9 papers
Learning Samples Importance: Parameterizing Dual Variables in Everywhere Learning
Ignacio Boero, Jonathan Nixon, Alejandro Ribeiro
Everywhere learning provides a principled framework for training AI models under constraints that must hold throughout the data distribution. In the dual domain, these pointwise co…
Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control
Antonio Pariente, Ignacio Boero, Nikolai Matni +1
World models jointly learn latent representations and dynamics that predict how high-dimensional observations evolve under actions. In this work, we propose a JEPA-style world mode…
Every Sample Counts: Supervised Fine-Tuning of Language Models with Pointwise Constraints
Ignacio Hounie, Ignacio Boero, Alejandro Ribeiro
Fine-tuning language models often requires enforcing constraints on individual inputs without compromising downstream performance. Existing constrained alignment methods impose con…
Everywhere Learning: Artificial Intelligence with Pointwise Constraints
Ignacio Boero, Ignacio Hounie, Luiz F. O. Chamon +2
Everywhere learning is a new paradigm whereby Artificial Intelligence (AI) systems are trained to satisfy loss constraints with probability one over the data distribution. This is…
AL-CoLe: Augmented Lagrangian for Constrained Learning
Ignacio Boero, Ignacio Hounie, Alejandro Ribeiro
Despite the non-convexity of most modern machine learning parameterizations, Lagrangian duality has become a popular tool for addressing constrained learning problems. We revisit A…
Distilling On-device Language Models for Robot Planning with Minimal Human Intervention
Zachary Ravichandran, Ignacio Hounie, Fernando Cladera +3
Large language models (LLMs) provide robots with powerful contextual reasoning abilities and a natural human interface. Yet, current LLM-enabled robots typically depend on cloud-ho…
Infinity Search: Approximate Vector Search with Projections on q-Metric Spaces
Antonio Pariente, Ignacio Hounie, Santiago Segarra +1
An ultrametric space or infinity-metric space is defined by a dissimilarity function that satisfies a strong triangle inequality in which every side of a triangle is not larger tha…
LoRTA: Low Rank Tensor Adaptation of Large Language Models
Ignacio Hounie, Charilaos Kanatsoulis, Arnuv Tandon +1
Low Rank Adaptation (LoRA) is a popular Parameter Efficient Fine Tuning (PEFT) method that effectively adapts large pre-trained models for downstream tasks. LoRA parameterizes mode…
Loss Shaping Constraints for Long-Term Time Series Forecasting
Ignacio Hounie, Javier Porras-Valenzuela, Alejandro Ribeiro
Several applications in time series forecasting require predicting multiple steps ahead. Despite the vast amount of literature in the topic, both classical and recent deep learning…