SOTAVerified

Quantization

Quantization is a promising technique to reduce the computation cost of neural network training, which can replace high-cost floating-point numbers (e.g., float32) with low-cost fixed-point numbers (e.g., int8/int16).

Source: Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 701–750 of 4925 papers

TitleStatusHype
Fuzzy Norm-Explicit Product Quantization for Recommender Systems—0
SizeGS: Size-aware Compression of 3D Gaussians with Hierarchical Mixed Precision Quantization—0
Efficient Distributed Training through Gradient Compression with Sparsification and Quantization Techniques—0
Sensor Selection and Distributed Quantization for Energy Efficiency in Massive MTC—0
Error Feedback Approach for Quantization Noise Reduction of Distributed Graph Filters—0
ULMRec: User-centric Large Language Model for Sequential Recommendation—0
Temporally Compressed 3D Gaussian Splatting for Dynamic ScenesCode1
GAQAT: gradient-adaptive quantization-aware training for domain generalization—0
Trimming Down Large Spiking Vision Transformers via Heterogeneous Quantization Search—0
APOLLO: SGD-like Memory, AdamW-level PerformanceCode3
SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization—0
Quantized and Interpretable Learning Scheme for Deep Neural Networks in Classification Task—0
QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint VideosCode2
Prompting Large Language Models for Clinical Temporal Relation Extraction—0
Evaluating Single Event Upsets in Deep Neural Networks for Semantic Segmentation: an embedded system perspectiveCode0
FlashAttention on a Napkin: A Diagrammatic Approach to Deep Learning IO-Awareness—0
Unifying KV Cache Compression for Large Language Models with LeanKV—0
Mixed-Precision Quantization: Make the Best Use of Bits Where They Matter Most—0
TokenFlow: Unified Image Tokenizer for Multimodal Understanding and GenerationCode3
Designing DNNs for a trade-off between robustness and processing performance in embedded devices—0
CPTQuant -- A Novel Mixed Precision Post-Training Quantization Techniques for Large Language Models—0
Robust Precoding for Multi-User Visible Light Communications with Quantized Channel Information—0
3D representation in 512-Byte:Variational tokenizer is the key for autoregressive 3D generation—0
Lean classical-quantum hybrid neural network model for image classification—0
Scaling Image Tokenizers with Grouped Spherical QuantizationCode0
Taming Scalable Visual Tokenizer for Autoregressive Image GenerationCode4
CEGI: Measuring the trade-off between efficiency and carbon emissions for SLMs and VLMs—0
Optimizing Domain-Specific Image Retrieval: A Benchmark of FAISS and Annoy with Fine-Tuned Features—0
Memory-Efficient Training for Deep Speaker Embedding Learning in Speaker Verification—0
XQ-GAN: An Open-source Image Tokenization Framework for Autoregressive GenerationCode3
Reducing Inference Energy Consumption Using Dual Complementary CNNsCode0
Improving Detail in Pluralistic Image Inpainting with Feature DequantizationCode1
RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model AccuracyCode0
Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control—0
DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined RotationCode1
A Wave is Worth 100 Words: Investigating Cross-Domain Transferability in Time Series—0
LAMBDA: Covering the Multimodal Critical Scenarios for Automated Driving Systems by Search Space Quantization—0
Privacy-Preserving Orthogonal Aggregation for Guaranteeing Gender Fairness in Federated Recommendation—0
CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation—0
DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding—0
Scaling Transformers for Low-Bitrate High-Quality Speech CodingCode3
Quantized Delta Weight Is Safety Keeper—0
Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads—0
On the effectiveness of discrete representations in sparse mixture of experts—0
FAMES: Fast Approximate Multiplier Substitution for Mixed-Precision Quantized DNNs--Down to 2 Bits!—0
COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection—0
LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and QuantizationCode0
Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens—0
MotionLLaMA: A Unified Framework for Motion Synthesis and ComprehensionCode2
Rapid Deployment of Domain-specific Hyperspectral Image Processors with Application to Autonomous Driving—0
Show:102550
← PrevPage 15 of 99Next →
All datasetsImageNetCIFAR-10Wiki-40BAgeDB-30CFP-FPCOCO (Common Objects in Context)IJB-BIJB-CKnowledge-based:LFW

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FQ-ViT (ViT-L)Top-1 Accuracy (%)85.03—Unverified
2FQ-ViT (ViT-B)Top-1 Accuracy (%)83.31—Unverified
3FQ-ViT (Swin-B)Top-1 Accuracy (%)82.97—Unverified
4FQ-ViT (Swin-S)Top-1 Accuracy (%)82.71—Unverified
5FQ-ViT (DeiT-B)Top-1 Accuracy (%)81.2—Unverified
6FQ-ViT (Swin-T)Top-1 Accuracy (%)80.51—Unverified
7FQ-ViT (DeiT-S)Top-1 Accuracy (%)79.17—Unverified
8Xception W8A8Top-1 Accuracy (%)78.97—Unverified
9ADLIK-MO-ResNet50-W4A4Top-1 Accuracy (%)77.88—Unverified
10ADLIK-MO-ResNet50-W3A4Top-1 Accuracy (%)77.34—Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_3MAP160,327.04—Unverified
2DTQMAP0.79—Unverified
#ModelMetricClaimedVerifiedStatus
1OutEffHop-Bert_basePerplexity6.3—Unverified
2OutEffHop-Bert_basePerplexity6.21—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy98.13—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy92.92—Unverified
#ModelMetricClaimedVerifiedStatus
1SSD ResNet50 V1 FPN 640x640MAP34.3—Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-495.13—Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-496.38—Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_5All84,809,664—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy99.8—Unverified