Search papers, labs, and topics across Lattice.
4
0
4
Memory compression can enhance long-horizon question answering, achieving a 6x increase in evidence-grounded answers while reducing memory usage by over two times.
Current Vision-Language Models struggle with engineering reasoning, revealing critical gaps in their ability to interpret technical diagrams and apply physical principles.
VLMs hallucinate less when you force them to "think twice" by contrasting language-driven and vision-driven token probabilities at each decoding step.
Pose-guided GANs and diffusion models can faithfully generate complex cultural dance postures, opening new avenues for digital preservation and education.
