jiakai's picture

168 731

jiakai

real-jiakai

·

https://blog.gujiakai.top

AI & ML interests

LLM && Smart QA

Recent Activity

liked a model about 8 hours ago

ASLP-lab/DiffRhythm-base

liked a model about 8 hours ago

alibaba-pai/Wan2.1-Fun-1.3B-Control

reacted to tonywu71's post with 🔥 about 12 hours ago

ColPali: A new approach to efficient and intelligent document retrieval 🚀 Our latest research paper, "ColPali: Efficient Document Retrieval with Vision Language Models," introduces a groundbreaking approach to large-scale visual document analysis. By leveraging Vision Language Models (VLMs), we have created a new framework for document retrieval that's both powerful and efficient. Key Insights: 💡 ColPali combines ColBERT's multi-vector strategy with VLMs' document understanding capabilities ⚙️ ColPali is based on PaliGemma-3B (SigLIP, Gemma-2B) + a linear projection layer and is trained to maximize the similarity between the document and the query embeddings 📊 The Vision Document Retrieval benchmark (ViDoRe) is a challenging dataset that spans various industry topics and aims at matching real-life retrieval scenarios 🏆 ColPali outperforms existing models on all datasets in ViDoRe (average NDCG@5 of 81.3% vs 67.0% for the best baseline model) ⚡ ColPali is faster at document embedding compared to traditional PDF parser pipelines, making ColPali viable for industrial use 🔍 ColPali is highly interpretable thanks to patch-based similarity maps Dive deeper into ColPali and explore our resources: 📑 Full paper: arxiv.org/abs/2407.01449 🛠️ Datasets, model weights, evaluation code, leaderboard, demos: huggingface.co/vidore Shoutout to my amazing co-authors Manuel Faysse (@manu) and Hugues Sibille (@HugSib). We are grateful for the invaluable feedback from Bilel Omrani, Gautier Viaud, Celine Hudelot, and Pierre Colombo. This work is sponsored by ILLUIN Technology. ✨

View all activity

Organizations

real-jiakai's activity

upvoted an article about 12 hours ago

Article

PaliGemma – Google's Cutting-Edge Open Vision Language Model

May 14, 2024

• 244

upvoted a paper about 20 hours ago

Long-Context Autoregressive Video Modeling with Next-Frame Prediction

Paper • 2503.19325 • Published 3 days ago • 66

upvoted a collection about 22 hours ago

Qwen2.5-Omni

End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 3 items • Updated about 15 hours ago • 61

upvoted a collection 1 day ago

TxGemma Release

Collection of open models to accelerate the development of therapeutics. • 5 items • Updated about 11 hours ago • 23

upvoted a paper 2 days ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published 3 days ago • 103

upvoted a paper 3 days ago

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published Feb 19 • 173

upvoted a collection 4 days ago

Open-RS

Model weights & datasets in the paper "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn’t" • 8 items • Updated 7 days ago • 11

upvoted an article 5 days ago

Article

The New and Fresh analytics in Inference Endpoints

7 days ago

• 17

upvoted 2 papers 5 days ago

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Paper • 2503.16419 • Published 7 days ago • 61

Survey on Evaluation of LLM-based Agents

Paper • 2503.16416 • Published 7 days ago • 75

upvoted a collection 7 days ago

👩‍💻 OlympicCoder

Reasoning datasets and models for competitive coding • 4 items • Updated 16 days ago • 15

upvoted 2 articles 7 days ago

Article

Open R1: How to use OlympicCoder locally for coding?

8 days ago

• 50

Article

AI Policy: 🤗 Response to the White House AI Action Plan RFI

9 days ago

• 21

upvoted a collection 7 days ago

Physical AI

Collection of commercial-grade datasets for physical AI developers • 10 items • Updated 1 day ago • 27

upvoted an article 7 days ago

Article

NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets

10 days ago

• 29

upvoted a paper 7 days ago

DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Paper • 2503.14476 • Published 9 days ago • 107

upvoted a collection 7 days ago

ColPali Models

Pre-trained checkpoints for the ColPali model. • 8 items • Updated Jan 23 • 5

upvoted a collection 8 days ago

Llama Nemotron

Open, Production-ready Enterprise Models • 3 items • Updated 1 day ago • 25