From the 1 of 4 linked papers with an AI index.
4 papers
-OPSD: Deriving with Policy Optimization, Training with Self-Distillation
Jiawei Xu, Minghui Liu, Juzheng Zhang +2
The paper proposes β‑OPSD, a generalized on‑policy self‑distillation method that treats the KL regularization weight as a tunable parameter, enabling a controlled interpolation bet…
Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models
Jiawei Xu, Minghui Liu, Aakriti Agrawal +2
Masked diffusion language models decode by iteratively unmasking tokens, where the unmasking order defines an "order of thought" that strongly influences generation quality yet is…
Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline
Jiawei Xu, Arief Koesdwiady, Sisong Bei +8
Recent advances in LLM-based multi-agent systems (MAS) show that workflows composed of multiple LLM agents with distinct roles, tools, and communication patterns can outperform sin…
Towards Effective Model Editing for LLM Personalization
Baixiang Huang, Limeng Cui, Jiapeng Liu +7
Personalization is becoming indispensable for LLMs to align with individual user preferences and needs. Yet current approaches are often computationally expensive, data-intensive,…