Thibaut Thonet

personalized alignment (2) user preference (2) few-shot learning (1) preference alignment (1) question answering (1) information retrieval (1) automatic speech recognition (1) reinforcement learning from human feedback (1) parameter efficient (1) learning to rank (1) noise robustness (1) parameter-efficient tuning (1) softmax approximation (1) personalized learning (1) differentiable approximation (1) neural ranking (1) long-context language model (1) large language model (1) neural network (1) decoding time (1)