DanielTian97 Profile Banner
Fangzheng Tian Profile
Fangzheng Tian

@DanielTian97

Followers
48
Following
295
Media
1
Statuses
35

A PhD student at University of Glasgow. Working on Information Retrieval and Natural Language Processing.

Glasgow, Scotland
Joined November 2021
Don't wanna be here? Send us removal request.
@DowntonAbbey
Downton Abbey
2 months
Cheers to 15 years of wonderful memories. Join us one last time, Downton Abbey: The Grand Finale is in theaters TODAY. 🎟️: https://t.co/8AnYwIeZET
40
158
1K
@sadjadeb
Sajad Ebrahimi
4 months
📢 Call For Papers: 1st workshop on Proactive Conversational Information Seeking with Large Language Models @cikm2025 For more info visit: https://t.co/IuPpmNNWCK 📅 When: November 14, 2025 📝 Deadline: August 31, 2025 #ProActLLM #cikm2025 #LLM #ProactiveAI #ConversationalAI
1
5
8
@iadh
Iadh Ounis
4 months
Journal article “Unifying Isolated Processes for Enhanced Multi-modal Recommendations Using a Graph Transformer” has been accepted at ACM Transactions on Recommender Systems (ToRS); Joint work with @ZixuanYI_  & part of a special issue on best papers from ACM #RecSys 2024
0
5
20
@iadh
Iadh Ounis
4 months
Want your LLMs to be safe and responsibly aligned? Time to vaccinate them! 🧬 Fascinating #ICDCS2025 keynote by Ling Liu (Georgia Tech) on reducing fine-tuning costs while boosting safety in LLM deployment.
0
6
12
@ICDCS2025
IEEE ICDCS 2025
4 months
The welcome reception at #ICDCS2025 is buzzing with energy! Fantastic to see so many smiling faces and lively conversations — a vibrant start to the conference. Here's to a great main conference ahead! 🎉
0
7
11
@iadh
Iadh Ounis
4 months
Delighted to see my former PhD student at @ir_glasgow and @GlasgowCS Jingmin Huang, now a lecturer at the University of Southampton; Jingmin served as Demo Co-Chair at #ICDCS2025. Great to catch up at the conference!
0
7
27
@debforit
Debasis Ganguly
4 months
After attending the panel at the Explainability for IR workshop, now attending my student's talk at the IR4RAG workshop. This paper is a first step towards building an adaptive multi-agent RAG pipeline. @craig_macdonald @DanielTian97
1
2
10
@andreas_chari
Andreas Chari
4 months
Now time for @ir_glasgow 's @DanielTian97 to present his impeccable QPP work "Am I on the Right Track?" at the IR-RAG Workshop #SIGIR2025 (work w/t @JinyuanF, @debforit, @mengzaiqiao and @craig_macdonald)
1
4
21
@craig_macdonald
Craig Macdonald
4 months
.@DanielTian97 is presenting our work on using QPP in agentic RAG w/ @JinyuanF @debforit @mengzaiqiao 📄 https://t.co/OkVsq7hQ0a
0
2
19
@_reachsumit
Sumit
4 months
Am I on the Right Track? What Can Predicted Query Performance Tell Us about the Search Behaviour of Agentic RAG @DanielTian97 et al. examine how query performance prediction can provide insights into the search behavior of agentic RAG systems. 📝 https://t.co/G2SncsKT4L
Tweet card summary image
arxiv.org
Agentic Retrieval-Augmented Generation (RAG) is a new paradigm where the reasoning model decides when to invoke a retriever (as a "tool") when answering a question. This paradigm, exemplified by...
0
4
21
@JackMcK1999
Jack McKechnie
5 months
Today, Florin Cuconasu @FlorinCuconasu from the Sapienza University of Rome @SapienzaRoma is giving an #IRTalk entitled "Beyond Relevance: Understanding the Distracting Effect of Retrieved Passages in RAG Systems". Details: https://t.co/oELqLtDZL4 @GlasgowCS @ir_glasgow
0
4
8
@DanielTian97
Fangzheng Tian
5 months
At 15:00 on 7th July, Florin Cuconasu from Sapienza University of Rome will give an #IRTalk entitled "Beyond Relevance: Understanding the Distracting Effect of Retrieved Passages in RAG Systems". Details: https://t.co/x3krgiA4Zs @GlasgowCS @ir_glasgow
0
1
3
@MrParryParry
Andrew Parry
5 months
❓Which retrieval library should you use for RAG? Which agent library? Where do you get datasets? We made PyTerrier RAG to stop your headaches! Led by @craig_macdonald /w (@JinyuanF , me and @mengzaiqiao )! 🧵 ⬇️
3
17
34
@MrParryParry
Andrew Parry
6 months
🚨 New Pre-Print! We show that in-context learning can steer LLM rankers to satisfy multiple objectives at once, relevance and fairness/diversity, without any parameter updates. Work done jointly with @nilanjansb from IIT Kharagpur and @debforit. 🧵 Below!
2
17
46
@MrParryParry
Andrew Parry
6 months
🚨 New Pre-Print! You've just added your 600th model to your negative mining pool and filtered all false negatives. Does any of this even matter when we can apply distillation? In this work with @debforit and @macavaney, we explore data selection in modern ranking. 🧵 Below
@_reachsumit
Sumit
6 months
Disentangling Locality and Entropy in Ranking Distillation @MrParryParry et al. separate example selection effects from teacher ranking entropy in neural ranking model optimization, showing complex hard-negative pipelines offer minimal gains. 📝 https://t.co/7dy5y2hTRj
1
10
24
@ZixuanYI_
Zixuan Yi
6 months
Today, Debasis Ganguly @debforit from the University of Glasgow is giving an #IRTalk entitled "The Role of Query Performance Prediction in Developing Adaptive Search and RAG Systems". Details: https://t.co/MOnTkHXiK8 @GlasgowCS @ir_glasgow
2
5
22
@JackMcK1999
Jack McKechnie
8 months
Finishing up #ECIR2025 for @ir_glasgow is @andreas_chari talking about his work (w/ @macavaney & @iadh) on improving low-resource retrieval with linguistic similarity transfer! A great end to the conference! @ir_glasgow @glasgowcs
0
8
21
@debforit
Debasis Ganguly
8 months
Delighted to deliver the keynote at the QPP++ workshop @ecir2025. Shared my view on the role of QPP models for Adaptive IR and RAG systems - building on our last year's SIGIR perspective https://t.co/7GRLR4ZNUj w/ @MrParryParry & Manish Chandra. Slides:
@JackMcK1999
Jack McKechnie
8 months
Back to back speakers from Glasgow in the QPP++ workshop at #ECIR2025, with lots of other interesting talks coming up. @DanielTian97 is presenting his work (w/ @craig_macdonald & @debforit) that revisits query variants for QPP. Great stuff! @ir_glasgow @glasgowcs #ECIR2025
0
3
13
@debforit
Debasis Ganguly
8 months
Happy to share some of the ongoing work of @DanielTian97 w/ @craig_macdonald as a vision for the potential of applying #qpp for adaptive #rag. For those who missed the talk, here're the slides: https://t.co/MkCriG44ly #ecir2025 @ir_glasgow
@DanielTian97
Fangzheng Tian
8 months
@debforit is giving keynote talk about QPP’s application in LLM era at the QPP++ workshop #ecir2025 @ir_glasgow
0
3
7