Picture for Junhong Wu

Junhong Wu

Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation

Add code
Oct 17, 2024
Viaarxiv icon

Language Imbalance Driven Rewarding for Multilingual Self-improving

Add code
Oct 11, 2024
Viaarxiv icon

Hit the Sweet Spot! Span-Level Ensemble for Large Language Models

Add code
Sep 27, 2024
Viaarxiv icon

BLSP-Emo: Towards Empathetic Large Speech-Language Models

Add code
Jun 06, 2024
Viaarxiv icon

F-MALLOC: Feed-forward Memory Allocation for Continual Learning in Neural Machine Translation

Add code
Apr 07, 2024
Viaarxiv icon

BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing

Add code
Sep 02, 2023
Viaarxiv icon