UC Berkeley
University of California, Berkeley, US
Records 10
Newest first. Open one to see it with its source.
Argues that prompt evolution can compete with RL on sample efficiency
The theoretical basis of DSPy's optimizers
The prototype of the out-of-context memory management line (later the memory tool and others)
A framework that shifted from writing prompts to compiling programs
The first large-scale counterevidence to the assumption that you can simply put in a long context
Manages the KV cache like OS paging, cutting memory waste to under 4%; the starting point of the open-source serving standard
Automated the search for parallelization strategies. Redefined manual 3D parallelism tuning as a compilation problem
A design that trains without paired data, lowering the data requirements of generative models
Proposed architecture-agnostic meta-learning, opening up research on few-shot adaptation