A computer-science researcher, interested in fields like Information Retrieval, Natural Language Understanding ...
Tsukuba-shi, Ibaraki
Joined December 2010
- Tweets619
- Following423
- Followers218
- Likes2.2K
耕深 retweeted
㊗️IRグループ発足以来初の卒業生・修了生。みなさん、ご卒業、修了おめでとうございます！今後のご活躍を心よりお祈りしています。A big congratulations to all IR Group members who graduated this March! Wishing each of you continued growth, success, and meaningful adventures ahead.🎉
耕深 retweeted
IR Group at University of Tsukuba will have four research paper presentations and two workshop presentations at #sigirap2025
耕深 retweeted
We’ve launched a new IR group at Tsukuba, continuing our HCIR research journey that started in 2020! Stay tuned for our upcoming activities.
耕深 retweeted
Following my visit to @knmnyn, our review of Sakana's #AIScientist caught the attention of @Nature, where we shared why AI novelty checks risk repeating flaws we saw years ago in Google Scholar’s ranking.
isg.beel.org/blog/2025/08/25… #plagiarism #GoogleScholar #AIScience
耕深 retweeted
Join us at SIGIR-AP for two exciting workshops: R3AG 2025: The Second Workshop on Refined and Reliable Retrieval-Augmented Generation, and BREV-RAG: Beyond Relevance-based EValuation of RAG systems. Submit your work by September 30! Learn more at sigir-ap.org/sigir-ap-2025/w….
耕深 retweeted
🚀 Launched! ✨@wing_nus's✨ open RAG course is mentoring 30+ on their Retrieval Augmented Generation journey.
🎥 First 2 sessions on YT (w slides):
👉 Intro: buff.ly/7iSQJP2
👉 RAG Overview: buff.ly/gF51ppe
Join us—or share w/ anyone curious about RAG!
#RAG #NLP
耕深 retweeted
Call for Papers: BREV-RAG at #sigirap2025 (Dec 10, Xi'an, China)
sakailab.com/brev-rag/
Let's talk about RAG evaluation axes other than relevance, correctness, and groundedness!
耕深 retweeted
📢Not sure about Retrieval Augmented Generation (RAG)🤔? Then join @wing_nus for our open-to-all, free public lab rotation course Aug–Nov '25. Offered live to UTC+8, then u/l to YT ▶️. 👀 our past LLM course ("Past Semesters")
👉 wing-nus.github.io/cs6101
@tag ppl who should join!
耕深 retweeted
We (@ZihanWa54274484, @joemonj, HaitaoYu, Weizhi Ma,@zhaochun_ren, @xinxin) are holding the R^3AG workshop(r3ag-sigir-ap.github.io/) on SIGIR-AP2024 (December 9-12, 2024, Tokyo, Japan);
The topics mainly include Reliable RAG-related research.
Submission DDL: October 3, 2024
耕深 retweeted
#sigirap2024 call for papers,
featuring the SIGIR Revise-and-Resubmit paper type, is available now!
sigir-ap.org/sigir-ap-2024/c…
耕深 retweeted
A history of LLMs derived from LLaMA.
agi-sphere.com/llama-models/
耕深 retweeted
I'm surprised how many people aren't using AI Chrome extensions yet.
Stop limiting yourself to just ChatGPT.
Here are 5 new AI chrome extensions that will turn you into a productivity machine:
耕深 retweeted
A survey of LLMs with a practical guide and evolutionary tree.
Number of LLMs from Meta = 7
Number of open source LLMs from Meta = 7
The architecture nomenclature for LLMs is somewhat confusing and unfortunate.
What's called "encoder only" actually has an encoder and a decoder (just not an auto-regressive decoder).
What's called "encoder-decoder" really means "encoder with auto-regressive decoder"
What's called "decoder only" really means "auto-regressive encoder-decoder"
github.com/Mooler0410/LLMsPr…
耕深 retweeted
Spacerini: Plug-and-play Search Engines with Pyserini and Hugging Face
abs: arxiv.org/abs/2302.14534
耕深 retweeted
SIGIR-AP (Asia-Pacific) 2023 call for papers.
Abstracts due June 26. Papers due July 3.
2-9 pages + references.
Regular submissions AND *SIGIR REVISE-AND-RESUBMIT submissions*!
#sigirap2023
sigir-ap.org/sigir-ap-2023/c…
耕深 retweeted
For those who are excited about the integration of search engines with conversational AI, here is a 2019 Dagstuhl report on conversation search discussed by the experts in IR, NLP, Dialogue Systems, and HCI. dagstuhl.de/19461
耕深 retweeted
I’m excited to present our work on zero-shot ranking in this blog post.
We present a unique hybrid ranking method that outperforms other evaluated methods on 12 of 13 evaluated BEIR datasets. 🧵 blog.vespa.ai/improving-zero…
耕深 retweeted
ウェブ検索研究のポスドク（Naverと雇用契約、常勤、二年、更新余地あり）を募集します。締切12/23。年収700万、初年度はプラス50万（但し書きあり）。ご検討ください。
waseda.box.com/naver-postoc2…