Large Language Models

EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling

Reasoning as Energy Minimization over Structured Latent Trajectories

Evaluating LLMs for Answering Student Questions in Introductory Programming Courses

CoE: Collaborative Entropy for Uncertainty Quantification in Agentic Multi-LLM Systems

Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science

COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum Game

The Scaffold Effect: How Prompt Framing Drives Apparent Multimodal Gains in Clinical VLM Evaluation

T-Norm Operators for EU AI Act Compliance Classification: An Empirical Comparison of Lukasiewicz, Product, and G\"odel Semantics in a Neuro-Symbolic Reasoning System

MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models

Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning

The Ultimate Tutorial for AI-driven Scale Development in Generative Psychometrics: Releasing AIGENIE from its Bottle

Not Search, But Scan: Benchmarking MLLMs on Scan-Oriented Academic Paper Reasoning

Exploring Cultural Variations in Moral Judgments with Large Language Models

SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs

M-RAG: Making RAG Faster, Stronger, and More Efficient

Bridge-RAG: An Abstract Bridge Tree Based Retrieval Augmented Generation Algorithm With Cuckoo Filter

ReCQR: Incorporating conversational query rewriting to improve Multimodal Image Retrieval

Can AI be a Teaching Partner? Evaluating ChatGPT, Gemini, and DeepSeek across Three Teaching Strategies

AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment

LITTA: Late-Interaction and Test-Time Alignment for Visually-Grounded Multimodal Retrieval

SpatialPoint: Spatial-aware Point Prediction for Embodied Localization

Complementarity-Preserving Generative Theory for Multimodal ECG Synthesis: A Quantum-Inspired Approach

The Cognitive Divergence: AI Context Windows, Human Attention Decline, and the Delegation Feedback Loop

Agentic AI for Human Resources: LLM-Driven Candidate Assessment

Brain-inspired AI for Edge Intelligence: a systematic review

SEAR: Schema-Based Evaluation and Routing for LLM Gateways

Contextual inference from single objects in Vision-Language models

Distilled Large Language Model-Driven Dynamic Sparse Expert Activation Mechanism

Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning

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

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

Language-Conditioned World Modeling for Visual Navigation

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

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

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

Learning to Select Visual In-Context Demonstrations

TED: Training-Free Experience Distillation for Multimodal Reasoning

Limits of Imagery Reasoning in Frontier LLM Models

Can We Change the Stroke Size for Easier Diffusion?

A Step Toward Federated Pretraining of Multimodal Large Language Models

CRISP: Characterizing Relative Impact of Scholarly Publications

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

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

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

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

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

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

PiCSRL: Physics-Informed Contextual Spectral Reinforcement Learning