mathematicallfs
Follow
Stars
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25).
A MAD laboratory to improve AI architecture designs 🧪
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
Some preliminary explorations of Mamba's context scaling.
official code for paper Probing the Decision Boundaries of In-context Learning in Large Language Models. https://arxiv.org/abs/2406.11233 [NeurIPS 2024]
GPT-2 (124M) quality in 5B tokens
Offical implementation of IJCAI 2024 paper "Cross-Domain Feature Augmentation for Domain Generalization"
[NeurIPS 2024] Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models
Collection of papers on state-space models
Understand and test language model architectures on synthetic tasks.
A simple and efficient Mamba implementation in pure PyTorch and MLX.
FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
Codes for "MixupE: Understanding and Improving Mixup from Directional Derivative Perspective" UAI 2023 Oral
[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
Official code for ''From Optimization Dynamics to Generalization Bounds via Łojasiewicz Gradient Inequality'' (TMLR)
Official code for "In Search of Robust Measures of Generalization" (NeurIPS 2020)
A visual no-code/code-free web crawler/spider易采集：一个可视化浏览器自动化测试/数据采集/爬虫软件，可以无代码图形化的设计和执行爬虫任务。别名：ServiceWrapper面向Web应用的智能化服务封装系统。
可视化Bilibili本地视频XML弹幕转换ASS字幕转换器
A library for users to write (experiment in research) configurations in Python Dict or JSON format, read and write parameter value via dot . in code, while can read parameters from the command line…
Training-free data valuation on deep neural network applications. (ICML-2022)
RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]