PonderNet: Learning to Ponder

12 July 2021

Papers citing "PonderNet: Learning to Ponder"

23 / 23 papers shown

Title
Large Language Models Are Human-Like Internally Tatsuki Kuribayashi Yohei Oseki Souhaib Ben Taieb Kentaro Inui Timothy Baldwin 69 4 0 03 Feb 2025
BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts Divya J. Bajpai M. Hanawal 76 0 0 02 Feb 2025
Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models Michael Toker Ido Galil Hadas Orgad Rinon Gal Yoad Tewel Gal Chechik Yonatan Belinkov DiffM 54 2 0 12 Jan 2025
Hyper-multi-step: The Truth Behind Difficult Long-context Tasks Yijiong Yu Ma Xiufa Fang Jianwei Zhi-liang Xu Su Guangyao ... Zhixiao Qi Wei Wang Wei Liu Ran Chen Ji Pei LRM RALM 29 0 0 06 Oct 2024
Adaptivity and Modularity for Efficient Generalization Over Task Complexity Samira Abnar Omid Saremi Laurent Dinh Shantel Wilson Miguel Angel Bautista ... Vimal Thilak Etai Littwin Jiatao Gu Josh Susskind Samy Bengio 34 5 0 13 Oct 2023
Adaptive Computation with Elastic Input Sequence Fuzhao Xue Valerii Likhosherstov Anurag Arnab N. Houlsby Mostafa Dehghani Yang You 31 18 0 30 Jan 2023
Logical Tasks for Measuring Extrapolation and Rule Comprehension Ippei Fujisawa Ryota Kanai ELM LRM 28 4 0 14 Nov 2022
Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms Surbhi Goel Sham Kakade Adam Tauman Kalai Cyril Zhang 32 1 0 01 Sep 2022
Faithful Reasoning Using Large Language Models Antonia Creswell Murray Shanahan ReLM LRM 18 120 0 30 Aug 2022
Transformers discover an elementary calculation system exploiting local attention and grid-like problem representation Samuel Cognolato Alberto Testolin 36 7 0 06 Jul 2022
Short-Term Plasticity Neurons Learning to Learn and Forget Hector Garcia Rodriguez Qinghai Guo Timoleon Moraitis 13 12 0 28 Jun 2022
The CLRS Algorithmic Reasoning Benchmark Petar Velivcković Adria Puigdomenech Badia David Budden Razvan Pascanu Andrea Banino Mikhail Dashevskiy R. Hadsell Charles Blundell 161 88 0 31 May 2022
Impartial Games: A Challenge for Reinforcement Learning Bei Zhou Søren Riis 26 6 0 25 May 2022
Dynamic Split Computing for Efficient Deep Edge Intelligence Arian Bakhtiarnia Nemanja Milošević Qi Zhang Dragana Bajović Alexandros Iosifidis 20 24 0 23 May 2022
PALBERT: Teaching ALBERT to Ponder Nikita Balagansky Daniil Gavrilov MoE 21 6 0 07 Apr 2022
Unsupervised Learning of Temporal Abstractions with Slot-based Transformers Anand Gopalakrishnan Kazuki Irie Jürgen Schmidhuber Sjoerd van Steenkiste OffRL 26 16 0 25 Mar 2022
End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking Arpit Bansal Avi Schwarzschild Eitan Borgnia Z. Emam Furong Huang Micah Goldblum Tom Goldstein LRM 11 24 0 11 Feb 2022
Show Your Work: Scratchpads for Intermediate Computation with Language Models Maxwell Nye Anders Andreassen Guy Gur-Ari Henryk Michalewski Jacob Austin ... Aitor Lewkowycz Maarten Bosma D. Luan Charles Sutton Augustus Odena ReLM LRM 57 702 0 30 Nov 2021
Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking Ronen Tamari Kyle Richardson Aviad Sar-Shalom Noam Kahlon Nelson F. Liu Reut Tsarfaty Dafna Shahaf 40 5 0 30 Nov 2021
Recurrent Vision Transformer for Solving Visual Reasoning Problems Nicola Messina Giuseppe Amato F. Carrara Claudio Gennaro Fabrizio Falchi ViT LRM 22 11 0 29 Nov 2021
The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization Róbert Csordás Kazuki Irie Jürgen Schmidhuber AI4CE 33 55 0 14 Oct 2021
Spike-inspired Rank Coding for Fast and Accurate Recurrent Neural Networks Alan Jeffares Qinghai Guo Pontus Stenetorp Timoleon Moraitis 33 16 0 06 Oct 2021
Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead Arian Bakhtiarnia Qi Zhang Alexandros Iosifidis 27 35 0 19 May 2021