Joemon Jose
@joemonj
Followers
606
Following
176
Media
27
Statuses
519
IR researcher and academic
Glasgow, Scotland
Joined March 2009
Big congrats to Ángela López Cardona & Sebastian Idesis on our latest IJCNN publication! We review how cognitive signals, esp. eye tracking, enhance language & image understanding in LLMs & VQA. Preprint: https://t.co/vuYYkAhus1
#AI #NLP #eyetracking #LLMs #IJCNN #TID
0
2
6
"An Instruction-Response Perspective on Large Language Models in Information Retrieval Tasks" by @hideo_joho and @joemonj (Glasgow) has been accepted at #sigir2025 as a perspective paper.
0
1
6
This is the first outcome of my sabbatical at Glasgow. Hopefully, more to follow. Thanks again to @joemonj and @ir_glasgow for their collaboration.
"An Instruction-Response Perspective on Large Language Models in Information Retrieval Tasks" by @hideo_joho and @joemonj (Glasgow) has been accepted at #sigir2025 as a perspective paper.
1
2
20
New short course: Attention in Transformers: Concepts and Code in PyTorch. Last week we released a course on how LLM transformers work. This week, go deeper and learn about the technical ideas behind the attention mechanism, and see how to code it in PyTorch. This course is
56
262
2K
📣 📣 The #sigir2025 LiveRAG Challenge is open at: https://t.co/1lgSaMoXTk Prizes: - First Prize: $5000 - Second Prize: $3000 - Third Prize: $2000 Deadlines: - Application submission deadline: February 24, 2025 More info? Ask sigir2025-liverag-gen@tii.ae.
0
16
32
I am excited to kick off this year with our first perspectives article, exploring bio-inspired AI and its groundbreaking applications in Telecommunications and Cybersecurity! https://t.co/uXdUUgdXwE
#telefonicascientificresearch #discovery #tid #ai #neuroscience
es.linkedin.com
🌿 La #IA avanza a pasos agigantados… ¡¡inspirándose en la naturaleza!! 🧠 Basada en la #neurociencia, la #InteligenciaArtificial aprende y se adapta como el cerebro humano, creando sistemas más...
0
1
4
@joemonj @alexk_z @iarapakis @XinXin_SDU @YueFeng__ @twitoogle @ron_junchen_fu Important Dates Submission Deadlines: January 1, 2025 Acceptance Notification: 13 January, 2025 Camera-ready: 2 February, 2025 EReL@MIR Workshop: 28-29 April 2025 Deadlines refer to 23:59 (11:59 pm) in the AoE (Anywhere on Earth) time zone.
0
1
2
Glad to organize the 1st EReL@MIR Workshop (Efficient Representation Learning for Multimodal IR) https://t.co/zv3Vn2rUeX at The Webconf25 (Sydney, Australia) with @joemonj @alexk_z @iarapakis @XinXin_SDU @YueFeng__ @twitoogle @ron_junchen_fu . Welcome everyone to contribute.
1
5
13
We (@ZihanWa54274484, @joemonj, HaitaoYu, Weizhi Ma,@zhaochun_ren, @xinxin) are holding the R^3AG workshop( https://t.co/GI1xH4Dmts) on SIGIR-AP2024 (December 9-12, 2024, Tokyo, Japan); The topics mainly include Reliable RAG-related research. Submission DDL: October 3, 2024
2
5
12
@ZihanWa54274484, @Solis_xurige, @XinXin_SDU, @joemonj, Haitao, Weizhi, and I will be organizing the workshop about Refined and Reliable Retrieval Augmented Generation at SIGIR-AP2024 @ACMSIGIR_AP
Check out the three exciting workshops accepted for #sigirap2024 Tokyo! Workshop date: Dec 12 (afternoon) https://t.co/W3N9Bvhu9E
0
4
11
📷 Thrilled to announce our workshop "Information Retrieval's Role in RAG Systems (IR-RAG)" has been accepted at #SIGIR2024! 📷 Can't wait to share ideas, innovations, and connect with fellow enthusiasts. #IRRAG2024 #InformationRetrieval #AIResearch
coda.io
Information Retrieval's Role in RAG Systems
1
8
52
Beyond a successful submission, it has also been an adrenaline-fueled research sprint positioned on the SoA of Reinforcement Learning-based Recommender Systems with Large Language Models, with @sasxbd, @joemonj and @alexk_z Our paper is available here:
arxiv.org
Reinforcement Learning (RL)-based recommender systems have demonstrated promising performance in meeting user expectations by learning to make accurate next-item recommendations from historical...
"Reinforcement Learning-based Recommender Systems with LLM for State Reward and Action Modeling" has been just accepted at #SIGIR2024 LLM (LE) simulates the user interactions generating state actions and rewards that are used to train the model with RL. https://t.co/xUHcyHzfCI
0
2
7
"Reinforcement Learning-based Recommender Systems with LLM for State Reward and Action Modeling" has been just accepted at #SIGIR2024 LLM (LE) simulates the user interactions generating state actions and rewards that are used to train the model with RL. https://t.co/xUHcyHzfCI
0
2
14
I really love the idea of MonsterCLEF at #clef2024! https://t.co/2MjO4ZkCst Makes so much sense but also hard to pull off! A meta-challenge organized so that task-specific LLMs run against diverse tasks without adapatation. New test data for each task, so no data leakage!
0
6
15
I am really honoured to join this amazing group of IR scholars. SIGIR has been a big part of my growth as a researcher, so a big thank you. It feels extra special to be welcomed into the SIGIR Academy with @IR_oldie; we both started working on IR around the same time in Glasgow.
It means a great deal to me to join the 2024 class of the @ACMSIGIR Academy. SIGIR is a community I have delighted to be part of for over 30 years. Sharing the honor with Donna Harman, @mounialalmas, @841io, & Yiqun Liu makes this all the more special.
9
6
72
Our paper, "IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT," has been accepted at #SIGIR2024 as a full paper!🎉🎉🎉 Thrilled to share this collaboration with @Solis_xurige , @joemonj , @alexk_z, & @iarapakis. 👏👏👏
3
4
5
Glad to share that our paper "CFIR: Fast and Effective Long-Text to Image Retrieval for Large Corpora" has been accepted at #SIGIR2024 as a full paper, a joint work with @Solis_xurige, @richardm_, and @joemonj.
1
3
22
Delighted to share that I'll be spending part of my sabbatical at the University of Glasgow until March 2025. Grateful to @joemonj for hosting me. Looking forward to meeting former colleagues and new friends.
0
1
14