HF
Hehe Fan
cs.CVcs.AIcs.LGcs.CLcs.MMcs.CEcs.RONeural Networks, ComputerBidirectional transition modelcs.GR
On Valency
published · living versionsW_zgpjrnuw·v1 · currentpublished
VideoMemBench: How Well Do MLLMs Remember in Video Conversations?
with Zhengdong Hu, Chao Wang, Kaituo Feng, Huanjin Yao +2
1 version
Preprints & journals
64 papers in the corpus · 2017–2026Text-to-Motion Generation With Discrete Representations and Large Language Models.42658702 · Zhang, Jianrong, Zhang, Yangsong, Cun, Xiaodong et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;PP
One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement2604.25444v1 · Yixiao Zhou, Dongzhou Cheng, zhiliang wu et al.2026 · 0 citationsarXiv
Variational Rectification Inference for Learning with Noisy Labels2603.17255v1 · Haoliang Sun, Qi Wei, Lei Feng et al.2026 · 17 citationsInternational Journal of Computer Vision, 2025
Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments2603.09740v1 · Haoyuan Li, Rui Liu, Hehe Fan et al.2026 · 1 citationarXiv
Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models2602.09713v2 · Ruisi Zhao, Haoren Zheng, Zongxin Yang et al.2026 · 0 citationsarXiv
OSCAgent: Accelerating the Discovery of Organic Solar Cells with LLM Agents2602.04510v2 · Zhaolin Hu, Zhiliang Wu, Kun Li et al.2026 · 0 citationsarXiv
4DPChat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping2602.03890v3 · Xindan Zhang, Weilong Yan, Yufei Shi et al.2026 · 0 citationsarXiv
Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies2602.01816v1 · Wenjin Hou, Wei Liu, Han Hu et al.2026 · 0 citationsarXiv
DRFormer: A Dual-Regularized Bidirectional Transformer for Person Re-identification2602.01059v1 · Ying Shu, Pujian Zhan, Huiqi Yang et al.2026 · 0 citationsarXiv
TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation2602.00839v1 · Mingwei Li, Hehe Fan, Yi Yang2026 · 0 citationsarXiv
DeMoGen: Towards Decompositional Human Motion Generation with Energy-Based Diffusion Models2512.22324v1 · Jianrong Zhang, Hehe Fan, Yi Yang2025 · 0 citationsarXiv
AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows2511.22357v1 · Zhenglin Zhou, Fan Ma, Chengzhuo Gui et al.2025 · 0 citationsarXiv
ITS3D: Inference-Time Scaling for Text-Guided 3D Diffusion Models2511.22456v1 · Zhenglin Zhou, Fan Ma, Xiaobo Xia et al.2025 · 0 citationsarXiv
Bidirectional transition consistency between multi-domain observations for visual reinforcement learning generalization.41218402 · Hu, Xiaobo, Lin, Youfang, Wang, Jinwen et al.2026 · 0 citationsNeural networks : the official journal of the International Neural Network Society. 2026;195:108265
GraphTARIF: Linear Graph Transformer with Augmented Rank and Improved Focus2510.10631v2 · Zhaolin Hu, Kun Li, Hehe Fan et al.2025 · 1 citationarXiv
Translution: Unifying Self-attention and Convolution for Adaptive and Relative Modeling2510.10060v1 · Hehe Fan, Yi Yang, Mohan Kankanhalli et al.2025 · 0 citationsarXiv
Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding2509.16721v1 · Haoyuan Li, Rui Liu, Hehe Fan et al.2025 · 0 citationsarXiv
Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs2509.10377v1 · Yixiao Zhou, Ziyu Zhao, Dongzhou Cheng et al.2025 · 4 citationsarXiv
Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognition2507.21977v4 · Jihao Gu, Kun Li, Fei Wang et al.2025 · 24 citationsarXiv
TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors2504.12799v2 · Mingwei Li, Pu Pang, Hehe Fan et al.2025 · 6 citationsarXiv
Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion2503.15851v2 · Zhenglin Zhou, Fan Ma, Hehe Fan et al.2025 · 6 citationsarXiv
VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing2502.17258v1 · Xiangpeng Yang, Linchao Zhu, Hehe Fan et al.2025 · 0 citationsarXiv
DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization2502.04370v1 · Zhenglin Zhou, Xiaobo Xia, Fan Ma et al.2025 · 0 citationsarXiv
TV-Dialogue: Crafting Theme-Aware Video Dialogues with Immersive Interaction2501.18940v1 · Sai Wang, Fan Ma, Xinyi Li et al.2025 · 0 citationsarXiv
EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space2412.14706v2 · Jianrong Zhang, Hehe Fan, Yi Yang2024 · 5 citationsarXiv
Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition2412.14719v3 · Kun Li, Dan Guo, Guoliang Chen et al.2024 · 41 citationsarXiv
Microscopic Artificial Intelligence: An Artificial Intelligence Research Roadmap for Molecules, Materials and Proteins10.26434/chemrxiv-2024-z5487 · Hehe Fan, Yi Yang2024 · 0 citationsChemRxiv
InfiniDreamer: Arbitrarily Long Human Motion Generation via Segment Score Distillation2411.18303v2 · Wenjie Zhuo, Fan Ma, Hehe Fan2024 · 6 citationsarXiv
CktGen: Automated Analog Circuit Design with Generative Artificial Intelligence2410.00995v3 · Yuxuan Hou, Hehe Fan, Jianrong Zhang et al.2024 · 0 citationsarXiv
ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning2408.14868v1 · Wenjin Hou, Dingjie Fu, Kun Li et al.2024 · 11 citationsarXiv
Prototype Learning for Micro-gesture Classification2408.03097v1 · Guoliang Chen, Fei Wang, Kun Li et al.2024 · 2 citationsarXiv
VividDreamer: Invariant Score Distillation For Hyper-Realistic Text-to-3D Generation2407.09822v2 · Wenjie Zhuo, Fan Ma, Hehe Fan et al.2024 · 10 citationsarXiv
Prompt-Aware Adapter: Towards Learning Adaptive Visual Tokens for Multimodal Large Language Models2405.15684v1 · Yue Zhang, Hehe Fan, Yi Yang2024 · 3 citationsarXiv
TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment2405.13911v2 · Wei Li, Hehe Fan, Yongkang Wong et al.2024 · 2 citationsarXiv
Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly2405.00181v3 · Hang Du, Sicheng Zhang, Binzhu Xie et al.2024 · 29 citationsarXiv
Clustering for Protein Representation Learning2404.00254v1 · Ruijie Quan, Wenguan Wang, Fan Ma et al.2024 · 11 citationsarXiv
EVA: Zero-shot Accurate Attributes and Multi-Object Video Editing2403.16111v1 · Xiangpeng Yang, Linchao Zhu, Hehe Fan et al.2024 · 0 citationsarXiv
HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting2402.06149v2 · Zhenglin Zhou, Fan Ma, Hehe Fan et al.2024 · 27 citationsarXiv
Hand-Centric Motion Refinement for 3D Hand-Object Interaction via Hierarchical Spatial-Temporal Modeling2401.15987v1 · Yuze Hao, Jianrong Zhang, Tao Zhuo et al.2024 · 5 citationsarXiv
DocMSU: A Comprehensive Benchmark for Document-level Multimodal Sarcasm Understanding2312.16023v1 · Hang Du, Guoshun Nan, Sicheng Zhang et al.2023 · 4 citationsarXiv
Building Category Graphs Representation with Spatial and Temporal Attention for Visual Navigation2312.03327v1 · Xiaobo Hu, Youfang Lin, HeHe Fan et al.2023 · 8 citationsarXiv
Learning Robust Representations via Bidirectional Transition for Visual Reinforcement Learning2312.01915v2 · Xiaobo Hu, Youfang Lin, Yue Liu et al.2023 · 1 citationarXiv
FlowZero: Zero-Shot Text-to-Video Synthesis with LLM-Driven Dynamic Scene Syntax2311.15813v1 · Yu Lu, Linchao Zhu, Hehe Fan et al.2023 · 2 citationsarXiv
Prior-Free Continual Learning with Unlabeled Data in the Wild2310.10417v1 · Tao Zhuo, Zhiyong Cheng, Hehe Fan et al.2023 · 1 citationarXiv
Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos2308.09245v1 · Zhiqiang Shen, Xiaoxiao Sheng, Hehe Fan et al.2023 · 21 citationsarXiv
Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos2308.09247v1 · Xiaoxiao Sheng, Zhiqiang Shen, Gang Xiao et al.2023 · 18 citationsarXiv
DPMix: Mixture of Depth and Point Cloud Video Experts for 4D Action Segmentation2307.16803v1 · Yue Zhang, Hehe Fan, Yi Yang et al.2023 · 2 citationsarXiv
Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering2307.13250v1 · Yi Cheng, Hehe Fan, Dongyun Lin et al.2023 · 18 citationsarXiv
A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 20232307.06569v1 · Yi Cheng, Ziwei Xu, Fen Fang et al.2023 · 0 citationsarXiv
Text to Point Cloud Localization with Relation-Enhanced Transformer2301.05372v1 · Guangzhi Wang, Hehe Fan, Mohan Kankanhalli2023 · 13 citationsarXiv
Career total: 106 works. 64 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.