3 papers
cs.CL2025
Words That Make Language Models Perceive
Sophie L. Wang, Phillip Isola, Brian Cheung
Large language models (LLMs) trained purely on text ostensibly lack any direct perceptual experience, yet their internal representations are implicitly shaped by multimodal regular…
cs.LG2025
Training Transformers with Enforced Lipschitz Constants
Laker Newhouse, R. Preston Hess, Franz Cesista +3
Neural networks are often highly sensitive to input and weight perturbations. This sensitivity has been linked to pathologies such as vulnerability to adversarial examples, diverge…
cs.CV2025
Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences
Hyojin Bahng, Caroline Chan, Fredo Durand +1
Measuring alignment between language and vision is a fundamental challenge, especially as multimodal data becomes increasingly detailed and complex. Existing methods often rely on…