{"total":16,"rows":[{"id":"2501.14794","title":"Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference","created":"2025-01-11","cited_by_count":22,"area":null},{"id":"2509.20241","title":"Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling","created":"2025-09-24","cited_by_count":13,"area":null},{"id":"2605.19537","title":"The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility","created":"2026-05-19","cited_by_count":8,"area":null},{"id":"2511.15699","title":"Joint Semantic-Channel Coding and Modulation for Token Communications","created":"2025-11-19","cited_by_count":7,"area":null},{"id":"2411.17847","title":"SoftmAP: Software-Hardware Co-design for Integer-Only Softmax on Associative Processors","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2504.07878","title":"Token Level Routing Inference System for Edge Devices","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2601.06118","title":"Beyond Reproducibility: Token Probabilities Expose Large Language Model Nondeterminism","created":"2026-01-03","cited_by_count":4,"area":null},{"id":"2503.12211","title":"Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs","created":"2025-03-15","cited_by_count":2,"area":null},{"id":"2505.11417","title":"EdgeWisePersona: A Dataset for On-Device User Profiling from Natural Language Interactions","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2503.12988","title":"ROMA: a Read-Only-Memory-based Accelerator for QLoRA-based On-Device LLM","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2602.20662","title":"TOM: A Ternary Read-only Memory Accelerator for LLM-powered Edge Intelligence","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2507.00016","title":"Gradient-based Fine-Tuning through Pre-trained Model Regularization","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2602.14462","title":"Silent Inconsistency in Data-Parallel Full Fine-Tuning: Diagnosing Worker-Level Optimization Misalignment","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.08749","title":"A Little Rank Goes a Long Way: Random Scaffolds with LoRA Adapters Are All You Need","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.21952","title":"Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation Models","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2607.01313","title":"Black-Box Inference of LLM Architectural Properties with Restrictive API Access","created":"2026-07-01","cited_by_count":0,"area":null}],"next_cursor":null}