{"total":832,"rows":[{"id":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880,"area":"inference"},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656,"area":null},{"id":"2310.01801","title":"Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs","created":"2023-10-03","cited_by_count":474,"area":"inference"},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464,"area":"lr"},{"id":"2406.02069","title":"PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling","created":"2024-06-04","cited_by_count":432,"area":"inference"},{"id":"2502.11089","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","created":"2025-02-16","cited_by_count":407,"area":null},{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383,"area":null},{"id":"2412.04467","title":"VisionZip: Longer is Better but Not Necessary in Vision Language Models","created":"2024-12-05","cited_by_count":313,"area":"mllm"},{"id":"2410.17247","title":"PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction","created":"2024-10-22","cited_by_count":294,"area":"mllm"},{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2407.11550","title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","created":"2024-07-16","cited_by_count":235,"area":"inference"},{"id":"2405.16444","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","created":"2024-05-26","cited_by_count":223,"area":"inference"},{"id":"2502.01776","title":"Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity","created":"2025-02-03","cited_by_count":217,"area":"diffusion"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2402.04617","title":"InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory","created":"2024-02-07","cited_by_count":197,"area":"agents"},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2406.01125","title":"$\\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers","created":"2024-06-03","cited_by_count":175,"area":"diffusion"},{"id":"2507.07957","title":"MIRIX: Multi-Agent Memory System for LLM-Based Agents","created":"2025-07-10","cited_by_count":173,"area":"agents"},{"id":"2506.06295","title":"dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching","created":"2025-05-17","cited_by_count":169,"area":null},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2405.05254","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","created":"2024-05-08","cited_by_count":144,"area":null},{"id":"2408.07055","title":"LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs","created":"2024-08-13","cited_by_count":144,"area":null},{"id":"2507.03724","title":"MemOS: A Memory OS for AI System","created":"2025-07-04","cited_by_count":138,"area":"rag"},{"id":"2410.21465","title":"ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference","created":"2024-10-28","cited_by_count":134,"area":"inference"},{"id":"2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","created":"2025-07-14","cited_by_count":133,"area":null},{"id":"2405.12981","title":"Reducing Transformer Key-Value Cache Size with Cross-Layer Attention","created":"2024-05-21","cited_by_count":131,"area":"inference"},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128,"area":null},{"id":"2405.14366","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","created":"2024-05-23","cited_by_count":125,"area":"inference"},{"id":"2504.19874","title":"TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate","created":"2025-04-28","cited_by_count":125,"area":null},{"id":"2502.20766","title":"FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference","created":"2025-02-28","cited_by_count":123,"area":null},{"id":"2502.18137","title":"SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference","created":"2025-02-25","cited_by_count":120,"area":null},{"id":"2403.09636","title":"Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference","created":"2024-03-14","cited_by_count":116,"area":null},{"id":"2409.10516","title":"RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval","created":"2024-09-16","cited_by_count":116,"area":null},{"id":"2404.09526","title":"LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism","created":"2024-04-15","cited_by_count":112,"area":"inference"},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"id":"2501.19324","title":"Reward-Guided Speculative Decoding for Efficient LLM Reasoning","created":"2025-01-31","cited_by_count":106,"area":"lr"},{"id":"2505.18875","title":"Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation","created":"2025-05-24","cited_by_count":106,"area":"diffusion"},{"id":"2401.03462","title":"Long Context Compression with Activation Beacon","created":"2024-01-07","cited_by_count":104,"area":"inference"},{"id":"2505.13389","title":"VSA: Faster Video Diffusion with Trainable Sparse Attention","created":"2025-05-19","cited_by_count":104,"area":"diffusion"},{"id":"2404.11912","title":"TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding","created":"2024-04-18","cited_by_count":102,"area":"inference"},{"id":"2410.11414","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","created":"2024-10-15","cited_by_count":101,"area":"rag"},{"id":"2407.15891","title":"RazorAttention: Efficient KV Cache Compression Through Retrieval Heads","created":"2024-07-22","cited_by_count":100,"area":"inference"},{"id":"2404.12457","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","created":"2024-04-18","cited_by_count":98,"area":"rag"},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97,"area":"inference"},{"id":"2410.19258","title":"Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning","created":"2024-10-25","cited_by_count":97,"area":"lr"},{"id":"2504.17343","title":"TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos","created":"2025-04-24","cited_by_count":97,"area":null},{"id":"2406.09136","title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs","created":"2024-06-13","cited_by_count":96,"area":"lr"},{"id":"2505.23416","title":"KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction","created":"2025-05-29","cited_by_count":95,"area":"inference"},{"id":"2405.14256","title":"ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification","created":"2024-05-23","cited_by_count":93,"area":"inference"},{"id":"2406.11430","title":"A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression","created":"2024-06-17","cited_by_count":86,"area":"inference"},{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"id":"2512.05081","title":"Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression","created":"2025-12-04","cited_by_count":85,"area":"diffusion"},{"id":"2310.18547","title":"Punica: Multi-Tenant LoRA Serving","created":"2023-10-28","cited_by_count":83,"area":null},{"id":"2405.03917","title":"KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization","created":"2024-05-07","cited_by_count":76,"area":"inference"},{"id":"2510.00636","title":"Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution","created":"2025-10-01","cited_by_count":74,"area":"inference"},{"id":"2411.11217","title":"MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs","created":"2024-11-18","cited_by_count":73,"area":"moe"},{"id":"2407.14057","title":"LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference","created":"2024-07-19","cited_by_count":70,"area":"inference"},{"id":"2502.08966","title":"RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage","created":"2025-02-13","cited_by_count":69,"area":"agents"},{"id":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68,"area":"lr"},{"id":"2412.16117","title":"PruneVid: Visual Token Pruning for Efficient Video Large Language Models","created":"2024-12-20","cited_by_count":67,"area":"inference"},{"id":"2502.16002","title":"KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse","created":"2025-02-21","cited_by_count":66,"area":"inference"},{"id":"2412.03213","title":"ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression","created":"2024-12-04","cited_by_count":65,"area":"lr"},{"id":"2407.21118","title":"Palu: Compressing KV-Cache with Low-Rank Projection","created":"2024-07-30","cited_by_count":64,"area":"inference"},{"id":"2410.07590","title":"TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text","created":"2024-10-10","cited_by_count":63,"area":"rag"},{"id":"2407.09450","title":"Human-inspired Episodic Memory for Infinite Context LLMs","created":"2024-07-12","cited_by_count":62,"area":null},{"id":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"area":"inference"},{"id":"2502.00299","title":"ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference","created":"2025-02-01","cited_by_count":60,"area":"inference"},{"id":"2412.00876","title":"Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification","created":"2024-12-01","cited_by_count":59,"area":"mllm"},{"id":"2503.12491","title":"CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences","created":"2025-03-16","cited_by_count":58,"area":"inference"},{"id":"2506.15745","title":"InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding","created":"2025-06-18","cited_by_count":58,"area":"inference"},{"id":"2508.15717","title":"StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding","created":"2025-08-21","cited_by_count":58,"area":"mllm"},{"id":"2411.09688","title":"Squeezed Attention: Accelerating Long Context Length LLM Inference","created":"2024-11-14","cited_by_count":57,"area":null},{"id":"2503.18278","title":"TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model","created":"2025-03-24","cited_by_count":57,"area":"mllm"},{"id":"2509.25911","title":"Mem-{\\alpha}: Learning Memory Construction via Reinforcement Learning","created":"2025-09-30","cited_by_count":55,"area":"lr"},{"id":"2502.00592","title":"M+: Extending MemoryLLM with Scalable Long-Term Memory","created":"2025-02-01","cited_by_count":54,"area":null},{"id":"2503.06692","title":"InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models","created":"2025-03-09","cited_by_count":54,"area":"lr"},{"id":"2505.24133","title":"R-KV: Redundancy-aware KV Cache Compression for Reasoning Models","created":"2025-05-30","cited_by_count":54,"area":"lr"},{"id":"2406.03482","title":"QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead","created":"2024-06-05","cited_by_count":52,"area":"inference"},{"id":"2406.16747","title":"Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers","created":"2024-06-24","cited_by_count":52,"area":null},{"id":"2410.03111","title":"LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy","created":"2024-10-04","cited_by_count":51,"area":"inference"},{"id":"2504.15364","title":"KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments","created":"2025-04-21","cited_by_count":51,"area":"inference"},{"id":"2502.02770","title":"Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning","created":"2025-02-04","cited_by_count":49,"area":null},{"id":"2403.17312","title":"ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching","created":"2024-03-26","cited_by_count":48,"area":null},{"id":"2410.15332","title":"EPIC: Efficient Position-Independent Caching for Serving Large Language Models","created":"2024-10-20","cited_by_count":47,"area":null},{"id":"2406.10260","title":"Flextron: Many-in-One Flexible Large Language Model","created":"2024-06-11","cited_by_count":45,"area":null},{"id":"2408.07092","title":"Post-Training Sparse Attention with Double Sparsity","created":"2024-08-11","cited_by_count":45,"area":null},{"id":"2412.19509","title":"MBQ: Modality-Balanced Quantization for Large Vision-Language Models","created":"2024-12-27","cited_by_count":45,"area":"mllm"},{"id":"2310.04064","title":"How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation","created":"2023-10-06","cited_by_count":44,"area":null},{"id":"2405.06219","title":"SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models","created":"2024-05-10","cited_by_count":44,"area":"inference"},{"id":"2405.08944","title":"Challenges in Deploying Long-Context Transformers: A Theoretical Peak Performance Analysis","created":"2024-05-14","cited_by_count":44,"area":"agents"},{"id":"2406.14909","title":"Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths","created":"2024-06-21","cited_by_count":44,"area":null},{"id":"2410.08584","title":"ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification","created":"2024-10-11","cited_by_count":44,"area":"mllm"},{"id":"2606.13392","title":"MiniMax Sparse Attention","created":"2026-06-11","cited_by_count":44,"area":"lr"},{"id":"2410.23317","title":"VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration","created":"2024-10-29","cited_by_count":43,"area":"mllm"},{"id":"2410.06270","title":"Mixture Compressor for Mixture-of-Experts LLMs Gains More","created":"2024-10-08","cited_by_count":41,"area":"moe"},{"id":"2410.18517","title":"KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing","created":"2024-10-24","cited_by_count":41,"area":"lr"},{"id":"2502.14051","title":"RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression","created":"2025-02-19","cited_by_count":41,"area":"inference"},{"id":"2502.14866","title":"LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention","created":"2025-02-20","cited_by_count":41,"area":"inference"}],"next_cursor":"100"}