{"total":64,"rows":[{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2510.01290","title":"ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models","created":"2025-10-01","cited_by_count":21,"area":"lr"},{"id":"2510.16292","title":"QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models","created":"2025-10-18","cited_by_count":16,"area":"mllm"},{"id":"2602.10238","title":"Learning to Evict from Key-Value Cache","created":"2026-02-10","cited_by_count":14,"area":"inference"},{"id":"2409.19315","title":"Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models","created":"2024-09-28","cited_by_count":11,"area":null},{"id":"2606.08382","title":"STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control","created":"2026-06-07","cited_by_count":11,"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":"2508.01506","title":"FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models","created":"2025-08-02","cited_by_count":9,"area":null},{"id":"2602.08005","title":"ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference","created":"2026-02-08","cited_by_count":9,"area":"inference"},{"id":"2512.19206","title":"MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning","created":"2025-12-22","cited_by_count":8,"area":"lr"},{"id":"2602.03152","title":"FASA: Frequency-aware Sparse Attention","created":"2026-02-03","cited_by_count":8,"area":"inference"},{"id":"2606.03928","title":"Value-Aware Stochastic KV Cache Eviction for Reasoning Models","created":"2026-06-02","cited_by_count":8,"area":"lr"},{"id":"2505.18231","title":"NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache","created":"2025-05-23","cited_by_count":7,"area":"inference"},{"id":"2505.22913","title":"Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference","created":"2025-05-28","cited_by_count":7,"area":"inference"},{"id":"2606.01563","title":"MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference","created":"2026-06-01","cited_by_count":6,"area":"inference"},{"id":"2604.19157","title":"SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving","created":"2026-04-21","cited_by_count":5,"area":"inference"},{"id":"2605.08234","title":"When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression","created":"2026-05-07","cited_by_count":5,"area":"inference"},{"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":"2509.10798","title":"Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction","created":"2025-09-13","cited_by_count":4,"area":"inference"},{"id":"2512.17452","title":"KV Admission: Learning What to Write for Efficient Long-Context LLM Inference","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2605.23258","title":"A Simple Plug-in for Improving Eviction-Based KV Cache Compression","created":"2026-05-22","cited_by_count":4,"area":"inference"},{"id":"2605.31105","title":"GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs","created":"2026-05-29","cited_by_count":4,"area":"inference"},{"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":"2601.21686","title":"Don't be so Stief! Learning KV Cache low-rank approximation over the Stiefel manifold","created":"2026-01-29","cited_by_count":3,"area":"inference"},{"id":"2602.02599","title":"RAP: KV-Cache Compression via RoPE-Aligned Pruning","created":"2026-02-01","cited_by_count":3,"area":"inference"},{"id":"2605.08314","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","created":"2026-05-08","cited_by_count":3,"area":"inference"},{"id":"2601.11471","title":"Low-Rank Key Value Attention","created":"2026-01-16","cited_by_count":2,"area":"inference"},{"id":"2603.02188","title":"Multi-Head Low-Rank Attention","created":"2026-03-02","cited_by_count":2,"area":"inference"},{"id":"2608.04771","title":"Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning","created":"2026-08-05","cited_by_count":2,"area":"lr"},{"id":"2507.01900","title":"High-Layer Attention Pruning with Rescaling","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2512.17917","title":"KVReviver: Reversible KV Cache Compression with Sketch-Based Token Reconstruction","created":"2025-12-01","cited_by_count":1,"area":"inference"},{"id":"2604.09406","title":"OASIS: Online Activation Subspace Learning for Memory-Efficient Training","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2606.24033","title":"RoPE-Aware Bit Allocation for KV-Cache Quantization","created":"2026-06-23","cited_by_count":1,"area":"inference"},{"id":"2607.00760","title":"MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression","created":"2026-07-01","cited_by_count":1,"area":"inference"},{"id":"2607.24555","title":"LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding","created":"2026-07-27","cited_by_count":1,"area":null},{"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":"2608.14191","title":"KV Cache Compression Through the Lens of Transform Coding","created":"2026-08-14","cited_by_count":1,"area":"inference"},{"id":"2609.26300","title":"CompKV: Compensation-Aware KV Selection for Long-Context LLM Inference","created":"2026-09-22","cited_by_count":1,"area":"inference"},{"id":"2604.09595","title":"Why Smaller Is Slower? Dimensional Misalignment in Compressed LLMs","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.17709","title":"DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.10875","title":"Compute Where it Counts: Self Optimizing Language Models","created":"2026-05-11","cited_by_count":0,"area":"inference"},{"id":"2605.16439","title":"KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2607.05399","title":"Benchmarking KV-Cache Optimizations across Task Quality and System Performance for Long-Context Serving","created":"2026-05-03","cited_by_count":0,"area":"inference"},{"id":"2607.12550","title":"A JoLT for the KV cache: Near-Lossless KV Cache Compression via Joint Rank-bit Allocation","created":"2026-07-14","cited_by_count":0,"area":"inference"},{"id":"2607.20538","title":"Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches","created":"2026-07-10","cited_by_count":0,"area":"inference"},{"id":"2608.00528","title":"S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching","created":"2026-08-01","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":"2608.23834","title":"Minima-KV: Retention-Preserving KV Cache Compression with Mixed-Format Paged Attention","created":"2026-08-24","cited_by_count":0,"area":"inference"},{"id":"2608.23843","title":"PuzzleKV: Page-Wise Low-Rank Decomposition for KV Cache Compression","created":"2026-08-24","cited_by_count":0,"area":"inference"},{"id":"2608.26389","title":"LowRankArena: A Standardized Evaluation Platform for SVD-Based LLM Compression","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.05152","title":"Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG","created":"2026-09-04","cited_by_count":0,"area":"rag"},{"id":"2609.06341","title":"Linear Algebra Foundations of Efficient Attention: A Phase Reversal in Rank Collapse Under SVD Compression","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.16617","title":"Divergence Timing and Cumulative Disagreement under KV-Cache Eviction","created":"2026-09-15","cited_by_count":0,"area":"inference"},{"id":"2609.21172","title":"TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching","created":"2026-09-18","cited_by_count":0,"area":"inference"},{"id":"2609.29913","title":"MILO: Efficient Many-shot In-Context Learning with Block-wise Low-rank Compression","created":"2026-09-24","cited_by_count":0,"area":"inference"},{"id":"2609.34060","title":"KVCMAS: Efficient KV cache Correction for Shared Context in Multi-Agent Systems","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2610.02953","title":"SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention","created":"2026-10-02","cited_by_count":0,"area":"inference"},{"id":"2610.06927","title":"AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD","created":"2026-10-03","cited_by_count":0,"area":"inference"},{"id":"2610.09827","title":"Dual-QK: Sharp Queries and Flat Keys for Prunable 2-bit KV Caches","created":"2026-10-07","cited_by_count":0,"area":"inference"},{"id":"2610.14475","title":"EdgeLLM-Nano: Auditing Polar-Guided Key-Cache Compression and Consistency-Anchored Pruning on a 33.6 MB On-Device Language Model","created":"2026-10-10","cited_by_count":0,"area":"inference"},{"id":"2610.17202","title":"MLAfication: Efficiently Enabling High-Fidelity MLA for Modern LLMs","created":"2026-10-12","cited_by_count":0,"area":"inference"},{"id":"2610.17966","title":"BELT : BEhavior-Aligned Low-Rank KV Cache Compression with Learned Top-k Rank Allocation","created":"2026-10-13","cited_by_count":0,"area":"inference"},{"id":"2610.17970","title":"AlignPred: Error-Controlled KV Cache Compression via Alignment and Predictive Coding","created":"2026-10-13","cited_by_count":0,"area":"inference"},{"id":"2610.19605","title":"PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference","created":"2026-10-14","cited_by_count":0,"area":"inference"}],"next_cursor":null}