Linfeng Zhang

26

Papers

203

Total Citations

Papers (26)

Accelerating Diffusion Transformers with Token-wise Feature Caching

LEGION: Learning to Ground and Explain for Synthetic Image Detection

REEF: Representation Encoding Fingerprints for Large Language Models

Dataset Distillation with Neural Characteristic Function: A Minmax Perspective

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

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

MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild

Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

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

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

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

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

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

Tiny Updater: Towards Efficient Neural Network-Driven Software Updating

Contrastive Deep Supervision

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

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

ProReflow: Progressive Reflow with Decomposed Velocity

EEdit : Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing

From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers

LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching

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

Auxiliary Training: Towards Accurate and Robust Models

End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems

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

Task-Oriented Feature Distillation