{"total":43,"rows":[{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2411.17787","title":"Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient","created":"2024-11-26","cited_by_count":33,"area":null},{"id":"2405.03144","title":"PTQ4SAM: Post-Training Quantization for Segment Anything","created":"2024-05-06","cited_by_count":32,"area":null},{"id":"2506.16054","title":"PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models","created":"2025-06-19","cited_by_count":17,"area":null},{"id":"2509.21302","title":"Quantized Visual Geometry Grounded Transformer","created":"2025-09-25","cited_by_count":17,"area":null},{"id":"2403.07134","title":"COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization","created":"2024-03-11","cited_by_count":12,"area":null},{"id":"2312.09028","title":"Design Space Exploration of Low-Bit Quantized Neural Networks for Visual Place Recognition","created":"2023-12-14","cited_by_count":11,"area":null},{"id":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2506.08908","title":"SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping","created":"2025-06-10","cited_by_count":11,"area":null},{"id":"2407.09111","title":"Inference Optimization of Foundation Models on AI Accelerators","created":"2024-07-12","cited_by_count":9,"area":null},{"id":"2405.14136","title":"Efficient Multitask Dense Predictor via Binarization","created":"2024-05-23","cited_by_count":7,"area":null},{"id":"2309.13682","title":"Causal-DFQ: Causality Guided Data-free Network Quantization","created":"2023-09-24","cited_by_count":6,"area":null},{"id":"2510.25590","title":"RegionE: Adaptive Region-Aware Generation for Efficient Image Editing","created":"2025-10-29","cited_by_count":6,"area":null},{"id":"2503.04201","title":"Knowledge-Decoupled Synergetic Learning: An MLLM based Collaborative Approach to Few-shot Multimodal Dialogue Intention Recognition","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2602.05213","title":"Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Textures","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2311.07414","title":"FIRST: A Million-Entry Dataset for Text-Driven Fashion Synthesis and Design","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2502.11897","title":"DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2601.21238","title":"PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2308.06948","title":"MixBCT: Towards Self-Adapting Backward-Compatible Training","created":"2023-08-14","cited_by_count":2,"area":null},{"id":"2505.11982","title":"FedHQ: Hybrid Runtime Quantization for Federated Learning","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2512.00814","title":"IRPO: Boosting Image Restoration via Post-training GRPO","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2512.08537","title":"Fast-ARDiff: An Entropy-informed Acceleration Framework for Continuous Space Autoregressive Generation","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2403.09998","title":"FBPT: A Fully Binary Point Transformer","created":"2024-03-15","cited_by_count":1,"area":null},{"id":"2405.01775","title":"Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2405.13859","title":"Accurate Quantization for Gait Representation Learning","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2503.07825","title":"Helios 2.0: A Robust, Ultra-Low Power Gesture Recognition System Optimised for Event-Sensor based Wearables","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2510.04066","title":"QuantDemoire: Quantization with Outlier Aware for Image Demoir\\'eing","created":"2025-10-05","cited_by_count":1,"area":null},{"id":"2511.06724","title":"Argus: Quality-Aware High-Throughput Text-to-Image Inference Serving System","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2603.18423","title":"SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2606.16131","title":"Shift-and-Sum Quantization for Visual Autoregressive Models","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2608.29264","title":"EpaCache: Error-Propagation-Aware Caching for Accelerating Diffusion-Based Visual Generation","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2410.09834","title":"Towards Defining an Efficient and Expandable File Format for AI-Generated Contents","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2509.00914","title":"TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2511.03201","title":"A Quantized VAE-MLP Botnet Detection Model: A Systematic Evaluation of Quantization-Aware Training and Post-Training Quantization Strategies","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2511.17801","title":"Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2602.23996","title":"Accelerating Masked Image Generation by Learning Controlled Latent Dynamics","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.28049","title":"Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.26628","title":"Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.02584","title":"RotateAttention: RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.14149","title":"QuaSAR: Quantization Compensation via Stable Activation-Aware Rank Truncation","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.25380","title":"APT: Accelerating Diffusion Transformers via Attention Probability-Guided Pruning and Quantization","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.28974","title":"Same Bit Width, Different Outcomes: Post-Training Quantization of Text-to-Speech Across Architectures","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.09877","title":"Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training Quantization","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}