12d ago
Self-Organized Learning in Oscillatory Neural Networks with Memristive Signed Couplings
Self-organized learning in oscillatory neural networks with memristive couplings for associative memory and optimization.
12d ago
Rosetta: Composable Native Multimodal Pretraining
Rosetta: Composable multimodal pretraining approach addressing gradient conflicts when integrating new modalities without catastrophic forgetting.
12d ago
DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
DiscoLoop: Method for internalizing multi-hop reasoning in LLMs within single forward pass using discrete embeddings and continuous states.
12d ago
SoK: Attack and Defense Landscape of Mobile On-device AI Systems
Systematization of knowledge on attack and defense landscape for mobile on-device AI systems.
12d ago
The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models
Structured evaluation showing text-to-image diffusion safety alignment methods create illusion of high utility through coarse metrics.
12d ago
MindAU: EEG-Conditioned Facial Action Unit Editing via Dual-Stream Manifold Alignment
EEG-conditioned facial action unit editing using dual-stream manifold alignment.
12d ago
A Mechanistic View of Authority Hierarchy in LLM Sycophancy
Mechanistic investigation of authority bias in LLMs showing how models prioritize source credibility over factual consistency.
12d ago
Information-Regularized Attention for Visual-Centric Reasoning
Information-regularized attention mechanism to improve visual grounding and reduce hallucination in vision-language models.
12d ago
StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning
StochasT: Visual instruction tuning method addressing visual attention decay in multi-turn vision-language model conversations.
12d ago
Predicting Lethal Outcome (Cause) And Understanding Key Biomarkers Linked With Acute Myocardial Infarction Using Deep Artificial Neural Network And Ensemble Of Machine Learning Methodologies
Deep neural networks and ensemble methods to predict mortality outcomes and identify biomarkers in acute myocardial infarction.
12d ago
How Environment and Urbanization Shape Bird Diversity in Sri Lanka
Analysis of bird diversity in Sri Lanka using spatial and environmental data.
12d ago
Optimal scaling of MCMC algorithms: exploiting the symmetry of the Metropolis-Hastings formula
Theoretical study of MCMC scaling properties using Metropolis-Hastings symmetry.
12d ago
Auditing Forgetting in Limited Memory Language Models
Causal auditing framework to detect whether deleted facts persist in limited memory language models through parametric memory or retrieval artifacts.
12d ago
Coachable agents for interactive gameplay
RL framework enabling interactive real-time control of agent behavior during gameplay through coachability mechanisms instead of learning single optimal policy.
12d ago
LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter
Lightweight backbone-agnostic segmentation benchmark adapter enabling fair comparison of transformer backbones independent of decoder and pretraining.
12d ago
Forensic-Oriented Intrusion Detection Using Synthetic Network Traffic Data and Explainable Artificial Intelligence
Intrusion detection framework using synthetic network traffic and explainable AI to produce court-defensible, traceable forensic outputs.
12d ago
Soft Mixture-of-Recursions: Going Deeper with Recursive Vision Transformers
Recursive Vision Transformer approach using soft mixture-of-recursions to build deeper models with better parameter efficiency and performance.
12d ago
Evaluating Pretrained Music Embeddings for Cross-Performance Jazz Standard Recognition
Evaluation of pretrained music embeddings for cross-performance jazz standard recognition, comparing CNNs against foundation model embeddings.
12d ago
Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learning
Self-supervised learning framework for Vision Transformers that preserves informative left-right correspondences in bilateral data like medical images.
12d ago
Shapley in Context: Explaining Financial Language with Domain Expertise
Method for explaining financial LLM decisions using Shapley values combined with domain expertise, addressing regulatory explainability requirements.
12d ago
MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment
Video-text alignment model using asymmetric dual projections to handle temporal misalignment and semantic heterogeneity in long videos.
12d ago
Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination
Graph-native RL system for materials discovery generating scientifically valid hypotheses through multi-step reasoning with traceable intermediate steps.
12d ago
A Geometric Perspective on Composable Emotion Steering in Text-to-Speech Models
Comparative study of speech language models and conditional flow-matching for emotion control in text-to-speech, using activation steering techniques.
12d ago
Bridging Quantum Computing Paradigms toward Semiconductor Yield: A Controlled CV-versus-DV Comparison on Wafer-Map Defect Classification
Controlled comparison of continuous-variable and discrete-variable quantum neural network paradigms on wafer-map defect classification tasks.
12d ago
Understanding How Humans Inject Knowledge into Machine Learning Workflows through Visual Analytics
Survey examining how humans inject knowledge into ML workflows through visual analytics tools, covering labeling, feature engineering, and hyperparameter tuning.
12d ago
Deep Multitask Learning for Mixed-Type Outcomes with Shared Sparsity
Multitask learning framework handling mixed-type outcomes with shared sparsity by unifying task-specific losses through transformation.
12d ago
Foundation Models vs. Radiomics for Lung Computed Tomography: A Benchmark of Feature Extractors, Classification Heads, and Segmentation Choices
Benchmark comparing foundation models and radiomics approaches for lung cancer detection across multiple feature extractors, classification heads, and segmentation methods.
12d ago
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
Method to identify attention heads in LLMs that synthesize answers from context meaning rather than literal copying, improving long-context model interpretability.
12d ago
How Much Do RF Drone Benchmarks Overstate? A Controlled Study and Theory of Data Leakage in UAV Signal Identification
Study of data leakage issues in RF-based drone detection benchmarks, showing how cross-validation methodology can artificially inflate reported accuracies.
12d ago
Characterizing and Identifying Separable Graphical Models
Mathematical framework for understanding independence structures in graphical models with directed, undirected, and bidirected edges.
12d ago
Message Passing Enables Efficient Reasoning
Research on message passing between LLM threads for efficient parallel reasoning, reducing computational cost of long chains-of-thought.
12d ago
Group-invariant Coresets for Data-efficient Active Learning
GRINCO uses group-invariant coresets for active learning that respect data symmetries and transformation groups.
12d ago
FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement
FAR enables robots to learn from failures at test time, adapt behavior, and improve policy without human intervention.
12d ago
GPU-Parallel Linearization Error Bounds for Real-Time Robust Optimal Control of Nonlinear and Neural Network Dynamics
GPU-parallel linearization error bounds for real-time robust optimal control with neural network dynamics.
12d ago
Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation
Cartridge distillation method exposes hidden biases in LLMs that favor specific entities or viewpoints.
12d ago
Semi-Bandit Learning for Monotone Stochastic Optimization
Semi-bandit learning approach for monotone stochastic optimization without full probability distribution knowledge.
12d ago
Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms
Compares PPO and SAC reinforcement learning algorithms for fault tolerance in autonomous machines.
12d ago
Invariance Pair Guidance: Robustness to Spurious Correlations via Corrective Gradients
Invariance Pair Guidance improves robustness to spurious correlations through corrective gradients without dense labels.
12d ago
Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning
Studies inherent many-to-many multiplicity in multimodal learning relationships beyond deterministic alignment.
12d ago
scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell Omics
scDataset provides scalable data loading for deep learning on large-scale single-cell genomics datasets.
12d ago
FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data
FusionFactory fuses capabilities of multiple LLMs using multi-LLM log data for improved performance.
12d ago
Fraud is Not Just Rarity: A Causal Prototype Attention Approach to Realistic Synthetic Oversampling
Causal prototype attention approach for synthetic oversampling in credit card fraud detection.
12d ago
FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learning
FLAT reveals hidden backdoor failures in federated learning through latent-conditioned reliability stress testing.
12d ago
TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
TANDEM uses neural differential equations with temporal attention for time series classification with missing data.
12d ago
FedIA: Importance-Aware Aggregation for Domain-Robust Federated Graph Learning
FedIA improves federated graph learning through importance-aware aggregation on distributed social media networks.
12d ago
Predicting LLM Reasoning Performance with Small Proxy Model
rBridge predicts reasoning performance of large LLMs using small proxy models under 1B parameters.
12d ago
Self-Improving Neural Pruning: A Graph Neural Network Framework for Scalable Mixed Bundle Pricing
Graph neural network approach for solving mixed bundle pricing problems in revenue management.
12d ago
K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
K-Merge enables online merging of LoRA adapters for efficient on-device LLM deployment with limited storage.
12d ago
Recursively Enumerably Representable Classes and Computable Versions of the Fundamental Theorem of Statistical Learning
Studies computable PAC learning and derives analogs of the Fundamental Theorem of Statistical Learning in the computable setting.
12d ago
FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification
FlowPath: invertible flow-based method for learning manifolds from irregularly-sampled time series, improving neural controlled differential equations robustness.