17 citations · 34 across the 18 of their papers we have counts for
18 papers
Rethinking Thinking Tokens: LLMs as Improvement Operators
Lovish Madaan, Aniket Didolkar, Suchin Gururangan +6
Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which among other things, allows them to explore solution strategies with self-checking. This res…
Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
Aniket Didolkar, Nicolas Ballas, Sanjeev Arora +1
Large language models (LLMs) now solve multi-step problems by emitting extended chains of thought. During the process, they often re-derive the same intermediate steps across probl…
CTRL-O: Language-Controllable Object-Centric Visual Representation Learning
Aniket Didolkar, Andrii Zadaianchuk, Rabiul Awal +3
Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current…
Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases
Cristian Meo, Akihiro Nakano, Mircea Lică +7
Unsupervised object-centric learning from videos is a promising approach towards learning compositional representations that can be applied to various downstream tasks, such as pre…
Masked Generative Priors Improve World Models Sequence Modelling Capabilities
Cristian Meo, Mircea Lica, Zarif Ikram +6
Deep Reinforcement Learning (RL) has become the leading approach for creating artificial agents in complex environments. Model-based approaches, which are RL methods with world mod…
Automated Discovery of Pairwise Interactions from Unstructured Data
Zuheng, Xu, Moksh Jain +5
Pairwise interactions between perturbations to a system can provide evidence for the causal dependencies of the underlying underlying mechanisms of a system. When observations are…
Zero-Shot Object-Centric Representation Learning
Aniket Didolkar, Andrii Zadaianchuk, Anirudh Goyal +4
The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that objec…
Learning Beyond Pattern Matching? Assaying Mathematical Understanding in LLMs
Siyuan Guo, Aniket Didolkar, Nan Rosemary Ke +3
We are beginning to see progress in language model assisted scientific discovery. Motivated by the use of LLMs as a general scientific assistant, this paper assesses the domain kno…
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
Aniket Didolkar, Anirudh Goyal, Nan Rosemary Ke +7
Metacognitive knowledge refers to humans' intuitive knowledge of their own thinking and reasoning processes. Today's best LLMs clearly possess some reasoning processes. The paper g…
Cycle Consistency Driven Object Discovery
Aniket Didolkar, Anirudh Goyal, Yoshua Bengio
Developing deep learning models that effectively learn object-centric representations, akin to human cognition, remains a challenging task. Existing approaches facilitate object di…
Representation Learning in Deep RL via Discrete Information Bottleneck
Riashat Islam, Hongyu Zang, Manan Tomar +8
Several self-supervised representation learning methods have been proposed for reinforcement learning (RL) with rich observations. For real-world applications of RL, recovering und…
Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
Riashat Islam, Manan Tomar, Alex Lamb +8
Learning to control an agent from data collected offline in a rich pixel-based visual observation space is vital for real-world applications of reinforcement learning (RL). A major…
CNT (Conditioning on Noisy Targets): A new Algorithm for Leveraging Top-Down Feedback
Alexia Jolicoeur-Martineau, Alex Lamb, Vikas Verma +1
We propose a novel regularizer for supervised learning called Conditioning on Noisy Targets (CNT). This approach consists in conditioning the model on a noisy version of the target…
Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models
Alex Lamb, Riashat Islam, Yonathan Efroni +7
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. For…
Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning
Aniket Didolkar, Kshitij Gupta, Anirudh Goyal +4
Recurrent neural networks have a strong inductive bias towards learning temporally compressed representations, as the entire history of a sequence is represented by a single vector…
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Nan Rosemary Ke, Aniket Didolkar, Sarthak Mittal +7
Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise that the causal variables themselves are ob…
Neural Production Systems: Learning Rule-Governed Visual Dynamics
Anirudh Goyal, Aniket Didolkar, Nan Rosemary Ke +5
Visual environments are structured, consisting of distinct objects or entities. These entities have properties -- both visible and latent -- that determine the manner in which they…
Coordination Among Neural Modules Through a Shared Global Workspace
Anirudh Goyal, Aniket Didolkar, Alex Lamb +7
Deep learning has seen a movement away from representing examples with a monolithic hidden state towards a richly structured state. For example, Transformers segment by position, a…