norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/LessWrongjust now
ResearchLessWrong

Visual Explainer of Empirical Neural Tangent Kernels

The paper introduces an empirical neural tangent kernel (eNTK) method for mechanistic interpretation of neural networks, focusing on identifying interpretable features through model updates rather than clustering activations. It explains how eNTK computes features by analyzing how model updates on one data point affect behavior on others, resulting in a weighted list of input-output pairs that influence the model's direction in weight space.

Open original
SIGNAL FROM THE SOURCE
20
source points
Tracking sinceOctober 7, 202620 source points
Momentum+9.09/hover 0.55 h
PublishedOctober 7, 2026Wuschel Schulz
BEHIND THE NUMBERS

How interest changes

LessWrong

History starts here

The chart will appear after repeat observations. The current metric comes from the source.

20 source points

Real observations only. History before source connection is not reconstructed.

WHY IT MAY MATTER

The eNTK method provides a new approach to understanding neural network behavior by analyzing how model updates on one data point affect other data points, offering insights into feature identification without relying on activation clustering.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
LessWrong

Determining the Date Without Real-Time Data

The text discusses a scenario where an AI must respond to the question 'What's the date?' without access to real-time data. It explores the challenge of providing an accurate date without hallucinating, considering OpenAI's training focus on avoiding false information. The text speculates on potential model versions and knowledge cutoff dates but acknowledges uncertainty due to lack of explicit information.

6 days agoDaily Papers

RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations

RealCompanion introduces a benchmark for evaluating AI's ability to understand humans through long-term conversations, featuring 27,218 messages from 10 real relationships. The study reveals that most queries don't require long-term memory and that current methods struggle to identify when memory is needed.

6 days agoDaily Papers

CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?

CheckerBench is a benchmark for evaluating coding agents' ability to synthesize static-analysis checkers from defect specifications, including tasks derived from 300 CVEs across multiple repositories and language ecosystems. CheckerLab, an evaluation framework, measures diagnostic contrast, patch localization, and tool use, with results showing that current agents struggle to develop reliable checkers, achieving a maximum Pass@1 of 45.33%.

yesterdayDaily Papers

Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation

Ego2Act is a benchmark for evaluating goal-directed manipulation in egocentric video generation, featuring 2,640 videos from 110 real-world tasks. It assesses whether video generation models can create realistic egocentric videos of a hand performing multi-step object manipulations to achieve high-level goals.

6 days agoDaily Papers

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

The paper investigates on-policy distillation (OPD) in cross-tokenizer settings, focusing on alignment coverage and supervision reliability. It finds that strict 1:1 token alignment covers most student-generated tokens despite vocabulary mismatches, and that restricting reverse KL to a top-16 subset of shared vocabulary achieves comparable accuracy to full shared-vocabulary OPD, while adding span supervision reduces accuracy.

yesterdayDaily Papers

World Action Learning via Interaction-Centric Spectral Latent Guidance

The paper introduces WING, a framework that transfers interaction knowledge from human egocentric videos to robot policies by separating observer-induced motion from hand-object interactions and using spectral analysis to identify shared temporal structures between human and robot behaviors. It achieves high success rates on multiple benchmarks and demonstrates strong performance in real-world tasks.

5 days ago