Xin Zhang

Automating software repository build and testing across languages and platforms is now possible, unlocking scalable benchmarking and training for coding agents.

HyperParallel unlocks the potential of supernode architectures for AI by offering a framework that simplifies parallel programming and boosts performance through hardware-aware orchestration.

LLMs can boost few-shot learning for pathology images, but only if you dynamically adapt the language priors to each image and stochastically integrate multiple "expert" descriptions.

By aligning attention patterns between intact and corrupted image processing paths, CrystaL crystallizes task-relevant visual semantics in MLLM latent spaces without needing extra annotations.