Linfeng Zhang

Orcid: 0000-0002-3341-183X

Affiliations:

Shanghai Jiao Tong University, China

According to our database¹, Linfeng Zhang authored at least 125 papers between 2007 and 2026.

Collaborative distances:

Dijkstra number² of three.
Erdős number³ of three.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models.

[BibT_eX]

[DOI]

IEEE Trans. Comput. Soc. Syst., April, 2026

Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models.

[BibT_eX]

[DOI]

CoRR, April, 2026

Draft-Refine-Optimize: Self-Evolved Learning for Natural Language to MongoDB Query Generation.

[BibT_eX]

[DOI]

CoRR, April, 2026

StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding.

[BibT_eX]

[DOI]

CoRR, April, 2026

AudioKV: KV Cache Eviction in Efficient Large Audio Language Models.

[BibT_eX]

[DOI]

CoRR, April, 2026

Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, March, 2026

Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models.

[BibT_eX]

[DOI]

CoRR, March, 2026

StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision.

[BibT_eX]

[DOI]

CoRR, March, 2026

Towards Principled Dataset Distillation: A Spectral Distribution Perspective.

[BibT_eX]

[DOI]

CoRR, March, 2026

InterCLIP-MEP: Interactive CLIP and Memory-Enhanced Predictor for Multi-Modal Sarcasm Detection.

[BibT_eX]

[DOI]

ACM Trans. Multim. Comput. Commun. Appl., February, 2026

Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning.

[BibT_eX]

[DOI]

CoRR, February, 2026

OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration.

[BibT_eX]

[DOI]

CoRR, February, 2026

Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction.

[BibT_eX]

[DOI]

CoRR, February, 2026

Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis.

[BibT_eX]

[DOI]

CoRR, February, 2026

Grounding and Enhancing Informativeness and Utility in Dataset Distillation.

[BibT_eX]

[DOI]

CoRR, January, 2026

Forecast Then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

D²Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

UNSEEN: Enhancing Dataset Pruning from a Generalization Perspective.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

ImageBindDC: Compressing Multi-modal Data with ImageBind-based Condensation.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

WaveEx: Accelerating Flow Matching-based Speech Generation via Wavelet-guided Extrapolation.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgement.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

UniLabOS: An AI-Native Operating System for Autonomous Laboratories.

[BibT_eX]

[DOI]

CoRR, December, 2025

D2Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning.

[BibT_eX]

[DOI]

CoRR, December, 2025

IPCV: Information-Preserving Compression for MLLM Visual Encoders.

[BibT_eX]

[DOI]

CoRR, December, 2025

SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding.

[BibT_eX]

[DOI]

CoRR, December, 2025

VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction.

[BibT_eX]

[DOI]

CoRR, November, 2025

Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks.

[BibT_eX]

[DOI]

CoRR, October, 2025

Diffusion LLM with Native Variable Generation Lengths: Let [EOS] Lead the Way.

[BibT_eX]

[DOI]

CoRR, October, 2025

CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs.

[BibT_eX]

[DOI]

CoRR, October, 2025

Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage Sampling.

[BibT_eX]

[DOI]

CoRR, October, 2025

AI for Service: Proactive Assistance with AI Glasses.

[BibT_eX]

[DOI]

CoRR, October, 2025

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution.

[BibT_eX]

[DOI]

CoRR, October, 2025

Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data?

[BibT_eX]

[DOI]

CoRR, October, 2025

Reasoning-Enhanced Large Language Models for Molecular Property Prediction.

[BibT_eX]

[DOI]

CoRR, October, 2025

Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference.

[BibT_eX]

[DOI]

CoRR, October, 2025

AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs.

[BibT_eX]

[DOI]

CoRR, October, 2025

Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods.

[BibT_eX]

[DOI]

CoRR, October, 2025

SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation.

[BibT_eX]

[DOI]

CoRR, October, 2025

Self Speculative Decoding for Diffusion Large Language Models.

[BibT_eX]

[DOI]

CoRR, October, 2025

Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention.

[BibT_eX]

[DOI]

CoRR, October, 2025

Efficient Multi-modal Large Language Models via Progressive Consistency Distillation.

[BibT_eX]

[DOI]

CoRR, October, 2025

Socratic-Zero : Bootstrapping Reasoning via Data-Free Agent Co-evolution.

[BibT_eX]

[DOI]

CoRR, September, 2025

Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning.

[BibT_eX]

[DOI]

CoRR, September, 2025

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing.

[BibT_eX]

[DOI]

CoRR, September, 2025

Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation.

[BibT_eX]

[DOI]

CoRR, September, 2025

PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era.

[BibT_eX]

[DOI]

CoRR, September, 2025

Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving.

[BibT_eX]

[DOI]

CoRR, August, 2025

Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs.

[BibT_eX]

[DOI]

CoRR, August, 2025

Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling.

[BibT_eX]

[DOI]

CoRR, July, 2025

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs.

[BibT_eX]

[DOI]

CoRR, July, 2025

MemOS: A Memory OS for AI System.

[BibT_eX]

[DOI]

CoRR, July, 2025

EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models.

[BibT_eX]

[DOI]

CoRR, June, 2025

TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration.

[BibT_eX]

[DOI]

CoRR, June, 2025

dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching.

[BibT_eX]

[DOI]

CoRR, June, 2025

Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs.

[BibT_eX]

[DOI]

CoRR, June, 2025

Shifting AI Efficiency From Model-Centric to Data-Centric Compression.

[BibT_eX]

[DOI]

CoRR, May, 2025

MLLMs are Deeply Affected by Modality Bias.

[BibT_eX]

[DOI]

CoRR, May, 2025

DD-Ranking: Rethinking the Evaluation of Dataset Distillation.

[BibT_eX]

[DOI]

Baharan Mirzasoleiman

Manolis Kellis

Konstantinos N. Plataniotis

CoRR, May, 2025

LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint.

[BibT_eX]

[DOI]

CoRR, February, 2025

Compression with Global Guidance: Towards Training-free High-Resolution MLLMs Acceleration.

[BibT_eX]

[DOI]

CoRR, January, 2025

Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free.

[BibT_eX]

[DOI]

CoRR, January, 2025

Safety-Enhanced Navigation Planning for Magnetic Microrobots.

[BibT_eX]

[DOI]

IEEE Trans Autom. Sci. Eng., 2025

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching.

[BibT_eX]

[DOI]

Proceedings of the 33rd ACM International Conference on Multimedia, 2025

SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching.

[BibT_eX]

[DOI]

Proceedings of the 33rd ACM International Conference on Multimedia, 2025

RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning.

[BibT_eX]

[DOI]

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Accelerating Diffusion Transformers with Token-wise Feature Caching.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

REEF: Representation Encoding Fingerprints for Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

LazyMAR: Accelerating Masked Autoregressive Models Via Feature Caching.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

LEGION: Learning to Ground and Explain for Synthetic Image Detection.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Stop Looking for "Important Tokens" in Multimodal Language Models: Duplication Matters More.

[BibT_eX]

[DOI]

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction.

[BibT_eX]

[DOI]

Xuelin Li

Xiangqi Jin

Linfeng Zhang

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning.

[BibT_eX]

[DOI]

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

ProReflow: Progressive Reflow with Decomposed Velocity.

[BibT_eX]

[DOI]

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

Dataset Distillation with Neural Characteristic Function: A Minmax Perspective.

[BibT_eX]

[DOI]

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

ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models.

[BibT_eX]

[DOI]

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

Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2025

LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint.

[BibT_eX]

[DOI]

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Unlocking Speech Instruction Data Potential with Query Rewriting.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2025

Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning.

[BibT_eX]

[DOI]

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Training-Free and Hardware-Friendly Acceleration for Diffusion Models via Similarity-based Token Pruning.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024

Gesture Recognition Using Visible Light on Mobile Devices.

[BibT_eX]

[DOI]

IEEE/ACM Trans. Netw., August, 2024

Accelerating Diffusion Transformers with Dual Feature Caching.

[BibT_eX]

[DOI]

CoRR, 2024

Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation.

[BibT_eX]

[DOI]

CoRR, 2024

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model.

[BibT_eX]

[DOI]

CoRR, 2024

Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Models.

[BibT_eX]

[DOI]

CoRR, 2024

Decouple-Then-Merge: Towards Better Training for Diffusion Models.

[BibT_eX]

[DOI]

CoRR, 2024

Accelerating Diffusion Models with One-to-Many Knowledge Distillation.

[BibT_eX]

[DOI]

Linfeng Zhang

Kaisheng Ma

CoRR, 2024

DRUPI: Dataset Reduction Using Privileged Information.

[BibT_eX]

[DOI]

CoRR, 2024

Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation.

[BibT_eX]

[DOI]

CoRR, 2024

DiTFastAttn: Attention Compression for Diffusion Transformer Models.

[BibT_eX]

[DOI]

CoRR, 2024

DiTFastAttn: Attention Compression for Diffusion Transformer Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Structured Knowledge Distillation for Accurate and Efficient Object Detection.

[BibT_eX]

[DOI]

Linfeng Zhang

Kaisheng Ma

IEEE Trans. Pattern Anal. Mach. Intell., December, 2023

A Good Data Augmentation Policy is not All You Need: A Multi-Task Learning Perspective.

[BibT_eX]

[DOI]

Linfeng Zhang

Kaisheng Ma

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

CORSD: Class-Oriented Relational Self Distillation.

[BibT_eX]

[DOI]

CoRR, 2023

Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study.

[BibT_eX]

[DOI]

Muzhou Yu

Linfeng Zhang

Kaisheng Ma

Proceedings of the International Joint Conference on Neural Networks, 2023

Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection.

[BibT_eX]

[DOI]

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

Tiny Updater: Towards Efficient Neural Network-Driven Software Updating.

[BibT_eX]

[DOI]

Linfeng Zhang

Kaisheng Ma

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

Multi-Frequency Representation Enhancement with Privilege Information for Video Super-Resolution.

[BibT_eX]

[DOI]

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

CORSD: Class-Oriented Relational Self Distillation.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Structured Knowledge Distillation Towards Efficient Multi-View 3D Object Detection.

[BibT_eX]

[DOI]

Proceedings of the 34th British Machine Vision Conference 2023, 2023

Region-aware Knowledge Distillation for Efficient Image-to-Image Translation.

[BibT_eX]

[DOI]

Proceedings of the 34th British Machine Vision Conference 2023, 2023

2022

Non-Structured DNN Weight Pruning - Is It Beneficial in Any Platform?

[BibT_eX]

[DOI]

IEEE Trans. Neural Networks Learn. Syst., 2022

Self-Distillation: Towards Efficient and Compact Neural Networks.

[BibT_eX]

[DOI]

Linfeng Zhang

Chenglong Bao

Kaisheng Ma

IEEE Trans. Pattern Anal. Mach. Intell., 2022

Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detection.

[BibT_eX]

[DOI]

CoRR, 2022

Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Contrastive Deep Supervision.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation.

[BibT_eX]

[DOI]

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

2021

SMART: screen-based gesture recognition on commodity mobile devices.

[BibT_eX]

[DOI]

Proceedings of the ACM MobiCom '21: The 27th Annual International Conference on Mobile Computing and Networking, 2021

SMART: screen-based gesture recognition on commodity mobile devices.

[BibT_eX]

[DOI]

Proceedings of the ACM MobiCom '21: The 27th Annual International Conference on Mobile Computing and Networking, 2021

Wavelet J-Net: A Frequency Perspective on Convolutional Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the International Joint Conference on Neural Networks, 2021

Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient Detectors.

[BibT_eX]

[DOI]

Linfeng Zhang

Kaisheng Ma

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Fine-grained emotion classification of Chinese microblogs based on graph convolution networks.

[BibT_eX]

[DOI]

World Wide Web, 2020

Task-Oriented Feature Distillation.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Auxiliary Training: Towards Accurate and Robust Models.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

Prediction of Marine Pycnocline Based on Kernel Support Vector Machine and Convex Optimization Technology.

[BibT_eX]

[DOI]

Sensors, 2019

Non-structured DNN Weight Pruning Considered Harmful.

[BibT_eX]

[DOI]

CoRR, 2019

SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation.

[BibT_eX]

[DOI]

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

2017

Optimization of the Power Flow in a Smart Home.

[BibT_eX]

[DOI]

Linfeng Zhang

Xingguo Xiong

Proceedings of the Online Engineering & Internet of Things, 2017

2008

Video Segmentation Algorithm in Virtual Advertisement System.

[BibT_eX]

[DOI]

Linqiang Chen

Jianping Han

Linfeng Zhang

Proceedings of the International Conference on Cyberworlds 2008, 2008

2007

The sensing mechanism and the response simulation of the MIS hydrogen sensor.

[BibT_eX]

[DOI]

Proceedings of the Advances in Computer and Information Sciences and Engineering, 2007

Linfeng Zhang

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...