Update README.md

README.md

@@ -111,6 +111,10 @@ Amir Gholami\* , Sehoon Kim\* , Zhen Dong\* , Zhewei Yao\* , Michael W. Mahoney,
 ### 2023
 
 - [[ICML](https://arxiv.org/pdf/2301.11233.pdf)] BiBench: Benchmarking and Analyzing Network Binarization [**`bnn`**] [[code](https://github.com/htqin/BiBench)]
+- [[ICML](https://arxiv.org/abs/2306.00317)] FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization [[code](https://openreview.net/attachment?id=-tYCaP0phY_&name=supplementary_material)]
+- [[ICML](https://arxiv.org/abs/2301.12017)] Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases [[code](https://github.com/microsoft/DeepSpeed)]
+- [[ICML](https://icml.cc/virtual/2023/28295)] GPT-Zip: Deep Compression of Finetuned Large Language Models
+- [[ICML](https://arxiv.org/abs/2307.03738)] QIGen: Generating Efficient Kernels for Quantized Inference on Large Language Models [[code](https://github.com/IST-DASLab/QIGen)]
 - [[TPAMI](https://ieeexplore.ieee.org/abstract/document/9735379)] Optimization-Based Post-Training Quantization With Bit-Split and Stitching
 - [[TPAMI](https://ieeexplore.ieee.org/abstract/document/10122994)] Single-path Bit Sharing for Automatic Loss-aware Model Compression
 - [[ICCV](https://openaccess.thecvf.com/content/ICCV2023/papers/Shang_Causal-DFQ_Causality_Guided_Data-Free_Network_Quantization_ICCV_2023_paper.pdf)] Causal-DFQ: Causality Guided Data-free Network Quantization [[code](https://github.com/42Shawn/Causal-DFQ)]
@@ -131,7 +135,10 @@ Amir Gholami\* , Sehoon Kim\* , Zhen Dong\* , Zhewei Yao\* , Michael W. Mahoney,
 - [[CVPR](https://arxiv.org/abs/2212.04780)] GENIE: Show Me the Data for Quantization
 - [[CVPR](https://arxiv.org/abs/2303.06424)] Regularized Vector Quantization for Tokenized Image Synthesis
 - [[ICLR](https://arxiv.org/abs/2210.17323)] GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers [[code](https://github.com/IST-DASLab/gptq)] [721⭐]
+- [[ACL](https://arxiv.org/abs/2306.00014)] PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models
+- [[ACL](https://aclanthology.org/2023.findings-acl.15/)] Boost Transformer-based Language Models with GPU-Friendly Sparsity and Quantization
 - [[EMNLP](https://arxiv.org/abs/2310.05079)] Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?
+- [[EMNLP](https://arxiv.org/abs/2310.13315)] Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models
 - [[TNNLS](https://ieeexplore.ieee.org/document/10049753/)] BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance. [__`bnn`__] [[code](https://github.com/htqin/BiFSMNv2)]
 - [[TNNLS](https://ieeexplore.ieee.org/abstract/document/10227741)] Quantization via Distillation and Contrastive Learning.
 - [[HPCA](https://ieeexplore.ieee.org/document/9773213/)] Enabling High-Quality Uncertainty Quantification in a PIM Designed for Bayesian Neural Network
@@ -153,30 +160,51 @@ Amir Gholami\* , Sehoon Kim\* , Zhen Dong\* , Zhewei Yao\* , Michael W. Mahoney,
 - [[arxiv](https://arxiv.org/abs/2303.12270)] EBSR: Enhanced Binary Neural Network for Image Super-Resolution. [__`bnn`__]
 - [[arxiv](https://arxiv.org/abs/2303.15493)] Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis. [__`bnn`__]
 - [[arxiv](https://arxiv.org/pdf/2304.09145.pdf)] Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling.
+- [[arxiv](https://arxiv.org/abs/2304.09785)] Improving Post-Training Quantization on Object Detection with Task Loss-Guided Lp Metric. [__`ptq`__]
+- [[arxiv](https://arxiv.org/abs/2305.12356)] Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models. 
 - [[arxiv](https://arxiv.org/abs/2206.09557)] LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
-- [[arxiv](https://arxiv.org/abs/2306.00978)] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration [[code](https://github.com/mit-han-lab/llm-awq)]
 - [[arxiv](https://arxiv.org/abs/2306.03078)] SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression [[code](https://github.com/Vahe1994/SpQR)]
 - [[arxiv](https://arxiv.org/abs/2305.14314)] QLORA: Efficient Finetuning of Quantized LLMs [[code](https://github.com/artidoro/qlora)]
+- [[arxiv](https://arxiv.org/abs/2302.02390)] Quantized Distributed Training of Large Models with Convergence Guarantees
 - [[arxiv](https://arxiv.org/abs/2305.17888)] LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
+- [[arxiv](https://arxiv.org/abs/2306.00978)] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration [[code](https://github.com/mit-han-lab/llm-awq)]
+- [[arxiv](https://arxiv.org/abs/2306.11987)] Training Transformers with 4-bit Integers [[code](https://github.com/xijiu9/Train_Transformers_with_INT4)]
 - [[arxiv](https://arxiv.org/abs/2305.11186)] Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt
 - [[arxiv](https://arxiv.org/abs/2305.10657)] PTQD: Accurate Post-Training Quantization for Diffusion Models
 - [[arxiv](https://arxiv.org/abs/2305.18723)] Towards Accurate Data-free Quantization for Diffusion Models
 - [[arxiv](https://arxiv.org/abs/2306.02316)] Temporal Dynamic Quantization for Diffusion Models
-- [[arxiv](https://arxiv.org/abs/2308.10187)] Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks [[code](https://github.com/Arktis2022/Spiking-Diffusion)] [__`snn`__] 
+- [[arxiv](https://arxiv.org/abs/2306.08162)] INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation
+- [[arxiv](https://arxiv.org/abs/2307.03712)] INT-FP-QSim: Mixed Precision and Formats For Large Language Models and Vision Transformers [[code](https://github.com/lightmatter-ai/INT-FP-QSim)]
 - [[arxiv](https://arxiv.org/abs/2306.07629)] SqueezeLLM: Dense-and-Sparse Quantization [[code](https://github.com/SqueezeAILab/SqueezeLLM)]
 - [[arxiv](https://arxiv.org/abs/2306.12929)] Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing
 - [[arxiv](https://arxiv.org/abs/2306.13515)] Binary domain generalization for sparsifying binary neural networks. [__`bnn`__]
-- [[arxiv](https://arxiv.org/abs/2307.09782)] ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats. 
-- [[arxiv](https://arxiv.org/abs/2305.12356)] Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models. 
+- [[arxiv](https://arxiv.org/abs/2307.09782)] ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats.
 - [[arxiv](https://arxiv.org/abs/2304.01089)] RPTQ: Reorder-based Post-training Quantization for Large Language Models. [[code](https://github.com/hahnyuan/RPTQ4LLM)]
 - [[arxiv](https://arxiv.org/abs/2306.02272)] OWQ: Lessons learned from activation outliers for weight quantization in large language models. 
 - [[arxiv](https://arxiv.org/abs/2305.14152)] Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization. 
 - [[arxiv](https://arxiv.org/abs/2307.13304)] QuIP: 2-Bit Quantization of Large Language Models With Guarantees. [[code](https://github.com/jerry-chee/QuIP)]
+- [[arxiv](https://arxiv.org/abs/2308.05600)] NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search
+- [[arxiv](https://arxiv.org/abs/2308.06744)] Token-Scaled Logit Distillation for Ternary Weight Generative Language Models
+- [[arxiv](https://arxiv.org/abs/2308.07662)] Gradient-Based Post-Training Quantization: Challenging the Status Quo
+- [[arxiv](https://arxiv.org/abs/2308.09723)] FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs
 - [[arxiv](https://arxiv.org/abs/2308.13137)] OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models. [[code](https://github.com/OpenGVLab/OmniQuant)]
+- [[arxiv](https://arxiv.org/abs/2308.14903)] MEMORY-VQ: Compression for Tractable Internet-Scale Memory
+- [[arxiv](https://arxiv.org/abs/2308.15987)] FPTQ: Fine-grained Post-Training Quantization for Large Language Models
+- [[arxiv](https://arxiv.org/abs/2309.00964)] eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models
+- [[arxiv](https://arxiv.org/abs/2309.01885)] QuantEase: Optimization-based Quantization for Language Models - An Efficient and Intuitive Algorithm
+- [[arxiv](https://arxiv.org/abs/2309.02784)] Norm Tweaking: High-performance Low-bit Quantization of Large Language Models
+- [[arxiv](https://arxiv.org/abs/2309.05210)] Understanding the Impact of Post-Training Quantization on Large Language Models
 - [[arxiv](https://arxiv.org/abs/2309.05516)] Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs. [[code](https://github.com/intel/neural-compressor)]
 - [[arxiv](https://arxiv.org/abs/2310.00034)] PB-LLM: Partially Binarized Large Language Models. [[code](https://github.com/hahnyuan/PB-LLM)]
-- [[arxiv](https://arxiv.org/abs/2304.09785)] Improving Post-Training Quantization on Object Detection with Task Loss-Guided Lp Metric. [__`ptq`__]
+- [[arxiv](https://arxiv.org/abs/2308.10187)] Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks [[code](https://github.com/Arktis2022/Spiking-Diffusion)] [__`snn`__] 
 - [[arxiv](https://arxiv.org/abs/2309.01885)] QuantEase: Optimization-based Quantization for Language Models - An Efficient and Intuitive Algorithm
+- [[arxiv](https://arxiv.org/abs/2309.14592)] Efficient Post-training Quantization with FP8 Formats [[code](https://github.com/intel/neural-compressor)]
+- [[arxiv](https://arxiv.org/abs/2309.14717)] QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models [[code](https://github.com/yuhuixu1993/qa-lora)]
+- [[arxiv](https://arxiv.org/abs/2309.15531)] Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models
+- [[arxiv](https://arxiv.org/abs/2309.16119)] ModuLoRA: Finetuning 3-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
+- [[arxiv](https://arxiv.org/abs/2310.07147)] QFT: Quantized Full-parameter Tuning of LLMs with Affordable Resources
+- [[arxiv](https://arxiv.org/abs/2310.08041)] QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
+- [[arxiv](https://arxiv.org/abs/2310.08659)] LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models [[code](https://github.com/yxli2123/LoftQ)]
 - [[arxiv](https://arxiv.org/abs/2310.10944)] TEQ: Trainable Equivalent Transformation for Quantization of LLMs [[code](https://github.com/intel/neural-compressor)]
 - [[arxiv](https://arxiv.org/abs/2310.11453)] BitNet: Scaling 1-bit Transformers for Large Language Models [[code](https://github.com/kyegomez/BitNet)]
 
@@ -625,7 +653,7 @@ Our team is part of the DIG group of the State Key Laboratory of Software Develo
 
 **Xingyu Zheng**
 
-- Xingyu Zheng is a junior student at Beihang University. After participating in model distillation and model stealing, he is currently devoted to the quantization of large language models. He hopes to gain a deeper understanding of models, and in turn make them more robust and generalizable.
+- Xingyu Zheng is a senior student at Beihang University, supervised by Prof. [Xianglong Liu](https://xlliu-beihang.github.io/). After participating in adversarial learning, he is currently devoted to the quantization of pretrained large models. He hopes to gain a deeper understanding of models, and in turn make them more efficient and robust.
 
 ### Alumnus