3 citations · 6 across the 10 of their papers we have counts for
14 papers
Predicting Privileged Information Effectiveness for On-Policy Self-Distillation
Kaijian Zou, Emiliano Penaloza, MohammadHossein Rezaei +5
On-policy self-distillation (OPSD) enables large language models (LLMs) to learn from privileged information (PI) without a separate teacher model. However, prior work largely trea…
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
Emiliano Penaloza, Dane Malenfant, Dheeraj Vattikonda +15
Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been the most popular mechanism to alleviate…
Shockingly Simple Self-retrospection Improves Agentic Models Without RL
Jonathan Light, Christopher Zhang Cui, Jeonghye Kim +7
People learn not only by repeating successful actions, but also by recounting and explaining their experiences, revising their understanding to guide future behavior. Can a languag…
FrogNano: Training a 4B Coding Agent via Online Task Synthesis
Minseon Kim, Zhengyan Shi, Emiliano Penaloza +14
We present FrogNano, a 4B coding agent designed to tackle software engineering (SWE) tasks efficiently and effectively, even under resource-constrained environments. It is post-tra…
Controllable and Content-Based Recommendations
Fırat Öncel, Jihoon Jeong, Emiliano Penaloza +3
Traditional recommendation systems rely on latent (dense) representations, making them difficult to interpret and control. We propose the Controllable and Content-Based Recommendat…
Privileged Information Distillation for Language Models
Emiliano Penaloza, Dheeraj Vattikonda, Nicolas Gontier +3
Training-time privileged information (PI) can enable language models to succeed on tasks they would otherwise fail, making it a powerful tool for reinforcement learning in hard, lo…
Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization
Linfeng Du, Ye Yuan, Zichen Zhao +8
Large language models (LLMs) excel at general-purpose tasks, yet adapting their responses to individual users remains challenging. Retrieval augmentation provides a lightweight alt…
Audio Prototypical Network For Controllable Music Recommendation
Fırat Öncel, Emiliano Penaloza, Haolun Wu +4
Traditional recommendation systems represent user preferences in dense representations obtained through black-box encoder models. While these models often provide strong recommenda…
How to Train Your LLM Web Agent: A Statistical Diagnosis
Dheeraj Vattikonda, Santhoshi Ravichandran, Emiliano Penaloza +13
LLM-based web agents have recently made significant progress, but much of it has occurred in closed-source systems, widening the gap with open-source alternatives. Progress has bee…
Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization
Emiliano Penaloza, Tianyue H. Zhang, Laurent Charlin +1
Concept Bottleneck Models (CBMs) propose to enhance the trustworthiness of AI systems by constraining their decisions on a set of human-understandable concepts. However, CBMs typic…
TEARS: Textual Representations for Scrutable Recommendations
Emiliano Penaloza, Olivier Gouvert, Haolun Wu +1
Traditional recommender systems rely on high-dimensional (latent) embeddings for modeling user-item interactions, often resulting in opaque representations that lack interpretabili…
Changepoint Detection in Highly-Attributed Dynamic Graphs
Emiliano Penaloza, Nathaniel Stevens
Detecting anomalous behavior in dynamic networks remains a constant challenge. This problem is further exacerbated when the underlying topology of these networks is affected by ind…
INFLECT-DGNN: Influencer Prediction with Dynamic Graph Neural Networks
Elena Tiukhova, Emiliano Penaloza, María Óskarsdóttir +3
Leveraging network information for predictive modeling has become widespread in many domains. Within the realm of referral and targeted marketing, influencer detection stands out a…
Influencer Detection with Dynamic Graph Neural Networks
Elena Tiukhova, Emiliano Penaloza, María Óskarsdóttir +5
Leveraging network information for prediction tasks has become a common practice in many domains. Being an important part of targeted marketing, influencer detection can potentiall…