Core AI

Large Language Models

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

24,746

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 19,447 Reads 5,299

Showing 5,299 reads from curated sources

Level: All Beginner Intermediate Advanced

Newest Popular Oldest

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

TurboAngle: Near-Lossless KV Cache Compression via Uniform Angle Quantization

arXiv:2603.27467v1 Announce Type: cross Abstract: We compress KV cache entries by quantizing angles in the Fast Walsh-Hadamard domain, where a random diagonal r

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

On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models

arXiv:2603.27481v1 Announce Type: cross Abstract: Multimodal Continual Instruction Tuning aims to continually enhance Large Vision Language Models (LVLMs) by le

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

Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning

arXiv:2603.27482v1 Announce Type: cross Abstract: Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style tr

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

Copilot-Assisted Second-Thought Framework for Brain-to-Robot Hand Motion Decoding

arXiv:2603.27492v1 Announce Type: cross Abstract: Motor kinematics prediction (MKP) from electroencephalography (EEG) is an important research area for developi

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

Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs

arXiv:2603.27494v1 Announce Type: cross Abstract: To enhance the perception and reasoning capabilities of multimodal large language models in complex visual sce

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

Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost Awareness

arXiv:2603.27539v1 Announce Type: cross Abstract: Multi-agent systems based on large language models (LLMs) for financial trading have grown rapidly since 2023,

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

STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding

arXiv:2603.27593v1 Announce Type: cross Abstract: Recent progress in video large language models (Video-LLMs) has enabled strong offline reasoning over long and

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

Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling

arXiv:2603.27624v1 Announce Type: cross Abstract: Mixture-of-Experts is a promising approach for edge AI with low-batch inference. Yet, on-device deployments of

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

Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents

arXiv:2603.27626v1 Announce Type: cross Abstract: I propose Umwelt engineering -- the deliberate design of the linguistic cognitive environment -- as a third la

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

EvA: An Evidence-First Audio Understanding Paradigm for LALMs

arXiv:2603.27667v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) still struggle in complex acoustic scenes because they often fail to prese

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

LVRPO: Language-Visual Alignment with GRPO for Multimodal Understanding and Generation

arXiv:2603.27693v1 Announce Type: cross Abstract: Unified multimodal pretraining has emerged as a promising paradigm for jointly modeling language and vision wi

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

RAP: Retrieve, Adapt, and Prompt-Fit for Training-Free Few-Shot Medical Image Segmentation

arXiv:2603.27705v1 Announce Type: cross Abstract: Few-shot medical image segmentation (FSMIS) has achieved notable progress, yet most existing methods mainly re

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

KVSculpt: KV Cache Compression as Distillation

arXiv:2603.27819v1 Announce Type: cross Abstract: KV cache compression is critical for efficient long-context LLM inference. Approaches that reduce the per-pair

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

Kernel Dynamics under Path Entropy Maximization

arXiv:2603.27880v1 Announce Type: cross Abstract: We propose a variational framework in which the kernel function k : X x X -> R, interpreted as the foundationa

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

ITQ3_S: High-Fidelity 3-bit LLM Inference via Interleaved Ternary Quantization with Rotation-Domain Smoothing

arXiv:2603.27914v1 Announce Type: cross Abstract: We present \textbf{ITQ3\_S} (Interleaved Ternary Quantization -- Specialized), a novel 3-bit weight quantizati

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

Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey

arXiv:2603.27918v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images,

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

JaWildText: A Benchmark for Vision-Language Models on Japanese Scene Text Understanding

arXiv:2603.27942v1 Announce Type: cross Abstract: Japanese scene text poses challenges that multilingual benchmarks often fail to capture, including mixed scrip

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

CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-Language Models

arXiv:2603.27982v1 Announce Type: cross Abstract: Vision-language models (VLMs) achieve strong performance on many benchmarks, yet a basic reliability question

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

FedFG: Privacy-Preserving and Robust Federated Learning via Flow-Matching Generation

arXiv:2603.27986v1 Announce Type: cross Abstract: Federated learning (FL) enables distributed clients to collaboratively train a global model using local privat

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

Beyond Dataset Distillation: Lossless Dataset Concentration via Diffusion-Assisted Distribution Alignment

arXiv:2603.27987v1 Announce Type: cross Abstract: The high cost and accessibility problem associated with large datasets hinder the development of large-scale v

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

ViviDoc: Generating Interactive Documents through Human-Agent Collaboration

arXiv:2603.27991v1 Announce Type: cross Abstract: Interactive documents help readers engage with complex ideas through dynamic visualization, interactive animat

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

Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers

arXiv:2603.28013v1 Announce Type: cross Abstract: We present a stage-decomposed analysis of prompt injection attacks against five frontier LLM agents. Prior wor

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

Synonymix: Unified Group Personas for Generative Simulations

arXiv:2603.28066v1 Announce Type: cross Abstract: Generative agent simulations operate at two scales: individual personas for character interaction, and populat

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

MolmoPoint: Better Pointing for VLMs with Grounding Tokens

arXiv:2603.28069v1 Announce Type: cross Abstract: Grounding has become a fundamental capability of vision-language models (VLMs). Most existing VLMs point by ge

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

MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions

arXiv:2603.28086v1 Announce Type: cross Abstract: Voice design from natural language aims to generate speaker timbres directly from free-form textual descriptio

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

Transcription and Recognition of Italian Parliamentary Speeches Using Vision-Language Models

arXiv:2603.28103v1 Announce Type: cross Abstract: Parliamentary proceedings represent a rich yet challenging resource for computational analysis, particularly w

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

Q-DIVER: Integrated Quantum Transfer Learning and Differentiable Quantum Architecture Search with EEG Data

arXiv:2603.28122v1 Announce Type: cross Abstract: Integrating quantum circuits into deep learning pipelines remains challenging due to heuristic design limitati

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

Does Claude's Constitution Have a Culture?

arXiv:2603.28123v1 Announce Type: cross Abstract: Constitutional AI (CAI) aligns language models with explicitly stated normative principles, offering a transpa

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

MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios

arXiv:2603.28130v1 Announce Type: cross Abstract: We introduce Multilingual Document Parsing Benchmark, the first benchmark for multilingual digital and photogr

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

RecycleLoRA: Rank-Revealing QR-Based Dual-LoRA Subspace Adaptation for Domain Generalized Semantic Segmentation

arXiv:2603.28142v1 Announce Type: cross Abstract: Domain Generalized Semantic Segmentation (DGSS) aims to maintain robust performance across unseen target domai

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

Evaluating Privilege Usage of Agents on Real-World Tools

arXiv:2603.28166v1 Announce Type: cross Abstract: Equipping LLM agents with real-world tools can substantially improve productivity. However, granting agents au

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

ERPO: Token-Level Entropy-Regulated Policy Optimization for Large Reasoning Models

arXiv:2603.28204v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (RLVR) has significantly advanced the reasoning capabilities of

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

DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning

arXiv:2603.28251v1 Announce Type: cross Abstract: Drivers' visual attention provides critical cues for anticipating latent hazards and directly shapes decision-

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

Categorical Perception in Large Language Model Hidden States: Structural Warping at Digit-Count Boundaries

arXiv:2603.28258v1 Announce Type: cross Abstract: Categorical perception (CP) -- enhanced discriminability at category boundaries -- is among the most studied p

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

Merge and Conquer: Instructing Multilingual Models by Adding Target Language Weights

arXiv:2603.28263v1 Announce Type: cross Abstract: Large Language Models (LLMs) remain heavily centered on English, with limited performance in low-resource lang

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

Pre-Deployment Complexity Estimation for Federated Perception Systems

arXiv:2603.28282v1 Announce Type: cross Abstract: Edge AI systems increasingly rely on federated learning to train perception models in distributed, privacy-pre

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

FI-KAN: Fractal Interpolation Kolmogorov-Arnold Networks

arXiv:2603.28288v1 Announce Type: cross Abstract: Kolmogorov-Arnold Networks (KAN) employ B-spline bases on a fixed grid, providing no intrinsic multi-scale dec

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

NeiGAD: Augmenting Graph Anomaly Detection via Spectral Neighbor Information

arXiv:2603.28300v1 Announce Type: cross Abstract: Graph anomaly detection (GAD) aims to identify irregular nodes or structures in attributed graphs. Neighbor in

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

Building evidence-based knowledge graphs from full-text literature for disease-specific biomedical reasoning

arXiv:2603.28325v1 Announce Type: cross Abstract: Biomedical knowledge resources often either preserve evidence as unstructured text or compress it into flat tr

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

Integrating Multimodal Large Language Model Knowledge into Amodal Completion

arXiv:2603.28333v1 Announce Type: cross Abstract: With the widespread adoption of autonomous vehicles and robotics, amodal completion, which reconstructs the oc

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

Crossing the NL/PL Divide: Information Flow Analysis Across the NL/PL Boundary in LLM-Integrated Code

arXiv:2603.28345v1 Announce Type: cross Abstract: LLM API calls are becoming a ubiquitous program construct, yet they create a boundary that no existing program

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

Coherent Without Grounding, Grounded Without Success: Observability and Epistemic Failure

arXiv:2603.28371v1 Announce Type: cross Abstract: When an agent can articulate why something works, we typically take this as evidence of genuine understanding.

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

Membership Inference Attacks against Large Audio Language Models

arXiv:2603.28378v1 Announce Type: cross Abstract: We present the first systematic Membership Inference Attack (MIA) evaluation of Large Audio Language Models (L

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

Critic-Free Deep Reinforcement Learning for Maritime Coverage Path Planning on Irregular Hexagonal Grids

arXiv:2603.28385v1 Announce Type: cross Abstract: Maritime surveillance missions, such as search and rescue and environmental monitoring, rely on the efficient

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

EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation

arXiv:2603.28405v1 Announce Type: cross Abstract: Diffusion Transformers (DiT) have established a new state-of-the-art in high-fidelity image synthesis; however

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

Evolutionary Discovery of Reinforcement Learning Algorithms via Large Language Models

arXiv:2603.28416v1 Announce Type: cross Abstract: Reinforcement learning algorithms are defined by their learning update rules, which are typically hand-designe

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

Spectral Higher-Order Neural Networks

arXiv:2603.28420v1 Announce Type: cross Abstract: Neural networks are fundamental tools of modern machine learning. The standard paradigm assumes binary interac

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

FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation

arXiv:2603.28455v1 Announce Type: cross Abstract: In federated healthcare systems, Federated Class-Incremental Learning (FCIL) has emerged as a key paradigm, en