Core AI

Large Language Models

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

24,701

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 19,444 Reads 5,257

Showing 5,257 reads from curated sources

Level: All Beginner Intermediate Advanced

Newest Popular Oldest

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

Neural Global Optimization via Iterative Refinement from Noisy Samples

arXiv:2604.03614v1 Announce Type: cross Abstract: Global optimization of black-box functions from noisy samples is a fundamental challenge in machine learning a

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

Toward Executable Repository-Level Code Generation via Environment Alignment

arXiv:2604.03622v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved strong performance on code generation, but existing methods still s

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

Persistent Cross-Attempt State Optimization for Repository-Level Code Generation

arXiv:2604.03632v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved substantial progress in repository-level code generation. However,

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

A Generative Foundation Model for Multimodal Histopathology

arXiv:2604.03635v1 Announce Type: cross Abstract: Accurate diagnosis and treatment of complex diseases require integrating histological, molecular, and clinical

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

Delayed Homomorphic Reinforcement Learning for Environments with Delayed Feedback

arXiv:2604.03641v1 Announce Type: cross Abstract: Reinforcement learning in real-world systems is often accompanied by delayed feedback, which breaks the Markov

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

Stabilizing Unsupervised Self-Evolution of MLLMs via Continuous Softened Retracing reSampling

arXiv:2604.03647v1 Announce Type: cross Abstract: In the unsupervised self-evolution of Multimodal Large Language Models, the quality of feedback signals during

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

AI Appeals Processor: A Deep Learning Approach to Automated Classification of Citizen Appeals in Government Services

arXiv:2604.03672v1 Announce Type: cross Abstract: Government agencies worldwide face growing volumes of citizen appeals, with electronic submissions increasing

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

Unlocking Prompt Infilling Capability for Diffusion Language Models

arXiv:2604.03677v1 Announce Type: cross Abstract: Masked diffusion language models (dLMs) generate text through bidirectional denoising, yet this capability rem

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

LightThinker++: From Reasoning Compression to Memory Management

arXiv:2604.03679v1 Announce Type: cross Abstract: Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognit

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

Fusion and Alignment Enhancement with Large Language Models for Tail-item Sequential Recommendation

arXiv:2604.03688v1 Announce Type: cross Abstract: Sequential Recommendation (SR) learns user preferences from their historical interaction sequences and provide

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

CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering

arXiv:2604.03750v1 Announce Type: cross Abstract: Reverse engineering (RE) is central to software security, particularly for cryptographic programs that handle

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

Testing the Limits of Truth Directions in LLMs

arXiv:2604.03754v1 Announce Type: cross Abstract: Large language models (LLMs) have been shown to encode truth of statements in their activation space along a l

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

Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News

arXiv:2604.03755v1 Announce Type: cross Abstract: Can humans tell whether a news article was written by a person or a large language model (LLM)? We investigate

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

Automated Attention Pattern Discovery at Scale in Large Language Models

arXiv:2604.03764v1 Announce Type: cross Abstract: Large language models have found success by scaling up capabilities to work in general settings. The same can

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

When Does Multimodal AI Help? Diagnostic Complementarity of Vision-Language Models and CNNs for Spectrum Management in Satellite-Terrestrial Networks

arXiv:2604.03774v1 Announce Type: cross Abstract: The adoption of vision-language models (VLMs) for wireless network management is accelerating, yet no systemat

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

CountsDiff: A Diffusion Model on the Natural Numbers for Generation and Imputation of Count-Based Data

arXiv:2604.03779v1 Announce Type: cross Abstract: Diffusion models have excelled at generative tasks for both continuous and token-based domains, but their appl

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

Automated Conjecture Resolution with Formal Verification

arXiv:2604.03789v1 Announce Type: cross Abstract: Recent advances in large language models have significantly improved their ability to perform mathematical rea

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

Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus

arXiv:2604.03809v1 Announce Type: cross Abstract: Multi-agent LLM committees replicate the same model under different role prompts and aggregate outputs by majo

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

k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS The Expressive Power of GraphGPS

arXiv:2604.03815v1 Announce Type: cross Abstract: Graph transformers have shown promise in overcoming limitations of traditional graph neural networks, such as

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

When Models Know More Than They Say: Probing Analogical Reasoning in LLMs

arXiv:2604.03877v1 Announce Type: cross Abstract: Analogical reasoning is a core cognitive faculty essential for narrative understanding. While LLMs perform wel

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

Enhancing behavioral nudges with large language model-based iterative personalization: A field experiment on electricity and hot-water conservation

arXiv:2604.03881v1 Announce Type: cross Abstract: Nudging is widely used to promote behavioral change, but its effectiveness is often limited when recipients mu

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

I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation

arXiv:2604.03904v1 Announce Type: cross Abstract: Large language models (LLMs) frequently produce confident but incorrect answers, partly because common binary

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

Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework

arXiv:2604.03912v1 Announce Type: cross Abstract: As cloud environments become increasingly complex, cybersecurity and forensic investigations must evolve to me

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

Interpreting Video Representations with Spatio-Temporal Sparse Autoencoders

arXiv:2604.03919v1 Announce Type: cross Abstract: We present the first systematic study of Sparse Autoencoders (SAEs) on video representations. Standard SAEs de

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

Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation

arXiv:2604.03924v1 Announce Type: cross Abstract: Goal-oriented conversational systems require making sequential decisions under uncertainty about the user's in

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

AdaptFuse: Training-Free Sequential Preference Learning via Externalized Bayesian Inference

arXiv:2604.03925v1 Announce Type: cross Abstract: Large language models struggle to accumulate evidence across multiple rounds of user interaction, failing to u

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

Diagonal-Tiled Mixed-Precision Attention for Efficient Low-Bit MXFP Inference

arXiv:2604.03950v1 Announce Type: cross Abstract: Transformer-based large language models (LLMs) have demonstrated remarkable performance across a wide range of

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

VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models

arXiv:2604.03956v1 Announce Type: cross Abstract: Vision-language-action (VLA) models are emerging as embodied foundation models for robotic manipulation, but t

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

Gram-Anchored Prompt Learning for Vision-Language Models via Second-Order Statistics

arXiv:2604.03980v1 Announce Type: cross Abstract: Parameter-efficient prompt learning has become the de facto standard for adapting Vision-Language Models (VLMs

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

Can LLMs Learn to Reason Robustly under Noisy Supervision?

arXiv:2604.03993v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) effectively trains reasoning models that rely on abundan

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

Causality Laundering: Denial-Feedback Leakage in Tool-Calling LLM Agents

arXiv:2604.04035v1 Announce Type: cross Abstract: Tool-calling LLM agents can read private data, invoke external services, and trigger real-world actions, creat

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

Geometric Limits of Knowledge Distillation: A Minimum-Width Theorem via Superposition Theory

arXiv:2604.04037v1 Announce Type: cross Abstract: Knowledge distillation compresses large teachers into smaller students, but performance saturates at a loss fl

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

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks

arXiv:2604.04060v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly deployed in complex applications, their vulnerability to adve

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

Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison

arXiv:2604.04064v1 Announce Type: cross Abstract: Small language models (SLMs) in the 100M-10B parameter range increasingly power production systems, yet whethe

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

Embedding Enhancement via Fine-Tuned Language Models for Learner-Item Cognitive Modeling

arXiv:2604.04088v1 Announce Type: cross Abstract: Learner-item cognitive modeling plays a central role in the web-based online intelligent education system by e

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

From Paper to Program: A Multi-Stage LLM-Assisted Workflow for Accelerating Quantum Many-Body Algorithm Development

arXiv:2604.04089v1 Announce Type: cross Abstract: Translating quantum many-body theory into scalable software traditionally requires months of effort. Zero-shot

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

Many Preferences, Few Policies: Towards Scalable Language Model Personalization

arXiv:2604.04144v1 Announce Type: cross Abstract: The holy grail of LLM personalization is a single LLM for each user, perfectly aligned with that user's prefer

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

Uncertainty-Aware Test-Time Adaptation for Cross-Region Spatio-Temporal Fusion of Land Surface Temperature

arXiv:2604.04153v1 Announce Type: cross Abstract: Deep learning models have shown great promise in diverse remote sensing applications. However, they often stru

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

GENFIG1: Visual Summaries of Scholarly Work as a Challenge for Vision-Language Models

arXiv:2604.04172v1 Announce Type: cross Abstract: In many science papers, "Figure 1" serves as the primary visual summary of the core research idea. These figur

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

Which English Do LLMs Prefer? Triangulating Structural Bias Towards American English in Foundation Models

arXiv:2604.04204v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains, yet they expose only limited la

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

Hierarchical Semantic Correlation-Aware Masked Autoencoder for Unsupervised Audio-Visual Representation Learning

arXiv:2604.04229v1 Announce Type: cross Abstract: Learning aligned multimodal embeddings from weakly paired, label-free corpora is challenging: pipelines often

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

Three Phases of Expert Routing: How Load Balance Evolves During Mixture-of-Experts Training

arXiv:2604.04230v1 Announce Type: cross Abstract: We model Mixture-of-Experts (MoE) token routing as a congestion game with a single effective parameter, the co

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

APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs

arXiv:2604.04261v1 Announce Type: cross Abstract: Aligning large language models (LLMs) with diverse human preferences requires pluralistic alignment, where a s

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

Commercial Persuasion in AI-Mediated Conversations

arXiv:2604.04263v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become a primary interface between users and the web, companies face growing e

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

Poisoned Identifiers Survive LLM Deobfuscation: A Case Study on Claude Opus 4.6

arXiv:2604.04289v1 Announce Type: cross Abstract: When an LLM deobfuscates JavaScript, can poisoned identifier names in the string table survive into the model'

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

HighFM: Towards a Foundation Model for Learning Representations from High-Frequency Earth Observation Data

arXiv:2604.04306v1 Announce Type: cross Abstract: The increasing frequency and severity of climate related disasters have intensified the need for real time mon

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

Effects of Generative AI Errors on User Reliance Across Task Difficulty

arXiv:2604.04319v1 Announce Type: cross Abstract: The capabilities of artificial intelligence (AI) lie along a jagged frontier, where AI systems surprisingly fa

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

GROUNDEDKG-RAG: Grounded Knowledge Graph Index for Long-document Question Answering

arXiv:2604.04359v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems have been widely adopted in contemporary large language models (L