{"list":"other","total":70,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"2303.00915","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","created":"2023-03-02","cited_by_count":520},{"id":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471},{"id":"2305.17118","title":"Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time","created":"2023-05-26","cited_by_count":439},{"id":"2308.13137","title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models","created":"2023-08-25","cited_by_count":424},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415},{"id":"2310.05736","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","created":"2023-10-09","cited_by_count":287},{"id":"2309.07544","title":"VerilogEval: Evaluating Large Language Models for Verilog Code Generation","created":"2023-09-14","cited_by_count":252},{"id":"1811.10959","title":"Dataset Distillation","created":"2018-11-27","cited_by_count":230},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179},{"id":"2311.00176","title":"ChipNeMo: Domain-Adapted LLMs for Chip Design","created":"2023-10-31","cited_by_count":174},{"id":"2402.14289","title":"TinyLLaVA: A Framework of Small-scale Large Multimodal Models","created":"2024-02-22","cited_by_count":164},{"id":"2308.05345","title":"RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Model","created":"2023-08-10","cited_by_count":148},{"id":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141},{"id":"2310.15141","title":"SpecTr: Fast Speculative Decoding via Optimal Transport","created":"2023-10-23","cited_by_count":129},{"id":"2310.07702","title":"ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models","created":"2023-10-11","cited_by_count":128},{"id":"2308.10204","title":"ChatEDA: A Large Language Model Powered Autonomous Agent for EDA","created":"2023-08-20","cited_by_count":122},{"id":"2306.11222","title":"LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation","created":"2023-06-20","cited_by_count":104},{"id":"2404.03663","title":"Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips","created":"2024-02-15","cited_by_count":103},{"id":"2002.10941","title":"A$^3$: Accelerating Attention Mechanisms in Neural Networks with Approximation","created":"2020-02-22","cited_by_count":101},{"id":"2402.09025","title":"SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks","created":"2024-02-14","cited_by_count":97},{"id":"2302.13939","title":"SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks","created":"2023-02-27","cited_by_count":88},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84},{"id":"2310.05424","title":"Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding","created":"2023-10-09","cited_by_count":80},{"id":"2310.03270","title":"EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models","created":"2023-10-05","cited_by_count":78},{"id":"2305.15805","title":"Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers","created":"2023-05-25","cited_by_count":67},{"id":"2501.09655","title":"A Survey of Research in Large Language Models for Electronic Design Automation","created":"2025-01-16","cited_by_count":41},{"id":"2406.00115","title":"Towards LLM-Powered Verilog RTL Assistant: Self-Verification and Self-Correction","created":"2024-05-31","cited_by_count":39},{"id":"2209.15200","title":"An efficient encoder-decoder architecture with top-down attention for speech separation","created":"2022-09-30","cited_by_count":38},{"id":"2410.04466","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","created":"2024-10-06","cited_by_count":38},{"id":"2009.08034","title":"Towards Fully 8-bit Integer Inference for the Transformer Model","created":"2020-09-17","cited_by_count":35},{"id":"2412.03220","title":"Survey of different Large Language Model Architectures: Trends, Benchmarks, and Challenges","created":"2024-12-04","cited_by_count":32},{"id":"2309.14021","title":"LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression","created":"2023-09-25","cited_by_count":26},{"id":"2405.07061","title":"LLMs and the Future of Chip Design: Unveiling Security Risks and Building Trust","created":"2024-05-11","cited_by_count":20},{"id":"2304.03986","title":"SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers","created":"2023-04-08","cited_by_count":18},{"id":"2401.09890","title":"A Survey on Hardware Accelerators for Large Language Models","created":"2024-01-18","cited_by_count":16},{"id":"2305.12086","title":"Prefix Propagation: Parameter-Efficient Tuning for Long Sequences","created":"2023-05-20","cited_by_count":15},{"id":"2309.13192","title":"Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation","created":"2023-09-22","cited_by_count":12},{"id":"2402.11322","title":"SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems","created":"2024-02-17","cited_by_count":12},{"id":"2503.13572","title":"VeriContaminated: Assessing LLM-Driven Verilog Coding for Data Contamination","created":"2025-03-17","cited_by_count":12},{"id":"2506.02089","title":"SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design","created":"2025-06-02","cited_by_count":12},{"id":"1902.10222","title":"ROMANet: Fine-Grained Reuse-Driven Off-Chip Memory Access Management and Data Organization for Deep Neural Network Accelerators","created":"2019-02-04","cited_by_count":11},{"id":"2004.10341","title":"DRMap: A Generic DRAM Data Mapping Policy for Energy-Efficient Processing of Convolutional Neural Networks","created":"2020-04-21","cited_by_count":11},{"id":"2503.13116","title":"VeriLeaky: Navigating IP Protection vs Utility in Fine-Tuning for LLM-Driven Verilog Coding","created":"2025-03-17","cited_by_count":11},{"id":"2512.00119","title":"NetDeTox: Adversarial and Efficient Evasion of Hardware-Security GNNs via RL-LLM Orchestration","created":"2025-11-27","cited_by_count":9},{"id":"2504.00948","title":"QSViT: A Methodology for Quantizing Spiking Vision Transformers","created":"2025-04-01","cited_by_count":8},{"id":"2507.13369","title":"VerilogDB: The Largest, Highest-Quality Dataset with a Preprocessing Framework for LLM-based RTL Generation","created":"2025-07-09","cited_by_count":8},{"id":"2509.11177","title":"Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs","created":"2025-09-14","cited_by_count":6},{"id":"2512.00591","title":"TrojanLoC: LLM-based Framework for RTL Trojan Localization","created":"2025-11-29","cited_by_count":6},{"id":"2310.18167","title":"MPrompt: Exploring Multi-level Prompt Tuning for Machine Reading Comprehension","created":"2023-10-27","cited_by_count":5},{"id":"2405.15842","title":"Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing","created":"2024-05-24","cited_by_count":5},{"id":"2505.22878","title":"BugWhisperer: Fine-Tuning LLMs for SoC Hardware Vulnerability Detection","created":"2025-05-28","cited_by_count":5},{"id":"2511.22749","title":"VeriDispatcher: Multi-Model Dispatching through Pre-Inference Difficulty Prediction for RTL Generation Optimization","created":"2025-11-27","cited_by_count":5},{"id":"2601.00679","title":"QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models","created":"2026-01-02","cited_by_count":3}],"next_cursor":null}