Christopher D Manning

Full Professor@Computer Science Department, Stanford University·OpenReview

研究方向

natural language processing · natural language understanding · deep learning · dependency parsing · neural word embeddings · neural language models · large language models

Christopher D Manning

Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky Similarity

WebDS: An End-to-End Benchmark for Web-based Data Science

DistillKac: Few-Step Image Generation via Damped Wave Equations

Turning Speech Language Models into Multilingual Listeners

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity

Thoughtbubbles: an Unsupervised Method for Parallel Thinking in Latent Space

Improved Representation Steering for Language Models

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Synthetic Data Generation and Multi-Step Reinforcement Learning for Reasoning and Tool Use

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

Do Language Models Use Their Depth Efficiently?

h4rm3l: A Language for Composable Jailbreak Attack Synthesis

Instruction Following without Instruction Tuning

NNetscape Navigator: Complex Demonstrations for Web Agents Without a Demonstrator

MrT5: Dynamic Token Merging for Efficient Byte-level Language Models