Liqing Zhang

Stochastic separability of embedding manifolds reveals that distinct object categories can be linearly separated in high-dimensional spaces, provided certain conditions are met.

Selective verification can boost accuracy while slashing verification costs, but sometimes a longer initial solve is the more efficient choice.

Even the best LLMs struggle to navigate the fine line between empathetic support and harmful validation in emotionally charged Bengali conversations.

Reconstruct a high-fidelity, full-head 3D avatar from a single image in under one second, finally breaking the quality-speed tradeoff.

MLLMs can achieve state-of-the-art multimodal retrieval by learning to compress information into a handful of "bottleneck" tokens, forcing the model to distill relevant semantics.