South America
Efficiency of the First-Price Auction in the Autobidding World
We study the price of anarchy of first-price auctions in the autobidding world, where bidders can be either utility maximizers (i.e., traditional bidders) or value maximizers (i.e., autobidders).
Y angsibo Huang 1 Noah A. Smith
When turned on, "GitHub Copilot checks code completion suggestions with their surrounding
Fisher Flow Matching for Generative Modeling over Discrete Data Oscar Davis
We observe that our approach obtains improved performance to comparable discrete diffusion and flow matching methods of Austin et al. [8], Stark et al. [68].
The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domains
It involves how a model's performance
ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
In this paper, we introduce a novel robust attention mechanism designed to enhance the resilience of transformer-based architectures.
Aligning LLM Agents by Learning Latent Preference from User Edits Ge Gao Alexey T aymanov Eduardo Salinas Paul Mineiro Dipendra Misra Department of Computer Science, Cornell University
The inferred user preference descriptions are used to define prompts for generating responses in the future.
IncomeSCM: From tabular dataset to time-series simulator and causal estimation benchmark
They can be constructed to satisfy conditions for identifiability and to answer interventional queries, providing ground truth labels for estimates.
DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph
The current paradigm of evaluating Large Language Models (LLMs) through static benchmarks comes with significant limitations, such as vulnerability to data contamination and a lack of adaptability to the evolving capabilities of LLMs.
