home research people contact donate

All topics

LLM Reasoning

Reasoning, verification, and calibration in language models.

Papers

HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning

HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning

Donggyun Kim, Jack Lu, Chanwoo Kim, Mengye Ren, and Seunghoon Hong

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

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

Amelia (Hui) Dai, Ryan Teehan, Parsa Torabian, and Mengye Ren

MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents

MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents

Kangsan Kim, Yanlai Yang, Suji Kim, Woongyeong Yeo, Youngwan Lee, Mengye Ren, and Sung Ju Hwang

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

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

Jack Lu, Ryan Teehan, Jinran Jin, and Mengye Ren

In-Context Clustering with Large Language Models

In-Context Clustering with Large Language Models

Ying Wang, Mengye Ren, and Andrew Gordon Wilson

StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding

StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding

Yanlai Yang, Zhuokai Zhao, Satya Narayan Shukla, Aashu Singh, Shlok Kumar Mishra, Lizhu Zhang, and Mengye Ren

Context Tuning for In-Context Optimization

Context Tuning for In-Context Optimization

Jack Lu, Ryan Teehan, Zhenbang Yang, and Mengye Ren

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

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

Amelia (Hui) Dai, Ryan Teehan, and Mengye Ren

CoLLEGe: Concept Embedding Generation for Large Language Models

CoLLEGe: Concept Embedding Generation for Large Language Models

Ryan Teehan, Brenden M. Lake, and Mengye Ren

Learning and Forgetting Unsafe Examples in Large Language Models

Learning and Forgetting Unsafe Examples in Large Language Models

Jiachen Zhao, Zhun Deng, David Madras, James Zou, and Mengye Ren

LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos

LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos

Ying Wang, Yanlai Yang, and Mengye Ren