{"total":97,"rows":[{"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":"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":"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":"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":"2411.00136","title":"LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators","created":"2024-10-31","cited_by_count":32,"area":null},{"id":"2507.02076","title":"Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2501.12389","title":"Taming Teacher Forcing for Masked Autoregressive Video Generation","created":"2025-01-21","cited_by_count":30,"area":null},{"id":"2410.14731","title":"MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection","created":"2024-10-16","cited_by_count":29,"area":"inference"},{"id":"2506.18879","title":"CommVQ: Commutative Vector Quantization for KV Cache Compression","created":"2025-06-23","cited_by_count":28,"area":"inference"},{"id":"2503.21411","title":"Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap","created":"2025-03-27","cited_by_count":26,"area":null},{"id":"2604.04921","title":"TriAttention: Efficient Long Reasoning with Trigonometric KV Compression","created":"2026-04-06","cited_by_count":21,"area":"lr"},{"id":"2412.13649","title":"SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation","created":"2024-12-18","cited_by_count":20,"area":"inference"},{"id":"2409.04267","title":"An overview of domain-specific foundation model: key technologies, applications and challenges","created":"2024-09-06","cited_by_count":19,"area":null},{"id":"2601.06007","title":"Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks","created":"2026-01-09","cited_by_count":19,"area":"agents"},{"id":"2410.01805","title":"Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices","created":"2024-10-02","cited_by_count":15,"area":"inference"},{"id":"2507.18537","title":"TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation","created":"2025-07-24","cited_by_count":15,"area":"lr"},{"id":"2510.00231","title":"The Pitfalls of KV Cache Compression","created":"2025-09-30","cited_by_count":15,"area":"inference"},{"id":"2410.13846","title":"LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation","created":"2024-10-17","cited_by_count":12,"area":"lr"},{"id":"2502.12082","title":"AdaSplash: Adaptive Sparse Flash Attention","created":"2025-02-17","cited_by_count":12,"area":null},{"id":"2506.15724","title":"MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference","created":"2025-06-06","cited_by_count":12,"area":"mllm"},{"id":"2508.06297","title":"KV Cache Compression for Inference Efficiency in LLMs: A Review","created":"2025-08-08","cited_by_count":12,"area":"inference"},{"id":"2502.08246","title":"Inference-time sparse attention with asymmetric indexing","created":"2025-02-12","cited_by_count":11,"area":null},{"id":"2503.13299","title":"A Survey on Transformer Context Extension: Approaches and Evaluation","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2511.20172","title":"Beluga: A CXL-Based Memory Architecture for Scalable and Efficient LLM KVCache Management","created":"2025-11-25","cited_by_count":11,"area":"inference"},{"id":"2504.00970","title":"SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching","created":"2025-04-01","cited_by_count":10,"area":"inference"},{"id":"2506.22950","title":"Infinite Sampling: Efficient and Stable Grouped RL Training for Large Language Models","created":"2025-06-28","cited_by_count":10,"area":"lr"},{"id":"2509.08315","title":"EvolKV: Evolutionary KV Cache Compression for LLM Inference","created":"2025-09-10","cited_by_count":10,"area":"inference"},{"id":"2512.05916","title":"KQ-SVD: Compressing the KV Cache with Provable Guarantees on Attention Fidelity","created":"2025-12-05","cited_by_count":10,"area":"inference"},{"id":"2411.15982","title":"Anda: Unlocking Efficient LLM Inference with a Variable-Length Grouped Activation Data Format","created":"2024-11-24","cited_by_count":9,"area":"inference"},{"id":"2504.09936","title":"KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference","created":"2025-04-14","cited_by_count":9,"area":"inference"},{"id":"2507.06517","title":"SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers","created":"2025-07-09","cited_by_count":9,"area":"inference"},{"id":"2508.16134","title":"CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing","created":"2025-08-22","cited_by_count":9,"area":"inference"},{"id":"2503.24000","title":"Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving","created":"2025-03-31","cited_by_count":8,"area":"inference"},{"id":"2602.06502","title":"DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM Serving","created":"2026-02-06","cited_by_count":8,"area":"inference"},{"id":"2502.04358","title":"Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives","created":"2025-02-04","cited_by_count":7,"area":"agents"},{"id":"2507.11942","title":"DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression","created":"2025-07-16","cited_by_count":7,"area":"inference"},{"id":"2509.04377","title":"PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference","created":"2025-09-04","cited_by_count":7,"area":"inference"},{"id":"2509.21623","title":"OjaKV: Context-Aware Online Low-Rank KV Cache Compression","created":"2025-09-25","cited_by_count":7,"area":"inference"},{"id":"2503.11513","title":"HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models","created":"2025-03-14","cited_by_count":6,"area":null},{"id":"2508.15212","title":"SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning","created":"2025-08-21","cited_by_count":6,"area":"inference"},{"id":"2509.24832","title":"SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching","created":"2025-09-29","cited_by_count":6,"area":"inference"},{"id":"2502.15955","title":"Compression Barriers for Autoregressive Transformers","created":"2025-02-21","cited_by_count":5,"area":"inference"},{"id":"2506.08018","title":"KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache","created":"2025-05-18","cited_by_count":5,"area":"inference"},{"id":"2510.11236","title":"XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression","created":"2025-10-13","cited_by_count":5,"area":"inference"},{"id":"2602.05929","title":"KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs","created":"2026-02-05","cited_by_count":5,"area":"inference"},{"id":"2604.25975","title":"Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective","created":"2026-04-28","cited_by_count":5,"area":"lr"},{"id":"2410.13166","title":"An Evolved Universal Transformer Memory","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2503.09579","title":"Cost-Optimal Grouped-Query Attention for Long-Context Modeling","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2503.11132","title":"X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression","created":"2025-03-14","cited_by_count":4,"area":"inference"},{"id":"2507.15428","title":"EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent","created":"2025-07-21","cited_by_count":4,"area":"lr"},{"id":"2510.05364","title":"The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2510.11292","title":"LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences","created":"2025-10-13","cited_by_count":4,"area":"inference"},{"id":"2602.10718","title":"SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2603.22910","title":"EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction","created":"2026-03-24","cited_by_count":4,"area":"inference"},{"id":"2604.14885","title":"RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding","created":"2026-04-16","cited_by_count":4,"area":"rag"},{"id":"2607.08057","title":"Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization","created":"2026-07-09","cited_by_count":4,"area":"inference"},{"id":"2502.12085","title":"APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2507.09955","title":"DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models","created":"2025-07-14","cited_by_count":3,"area":"moe"},{"id":"2508.17243","title":"CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models","created":"2025-08-24","cited_by_count":3,"area":"mllm"},{"id":"2509.03136","title":"Adaptive KV-Cache Compression without Manually Setting Budget","created":"2025-09-03","cited_by_count":3,"area":"inference"},{"id":"2511.16786","title":"Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach","created":"2025-11-20","cited_by_count":3,"area":"mllm"},{"id":"2511.20340","title":"Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios","created":"2025-11-25","cited_by_count":3,"area":"inference"},{"id":"2604.17935","title":"How Much Cache Does Reasoning Need? Depth-Cache Tradeoffs in KV-Compressed Transformers","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2604.24647","title":"DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference","created":"2026-04-27","cited_by_count":3,"area":"inference"},{"id":"2408.11062","title":"Multi-Turn Interactions for Text-to-SQL with Large Language Models","created":"2024-08-09","cited_by_count":2,"area":"lr"},{"id":"2502.08363","title":"Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding","created":"2025-02-12","cited_by_count":2,"area":null},{"id":"2504.07479","title":"UniCAIM: A Unified CAM/CIM Architecture with Static-Dynamic KV Cache Pruning for Efficient Long-Context LLM Inference","created":"2025-04-10","cited_by_count":2,"area":"inference"},{"id":"2604.01609","title":"Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression","created":"2026-04-02","cited_by_count":2,"area":"inference"},{"id":"2604.04500","title":"Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward","created":"2026-04-06","cited_by_count":2,"area":"lr"},{"id":"2605.04901","title":"On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference","created":"2026-05-06","cited_by_count":2,"area":null},{"id":"2608.04771","title":"Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning","created":"2026-08-05","cited_by_count":2,"area":"lr"},{"id":"2609.15160","title":"T-LoopFormer: Token-Level Elastic-Depth Looped Transformers for Latent Reasoning with Dynamic Routing","created":"2026-09-14","cited_by_count":2,"area":"inference"},{"id":"2411.12663","title":"PoM: Efficient Image and Video Generation with the Polynomial Mixer","created":"2024-11-19","cited_by_count":1,"area":"diffusion"},{"id":"2502.20295","title":"Judge a Book by its Cover: Investigating Multi-Modal LLMs for Multi-Page Handwritten Document Transcription","created":"2025-02-27","cited_by_count":1,"area":"mllm"},{"id":"2503.23924","title":"Model Hemorrhage and the Robustness Limits of Large Language Models","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2504.08838","title":"SD$^2$: Self-Distilled Sparse Drafters","created":"2025-04-10","cited_by_count":1,"area":"inference"},{"id":"2506.12204","title":"Semantic Scheduling for LLM Inference","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2509.18136","title":"From Parameters to Performance: A Data-Driven Study on LLM Structure and Development","created":"2025-09-14","cited_by_count":1,"area":null},{"id":"2510.08143","title":"UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2601.18383","title":"Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models","created":"2026-01-26","cited_by_count":1,"area":"lr"},{"id":"2602.13665","title":"HyFunc: Accelerating LLM-based Function Calls for Agentic AI through Hybrid-Model Cascade and Dynamic Templating","created":"2026-02-14","cited_by_count":1,"area":"agents"},{"id":"2602.16192","title":"Revolutionizing Long-Term Memory in AI: New Horizons with High-Capacity and High-Speed Storage","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2606.00620","title":"FlowNar: Scalable Streaming Narration for Long-Form Videos","created":"2026-05-30","cited_by_count":1,"area":"mllm"},{"id":"2608.09412","title":"KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models","created":"2026-08-10","cited_by_count":1,"area":"inference"},{"id":"2503.00022","title":"KVCrush: Key value cache size-reduction using similarity in head-behaviour","created":"2025-02-24","cited_by_count":0,"area":"inference"},{"id":"2503.17922","title":"WindowKV: Task-Adaptive Group-Wise KV Cache Window Selection for Efficient LLM Inference","created":"2025-03-23","cited_by_count":0,"area":"inference"},{"id":"2505.14992","title":"Effective and Efficient Schema-aware Information Extraction Using On-Device Large Language Models","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2507.16229","title":"Voice-based AI Agents: Filling the Economic Gaps in Digital Health Delivery","created":"2025-07-22","cited_by_count":0,"area":"agents"},{"id":"2509.15024","title":"Attention Beyond Neighborhoods: Reviving Transformer for Graph Clustering","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2510.01251","title":"Efficient Uncertainty Estimation for LLM-based Entity Linking in Tabular Data","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2511.17693","title":"DeepCoT: Deep Continual Transformers for Real-Time Inference on Data Streams","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2512.11892","title":"Should AI Become an Intergenerational Civil Right?","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2604.06129","title":"PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.12634","title":"RPRA: Predicting an LLM-Judge for Efficient but Performant Inference","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2607.11211","title":"FastTPS: An Optimized Method for LLM Token Phase for AI accelerators","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.07855","title":"CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents","created":"2026-08-08","cited_by_count":0,"area":"inference"},{"id":"2609.08131","title":"Jacap: Robust KV Cache Eviction via Jacobian-Based Nonlinear Information Capacity Preservation","created":"2026-09-08","cited_by_count":0,"area":"inference"}],"next_cursor":null}