A full-screen timer for presenters

[ACL 2026] Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization

[CVPR2026 Highlight] Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation

Learning Deep Kernels for Non-Parametric Independence Testing

Tool box for Data Adaptive Hypothesis Testing

MMDAgg package implementing the MMDAgg test proposed in MMD Aggregated Two-Sample Test by Schrab, Kim, Albert, Laurent, Guedj and Gretton: https://arxiv.org/abs/2110.15073

Expertise modeling for the OpenReview matching system

[NeurIPS 2024 Oral] "Bayesian-Guided Label Mapping for Visual Reprogramming"

[NeurIPS 2024] "Bayesian-Guided Label Mapping for Visual Reprogramming". Official Website: https://github.com/tmlr-group/BayesianLM

COALA: A Practical and Vision-Centric Federated Learning Platform, accepted to ICML'24

[ICML 2024] "Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models"

MMD-FUSE package implementing the MMD-FUSE test proposed in MMD-FUSE: Learning and Combining Kernels for Two-Sample Testing Without Data Splitting by Biggs, Schrab, and Gretton: https://arxiv.org/a…

Inference code for Llama models

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

A list of totally open alternatives to ChatGPT

中文版的ai地牢，直接使用的openai的ChatGPT api作为讲故事的模型。

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature

This repo contains source code and datasets used in code for Deep transfer learning enables lesion tracing of circulating tumor cells(CTC-Tracer), published in Nature Communications (2022).

Source code for ICLR 2022 paper "Meta Discovery: Learning to Discover Novel Classes given Very Limited Data".

This is the source code for Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack (ICML2022).

Adversarial Attacks and Defense for Non-Parametric Two-Sample Tests (ICML 2022)

[KDD 2022] "Bilateral Dependency Optimization: Defending Against Model-inversion Attacks"

Code for paper "Hidden in Plain Sight: Subgroup Shifts Escape OOD Detection"

Code for reproducing results in the sliced score matching paper (UAI 2019)