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 51–100 of 4925 papers

TitleStatusHype
LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression ToolkitCode4
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming HeadsCode4
LLM Inference Unveiled: Survey and Roofline Model InsightsCode4
Large Language Models for Time Series: A SurveyCode4
T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on EdgeCode4
UniTok: A Unified Tokenizer for Visual Generation and UnderstandingCode4
The case for 4-bit precision: k-bit Inference Scaling LawsCode4
The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language ModelsCode4
Restructuring Vector Quantization with the Rotation TrickCode4
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion ModelsCode4
BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-DistillationCode4
BitNet a4.8: 4-bit Activations for 1-bit LLMsCode4
SNAC: Multi-Scale Neural Audio CodecCode4
Link and code: Fast indexing with graphs and compact regression codesCode4
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM ServingCode4
Taming Scalable Visual Tokenizer for Autoregressive Image GenerationCode4
BigCodec: Pushing the Limits of Low-Bitrate Neural Speech CodecCode3
HAC: Hash-grid Assisted Context for 3D Gaussian Splatting CompressionCode3
Scaling Transformers for Low-Bitrate High-Quality Speech CodingCode3
RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust AdaptationCode3
HAC++: Towards 100X Compression of 3D Gaussian SplattingCode3
Behavior Generation with Latent ActionsCode3
GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian SplattingCode3
FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-DesignCode3
Autoregressive Image Generation using Residual QuantizationCode3
FlatQuant: Flatness Matters for LLM QuantizationCode3
BiLLM: Pushing the Limit of Post-Training Quantization for LLMsCode3
A Survey on Large Language Model Acceleration based on KV Cache ManagementCode3
A Survey on Inference Optimization Techniques for Mixture of Experts ModelsCode3
Fast Matrix Multiplications for Lookup Table-Quantized LLMsCode3
Pushing the Limits of Large Language Model Quantization via the Linearity TheoremCode3
APOLLO: SGD-like Memory, AdamW-level PerformanceCode3
PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language ModelsCode3
OneBit: Towards Extremely Low-bit Large Language ModelsCode3
MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector QuantizationCode3
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion ModelsCode3
ParetoQ: Scaling Laws in Extremely Low-bit LLM QuantizationCode3
Ditto: Quantization-aware Secure Inference of Transformers upon MPCCode3
ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language ModelsCode3
MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of ExpertsCode3
DPLM-2: A Multimodal Diffusion Protein Language ModelCode3
EfficientQAT: Efficient Quantization-Aware Training for Large Language ModelsCode3
MotionGPT: Human Motion as a Foreign LanguageCode3
Data Generation for Hardware-Friendly Post-Training QuantizationCode3
LLM-QAT: Data-Free Quantization Aware Training for Large Language ModelsCode3
Language-Codec: Bridging Discrete Codec Representations and Speech Language ModelsCode3
Compact 3D Scene Representation via Self-Organizing Gaussian GridsCode3
Compact 3D Gaussian Splatting for Static and Dynamic Radiance FieldsCode3
Addressing Representation Collapse in Vector Quantized Models with One Linear LayerCode3
Latent Action Pretraining from VideosCode3
Show:102550
← PrevPage 2 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