001 HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding arXiv Paper Chao Fang, Jun Yin et al. 7 days ago 002 QC-PHAST Search: Classical--Quantum Query Benchmarks for Finite-Pool Rare-Regime Discovery arXiv Paper Harsh Milind Tirhekar, Chandrajit Bajaj 7 days ago 003 Sparse by Command: Task-Conditional Compute Skipping for Multi-Task Inference Accelerators arXiv Paper Afzal Ahmad, Gaoyu Mao et al. 7 days ago 004 Unified Static-Dynamic Pruning for Efficient LLM Inference arXiv Paper Deyu Yang, Rundong Wei et al. 7 days ago 005 An Analytically Trained Variational Surrogate for Quantum Phase Estimation on NISQ Hardware arXiv Paper Mousumi Kundu, A. Patra et al. Jul 23 006 Approximate Quantum State Preparation Through Proximal Policy Optimization arXiv Paper Marco Mordacci, Michele Amoretti Jul 23 007 Clustered Edge Intelligence: Beyond Just Convergence of Edge Computing and AI arXiv Paper C. Dehury, Boris Sedlak et al. Jul 23 008 Decentralized Compute on Untrusted Hardware Using Intel TDX and Encrypted CVMs arXiv Paper J. Hurtado Jul 23 009 Hardware-Software Co-Design for Float16 On-Device Training on RISC-V Single-Core arXiv Paper Benjamin Hubinet, P. Moellic et al. Jul 23 010 RED-PIM: Reducing Data Movement for Transformers using Processing-in-Memory arXiv Paper Alexandru Meterez, Pranav Ajit Nair et al. Jul 23 011 Scaling Up Formal Representation of Clinical Trial Protocols in Ensemble Logic Using LLMs: A Preliminary Study arXiv Paper Yan Huang, Xubing Hao et al. Jul 23 012 Spectral Transformation for Layer-wise Global Rank Discovery in Federated LoRA for Vision Transformers arXiv Paper Hariharan Ramesh, Jyotikrishna Dass Jul 23 013 The Boundaries of Automation: A Theory of Persistent Human Participation arXiv Paper Fares Fourati, Hinrich Schütze et al. Jul 23 014 The Consensus Number of Untraceable Cryptocurrencies arXiv Paper Christian Cachin, David Lehnherr et al. Jul 23 015 Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry arXiv Paper Natan Levy, Harel Berger Jul 23 016 Unsupervised Consensus-Based Anomaly Detection for Spatiotemporal Malaria Incidence in Ghana arXiv Paper T. Ansah-Narh, Y. Afrane Jul 23 017 Windowed-MTP: Removing the Full-Context Draft-KV Tax at Million-Token Context arXiv Paper Alagappan Valliappan Jul 23 018 A Framework for Reputation Aware Uninorm-driven Consensus Algorithms for Blockchain Networks arXiv Paper Bruno Ramos-Cruz, Javier Andreu-Pérez et al. Jul 22 019 AlphaRoute: Large Language Models as Semantic Optimizers for Multi-Objective Routing arXiv Paper Kabir Murjani, Mishri Bhavsar et al. Jul 22 020 DQAOA-GPT: AI-Accelerated Distributed Quantum Optimization for Combinatorial Problems arXiv Paper Seongmin Kim, A. Rijal et al. Jul 22 021 FMRP-LEAN: A HIPAA-Compliant AI-Augmented LIMS Architecture for End-to-End Clinical Assay Workflow Optimization arXiv Paper Eva McCord, Ernie V Pedapati et al. Jul 22 022 Formal Foundations for Known Good Reliable Die Screening in Chiplet-Based AI Systems-on-Chip arXiv Paper Prashanthi Metku, Chandra Gandu Jul 22 023 Leveraging ECRAM for Edge Continual Learning arXiv Paper Nabila Tasnim, Haoran Liu et al. Jul 22 024 Machine-Learned Compact Subspace Generation for Quantum Selected Configuration Interaction within Density Matrix Embedding Framework arXiv Paper A. Patra, V. AnuragK.S. et al. Jul 22 025 Self-organizing Architecture of Receptron Units: a Hardware-Aware Framework for Edge Intelligence arXiv Paper Stefano Radice, Ludovico Casaccia et al. Jul 22 026 WaveformQA: Benchmarking LLM Temporal Reasoning on Digital Waveforms arXiv Paper Yichuan Liu, Daniel G Cummings et al. Jul 22 027 BaseRT: Advancing Best-in-Class LLM Inference with Apple M5 Neural Accelerators arXiv Paper Fabian Waschkowski, Prabod Rathnayaka et al. Jul 21 028 CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability arXiv Paper Pratinav Seth, Hem Gosalia et al. Jul 21 029 Fine-grained Computation-Communication Overlap via Tile-level Signaling and Scheduling for Mixture-of-Experts arXiv Paper Minyu Cui, Anna Wingkvist et al. Jul 21 030 Formulation-Level Auto-Tuning for QUBO-Based Machine Learning: A Case Study Across Multiple Quantum-Inspired Annealers arXiv Paper Naoya Mizuki, Takahiro Katagiri et al. Jul 21 031 From Bit-Position Sensitivity to Unequal Error Protection for DNN Inference Memory arXiv Paper Muhammad Husnain Mubarik, Karthik Mohan Kumar et al. Jul 21 032 Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark arXiv Paper Zihan Zhang, Yu Bao et al. Jul 21 033 SynPre-FL: Synthetic data-driven pretraining integrated Federated Learning training framework arXiv Paper Akarsh K. Nair, Muhammad Arifur Rahman et al. Jul 21 034 AutoEncoder-Compressed Parallel Split Learning for Pre-trained Model Fine-Tuning arXiv Paper Bas Meuwissen, Vasileios Tsouvalas et al. Jul 20 035 BRIM: Workload-Balanced Dual-Sided Bit-Serial Sparse Inference Accelerator arXiv Paper Varun Manjunath, Ruokai Yin et al. Jul 20 036 COLIP-2: Olfaction-Vision-Language Embeddings arXiv Paper Kordel K. France Jul 20 037 Can AI Agents Really Complete RTL-to-GDS? Lessons from Benchmarking Tool-Interactive EDA Workflows arXiv Paper Jinyuan Deng, Zhengrui Chen et al. Jul 20 038 D-NOVA: In-Storage Retrieval Accelerator via Dual-Bound 3D NAND-Optimized Similarity Search with Vector Adaptation arXiv Paper Chang Eun Song, Sumukh Pinge et al. Jul 20 039 Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator arXiv Paper M. Piechocki, Alessandro Capotondi et al. Jul 20 040 Entanglement geometry separates circuit cutting, classical hardness, and trainability arXiv Paper Maria Gragera Garces, Sabin V. Dragoi et al. Jul 20 041 Governing Well in the Algorithmic Age: The Foundations of Digital Statecraft arXiv Paper Zeynep Engin, Tim Gordon et al. Jul 20 042 Hardware Mechanisms to Dynamically Throttle AI Performance arXiv Paper Haiyue Ma, Lauren Malek et al. Jul 20 043 Isolation Failure From Shared Storage: Characterizing and Exploiting Page-Cache SCA Leakage Across Containers and VMs arXiv Paper Alon Abudraham, Xingyu Chen et al. Jul 20 044 Mobius Learning: Cyclic Depth Folding in Transformers arXiv Paper Tongtian Zhu Jul 20 045 Opto-ViT-v2: Noise-Resilient On-Chip Fine-Tuning for Photonic Near-Sensor Vision Transformer Accelerators arXiv Paper Xuming Chen et al. Jul 20 046 PIP-NTT: Towards a Scalable Memory-Parallelized Accelerator for Iterative NTT in PQC arXiv Paper Malik Imran, A. Khalid et al. Jul 20 047 PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption arXiv Paper Sahaj Majavdia, Mahdi Taheri Jul 20 048 RRAM-DP: Device-Calibrated Differential Privacy for In-Memory Edge Learning arXiv Paper Kwunhang Wong, Jichang Yang et al. Jul 20 049 SALT: Salience-Aware Lexical Trie for Long-Context Compression arXiv Paper Oteo Mamo, Hyunji Yi et al. Jul 20 050 OrderMoE: An expert similarity driven distributed edge MoE inference arXiv Paper Xin Yuan, Ning Li et al. Jul 19 051 Talaria: Session-Aware Serverless Serving of Hundred-Billion-Parameter LLMs arXiv Paper Utopia Meng, Unicornt Zhao et al. Jul 19 052 Taurus: Accelerating Out-of-Core Graph Neural Network Inference on Billion-Scale Graphs arXiv Paper Pranjal Naman, Yogesh L. Simmhan Jul 19 053 ThAME: 3D Memory-Enabled Heterogeneous Accelerator for LLM Mixture of Experts arXiv Paper Pratyush Dhingra, Pramit Kumar Pal et al. Jul 19 054 ThRIve: Thermally Robust CNN Inference via Low-Rank Adaptation in Heterogeneous PIM Architectures arXiv Paper Vibhanshu Sharma, Pratyush Dhingra et al. Jul 19 055 The Optimization Trilemma: Efficiency, Comfort and Fairness in Decentralized Multi-agent Coordination arXiv Paper Jovan Nikolic, M. Zuziak et al. Jul 19 056 Explainable Lightweight Compact Deep Models for Speech Emotion Recognition arXiv Paper Nelly Elsayed Jul 18 057 SABLE: Minimalist Instruction-Level Authenticated Encryption for Constrained Confidential Computing arXiv Paper Hamid Noori, Carlton Shepherd Jul 18 058 A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing arXiv Paper Owen Lockwood, Jérémy H. Béjanin et al. Jul 17 059 A Quantum-Classical Hybrid Framework for Multivariate Time-Series Forecasting Complexity-Fidelity Trade-offs and Limitations arXiv Paper S. Chakraborty, Fredrik Heintz Jul 17 060 AgentFAIR: A Multi-Agent Collaborative Framework for FAIRness Evaluation of Geospatial Datasets arXiv Paper Ming Chen, Pranav Pai Jul 17