Ningyu Zhang

LabVLA achieves unprecedented success rates in executing complex laboratory protocols, outperforming all existing models in both familiar and novel settings.

Today's best data analysis agents forget crucial context as conversations drag on, dropping nearly 50 points in accuracy when reasoning through longer analyses.

LLMs exhibit a quantifiable "Parametric Memory Law" during LoRA finetuning, where loss reduction scales predictably with effective parameters and sequence length, revealing fundamental limits on how much they can memorize.

LLM memory failures are systematic, stemming from operation-level issues like information loss and retrieval misalignment, and can be automatically corrected with prompt optimization guided by fine-grained error tracing.

LLM agents can achieve state-of-the-art performance in dynamic environments by treating memory as a continuously evolving graph, rather than a static repository.

Unlock interdisciplinary breakthroughs: SciAtlas provides a panoramic scientific evolution network of 43M papers, enabling AI agents to navigate complex logical connections and discover non-obvious insights.

Unlock the secrets of the deep: OceanPile, a massive, meticulously curated multimodal dataset, finally brings the power of foundation models to the vast and underexplored ocean.

AI agents can now learn durable skills instead of constantly "reinventing the wheel," thanks to SkillNet's infrastructure for creating, evaluating, and connecting AI skills at scale.