9 papers
DeltaNet-PC: Test-Time Memory Without Backpropagation Through Time
Todd Morrill, Richard Zemel
Test-time memorization of sequential information is a foundational capability for any intelligent system that needs to rapidly store and retrieve data, as demonstrated by the atten…
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.,…
Binary Agreement for Efficient Unsupervised Confidence Calibration of Reasoning LLMs
Thomas Zollo, Jimmy Wang, Richard Zemel
Reasoning language models often lack the calibrated confidence needed for reliable deployment, particularly when correctness labels are unavailable and sampling budgets are limited…
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…
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…
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…
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…
QuEst: Enhancing Estimates of Quantile-Based Distributional Measures Using Model Predictions
Zhun Deng, Thomas P Zollo, Benjamin Eyre +3
As machine learning models grow increasingly competent, their predictions can supplement scarce or expensive data in various important domains. In support of this paradigm, algorit…
Adaptive Elicitation of Latent Information Using Natural Language
Jimmy Wang, Thomas Zollo, Richard Zemel +1
Eliciting information to reduce uncertainty about a latent entity is a critical task in many application domains, e.g., assessing individual student learning outcomes, diagnosing u…