影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
86.22/100
前 0.8%
全站排名 #539
发表论文38 篇
平均评分
年均产出12.7 篇/年
Ran He
Full Professor@Institute of automation, Chinese academy of science, Chinese Academy of Sciences·中国·OpenReview
研究方向
generative model · image generation · face recognition · transfer learning · domain adaptation · image superresolution · Representation Learning
20
Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation
ICLR 2026Oral
三作24
ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models
ICLR 2026Poster
通讯29
Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs
ICLR 2026Poster
三作19
VITA-E: A Dual-Model Framework for Real-Time, Interruptible, and Concurrent Human-Robot Interaction
ICLR 2026Rejected
通讯21
Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluation
ICLR 2026Rejected
21
HAD: Hybrid Architecture Distillation for Bridging Large-Transformer Knowledge into Compact Genomic Models
ICLR 2026Rejected
通讯5
ID-Cloak: Crafting Identity-Specific Cloaks Against Personalized Text-to-Image Generation
ICLR 2026Withdrawn
通讯11
PROOF: Perturbation-Robust Noise Finetune via Optimal Transport Information Bottleneck for Highly-Correlated Asset Generation
ICLR 2026Rejected
通讯15
Discrepancy-Aware Knowledge Distillation for Large Language Models
ICLR 2026Rejected
19
Reranker Helps, but Not Enough: Towards Strong Poisoning Attacks Against RAG
ICLR 2026Rejected
10
Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging
ICLR 2026Withdrawn
5
Boosting RL-based Multimodal Reasoning via Difficulty Prior
ICLR 2026Withdrawn
通讯6
InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing
ICLR 2026Withdrawn
5
VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation
ICLR 2026Withdrawn
6
Adaptive Jailbreak Defense: A Self-Evolving Framework for Large Language Models
ICLR 2026Withdrawn
三作5
GAT-Flow: Predictor-Corrector Flow Matching with Graph Attention Network for Crystalline Materials
ICLR 2026Withdrawn
通讯23
DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling
NeurIPS 2025Spotlight
19
LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
ICLR 2025Spotlight
三作16
ZeroPatcher: Training-free Sampler for Video Inpainting and Editing
NeurIPS 2025Poster
三作24
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
NeurIPS 2025Spotlight
通讯24
Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent Debate
ICLR 2025Poster
6
Semantic Equitable Clustering: You Only Iterate Once to Cluster Vision Tokens
ICLR 2025Withdrawn
通讯8
eRAM-V: From Interaction to Integration in Efficient Multimodal Large Language Models
ICLR 2025Rejected
通讯11
Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models
ICML 2025Rejected
三作5
Personalized Prompt Tuning for Unsupervised Federated Learning
ICLR 2025Withdrawn
5
Self-Choose: Leveraging Diverse Reasoning Solutions to Self-Correct Multimodal Large Language Models
ICLR 2025Withdrawn
三作