Core AI

Large Language Models

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

24,666

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 19,438 Reads 5,228

Showing 5,228 reads from curated sources

Level: All Beginner Intermediate Advanced

Newest Popular Oldest

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

MECO: A Multimodal Dataset for Emotion and Cognitive Understanding in Older Adults

arXiv:2604.03050v1 Announce Type: cross Abstract: While affective computing has advanced considerably, multimodal emotion prediction in aging populations remain

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Verbalizing LLMs' assumptions to explain and control sycophancy

arXiv:2604.03058v1 Announce Type: cross Abstract: LLMs can be socially sycophantic, affirming users when they ask questions like "am I in the wrong?" rather tha

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study

arXiv:2604.03070v1 Announce Type: cross Abstract: Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in priv

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems

arXiv:2604.03081v1 Announce Type: cross Abstract: LLM-based coding agents extend their capabilities via third-party agent skills distributed through open market

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Co-Evolution of Policy and Internal Reward for Language Agents

arXiv:2604.03098v1 Announce Type: cross Abstract: Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fu

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning

arXiv:2604.03114v1 Announce Type: cross Abstract: VLMs trained on web-scale data retain sensitive and copyrighted visual concepts that deployment may require re

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

An Independent Safety Evaluation of Kimi K2.5

arXiv:2604.03121v1 Announce Type: cross Abstract: Kimi K2.5 is an open-weight LLM that rivals closed models across coding, multimodal, and agentic benchmarks, b

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts

arXiv:2604.03127v1 Announce Type: cross Abstract: Automated annotation of pedagogical dialogue is a high-stakes task where LLMs often fail without sufficient do

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control

arXiv:2604.03147v1 Announce Type: cross Abstract: We present a method to identify a valence-arousal (VA) subspace within large language model representations. F

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation

arXiv:2604.03174v1 Announce Type: cross Abstract: Large language models (LLMs) encode vast world knowledge in their parameters, yet they remain fundamentally li

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models

arXiv:2604.03179v1 Announce Type: cross Abstract: The recent success of reinforcement learning (RL) in large reasoning models has inspired the growing adoption

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Reflective Context Learning: Studying the Optimization Primitives of Context Space

arXiv:2604.03189v1 Announce Type: cross Abstract: Generally capable agents must learn from experience in ways that generalize across tasks and environments. The

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Gradient Boosting within a Single Attention Layer

arXiv:2604.03190v1 Announce Type: cross Abstract: Transformer attention computes a single softmax-weighted average over values -- a one-pass estimate that canno

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Reliability Gated Multi-Teacher Distillation for Low Resource Abstractive Summarization

arXiv:2604.03192v1 Announce Type: cross Abstract: We study multiteacher knowledge distillation for low resource abstractive summarization from a reliability awa

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Enhancing Robustness of Federated Learning via Server Learning

arXiv:2604.03226v1 Announce Type: cross Abstract: This paper explores the use of server learning for enhancing the robustness of federated learning against mali

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

WiseMind: a knowledge-guided multi-agent framework for accurate and empathetic psychiatric diagnosis

arXiv:2502.20689v3 Announce Type: replace Abstract: Large Language Models (LLMs) offer promising opportunities to support mental healthcare workflows, yet they

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Learn to Relax with Large Language Models: Solving Constraint Optimization Problems via Bidirectional Coevolution

arXiv:2509.12643v4 Announce Type: replace Abstract: Large Language Model (LLM)-based optimization has recently shown promise for autonomous problem solving, yet

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents

arXiv:2511.02734v2 Announce Type: replace Abstract: Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlook

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics

arXiv:2601.23048v3 Announce Type: replace Abstract: Large language models now solve many benchmark math problems at near-expert levels, yet this progress has no

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

OSCAR: Orchestrated Self-verification and Cross-path Refinement

arXiv:2604.01624v2 Announce Type: replace Abstract: Diffusion language models (DLMs) expose their denoising trajectories, offering a natural handle for inferenc

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models

arXiv:2604.02315v2 Announce Type: replace Abstract: Standard LLM benchmarks evaluate the assistant turn: the model generates a response to an input, a verifier

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Efficient Causal Graph Discovery Using Large Language Models

arXiv:2402.01207v5 Announce Type: replace-cross Abstract: We propose a novel framework that leverages LLMs for full causal graph discovery. While previous LLM-b

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Expressive Prompting: Improving Emotion Intensity and Speaker Consistency in Zero-Shot TTS

arXiv:2409.18512v2 Announce Type: replace-cross Abstract: Recent advancements in speech synthesis have enabled large language model (LLM)-based systems to perfo

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization

arXiv:2410.10238v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs), such as GPT4o, have shown strong capabilities in visual reas

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Zero-shot Concept Bottleneck Models

arXiv:2502.09018v2 Announce Type: replace-cross Abstract: Concept bottleneck models (CBMs) are inherently interpretable and intervenable neural network models,

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs

arXiv:2505.20139v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) become integral to software development workflows, their ability to ge

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

FLEX: A Largescale Multimodal, Multiview Dataset for Learning Structured Representations for Fitness Action Quality Assessment

arXiv:2506.03198v4 Announce Type: replace-cross Abstract: Action Quality Assessment (AQA) -- the task of quantifying how well an action is performed -- has grea

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

SmartCLIP: Modular Vision-language Alignment with Identification Guarantees

arXiv:2507.22264v2 Announce Type: replace-cross Abstract: Contrastive Language-Image Pre-training (CLIP)~\citep{radford2021learning} has emerged as a pivotal mo

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Human Psychometric Questionnaires Mischaracterize LLM Psychology: Evidence from Generation Behavior

arXiv:2509.10078v3 Announce Type: replace-cross Abstract: Psychological profiling of large language models (LLMs) using psychometric questionnaires designed for

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

What Is The Political Content in LLMs' Pre- and Post-Training Data?

arXiv:2509.22367v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are known to generate politically biased text. Yet, it remains unclear ho

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers

arXiv:2510.00361v2 Announce Type: replace-cross Abstract: AI answer engines are a relatively new kind of information search tool: rather than returning a ranked

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference

arXiv:2510.05497v4 Announce Type: replace-cross Abstract: Large-scale Mixture of Experts (MoE) Large Language Models (LLMs) have recently become the frontier op

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions

arXiv:2510.06649v2 Announce Type: replace-cross Abstract: The Forward-Forward (FF) Algorithm is a recently proposed learning procedure for neural networks that

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

SAGA: Source Attribution of Generative AI Videos

arXiv:2511.12834v2 Announce Type: replace-cross Abstract: The proliferation of generative AI has led to hyper-realistic synthetic videos, escalating misuse risk

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment

arXiv:2511.21331v2 Announce Type: replace-cross Abstract: Learning joint representations across multiple modalities remains a central challenge in multimodal ma

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation

arXiv:2512.18809v2 Announce Type: replace-cross Abstract: Short-form video moderation increasingly needs learning pipelines that protect user privacy without pa

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

No Universal Hyperbola: A Formal Disproof of the Epistemic Trade-Off Between Certainty and Scope in Symbolic and Generative AI

arXiv:2601.08845v2 Announce Type: replace-cross Abstract: In direct response to requests for a logico-mathematical test of the conjecture, we formally disprove

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Textual Equilibrium Propagation for Deep Compound AI Systems

arXiv:2601.21064v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as part of compound AI systems that coordinate

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Equivariant Evidential Deep Learning for Interatomic Potentials

arXiv:2602.10419v2 Announce Type: replace-cross Abstract: Uncertainty quantification (UQ) is critical for assessing the reliability of machine learning interato

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking

arXiv:2602.16746v3 Announce Type: replace-cross Abstract: Grokking -- the delayed transition from memorization to generalization in small algorithmic tasks -- r

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Early-Warning Signals of Grokking via Loss-Landscape Geometry

arXiv:2602.16967v3 Announce Type: replace-cross Abstract: Grokking -- the abrupt transition from memorization to generalization after prolonged training -- has

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

The Geometry of Multi-Task Grokking: Transverse Instability, Superposition, and Weight Decay Phase Structure

arXiv:2602.18523v3 Announce Type: replace-cross Abstract: Grokking -- the abrupt transition from memorization to generalization long after near-zero training lo

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

CeRA: Overcoming the Linear Ceiling of Low-Rank Adaptation via Capacity Expansion

arXiv:2602.22911v5 Announce Type: replace-cross Abstract: Low-Rank Adaptation (LoRA) dominates parameter-efficient fine-tuning (PEFT). However, it faces a ``lin

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond

arXiv:2603.01589v2 Announce Type: replace-cross Abstract: The success of large language models (LLMs) in scientific domains has heightened safety concerns, prom

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding

arXiv:2603.03312v2 Announce Type: replace-cross Abstract: Decoding natural language from non-invasive EEG signals is a promising yet challenging task. However,

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models

arXiv:2603.17677v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) improves factual grounding by incorporating external knowledge in

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models

arXiv:2603.18545v2 Announce Type: replace-cross Abstract: Medical vision--language models (MVLMs) are increasingly used as perceptual backbones in radiology pip

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 2w ago

JointFM-0.1: A Foundation Model for Multi-Target Joint Distributional Prediction

arXiv:2603.20266v2 Announce Type: replace-cross Abstract: Despite the rapid advancements in Artificial Intelligence (AI), Stochastic Differential Equations (SDE