activity
20242026
collaborators

6 papers

cs.CL2026

Context Tuning for In-Context Optimization

Jack Lu, Ryan Teehan, Zhenbang Yang +1

We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of large language models (LLMs) without weight updates. In-Context Learning…

cs.LG2026

Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting

Hui Dai, Ryan Teehan, Parsa Torabian +1

Probabilistic forecasting estimates the likelihood of uncertain future events. To improve LLM forecasting, existing methods typically learn from binary outcomes to output verbalize…

cs.CL2026

When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers

Jack Lu, Ryan Teehan, Jinran Jin +1

Large language models (LLMs) can act as both problem solvers and solution verifiers, where the latter select high-quality answers from a pool of solver-generated candidates. This r…

cs.LG2025

A General Framework for Inference-time Scaling and Steering of Diffusion Models

Raghav Singhal, Zachary Horvitz, Ryan Teehan +4

Diffusion models produce impressive results in modalities ranging from images and video to protein design and text. However, generating samples with user-specified properties remai…

cs.CL2025

Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle

Hui Dai, Ryan Teehan, Mengye Ren

Many existing evaluation benchmarks for Large Language Models (LLMs) quickly become outdated due to the emergence of new models and training data. These benchmarks also fall short…

cs.CL2024

CoLLEGe: Concept Embedding Generation for Large Language Models

Ryan Teehan, Brenden Lake, Mengye Ren

Current language models are unable to quickly learn new concepts on the fly, often requiring a more involved finetuning process to learn robustly. Prompting in-context is not robus…