Institution profile

RAI Institute

Academic institution
Research library8linked papers
Opportunities0open roles
Selected work

Representative Papers

HuMBLE: Human Motion-Driven Behavior Learning for Embodied Locomotion

Oct 07, 2026

This study addresses the inherent trade-off between mechanically rigid gaits and limited command generalization in humanoid robots by proposing a control framework that integrates human motion priors with multi-task reinforcement learning. The method extracts naturalistic kinematic features via teacher-student knowledge distillation, followed by multi-task reinforcement fine-tuning to achieve robust tracking of out-of-distribution velocity commands while preserving biomechanical anthropomorphism. Experimental results demonstrate that the proposed policy enables real-time, controllable, and robust human-like locomotion across both indoor and outdoor environments on physical Atlas and Unitree G1 platforms. It significantly outperforms data-free baselines while offering distinct advantages for lightweight deployment.

0 citationsRead paper

Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL

Aug 12, 2026

This work addresses the challenge of scaling reinforcement learning to complex loco-manipulation tasks, where conventional approaches rely heavily on handcrafted dense rewards. The authors propose a novel framework that leverages sample-based model predictive control (SMPC) as an automated expert policy generator to efficiently construct large-scale offline datasets in simulation. This dataset is then used within a hierarchical architecture combining offline-to-online reinforcement learning under sparse rewards with a low-level dynamically stable controller. Notably, the method eliminates the need for manual reward engineering and enables agents trained solely with sparse rewards to surpass the performance of the SMPC teacher policy. The approach demonstrates strong empirical results, successfully deploying on both the Spot quadruped and G1 humanoid robots with high performance, robustness, and effective sim-to-real transfer.

0 citationsRead paper

Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environments

Aug 06, 2026

This work addresses the challenge of accurately segmenting semantic regions in open-ended environments for scene graph construction, a task where existing methods falter due to their reliance on local visual clustering or rigid geometric heuristics. The proposed approach formulates scene graph generation as a probabilistic alignment problem, integrating RGB-D instance maps with dynamic task- and structure-level priors derived from large language models (LLMs). By optimizing a Markov random field that fuses these multimodal sources, the method infers high-level functional semantics. Notably, it introduces task-driven LLM-derived topological priors, enabling zero-shot ontological flexibility and supporting task-adaptive spatial reconceptualization even in the absence of physical partitions. Evaluated in both simulated and real-world open environments, the approach achieves state-of-the-art performance and robustly identifies distant functional boundaries.

0 citationsRead paper

Semantic Homogenization in Italian Popular Music: A Diachronic Analysis

Jul 06, 2026

This study investigates whether semantic diversity in Italian popular music lyrics has declined over time, thereby testing the universality of global semantic convergence beyond English-language contexts. Drawing on 75 years of finalist songs from the Sanremo Music Festival, the authors develop a multi-granular analytical framework that integrates word embeddings and large language models to trace diachronic semantic shifts at the levels of full texts, lyrical segments, thematic content, and individual vocabulary. The research presents the first systematic evidence of progressive semantic convergence in Italian pop lyrics, revealing patterns closely aligned with those observed in English-language songs. These findings not only validate the efficacy of natural language processing techniques for studying long-term cultural expression but also introduce a transferable paradigm for analyzing semantic evolution across linguistic and cultural domains.

0 citationsRead paper
Recent publications

Latest Papers

HuMBLE: Human Motion-Driven Behavior Learning for Embodied Locomotion

Oct 07, 2026

This study addresses the inherent trade-off between mechanically rigid gaits and limited command generalization in humanoid robots by proposing a control framework that integrates human motion priors with multi-task reinforcement learning. The method extracts naturalistic kinematic features via teacher-student knowledge distillation, followed by multi-task reinforcement fine-tuning to achieve robust tracking of out-of-distribution velocity commands while preserving biomechanical anthropomorphism. Experimental results demonstrate that the proposed policy enables real-time, controllable, and robust human-like locomotion across both indoor and outdoor environments on physical Atlas and Unitree G1 platforms. It significantly outperforms data-free baselines while offering distinct advantages for lightweight deployment.

0 citationsRead paper

Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL

Aug 12, 2026

This work addresses the challenge of scaling reinforcement learning to complex loco-manipulation tasks, where conventional approaches rely heavily on handcrafted dense rewards. The authors propose a novel framework that leverages sample-based model predictive control (SMPC) as an automated expert policy generator to efficiently construct large-scale offline datasets in simulation. This dataset is then used within a hierarchical architecture combining offline-to-online reinforcement learning under sparse rewards with a low-level dynamically stable controller. Notably, the method eliminates the need for manual reward engineering and enables agents trained solely with sparse rewards to surpass the performance of the SMPC teacher policy. The approach demonstrates strong empirical results, successfully deploying on both the Spot quadruped and G1 humanoid robots with high performance, robustness, and effective sim-to-real transfer.

0 citationsRead paper

Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environments

Aug 06, 2026

This work addresses the challenge of accurately segmenting semantic regions in open-ended environments for scene graph construction, a task where existing methods falter due to their reliance on local visual clustering or rigid geometric heuristics. The proposed approach formulates scene graph generation as a probabilistic alignment problem, integrating RGB-D instance maps with dynamic task- and structure-level priors derived from large language models (LLMs). By optimizing a Markov random field that fuses these multimodal sources, the method infers high-level functional semantics. Notably, it introduces task-driven LLM-derived topological priors, enabling zero-shot ontological flexibility and supporting task-adaptive spatial reconceptualization even in the absence of physical partitions. Evaluated in both simulated and real-world open environments, the approach achieves state-of-the-art performance and robustly identifies distant functional boundaries.

0 citationsRead paper

Semantic Homogenization in Italian Popular Music: A Diachronic Analysis

Jul 06, 2026

This study investigates whether semantic diversity in Italian popular music lyrics has declined over time, thereby testing the universality of global semantic convergence beyond English-language contexts. Drawing on 75 years of finalist songs from the Sanremo Music Festival, the authors develop a multi-granular analytical framework that integrates word embeddings and large language models to trace diachronic semantic shifts at the levels of full texts, lyrical segments, thematic content, and individual vocabulary. The research presents the first systematic evidence of progressive semantic convergence in Italian pop lyrics, revealing patterns closely aligned with those observed in English-language songs. These findings not only validate the efficacy of natural language processing techniques for studying long-term cultural expression but also introduce a transferable paradigm for analyzing semantic evolution across linguistic and cultural domains.

0 citationsRead paper