Publications (14)
Experience-Guided Adaptation of Inference-Time Reasoning Strategies
Adam Stein, Matthew Trager, Benjamin Bowman +4
Enabling agentic AI systems to adapt their problem-solving approaches based on post-training interactions remains a fundamental challenge. While systems that update and maintain a…
Ã-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting
Benjamin Bowman, Alessandro Achille, Luca Zancato +4
We introduce Ã-la-carte Prompt Tuning (APT), a transformer-based scheme to tune prompts on distinct data so that they can be arbitrarily composed at inference time. The individual…
Expansion Span: Combining Fading Memory and Retrieval in Hybrid State Space Models
Elvis Nunez, Luca Zancato, Benjamin Bowman +3
The "state" of State Space Models (SSMs) represents their memory, which fades exponentially over an unbounded span. By contrast, Attention-based models have "eidetic" (i.e., verbat…
Automated Cyber Defense with Generalizable Graph-based Reinforcement Learning Agents
Isaiah J. King, Benjamin Bowman, H. Howie Huang
Deep reinforcement learning (RL) is emerging as a viable strategy for automated cyber defense (ACD). The traditional RL approach represents networks as a list of computers in vario…
Your representations are in the network: composable and parallel adaptation for large scale models
Yonatan Dukler, Alessandro Achille, Hao Yang +7
We propose InCA, a lightweight method for transfer learning that cross-attends to any activation layer of a pre-trained model. During training, InCA uses a single forward pass to e…
Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime
Benjamin Bowman, Guido Montufar
We provide quantitative bounds measuring the difference in function space between the trajectory of a finite-width network trained on finitely many samples from the idealized…