activity
20232026
collaborators

17 papers

cs.RO2026

Latent Cluster Analysis for Vision-Language-Action Models

Theodor Wulff, Sergio Lanza, Tamara Bila +3

Vision-Language-Action (VLA) Models are increasingly used in robotics for their ability to ground language and perception into action, yet the internal representations driving thei…

cs.CL2026

Vision-Language Models are Fragile Multilingual Associators

Ritabrata Chakraborty, Rajatsubhra Chakraborty, Shivakumara Palaiahnakote +2

Vision-language models must associate visual entities with textual attributes. Whether these associations or concept bindings remain stable when the language of the input changes i…

cs.AI2026

LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback

Manith Adikari, Bei Peng, Samuele Vinanzi +1

Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function. However, real-world decision-making tasks often involve multiple, c…

cs.RO2026

Grounding Hierarchical Vision-Language-Action Models Through Explicit Language-Action Alignment

Theodor Wulff, Federico Tavella, Rahul Singh Maharjan +2

Achieving robot transparency is a critical step toward effective human-robot collaboration. To be transparent, a robot's natural language communication must be consistent with its…

cs.CV2026

Hierarchical, Interpretable, Label-Free Concept Bottleneck Model

Haodong Xie, Yujun Cai, Rahul Singh Maharjan +3

Concept Bottleneck Models (CBMs) introduce interpretability to black-box deep learning models by predicting labels through human-understandable concepts. However, unlike humans, wh…

cs.AI2025

The Safety Challenge of World Models for Embodied AI Agents: A Review

Lorenzo Baraldi, Zifan Zeng, Chongzhe Zhang +8

The rapid progress in embodied artificial intelligence has highlighted the necessity for more advanced and integrated models that can perceive, interpret, and predict environmental…