Hui Chen

Orcid: 0000-0003-4180-5801

Affiliations:
  • Tsinghua University, School of Software, Beijing, China


According to our database1, Hui Chen authored at least 80 papers between 2017 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing.
CoRR, May, 2026

CAIT: Triple-Win Compression Toward High Accuracy, Fast Inference, and Favorable Transferability for ViTs.
IEEE Trans. Pattern Anal. Mach. Intell., February, 2026

LLMI3D: MLLM-Based 3D Perception From a Single 2D Image.
IEEE Trans. Multim., 2026

2025
OOCO: Latency-disaggregated Architecture for Online-Offline Co-locate LLM Serving.
CoRR, November, 2025

PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning.
CoRR, October, 2025

xLLM Technical Report.
CoRR, October, 2025

Neutralizing Token Aggregation via Information Augmentation for Efficient Test-Time Adaptation.
CoRR, August, 2025

Cream of the Crop: Harvesting Rich, Scalable and Transferable Multi-Modal Data for Instruction Fine-Tuning.
CoRR, March, 2025

YOLOE: Real-Time Seeing Anything.
CoRR, March, 2025

Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts.
CoRR, February, 2025

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs.
CoRR, February, 2025

UniAttn: Reducing Inference Costs via Softmax Unification for Post-Training LLMs.
CoRR, February, 2025

Cross-Modality Prompts: Few-Shot Multi-Label Recognition With Single-Label Training.
IEEE Trans. Multim., 2025

Source-Free Object Detection With Detection Transformer.
IEEE Trans. Image Process., 2025

DAR-Prompt: Dynamic Regulation in Prompt Tuning for Multi-Label Zero-Shot Learning.
IEEE Trans. Image Process., 2025

Multi-source multi-modal domain adaptation.
Inf. Fusion, 2025

AD<sup>2</sup>: Anomaly Detection During Training an Distillation-Based Anomaly Detection Model.
Proceedings of the Pattern Recognition and Computer Vision - 8th Chinese Conference, 2025

Mitigating Hallucinations in Multi-modal Large Language Models via Image Token Attention-Guided Decoding.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations.
Proceedings of the 33rd ACM International Conference on Multimedia, 2025

Exploiting Position Information in Convolutional Kernels for Structural Re-parameterization.
Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025

YOLOE: Real-Time Seeing Anythi.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

LBPE: Long-token-first Tokenization to Improve Large Language Models.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Temporal Scaling Law for Large Language Models.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Fast Quiet-STaR: Thinking Without Thought Tokens.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

LSNet: See Large, Focus Small.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models.
Proceedings of the 31st International Conference on Computational Linguistics, 2025

Can Sequential Persuasion Strategies Referencing Specific Purposes Enhance the Persuasiveness of Online Requests? A Case Study.
Proceedings of the 47th Annual Meeting of the Cognitive Science Society, 2025

Extending LLM Context Window with Adaptive Grouped Positional Encoding: A Training-Free Method.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning.
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal.
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024
YOLO-UniOW: Efficient Universal Open-World Object Detection.
CoRR, 2024

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs.
CoRR, 2024

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation.
CoRR, 2024

LLMI3D: Empowering LLM with 3D Perception from a Single 2D Image.
CoRR, 2024

MaskMoE: Boosting Token-Level Learning via Routing Mask in Mixture-of-Experts.
CoRR, 2024

Scaffold-BPE: Enhancing Byte Pair Encoding with Simple and Effective Scaffold Token Removal.
CoRR, 2024

Temporal Scaling Law for Large Language Models.
CoRR, 2024

YOLOv10: Real-Time End-to-End Object Detection.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2024, 2024

Multi-Label Learning with Block Diagonal Labels.
Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

More is Better: Deep Domain Adaptation with Multiple Sources.
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

TaD: A Plug-and-Play Task-Aware Decoding Method to Better Adapt LLMs on Downstream Tasks.
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

A Simple Confidence-Supervised Model for High-Resolution Defect Recognition.
Proceedings of the 8th International Conference on Robotics, Control and Automation, 2024

PYRA: Parallel Yielding Re-activation for Training-Inference Efficient Task Adaptation.
Proceedings of the Computer Vision - ECCV 2024, 2024

Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence.
Proceedings of the Computer Vision - ECCV 2024, 2024

Quantized Prompt for Efficient Generalization of Vision-Language Models.
Proceedings of the Computer Vision - ECCV 2024, 2024

Context Enhancement with Reconstruction as Sequence for Unified Unsupervised Anomaly Detection.
Proceedings of the ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, 2024

Rep ViT: Revisiting Mobile CNN From ViT Perspective.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

One-dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Geometry-Guided Domain Generalization for Monocular 3D Object Detection.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
GPro3D: Deriving 3D BBox from ground plane in monocular 3D object detection.
Neurocomputing, December, 2023

Re-parameterized Low-rank Prompt: Generalize a Vision-Language Model within 0.5K Parameters.
CoRR, 2023

RepViT-SAM: Towards Real-Time Segmenting Anything.
CoRR, 2023

InfoEntropy Loss to Mitigate Bias of Learning Difficulties for Generative Language Models.
CoRR, 2023

CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs.
CoRR, 2023

RepViT: Revisiting Mobile CNN From ViT Perspective.
CoRR, 2023

Consolidator: Mergeable Adapter with Grouped Connections for Visual Adaptation.
CoRR, 2023

Hierarchical Prompt Learning Using CLIP for Multi-label Classification with Single Positive Labels.
Proceedings of the 31st ACM International Conference on Multimedia, 2023

Consolidator: Mergable Adapter with Group Connections for Visual Adaptation.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Box-Level Active Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection.
CoRR, 2022

2021
Image Captioning with Memorized Knowledge.
Cogn. Comput., 2021

2020
ACMNet: Adaptive Confidence Matching Network for Human Behavior Analysis via Cross-modal Retrieval.
ACM Trans. Multim. Comput. Commun. Appl., 2020

IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

A Consistent Address Allocation Algorithm Mitigating Address Conflict for Large-Scale LoRa-Enabled IoT Networks.
Proceedings of the 23rd IEEE International Conference on Computational Science and Engineering, 2020

Enhanced Meta-Learning for Cross-Lingual Named Entity Recognition with Minimal Resources.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
Neural Image Caption Generation with Weighted Training and Reference.
Cogn. Comput., 2019

PDANet: Polarity-consistent Deep Attention Network for Fine-grained Visual Emotion Regression.
Proceedings of the 27th ACM International Conference on Multimedia, 2019

Cross-Modal Image-Text Retrieval with Semantic Consistency.
Proceedings of the 27th ACM International Conference on Multimedia, 2019

An Adaptive MAC Layer Energy-Saving Algorithm for ZigBee-Enabled IoT Networks.
Proceedings of the Smart City and Informatization - 7th International Conference, 2019

GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

2018
Show, Observe and Tell: Attribute-driven Attention Model for Image Captioning.
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018

Attend to Knowledge: Memory-Enhanced Attention Network for Image Captioning.
Proceedings of the Advances in Brain Inspired Cognitive Systems, 2018

Temporal-Difference Learning With Sampling Baseline for Image Captioning.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

2017
Reference Based LSTM for Image Captioning.
Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017


  Loading...