activity
20242026
most citedHumans Coexist, So Must Embodied Artificial Agents

2 citations · 3 across the 11 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

SCENT: Aligning Mass Spectra with Molecular Structure for Olfactory Perception

Ziqi Zhang, Eunyeong Jin, Miguel Vasco +6

Predicting human olfactory perception from molecular structure has seen remarkable progress, yet these approaches require explicit chemical structure at inference, which is not ava…

cs.LG2026

Geometry of Uncertainty: Learning Metric Spaces for Multimodal State Estimation in RL

Alfredo Reichlin, Adriano Pacciarelli, Danica Kragic +1

Estimating the state of an environment from high-dimensional, multimodal, and noisy observations is a fundamental challenge in reinforcement learning (RL). Traditional approaches r…

cs.LG2025

Walking on the Fiber: A Simple Geometric Approximation for Bayesian Neural Networks

Alfredo Reichlin, Miguel Vasco, Danica Kragic

Bayesian Neural Networks provide a principled framework for uncertainty quantification by modeling the posterior distribution of network parameters. However, exact posterior infere…

cs.LG2025★ 2 cited

Humans Coexist, So Must Embodied Artificial Agents

Hannah Kuehn, Joseph La Delfa, Miguel Vasco +2

This paper introduces the concept of coexistence for embodied artificial agents and argues that it is a prerequisite for long-term, in-the-wild interaction with humans. Contemporar…

cs.LG2024★ 1 cited

Can Transformers Smell Like Humans?

Farzaneh Taleb, Miguel Vasco, Antônio H. Ribeiro +2

The human brain encodes stimuli from the environment into representations that form a sensory perception of the world. Despite recent advances in understanding visual and auditory…

cs.LG2024

Reducing Variance in Meta-Learning via Laplace Approximation for Regression Tasks

Alfredo Reichlin, Gustaf Tegnér, Miguel Vasco +3

Given a finite set of sample points, meta-learning algorithms aim to learn an optimal adaptation strategy for new, unseen tasks. Often, this data can be ambiguous as it might belon…