Peng Ye

Orcid: 0000-0002-6272-2792

Affiliations:

Chinese University of Hong Kong
Shanghai Artificial Intelligence Laboratory, China
Fudan University, School of Information Science and Technology, Shanghai, China (PhD 2024)

According to our database¹, Peng Ye authored at least 92 papers between 2022 and 2025.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2025

RegionE: Adaptive Region-Aware Generation for Efficient Image Editing.

[BibT_eX]

[DOI]

CoRR, October, 2025

scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration.

[BibT_eX]

[DOI]

CoRR, October, 2025

ICL-Router: In-Context Learned Model Representations for LLM Routing.

[BibT_eX]

[DOI]

CoRR, October, 2025

The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback.

[BibT_eX]

[DOI]

CoRR, October, 2025

Learning Compact Representations of LLM Abilities via Item Response Theory.

[BibT_eX]

[DOI]

CoRR, October, 2025

PhysicsMinions: Winning Gold Medals in the Latest Physics Olympiads with a Coevolutionary Multimodal Multi-Agent System.

[BibT_eX]

[DOI]

CoRR, September, 2025

SCI-Verifier: Scientific Verifier with Thinking.

[BibT_eX]

[DOI]

CoRR, September, 2025

Sequential Token Merging: Revisiting Hidden States.

[BibT_eX]

[DOI]

CoRR, September, 2025

HiPhO: How Far Are (M)LLMs from Humans in the Latest High School Physics Olympiad Benchmark?

[BibT_eX]

[DOI]

CoRR, September, 2025

Dynamic Model Merging With Mixture of Weights.

[BibT_eX]

[DOI]

IEEE Trans. Circuits Syst. Video Technol., August, 2025

Stimulative Training++: Go Beyond the Performance Limits of Residual Networks.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., August, 2025

Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing.

[BibT_eX]

[DOI]

CoRR, August, 2025

Wisdom of the Crowd: Reinforcement Learning from Coevolutionary Collective Feedback.

[BibT_eX]

[DOI]

CoRR, August, 2025

CTTS: Collective Test-Time Scaling.

[BibT_eX]

[DOI]

CoRR, August, 2025

Open-Source LLMs Collaboration Beats Closed-Source LLMs: A Scalable Multi-Agent System.

[BibT_eX]

[DOI]

CoRR, July, 2025

Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning.

[BibT_eX]

[DOI]

CoRR, July, 2025

PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding.

[BibT_eX]

[DOI]

CoRR, June, 2025

Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers.

[BibT_eX]

[DOI]

CoRR, June, 2025

Control-R: Towards controllable test-time scaling.

[BibT_eX]

[DOI]

CoRR, June, 2025

Scaling Physical Reasoning with the PHYSICS Dataset.

[BibT_eX]

[DOI]

CoRR, June, 2025

BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-Task Dense Predictions.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., May, 2025

Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models.

[BibT_eX]

[DOI]

CoRR, May, 2025

The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants.

[BibT_eX]

[DOI]

CoRR, May, 2025

Doc-CoB: Enhancing Multi-Modal Document Understanding with Visual Chain-of-Boxes Reasoning.

[BibT_eX]

[DOI]

CoRR, May, 2025

NovelSeek: When Agent Becomes the Scientist - Building Closed-Loop System from Hypothesis to Verification.

[BibT_eX]

[DOI]

CoRR, May, 2025

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging.

[BibT_eX]

[DOI]

CoRR, May, 2025

Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression.

[BibT_eX]

[DOI]

CoRR, May, 2025

Dynamic Base model Shift for Delta Compression.

[BibT_eX]

[DOI]

CoRR, May, 2025

When Dynamic Data Selection Meets Data Augmentation.

[BibT_eX]

[DOI]

CoRR, May, 2025

Consistency-aware Self-Training for Iterative-based Stereo Matching.

[BibT_eX]

[DOI]

CoRR, March, 2025

FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding.

[BibT_eX]

[DOI]

CoRR, March, 2025

TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models.

[BibT_eX]

[DOI]

CoRR, March, 2025

Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs.

[BibT_eX]

[DOI]

CoRR, March, 2025

Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform.

[BibT_eX]

[DOI]

CoRR, March, 2025

Nature-Inspired Population-Based Evolution of Large Language Models.

[BibT_eX]

[DOI]

CoRR, March, 2025

Efficient Architecture Search via Bi-Level Data Pruning.

[BibT_eX]

[DOI]

IEEE Trans. Circuits Syst. Video Technol., February, 2025

GoRA: Gradient-driven Adaptive Low Rank Adaptation.

[BibT_eX]

[DOI]

CoRR, February, 2025

Multi-Level Decoupled Relational Distillation for Heterogeneous Architectures.

[BibT_eX]

[DOI]

CoRR, February, 2025

DualMamba: A Lightweight Spectral-Spatial Mamba-Convolution Network for Hyperspectral Image Classification.

[BibT_eX]

[DOI]

IEEE Trans. Geosci. Remote. Sens., 2025

MF-ID: A Benchmark and Approach for Multi-Category Fine-Grained Intrusion Detection.

[BibT_eX]

[DOI]

IEEE Trans Autom. Sci. Eng., 2025

Enhancing visibility in hazy conditions: A multimodal multispectral image dehazing approach.

[BibT_eX]

[DOI]

Mohammad Mahdizadeh

Peng Ye

Shaoqing Zhao

J. Vis. Commun. Image Represent., 2025

ClipSAM: CLIP and SAM collaboration for zero-shot anomaly segmentation.

[BibT_eX]

[DOI]

Neurocomputing, 2025

Illuminating the night: A light source-aware and exposure-balanced low-light enhancement approach for real nighttime scenes.

[BibT_eX]

[DOI]

Mohammad Mahdizadeh

Shijie Chen

Peng Ye

Digit. Signal Process., 2025

A CLIP-Powered Framework for Robust and Generalizable Data Selection.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Revisiting Convolution Architecture in the Realm of DNA Foundation Models.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Less is More: Efficient Model Merging with Binary Task Switch.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

All-in-One: Transferring Vision Foundation Models into Stereo Matching.

[BibT_eX]

[DOI]

Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024

MMID-Bench: A Comprehensive Benchmark for Multi-Domain Multi-Category Intrusion Detection.

[BibT_eX]

[DOI]

IEEE Trans. Intell. Veh., October, 2024

DeNKD: Decoupled Non-Target Knowledge Distillation for Complementing Transformer-Based Unsupervised Domain Adaptation.

[BibT_eX]

[DOI]

IEEE Trans. Circuits Syst. Video Technol., May, 2024

Exploring Multi-Timestep Multi-Stage Diffusion Features for Hyperspectral Image Classification.

[BibT_eX]

[DOI]

IEEE Trans. Geosci. Remote. Sens., 2024

U²ConvFormer: Marrying and Evolving Nested U-Net and Scale-Aware Transformer for Hyperspectral Image Classification.

[BibT_eX]

[DOI]

IEEE Trans. Geosci. Remote. Sens., 2024

Latency-Aware Neural Architecture Performance Predictor With Query-to-Tier Technique.

[BibT_eX]

[DOI]

IEEE Trans. Circuits Syst. Video Technol., 2024

Biology Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

COMET: Benchmark for Comprehensive Biological Multi-omics Evaluation Tasks and Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

DynaSurfGS: Dynamic Surface Reconstruction with Planar-based Gaussian Splatting.

[BibT_eX]

[DOI]

CoRR, 2024

Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision.

[BibT_eX]

[DOI]

CoRR, 2024

Δ-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers.

[BibT_eX]

[DOI]

Christos-Savvas Bouganis

Yiren Zhao

Tao Chen

CoRR, 2024

BEACON: Benchmark for Comprehensive RNA Tasks and Language Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

EMR-Merging: Tuning-Free High-Performance Model Merging.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

FNP: Fourier Neural Processes for Arbitrary-Resolution Data Assimilation.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Ada-iD: Active Domain Adaptation for Intrusion Detection.

[BibT_eX]

[DOI]

Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

Multi-dimensional Search with Strip Convolution and R-Squared Loss for Lane Detection.

[BibT_eX]

[DOI]

Proceedings of the International Joint Conference on Neural Networks, 2024

CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modelling.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Enhanced Sparsification via Stimulative Training.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Boosting Residual Networks with Group Knowledge.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Automatic Loss Function Search for Adversarial Unsupervised Domain Adaptation.

[BibT_eX]

[DOI]

IEEE Trans. Circuits Syst. Video Technol., October, 2023

Hyperspectral Image Classification Using Spectral-Spatial Token Enhanced Transformer With Hash-Based Positional Embedding.

[BibT_eX]

[DOI]

IEEE Trans. Geosci. Remote. Sens., 2023

Merging Vision Transformers from Different Tasks and Domains.

[BibT_eX]

[DOI]

CoRR, 2023

Partial Fine-Tuning: A Successor to Full Fine-Tuning for Vision Transformers.

[BibT_eX]

[DOI]

CoRR, 2023

Rethinking of Feature Interaction for Multi-task Learning on Dense Prediction.

[BibT_eX]

[DOI]

CoRR, 2023

Towards an End-to-End Artificial Intelligence Driven Global Weather Forecasting System.

[BibT_eX]

[DOI]

CoRR, 2023

Rethinking the BERT-like Pretraining for DNA Sequences.

[BibT_eX]

[DOI]

CoRR, 2023

StructChart: Perception, Structuring, Reasoning for Visual Chart Understanding.

[BibT_eX]

[DOI]

CoRR, 2023

RFD-ECNet: Extreme Underwater Image Compression with Reference to Feature Dictionar.

[BibT_eX]

[DOI]

CoRR, 2023

Experts Weights Averaging: A New General Training Scheme for Vision Transformers.

[BibT_eX]

[DOI]

CoRR, 2023

When Hyperspectral Image Classification Meets Diffusion Models: An Unsupervised Feature Learning Framework.

[BibT_eX]

[DOI]

CoRR, 2023

β-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search.

[BibT_eX]

[DOI]

CoRR, 2023

RFD-ECNet: Extreme Underwater Image Compression with Reference to Feature Dictionary.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

A2S-NAS: Asymmetric Spectral-Spatial Neural Architecture Search for Hyperspectral Image Classification.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

JNDMix: Jnd-Based Data Augmentation for No-Reference Image Quality Assessment.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., 2022

Neural Architecture Ranker.

[BibT_eX]

[DOI]

CoRR, 2022

Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier Search.

[BibT_eX]

[DOI]

Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

β-DARTS: Beta-Decay Regularization for Differentiable Architecture Search.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Peng Ye

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...