Social Post Explorers

community

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

gabrielchua authored a paper about 10 hours ago

Measuring What Matters: A Framework for Evaluating Safety Risks in Real-World LLM Applications

Smooke new activity 1 day ago

social-post-explorers/README:Request to post

gabrielchua authored a paper 7 days ago

RabakBench: Scaling Human Annotations to Construct Localized Multilingual Safety Benchmarks for Low-Resource Languages

View all activity

Smooke

in social-post-explorers/README 1 day ago

Request to post

➕ 2

#36 opened about 1 year ago by

Walmart-the-bag

appvoid

posted an update 21 days ago

Post

233

have you ever wanted to quickly prototype an idea with a language model but get intimidated by the whole setup? no issues! now you can try building a custom one from scratch!

beware, it might be addictive once you learn how it works: https://nohak.pythonanywhere.com/

KingNish

posted an update about 1 month ago

Post

842

What's currently the biggest gap in Open Source Datasets ??

4 replies

shivance

posted an update about 1 month ago

Post

1702

The AI Memory Layer Will Change Everything ‼️

Why do even the smartest AIs like OpenAI's o3 and GPT-4o, Google's Gemini and Anthropic's Claude forget?

In this blog we unpack this challenge and explore how building a real memory into AI will redefine personalization and agent capabilities!

https://fullstackagents.substack.com/p/forget-me-not-the-ai-memory-layer

joaogante

posted an update about 2 months ago

Post

503

Let's go! Custom generation code has landed in transformers 🚀

Have you designed a new cool KV cache? Maybe you're comparing new test-time compute ideas you've been researching? Have you found a way to do diffusion with existing models? You can now easily share your findings with the community with custom generation code, sharing the well-known generate interface 🤓

In a nutshell, we have expanded the support of custom modeling code on the Hub with *model-agnostic* custom generation code. Write for one model, reuse with any model -- hopefully, this will democratize access to new generation ideas 🫡

As a creator, you gain the ability to get your ideas in transformers with minimal effort. You'll also have access to all Hub features: a landing page for your creation, discussions, usage metrics, ... 🤓

💎 Resources 💎
- docs: https://huggingface.co/docs/transformers/generation_strategies#custom-decoding-methods
- minimal example: transformers-community/custom_generate_example
- discussion: transformers-community/support#10

anastasiastasenko

authored a paper 3 months ago

Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family

Paper • 2504.18225 • Published Apr 25 • 13

MrOvkill

posted an update 3 months ago

Post

459

Hello!

Got permission to make a quick announcement for

DigitalClockwork , and we're happy to say that easy granular GGUF quantization within Colab for GGUF is now easy-peasy!

And, no, we did not invent magic ( yet. Wait til we get us some time and funding... ) nor did we create a super-model-glue. It still needs to be a model llama.cpp supports.

https://colab.research.google.com/drive/1s60fNyiaLckl0ZscAC0vhnW7KZU0yn5n?usp=sharing

natolambert

authored a paper 3 months ago

Reinforcement Learning from Human Feedback

Paper • 2504.12501 • Published Apr 16 • 3

KennethEnevoldsen

authored a paper 3 months ago

MIEB: Massive Image Embedding Benchmark

Paper • 2504.10471 • Published Apr 14 • 18

soldni

authored a paper 3 months ago

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

Paper • 2504.07096 • Published Apr 9 • 75

nouamanetazi

authored a paper 3 months ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published Apr 7 • 192

birgermoell

authored a paper 3 months ago

Medical Reasoning in LLMs: An In-Depth Analysis of DeepSeek R1

Paper • 2504.00016 • Published Mar 27 • 1

birgermoell

authored 2 papers 4 months ago

The order in speech disorder: a scoping review of state of the art machine learning methods for clinical speech classification

Paper • 2503.04802 • Published Mar 3

Artificial Humans

Paper • 2503.16502 • Published Mar 12

ydeng9

authored a paper 4 months ago

OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement

Paper • 2503.17352 • Published Mar 21 • 24

reddgr

posted an update 4 months ago

Post

1015

The latest Space I'm working on. A UI for browsing, searching, and annotating one million chatbot chats from lmsys/lmsys-chat-1m

reddgr/chatbot-arena-dataset-wrapper

MrDragonFox

in social-post-explorers/README 4 months ago

Post button doesn't appear.

#46 opened 4 months ago by

Blazgo

kramp

in social-post-explorers/README 4 months ago

Post button doesn't appear.

#46 opened 4 months ago by

Blazgo

reddgr

posted an update 4 months ago

Post

612

"Attention Is All You Need" - Spoken Word / Rap tribute song to the popular article.

Attention Is All You Need (1706.03762)

While most music generated by transformer-based models inevitably produces a perception of inexplicable "soullessness" that is behind most of the AI hate and the discourse created around "slop," just as happens with long text produced by LLM inference, some of us enjoy the process of endless iteration and experimentation until we find something we consider unique and representative of our creative ideas and craft. The process of creating this song was not an easy one, and certainly not the random-press-button way that the anti-AI crowd tends to think about any piece of content subject to being labeled "AI-generated." The process is certainly much more complex than sending a prompt and clicking "generate," and it wouldn't fit in this post, so I just wanted to share the piece in case anyone else enjoys this kind of AI-fueled musical "extravaganza."

birgermoell

authored a paper 4 months ago

Voice Cloning for Dysarthric Speech Synthesis: Addressing Data Scarcity in Speech-Language Pathology

Paper • 2503.01266 • Published Mar 3

AI & ML interests

Recent Activity

Team members 860