tbruckner

2026-01-06 3:16

Submitted: "U-Haul Migration Trends"

3 points0 commentsmisc-uhaul-com.azurewebsites.net

2025-12-09 10:31

Submitted: "How to Guess a Gradient"

2 points0 commentsarxiv.org

How much can you say about the gradient of a neural network without computing a loss or knowing the label? This may sound like a strange question: surely the answer is "very little." However, in this…

2025-12-09 5:24

Submitted: "Words That Make Language Models Perceive"

3 points0 commentsarxiv.org

Large language models (LLMs) trained purely on text ostensibly lack any direct perceptual experience, yet their internal representations are implicitly shaped by multimodal regularities encoded in…

2025-12-08 4:45

Commented: "Words that make language models perceive"

A simple cue like asking the model to 'see' or 'hear' can push a purely text-trained language model towards the representations of purely image-trained or purely-audio trained encoders.

2025-12-08 4:45

Submitted: "Words that make language models perceive"

1 points1 comments

Hacker News

tbruckner

308

2022-09-11

Recent Activity

Submitted: "U-Haul Migration Trends"

Submitted: "How to Guess a Gradient"

Submitted: "Words That Make Language Models Perceive"

Commented: "Words that make language models perceive"

Submitted: "Words that make language models perceive"

HackerNews