Open-Source Frontier Voice AI

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

[ACM MM 2025] TimeChat-online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Enhances Overleaf by allowing article searches and BibTeX retrieval from DBLP and Google Scholar | 通过允许从 DBLP 和 Google Scholar 进行文章搜索和获取 BibTeX 来增强 Overleaf。

[Survey] Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey

Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"

[ICLR 2025] Benchmarking Agentic Workflow Generation

Instruction Tuning with GPT-4

A curated list of awesome instruction tuning datasets, models, papers and repositories.

A comprehensive benchmark for evaluating Large Multimodal Models' capacities of visual deep semantics.

The official Meta Llama 3 GitHub site

Arena-Hard-Auto: An automatic LLM benchmark.

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

服务器 GPU 监控程序，当 GPU 属性满足预设条件时通过微信发送提示消息

Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)

📰 Must-read papers and blogs on Speculative Decoding ⚡️

[NeurlPS D&B 2024] Generative AI for Math: MathPile

SWE-bench: Can Language Models Resolve Real-world Github Issues?

A collection of useful .gitignore templates

Just a bunch of benchmark logs for different LLMs

✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

AllenAI's post-training codebase

Foundation Architecture for (M)LLMs

Code for EMNLP 2023 Findings paper: "Not All Demonstration Examples are Equally Beneficial: Reweighting Demonstration Examples for In-Context Learning"