3/18/2026
AI4EOSC: a Federated Cloud Platform for Artificial Intelligence in Scientific Research
AI4EOSC federated cloud platform for AI in scientific research with reproducible ML lifecycle management across distributed e-Infrastructures.
3/18/2026
SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering
SentGraph hierarchical sentence graph enables multi-hop retrieval-augmented generation by constructing coherent evidence chains from multiple documents for complex QA.
3/18/2026
Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias
Audits political alignment in 26 LLMs using psychometric inventories and news bias labeling across prompt variants to evaluate behavioral bias.
3/18/2026
Urban Socio-Semantic Segmentation with Vision-Language Reasoning
Vision-language reasoning for urban socio-semantic segmentation from satellite imagery, distinguishing socially-defined categories beyond physical attributes.
3/18/2026
Aletheia: What Makes RLVR For Code Verifiers Tick?
Ablates RLVR pipeline components for code verifiers: intermediate thinking traces, negative samples, and on-policy training to reduce adoption cost barriers.
3/18/2026
CFM: Language-aligned Concept Foundation Model for Vision
CFM language-aligned concept foundation model decomposes vision model representations into human-interpretable concepts with spatial grounding for diverse downstream tasks.
3/18/2026
From Intuition to Calibrated Judgment: A Rubric-Based Expert-Panel Study of Human Detection of LLM-Generated Korean Text
LREAD rubric-based framework with three-phase expert study calibrates human detection of LLM-generated Korean text to improve attribution accuracy beyond surface-level assessment.
3/18/2026
Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models
Time-annealed perturbation sampling for diffusion language models enables diverse generation across semantic and reasoning paths by controlling temporal denoising.
3/18/2026
Building a Correct-by-Design Lakehouse. Data Contracts, Versioning, and Transactional Pipelines for Humans and Agents
Bauplan code-first lakehouse with data contracts, versioning, and transactional pipelines for concurrent AI/analytics workloads supporting both human and agent workflows.
3/18/2026
LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations
Predicts LLM success from pre-generation internal activations using linear probes to enable efficient inference routing on math and coding tasks.
3/18/2026
Can Multimodal LLMs See Science Instruction? Benchmarking Pedagogical Reasoning in K-12 Classroom Videos
Benchmark evaluating multimodal LLMs' ability to understand pedagogical reasoning and science instruction in K-12 classroom videos with model-based explanations.
3/18/2026
Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning
Descent-guided policy gradient method addresses cross-agent noise scaling in multi-agent reinforcement learning, improving sample complexity from O(N/ε) to sublinear bounds.
3/18/2026
KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning
KEEP system optimizes KV-cache memory management for memory-augmented LLMs in embodied planning, reducing prompt length and prefill latency for long-horizon tasks.
3/18/2026
Ask don't tell: Reducing sycophancy in large language models
Experimental study of sycophancy in LLMs—tendency to favor user-affirming over critical responses—with controlled interventions to identify and prevent the alignment failure.
3/18/2026
Prompt Sensitivity and Answer Consistency of Small Open-Source Language Models for Clinical Question Answering in Low-Resource Healthcare
Evaluates 5 open-source small LLMs (Gemma, Phi, Llama, Mistral, Meditron) for clinical QA reliability and prompt sensitivity in low-resource healthcare settings.
3/18/2026
AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
AOI: Trainable multi-agent LLM framework for autonomous cloud diagnosis and SRE automation learning from failed trajectories.
3/18/2026
SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration
SWE-CI: Benchmark evaluating LLM agent capabilities in continuous integration for long-term codebase maintenance and feature iterations.
3/18/2026
Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection
Optimizes KV cache in transformers by reducing key dimensionality to log(N) while preserving value information for efficiency.
3/18/2026
CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report Evaluation
CRIMSON: Clinically-grounded LLM metric for evaluating chest X-ray report generation on diagnostic correctness and patient safety.
3/18/2026
Defining AI Models and AI Systems: A Framework to Resolve the Boundary Problem
Systematic framework defining boundaries between AI models and AI systems for regulatory and policy compliance purposes.
3/18/2026
Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language Models
Amnesia: Adversarial semantic activation steering technique for controlling harmful content generation in large language models.
3/18/2026
DUCTILE: Agentic LLM Orchestration of Engineering Analysis in Product Development Practice
DUCTILE: Agentic LLM orchestration framework for automating engineering analysis and tool coordination in product development.
3/18/2026
ELISA: An Interpretable Hybrid Generative AI Agent for Expression-Grounded Discovery in Single-Cell Genomics
ELISA: Interpretable AI agent combining scGPT embeddings with BioBERT for expression-grounded discovery in single-cell genomics.
3/18/2026
Real-World AI Evaluation: How FRAME Generates Systematic Evidence to Resolve the Decision-Maker's Dilemma
FRAME: Systematic framework for real-world AI evaluation generating contextual evidence on model behavior in organizational environments.
3/18/2026
APEX-Searcher: Augmenting LLMs' Search Capabilities through Agentic Planning and Execution
APEX-Searcher: LLM agent with agentic planning for multi-hop retrieval-augmented generation to enhance complex question answering.
3/18/2026
LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement
Audio-visual speech enhancement using RL with LLM-based interpretable reward model for perceptual quality optimization.
3/18/2026
Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations
arXiv: Post-hoc model-agnostic explanation method using perturbation selection for uncertainty-aware surrogate model approximations.
3/18/2026
Analyzing Error Sources in Global Feature Effect Estimation
arXiv: Analyzes error sources in global feature effect estimation (PD, ALE plots) for black-box model interpretation.
3/18/2026
Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database
arXiv: Open-source biomedical knowledge graphs (Pathways, Clinical Trials, Drug-Gene) with AI agent access via Samyama database.
3/18/2026
To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation
arXiv: Addresses LLM limitations in private-library code generation; shows API documentation retrieval alone is insufficient.
3/18/2026
HindSight: Evaluating LLM-Generated Research Ideas via Future Impact
arXiv: HindSight framework evaluates LLM-generated research ideas by matching against future publications and citation impact.
3/18/2026
More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam Search
arXiv: Analyzes how wider beam search can hurt LLM output quality due to overestimation bias in noisy scoring.
3/18/2026
The PokeAgent Challenge: Competitive and Long-Context Learning at Scale
arXiv: PokeAgent benchmark for multi-agent AI decision-making with partial observability, game theory, and long-horizon planning in Pokemon RPG.
3/18/2026
Physics-Informed Neural Systems for the Simulation of EUV Electromagnetic Wave Diffraction from a Lithography Mask
arXiv: Physics-informed neural networks for simulating EUV electromagnetic wave diffraction in lithography. Domain-specific neural networks.
3/18/2026
Tokenization Tradeoffs in Structured EHR Foundation Models
arXiv: Analyzes tokenization design choices for foundation models trained on structured electronic health records.
3/18/2026
Alternating Reinforcement Learning with Contextual Rubric Rewards
Reinforcement learning framework extending RLHF with multi-dimensional contextual rubric rewards and alternating optimization.
3/18/2026
Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing
Inference-time steering mechanism for frozen LLMs using adaptive prompt routing to enable evolving safety alignment without retraining.
3/18/2026
How to Achieve Prototypical Birth and Death for OOD Detection?
Prototype-based OOD detection method with dynamic prototype count adaptation based on category complexity.
3/18/2026
A federated learning framework with knowledge graph and temporal transformer for early sepsis prediction in multi-center ICUs
Federated learning framework combining knowledge graphs and temporal transformers for early sepsis prediction across multi-center ICUs.
3/18/2026
Discovering the Hidden Role of Gini Index In Prompt-based Classification
Study of Gini Index role in detecting and debiasing class accuracy disparities in prompt-based classification tasks.
3/18/2026
Beyond Reward Suppression: Reshaping Steganographic Communication Protocols in MARL via Dynamic Representational Circuit Breaking
Defense mechanism against steganographic collusion in multi-agent RL using dynamic representational circuit breaking at optimization substrate.
3/18/2026
Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors
Attribution-guided framework using rank-one model editing to rectify unreliable neural network behavior on non-robust features.
3/18/2026
Spectral Edge Dynamics of Training Trajectories: Signal--Noise Geometry Across Scales
Analysis of transformer training dynamics via spectral edge detection showing parameter updates concentrate in few coherent directions.
3/18/2026
Evidential Domain Adaptation for Remaining Useful Life Prediction with Incomplete Degradation
Domain adaptation method for remaining useful life prediction with incomplete degradation trajectories using evidential learning.
3/18/2026
Tackling Over-smoothing on Hypergraphs: A Ricci Flow-guided Neural Diffusion Approach
Hypergraph neural network approach using Ricci flow to address over-smoothing and improve message passing.
3/18/2026
Mastering the Minority: An Uncertainty-guided Multi-Expert Framework for Challenging-tailed Sequence Learning
Multi-expert framework with uncertainty guidance for imbalanced sequence learning and minority class detection.
3/18/2026
Embedding-Aware Feature Discovery: Bridging Latent Representations and Interpretable Features in Event Sequences
Method bridging learned embeddings and interpretable handcrafted features for temporal event sequences in financial systems.
3/18/2026
Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning in Unified Multimodal Models
Metacognitive test-time reinforcement learning framework for unified multimodal models enabling knowledge accumulation across similar prompts.
3/18/2026
OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning
Physics-grounded multimodal LLM agent combining language models with PDE solvers for scientific reasoning without domain-specific fine-tuning.
3/18/2026
Time-Aware Prior Fitted Networks for Zero-Shot Forecasting with Exogenous Variables
Zero-shot forecasting method for time series with exogenous variables using prior-fitted networks.