ReNeuIR'26
Workshop on Reaching Efficiency in Neural Information Retrieval
Tentative Workshop Program
ReNeuIR is colocated with SIGIR 2026 in Melbourne, Australia and takes place on July 24, 2026. All times in the table below are according to the local time zone.
| Time | Agenda |
|---|---|
| 09:00 - 09:15 | Welcome and Introduction |
| 09:15 - 10:00 | Keynote by Harry Scells |
| 10:00 - 10:30 | Invited Talks I |
| 10:30 - 11:00 | Coffee Break |
| 11:00 - 12:30 | Paper Presentations I |
| 12:30 - 14:00 | Lunch Break + Posters |
| 14:00 - 15:00 | Invited Talks II |
| 15:00 - 15:30 | Coffee Break |
| 15:30 - 17:15 | Paper Presentations II |
Detailed Schedule for the Invited Talks I Session (10:00 - 10:30)
We will have two invited talks:
- Silvio Martinico, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini. Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing. (10 minutes + 5 minutes QA)
- Arne Eichholtz, Yongkang Li, Jutte Vijverberg, Tobias Groot, Mohammad Aliannejadi: Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrieval. (10 minutes + 5 minutes QA)
Detailed Schedule for the Paper Presentations I Session (11:00 - 12:30)
We have three paper presentations and two invited talks:
- Harsh Peswani, Narendra Babu Unnam, Dhruv Garg and Poojan Vachharajani. Mind the Gap: A Cheap Pre-Reranker that Predicts the Second Hop. (15 minutes + 5 minutes QA)
- Rahul Seetharaman, Aman Bansal, Hamed Zamani and Kaustubh Dhole. Scaling Laws for Cross-Encoder Reranking. (15 minutes + 5 minutes QA)
- Anirudh Lakhotia and Nischal Helagally Shantharaju. Most MaxSim Winners Flip. Retrieval Survives: Low-Margin Substitution in Sign-Coded Late Interaction. (15 minutes + 5 minutes QA)
- Parker Carlson, Wentai Xie, Rohil Devang Shah, Tao Yang. Efficient Sparse Retrieval with Lightweight Superblock Pruning. (10 minutes + 5 minutes QA)
- Yash Kankanampati, Yuxuan Zong, Nadi Tomeh, Benjamin Piwowarski, Joseph Le Roux: A Voronoi Cell Formulation for Principled Token Pruning in Late-Interaction Retrieval Models. (10 minutes + 5 minutes QA)
Lunch Break + Posters (12:30 - 14:00)
- Silvio Martinico, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini. Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing.
- Thong Nguyen, Cosimo Rulli, Franco Maria Nardini, Rossano Venturini, Andrew Yates. Sparton: Fast and Memory-Efficient Triton Kernel for Learned Sparse Retrieval.
- Tuan-Luc Huynh. Efficient Continual Adaptation of Generative Retrieval Systems over Dynamic Corpora.
- Jingfen Qiao, Gabrielle Poerwawinata, Thong Nguyen, Jia-Huei Ju, Eugene Yang, Evangelos Kanoulas, Andrew Yates. Better than Dense? Investigating the Natural Backward Compatibility of Learned Sparse Representations
- Maik Fröbe. Efficiency-Oriented Shared Task.
Detailed Schedule for the Invited Talks II Session (14:00 - 15:00)
We will have three invited talks:
- Patrick Iff, Paul Brügger, Marcin Chrapek, David Kochergin, Maciej Besta, Torsten Hoefler. Benchmarking Filtered Approximate Nearest Neighbor Search Algorithms on Transformer-based Embedding Vectors. (10 minutes + 5 minutes QA)
- Katelyn Harlan, Andrew Trotman, Veronica Liesaputra. On Accumulator Management. (10 minutes + 5 minutes QA)
- Leonardo Kuffo, Ioanna Tsakalidou, Roberta De Viti, Albert Angel, Jiří Iša, Rastislav Lenhardt. Semantic Recall for Vector Search. (10 minutes + 5 minutes QA)
- Charlie Yang. Key Findings on Learned Sparse Retrieval Effectiveness and Efficiency. (10 minutes + 5 minutes QA)
Detailed Schedule for the Paper Presentations II Session (15:30 - 17:15)
We have five paper presentations:
- Boris Malashenko, Ivan Jarsky, Egor Soldatov, Vladislav Luzhnov, Sviatoslav Stumpf, Vladislav Shmatkov, Viacheslav Shalamov, Andrey Stankevich, and Valeria Efimova. StaRSE: Compact Russian Sentence Embeddings with a Sign-Coded Static Encoder. (15 minutes + 5 minutes QA)
- Florian Hönicke, Michael Günther, Andreas Koukounas, Mohammad Kalim Akram, Scott Martens, Saba Sturua, and Han Xiao. jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers. (15 minutes + 5 minutes QA)
- Irene Anu and Craig Macdonald. Trie-based Experiment Plans for Efficient IR Pipeline Experiments. (15 minutes + 5 minutes QA)
- Yibo Yan, Guangwei Xu, Xin Zou, Shuliang Liu, Mingdong Ou, James Kwok, and Xuming Hu. DocSculptor: Near-Lossless Compression of Multi-Vector Visual Document Retrieval via Adaptive Pruning. (15 minutes + 5 minutes QA)
- Gautham Krithiwas, Revanth Sreeram Ambati, and Joshita Gautam. Exploring Lightweight Query Encoders for Fixed Sparse Document Indexes. (15 minutes + 5 minutes QA)