375 citations · 548 across the 11 of their papers we have counts for
13 papers
The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery
Robert Tjarko Lange, Luca Grillotti, Yutaro Yamada +2
Modern coding agents are fundamentally reshaping the role of human input for computational research: they write code, launch in silico experiments, analyze their results, and auton…
Self Improvement via Fast Tree-search
Xinghong Fu, Aravinth Kulanthaivelu, Yutaro Yamada
Coding agents can recursively modify their own implementations, forming a loop of self-improvement. While prior work shows this can boost performance on coding benchmarks, existing…
Diffusing Blame: Task-Dependent Credit Assignment in Biologically Plausible Dual-Stream Networks
Yutaro Yamada, Luca Grillotti, Rujikorn Charakorn +3
Biological neural circuits obey Dale's principle: each neuron's synapses are uniformly excitatory or inhibitory. Artificial networks that respect this constraint must coordinate se…
Towards End-to-End Automation of AI Research
Yutaro Yamada, Robert Tjarko Lange, Cong Lu +5
The automation of science is a long-standing ambition in the field of AI. While the community has made significant progress in automating individual components of the scientific pr…
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
Yutaro Yamada, Robert Tjarko Lange, Cong Lu +5
AI is increasingly playing a pivotal role in transforming how scientific discoveries are made. We introduce The AI Scientist-v2, an end-to-end agentic system capable of producing t…
L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects
Yutaro Yamada, Khyathi Chandu, Yuchen Lin +3
Diffusion-based image generation models such as DALL-E 3 and Stable Diffusion-XL demonstrate remarkable capabilities in generating images with realistic and unique compositions. Ye…
Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations
Jungo Kasai, Yuhei Kasai, Keisuke Sakaguchi +2
As large language models (LLMs) gain popularity among speakers of diverse languages, we believe that it is crucial to benchmark them to better understand model behaviors, failures,…
Does Robustness on ImageNet Transfer to Downstream Tasks?
Yutaro Yamada, Mayu Otani
As clean ImageNet accuracy nears its ceiling, the research community is increasingly more concerned about robust accuracy under distributional shifts. While a variety of methods ha…
Can Wikipedia Help Offline Reinforcement Learning?
Machel Reid, Yutaro Yamada, Shixiang Shane Gu
Fine-tuning reinforcement learning (RL) models has been challenging because of a lack of large scale off-the-shelf datasets as well as high variance in transferability among differ…
Support Recovery with Stochastic Gates: Theory and Application for Linear Models
Soham Jana, Henry Li, Yutaro Yamada +1
Consider the problem of simultaneous estimation and support recovery of the coefficient vector in a linear data model with additive Gaussian noise. We study the problem of estimati…
Feature Selection using Stochastic Gates
Yutaro Yamada, Ofir Lindenbaum, Sahand Negahban +1
Feature selection problems have been extensively studied for linear estimation, for instance, Lasso, but less emphasis has been placed on feature selection for non-linear functions…
Defending against Adversarial Images using Basis Functions Transformations
Uri Shaham, James Garritano, Yutaro Yamada +5
We study the effectiveness of various approaches that defend against adversarial attacks on deep networks via manipulations based on basis function representations of images. Speci…
Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization
Uri Shaham, Yutaro Yamada, Sahand Negahban
We propose a general framework for increasing local stability of Artificial Neural Nets (ANNs) using Robust Optimization (RO). We achieve this through an alternating minimization-m…