COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation
arXiv:2607.08071v1 Announce Type: new Abstract: Online ads are essential to all businesses and ad headlines are one of their core creative component. Existing methods can generate headlines…
Read the full articleYou might also wanna read
Beyond Autoregression: LLaDA2.1 and the Case for Self-Editing Language Models
Introduction Every mainstream large language model today generates text the same way: one token at a time, left to right, no looking back. I
JavelinGuard: Low-Cost Transformer Architectures for LLM Security
We present JavelinGuard, a suite of low-cost, high-performance model architectures designed for detecting malicious intent in Large Language
iLLaDA: An 8B Masked Diffusion Language Model Trained with Bidirectional Attention
Modern large language models are predominantly trained with autoregressive factorization and causal attention. We present \emph{iLLaDA}, an
arxiv.org·14d ago
Google's DiffusionGemma achieves 4x faster text generation using diffusion-based approach
An overview of DiffusionGemma, an exceptionally fast text generation model with up to 4x faster speeds.
deepmind.google·25d ago
Google Experiments with AI-Generated Headlines in Discover News Feed
Google Discover, the company’s smartphone news feed, is experimenting with AI headlines. Many of them are very bad.
The Verge·7mo ago
MODUS: A Unified Decoder-Only Model for Any-to-Any Multimodal Generation
MODUS unifies any-to-any multimodal generation in a single decoder-only model.
Comments
Sign in to join the conversation.
No comments yet. Be the first.