🏢 Rutgers University
The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
·4880 words·23 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Multimodal Learning
Vision-Language Models
🏢 Rutgers University
VISTA steers LVLMs away from hallucinations by cleverly adjusting token rankings during inference, improving visual grounding and semantic coherence.
Improved Training Technique for Latent Consistency Models
·3409 words·17 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Rutgers University
Researchers significantly enhance latent consistency models’ performance by introducing Cauchy loss, mitigating outlier effects, and employing novel training strategies, thus bridging the gap with dif…