Researcher — paper.dinq.me

2026 顶会论文

作者位次 #5/6ICML 2026Poster· Social Aspects / Safety

Reranker Helps, but Not Enough: Towards Strong Poisoning Attacks Against Retrieval-Augmented Generation

Xiaokun Yang · Jian Liang · Yesheng Liu · Xin Xiong · Ran He · Tieniu Tan

安全检索与知识社会与人本OpenReview

作者位次 #6/6ICML 2026Poster· Social Aspects / Safety

Mitigating the Safety–Utility Trade-off in LLM Alignment via Adaptive Safe Context Learning

Yanbo Wang · Minzheng Wang · Jian Liang · Lu Wang · Yongcan Yu · Ran He

对齐与偏好安全社会与人本OpenReview

作者位次 #6/6ICML 2026Poster· Applications / Computer Vision

Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution

Hongbo Wang · Huaibo Huang · Pin Wang · Jinhua Hao · Chao Zhou · Ran He

多模态对齐与偏好安全OpenReview

作者位次 #8/9ICML 2026Poster· Reinforcement Learning / Deep RL

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning

Zihan Lin · Xiaohan Wang · Jie Cao · Jiajun Chai · Li Wang · Xiaodong Lu · Wei Lin · Ran He · Guojun Yin

强化学习与后训练推理OpenReview

作者位次 #3/4ICML 2026Poster· General Machine Learning / Transfer, Multitask and Meta-learning

USE: A Unified Self-Ensembling Framework for Test-Time Prompt Tuning

Siru Jiang · Jian Liang · Ran He · Tieniu Tan

OpenReview

作者位次 #8/9ICML 2026Poster· Deep Learning / Large Language Models

Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion

Lijiang Li · zuwei long · Yunhang Shen · Heting Gao · Haoyu Cao · Xing Sun · Caifeng Shan · Ran He · Chaoyou Fu

多模态OpenReview

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

Think-Then-Generate: Structural Chain-of-Thought Reasoning for Consistent 3D Generation

Xinyue Liu · Jin Liu · Hongbo Wang · Ran He · Huaibo Huang

推理多模态OpenReview 项目页

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

Think 360deg: Beyond Depth: Evaluating the Width-centric Reasoning Capability of MLLMs

Mingrui Chen · Hexiong Yang · Haogeng Liu · Huaibo Huang · Ran He

推理多模态评测与基准OpenReview 项目页

作者位次 #6/6CVPR 2026Poster· Computer Vision & Pattern Recognition

Towards Fine-Grained Attribution: Instance-Aware Preference Optimization for Aligning Diffusion Models

Jiayang Sun · Pin Wang · Hongbo Wang · Xinyue Liu · Huaibo Huang · Ran He

对齐与偏好多模态OpenReview 项目页

作者位次 #6/6CVPR 2026Poster· Computer Vision & Pattern Recognition

Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Models

Shiran Ge · Chenyi Huang · Yuang Ai · Qihang Fan · Huaibo Huang · Ran He

多模态强化学习与后训练效率与系统OpenReview 项目页

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

Random Wins All: Rethinking Grouping Strategies for Vision Tokens

Qihang Fan · Yuang Ai · Huaibo Huang · Ran He

多模态OpenReview 项目页

Ran He

获取完整研究档案

联系方式