Avishek Anand retweeted
We are happy to sponsor the Keith Van Rijsbergen (KvR) Award at #ECIR2026
๐ข ๐ก๐ผ๐บ๐ถ๐ป๐ฎ๐๐ถ๐ผ๐ป๐ ๐ฎ๐ฟ๐ฒ ๐ป๐ผ๐ ๐ผ๐ฝ๐ฒ๐ป!
Details and Submission Form: lnkd.in/emecdsXm
๐ ๐๐ฒ๐ฎ๐ฑ๐น๐ถ๐ป๐ฒ: ๐ญ๐ฑ ๐๐ฎ๐ป๐๐ฎ๐ฟ๐ ๐ฎ๐ฌ๐ฎ๐ฒ
linkedin.com/posts/glasgow-iโฆ
Avishek Anand retweeted
Indeed, awesome to see another method leverage rerankers with document proximity to overcome first-stage recall limitations ๐ค
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.
Avishek Anand retweeted
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
Avishek Anand retweeted
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.
๐arxiv.org/abs/2509.07163
๐จ๐ฝโ๐ปgithub.com/xuhaike/Reranker-โฆ
Avishek Anand retweeted
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
๐ Paper: arxiv.org/abs/2506.08607
๐งโ๐ป Code: github.com/kiranpurohit/CASE
(1/5)
Avishek Anand retweeted
๐ Excited to share the preprint and code for our ICML 2025 paper.
๐ Preprint: "Sample Efficient Demonstration Selection for ICL"
๐ arxiv.org/pdf/2506.08607
๐ป Code:
๐ github.com/kiranpurohit/CASE
๐ Project Page:
๐ kiranpurohit.github.io/CASE-โฆ
@vvenki22, @sourangshub, @run4avi
Avishek Anand retweeted
Had a great time at #ECIR2025! ๐ in Lucca, Italy. I met some amazing researchers. Really enjoyed the company for my all collaborators @vvenki22 , @macavaney and @run4avi. Thanks @vinaysetty for suggesting amazing food places in the city.
ECIR 2025 was a great success. Hoping to make a memorable #ECIR2026 with the dream team of @suzan and @zhaochun_ren โฆ We will be preparing to welcoming all of us to Delft.
Excited for our Explainable IR tutorial at ECIR 2025 with @vvenky42 & Sourav Saha! Sunday morning โ๏ธ: elixir-research-group.githubโฆ #ECIR2025 ๐ก #ExplainableIR
Avishek Anand retweeted
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/vโฆ
@GlasgowCS
@ir_glasgow
Avishek Anand retweeted
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.
Avishek Anand retweeted
"ACM ICTIR, formerly known as the โACM SIGIR International Conference on the Theory of Information Retrievalโ, is renamed to ACM SIGIR International Conference on Innovative Concepts and Theories in Information Retrieval." @acm_ictir #ictir2025
ictir2025.cs.umass.edu/
Avishek Anand retweeted
Talk By Manish Gupta (Microsoft Research): Tutorial-2: Retrieval Augmented Generation
#indoml2024 @gangulyniloy @appcair @bitspilaniindia
Avishek Anand retweeted
Day 2:
Talk by Avishek Anand @run4avi (Delft University of Technology): Explainable information retrieval
#indoml2024
@gangulyniloy @appcair @bitspilaniindia
Amazing talk by @MilindTambe_AI literally saving lives.
Kudos to the organisers of #indoml24 . Great talks in day 1. Tough act to follow in day 2 ;-)
@indoml_sym
At IndoML'24 discussing use of foundation models to accelerate #AIforSocialImpact
Avishek Anand retweeted
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/maaโฆ
Wow .. thatโs amazing ๐คฉ
Great way to start #RecSys2024 : @r_ungruh paper is nominated for Best Paper! ๐๐๐ doi.org/10.1145/3640457.3688โฆ @wisdelft
Attending the Search and Relevance conference #haystack-conference today. @macavaney is speaking about rethinking reranking.
๐ Calling for demo papers for WSDM 2025 before the October 4 (AOE) deadline. Donโt miss this opportunity to showcase your work!
Submit here: cmt3.research.microsoft.com/โฆ
#WSDM2025



























