Naphula

Naphula's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 4 days ago

Measuring Massive Multitask Language Understanding

Paper • 2009.03300 • Published Sep 7, 2020 • 7

What the HellaSwag? On the Validity of Common-Sense Reasoning Benchmarks

Paper • 2504.07825 • Published Apr 10, 2025 • 1

upvoted 2 papers 5 days ago

Faithful or Fabricated? A Causal Framework for Rationalization Bias in LLM Judges

Paper • 2605.23970 • Published May 13 • 2

Don't Judge an LLM Only by Its Activations: Discovering Suppressed Safety Features via Counterfactual Activation Potential

Paper • 2610.05541 • Published 8 days ago • 2

upvoted a collection 27 days ago

Boulesis

Collection

3 items • Updated 21 days ago • 1

upvoted an article 28 days ago

view article

Article

What if all that speed is slowing you down?

• 

darkc0de

•

28 days ago

• 4

upvoted 3 articles about 1 month ago

view article

Article

New imatrix dataset

• 

bartowski

•

Aug 17

• 18

view article

Article

Making LLMs Smaller Without Breaking Them: A GLU-Aware Pruning Approach

• 

oopere

•

Nov 24, 2024

• 23

view article

Article

Frontier-Assisted Single-Prompt Disposable Risk Assessment

• 

darkc0de

•

Aug 30

• 5

upvoted 4 papers about 1 month ago

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Paper • 2508.06471 • Published Aug 8, 2025 • 217

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Paper • 2403.03853 • Published Mar 6, 2024 • 66

Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels

Paper • 2406.17415 • Published Jun 25, 2024 • 1

SliderQuant: Accurate Post-Training Quantization for LLMs

Paper • 2603.25284 • Published Mar 26 • 1

upvoted 2 papers about 2 months ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published Aug 20 • 161

Fool's Gold: Defensive Deception Against Safety-Removal Attacks on Open-Weight Models

Paper • 2608.17202 • Published Aug 17 • 1

upvoted a collection about 2 months ago

Python Pre-compiled Binaries

Collection

These are python wheels that are built and saved in their completed format for specific cuda/torch combinations. Use in images or GPaaS instances. • 3 items • Updated 27 days ago • 1

upvoted a paper about 2 months ago

Data Attribution of Emergent Misalignment with Persona Features

Paper • 2608.11025 • Published Aug 11 • 1

upvoted 3 articles 3 months ago

view article

Article

The State of Simulation for Physical AI: An Overview

• 

nvidia

•

Jul 21

• 74

view article

Article

Security incident disclosure — July 2026

• 

system

•

Jul 16

• 804

view article

Article

We Just Surgically Changed What Your Model Believes

• 

ApolloRaines

•

Jul 20

• 3