Google

company

Verified

AI & ML interests

Google ❤️ Open Source AI

Recent Activity

sonali-kumari11 new activity about 6 hours ago

google/translategemma-27b-it:FP8-Dynamic Version for vLLM

perrynelson updated a dataset about 21 hours ago

google/WaxalNLP

pannaga10 new activity about 23 hours ago

google/gemma-3-12b-it:Inference Widget (Featherless AI) is broken: severe hallucinations and repetition loops due to missing chat template

View all activity

Papers

Unified Latents (UL): How to train your latents

Discovering Multiagent Learning Algorithms with Large Language Models

View all Papers

sonali-kumari11

in google/translategemma-27b-it about 6 hours ago

FP8-Dynamic Version for vLLM

#5 opened 2 days ago by

updated a dataset about 21 hours ago

google/WaxalNLP

Viewer • Updated about 21 hours ago • 2.56M • 9.72k • 142

in google/gemma-3-12b-it about 23 hours ago

Inference Widget (Featherless AI) is broken: severe hallucinations and repetition loops due to missing chat template

#30 opened about 2 months ago by

in google/medasr about 24 hours ago

Output text from test_audio.wav contains many epsilons

#7 opened about 1 month ago by

in google/gemma-3n-E2B-it-litert-lm 1 day ago

Actual iOS usage in app

#9 opened 3 months ago by

in google/embeddinggemma-300m 1 day ago

Explicit Title Format Performs Worse Than Simple Format (Contradicts Docs)

#35 opened 3 months ago by

in google/timesfm-2.5-200m-transformers 4 days ago

Update README.md

#1 opened 4 days ago by

updated a dataset 4 days ago

google/ConvApparel

Viewer • Updated 4 days ago • 1 • 112 • 4

in google/gemma-3-270m-it 4 days ago

Towards fine-tune perfection

#16 opened 5 days ago by

submitted a paper to Daily Papers 4 days ago

Unified Latents (UL): How to train your latents

Paper • 2602.17270 • Published 5 days ago • 49

updated a collection 5 days ago

TimesFM Release

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. • 7 items • Updated 5 days ago • 35

published a model 5 days ago

google/timesfm-2.5-200m-transformers

Time Series Forecasting • 0.2B • Updated 4 days ago • 909 • 14

updated a model 5 days ago

google/timesfm-2.5-200m-transformers

Time Series Forecasting • 0.2B • Updated 4 days ago • 909 • 14

in google/medasr 5 days ago

Bug with Tokenizer

#9 opened 24 days ago by

nitay

submitted a paper to Daily Papers 5 days ago

Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality

Paper • 2602.14080 • Published 9 days ago • 20

in google/gemma-3n-E2B-it-litert-lm 5 days ago

Hey

#12 opened 6 days ago by

submitted a paper to Daily Papers 5 days ago

Multi-agent cooperation through in-context co-player inference

Paper • 2602.16301 • Published 6 days ago • 15

in google/t5gemma-2-270m-270m 6 days ago

Is the training speed of t5gemma really much slower than Qwen/Intern VL?

#4 opened 8 days ago by

submitted a paper to Daily Papers 6 days ago

On Surprising Effectiveness of Masking Updates in Adaptive Optimizers

Paper • 2602.15322 • Published 7 days ago • 9

in google/svq 7 days ago

Update README

#4 opened 10 days ago by