{"total":125,"rows":[{"id":"2503.06923","title":"From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers","created":"2025-03-10","cited_by_count":136,"area":"diffusion"},{"id":"2407.08454","title":"Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks","created":"2024-07-11","cited_by_count":96,"area":"inference"},{"id":"2505.18227","title":"Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality","created":"2025-05-23","cited_by_count":50,"area":"inference"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2405.16148","title":"Accelerating Transformers with Spectrum-Preserving Token Merging","created":"2024-05-25","cited_by_count":35,"area":"inference"},{"id":"2503.11549","title":"Similarity-Aware Token Pruning: Your VLM but Faster","created":"2025-03-14","cited_by_count":35,"area":"mllm"},{"id":"2509.11628","title":"SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching","created":"2025-09-15","cited_by_count":29,"area":"diffusion"},{"id":"2505.20353","title":"FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation","created":"2025-05-26","cited_by_count":24,"area":"diffusion"},{"id":"2411.16720","title":"Importance-Based Token Merging for Efficient Image and Video Generation","created":"2024-11-23","cited_by_count":22,"area":"diffusion"},{"id":"2503.22796","title":"DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers","created":"2025-03-28","cited_by_count":20,"area":"diffusion"},{"id":"2510.08669","title":"FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching","created":"2025-10-09","cited_by_count":20,"area":"diffusion"},{"id":"2412.00965","title":"Token Cropr: Faster ViTs for Quite a Few Tasks","created":"2024-12-01","cited_by_count":19,"area":"inference"},{"id":"2509.10312","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","created":"2025-09-12","cited_by_count":19,"area":"diffusion"},{"id":"2509.10918","title":"ToMA: Token Merge with Attention for Diffusion Models","created":"2025-09-13","cited_by_count":18,"area":"diffusion"},{"id":"2403.09192","title":"PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation","created":"2024-03-14","cited_by_count":17,"area":null},{"id":"2402.10787","title":"Squat: Quant Small Language Models on the Edge","created":"2024-02-16","cited_by_count":16,"area":null},{"id":"2501.00946","title":"Cached Adaptive Token Merging: Dynamic Token Reduction and Redundant Computation Elimination in Diffusion Model","created":"2025-01-01","cited_by_count":16,"area":"diffusion"},{"id":"2510.19755","title":"A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation","created":"2025-10-22","cited_by_count":16,"area":"diffusion"},{"id":"2511.19515","title":"Fewer Tokens, Greater Scaling: Self-Adaptive Visual Bases for Efficient and Expansive Representation Learning","created":"2025-11-24","cited_by_count":16,"area":null},{"id":"2410.13859","title":"$\\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models","created":"2024-10-17","cited_by_count":14,"area":"mllm"},{"id":"2504.16081","title":"Survey of Video Diffusion Models: Foundations, Implementations, and Applications","created":"2025-04-22","cited_by_count":14,"area":"diffusion"},{"id":"2409.18314","title":"Realistic Evaluation of Model Merging for Compositional Generalization","created":"2024-09-26","cited_by_count":12,"area":null},{"id":"2504.01690","title":"Token Pruning in Audio Transformers: Optimizing Performance and Decoding Patch Importance","created":"2025-04-02","cited_by_count":12,"area":"inference"},{"id":"2507.17135","title":"SADA: Stability-guided Adaptive Diffusion Acceleration","created":"2025-07-23","cited_by_count":11,"area":"diffusion"},{"id":"2602.18993","title":"SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models","created":"2026-02-22","cited_by_count":11,"area":"diffusion"},{"id":"2403.07965","title":"Conditional computation in neural networks: principles and research trends","created":"2024-03-12","cited_by_count":10,"area":"moe"},{"id":"2510.04188","title":"Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers","created":"2025-10-05","cited_by_count":10,"area":"diffusion"},{"id":"2511.14751","title":"Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers","created":"2025-11-18","cited_by_count":10,"area":"inference"},{"id":"2403.16020","title":"PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference","created":"2024-03-24","cited_by_count":9,"area":null},{"id":"2508.17588","title":"HERO: Hierarchical Extrapolation and Refresh for Efficient World Models","created":"2025-08-25","cited_by_count":9,"area":"wm"},{"id":"2511.21317","title":"HTTM: Head-wise Temporal Token Merging for Faster VGGT","created":"2025-11-26","cited_by_count":9,"area":null},{"id":"2506.11418","title":"CentroidKV: Efficient Long-Context LLM Inference via KV Cache Clustering","created":"2025-06-13","cited_by_count":8,"area":"inference"},{"id":"2605.11856","title":"UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs","created":"2026-05-12","cited_by_count":8,"area":"lr"},{"id":"2405.17951","title":"Efficient Time Series Processing for Transformers and State-Space Models through Token Merging","created":"2024-05-28","cited_by_count":7,"area":"inference"},{"id":"2407.15219","title":"Efficient Visual Transformer by Learnable Token Merging","created":"2024-07-21","cited_by_count":7,"area":"inference"},{"id":"2509.09955","title":"Adaptive Token Merging for Efficient Transformer Semantic Communication at the Edge","created":"2025-09-12","cited_by_count":7,"area":"inference"},{"id":"2512.09927","title":"Token Expand-Merge: Training-Free Token Compression for Vision-Language-Action Models","created":"2025-12-10","cited_by_count":7,"area":"vla"},{"id":"2602.05449","title":"DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching","created":"2026-02-05","cited_by_count":7,"area":"diffusion"},{"id":"2508.02240","title":"Forecasting When to Forecast: Accelerating Diffusion Models with Confidence-Gated Taylor","created":"2025-08-04","cited_by_count":6,"area":"diffusion"},{"id":"2604.01552","title":"ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor","created":"2026-04-02","cited_by_count":6,"area":"diffusion"},{"id":"2501.07451","title":"A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion","created":"2025-01-13","cited_by_count":5,"area":null},{"id":"2504.02522","title":"Charm: The Missing Piece in ViT fine-tuning for Image Aesthetic Assessment","created":"2025-04-03","cited_by_count":5,"area":null},{"id":"2505.18051","title":"LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2505.21847","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2505.21960","title":"One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models","created":"2025-05-28","cited_by_count":5,"area":"diffusion"},{"id":"2512.18747","title":"IPCV: Information-Preserving Compression for MLLM Visual Encoders","created":"2025-12-21","cited_by_count":5,"area":"mllm"},{"id":"2408.17062","title":"Vote&Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer","created":"2024-08-30","cited_by_count":4,"area":"inference"},{"id":"2503.23455","title":"Efficient Token Compression for Vision Transformer with Spatial Information Preserved","created":"2025-03-30","cited_by_count":4,"area":"inference"},{"id":"2505.15755","title":"Exploring The Visual Feature Space for Multimodal Neural Decoding","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2509.23931","title":"AutoPrune: Each Complexity Deserves a Pruning Policy","created":"2025-09-28","cited_by_count":4,"area":"mllm"},{"id":"2510.27186","title":"Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications","created":"2025-10-31","cited_by_count":4,"area":null},{"id":"2511.05449","title":"How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?","created":"2025-11-07","cited_by_count":4,"area":null},{"id":"2601.07396","title":"Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Efficient Diffusion Transformers","created":"2026-01-12","cited_by_count":4,"area":"diffusion"},{"id":"2602.16968","title":"DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers","created":"2026-02-19","cited_by_count":4,"area":"diffusion"},{"id":"2603.03792","title":"TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration","created":"2026-03-04","cited_by_count":4,"area":"diffusion"},{"id":"2603.23491","title":"Foveated Diffusion: Efficient Spatially Adaptive Image and Video Generation","created":"2026-03-24","cited_by_count":4,"area":"diffusion"},{"id":"2406.00210","title":"A-SDM: Accelerating Stable Diffusion through Model Assembly and Feature Inheritance Strategies","created":"2024-05-31","cited_by_count":3,"area":"diffusion"},{"id":"2505.15160","title":"Lossless Token Merging Even Without Fine-Tuning in Vision Transformers","created":"2025-05-21","cited_by_count":3,"area":"inference"},{"id":"2505.22195","title":"S2AFormer: Strip Self-Attention for Efficient Vision Transformer","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2507.09702","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","created":"2025-07-13","cited_by_count":3,"area":"inference"},{"id":"2602.22779","title":"TrajTok: Learning Trajectory Tokens enables better Video Understanding","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2603.05663","title":"Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding","created":"2026-03-05","cited_by_count":3,"area":"inference"},{"id":"2603.24260","title":"Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep","created":"2026-03-25","cited_by_count":3,"area":"diffusion"},{"id":"2605.20551","title":"Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2606.06060","title":"ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE","created":"2026-06-04","cited_by_count":3,"area":"diffusion"},{"id":"2411.15397","title":"Visual-Word Tokenizer: Beyond Fixed Sets of Tokens in Vision Transformers","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2506.03885","title":"Video, How Do Your Tokens Merge?","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2511.17885","title":"FastMMoE: Accelerating Multimodal Large Language Models through Dynamic Expert Activation and Routing-Aware Token Pruning","created":"2025-11-22","cited_by_count":2,"area":"mllm"},{"id":"2602.01609","title":"Token Pruning for In-Context Generation in Diffusion Transformers","created":"2026-02-02","cited_by_count":2,"area":"diffusion"},{"id":"2602.05605","title":"Shiva-DiT: Residual-Based Differentiable Top-$k$ Selection for Efficient Diffusion Transformers","created":"2026-02-05","cited_by_count":2,"area":"diffusion"},{"id":"2603.07307","title":"StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models","created":"2026-03-07","cited_by_count":2,"area":"inference"},{"id":"2603.26258","title":"ARTA: Adaptive Mixed-Resolution Token Allocation for Efficient Dense Feature Extraction","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2604.05718","title":"MPM: Mutual Pair Merging for Efficient Vision Transformers","created":"2026-04-07","cited_by_count":2,"area":"inference"},{"id":"2607.02612","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","created":"2026-07-01","cited_by_count":2,"area":"inference"},{"id":"2607.04163","title":"SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering","created":"2026-07-05","cited_by_count":2,"area":"mllm"},{"id":"2505.24033","title":"Studying the Soupability of Documents in State Space Models","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2507.10283","title":"FTCFormer: Fuzzy Token Clustering Transformer for Image Classification","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2508.03388","title":"Neutralizing Token Aggregation via Information Augmentation for Efficient Test-Time Adaptation","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.13204","title":"QuickMerge++: Fast Token Merging with Autoregressive Prior","created":"2025-08-16","cited_by_count":1,"area":"inference"},{"id":"2508.16311","title":"Exploiting Information Redundancy in Attention Maps for Extreme Quantization of Vision Transformers","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2509.06415","title":"Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models","created":"2025-09-08","cited_by_count":1,"area":"mllm"},{"id":"2511.16783","title":"Generative Augmented Reality: Paradigms, Technologies, and Future Applications","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2512.09010","title":"Towards Lossless Ultimate Vision Token Compression for VLMs","created":"2025-12-09","cited_by_count":1,"area":"mllm"},{"id":"2603.14549","title":"ASAP: Attention-Shift-Aware Pruning for Efficient LVLM Inference","created":"2026-03-15","cited_by_count":1,"area":"mllm"},{"id":"2603.23483","title":"SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning","created":"2026-03-24","cited_by_count":1,"area":"lr"},{"id":"2604.12319","title":"RSGMamba: Reliability-Aware Self-Gated State Space Model for Multimodal Semantic Segmentation","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2604.14563","title":"Revisiting Token Compression for Accelerating ViT-based Sparse Multi-View 3D Object Detectors","created":"2026-04-16","cited_by_count":1,"area":"inference"},{"id":"2605.11803","title":"OTT-Vid: Optimal Transport Temporal Token Compression for Video Large Language Models","created":"2026-05-12","cited_by_count":1,"area":"inference"},{"id":"2606.18439","title":"RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2606.19849","title":"ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference","created":"2026-06-18","cited_by_count":1,"area":"inference"},{"id":"2608.17973","title":"LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching","created":"2026-08-18","cited_by_count":1,"area":"diffusion"},{"id":"2404.09245","title":"Arena: A Patch-of-Interest ViT Inference Acceleration System for Edge-Assisted Video Analytics","created":"2024-04-14","cited_by_count":0,"area":"inference"},{"id":"2507.00789","title":"OptiPrune: Boosting Prompt-Image Consistency with Attention-Guided Noise and Dynamic Token Selection","created":"2025-07-01","cited_by_count":0,"area":"diffusion"},{"id":"2507.12125","title":"Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2507.12780","title":"Compact Vision Transformer by Reduction of Kernel Complexity","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2508.13599","title":"Towards Efficient Vision State Space Models via Token Merging","created":"2025-08-19","cited_by_count":0,"area":"inference"},{"id":"2509.03379","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","created":"2025-09-03","cited_by_count":0,"area":"inference"},{"id":"2509.14165","title":"Where Do Tokens Go? Understanding Pruning Behaviors in STEP at High Resolutions","created":"2025-09-17","cited_by_count":0,"area":"inference"},{"id":"2509.21764","title":"CubistMerge: Spatial-Preserving Token Merging For Diverse ViT Backbones","created":"2025-09-26","cited_by_count":0,"area":"inference"}],"next_cursor":"100"}