4/9/2026
The Human Condition as Reflected in Contemporary Large Language Models
Analysis of latent cultural themes in training corpora by prompting six leading LLMs to identify recurring patterns about human culture.
4/9/2026
A Comparative Study of Demonstration Selection for Practical Large Language Models-based Next POI Prediction
Study comparing demonstration selection strategies for in-context learning in LLM-based next point-of-interest prediction.
4/9/2026
Extracting Breast Cancer Phenotypes from Clinical Notes: Comparing LLMs with Classical Ontology Methods
Comparison of LLMs versus classical ontology methods for extracting breast cancer phenotypes from unstructured clinical notes.
4/9/2026
Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
DOVE benchmark for evaluating LLM cultural value alignment using open-ended generation rather than multiple-choice formats.
4/9/2026
Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models
Study on improving faithfulness and traceability in retrieval-augmented generation through illocutionary explanation planning.
4/9/2026
Invisible Influences: Investigating Implicit Intersectional Biases through Persona Engineering in Large Language Models
Research investigating implicit intersectional biases in LLMs under persona-driven contexts, introducing Bias Amplification framework to capture dynamic bias shifts.
4/9/2026
Unsupervised Neural Network for Automated Classification of Surgical Urgency Levels in Medical Transcriptions
Unsupervised neural network using BioClinicalBERT to automatically classify surgical urgency levels from medical transcriptions.
4/9/2026
Blending Human and LLM Expertise to Detect Hallucinations and Omissions in Mental Health Chatbot Responses
Research on detecting hallucinations and omissions in LLM-powered mental health chatbots, finding LLM judges achieve only 52% accuracy on safety-critical healthcare data.
4/9/2026
The End of the Foundation Model Era: Open-Weight Models, Sovereign AI, and Inference as Infrastructure
ArXiv paper arguing the foundation model era (2020-2025) is ending as open-source models reach frontier performance and inference costs drop, making pre-training non-competitive.
4/9/2026
Development of ML model for triboelectric nanogenerator based sign language detection system
ML and deep learning model comparison for triboelectric sensor-based sign language recognition.
4/9/2026
Probabilistic Language Tries: A Unified Framework for Compression, Decision Policies, and Execution Reuse
Probabilistic language tries framework unifying compression, decision policies, and execution reuse for sequence models.
4/9/2026
Automating Database-Native Function Code Synthesis with LLMs
LLM-based code synthesis for database-native functions addressing hallucination and domain-specific challenges.
4/9/2026
The Art of Building Verifiers for Computer Use Agents
Framework for building verifiers for computer use agents with principles for constructing rubrics and training signals.
4/9/2026
SALLIE: Safeguarding Against Latent Language & Image Exploits
Unified defense mechanism against textual and visual jailbreaks and prompt injections in LLMs and VLMs.
4/9/2026
DISSECT: Diagnosing Where Vision Ends and Language Priors Begin in Scientific VLMs
Study on perception-integration gap in vision-language models: models extract visual info but fail in reasoning.
4/9/2026
FLeX: Fourier-based Low-rank EXpansion for multilingual transfer
Fourier-based low-rank parameter-efficient fine-tuning for cross-lingual code generation with Code Llama 7B.
4/9/2026
SE-Enhanced ViT and BiLSTM-Based Intrusion Detection for Secure IIoT and IoMT Environments
SE-Enhanced Vision Transformer and BiLSTM hybrid architecture for intrusion detection in IoT/medical environments.
4/9/2026
Spectral Edge Dynamics Reveal Functional Modes of Learning
Analysis of training dynamics during grokking via spectral edge directions, showing mechanistic interpretability tools miss structured functional modes of learning.
4/9/2026
$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models
S³: stratified scaling search for test-time inference in diffusion language models using verifier-guided sampling to improve generation quality without retraining.
4/9/2026
From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning
Dual-stream calibration method for improving contextual clinical reasoning in LLMs through dynamic representation adjustment via in-context learning and RAG.
4/9/2026
Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models
IAMFM framework optimizing sponsorship configurations in LLM-generated ads using VCG incentives and multi-fidelity optimization under advertiser strategic behavior.
4/9/2026
ToxReason: A Benchmark for Mechanistic Chemical Toxicity Reasoning via Adverse Outcome Pathway
ToxReason benchmark for evaluating LLM mechanistic reasoning in chemical toxicity prediction via adverse outcome pathways beyond structural features.
4/9/2026
Attribution-Driven Explainable Intrusion Detection with Encoder-Based Large Language Models
Attribution-based explainability for LLM-based intrusion detection in SDN environments, addressing transparency and interpretability in security-critical applications.
4/9/2026
MAT-Cell: A Multi-Agent Tree-Structured Reasoning Framework for Batch-Level Single-Cell Annotation
MAT-Cell: neuro-symbolic multi-agent framework combining LLMs with biological priors for single-cell annotation, addressing generalization and spurious association problems.
4/9/2026
Towards the Development of an LLM-Based Methodology for Automated Security Profiling in Compliance with Ukrainian Cybersecurity Regulations
LLM methodology for automated security profiling in Ukrainian cybersecurity compliance, integrating ISO/IEC 27001 and NIST frameworks.
4/9/2026
Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations
Plasma GraphRAG: integrates Graph RAG with LLMs for automated physics-grounded parameter selection in gyrokinetic plasma simulations.
4/9/2026
DosimeTron: Automating Personalized Monte Carlo Radiation Dosimetry in PET/CT with Agentic AI
DosimeTron: agentic AI system automating personalized Monte Carlo radiation dosimetry in PET/CT with GPT as reasoning engine and 23 specialized tools.
4/9/2026
ClawLess: A Security Model of AI Agents
ClawLess: security framework enforcing formally verified policies on autonomous LLM-based AI agents to mitigate code execution and data retrieval risks.
4/9/2026
Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization
Hyperbolic geometry-based approach for detecting and sanitizing harmful prompts in Vision-Language Models.
4/9/2026
TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models
TalkLoRA: communication-aware Mixture-of-Experts LoRA framework for parameter-efficient fine-tuning of LLMs with stable expert routing.
4/9/2026
AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent
AgentOpt v0.1: client-side optimization framework for LLM-based agents composing local tools and remote APIs to reduce latency and costs.
4/9/2026
A Novel Automatic Framework for Speaker Drift Detection in Synthesized Speech
Automatic framework for detecting speaker drift in diffusion-based text-to-speech models using binary classification.
4/9/2026
"Don't Be Afraid, Just Learn": Insights from Industry Practitioners to Prepare Software Engineers in the Age of Generative AI
Survey of 51 industry practitioners on preparing software engineers for generative AI tools, covering hiring and skill gaps.
4/9/2026
Severity-Aware Weighted Loss for Arabic Medical Text Generation
Severity-aware weighted loss function for fine-tuning Arabic language models on medical complaint text generation.
4/9/2026
Bi-Level Optimization for Single Domain Generalization
Bi-level optimization framework (BiSDG) for single domain generalization without target domain access during training.
4/9/2026
In-Context Learning in Speech Language Models: Analyzing the Role of Acoustic Features, Linguistic Structure, and Induction Heads
Analyzes in-context learning in speech language models, studying acoustic features, linguistic structure, and induction heads for text-to-speech tasks.
4/9/2026
A Severity-Based Curriculum Learning Strategy for Arabic Medical Text Generation
Severity-based curriculum learning strategy for Arabic medical text generation using LLMs.
4/9/2026
WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks
WebSP-Eval benchmark for evaluating web agents on security and privacy tasks like cookie management and account settings configuration.
4/9/2026
Beyond Functional Correctness: Design Issues in AI IDE-Generated Large-Scale Projects
Empirical study of design issues in large-scale code generation by AI IDEs with agentic capabilities, beyond functional correctness.
4/9/2026
The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment
Proposes Master Key Hypothesis and UNLOCK method for training-free capability transfer across different LLM scales via linear subspace alignment.
4/9/2026
Toward a universal foundation model for graph-structured data
Research on foundation models for graph-structured data in biomedical applications, extending language/vision foundation model approaches to graph analysis.
4/9/2026
FMI@SU ToxHabits: Evaluating LLMs Performance on Toxic Habit Extraction in Spanish Clinical Texts
arXiv paper on using LLMs for toxic habit extraction in Spanish clinical texts. Zero-shot and few-shot approaches for substance use classification.
4/9/2026
Say Something Else: Rethinking Contextual Privacy as Information Sufficiency
arXiv paper on privacy-preserving strategies for LLM-drafted messages. Evaluates suppression and generalization approaches for sensitive information.
4/9/2026
Attention Flows: Tracing LLM Conceptual Engagement via Story Summaries
Evaluates LLM performance on long-form text understanding by comparing human and model-generated novel summaries, assessing conceptual engagement patterns.
4/9/2026
When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't
Introduces Graded Color Attribution dataset to evaluate whether Vision-Language Models follow their own introspective reasoning rules compared to human behavior.
4/9/2026
Neural Computers
Proposes Neural Computers (NCs), a model architecture unifying computation, memory, and I/O as learned runtime state, aiming toward completely neural computing systems.
4/9/2026
The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning
Research on limits of latent reasoning in LLMs, testing whether models can discover multi-step planning strategies without supervision using graph path-finding tasks.
4/9/2026
Continual Visual Anomaly Detection on the Edge: Benchmark and Efficient Solutions
Benchmark and solutions for visual anomaly detection on edge devices with continual learning to adapt to evolving data distributions.
4/9/2026
The Defense Trilemma: Why Prompt Injection Defense Wrappers Fail?
Theoretical proof that no continuous wrapper defense can prevent all prompt injections in LLMs with connected prompt space, characterizing defense failure modes.
4/9/2026
From Load Tests to Live Streams: Graph Embedding-Based Anomaly Detection in Microservice Architectures
Graph embedding-based anomaly detection system identifies under-represented services in microservice architectures using unsupervised learning.