How do we define creativity in LLMs?
An ACL 2026 paper that measures LLM creativity with two metrics: divergent creativity (exploring different ideas) and convergent creativity (executing an idea well).
Series
AI explained
Short notes from the AI explained series: LLMs, agents, multimodal models, and the ideas that made the field move.
Reducing the Reversal Curse?
A follow-up on the reversal curse and how reverse training may help language models handle reversed relations.
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
Apple's MM1 paper distilled into practical lessons on data mixtures, image resolution, synthetic data, and multimodal architecture.
Chain-of-Thought: Do LLMs Need Prompts to Think?
A look at CoT decoding, an approach that explores alternative decoding paths to reveal reasoning without explicit chain-of-thought prompts.
Efficient Exploration for LLMs
A look at active exploration for RLHF-style feedback collection and why choosing better questions can improve LLM training efficiency.
An Interactive Agent Foundation Model
A short note on embodied agent foundation models, multimodal perception, planning, and what scale could mean for agent capabilities.
Evaluating Multi-modal Large Language Models
A short overview of how a large benchmark evaluates multimodal language models across generalization, trustworthiness, and causality.
Self-Rewarding LLMs
An explanation of self-rewarding language models, where models generate prompts, judge responses, and iteratively train from their own feedback.
Towards Conversational Diagnostic AI
A short explainer on AMIE, Google's diagnostic dialogue system for medical interviews and clinical reasoning.
AI Content Detectors Are Not Reliable
A follow-up note on why AI text detectors can fail, from perplexity and burstiness limits to false positives and bias against non-native writers.
Language Models May Not Be Few-Shot Anymore
A look at task contamination and why benchmark gains in zero-shot and few-shot LLM evaluation may be misleading.
What Could LLM Do with Your Smartphone?
A look at AppAgent, a multimodal agent that learns to operate smartphone apps through tapping, swiping, screenshots, and memory.
How Susceptible Are LLMs to Persuasive Misinformation?
A study of how persuasive misinformation can change LLM responses, from rejection and uncertainty to acceptance.
Who Would Learn Faster? A Chicken or Vision Transformer?
A NeurIPS study comparing newborn chicks and Vision Transformers on view-invariant object recognition from limited visual experience.
Mamba: Selective State Space Model That Outperformed Transformers
An introduction to Mamba, selective state space models, and why linear-time sequence modeling is exciting for language models.
Scalable Extraction of Training Data from Production Language Models
A look at how researchers extracted memorized training examples from ChatGPT and what that means for privacy and copyright.
Removing Irrelevant Text for Better Answer Generation
A short explanation of System 2 Attention, a method for regenerating context before answering to reduce distraction and sycophancy.
The Reversal Curse
An explanation of why LLMs can learn A equals B but fail to answer the reverse relation B equals A.
How to Detect AI-Written Texts?
A practical explanation of Ghostbuster, perplexity features, and why AI text detection remains difficult.
Three ML Blogs Worth Reading
A short recommendation list of high-quality machine learning blogs by Lilian Weng, Eugene Yan, and Chip Huyen.
Implicit Reasoning in LLMs
An explanation of implicit chain-of-thought reasoning through hidden states and knowledge distillation.
The Technology Behind Illusion-Like Generated Images
A quick explanation of ControlNet and how diffusion models can generate QR-code and illusion-like images.
Large Language Models Understand and Can Be Enhanced by Emotional Stimuli
A short explainer on EmotionPrompt and how emotional stimuli can affect LLM task performance.
Enhancing LLMs Reasoning Abilities with Step-Back Prompting
An explanation of step-back prompting and how abstraction can improve LLM reasoning on complex tasks.
Controlling DALL-E 3 Output with Seeds
A short practical note on using random seeds with DALL-E 3 to make image generation more reproducible and controllable.
What Are LLM Agents?
A practical explanation of LLM chains, agents, tools, memory, and why autonomous planning changes how LLM apps behave.
Are LLMs the Future of Image Generation?
A look at why visual tokenizers like MAGVIT-v2 make language-model-based image and video generation more competitive with diffusion models.
Summarize a Video with LLM: a Tutorial
A short tutorial on downloading YouTube transcripts, restoring punctuation, and using the OpenAI API to summarize or query a video.
Claude Doesn't Get the Attention It Deserves
A short note on Claude's long-context advantage, why full-document context matters, and Anthropic's analysis of prompting strategies.
RAIN: Aligning LLMs Without Finetuning
A short note on RAIN, a rewindable inference technique for making pretrained LLM outputs more helpful and harmless without weight updates.
Transform Your CV into an Interactive Chatbot with LLM, FAISS and LangChain
A step-by-step tutorial for building an interactive CV chatbot with TRURL, Hugging Face embeddings, FAISS, and LangChain.
Why SentenceBERT Became Useful Again in LLM Pipelines
A short note on why LangChain, FAISS, and RAG made smaller embedding models like SentenceBERT important again.
Detect Waste: Project Summary
A wrap-up of the 5-month non-profit project, roles, outputs, arXiv paper, repository, and blog series.
By Agnieszka Mikołajczyk · DetectWaste Project
Detect Waste: Pseudo-labeling for Waste Classification
Using pseudo-labeling and OpenLitterMap data to expand a waste classifier beyond the labeled dataset.
By Sylwia Majchrowska, Agnieszka Mikołajczyk · DetectWaste Project
Detect Waste: Comparing Approaches on Extended TACO
EfficientDet results on 7-class and one-class waste detection, plus the motivation for separating detection and classification.
By Sylwia Majchrowska, Agnieszka Mikołajczyk · DetectWaste Project
Detect Waste: TACO Dataset Analysis
Exploratory analysis of extended TACO annotations, category mapping, bounding boxes, and dataset imbalance.
By Maria Ferlin, Agnieszka Mikołajczyk · DetectWaste Project
Detect Waste: Project Introduction
How the Detect Waste story began: motivation, recycling rules, waste categories, and the TACO dataset.
By Maria Ferlin, Agnieszka Mikołajczyk · DetectWaste Project
Sound-Based Bird Classification
How a WiMLDS Trójmiasto team used deep learning, acoustics, and ornithology to classify bird species from sound.
By Agnieszka Mikołajczyk, Magdalena Kortas · Bird Song Classification