Researcher — paper.dinq.me

2026 顶会论文

作者位次 #7/7ICML 2026Poster· Applications / Robotics

See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model

Yixu Feng · Zinan Zhao · Yanxiang Ma · Chenghao Xia · Chengbin Du · Yunke Wang · Chang Xu

多模态效率与系统理论与学习动力学OpenReview

作者位次 #8/8ICML 2026Poster· Applications / Robotics

VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model

Wenhao Li · Xiu Su · Yichao Cao · Hongyan Xu · Xiaobo Xia · Shan You · Yi Chen · Chang Xu

推理OpenReview

作者位次 #9/9ICML 2026Poster· Applications / Robotics

Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery

Wenhao Li · Xiu Su · Dan Niu · Yichao Cao · Hongyan Xu · Zhe Qu · Lei Fan · Shan You · Chang Xu

推理OpenReview

作者位次 #4/6ICML 2026Poster· Deep Learning / Large Language Models

Block Rotation is All You Need for MXFP4 Quantization

Yuantian Shao · Peisong Wang · Yuanteng Chen · Chang Xu · Zhihui Wei · Jian Cheng

效率与系统OpenReview

作者位次 #5/5ICML 2026Poster· Applications / Computer Vision

Sample Margin-Aware Recalibration of Temperature Scaling

Haolan Guo · Linwei Tao · Haoyang Luo · Minjing Dong · Chang Xu

多模态OpenReview

作者位次 #6/7ICML 2026Poster· Deep Learning / Large Language Models

Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Vision-Language Models

Chengcheng Wang · Jianyuan Guo · Hongguang Li · Yuchuan Tian · Ying Nie · Chang Xu · Kai Han

多模态长上下文与架构OpenReview

作者位次 #4/4ICML 2026Poster· Deep Learning / Large Language Models

HiCI: Hierarchical Construction–Integration for Long-Context Attention

Xiangyu Zeng · Qi Xu · Yunke Wang · Chang Xu

长上下文与架构OpenReview

作者位次 #8/8ICML 2026Poster· Applications / Robotics

Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation

Chenyu Hui · Xiaodi Huang · Siyu Xu · Yunke Wang · Shan You · Fei Wang · Tao Huang · Chang Xu

多模态效率与系统社会与人本OpenReview

作者位次 #6/7ICML 2026Poster· Deep Learning / Generative Models and Autoencoders

Contrastive Flow Map Matching

Junyu Zhang · Daochang Liu · Younghyun Kim · Jong Hwan Ko · Shichao Zhang · Chang Xu · Eunbyung Park

OpenReview

作者位次 #7/7ICML 2026Poster· Deep Learning / Generative Models and Autoencoders

Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance

Ky Dan Nguyen · Hoang Lam Tran · Anh-Dung Dinh · Daochang Liu · Weidong Cai · Xiuying Wang · Chang Xu