Core AI

Large Language Models

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

24,516

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 19,400 Reads 5,116

Showing 5,116 reads from curated sources

Level: All Beginner Intermediate Advanced

Newest Popular Oldest

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

SleepVLM: Explainable and Rule-Grounded Sleep Staging via a Vision-Language Model

arXiv:2603.26738v1 Announce Type: cross Abstract: While automated sleep staging has achieved expert-level accuracy, its clinical adoption is hindered by a lack

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Quantum Fuzzy Sets Revisited: Density Matrices, Decoherence, and the Q-Matrix Framework

arXiv:2603.26739v1 Announce Type: cross Abstract: In 2006 we proposed Quantum Fuzzy Sets, observing that states of a quantum register could serve as characteris

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Language-Conditioned World Modeling for Visual Navigation

arXiv:2603.26741v1 Announce Type: cross Abstract: We study language-conditioned visual navigation (LCVN), in which an embodied agent is asked to follow a natura

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract)

arXiv:2603.26743v1 Announce Type: cross Abstract: Dynamic head pruning in Vision Transformers (ViTs) improves efficiency by removing redundant attention heads,

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Edge Reliability Gap in Vision-Language Models: Quantifying Failure Modes of Compressed VLMs Under Visual Corruption

arXiv:2603.26769v1 Announce Type: cross Abstract: The rapid compression of large vision-language models (VLMs) for edge deployment raises an underexplored quest

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

From Content to Audience: A Multimodal Annotation Framework for Broadcast Television Analytics

arXiv:2603.26772v1 Announce Type: cross Abstract: Automated semantic annotation of broadcast television content presents distinctive challenges, combining struc

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Learning to Select Visual In-Context Demonstrations

arXiv:2603.26775v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) adapt to visual tasks via in-context learning (ICL), which relies hea

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

TED: Training-Free Experience Distillation for Multimodal Reasoning

arXiv:2603.26778v1 Announce Type: cross Abstract: Knowledge distillation is typically realized by transferring a teacher model's knowledge into a student's para

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Limits of Imagery Reasoning in Frontier LLM Models

arXiv:2603.26779v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, yet they struggle with spati

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Can We Change the Stroke Size for Easier Diffusion?

arXiv:2603.26783v1 Announce Type: cross Abstract: Diffusion models can be challenged in the low signal-to-noise regime, where they have to make pixel-level pred

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

A Step Toward Federated Pretraining of Multimodal Large Language Models

arXiv:2603.26786v1 Announce Type: cross Abstract: The rapid evolution of Multimodal Large Language Models (MLLMs) is bottlenecked by the saturation of high-qual

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

CRISP: Characterizing Relative Impact of Scholarly Publications

arXiv:2603.26791v1 Announce Type: cross Abstract: Assessing a cited paper's impact is typically done by analyzing its citation context in isolation within the c

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

HASS: Hierarchical Simulation of Logopenic Aphasic Speech for Scalable PPA Detection

arXiv:2603.26795v1 Announce Type: cross Abstract: Building a diagnosis model for primary progressive aphasia (PPA) has been challenging due to the data scarcity

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints

arXiv:2603.26796v1 Announce Type: cross Abstract: We study the problem of routing queries to large language models (LLMs) under cost, GPU resources, and concurr

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings

arXiv:2603.26798v1 Announce Type: cross Abstract: Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a sh

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Sparse-by-Design Cross-Modality Prediction: L0-Gated Representations for Reliable and Efficient Learning

arXiv:2603.26801v1 Announce Type: cross Abstract: Predictive systems increasingly span heterogeneous modalities such as graphs, language, and tabular records, b

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

GroupRAG: Cognitively Inspired Group-Aware Retrieval and Reasoning via Knowledge-Driven Problem Structuring

arXiv:2603.26807v1 Announce Type: cross Abstract: The performance of language models is commonly limited by insufficient knowledge and constrained reasoning. Pr

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Resolving the Robustness-Precision Trade-off in Financial RAG through Hybrid Document-Routed Retrieval

arXiv:2603.26815v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems for financial document question answering typically follow a chun

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

PiCSRL: Physics-Informed Contextual Spectral Reinforcement Learning

arXiv:2603.26816v1 Announce Type: cross Abstract: High-dimensional low-sample-size (HDLSS) datasets constrain reliable environmental model development, where la

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Epileptic Seizure Prediction Using Patient-Adaptive Transformer Networks

arXiv:2603.26821v1 Announce Type: cross Abstract: Epileptic seizure prediction from electroencephalographic (EEG) recordings remains challenging due to strong i

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Throughput Optimization as a Strategic Lever in Large-Scale AI Systems: Evidence from Dataloader and Memory Profiling Innovations

arXiv:2603.26823v1 Announce Type: cross Abstract: The development of large-scale foundation models, particularly Large Language Models (LLMs), is constrained by

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Squish and Release: Exposing Hidden Hallucinations by Making Them Surface as Safety Signals

arXiv:2603.26829v1 Announce Type: cross Abstract: Language models detect false premises when asked directly but absorb them under conversational pressure, produ

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Hybrid Diffusion Model for Breast Ultrasound Image Augmentation

arXiv:2603.26834v1 Announce Type: cross Abstract: We propose a hybrid diffusion-based augmentation framework to overcome the critical challenge of ultrasound da

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Dual-branch Graph Domain Adaptation for Cross-scenario Multi-modal Emotion Recognition

arXiv:2603.26840v1 Announce Type: cross Abstract: Multimodal Emotion Recognition in Conversations (MERC) aims to predict speakers' emotional states in multi-tur

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection

arXiv:2603.26842v1 Announce Type: cross Abstract: Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

GISclaw: An Open-Source LLM-Powered Agent System for Full-Stack Geospatial Analysis

arXiv:2603.26845v1 Announce Type: cross Abstract: The convergence of Large Language Models (LLMs) and Geographic Information Science has opened new avenues for

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry

arXiv:2603.26846v1 Announce Type: cross Abstract: As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes crit

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection

arXiv:2603.26856v1 Announce Type: cross Abstract: The rapid advancement of generative models has enabled highly realistic audio deepfakes, yet current detectors

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Strategic Candidacy in Generative AI Arenas

arXiv:2603.26891v1 Announce Type: cross Abstract: AI arenas, which rank generative models from pairwise preferences of users, are a popular method for measuring

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation

arXiv:2603.26898v1 Announce Type: cross Abstract: Political scientists are rapidly adopting large language models (LLMs) for text annotation, yet the sensitivit

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Are LLMs Good For Quantum Software, Architecture, and System Design?

arXiv:2603.26904v1 Announce Type: cross Abstract: Quantum computers promise massive computational speedup for problems in many critical domains, such as physics

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Mimetic Alignment with ASPECT: Evaluation of AI-inferred Personal Profiles

arXiv:2603.26922v1 Announce Type: cross Abstract: AI agents that communicate on behalf of individuals need to capture how each person actually communicates, yet

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

AutoSiMP: Autonomous Topology Optimization from Natural Language via LLM-Driven Problem Configuration and Adaptive Solver Control

arXiv:2603.27000v1 Announce Type: cross Abstract: We present AutoSiMP, an autonomous pipeline that transforms a natural-language structural problem description

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

TAPS: Task Aware Proposal Distributions for Speculative Sampling

arXiv:2603.27027v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive generation by letting a lightweight draft model propose future

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching

arXiv:2603.27044v1 Announce Type: cross Abstract: Deep Reinforcement Learning (DRL) is widely recognized as sample-inefficient, a limitation attributable in par

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Persona-Based Simulation of Human Opinion at Population Scale

arXiv:2603.27056v1 Announce Type: cross Abstract: What does it mean to model a person, not merely to predict isolated responses, preferences, or behaviors, but

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Debiasing Large Language Models toward Social Factors in Online Behavior Analytics through Prompt Knowledge Tuning

arXiv:2603.27057v1 Announce Type: cross Abstract: Attribution theory explains how individuals interpret and attribute others' behavior in a social context by em

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding

arXiv:2603.27064v1 Announce Type: cross Abstract: Understanding charts requires models to jointly reason over geometric visual patterns, structured numerical da

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Voice-based debate with an AI adversary is associated with increased divergent ideation

arXiv:2603.27073v1 Announce Type: cross Abstract: Concerns that interacting with generative AI homogenizes human cognition are largely based on evidence from te

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Sovereign Context Protocol: An Open Attribution Layer for Human-Generated Content in the Age of Large Language Models

arXiv:2603.27094v1 Announce Type: cross Abstract: Large Language Models (LLMs) consume vast quantities of human-generated content for both training and real-tim

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Bayesian-Symbolic Integration for Uncertainty-Aware Parking Prediction

arXiv:2603.27119v1 Announce Type: cross Abstract: Accurate parking availability prediction is critical for intelligent transportation systems, but real-world de

ArXiv cs.AI 🧠 Large Language Models 📄 Paper 3w ago

A Tight Expressivity Hierarchy for GNN-Based Entity Resolution in Master Data Management

arXiv:2603.27154v1 Announce Type: cross Abstract: Entity resolution -- identifying database records that refer to the same real-world entity -- is naturally mod

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

GSR-GNN: Training Acceleration and Memory-Saving Framework of Deep GNNs on Circuit Graph

arXiv:2603.27156v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) show strong promise for circuit analysis, but scaling to modern large-scale circu

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

EuraGovExam: A Multilingual Multimodal Benchmark from Real-World Civil Service Exams

arXiv:2603.27223v1 Announce Type: cross Abstract: We present EuraGovExam, a multilingual and multimodal benchmark sourced from real-world civil service examinat

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection

arXiv:2603.27240v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved impressive performance across multimodal understanding and

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Zero-shot Vision-Language Reranking for Cross-View Geolocalization

arXiv:2603.27251v1 Announce Type: cross Abstract: Cross-view geolocalization (CVGL) systems, while effective at retrieving a list of relevant candidates (high R

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

Amalgam: Hybrid LLM-PGM Synthesis Algorithm for Accuracy and Realism

arXiv:2603.27254v1 Announce Type: cross Abstract: To generate synthetic datasets, e.g., in domains such as healthcare, the literature proposes approaches of two

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 3w ago

From Foundation ECG Models to NISQ Learners: Distilling ECGFounder into a VQC Student

arXiv:2603.27269v1 Announce Type: cross Abstract: Foundation models have recently improved electrocardiogram (ECG) representation learning, but their deployment