{"total":125,"rows":[{"id":"2605.18739","title":"LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation","created":"2026-05-18","cited_by_count":30,"area":"diffusion"},{"id":"2607.19191","title":"ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU","created":"2026-07-21","cited_by_count":16,"area":"wm"},{"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":"2605.17757","title":"OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization","created":"2026-05-18","cited_by_count":9,"area":"inference"},{"id":"2604.18555","title":"A Note on TurboQuant and the Earlier DRIVE/EDEN Line of Work","created":"2026-04-20","cited_by_count":8,"area":null},{"id":"2605.13810","title":"Provable Quantization with Randomized Hadamard Transform","created":"2026-05-13","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":"2601.17187","title":"High-Rate Quantized Matrix Multiplication I","created":"2026-01-23","cited_by_count":7,"area":null},{"id":"2605.06014","title":"Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven","created":"2026-05-07","cited_by_count":6,"area":"inference"},{"id":"2607.02461","title":"OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers","created":"2026-07-02","cited_by_count":6,"area":"diffusion"},{"id":"2608.27513","title":"DAMP: Decay-Aware Mixed-Precision Recurrent-State Quantization","created":"2026-08-27","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":"2605.16732","title":"DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers","created":"2026-05-16","cited_by_count":5,"area":"diffusion"},{"id":"2605.17613","title":"VeriCache: Turning Lossy KV Cache into Lossless LLM Inference","created":"2026-05-17","cited_by_count":5,"area":"inference"},{"id":"2605.19660","title":"OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond","created":"2026-05-19","cited_by_count":5,"area":"inference"},{"id":"2604.14442","title":"Hierarchical vs. Flat Iteration in Shared-Weight Transformers","created":"2026-04-15","cited_by_count":4,"area":null},{"id":"2605.05602","title":"Nearly Optimal Attention Coresets","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2605.19932","title":"PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents","created":"2026-05-19","cited_by_count":4,"area":"agents"},{"id":"2605.20868","title":"Runtime-Certified Bounded-Error Quantized Attention","created":"2026-05-20","cited_by_count":4,"area":"inference"},{"id":"2605.25880","title":"The Quantization Benefits of Residual-Free Transformers","created":"2026-05-25","cited_by_count":4,"area":null},{"id":"2602.23200","title":"InnerQ: Hardware-Aware Tuning-Free Quantization of KV Cache for Large Language Models","created":"2026-02-26","cited_by_count":3,"area":"inference"},{"id":"2603.28522","title":"RAD-LAD: Rule and Language Grounded Autonomous Driving in Real-Time","created":"2026-03-30","cited_by_count":3,"area":"driving"},{"id":"2604.19528","title":"Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments","created":"2026-04-21","cited_by_count":3,"area":null},{"id":"2605.06675","title":"RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory","created":"2026-04-22","cited_by_count":3,"area":"inference"},{"id":"2603.27467","title":"TurboAngle: Near-Lossless KV Cache Compression via Uniform Angle Quantization","created":"2026-03-29","cited_by_count":2,"area":"inference"},{"id":"2603.28430","title":"IsoQuant: Hardware-Aligned SO(4) Isoclinic Rotations for LLM KV Cache Compression","created":"2026-03-30","cited_by_count":2,"area":"inference"},{"id":"2603.29078","title":"PolarQuant: Optimal Gaussian Weight Quantization via Hadamard Rotation for LLM Compression","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2604.04514","title":"SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems","created":"2026-04-06","cited_by_count":2,"area":"agents"},{"id":"2604.16957","title":"Open-TQ-Metal: Fused Compressed-Domain Attention for Long-Context LLM Inference on Apple Silicon","created":"2026-04-18","cited_by_count":2,"area":"inference"},{"id":"2604.23418","title":"Approximating Uniform Random Rotations by Two-Stage Structured Hadamard Rotations in High Dimensions","created":"2026-04-25","cited_by_count":2,"area":null},{"id":"2605.02905","title":"eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization","created":"2026-04-06","cited_by_count":2,"area":"inference"},{"id":"2605.05170","title":"Design Conductor 2.0: An agent builds a TurboQuant inference accelerator in 80 hours","created":"2026-05-06","cited_by_count":2,"area":"agents"},{"id":"2605.08114","title":"Statistical Inference and Quality Measures of KV Cache Quantisations Inspired by TurboQuant","created":"2026-04-27","cited_by_count":2,"area":"inference"},{"id":"2605.11478","title":"FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression","created":"2026-05-12","cited_by_count":2,"area":"inference"},{"id":"2605.21226","title":"OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization","created":"2026-05-20","cited_by_count":2,"area":"inference"},{"id":"2605.26266","title":"Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion","created":"2026-05-25","cited_by_count":2,"area":"diffusion"},{"id":"2608.02691","title":"Output-Aware Rotation for INT2 KV-Cache Quantization","created":"2026-08-03","cited_by_count":2,"area":"inference"},{"id":"2608.04074","title":"Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms","created":"2026-08-04","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":"2608.08253","title":"SuperLocalMemory 4.0: The Governed Memory Operating System for AI Agents","created":"2026-08-08","cited_by_count":2,"area":null},{"id":"2604.02638","title":"AXELRAM: Quantize Once, Never Dequantize","created":"2026-04-03","cited_by_count":1,"area":"inference"},{"id":"2604.10603","title":"MoEITS: A Green AI approach for simplifying MoE-LLMs","created":"2026-04-12","cited_by_count":1,"area":"moe"},{"id":"2604.15356","title":"Sequential KV Cache Compression via Probabilistic Language Tries: Beyond the Per-Vector Shannon Limit","created":"2026-04-10","cited_by_count":1,"area":"inference"},{"id":"2604.25080","title":"CacheFlow: Efficient LLM Serving with 3D-Parallel KV Cache Restoration","created":"2026-04-28","cited_by_count":1,"area":"rag"},{"id":"2605.15507","title":"PrismQuant: Rate-Distortion-Optimal Vector Quantization for Gaussian-Mixture Sources","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.22850","title":"ObjectCache: Layerwise Object-Storage Retrieval for KV Cache Reuse","created":"2026-05-16","cited_by_count":1,"area":"inference"},{"id":"2606.01074","title":"When Is 0.1% Enough? Analyzing the Combined Effects of Dimensionality Reduction and Quantization on Text Embedding Compression","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2606.07116","title":"OffQ: Taming Structured Outliers in LLM Quantization by Offsetting","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.08761","title":"APEX4: Efficient Pure W4A4 LLM Inference via Intra-SM Compute Rebalancing","created":"2026-06-07","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":"2606.27567","title":"On the Inseparability of Instructions and Data in Shared-Embedding Sequence Models","created":"2026-06-25","cited_by_count":1,"area":"safety"},{"id":"2607.12188","title":"Cost-Governed RAG: Unified Per-Tenant Cost Attribution Across Retrieval and Generation in Multi-Tenant LLM Systems","created":"2026-07-13","cited_by_count":1,"area":"rag"},{"id":"2607.27546","title":"Memory Efficient Tabular Foundation Models","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2607.27600","title":"Back from the Future: Key-Value Cache Management by Counter-Causal Surprise","created":"2026-07-30","cited_by_count":1,"area":"inference"},{"id":"2608.01428","title":"When Replanning Becomes the Bottleneck: Budgeted Replanning for Embodied Agents","created":"2026-08-02","cited_by_count":1,"area":"agents"},{"id":"2608.02901","title":"AnchorKV: Anchor-Residual KV Cache Compression","created":"2026-08-03","cited_by_count":1,"area":"inference"},{"id":"2608.07915","title":"SPECTRA: Pushing the KV Cache Beyond the 2-Bit Cliff via Spectral Transform Coding","created":"2026-08-08","cited_by_count":1,"area":"agents"},{"id":"2608.14191","title":"KV Cache Compression Through the Lens of Transform Coding","created":"2026-08-14","cited_by_count":1,"area":"inference"},{"id":"2609.24298","title":"KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation","created":"2026-09-21","cited_by_count":1,"area":"inference"},{"id":"2609.39329","title":"PatchKV: Weight-Space Compensation of KV Cache","created":"2026-09-30","cited_by_count":1,"area":"inference"},{"id":"2602.00079","title":"Embedding Compression via Spherical Coordinates","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.00165","title":"Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2604.05366","title":"3DTurboQuant: Training-Free Near-Optimal Quantization for 3D Reconstruction Models","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.21026","title":"MCAP: Deployment-Time Layer Profiling for Memory-Constrained LLM Inference","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.22786","title":"AutoCompress: Critical Layer Isolation for Efficient Transformer Compression","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.24008","title":"Coverage-Based Calibration for Post-Training Quantization via Weighted Set Cover over Outlier Channels","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.03562","title":"HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization","created":"2026-05-05","cited_by_count":0,"area":"inference"},{"id":"2605.05699","title":"When Quantization Is Free: An int4 KV Cache That Outruns fp16 on Apple Silicon","created":"2026-05-07","cited_by_count":0,"area":"inference"},{"id":"2605.07662","title":"Direction-Preserving Number Representations","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.17415","title":"IVF-TQ: Calibration-Free Streaming Vector Search via a Codebook-Free Residual Layer","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.19972","title":"Block-Sphere Vector Quantization","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.00289","title":"Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive Algorithms","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.07404","title":"Reversible Foundations: Training a 120B Sparse MoE through State-Preserving Scaling","created":"2026-06-05","cited_by_count":0,"area":"moe"},{"id":"2606.08565","title":"EinSort: Sorting is All We Need for Tensorizing LLM","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.19562","title":"Advances in Scientific Machine Learning for Coupled Fluid Flow and Transport","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.20295","title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.20474","title":"UltraQuant: 4-bit KV Caching for Context-Heavy Agents","created":"2026-06-18","cited_by_count":0,"area":null},{"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":"2607.07207","title":"Memory Scarcity, Open Models, and the Restructuring of the AI Industry, 2026-2030 -- A quantitative scenario analysis of inference economics, training-cost divergence, and infrastructure solvency","created":"2026-07-08","cited_by_count":0,"area":"inference"},{"id":"2607.09683","title":"Ablation, Statistical Inference, and Validation for KV-Cache Compression","created":"2026-06-14","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":"2607.16248","title":"High-accuracy Low-Bit KV-Cache Quantization via Local Distribution Restoration","created":"2026-06-27","cited_by_count":0,"area":"inference"},{"id":"2607.16973","title":"TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious Quantization","created":"2026-07-18","cited_by_count":0,"area":"rag"},{"id":"2608.05127","title":"SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.11240","title":"VQ-bench: A Composable Vector Quantization Framework","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.13365","title":"When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.14648","title":"Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.15369","title":"AudioTQ: A Data-Oblivious 6-Bit CPU Audio Codec via Randomized Hadamard Rotation and Lloyd-Max Quantization","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.19920","title":"Learning how to Forget: Fine-tuning for Long-Context Sparse Attention","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.21693","title":"Benchmarking Composable Compression Techniques in Mixture-of-Experts LLMs","created":"2026-08-22","cited_by_count":0,"area":"moe"},{"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":"2608.24971","title":"HCC+: Hyperbolic Guarding for Certified Attention Retrieval","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.25188","title":"Transforms for LLM Quantization: The Great Inversion and Format Co-Design","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.28293","title":"A Probabilistic Interpretation of KV Cache Eviction","created":"2026-08-28","cited_by_count":0,"area":"inference"},{"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":"2608.30384","title":"RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.05764","title":"Interface-Aware KV Cache Quantization for Dense On-Chip NVM in Long-Context LLM Decoding","created":"2026-09-04","cited_by_count":0,"area":"inference"},{"id":"2609.06940","title":"Unified AI Gateway: A Framework for Joint Model Routing and KV Cache Management","created":"2026-09-07","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":"100"}