{"total":92,"rows":[{"id":"2406.02657","title":"Block Transformer: Global-to-Local Language Modeling for Fast Inference","created":"2024-06-04","cited_by_count":32,"area":"inference"},{"id":"2505.07004","title":"GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance","created":"2025-05-11","cited_by_count":32,"area":null},{"id":"2406.05981","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2405.07518","title":"SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts","created":"2024-05-13","cited_by_count":18,"area":null},{"id":"2411.11745","title":"BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration","created":"2024-11-18","cited_by_count":18,"area":null},{"id":"2502.03304","title":"Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning","created":"2025-02-05","cited_by_count":18,"area":null},{"id":"2502.13575","title":"ETS: Efficient Tree Search for Inference-Time Scaling","created":"2025-02-19","cited_by_count":16,"area":"lr"},{"id":"2412.11702","title":"Flex-PE: Flexible and SIMD Multi-Precision Processing Element for AI Workloads","created":"2024-12-16","cited_by_count":15,"area":null},{"id":"2405.01814","title":"Efficient Heterogeneous Large Language Model Decoding with Model-Attention Disaggregation","created":"2024-05-03","cited_by_count":12,"area":null},{"id":"2406.11151","title":"Recent and Upcoming Developments in Randomized Numerical Linear Algebra for Machine Learning","created":"2024-06-17","cited_by_count":11,"area":null},{"id":"2412.01380","title":"Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking","created":"2024-12-02","cited_by_count":11,"area":"inference"},{"id":"2501.01144","title":"BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference","created":"2025-01-02","cited_by_count":11,"area":"inference"},{"id":"2602.11287","title":"HiFloat4 Format for Language Model Inference","created":"2026-02-11","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":"2412.15304","title":"TinyLLM: A Framework for Training and Deploying Language Models at the Edge Computers","created":"2024-12-19","cited_by_count":9,"area":null},{"id":"2408.14158","title":"Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning","created":"2024-08-26","cited_by_count":8,"area":null},{"id":"2412.03317","title":"FlashAttention on a Napkin: A Diagrammatic Approach to Deep Learning IO-Awareness","created":"2024-12-04","cited_by_count":7,"area":null},{"id":"2502.02790","title":"Leveraging the true depth of LLMs","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2606.04980","title":"AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization","created":"2026-06-03","cited_by_count":7,"area":"moe"},{"id":"2409.15022","title":"A Diagonal Structured State Space Model on Loihi 2 for Efficient Streaming Sequence Processing","created":"2024-09-23","cited_by_count":6,"area":"ssm"},{"id":"2412.04180","title":"SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization","created":"2024-12-05","cited_by_count":6,"area":null},{"id":"2502.16473","title":"TerEffic: Highly Efficient Ternary LLM Inference on FPGA","created":"2025-02-23","cited_by_count":6,"area":null},{"id":"2505.13430","title":"Fine-tuning Quantized Neural Networks with Zeroth-order Optimization","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2510.14719","title":"Tawa: Automatic Warp Specialization for Modern GPUs with Asynchronous References","created":"2025-10-16","cited_by_count":6,"area":null},{"id":"2602.05902","title":"CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2606.18967","title":"EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts","created":"2026-06-17","cited_by_count":6,"area":"lr"},{"id":"2507.00004","title":"A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search","created":"2025-06-10","cited_by_count":5,"area":"lr"},{"id":"2503.04424","title":"Determinant Estimation under Memory Constraints and Neural Scaling Laws","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2506.08785","title":"POLARON: Precision-aware On-device Learning and Adaptive Runtime-cONfigurable AI acceleration","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2508.10395","title":"XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization","created":"2025-08-14","cited_by_count":4,"area":"inference"},{"id":"2511.00321","title":"Scalable Processing-Near-Memory for 1M-Token LLM Inference: CXL-Enabled KV-Cache Management Beyond GPU Limits","created":"2025-10-31","cited_by_count":4,"area":"inference"},{"id":"2602.08923","title":"DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2605.06676","title":"LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction","created":"2026-04-22","cited_by_count":4,"area":"inference"},{"id":"2404.08811","title":"Reducing the Barriers to Entry for Foundation Model Training","created":"2024-04-12","cited_by_count":3,"area":null},{"id":"2409.05227","title":"BBS: Bi-directional Bit-level Sparsity for Deep Learning Acceleration","created":"2024-09-08","cited_by_count":3,"area":null},{"id":"2411.17309","title":"PIM-AI: A Novel Architecture for High-Efficiency LLM Inference","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2501.11847","title":"A Survey on Memory-Efficient Transformer-Based Model Training in AI for Science","created":"2025-01-21","cited_by_count":3,"area":null},{"id":"2602.02599","title":"RAP: KV-Cache Compression via RoPE-Aligned Pruning","created":"2026-02-01","cited_by_count":3,"area":"inference"},{"id":"2603.21725","title":"CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2501.19099","title":"Elucidating Subspace Perturbation in Zeroth-Order Optimization: Theory and Practice at Scale","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2505.02380","title":"EntroLLM: Entropy Encoded Weight Compression for Efficient Large Language Model Inference on Edge Devices","created":"2025-05-05","cited_by_count":2,"area":"inference"},{"id":"2512.05033","title":"Arbitrage: Efficient Reasoning via Advantage-Aware Speculation","created":"2025-12-04","cited_by_count":2,"area":"lr"},{"id":"2603.02188","title":"Multi-Head Low-Rank Attention","created":"2026-03-02","cited_by_count":2,"area":"inference"},{"id":"2605.04738","title":"OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization","created":"2026-05-06","cited_by_count":2,"area":null},{"id":"2606.02775","title":"AURA: Action-Gated Memory for Robot Policies at Constant VRAM","created":"2026-06-01","cited_by_count":2,"area":"inference"},{"id":"2407.08205","title":"OPIMA: Optical Processing-In-Memory for Convolutional Neural Network Acceleration","created":"2024-07-11","cited_by_count":1,"area":null},{"id":"2407.09093","title":"On Exact Bit-level Reversible Transformers Without Changing Architectures","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2407.10545","title":"LightCL: Compact Continual Learning with Low Memory Footprint For Edge Device","created":"2024-07-15","cited_by_count":1,"area":null},{"id":"2505.01107","title":"CIMFlow: An Integrated Framework for Systematic Design and Evaluation of Digital CIM Architectures","created":"2025-05-02","cited_by_count":1,"area":null},{"id":"2506.01827","title":"Memory Access Characterization of Large Language Models in CPU Environment and its Potential Impacts","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2506.11994","title":"Spectral Estimation with Free Decompression","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2508.13231","title":"Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System","created":"2025-08-17","cited_by_count":1,"area":"inference"},{"id":"2509.25853","title":"SAIL: SRAM-Accelerated LLM Inference System with Lookup-Table-based GEMV","created":"2025-09-30","cited_by_count":1,"area":"inference"},{"id":"2510.11234","title":"Neural Weight Compression for Language Models","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2602.00608","title":"Scalable Generative Game Engine: Breaking the Resolution Wall via Hardware-Algorithm Co-Design","created":"2026-01-31","cited_by_count":1,"area":"wm"},{"id":"2603.17910","title":"SpiderCam: Low-Power Snapshot Depth from Differential Defocus","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2604.05438","title":"Residual-Mass Accounting for Partial-KV Decoding","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.15250","title":"GQLA: Group-Query Latent Attention for Hardware-Adaptive Decoding","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2609.16161","title":"LLM Inference in a Flash!","created":"2026-09-14","cited_by_count":1,"area":"inference"},{"id":"2609.35751","title":"How to Loop MoE: Flatten the Experts, Untie the Attention","created":"2026-09-28","cited_by_count":1,"area":"moe"},{"id":"2407.14504","title":"Physical Data Embedding for Memory Efficient AI","created":"2024-07-19","cited_by_count":0,"area":null},{"id":"2408.10942","title":"Robust Regression with Ensembles Communicating over Noisy Channels","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2411.01818","title":"Shrinking the Giant : Quasi-Weightless Transformers for Low Energy Inference","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2411.08645","title":"A System Level Performance Evaluation for Superconducting Digital Systems","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2411.10764","title":"ML$^2$Tuner: Efficient Code Tuning via Multi-Level Machine Learning Models","created":"2024-11-16","cited_by_count":0,"area":null},{"id":"2412.01195","title":"Memory-Efficient Training for Deep Speaker Embedding Learning in Speaker Verification","created":"2024-12-02","cited_by_count":0,"area":null},{"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":"2505.18313","title":"PLUMAGE: Probabilistic Low rank Unbiased Min Variance Gradient Estimator for Efficient Large Model Training","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.23225","title":"Masked Gated Linear Unit","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2507.06461","title":"Energy-Efficient Supervised Learning with a Binary Stochastic Forward-Forward Algorithm","created":"2025-07-09","cited_by_count":0,"area":null},{"id":"2509.03846","title":"Hardware-Aware Data and Instruction Mapping for AI Tasks: Balancing Parallelism, I/O and Memory Tradeoffs","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2510.22909","title":"Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directions","created":"2025-10-27","cited_by_count":0,"area":"lr"},{"id":"2512.12428","title":"Learning Dynamics in Memristor-Based Equilibrium Propagation","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2601.19904","title":"DABench-LLM: Standardized and In-Depth Benchmarking of Post-Moore Dataflow AI Accelerators for LLMs","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2602.08062","title":"Efficient and Adaptable Detection of Malicious LLM Prompts via Bootstrap Aggregation","created":"2026-02-08","cited_by_count":0,"area":"synth"},{"id":"2602.09323","title":"LLM-CoOpt: A Co-Design and Optimization Framework for Efficient LLM Inference on Heterogeneous Platforms","created":"2026-02-10","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":"2604.04701","title":"MUXQ: Mixed-to-Uniform Precision MatriX Quantization via Low-Rank Outlier Decomposition","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.07242","title":"Weaves, Wires, and Morphisms: Formalizing and Implementing the Algebra of Deep Learning","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.30728","title":"Reducing the GPU Memory Bottleneck with Lossless Compression for ML -- Extended","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.01127","title":"$\\text{Log}_\\text{b}$Quant: Quantizing Language Models in Logarithmic Space","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.18548","title":"Engineering Trustworthy Agentic AI for Critical Systems","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2607.29575","title":"SLIM: Saturation-Aware Lightweight Performance Modeling for LLM Serving","created":"2026-07-31","cited_by_count":0,"area":"inference"},{"id":"2608.11688","title":"APEX: Adaptive Expert Prefetching for Memory-Efficient Edge MoE Inference","created":"2026-08-12","cited_by_count":0,"area":"moe"},{"id":"2608.22613","title":"NOVA: Technology-Architecture Co-Design of Near-Memory Processing for Attention-SSM-MoE Hybrid LLM Inference","created":"2026-08-23","cited_by_count":0,"area":"moe"},{"id":"2608.25062","title":"FLINT: Efficiently Leveraging High Bandwidth Flash for Capacity-Scalable LLM Inference Acceleration","created":"2026-08-25","cited_by_count":0,"area":"inference"},{"id":"2608.28667","title":"GreenBench: Benchmarking Energy Efficiency and Carbon Footprint of Open-Source LLM Inference on Apple Silicon","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.23816","title":"SPLASH: Co-Designing Sparse Attention with High-Bandwidth Flash for Efficient Long-Context Inference","created":"2026-09-20","cited_by_count":0,"area":"inference"},{"id":"2609.28358","title":"MicroQonv: Reshaping Convolution Tensors for Efficient Microscaling in Training and Inference","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.14277","title":"Echo: Error-Compensated 4-Bit Tensor-Parallel Communication for LLM Training and Inference","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.19232","title":"Spectral-MoE: Heterogeneous Per-Layer Expert Utilization in Dense-to-MoE Conversion","created":"2026-10-13","cited_by_count":0,"area":"moe"}],"next_cursor":null}