ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Linfeng Zhang

Linfeng Zhang

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:22 PM AMS

24

papers

539

total citations

papers (24)

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

Accelerating Diffusion Transformers with Token-wise Feature Caching

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

Contrastive Deep Supervision

From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers

LEGION: Learning to Ground and Explain for Synthetic Image Detection

Dataset Distillation with Neural Characteristic Function: A Minmax Perspective

REEF: Representation Encoding Fingerprints for Large Language Models

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

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

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

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

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

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

Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention

NEURIPS 2025arXiv

Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

NEURIPS 2025arXiv

LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching

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

ProReflow: Progressive Reflow with Decomposed Velocity

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

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

Auxiliary Training: Towards Accurate and Robust Models

Task-Oriented Feature Distillation

Tiny Updater: Towards Efficient Neural Network-Driven Software Updating