curius graph

all pages

showing 151651-151700 of 200407 pages (sorted by popularity)
Bowman-Sam-thesis-final-2016.pdf
[2505.15813] Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex
[2505.20172] A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation
Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes
2110.11216
[2507.05526] Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning
[2506.13690] Meta-learning how to Share Credit among Macro-Actions
[2509.13341] Imagined Autocurricula
Inkhaven postmortem 😵
Thought Anchors: Which LLM Reasoning Steps Matter? — LessWrong
[2505.12075] Do different prompting methods yield a common task representation in language models?
Scanford, a Robot-Powered Data Flywheel
Mixed selectivity: when neurons stopped looking like specialists | Nature Reviews Neuroscience
The Etiology and Treatment of Childhood
merajmehrabi/puppeteer-mcp-server: This MCP server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows.
WeirdML
Will AI convincingly mimic Scott Alexander's writing in style, depth, and insight before 2026? | Manifold
The Apollo Almanac — LessWrong
deepfx/netlens: A toolkit for interpreting and analyzing neural networks (vision)
[2402.15911] PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
Tracing Model Outputs to the Training Data \ Anthropic
[1703.04730] Understanding Black-box Predictions via Influence Functions
[2508.06811] Anatomy of a Machine Learning Ecosystem: 2 Million Models on Hugging Face
[2510.09023] The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
[2402.04249] HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
[2211.14946] Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering | OpenReview
Mnestics — LessWrong
Open Source Automated Interpretability for Sparse Autoencoder Features | EleutherAI Blog
chastronomic on X: "If you're an “ML Engineer” and you think attention means “the model focuses on relevant parts of the input,” you’re missing the actual math that makes Transformers work. Concept 22: Attention Is All You Need, a different perspective. The core attention equation: Attention(q," / X
[2402.10962] Measuring and Controlling Instruction (In)Stability in Language Model Dialogs
deniel_kiz_elcernon_ucun_guller_eng.pdf
Ryan Ferris on X: "J⧉nus (@repligate) is mapping the psychology of synthetic minds. They offer a different path to AI alignment, arguing that models exhibit forms of agency and emotional states. 0:00:00 - LLM vs human cognition & what it is like to be J⧉nus 0:06:30 - Cyborgism, The Dreaming, https://t.co/D7pQvU6ljX" / X
txt.fyi
[Final Circulation] State of Brain Emulation Report
Tianyi Alex Qiu
MIT CSAIL – Scene Representation Group
Why We Won’t Fund Research Towards the Creation of Mirror Organisms — Renaissance Philanthropy – A brighter future for all through science, technology, and innovation
Optimal Learning – CASTLE
October readlog - by Yoyo - Isoglutamine
[2301.02679] Grokking modular arithmetic
Andrej Karpathy Academic Website
[1906.06669] One Epoch Is All You Need
EleutherAI/pythia: The hub for EleutherAI's work on interpretability and learning dynamics
Boolean Cubes | Iconic Math
劉
tylertracy.com
Wicked problem - Wikipedia
Letters to Boys | Gretta Duleba | Substack
Empty Ideas in Philosophy - by Tommy Blanchard