← authors · overview

• Boosting LLM Translation Skills Without General Ability Loss Via Rationale Distillation
  2024 · 7 citations
• BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing
  2023 · 2 citations
• Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs
  2026
• Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
  2026
• Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
  2025
• Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective
  2025
• LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs
  2025
• BLSP-Emo: Towards Empathetic Large Speech-Language Models
  2024