Search papers, labs, and topics across Lattice.
5
0
8
RaBitQCache accelerates long-context LLM inference while cutting memory I/O by intelligently adapting token budgets based on attention sparsity.
Agents fail to effectively integrate data discovery with code execution, achieving only 61.1% success in real-world-like scenarios.
Paraphrased prompts may seem equivalent, but they can drastically alter learning dynamics, with some prompts leading to better generalization and less forgetting.
GAIS enables the synthesis of complex tasks that not only outperform existing methods but also do so with dramatically improved data efficiency.
LLMs can boost K-12 writing skills, but over-reliance on AI feedback hits a ceiling, revealing the sweet spot for human-AI collaboration in education.
