Xiao Luo

Predicting targeted protein degradation on underexplored E3 ligases no longer requires dense labeled datasets: support-conditioned prototype estimation enables zero-fine-tuning transfer across ligases with as few as two samples per class.

Treating automated feature transformations as permutation-invariant hierarchies rather than ordered sequences eliminates a fundamental representation bias, enabling policy-guided RL to efficiently navigate non-convex search spaces.

MCTH revolutionizes biomolecular design by enabling adaptive search strategies that outperform conventional methods, even in complex multi-modal scenarios.

Guardrails in AI systems may claim safety benefits that are largely illusory, with their actual effectiveness hinging on the specifics of input encoding and channel dynamics.

Attention Collapse reveals a hidden vulnerability in RAG systems, enabling the detection of poisoning attacks that traditional methods fail to catch.

Achieving high-fidelity 3D generation with just 1.5% of the training data could revolutionize resource allocation in 3D modeling.

LLMs can learn to reason better by validating "skill-based teachers" derived from past experiences, even when those teachers are sometimes wrong.

MiniMax-M2 proves that massive parameter counts don't always translate to better agentic performance; strategic activation of a smaller subset can unlock frontier-level intelligence.