Tag: Vision-Language Models
Browse our exclusive articles!
HiVLA: Advanced Visual-Grounded Robotic Manipulation System
Discover HiVLA, a hierarchical system enhancing robotic manipulation with visual grounding and separate planning and control for superior performance.
Early Visual Cortex Alignment Reduces Vision-Language Model Manipulation
Discover how aligning vision-language models with early visual cortex activity helps prevent sycophantic manipulation and enhances AI robustness.
Optimizing Rewards for Physical Reasoning in Vision-Language Models
Explore how reward design impacts physical reasoning in vision-language models, improving accuracy and spatial reasoning on physics benchmarks.
ReXSonoVQA: Benchmark for Procedure-Centric Ultrasound AI
Discover ReXSonoVQA, a video QA benchmark enhancing AI understanding of procedure-centric ultrasound for improved medical imaging and training.
ROVA Boosts Video Reasoning Models for Real-World Use
Discover how ROVA improves video reasoning models' robustness and accuracy under real-world disturbances like weather and motion.