Large Language Models

Separating Diagnosis from Control: Auditable Policy Adaptation in Agent-Based Simulations with LLM-Based Diagnostics

ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning

Ran Score: a LLM-based Evaluation Score for Radiology Report Generation

PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference

JFTA-Bench: Evaluate LLM's Ability of Tracking and Analyzing Malfunctions Using Fault Trees

Can Large Language Models Reason and Optimize Under Constraints?

Minibal: Balanced Game-Playing Without Opponent Modeling

MedCausalX: Adaptive Causal Reasoning with Self-Reflection for Trustworthy Medical Vision-Language Models

Between Rules and Reality: On the Context Sensitivity of LLM Moral Judgment

Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models

SAiW: Source-Attributable Invisible Watermarking for Proactive Deepfake Defense

PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments

MemCollab: Cross-Agent Memory Collaboration via Contrastive Trajectory Distillation

LLM Olympiad: Why Model Evaluation Needs a Sealed Exam

RelayS2S: A Dual-Path Speculative Generation for Real-Time Dialogue

Bilevel Autoresearch: Meta-Autoresearching Itself

Mecha-nudges for Machines

Automated Microservice Pattern Instance Detection Using Infrastructure-as-Code Artifacts and Large Language Models

Founder effects shape the evolutionary dynamics of multimodality in open LLM families

Evaluating Prompting Strategies for Chart Question Answering with Large Language Models

MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing

Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning

TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs

Efficient Embedding-based Synthetic Data Generation for Complex Reasoning Tasks

Whether, Not Which: Mechanistic Interpretability Reveals Dissociable Affect Reception and Emotion Categorization in LLMs

Between the Layers Lies the Truth: Uncertainty Estimation in LLMs Using Intra-Layer Local Information Scores

Latent Semantic Manifolds in Large Language Models

Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models

CN-Buzz2Portfolio: A Chinese-Market Dataset and Benchmark for LLM-Based Macro and Sector Asset Allocation from Daily Trending Financial News

UniFluids: Unified Neural Operator Learning with Conditional Flow-matching

Emergency Preemption Without Online Exploration: A Decision Transformer Approach

Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation Learning

From Instructions to Assistance: a Dataset Aligning Instruction Manuals with Assembly Videos for Evaluating Multimodal LLMs

AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulations

A Multi-Task Targeted Learning Framework for Lithium-Ion Battery State-of-Health and Remaining Useful Life

DAQ: Delta-Aware Quantization for Post-Training LLM Weight Compression

AgentSLR: Automating Systematic Literature Reviews in Epidemiology with Agentic AI

Trained Persistent Memory for Frozen Decoder-Only LLMs

Large Language Models for Missing Data Imputation: Understanding Behavior, Hallucination Effects, and Control Mechanisms

Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta Modulation

Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation

Graphs RAG at Scale: Beyond Retrieval-Augmented Generation With Labeled Property Graphs and Resource Description Framework for Complex and Unknown Search Spaces

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search

WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement

Early Discoveries of Algorithmist I: Promise of Provable Algorithm Synthesis at Scale

MCLR: Improving Conditional Modeling in Visual Generative Models via Inter-Class Likelihood-Ratio Maximization and Establishing the Equivalence between Classifier-Free Guidance and Alignment Objectives

Q-AGNN: Quantum-Enhanced Attentive Graph Neural Network for Intrusion Detection

Modeling Quantum Federated Autoencoder for Anomaly Detection in IoT Networks