Institution profile

Université de Sherbrooke

Academic institutionnorthamerica · ca
Official website
Research library97linked papers
Opportunities0open roles
Selected work

Representative Papers

Towards a Cryogenic CMOS-Memristor Neural Decoder for Quantum Error Correction

Sep 15, 2024International Conference on Quantum Computing and Engineering

To address the urgent need for real-time, ultra-low-power decoding in quantum error correction, this work presents a neuromorphic decoder chip designed for cryogenic operation at 1.2 K. The chip integrates 180-nm CMOS with metal-oxide memristors in an in-memory computing architecture. It demonstrates, for the first time at 1.2 K, stable analog sigmoid and threshold activation functions, as well as reliable spiking responses, using memristive crossbar arrays. The design supports a fully analog three-layer neural decoding structure—input–recurrent–output—and exhibits functional consistency across a broad temperature range (300 K to 1.2 K). Experimental results confirm that activation function shape, spiking dynamics, and power consumption retain room-temperature-level stability at cryogenic temperatures. This work establishes the first viable cryogenic integrated circuit solution for scalable, ultra-low-power, real-time hardware decoding in quantum error correction.

1 citationsRead paper

Exposing Weaknesses in Emotion Recognition in Conversations

Sep 05, 2026

Emotion Recognition in Conversations (ERC) aims to identify speakers'emotions in multi-turn dialogue. Accurate emotion recognition can support a wide range of applications, including empathetic conversational agents, mental health support, and educational technologies. While many recent approaches rely on task-specific fine-tuning, such models may exploit dataset-specific cues. A central yet rarely questioned assumption in ERC is that each utterance can be assigned a single unambiguous emotion label. To investigate this assumption, we study ERC using Large Language Models (LLMs) in a zero-shot setting while incorporating preceding conversational turns as context. We show that aggregate metrics mask systematic failures. Errors concentrate around utterances containing negations, exclamations, and interjections. This pattern is consistent across all evaluated models, suggesting limitations in the benchmarks rather than model-specific weaknesses. A controlled re-annotation study involving four human annotators supports this finding: strong agreement is observed in only 35 percent of cases, with neutral utterances dominating high-agreement instances, while many emotional categories fall into low-agreement regimes. These findings suggest that many apparent model errors reflect genuine annotation ambiguity rather than poor emotion understanding. Standard single-label evaluation is therefore insufficient. To address this limitation, we introduce an LLM-as-Judge framework that evaluates each emotion independently according to its plausibility in the conversational context rather than enforcing a single-label decision.

0 citationsRead paper
Recent publications

Latest Papers

Exposing Weaknesses in Emotion Recognition in Conversations

Sep 05, 2026

Emotion Recognition in Conversations (ERC) aims to identify speakers'emotions in multi-turn dialogue. Accurate emotion recognition can support a wide range of applications, including empathetic conversational agents, mental health support, and educational technologies. While many recent approaches rely on task-specific fine-tuning, such models may exploit dataset-specific cues. A central yet rarely questioned assumption in ERC is that each utterance can be assigned a single unambiguous emotion label. To investigate this assumption, we study ERC using Large Language Models (LLMs) in a zero-shot setting while incorporating preceding conversational turns as context. We show that aggregate metrics mask systematic failures. Errors concentrate around utterances containing negations, exclamations, and interjections. This pattern is consistent across all evaluated models, suggesting limitations in the benchmarks rather than model-specific weaknesses. A controlled re-annotation study involving four human annotators supports this finding: strong agreement is observed in only 35 percent of cases, with neutral utterances dominating high-agreement instances, while many emotional categories fall into low-agreement regimes. These findings suggest that many apparent model errors reflect genuine annotation ambiguity rather than poor emotion understanding. Standard single-label evaluation is therefore insufficient. To address this limitation, we introduce an LLM-as-Judge framework that evaluates each emotion independently according to its plausibility in the conversational context rather than enforcing a single-label decision.

0 citationsRead paper