Linfeng Zhang

Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep CVPR 2026 Accelerating Streaming Video Large Language Models via Hierarchical Token Compression CVPR 2026 AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems ACL 2026 Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods ACL 2026 Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models CVPR 2026 D²Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning AAAI 2026 DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching CVPR 2026 Forecast Then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers AAAI 2026 Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Diffusion Transformers CVPR 2026 From Sketch to Fresco: Efficient Diffusion Transformer with Progressive Resolution CVPR 2026 ImageBindDC: Compressing Multi-modal Data with ImageBind-based Condensation AAAI 2026 LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration CVPR 2026 MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing ACL 2026 Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving CVPR 2026 SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgement AAAI 2026 SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding ACL 2026 Socratic-Geo: Synthetic Data Generation and Cross-Modal Geometric Reasoning via Multi-Agent Interaction CVPR 2026 Stability Implies Redundancy: Delta Attention Selective Halting for Efficient Long-Context Prefilling ACL 2026 UNSEEN: Enhancing Dataset Pruning from a Generalization Perspective AAAI 2026 WaveEx: Accelerating Flow Matching-based Speech Generation via Wavelet-guided Extrapolation AAAI 2026 Accelerating Diffusion Transformers with Token-wise Feature Caching ICLR 2025 Beyond Atoms: Enhancing Molecular Pretrained Representations with 3D Space Modeling ICML 2025 Dataset Distillation with Neural Characteristic Function: A Minmax Perspective CVPR 2025 Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning ACL 2025 Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning CVPR 2025 EEdit : Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing ICCV 2025 From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers ICCV 2025 Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers ICLR 2025 GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction EMNLP 2025 ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models CVPR 2025 LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching ICCV 2025 Learning local equivariant representations for quantum operators ICLR 2025 LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint ACL 2025 LEGION: Learning to Ground and Explain for Synthetic Image Detection ICCV 2025 MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild ICCV 2025 OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation ICCV 2025 ProReflow: Progressive Reflow with Decomposed Velocity CVPR 2025 RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning ICML 2025 REEF: Representation Encoding Fingerprints for Large Language Models ICLR 2025 SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis NAACL 2025 SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding ICLR 2025 Stop Looking for “Important Tokens” in Multimodal Language Models: Duplication Matters More EMNLP 2025 Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem? ACL 2025 Training-Free and Hardware-Friendly Acceleration for Diffusion Models via Similarity-based Token Pruning AAAI 2025 Unlocking Speech Instruction Data Potential with Query Rewriting ACL 2025 Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models EMNLP 2025 DiTFastAttn: Attention Compression for Diffusion Transformer Models NeurIPS 2024 Exploring Molecular Pretraining Model at Scale NeurIPS 2024 Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection ICCV 2023 Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning? ICLR 2023 Multi-Frequency Representation Enhancement with Privilege Information for Video Super-Resolution ICCV 2023 PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection CVPR 2023 Tiny Updater: Towards Efficient Neural Network-Driven Software Updating ICCV 2023 Uni-Mol: A Universal 3D Molecular Representation Learning Framework ICLR 2023 Contrastive Deep Supervision ECCV 2022 Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks ICML 2022 Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation CVPR 2022 Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient Detectors ICLR 2021 Auxiliary Training: Towards Accurate and Robust Models CVPR 2020 Task-Oriented Feature Distillation NeurIPS 2020 Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation ICCV 2019 SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models NeurIPS 2019 End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems NeurIPS 2018