Search papers, labs, and topics across Lattice.
6
0
12
0
Achieve centralized-level performance in federated LLM fine-tuning without compromising IP, privacy, or performance on heterogeneous data by using a compressed "proxy" model.
Automating LLM fine-tuning is now possible: a multi-agent system, TREX, matches or exceeds human performance on a diverse set of real-world tasks.
Despite advances in vision-language models, they still struggle to reason about the complex dynamics of traffic crashes, highlighting a critical gap in safety-critical applications.
Forget bigger models: massive gains in document parsing accuracy are still possible through smarter data engineering alone.
Lifelong learning beats static fine-tuning: PsychAgent, an AI counselor that learns from its own experience, surpasses GPT-4 and Gemini in multi-session counseling quality.
Fine-tuning smaller reasoning models on data from larger models can backfire spectacularly unless you carefully match the stylistic nuances of the student.
