What are you looking for?

SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation

AI·SQuaD-SQL uses LLM-guided synthetic data and LoRA fine-tuning to train 1.5B-parameter SLMs to reach 86.9% execution accuracy on WikiSQL, matching large models while requiring only one consumer GPU and delivering faster, lower-memory inference.

Echoes Across Vietnam's Highlands, Delta, and Coast: A Multilingual Corpus for Cham, Khmer, and Tay-Nung

AI·CKTN multilingual corpus covers Cham, Khmer, and Tay-Nung from Vietnam's highlands, delta, and coast for NLP of under-resourced minority languages.

Accelerating Gemini Nano models on Pixel with frozen Multi-Token Prediction

Machine Intelligence

Thinking to recall: How reasoning unlocks parametric knowledge in LLMs

Generative AI

Unlocking dependable responses with Gemini Enterprise Agent Platform’s Agentic RAG

Data Management

Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery

General Science

ReasoningBank: Enabling agents to learn from experience

Generative AI

Designing synthetic datasets for the real world: Mechanism design and reasoning from first principles

Generative AI

ConvApparel: Measuring and bridging the realism gap in user simulators

Generative AI

Improving the academic workflow: Introducing two AI agents for better figures and peer review

Generative AI

Testing LLMs on superconductivity research questions

Education Innovation

Introducing Groundsource: Turning news reports into data with Gemini

Climate & Sustainability

WAXAL: A large-scale open resource for African language speech technology

Natural Language Processing