8 papers
Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning
Amogh Inamdar, Zhenwei Tang, Ashton Anderson +1
Curriculum learning--ordering training examples in a sequence to aid machine learning--takes inspiration from human learning, but has not gained widespread acceptance. Static strat…
Re-Evaluating Continual Learning with Few-Shot Adaptation
Amogh Inamdar, Matthew So, Vici Milenia +1
Continual learning methods aim to maximize the stability and plasticity of machine learning models that are trained on a sequence of tasks. The standard measure of stability (i.e.,…
Whom to Query for What: Adaptive Group Elicitation via Multi-Turn LLM Interactions
Ruomeng Ding, Tianwei Gao, Thomas P. Zollo +3
Eliciting information to reduce uncertainty about latent group-level properties from surveys and other collective assessments requires allocating limited questioning effort under r…
Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation
Thomas Zollo, Jimmy Wang, Richard Zemel
Reasoning language models can solve increasingly complex tasks, but struggle to produce the calibrated confidence estimates necessary for reliable deployment. Existing calibration…
Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language
Max S. Bennett, Thomas P. Zollo, Richard Zemel
Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledge. Continual fine-tuning and…
Test-Time Warmup for Multimodal Large Language Models
Nikita Rajaneesh, Thomas Zollo, Richard Zemel
Multimodal Large Language Models (MLLMs) hold great promise for advanced reasoning at the intersection of text and images, yet they have not fully realized this potential. MLLMs ty…