AI Coffee Break with Letitia
AI Coffee Break with Letitia 26 folgen Nov 12, 2026
AI Coffee Break with Letitia is a short-form podcast that explains recent developments in artificial intelligence in an accessible, lighthearted way. Episodes cover topics such as large language models, text-to-image generation, natural language processing, and computer vision. The show is aimed at listeners who want bite-sized technical updates without overly academic jargon. It also points listeners toward related community links and resources.
Folgen
MAMBA and State Space Models explained | SSM explained
Leaking training data from GPT-2. How is this possible?
Genie explained 🧞 Generative Interactive Environments paper explained
NVIDIA Jarvis (now NVIDIA Riva) meets Ms. Coffee Bean
How OpenAI made o1 "think" – Here is what we think and already know about o1 reinforcement learning
The curse of dimensionality. Or is it a blessing?
What nobody tells you about MULTIMODAL Machine Learning! 🙊 THE definition.
PCA explained with intuition, a little math and code
![Graph Language Models EXPLAINED in 5 Minutes! [Author explanation 🔴 at ACL 2024]](https://megaphone.imgix.net/podcasts/8a19733a-cc94-11f1-9326-3b660b2cf165/image/eb181587f52d4aa449224330586ce999.jpg?ixlib=rails-4.3.1&max-w=3000&max-h=3000&fit=crop&auto=format,compress)
Graph Language Models EXPLAINED in 5 Minutes! [Author explanation 🔴 at ACL 2024]
DALL-E 3 is better at following Text Prompts! Here is why. — DALL-E 3 explained
Direct Preference Optimization: Your Language Model is Secretly a Reward Model | DPO paper explained
GANs explained | Generative Adversarial Networks video with showcase!
Data-efficient Image Transformers EXPLAINED! Facebook AI's DeiT paper
GPT2 wrote this 1000 subscribers special!
Math Anxiety? and what it has to do with AI – 🔴at #HLF24 with Prof. Yael Tauman Kalai
Can language models understand? Bender and Koller argument.
REPA Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You ...
The ultimate intro to Graph Neural Networks. Maybe.
LLM Lecture: A Deep Dive into Transformers, Prompts, and Human Feedback
Training large language models to reason in a continuous latent space – COCONUT Paper explained
BERTology meets Biology | Solving biological problems with Transformers
s1: Simple test-time scaling: Just “wait…” + 1,000 training examples? | PAPER EXPLAINED
Adversarial Machine Learning explained! | With examples.
Sparse LLMs at inference: 6x faster transformers! | DEJAVU paper explained
4-Bit Training for Billion-Parameter LLMs? Yes, Really.
![[RANT] Adversarial attack on OpenAI’s CLIP? Are we the fools or the foolers?](https://megaphone.imgix.net/podcasts/c0979dca-cc98-11f1-8d32-43c0829a13c0/image/c53feb3bee143ced01e5b68f8832687c.jpg?ixlib=rails-4.3.1&max-w=3000&max-h=3000&fit=crop&auto=format,compress)
[RANT] Adversarial attack on OpenAI’s CLIP? Are we the fools or the foolers?
GPT-3 explained with examples. Possibilities, and implications.
Stealing Part of a Production LLM | API protects LLMs no more
Token-Efficient Long Video Understanding for Multimodal LLMs | Paper explained
Pre-training of BERT-based Transformer architectures explained – language and vision!
AlphaEvolve: Using LLMs to solve Scientific and Engineering Challenges | AlphaEvolve explained
FunSearch from DeepMind explained | LLM hallucinations discover new math solutions!?
Transformer combining Vision and Language? ViLBERT - NLP meets Computer Vision
GaLore EXPLAINED: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Supercharging RAG with Generative Feedback Loops from Weaviate
Shapley Values Explained | Interpretability for AI models, even LLMs!
OpenAI's DALL-E explained. How GPT-3 creates images from descriptions.
![[Own work] On Measuring Faithfulness or Self-consistency of Natural Language Explanations](https://megaphone.imgix.net/podcasts/3f9ae280-cc9e-11f1-8ce0-a76051e8803b/image/22ebc5014d9640e84df319aced987a4f.jpg?ixlib=rails-4.3.1&max-w=3000&max-h=3000&fit=crop&auto=format,compress)
[Own work] On Measuring Faithfulness or Self-consistency of Natural Language Explanations
Greedy? Min-p? Beam Search? How LLMs Actually Pick Words – Decoding Strategies Explained
Preparing for Virtual Conferences – 7 Tips for recording a good conference talk
Empfohlen
Blautöne – Podcast der AfD-Fraktion im Bundestag
Audio Porno – Erotische Hörspiele & Kopfkino
unter den linden - Podcast
Nicos Weg – German course A1 | Videos | DW Learn German
Langsam Deutsch - Deutsch lernen
Learn German with Thomas
Deutsch mit Rieke
5 Minuten Märchen - Frederik der kleine Fuchs - kurze Hörspiele für kleine Abenteurer
Machtwechsel
Das Wichtigste heute Morgen
Learn German, one step at a time
Easy German Dialogues - Deutsch lernen mit Dan
