←
Avishek Anand586 posts
Avishek Anand avatar

Avishek Anand

@run4avi

Associate Professor @ TU Delft, Explainable information retrieval, efficiency and scalability in ir, Sports buff

◷ Joined November 2008▧ 44 Photos and videos
Glasgow IR Group avatar
⟳ Avishek Anand retweeted
Glasgow IR Group@ir_glasgow·28 Nov 2025

We are happy to sponsor the Keith Van Rijsbergen (KvR) Award at #ecir2026 📢 𝗡𝗼𝗺𝗶𝗻𝗮𝘁𝗶𝗼𝗻𝘀 𝗮𝗿𝗲 𝗻𝗼𝘄 𝗼𝗽𝗲𝗻! Details and Submission Form: lnkd.in/emecdsXm 🗓 𝗗𝗲𝗮𝗱𝗹𝗶𝗻𝗲: 𝟭𝟱 𝗝𝗮𝗻𝘂𝗮𝗿𝘆 𝟮𝟬𝟮𝟲 linkedin.com/posts/glasgow-i…

Sean MacAvaney avatar
⟳ Avishek Anand retweeted
Sean MacAvaney@macavaney·11 Sep 2025

Indeed, awesome to see another method leverage rerankers with document proximity to overcome first-stage recall limitations 🤓

Happy to see another research group, @haike_xu working in the same direction and our SlideGAR in the BRIGHT world. However, Reranker-Guided Search is not new. There are papers like Quam (WSDM'25), ORE (SIGIR'25), ReFIT(SIGIR'25), TOUR (ACL'23) that use the ranker's guidance.

Mandeep Rathee avatar
⟳ Avishek Anand retweeted
Mandeep Rathee@rathee_mandeep·11 Sep 2025

We have also released our survey paper, which unifies feedback-based (including Reranker) methods to improve the search, both in Retrieval and RAG tasks. - Test-time Corpus Feedback: From Retrieval to RAG arxiv.org/pdf/2508.15437

Post attachment
Mandeep Rathee avatar
⟳ Avishek Anand retweeted
Mandeep Rathee@rathee_mandeep·11 Sep 2025

Happy to see another research group, @haike_xu working in the same direction and our SlideGAR in the BRIGHT world. However, Reranker-Guided Search is not new. There are papers like Quam (WSDM'25), ORE (SIGIR'25), ReFIT(SIGIR'25), TOUR (ACL'23) that use the ranker's guidance.

Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval @haike_xu et al. propose a graph-based search method that strategically selects documents for reranking. 📝arxiv.org/abs/2509.07163 👨🏽‍💻github.com/xuhaike/Reranker-…

venktesh avatar
⟳ Avishek Anand retweeted
venktesh@vvenki22·14 Jun 2025

Can we compose skills for solving a task by principled selection of exemplars to use in In-Context Learning. We answer this question in our ICML 2025 paper with @kiranpurohit08 @run4avi @sourangshub 📜 Paper: arxiv.org/abs/2506.08607 🧑‍💻 Code: github.com/kiranpurohit/CASE (1/5)

Mandeep Rathee avatar
⟳ Avishek Anand retweeted
Mandeep Rathee@rathee_mandeep·3 Mar 2025

It was a great experience to present my work at the Glasgow IR group @ir_glasgow. This talk was based on recently accepted papers -Quam (accepted at #wsdm2025) and SlideGAR (accepted at #ecir2025) --done in collaboration with Sean MacAvaney @macavaney and Avishek Anand @run4avi

Today, Mandeep Rathee @rathee_mandeep from the L3S Research Center @l3s_luh is giving an #irtalk entitled "Beyond Bounded Recall: Adaptive Retrieval using Query Affinity Modelling and LLM based Rerankers". Details: samoa.dcs.gla.ac.uk/events/v… @GlasgowCS @ir_glasgow

Post attachmentPost attachmentPost attachment
venktesh avatar
⟳ Avishek Anand retweeted
venktesh@vvenki22·16 Feb 2025

I am also currently on academic job market. I am currently focusing on scaling retrieval and reasoning for complex knowledge intensive tasks. Please feel free to connect with me if these research goals interest you.

Asia Biega avatar
⟳ Avishek Anand retweeted
Asia Biega@asia_biega·5 Dec 2024

Sharing with permission: The daughter of one of our colleagues in the SIGIR community passed away from an epileptic seizure. If you'd like to support -- he is now organizing a donation to help provide support to epilepsy patients and their loved ones: epilepsie.digicollect.nl/maa…