5.1k citations · 9.6k across the 102 of their papers we have counts for
10 papers · 1 filter
ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data
Junhong Shen, Atishay Jain, Zedian Xiao +4
Large Language Model (LLM) agents are rapidly improving to handle increasingly complex web-based tasks. Most of these agents rely on general-purpose, proprietary models like GPT-4…
Specialized Foundation Models Struggle to Beat Supervised Baselines
Zongzhe Xu, Ritvik Gupta, Wenduo Cheng +4
Following its success for vision and text, the "foundation model" (FM) paradigm -- pretraining large models on massive data, then fine-tuning on target tasks -- has rapidly expande…
The Impact of Element Ordering on LM Agent Performance
Wayne Chi, Ameet Talwalkar, Chris Donahue
There has been a surge of interest in language model agents that can navigate virtual environments such as the web or desktop. To navigate such environments, agents benefit from in…
Understanding Optimization in Deep Learning with Central Flows
Jeremy M. Cohen, Alex Damian, Ameet Talwalkar +2
Traditional theories of optimization cannot describe the dynamics of optimization in deep learning, even in the simple setting of deterministic training. The challenge is that opti…
Need Help? Designing Proactive AI Assistants for Programming
Valerie Chen, Alan Zhu, Sebastian Zhao +3
While current chat-based AI assistants primarily operate reactively, responding only when prompted by users, there is significant potential for these systems to proactively assist…
Modulating Language Model Experiences through Frictions
Katherine M. Collins, Valerie Chen, Ilia Sucholutsky +6
Language models are transforming the ways that their users engage with the world. Despite impressive capabilities, over-consumption of language model outputs risks propagating unch…
Agreement-Based Cascading for Efficient Inference
Steven Kolawole, Don Dennis, Ameet Talwalkar +1
Adaptive inference schemes reduce the cost of machine learning inference by assigning smaller models to easier examples, attempting to avoid invocation of larger models when possib…
The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers
Hussein Mozannar, Valerie Chen, Mohammed Alsobay +7
Evaluation of large language models for code has primarily relied on static benchmarks, including HumanEval (Chen et al., 2021), or more recently using human preferences of LLM res…
UPS: Efficiently Building Foundation Models for PDE Solving via Cross-Modal Adaptation
Junhong Shen, Tanya Marwah, Ameet Talwalkar
We present Unified PDE Solvers (UPS), a data- and compute-efficient approach to developing unified neural operators for diverse families of spatiotemporal PDEs from various domains…
Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes
Steven Kolawole, Lucio Dery, Jean-François Kagy +3
Structured pruning is a promising approach to create smaller, faster large language models. However, existing methods typically rely on computing the gradient via backward passes,…