#
Lists (8)
Starred repositories
Implementing DeepSeek R1's GRPO algorithm from scratch
Lightweight coding agent that runs in your terminal
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
Stable Virtual Camera: Generative View Synthesis with Diffusion Models
SGLang is a fast serving framework for large language models and vision language models.
GroupMamba: Parameter-Efficient and Accurate Group Visual State Space Model [CVPR -2025]
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
Official code for MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting
a training-free approach to accelerate ViTs and VLMs by pruning redundant tokens based on similarity
UICrit is a dataset containing human-generated natural language design critiques, corresponding bounding boxes for each critique, and design quality ratings for 1,000 mobile UIs from RICO. This dat…
PyTorch code for our paper "Image Super-Resolution with Text Prompt Diffusion"
Rethinking Step-by-step Visual Reasoning in LLMs
CVPR2025 - CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution
A curated collection of resources on video saliency prediction, including papers, datasets, and tools.
2
Updated Apr 26, 2025
Toolkit for linearizing PDFs for LLM datasets/training
The official repo for paper, LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods.
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
[ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…
Witness the aha moment of VLM with less than $3.
Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.
The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many mo…
This repository is for the paper entitled: From News to Forecast: Integrating Event Analysis in LLM-based Time Series Forecasting with Reflection (NeurIPS 2024)
Janus-Series: Unified Multimodal Understanding and Generation Models
Fully open reproduction of DeepSeek-R1