Large Language Model
Global Convergence in Training Large-Scale Transformers
Despite the widespread success of Transformers across various domains, their optimization guarantees in large-scale model settings are not well-understood.
A Critical Evaluation of AI Feedback for Aligning Large Language Models
Learning from AI feedback (LAIF) is a popular paradigm for improving the instruction-following abilities of powerful pre-trained language models.
AI power players pour cash into competitive primaries as 2026 midterms heat up
OpenAI President Greg Brockman and venture capitalist Ben Horowitz are funding a political group to support lawmakers who support AI regulatory frameworks.
VPGTrans: Transfer Visual Prompt Generator across LLMs
Specifically, we explore VPG transfer across different LLM sizes ( e .
VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
Transformers are central in modern natural language processing and computer vision applications.
Not All Tokens Are What You Need for Pretraining
See author contributions for details.
Multi-LLM Debate: Framework, Principals, and Interventions
We first take a theoretical approach to analyzing debate and provide a framework through which debate can be mathematically examined. Building on this framework, we provide several theoretical results for multi-agent debate.
