3 papers
q-bio.NC2026
Learning Biophysical Models of Large-Scale Multineuronal Data to Enable Precise Neurostimulation
Amrith Lotlikar, Ian Christopher Tanoh, Praful Vasireddy +9
Multi-compartment Hodgkin-Huxley (HH) models provide a principled framework for predicting neural dynamics and responses to electrical stimulation. However, fitting HH biophysical…
cs.LG2026
PreFT: Prefill-only finetuning for efficient inference
Andrew Lanpouthakoun, Aryaman Arora, Zhengxuan Wu +4
Large language models can now be personalised efficiently at scale using parameter efficient finetuning methods (PEFTs), but serving user-specific PEFTs harms throughput, even with…
cs.SE2026
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini +82
AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not…