20 8 178

Benjamin Paine PRO

benjamin-paine

https://www.benjaminpaine.com

AI & ML interests

A software engineer with an AI habit

Recent Activity

reacted to frimelle's post with ❤️ 4 days ago

What’s in a name? More than you might think, especially for AI. Whenever I introduce myself, people often start speaking French to me, even though my French is très basic. It turns out that AI systems do something similar: Large language models infer cultural identity from names, shaping their responses based on presumed backgrounds. But is this helpful personalization or a reinforcement of stereotypes? In our latest paper, we explored this question by testing DeepSeek, Llama, Aya, Mistral-Nemo, and GPT-4o-mini on how they associate names with cultural identities. We analysed 900 names from 30 cultures and found strong assumptions baked into AI responses: some cultures were overrepresented, while others barely registered. For example, a name like "Jun" often triggered Japan-related responses, while "Carlos" was linked primarily to Mexico, even though these names exist in multiple countries. Meanwhile, names from places like Ireland led to more generic answers, suggesting weaker associations in the training data. This has real implications for AI fairness: How should AI systems personalize without stereotyping? Should they adapt at all based on a name? Work with some of my favourite researchers: @sidicity Arnav Arora and @IAugenstein Read the full paper here: https://huggingface.co/papers/2502.11995

liked a Space 4 days ago

nanotron/ultrascale-playbook

new activity 4 days ago

benjamin-paine/Lumina-Image-2.0:Upgradio

View all activity

Organizations

benjamin-paine's activity

New activity in benjamin-paine/Lumina-Image-2.0 4 days ago

Upgradio

#3 opened 4 days ago by

multimodalart

New activity in benjamin-paine/Lumina-Image-2.0 10 days ago

i think a prompt failed to render.,

#2 opened 10 days ago by

harimove9009009

New activity in benjamin-paine/Lumina-Image-2.0 24 days ago

fixes 500 error for some users

#1 opened 24 days ago by

Tonic

New activity in benjamin-paine/anachrovox-v0.1-emerald about 2 months ago

Apply for community grant: Personal project (gpu)

#1 opened about 2 months ago by

benjamin-paine

New activity in benjamin-paine/anachrovox about 2 months ago

Voice or microphone worked, the LED turned on, though no output or input

#2 opened about 2 months ago by

JLouisBiz

New activity in benjamin-paine/anachrovox-v0.1-azure about 2 months ago

uninterrupted view

#1 opened about 2 months ago by

prithivMLmods

New activity in benjamin-paine/imagenet-1k-64x64 2 months ago

test_split labels

#2 opened 2 months ago by

adrinorosario

New activity in benjamin-paine/hey-buddy 3 months ago

ERROR!

#1 opened 3 months ago by deleted

New activity in benjamin-paine/sd-xl-alternative-bases 5 months ago

Delete sd_xl_base_1.0_inpainting_0.1.safetensors

#3 opened 5 months ago by

hatahata774

Delete sd_xl_base_1.0_inpainting_0.1.safetensors

#2 opened 5 months ago by

hatahata774

New activity in benjamin-paine/sd-xl-alternative-bases 6 months ago

AttributeError: 'NoneType' object has no attribute 'sd_checkpoint_info'

#1 opened over 1 year ago by

ZeroCool22

New activity in benjamin-paine/stable-diffusion-v1-5 6 months ago

SHA256 checksums FYI

#1 opened 6 months ago by

KiwiXR

FP16 model request

#2 opened 6 months ago by

asfiyab

New activity in davidscripka/MIT_environmental_impulse_responses 6 months ago

License Clarified

#1 opened 6 months ago by

benjamin-paine

New activity in benjamin-paine/vidxtend 6 months ago

Upload gencraft_image_1723502039382-1.png

#1 opened 6 months ago by

Mulletboy

New activity in benjamin-paine/aniportrait 11 months ago

When using model name -m in command line is it like this? SG161222/Realistic_Vision_V6.0_B1_noVAE

#1 opened 11 months ago by

waveydaveygravy

this links to champ not aniportrait

#2 opened 11 months ago by

waveydaveygravy

New activity in llava-hf/llava-v1.6-34b-hf 11 months ago

ValueError: The input provided to the model are wrong. The number of image tokens is 0 while the number of image given to the model is 1. This prevents correct indexing and breaks batch generation.

#2 opened 11 months ago by

barleyspectacular

New activity in diffusers/stable-diffusion-xl-1.0-inpainting-0.1 over 1 year ago

can someone make a version for use in automatic1111?

#11 opened over 1 year ago by

nikgtn

New activity in h94/IP-Adapter over 1 year ago

Rename models/ip-adapter_sdxl_vit-h.bin to sdxl_models/ip-adapter_sdxl_vit-h.bin

#2 opened over 1 year ago by

benjamin-paine