{"total":60,"rows":[{"id":"2503.08026","title":"In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents","created":"2025-03-11","cited_by_count":106,"area":"agents"},{"id":"2510.02912","title":"Don't Just Chase \"Highlighted Tokens\" in MLLMs: Revisiting Visual Holistic Context Retention","created":"2025-10-03","cited_by_count":47,"area":"mllm"},{"id":"2602.06052","title":"A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents","created":"2026-01-14","cited_by_count":44,"area":"agents"},{"id":"2502.01941","title":"Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression","created":"2025-02-04","cited_by_count":16,"area":"lr"},{"id":"2602.21221","title":"Latent Context Compilation: Distilling Long Context into Compact Portable Memory","created":"2026-01-31","cited_by_count":13,"area":null},{"id":"2503.08640","title":"Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention","created":"2025-03-11","cited_by_count":12,"area":null},{"id":"2510.16234","title":"ScholarEval: Research Idea Evaluation Grounded in Literature","created":"2025-10-17","cited_by_count":12,"area":null},{"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":"2605.15677","title":"VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing","created":"2026-05-15","cited_by_count":9,"area":"mllm"},{"id":"2509.15038","title":"Value-Guided KV Compression for LLMs via Approximated CUR Decomposition","created":"2025-09-18","cited_by_count":7,"area":null},{"id":"2505.15347","title":"FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management","created":"2025-05-21","cited_by_count":6,"area":"inference"},{"id":"2603.11504","title":"LongFlow: Efficient KV Cache Compression for Reasoning Models","created":"2026-03-12","cited_by_count":6,"area":"lr"},{"id":"2512.07993","title":"SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models","created":"2025-12-08","cited_by_count":5,"area":"lr"},{"id":"2602.23592","title":"KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning","created":"2026-02-27","cited_by_count":5,"area":"inference"},{"id":"2605.05838","title":"MDN: Parallelizing Stepwise Momentum for Delta Linear Attention","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2603.04592","title":"From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2607.10582","title":"MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference","created":"2026-07-12","cited_by_count":3,"area":"agents"},{"id":"2608.01247","title":"RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction","created":"2026-08-02","cited_by_count":3,"area":"inference"},{"id":"2608.19662","title":"ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents","created":"2026-08-20","cited_by_count":3,"area":"agents"},{"id":"2602.08686","title":"CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2603.00188","title":"ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents","created":"2026-02-27","cited_by_count":2,"area":"inference"},{"id":"2605.18856","title":"SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference","created":"2026-05-13","cited_by_count":2,"area":"inference"},{"id":"2606.26472","title":"Epiphany-Aware KV Cache Eviction Without the Attention Matrix","created":"2026-06-25","cited_by_count":2,"area":"lr"},{"id":"2607.01237","title":"KARA: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression","created":"2026-05-01","cited_by_count":2,"area":"lr"},{"id":"2608.01631","title":"Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression","created":"2026-08-03","cited_by_count":2,"area":"inference"},{"id":"2608.07001","title":"Every Cache Entry Earns Its Place: Global Allocation of Resolution and Coverage for KV Cache Compression","created":"2026-08-07","cited_by_count":2,"area":"inference"},{"id":"2502.13251","title":"Neural Attention Search","created":"2025-02-18","cited_by_count":1,"area":"inference"},{"id":"2512.09238","title":"Training-free Context-adaptive Attention for Efficient Long Context Modeling","created":"2025-12-10","cited_by_count":1,"area":"inference"},{"id":"2601.13631","title":"ContiguousKV: Accelerating LLM Prefill with Granularity-Aligned KV Cache Management","created":"2026-01-20","cited_by_count":1,"area":"inference"},{"id":"2601.17702","title":"S$^3$-Attention:Attention-Aligned Endogenous Retrieval for Memory-Bounded Long-Context Inference","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2602.20732","title":"CHESS: Context-aware Hierarchical Efficient Semantic Selection for Long-Context LLM Inference","created":"2026-02-24","cited_by_count":1,"area":"inference"},{"id":"2603.12038","title":"Slow-Fast Inference: Training-Free Inference Acceleration via Within-Sentence Support Stability","created":"2026-03-12","cited_by_count":1,"area":"inference"},{"id":"2604.10235","title":"CodeComp: Structural KV Cache Compression for Agentic Coding","created":"2026-04-11","cited_by_count":1,"area":"agents"},{"id":"2604.11288","title":"Transactional Attention: Semantic Sponsorship for KV-Cache Retention","created":"2026-04-13","cited_by_count":1,"area":"inference"},{"id":"2605.03644","title":"AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2605.11744","title":"Training-Inference Consistent Segmented Execution for Long-Context LLMs","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.23200","title":"Adaptive Mass-Segmented KV Compression for Long-Context Reasoning","created":"2026-05-22","cited_by_count":1,"area":"lr"},{"id":"2607.06523","title":"DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression","created":"2026-07-07","cited_by_count":1,"area":"inference"},{"id":"2608.00311","title":"SeDeM: Selective Decompression of Hidden-State Memories for Long-Context Question Answering","created":"2026-07-31","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":"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":"2602.03184","title":"DynSplit-KV: Dynamic Semantic Splitting for KVCache Compression in Efficient Long-Context LLM Inference","created":"2026-02-03","cited_by_count":0,"area":"inference"},{"id":"2603.21576","title":"PRISM: Breaking the O(n) Memory Wall in Long-Context LLM Inference via O(1) Photonic Block Selection","created":"2026-03-23","cited_by_count":0,"area":"inference"},{"id":"2604.12452","title":"Latent-Condensed Transformer for Efficient Long Context Modeling","created":"2026-04-14","cited_by_count":0,"area":"inference"},{"id":"2606.00024","title":"ART: Attention Run-time Termination for Efficient Large Language Model Decoding","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2606.31145","title":"SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference","created":"2026-06-30","cited_by_count":0,"area":"inference"},{"id":"2607.02574","title":"From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving","created":"2026-06-30","cited_by_count":0,"area":"inference"},{"id":"2607.06519","title":"FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference","created":"2026-07-07","cited_by_count":0,"area":"inference"},{"id":"2607.16213","title":"SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation","created":"2026-05-19","cited_by_count":0,"area":"inference"},{"id":"2607.20981","title":"Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence","created":"2026-07-23","cited_by_count":0,"area":"moe"},{"id":"2608.08569","title":"VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference","created":"2026-08-09","cited_by_count":0,"area":"inference"},{"id":"2608.22704","title":"WnW: Waxing-and-Waning KV Cache for Long-Form Speech LLMs","created":"2026-08-24","cited_by_count":0,"area":"inference"},{"id":"2608.27128","title":"Small Frequency Corrections Can Change What Survives KV Cache Compression","created":"2026-08-27","cited_by_count":0,"area":"inference"},{"id":"2608.28276","title":"Parser Transitions Already Reveal Structural Responsibility: KV Persistence for Structured Generation","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.28911","title":"SemKV: Semantic Mixed-Precision KV Cache Quantization Guided by the Quality Cliff for Long-Context LLM Inference","created":"2026-08-28","cited_by_count":0,"area":"inference"},{"id":"2609.32046","title":"Receiver-Conditioned Latent Communication gives 94% CacheBack","created":"2026-09-25","cited_by_count":0,"area":"inference"},{"id":"2610.02736","title":"TPBench: A Turning-Point Benchmark for Dialogue Compression","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.12133","title":"Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.16636","title":"SuPER-Mamba: Surprisal Prioritization for Extended-Context Routing in Mamba","created":"2026-10-12","cited_by_count":0,"area":"ssm"},{"id":"2610.17926","title":"CineMem: Attention-Aligned Fine-grained Memory Retrieval for Multi-Shot Long Video Generation","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}