Brainstorm

Brainstorm is the group’s reading session, which focuses on developing a wholesome knowledge about various topics in which research is being conducted at Precog. It provides an opportunity for focused discussions and exploring current state of the art. We believe these sessions help in developing scientific approach to problem articulation, sound research practices, and fact-based learning through accepted publications and case studies. The current reading group is comprised of vivacious graduate and undergraduate students at IIIT-H, with common interest in improving and contributing towards above mentioned areas of work. Please join the mailing list to get meet details, & reminders.

  • When: 2030-2130 hrs IST, Tuesdays

    07 January 2025

    Toy Models of Superposition

    by Nelson Elhage, Tristan Hume, Catherine Olsson, Nicholas Schiefer, Tom Henighan, Shauna Kravec, Zac Hatfield-Dodds, Robert Lasenby, Dawn Drain, Carol Chen, Roger Grosse, Sam McCandlish, Jared Kaplan, Dario Amodei, Martin Wattenberg,Christopher Olah

    Presenter: Vaishnavi Shivkumar

    Paper
    15 January 2025

    Large Concept Models: Language Modeling in a Sentence Representation Space

    by LCM team, Loïc Barrault, Paul-Ambroise Duquenne, Maha Elbayad, Artyom Kozhevnikov, Belen Alastruey, Pierre Andrews, Mariano Coria, Guillaume Couairon, Marta R. Costa-jussà, David Dale, Hady Elsahar, Kevin Heffernan, João Maria Janeiro, Tuan Tran, Christophe Ropers, Eduardo Sánchez, Robin San Roman, Alexandre Mourachko, Safiyyah Saleem, Holger Schwenk

    Presenter: Varshita Kolipaka

    Paper
    21 January 2025

    GraphAny: A Foundation Model for Node Classification on Any Graph

    by Jianan Zhao, Hesham Mostafa, Mikhail Galkin, Michael Bronstein, Zhaocheng Zhu, Jian Tang

    Presenter: Akshit Sinha

    Paper
    28 January 2025

    Towards Foundation Models for Knowledge Graph Reasoning

    by Mikhail Galkin, Xinyu Yuan, Hesham Mostafa, Jian Tang, Zhaocheng Zhu

    Presenter: Sumit Kumar

    Paper

  • When: 2045-2145 hrs IST, Mondays

    12 October 2024

    Linformer: Self-attention with linear complexity

    by Wang, Sinong, et al.

    Presenter: Debangan Mishra

    Paper
    09 September 2024

    Graph neural networks are dynamic programmers

    by Andrew J. Dudzik, Petar Veličković

    Presenter: Monish Singhal

    Paper Slides
    31 August 2024

    Understanding convolutions on graphs

    by Ameya Daigavane, Balaraman Ravindran, Gaurav Aggarwal

    Presenter: Akshit Sinha

    Paper Slides Contact
    24 August 2024

    Auto-regressive next-token predictors are universal learners

    by Malach, Eran

    Presenter: Sreeram Vennam

    Paper Slides Contact
    17 August 2024

    Reasoning or reciting? exploring the capabilities and limitations of language models through counterfactual tasks

    by Wu, Zhaofeng, Linlu Qiu, Alexis Ross, Ekin Akyürek, Boyuan Chen, Bailin Wang, Najoung Kim, Jacob Andreas, Yoon Kim

    Presenter: Vamshi Krishna

    Paper

  • When: 1530-1630 hrs IST, Saturdays

    08 June 2024

    Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision

    by Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, Ilya Sutskever, Jeff Wu

    Presenter: Swarang Joshi, Prishanshul Govil

    Paper
    01 June 2024

    The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

    by Shuming Ma, Hongyu Wang, Lingxiao Ma, Lei Wang, Wenhui Wang, Shaohan Huang, Li Dong, Ruiping Wang, Jilong Xue, Furu Wei

    Presenter: Hari, Vamsi Krishna

    Paper
    25 May 2024

    Stealing Part of a Production Language Model

    by Nicholas Carlini, Daniel Paleka, Krishnamurthy Dj Dvijotham, Thomas Steinke, Jonathan Hayase, A. Feder Cooper, Katherine Lee, Matthew Jagielski, Milad Nasr, Arthur Conmy, Eric Wallace, David Rolnick, Florian Tramèr

    Presenter: Sumit Kumar, Shiven Sinha

    Paper
    18 May 2024

    Evolutionary Optimization of Model Merging Recipes

    by Takuya Akiba, Makoto Shing, Yujin Tang, Qi Sun, David Ha

    Presenter: Anish R Joishy, Varshita Kolipaka

    Paper
    11 May 2024

    Mamba: Linear-Time Sequence Modeling with Selective State Spaces

    by Albert Gu, Tri Dao

    Presenter: Ameya Rathod, Ishan Kavathekar

    Paper