Scalable Diffusion Models with Transformers

www.wpeebles.com/DiT

2402.16288v1.pdf

arxiv.org/pdf/2402.16288v1

2312.12232v1.pdf

arxiv.org/pdf/2312.12232v1

Finally, a Replacement for BERT: Introducing ModernBERT

huggingface.co/blog/modernbert

2203.05797v2.pdf

arxiv.org/pdf/2203.05797

2406.05925v1.pdf

arxiv.org/pdf/2406.05925v1

2308.15022v2.pdf

arxiv.org/pdf/2308.15022

Memory profiling in Python with tracemalloc

www.red-gate.com/simple-talk/development/python/memory-profiling-in-python-with-tracemalloc/

Memory leak in a Python project

owlet.today/posts/memory-leak-in-a-python-project/

2404.16130v1.pdf

arxiv.org/pdf/2404.16130

jp5ReklDNpcnUnZY_zaT8RbqN_ZprXqjydz4_lBE1Y6qU4ZnyjzC9h9q2ltpmGuzj798wxI2J6d_QpEuliDnVyvaBfILoc1_Y3nv-_Yf9oAw2dx9sg0i48KFPDVrv10LlqnEnC-YLrdE3WoApleV2v546UlRx5msXtKMzlV7LIU7CqwXcAesODe1UAQgY3zhw3vzlBIdUrVj13wMfvqz4A5rVDHd (285×214)

link-thumb.1vn.app/jp5ReklDNpcnUnZY_zaT8RbqN_ZprXqjydz4_lBE1Y6qU4ZnyjzC9h9q2ltpmGuzj798wxI2J6d_QpEuliDnVyvaBfILoc1_Y3nv-_Yf9oAw2dx9sg0i48KFPDVrv10LlqnEnC-YLrdE3WoApleV2v546UlRx5msXtKMzlV7LIU7CqwXcAesODe1UAQgY3zhw3vzlBIdUrVj13wMfvqz4A5rVDHd

1910.12840v1.pdf

arxiv.org/pdf/1910.12840

2404.12096v2.pdf

arxiv.org/pdf/2404.12096

2402.05672v1.pdf

arxiv.org/pdf/2402.05672

User preference modeling in a recommender system

substack.com/inbox/post/144215856

2309.08210v1.pdf

arxiv.org/pdf/2309.08210

2312.02724.pdf

arxiv.org/pdf/2312.02724.pdf

2311.11045.pdf

arxiv.org/pdf/2311.11045.pdf

EMNLP2019-NRMS.pdf

wuch15.github.io/paper/EMNLP2019-NRMS.pdf

Learning to Learn

hbr.org/2016/03/learning-to-learn

AI Watermarking 101: Tools and Techniques

huggingface.co/blog/watermarking

A Visual Guide to Mamba and State Space Models

maartengrootendorst.substack.com/p/a-visual-guide-to-mamba-and-state?utm_source=post-email-title&publication_id=1741130&post_id=141228095&utm_campaign=email-post-title&isFreemail=true&r=12vrjf&utm_medium=email

khoahocdulieu.github.io/2021/07/16/OT1.html

2402.08268.pdf

arxiv.org/pdf/2402.08268.pdf

gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Sampling - 2308.07192.pdf

arxiv.org/pdf/2308.07192.pdf

2401.07519.pdf

arxiv.org/pdf/2401.07519.pdf

2312.00752.pdf

arxiv.org/pdf/2312.00752.pdf

State-Space Modelling

kevinkotze.github.io/ts-4-state-space/

2308.06721.pdf

arxiv.org/pdf/2308.06721.pdf

Push Notifications - What to Push, What Not to Push, and How Often

eugeneyan.com/writing/push/

Mixture of Experts Explained

huggingface.co/blog/moe

2311.12908.pdf

arxiv.org/pdf/2311.12908.pdf

Advantage Actor-Critic (A2C) - Hugging Face Deep RL Course

huggingface.co/learn/deep-rl-course/unit6/advantage-actor-critic

Practical Tips for Finetuning LLMs Using LoRA (Low-Rank Adaptation)

substack.com/inbox/post/138081202

Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News RecommendationPositive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation - 2205.06058.pdf

arxiv.org/pdf/2205.06058.pdf

News Graph: An Enhanced Knowledge Graph for News Recommendation - kars2019.pdf

www.microsoft.com/en-us/research/uploads/prod/2019/09/kars2019.pdf

The hidden forces behind China's content king Toutiao : YC Startup Library | Y Combinator

www.ycombinator.com/library/3x-the-hidden-forces-behind-china-s-content-king-toutiao

2207.12598.pdf

arxiv.org/pdf/2207.12598.pdf

Speech synthesis: A review of the best text to speech architectures with Deep Learning | AI Summer

theaisummer.com/text-to-speech/

Real-time Retrieval for Recommendations

applyingml.com/resources/real-time-recommendations/

A forty-year career.

lethain.com/forty-year-career/

Generative Modeling by Estimating Gradients of the Data Distribution | Yang Song

yang-song.net/blog/2021/score/

Guidance: a cheat code for diffusion models

sander.ai/2022/05/26/guidance.html

1907.09682.pdf

arxiv.org/pdf/1907.09682.pdf

DreamBooth

huggingface.co/docs/diffusers/training/dreambooth

The Illustrated Stable Diffusion

jalammar.github.io/illustrated-stable-diffusion/

TF Recommenders: Encode user watch history using OpenAI embeddings | Xmartlabs Blog

blog.xmartlabs.com/blog/tf-recommenders-encode-user-watch-history-using-openai-embeddings/

1302_towards_good_practices_in_self.pdf

openreview.net/pdf?id=YYvtmM9TPw

Understanding self-supervised and contrastive learning with "Bootstrap Your Own Latent" (BYOL)

imbue.com/research/2020-08-24-understanding-self-supervised-contrastive-learning/

Weights & Biases

wandb.ai/wandb_fc/Normalization-Series/reports/Instance-Normalization-in-PyTorch-With-Examples---VmlldzoxNDIyNTQx

1809.10341.pdf

arxiv.org/pdf/1809.10341.pdf