a target object or person in a video given a text query. Most existing approaches perform frame-wise spatial localization within a predicted temporal span, resulting in redundant computation, heavy supervision req...

多模态推理评测与基准OpenReview

作者位次 #5/7KDD 2026Oral· Knowledge Discovery & Data Mining

Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs

Tianyi Tang · Zhuoyi Lin · Zeyu Feng · Tianyi Ma · Yew-Soon Ong · Ivor W. Tsang · Haiyan Yin

推理多模态评测与基准OpenReview

作者位次 #5/6KDD 2026Oral· Knowledge Discovery & Data Mining

Ready to Sim? Inverse Parametric Building Modeling via Universal Anchor Representation for Urban Simulation

Jaeyeon Kim · Po-Yen Lai · Jian Cheng Wong · Chin Chun Ooi · Yew-Soon Ong · Ivor W. Tsang

可解释性检索与知识社会与人本OpenReview

作者位次 #6/7AAAI 2026Poster· Artificial Intelligence

Pushing Rendering Boundaries: Hard Gaussian Splatting

Qingshan Xu · Jiequan Cui · Xuanyu Yi · Yuxuan Wang · Yuan Zhou · Yew-Soon Ong · Hanwang Zhang

OpenReview

作者位次 #8/9AAAI 2026Poster· Artificial Intelligence

NeuSpring: Neural Spring Fields for Reconstruction and Simulation of Deformable Objects from Videos

Qingshan Xu · Jiao Liu · Shangshu Yu · Yuxuan Wang · Yuan Zhou · Junbao Zhou · Jiequan Cui · Yew-Soon Ong · Hanwang Zhang

多模态社会与人本OpenReview

作者位次 #4/4AAAI 2026Poster· Artificial Intelligence

Scale-Net: A Hierarchical U-Net Framework for Cross-Scale Generalization in Multi-Task Vehicle Routing

Suyu Liu · Zhiguang Cao · nan yin · Yew-Soon Ong

理论与学习动力学OpenReview

Yew-Soon Ong

获取完整研究档案

联系方式