TempoControl: Precise Temporal Guidance for Text-to-Video AI
Discover TempoControl, a method for fine-grained temporal control in text-to-video models enabling precise timing of visual elements without retraining.
Are Vision-Language Models Ready to Aid Blind Users?
Explore how large vision-language models can support blind and low-vision individuals with improved accuracy and efficiency.
Adaptive Data-Knowledge Alignment for Genetic Prediction
Discover ALIGNED, a neuro-symbolic framework that improves genetic perturbation prediction by integrating data-driven learning with biological knowledge.
Polychromic Objectives Boost Reinforcement Learning Diversity
Enhance reinforcement learning with polychromic objectives that improve exploration, diversity, and generalization in pretrained policies.
FedKLPR: Efficient Federated Learning for Person Re-ID
Discover FedKLPR, a communication-efficient federated learning framework enhancing person re-identification with pruning and KL-divergence techniques.