YijuGuo's picture

YijuGuo

YijuGuo

openbmb

·

https://yijuguo.github.io/

AI & ML interests

LLM Alignment

Recent Activity

upvoted a paper 19 days ago

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

upvoted a paper 22 days ago

AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research

authored a paper 28 days ago

Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment

View all activity

Organizations

authored 3 papers 28 days ago

Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment

Paper • 2402.19085 • Published Feb 29, 2024

LaSeR: Reinforcement Learning with Last-Token Self-Rewarding

Paper • 2510.14943 • Published Oct 16, 2025 • 40

Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning

Paper • 2506.07851 • Published Jun 9, 2025

submitted a paper to Daily Papers 28 days ago

Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification

Paper • 2601.21244 • Published Jan 29 • 12

authored a paper 29 days ago

Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification

Paper • 2601.21244 • Published Jan 29 • 12