Researcher — paper.dinq.me

2026 顶会论文

作者位次 #8/8ICLR 2026Poster· Computer Vision / Image and Video Generation

Learnable Sparsity for Vision Generative Models

Yang Zhang · Er Jin · Wenzhong Liang · Yanfei Dong · Ashkan Khakzar · Philip Torr · Johannes Stegmaier · Kenji Kawaguchi

多模态效率与系统OpenReview

作者位次 #3/5ICLR 2026Poster· Applications / Physics

HSG-12M: A Large-Scale Benchmark of Spatial Multigraphs from the Energy Spectra of Non-Hermitian Crystals

Xianquan Yan · Hakan Akgün · Kenji Kawaguchi · Duane Loh · Ching Lee

评测与基准OpenReview

作者位次 #4/5ICLR 2026Poster· Social Aspects / Trustworthy Machine Learning

SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From

Yao Tong · Haonan Wang · Siquan Li · Kenji Kawaguchi · Tianyang Hu

社会与人本OpenReview

作者位次 #3/4ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders

DeRaDiff: Denoising Time Realignment of Diffusion Models

Ratnavibusena Don Shahain Manujith · Teoh Tzun · Kenji Kawaguchi · Yang Zhang

对齐与偏好OpenReview

作者位次 #6/7ICLR 2026Poster· Deep Learning / Attention Mechanisms

PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention

Haonan Wang · Brian Chen · Siquan Li · Liang Xinhe · Hwee Lee · Kenji Kawaguchi · Tianyang Hu

可解释性检索与知识OpenReview

作者位次 #5/7ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

Fostering Video Reasoning via Next-Event Prediction

Haonan Wang · Hongfu Liu · Xiangyan Liu · Chao Du · Kenji Kawaguchi · Ye Wang · Tianyu Pang

多模态推理OpenReview

作者位次 #3/4ICLR 2026Poster· Deep Learning / Everything Else

Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning

Haonan Wang · Chao Du · Kenji Kawaguchi · Tianyu Pang

推理OpenReview

作者位次 #4/6ACL 2026Findings· Findings of ACL

C omic VQA : A Benchmark for Visual Reasoning in Multimodal LLM s

Esther Gan · Hannah Brown · David Herel · Kenji Kawaguchi · Min-Yen Kan · Michael Qizhe Shieh

摘要

We introduce Comic Visual Question Answering ( ComicVQA ), a comics-based benchmark for evaluating MLLMs on visual reasoning. ComicVQA comprises of (i) Missing Panel Prediction , testing fine-grained visual grounding and (ii) Panel Sorting , which evaluates sequential narrative understanding. Pro...

多模态评测与基准推理OpenReview 项目页

Kenji Kawaguchi

获取完整研究档案

联系方式