A new RAG approach for EDA documentation groups related artifacts into functional units and trains an encoder to align queries with them, combining unit and chunk retrieval to handle scattered, tightly coupled technical…
#RAG #EDADocs #DocQA #InformationRetrieval
https://arxiv.org/abs/2610.09361
#RAG #EDADocs #DocQA #InformationRetrieval
https://arxiv.org/abs/2610.09361
October 8, 2026 at 12:01 PM
A new RAG approach for EDA documentation groups related artifacts into functional units and trains an encoder to align queries with them, combining unit and chunk retrieval to handle scattered, tightly coupled technical…
#RAG #EDADocs #DocQA #InformationRetrieval
https://arxiv.org/abs/2610.09361
#RAG #EDADocs #DocQA #InformationRetrieval
https://arxiv.org/abs/2610.09361
QwenLong-L1🔥 long-context reasoning model by Alibaba Tongyi Zhiwen team.
huggingface.co/papers/2505....
huggingface.co/Tongyi-Zhiwe...
✨ 32B & Apache 2.0
✨ Outperforms OpenAI-o3-mini & Qwen3-235B-A22B
✨ Trained on a unique 1.6K DocQA RL dataset spanning math, logic & multi-hop reasoning
huggingface.co/papers/2505....
huggingface.co/Tongyi-Zhiwe...
✨ 32B & Apache 2.0
✨ Outperforms OpenAI-o3-mini & Qwen3-235B-A22B
✨ Trained on a unique 1.6K DocQA RL dataset spanning math, logic & multi-hop reasoning
Paper page - QwenLong-L1: Towards Long-Context Large Reasoning Models with
Reinforcement Learning
Join the discussion on this paper page
huggingface.co
May 26, 2025 at 2:41 PM
QwenLong-L1🔥 long-context reasoning model by Alibaba Tongyi Zhiwen team.
huggingface.co/papers/2505....
huggingface.co/Tongyi-Zhiwe...
✨ 32B & Apache 2.0
✨ Outperforms OpenAI-o3-mini & Qwen3-235B-A22B
✨ Trained on a unique 1.6K DocQA RL dataset spanning math, logic & multi-hop reasoning
huggingface.co/papers/2505....
huggingface.co/Tongyi-Zhiwe...
✨ 32B & Apache 2.0
✨ Outperforms OpenAI-o3-mini & Qwen3-235B-A22B
✨ Trained on a unique 1.6K DocQA RL dataset spanning math, logic & multi-hop reasoning
Lokesh Mishra, Cesar Berrospi, Kasper Dinkla, Diego Antognini, Francesco Fusco, Benedikt Bothur, Maksym Lysak, Nikolaos Livathinos, Ahmed Nassar, Panagiotis Vagenas, Lucas M...
ESG Accountability Made Easy: DocQA at Your Service. (arXiv:2311.18481v1 [cs.CL])
http://arxiv.org/abs/2311.18481
ESG Accountability Made Easy: DocQA at Your Service. (arXiv:2311.18481v1 [cs.CL])
http://arxiv.org/abs/2311.18481
December 1, 2023 at 4:03 AM
Lokesh Mishra, Cesar Berrospi, Kasper Dinkla, Diego Antognini, Francesco Fusco, Benedikt Bothur, Maksym Lysak, Nikolaos Livathinos, Ahmed Nassar, Panagiotis Vagenas, Lucas M...
ESG Accountability Made Easy: DocQA at Your Service. (arXiv:2311.18481v1 [cs.CL])
http://arxiv.org/abs/2311.18481
ESG Accountability Made Easy: DocQA at Your Service. (arXiv:2311.18481v1 [cs.CL])
http://arxiv.org/abs/2311.18481
MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval
Presents a graph-based retrieval method that combines semantic and logical relevance for multi-page document understanding.
📝 arxiv.org/abs/2509.07666
👨🏽💻 github.com/WxxShirley/M...
Presents a graph-based retrieval method that combines semantic and logical relevance for multi-page document understanding.
📝 arxiv.org/abs/2509.07666
👨🏽💻 github.com/WxxShirley/M...
MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval
Document Understanding is a foundational AI capability with broad applications, and Document Question Answering (DocQA) is a key evaluation task. Traditional methods convert the document into text for...
arxiv.org
September 10, 2025 at 2:11 AM
MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval
Presents a graph-based retrieval method that combines semantic and logical relevance for multi-page document understanding.
📝 arxiv.org/abs/2509.07666
👨🏽💻 github.com/WxxShirley/M...
Presents a graph-based retrieval method that combines semantic and logical relevance for multi-page document understanding.
📝 arxiv.org/abs/2509.07666
👨🏽💻 github.com/WxxShirley/M...
MMRAG-DocQA: A Multi-Modal Retrieval-Augmented Generation Method for Document Question-Answering with Hierarchical Index and Multi-Granularity Retrieval
Combines hierarchical indexing with multi-granularity retrieval.
📝 arxiv.org/abs/2508.00579
👨🏽💻 github.com/Gzy1112/MMRA...
Combines hierarchical indexing with multi-granularity retrieval.
📝 arxiv.org/abs/2508.00579
👨🏽💻 github.com/Gzy1112/MMRA...
MMRAG-DocQA: A Multi-Modal Retrieval-Augmented Generation Method for Document Question-Answering with Hierarchical Index and Multi-Granularity Retrieval
The multi-modal long-context document question-answering task aims to locate and integrate multi-modal evidences (such as texts, tables, charts, images, and layouts) distributed across multiple pages,...
arxiv.org
August 4, 2025 at 4:04 AM
MMRAG-DocQA: A Multi-Modal Retrieval-Augmented Generation Method for Document Question-Answering with Hierarchical Index and Multi-Granularity Retrieval
Combines hierarchical indexing with multi-granularity retrieval.
📝 arxiv.org/abs/2508.00579
👨🏽💻 github.com/Gzy1112/MMRA...
Combines hierarchical indexing with multi-granularity retrieval.
📝 arxiv.org/abs/2508.00579
👨🏽💻 github.com/Gzy1112/MMRA...
Ascend-native and MIT-licenced, this tiny vision-encoder-decoder streamlines DocQA, cutting traditional OCR pipelines. But sparse documentation means its reasoning vs Qwen-VL unverified. Hard to trust for complex production reasoning without clearer benchmarks.
Tiny but Mighty: Streamlining Document Intelligence with the New Doc-QA Vision-Encoder-Decoder
aichina.news
May 22, 2026 at 5:56 PM
Ascend-native and MIT-licenced, this tiny vision-encoder-decoder streamlines DocQA, cutting traditional OCR pipelines. But sparse documentation means its reasoning vs Qwen-VL unverified. Hard to trust for complex production reasoning without clearer benchmarks.
DocQA: Japanese Document Question Answering Dataset for Generative Language Models https://cstu.io/2b9b0a #python #developer #potatosecurity
May 10, 2025 at 6:48 AM
DocQA: Japanese Document Question Answering Dataset for Generative Language Models https://cstu.io/2b9b0a #python #developer #potatosecurity
results demonstrate that RASD achieves state-of-the-art inference acceleration across tasks such as DocQA, Summary, Code, and In-Domain QA. Moreover, RASD exhibits strong scalability, seamlessly integrating with various speculative decoding [6/7 of https://arxiv.org/abs/2503.03434v1]
March 6, 2025 at 6:32 AM
results demonstrate that RASD achieves state-of-the-art inference acceleration across tasks such as DocQA, Summary, Code, and In-Domain QA. Moreover, RASD exhibits strong scalability, seamlessly integrating with various speculative decoding [6/7 of https://arxiv.org/abs/2503.03434v1]
compared to current state-of-the-art method. This work contributes to the development of more robust and comprehensive DocQA systems capable of handling the complexities of real-world documents containing rich textual and visual information. Our data [6/7 of https://arxiv.org/abs/2503.13964v1]
March 19, 2025 at 6:03 AM
compared to current state-of-the-art method. This work contributes to the development of more robust and comprehensive DocQA systems capable of handling the complexities of real-world documents containing rich textual and visual information. Our data [6/7 of https://arxiv.org/abs/2503.13964v1]
arXiv:2503.13964v1 Announce Type: new
Abstract: Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Generation (RAG) often [1/7 of https://arxiv.org/abs/2503.13964v1]
Abstract: Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Generation (RAG) often [1/7 of https://arxiv.org/abs/2503.13964v1]
March 19, 2025 at 6:03 AM
arXiv:2503.13964v1 Announce Type: new
Abstract: Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Generation (RAG) often [1/7 of https://arxiv.org/abs/2503.13964v1]
Abstract: Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Generation (RAG) often [1/7 of https://arxiv.org/abs/2503.13964v1]
Ziyu Gong, Yihua Huang, Chengcheng Mai: MMRAG-DocQA: A Multi-Modal Retrieval-Augmented Generation Method for Document Question-Answering with Hierarchical Index and Multi-Granularity Retrieval https://arxiv.org/abs/2508.00579 https://arxiv.org/pdf/2508.00579 https://arxiv.org/html/2508.00579
August 4, 2025 at 6:33 AM
Ziyu Gong, Yihua Huang, Chengcheng Mai: MMRAG-DocQA: A Multi-Modal Retrieval-Augmented Generation Method for Document Question-Answering with Hierarchical Index and Multi-Granularity Retrieval https://arxiv.org/abs/2508.00579 https://arxiv.org/pdf/2508.00579 https://arxiv.org/html/2508.00579