ChengHan111

MPDistil

Source code for MPDistil

HEP-LLM-play-StarCraftII

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

CD

"Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?"

low-dimensional-probing

The Low-Dimensional Linear Geometry of Contexutalized Word Representations, CoNLL 2021

representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

Causal_Reading_Group

We will keep updating the paper list about machine learning + causal theory. We also internally discuss related papers between NExT++ (NUS) and LDS (USTC) by week.

CRATE

Code for CRATE (Coding RAte reduction TransformEr).

platonic-rep

DAIR-V2X

pykan

Kolmogorov Arnold Networks

ISL-python

Solutions to labs and excercises from An Introduction to Statistical Learning, as Jupyter Notebooks.

MMBench

Official Repo of "MMBench: Is Your Multi-modal Model an All-around Player?"

vlpmarker

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

pyreft

ReFT: Representation Finetuning for Language Models

3D-Gaussian-Splatting-Papers

3D高斯论文，持续更新，欢迎交流讨论。

Awesome-LLM-Watermark

UP-TO-DATE LLM Watermark paper. 🔥🔥🔥

ViT-Anti-Oversmoothing

[ICLR 2022] "Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice" by Peihao Wang, Wenqing Zheng, Tianlong Chen, Zhangyang Wang

GFNet

[NeurIPS 2021] [T-PAMI] Global Filter Networks for Image Classification

ml-mobileclip

This repository contains the official implementation of the research paper, "MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training" CVPR 2024

civrealm

CivRealm is an interactive environment for the open-source strategy game Freeciv-web based on Freeciv, a Civilization-inspired game.

Neural-Network-Parameter-Diffusion

We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters

rcg

PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

NNDVS

The official implementation of the ICCV 2023 paper: Minimum Latency Deep Online Video Stabilization

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

U-Mamba

U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation

MISS

LLM-Shearing

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

FourierTransformer

The official Pytorch implementation of the paper "Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator" (ACL 2023 Findings)