Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering Paper • 2610.05894 • Published 3 days ago • 15
Diptych: Scoped, AI-Interpreted Comparison for Reference Listening in Music Production Paper • 2609.39963 • Published 8 days ago • 21
RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting Paper • 2609.07414 • Published Sep 7 • 11
Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre Expansion Paper • 2608.13947 • Published Aug 14 • 15
VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use Paper • 2608.08477 • Published Aug 9 • 6
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents Paper • 2608.04003 • Published Aug 4 • 36
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published Aug 3 • 161