Core AI

Large Language Models

Deep dives into GPT, Claude, Gemini, Llama and the transformers powering modern AI

24,943

lessons

Skills in this topic

5 skills — Sign in to track your progress

View full skill map →

LLM Foundations

Explain how transformers generate text

Write zero-shot and few-shot prompts

LLM Engineering

Call LLM APIs with function/tool use

Fine-tuning LLMs

Prepare fine-tuning datasets

Multimodal LLMs

Use GPT-4V / Claude Vision for image understanding

Videos 19,459 Reads 5,484

Showing 5,484 reads from curated sources

Level: All Beginner Intermediate Advanced

Newest Popular Oldest

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Consequentialist Objectives and Catastrophe

arXiv:2603.15017v2 Announce Type: replace Abstract: Because human preferences are too complex to codify, AIs operate with misspecified objectives. Optimizing su

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Characterizing Linear Alignment Across Language Models

arXiv:2603.18908v3 Announce Type: replace Abstract: Language models increasingly appear to learn similar representations, despite differences in training object

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Man and machine: artificial intelligence and judicial decision making

arXiv:2603.19042v2 Announce Type: replace Abstract: The integration of artificial intelligence (AI) technologies into judicial decision-making, particularly in

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers

arXiv:2401.11605v2 Announce Type: replace-cross Abstract: We present the Hourglass Diffusion Transformer (HDiT), an image generative model that exhibits linear

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

The Future of AI-Driven Software Engineering

arXiv:2406.07737v2 Announce Type: replace-cross Abstract: A paradigm shift is underway in Software Engineering, with AI systems such as LLMs playing an increasi

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

CodeRefine: A Pipeline for Enhancing LLM-Generated Code Implementations of Research Papers

arXiv:2408.13366v2 Announce Type: replace-cross Abstract: This paper presents CodeRefine, a novel framework for automatically transforming research paper method

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts

arXiv:2410.10700v3 Announce Type: replace-cross Abstract: Safety concerns in large language models (LLMs) have gained significant attention due to their exposur

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future Trends

arXiv:2410.15281v5 Announce Type: replace-cross Abstract: With the broader adoption and highly successful development of Large Language Models (LLMs), there has

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

The Limits of Inference Scaling Through Resampling

arXiv:2411.17501v3 Announce Type: replace-cross Abstract: Recent research has generated hope that inference scaling, such as resampling solutions until they pas

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Physics-Informed Evolution: An Evolutionary Framework for Solving Quantum Control Problems Involving the Schr\"odinger Equation

arXiv:2502.05228v3 Announce Type: replace-cross Abstract: Physics-informed Neural Networks (PINNs) show that embedding physical laws directly into the learning

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition

arXiv:2505.24840v2 Announce Type: replace-cross Abstract: This paper reveals that many open-source large language models (LLMs) lack hierarchical knowledge abou

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents

arXiv:2506.12104v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Instruction Following by Principled Boosting Attention of Large Language Models

arXiv:2506.13734v3 Announce Type: replace-cross Abstract: Large language models' behavior is often shaped by instructions such as system prompts, refusal bounda

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

BMFM-RNA: whole-cell expression decoding improves transcriptomic foundation models

arXiv:2506.14861v2 Announce Type: replace-cross Abstract: Transcriptomic foundation models pretrained with masked language modeling can achieve low pretraining

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Predicting Human Mobility during Extreme Events via LLM-Enhanced Cross-City Learning

arXiv:2507.19737v2 Announce Type: replace-cross Abstract: The vulnerability of cities has increased with urbanization and climate change, making it more importa

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

CodeNER: Code Prompting for Named Entity Recognition

arXiv:2507.20423v4 Announce Type: replace-cross Abstract: Recent studies have explored various approaches for treating candidate named entity spans as both sour

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation

arXiv:2508.09223v2 Announce Type: replace-cross Abstract: Test-time adaptation allows pretrained models to adjust to incoming data streams, addressing distribut

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Mapping the Course for Prompt-based Structured Prediction

arXiv:2508.15090v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated strong performance in a wide-range of language tasks wi

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

The Information Dynamics of Generative Diffusion

arXiv:2508.19897v4 Announce Type: replace-cross Abstract: Generative diffusion models have emerged as a powerful class of models in machine learning, yet a unif

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

End-to-End Low-Level Neural Control of an Industrial-Grade 6D Magnetic Levitation System

arXiv:2509.01388v2 Announce Type: replace-cross Abstract: Magnetic levitation is poised to revolutionize industrial automation by integrating flexible in-machin

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

GeoResponder: Towards Building Geospatial LLMs for Time-Critical Disaster Response

arXiv:2509.19354v3 Announce Type: replace-cross Abstract: LLMs excel at linguistic tasks but lack the inner geospatial capabilities needed for time-critical dis

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models

arXiv:2509.24296v2 Announce Type: replace-cross Abstract: The rapid advancement of Diffusion Large Language Models (dLLMs) introduces unprecedented vulnerabilit

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation

arXiv:2510.24821v3 Announce Type: replace-cross Abstract: We propose Ming-Flash-Omni, an upgraded version of Ming-Omni, built upon a sparser Mixture-of-Experts

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Foundry: Distilling 3D Foundation Models for the Edge

arXiv:2511.20721v2 Announce Type: replace-cross Abstract: Foundation models pre-trained with self-supervised learning (SSL) on large-scale datasets have become

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

A cross-species neural foundation model for end-to-end speech decoding

arXiv:2511.21740v4 Announce Type: replace-cross Abstract: Speech brain-computer interfaces (BCIs) aim to restore communication for people with paralysis by tran

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Epistemic Bias Injection: Biasing LLMs via Selective Context Retrieval

arXiv:2512.00804v2 Announce Type: replace-cross Abstract: When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-a

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

SWAA: Sliding Window Attention Adaptation for Efficient and Quality Preserving Long Context Processing

arXiv:2512.10411v5 Announce Type: replace-cross Abstract: The quadratic complexity of self attention in Transformer based LLMs renders long context inference pr

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

arXiv:2512.14698v2 Announce Type: replace-cross Abstract: This paper does not introduce a novel method but instead establishes a straightforward, incremental, y

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Context Matters: Peer-Aware Student Behavioral Engagement Measurement via VLM Action Parsing and LLM Sequence Classification

arXiv:2601.06394v2 Announce Type: replace-cross Abstract: Understanding student behavior in the classroom is essential to improve both pedagogical quality and s

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts

arXiv:2601.08881v2 Announce Type: replace-cross Abstract: Unified image generation and editing models suffer from severe task interference in dense diffusion tr

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Information Access of the Oppressed: A Problem-Posing Framework for Envisioning Emancipatory Information Access Platforms

arXiv:2601.09600v2 Announce Type: replace-cross Abstract: Online information access (IA) platforms are targets of authoritarian capture. We explore the question

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Impact of AI Search Summaries on Website Traffic: Evidence from Google AI Overviews and Wikipedia

arXiv:2602.18455v2 Announce Type: replace-cross Abstract: Search engines increasingly display LLM-generated answers shown above organic links, shifting search f

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis

arXiv:2602.20951v2 Announce Type: replace-cross Abstract: Despite recent advances in diffusion models, AI generated images still often contain visual artifacts

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails

arXiv:2603.03099v3 Announce Type: replace-cross Abstract: Despite Adam demonstrating faster empirical convergence than SGD in many applications, much of the exi

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Graph-of-Mark: Promote Spatial Reasoning in Multimodal Language Models with Graph-Based Visual Prompting

arXiv:2603.06663v2 Announce Type: replace-cross Abstract: Recent advances in training-free visual prompting, such as Set-of-Mark, have emerged as a promising di

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Evaluation format, not model capability, drives triage failure in the assessment of consumer health AI

arXiv:2603.11413v3 Announce Type: replace-cross Abstract: Ramaswamy et al. reported in Nature Medicine that ChatGPT Health under-triages 51.6% of emergencies, c

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

UtilityMax Prompting: A Formal Framework for Multi-Objective Large Language Model Optimization

arXiv:2603.11583v2 Announce Type: replace-cross Abstract: The success of a Large Language Model (LLM) task depends heavily on its prompt. Most use-cases specify

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

SemBench: A Universal Semantic Framework for LLM Evaluation

arXiv:2603.11687v2 Announce Type: replace-cross Abstract: Recent progress in Natural Language Processing (NLP) has been driven by the emergence of Large Languag

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

Seeking Physics in Diffusion Noise

arXiv:2603.14294v2 Announce Type: replace-cross Abstract: Do video diffusion models encode signals predictive of physical plausibility? We probe intermediate de

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

360{\deg} Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method

arXiv:2603.16179v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have shown impressive abilities in understanding and reasonin

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making

arXiv:2603.16673v2 Announce Type: replace-cross Abstract: Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 1mo ago

P^2O: Joint Policy and Prompt Optimization

arXiv:2603.21877v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing

Dev.to AI 🧠 Large Language Models ⚡ AI Lesson 1mo ago

Anthropic wins injunction against Trump administration over Defense Department saga

The recent ruling in favor of Anthropic, granting an injunction against the Trump administration, is a significant development in the ongoing saga between the A

Dev.to AI 🧠 Large Language Models ⚡ AI Lesson 1mo ago

Gemini vs ChatGPT in 2026: Real Comparison by Task

Originally published at https://konabayev.com/blog/gemini-vs-chatgpt/ Direct Answer: Gemini vs ChatGPT for Marketers at a Glance For most marketers, ChatGPT is

Dev.to AI 🧠 Large Language Models ⚡ AI Lesson 1mo ago

Kling 3.0 API Tutorial: Generate 4K AI Videos for Pennies (Not $1,400/Month)

Kling 3.0 API Tutorial: Generate 4K AI Videos for Pennies (Not $1,400/Month) Kling 3.0 just dropped, and it's arguably the most capable AI video generation mode

Dev.to AI 🧠 Large Language Models ⚡ AI Lesson 1mo ago

Perplexity vs ChatGPT in 2026: Which AI Search Tool Wins?

Originally published at https://konabayev.com/blog/perplexity-vs-chatgpt/ Direct Answer: Perplexity AI vs ChatGPT at a Glance Perplexity AI is an AI-powered sea

TechCrunch AI 🧠 Large Language Models ⚡ AI Lesson 1mo ago

Anthropic wins injunction against Trump administration over Defense Department saga

A federal judge has ordered that the Trump administration rescind recent restrictions it placed on the AI company.

Siri Reboot, Sora Shutdown, Meta And Google Lose Mental Health Lawsuits

Forbes Innovation 🧠 Large Language Models ⚡ AI Lesson 1mo ago

Siri Reboot, Sora Shutdown, Meta And Google Lose Mental Health Lawsuits

OpenAI shuts down Sora, Meta and Google face a landmark jury verdict, Epic Games cuts 1,000 jobs, Apple retools Siri, and Meta scales back metaverse spending am