← authors · overview

• Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
  2024 · 7 citations
• Tuna: Instruction Tuning using Feedback from Large Language Models
  2023 · 4 citations
• Self-Harmonized Chain of Thought
  2024 · 1 citations
• Multilingual Fine-Tuning via Localized Gradient Conflict Resolution
  2026
• Language Models Can Learn from Verbal Feedback Without Scalar Rewards
  2025
• Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
  2025
• Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs
  2025
• Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model
  2025
• Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering
  2025
• Through the Valley: Path to Effective Long CoT Training for Small Language Models
  2025
• PEAR: Phase Entropy Aware Reward for Efficient Reasoning
  2025
• TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data
  2025
• Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models
  2024