Search Results for author: Aniket Didolkar

Found 16 papers, 4 papers with code

Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases

no code implementations21 Oct 2024 Cristian Meo, Akihiro Nakano, Mircea Lică, Aniket Didolkar, Masahiro Suzuki, Anirudh Goyal, Mengmi Zhang, Justin Dauwels, Yutaka Matsuo, Yoshua Bengio

Unsupervised object-centric learning from videos is a promising approach towards learning compositional representations that can be applied to various downstream tasks, such as prediction and reasoning.

Object Question Answering +2

Automated Discovery of Pairwise Interactions from Unstructured Data

no code implementations11 Sep 2024 Zuheng, Xu, Moksh Jain, Ali Denton, Shawn Whitfield, Aniket Didolkar, Berton Earnshaw, Jason Hartford

We derive two interaction tests that are based on pairwise interventions, and show how these tests can be integrated into an active learning pipeline to efficiently discover pairwise interactions between perturbations.

Active Learning

Zero-Shot Object-Centric Representation Learning

no code implementations17 Aug 2024 Aniket Didolkar, Andrii Zadaianchuk, Anirudh Goyal, Mike Mozer, Yoshua Bengio, Georg Martius, Maximilian Seitzer

We find that the proposed approach results in state-of-the-art performance for unsupervised object discovery, exhibiting strong zero-shot transfer to unseen datasets.

Object Object Discovery +2

Learning Beyond Pattern Matching? Assaying Mathematical Understanding in LLMs

no code implementations24 May 2024 Siyuan Guo, Aniket Didolkar, Nan Rosemary Ke, Anirudh Goyal, Ferenc Huszár, Bernhard Schölkopf

By contrast, certain instruction-tuning leads to similar performance changes irrespective of training on different data, suggesting a lack of domain understanding across different skills.

In-Context Learning Language Modeling +3

Cycle Consistency Driven Object Discovery

no code implementations3 Jun 2023 Aniket Didolkar, Anirudh Goyal, Yoshua Bengio

To tackle the second limitation, we apply the learned object-centric representations from the proposed method to two downstream reinforcement learning tasks, demonstrating considerable performance enhancements compared to conventional slot-based and monolithic representation learning methods.

Object Object Discovery +2

Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information

2 code implementations31 Oct 2022 Riashat Islam, Manan Tomar, Alex Lamb, Yonathan Efroni, Hongyu Zang, Aniket Didolkar, Dipendra Misra, Xin Li, Harm van Seijen, Remi Tachet des Combes, John Langford

We find that contemporary representation learning techniques can fail on datasets where the noise is a complex and time dependent process, which is prevalent in practical applications.

Offline RL Reinforcement Learning (RL) +1

Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models

no code implementations17 Jul 2022 Alex Lamb, Riashat Islam, Yonathan Efroni, Aniket Didolkar, Dipendra Misra, Dylan Foster, Lekan Molu, Rajan Chari, Akshay Krishnamurthy, John Langford

In many sequential decision-making tasks, the agent is not able to model the full complexity of the world, which consists of multitudes of relevant and irrelevant information.

Decision Making Sequential Decision Making

Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning

2 code implementations30 May 2022 Aniket Didolkar, Kshitij Gupta, Anirudh Goyal, Nitesh B. Gundavarapu, Alex Lamb, Nan Rosemary Ke, Yoshua Bengio

A slow stream that is recurrent in nature aims to learn a specialized and compressed representation, by forcing chunks of $K$ time steps into a single representation which is divided into multiple vectors.

Decision Making Inductive Bias +1

ARHNet - Leveraging Community Interaction for Detection of Religious Hate Speech in Arabic

no code implementations ACL 2019 Arijit Ghosh Chowdhury, Aniket Didolkar, Ramit Sawhney, Rajiv Ratn Shah

The rapid widespread of social media has lead to some undesirable consequences like the rapid increase of hateful content and offensive language.

Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.