Search papers, labs, and topics across Lattice.
The Hong Kong University of Science and Technology (
5
0
10
Adversarial attacks on ASR systems can achieve a +26.6 WER improvement by targeting feature representations instead of raw audio, exposing a significant blind spot in current robustness evaluations.
Stop letting bad actions ruin your VLA rollouts: Pre-VLA uses runtime verification to boost success rates by 7% while slashing execution steps.
Current MLLMs fail to detect covert advertisements, revealing a critical gap in social media moderation that could mislead consumers and pose ethical risks.
Training embodied intelligence models just got 40x faster thanks to a thousand-GPU cloud platform and a suite of optimizations spanning data pipelines, model architecture, and infrastructure.
Navigate faster and cheaper: SFCo-Nav cuts VLN token consumption by 50% and speeds up execution by 3.5x by intelligently triggering a slow LLM only when a fast reactive navigator loses confidence.
