27 citations · 102 across the 20 of their papers we have counts for
22 papers
A2Perf: Real-World Autonomous Agents Benchmark
Ikechukwu Uchendu, Jason Jabbour, Korneel Van den Berghe +15
Autonomous agents and systems cover a number of application areas, from robotics and digital assistants to combinatorial optimization, all sharing common, unresolved research chall…
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models
Yinlam Chow, Guy Tennenholtz, Izzeddin Gur +7
Recent studies have indicated that effectively utilizing inference-time compute is crucial for attaining better performance from large language models (LLMs). In this work, we prop…
Geometric-Averaged Preference Optimization for Soft Preference Labels
Hiroki Furuta, Kuang-Huei Lee, Shixiang Shane Gu +4
Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic. However, human preferences can vary across individuals, and the…
Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability
Jiri Hron, Laura Culp, Gamaleldin Elsayed +28
While many capabilities of language models (LMs) improve with increased training budget, the influence of scale on hallucinations is not yet fully understood. Hallucinations come i…
Scaling Exponents Across Parameterizations and Optimizers
Katie Everett, Lechao Xiao, Mitchell Wortsman +8
Robust and effective scaling of models from small to large width typically requires the precise adjustment of many algorithmic and architectural details, such as parameterization a…
Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
Avi Singh, John D. Co-Reyes, Rishabh Agarwal +38
Fine-tuning language models~(LMs) on human-generated data remains a prevalent practice. However, the performance of such models is often limited by the quantity and diversity of hi…
Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?
C. Daniel Freeman, Laura Culp, Aaron Parisi +27
We introduce and study the problem of adversarial arithmetic, which provides a simple yet challenging testbed for language model alignment. This problem is comprised of arithmetic…
Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web
Hiroki Furuta, Yutaka Matsuo, Aleksandra Faust +1
Language model agents (LMA) recently emerged as a promising paradigm on muti-step decision making tasks, often outperforming humans and other reinforcement learning agents. Despite…
Small-scale proxies for large-scale Transformer training instabilities
Mitchell Wortsman, Peter J. Liu, Lechao Xiao +13
Teams that have trained large Transformer-based models have reported training instabilities at large scale that did not appear when training with the same hyperparameters at smalle…
A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
Izzeddin Gur, Hiroki Furuta, Austin Huang +4
Pre-trained large language models (LLMs) have recently achieved better generalization and sample efficiency in autonomous web automation. However, the performance on real-world web…
Multimodal Web Navigation with Instruction-Finetuned Foundation Models
Hiroki Furuta, Kuang-Huei Lee, Ofir Nachum +4
The progress of autonomous web navigation has been hindered by the dependence on billions of exploratory interactions via online reinforcement learning, and domain-specific model d…
Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration
Srivatsan Krishnan, Natasha Jaques, Shayegan Omidshafiei +4
Microprocessor architects are increasingly resorting to domain-specific customization in the quest for high-performance and energy-efficiency. As the systems grow in complexity, fi…
CLUTR: Curriculum Learning via Unsupervised Task Representation Learning
Abdus Salam Azad, Izzeddin Gur, Jasper Emhoff +4
Reinforcement Learning (RL) algorithms are often known for sample inefficiency and difficult generalization. Recently, Unsupervised Environment Design (UED) emerged as a new paradi…
Understanding HTML with Large Language Models
Izzeddin Gur, Ofir Nachum, Yingjie Miao +6
Large language models (LLMs) have shown exceptional performance on a variety of natural language tasks. Yet, their capabilities for HTML understanding -- i.e., parsing the raw HTML…
Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization
Sungryull Sohn, Hyunjae Woo, Jongwook Choi +4
We tackle real-world problems with complex structures beyond the pixel-based game or simulator. We formulate it as a few-shot reinforcement learning problem where a task is charact…
Environment Generation for Zero-Shot Compositional Reinforcement Learning
Izzeddin Gur, Natasha Jaques, Yingjie Miao +4
Many real-world problems are compositional - solving them requires completing interdependent sub-tasks, either in series or in parallel, that can be represented as a dependency gra…
Less is More: Generating Grounded Navigation Instructions from Landmarks
Su Wang, Ceslee Montgomery, Jordi Orbay +7
We study the automatic generation of navigation instructions from 360-degree images captured on indoor routes. Existing generators suffer from poor visual grounding, causing them t…
Adversarial Environment Generation for Learning to Navigate the Web
Izzeddin Gur, Natasha Jaques, Kevin Malta +3
Learning to autonomously navigate the web is a difficult sequential decision making task. The state and action spaces are large and combinatorial in nature, and websites are dynami…
Assessing Post-Disaster Damage from Satellite Imagery using Semi-Supervised Learning Techniques
Jihyeon Lee, Joseph Z. Xu, Kihyuk Sohn +8
To respond to disasters such as earthquakes, wildfires, and armed conflicts, humanitarian organizations require accurate and timely data in the form of damage assessments, which in…
Learning to Navigate the Web
Izzeddin Gur, Ulrich Rueckert, Aleksandra Faust +1
Learning in environments with large state and action spaces, and sparse rewards, can hinder a Reinforcement Learning (RL) agent's learning through trial-and-error. For instance, fo…
User Modeling for Task Oriented Dialogues
Izzeddin Gur, Dilek Hakkani-Tur, Gokhan Tur +1
We introduce end-to-end neural network based models for simulating users of task-oriented dialogue systems. User simulation in dialogue systems is crucial from two different perspe…
Global Relation Embedding for Relation Extraction
Yu Su, Honglei Liu, Semih Yavuz +3
We study the problem of textual relation embedding with distant supervision. To combat the wrong labeling problem of distant supervision, we propose to embed textual relations with…