Search papers, labs, and topics across Lattice.
Guangdong Institute of Intelligence Science and Technology
2
0
6
VLMs can achieve state-of-the-art adversarial robustness by iteratively refining visual and textual representations through a closed-loop prompting mechanism, even with frozen encoders.
LLMs can now compress their KV cache more effectively by dynamically synthesizing soft tokens tailored to the input, preserving crucial context that's otherwise lost with static methods.
