Francisco Ribeiro

Pedro Duarte, André Coelho, Francisco Ribeiro et al.

This paper proposes a vision-based framework for the intelligent control of mobile Open Radio Access Network (O-RAN) base stations (gNBs) operating in dynamic wireless environments. The framework comprises three innovative components. The first is the introduction of novel Service Models (SMs) within a vision-enabled O-RAN architecture, termed VisionRAN. These SMs extend state-of-the-art O-RAN-based architectures by enabling the transmission of vision-based sensing data and gNB positioning control messages. The second is an O-RAN xApp, VisionApp, which fuses vision and radio data, and uses this information to control the position of a mobile gNB, using a Deep Q-Network (DQN). The third is a digital twin environment, VisionTwin, which incorporates vision data and can emulate realistic wireless scenarios; this digital twin was used to train the DQN running in VisionApp and validate the overall system. Experimental results, obtained using real vision data and an emulated radio, demonstrate that the proposed approach reduces the duration of Line-of-Sight (LoS) blockages by up to 75% compared to a static gNB. These findings confirm the viability of integrating multimodal perception and learning-based control within RANs.

Francisco Ribeiro, Claudio Spiess, Prem Devanbu et al.

Despite the effectiveness of large language models (LLMs) for code generation, they often output incorrect code. One reason is that model output probabilities are often not well-correlated with correctness, and reflect only the final output of the generation process. Inspired by findings that LLMs internally encode concepts like truthfulness, this paper explores if LLMs similarly represent code correctness. Specifically, we identify a correctness representation inside LLMs by contrasting the hidden states between pairs of correct and incorrect code for the same programming tasks. By experimenting on four LLMs, we show that exploiting this extracted correctness representation outperforms standard log-likelihood ranking, as well as verbalized model confidence. Furthermore, we explore how this internal correctness signal can be used to select higher-quality code samples, without requiring test execution. Ultimately, this work demonstrates how leveraging internal representations can enhance code generation systems and make LLMs more reliable, thus improving confidence in automatically generated code.