6 citations · 12 across the 12 of their papers we have counts for
13 papers
Dynamic Compression in Recurrent Networks
Jyothish Pari, Ryan Bahlous-Boldi, Pulkit Agrawal
Recurrent models process long contexts efficiently by compressing their history into a fixed-size state, but modern architectures typically do so in a single causal pass over the s…
RL's Razor: Why Online Reinforcement Learning Forgets Less
Idan Shenfeld, Jyothish Pari, Pulkit Agrawal
Comparison of fine-tuning models with reinforcement learning (RL) and supervised fine-tuning (SFT) reveals that, despite similar performance at a new task, RL preserves prior knowl…
Self-Adapting Language Models
Adam Zweiger, Jyothish Pari, Han Guo +3
Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs…
General Intelligence Requires Reward-based Pretraining
Seungwook Han, Jyothish Pari, Samuel J. Gershman +1
Large Language Models (LLMs) have demonstrated impressive real-world utility, exemplifying artificial useful intelligence (AUI). However, their ability to reason adaptively and rob…
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning
Moritz Reuss, Jyothish Pari, Pulkit Agrawal +1
Diffusion Policies have become widely used in Imitation Learning, offering several appealing properties, such as generating multimodal and discontinuous behavior. As models are bec…
Collective Model Intelligence Requires Compatible Specialization
Jyothish Pari, Samy Jelassi, Pulkit Agrawal
In this work, we explore the limitations of combining models by averaging intermediate features, referred to as model merging, and propose a new direction for achieving collective…
The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
Ekin Akyürek, Mehul Damani, Adam Zweiger +5
Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks even when given a small number…
Few-Shot Task Learning through Inverse Generative Modeling
Aviv Netanyahu, Yilun Du, Antonia Bronars +4
Learning the intents of an agent, defined by its goals or motion style, is often extremely challenging from just a few examples. We refer to this problem as task concept learning a…
Train Offline, Test Online: A Real Robot Learning Benchmark
Gaoyue Zhou, Victoria Dean, Mohan Kumar Srirama +9
Three challenges limit the progress of robot learning research: robots are expensive (few labs can participate), everyone uses different robots (findings do not generalize across l…
Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations
Siddhant Haldar, Jyothish Pari, Anant Rai +1
While imitation learning provides us with an efficient toolkit to train robots, learning skills that are robust to environment variations remains a significant challenge. Current a…
The Surprising Effectiveness of Representation Learning for Visual Imitation
Jyothish Pari, Nur Muhammad Shafiullah, Sridhar Pandian Arunachalam +1
While visual imitation learning offers one of the most effective ways of learning from visual demonstrations, generalizing from them requires either hundreds of diverse demonstrati…
Playful Interactions for Representation Learning
Sarah Young, Jyothish Pari, Pieter Abbeel +1
One of the key challenges in visual imitation learning is collecting large amounts of expert demonstrations for a given task. While methods for collecting human demonstrations are…
A Semi-Automated Computational Approach for Infrared Dark Cloud Localization: A Catalog of Infrared Dark Clouds
Jyothish Pari, Joseph L. Hora
The field of computer vision has greatly matured in the past decade, and many of the methods and techniques can be useful for astronomical applications. One example is in searching…