James Zou

30

Papers

72

Total Citations

Papers (30)

Reducing Hallucinations in Large Vision-Language Models via Latent Space Steering

SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning

Cost-efficient Collaboration between On-device and Cloud Language Models

Solving Inequality Proofs with Large Language Models

A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

metaTextGrad: Automatically optimizing language model optimizers

FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees

Prospector Heads: Generalized Feature Attribution for Large Models & Data

How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis

Selecting Large Language Model to Fine-tune via Rectified Scaling Law

Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews

ArtWhisperer: A Dataset for Characterizing Human-AI Interactions in Artistic Creations

Position: TrustLLM: Trustworthiness in Large Language Models

Clustering Plotted Data by Image Segmentation

CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers

Simple linear attention language models balance the recall-throughput tradeoff

SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals

Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits

Scaling Laws for the Value of Individual Data Points in Machine Learning

Learning and Forgetting Unsafe Examples in Large Language Models

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Intersecting Faces: Non-negative Matrix Factorization With New Guarantees

Rich Component Analysis

Estimating the unseen from multiple populations

Learning Latent Space Models with Angular Constraints

CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions

Concrete Autoencoders: Differentiable Feature Selection and Reconstruction

Data Shapley: Equitable Valuation of Data for Machine Learning

Discovering Conditionally Salient Features with Statistical Guarantees

Adaptive Monte Carlo Multiple Testing via Multi-Armed Bandits