3/19/2026
SA-CycleGAN-2.5D: Self-Attention CycleGAN with Tri-Planar Context for Multi-Site MRI Harmonization
Self-attention CycleGAN variant for harmonizing MRI data across scanner sites to reduce acquisition variance.
3/19/2026
TharuChat: Bootstrapping Large Language Models for a Low-Resource Language via Synthetic Data and Human Validation
Approach for developing Tharu language LLM using synthetic data generation and human validation to address low-resource language gap.
3/19/2026
From Drop-off to Recovery: A Mechanistic Analysis of Segmentation in MLLMs
Analysis of multimodal LLM segmentation capabilities through layerwise probing and attention mechanisms.
3/19/2026
Wasserstein-type Gaussian Process Regressions for Input Measurement Uncertainty
Gaussian process regression method handling input measurement uncertainty using Wasserstein distance.
3/19/2026
Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
Red-teaming alignment framework (CRAFT) that improves LLM robustness against jailbreaks by optimizing hidden representations.
3/19/2026
ReLMXEL: Adaptive RL-Based Memory Controller with Explainable Energy and Latency Optimization
Multi-agent RL framework for dynamic memory controller optimization with explainable energy and latency objectives.
3/19/2026
Physics-informed offline reinforcement learning eliminates catastrophic fuel waste in maritime routing
Offline RL framework (PIER) for fuel-efficient maritime routing using physics-informed models and historical vessel data.
3/19/2026
A Progressive Visual-Logic-Aligned Framework for Ride-Hailing Adjudication
Multimodal LLM framework for ride-hailing dispute resolution combining visual and logical reasoning with transparency.
3/19/2026
Rapid Neural Network Prediction of Linear Block Copolymer Free Energies
Neural network model for rapid prediction of free energies in polymer systems.
3/19/2026
Bootstrapping Coding Agents: The Specification Is the Program
AI coding agent that bootstraps itself by re-implementing its own specification, demonstrating meta-circular properties similar to compiler bootstrapping.
3/19/2026
Mutually Causal Semantic Distillation Network for Zero-Shot Learning
Zero-shot learning approach using causal semantic distillation to transfer knowledge from seen to unseen classes.
3/19/2026
Structured SIR: Efficient and Expressive Importance-Weighted Inference for High-Dimensional Image Registration
Probabilistic inference method for high-dimensional image registration using variational approaches.
3/19/2026
Data-driven model order reduction for structures with piecewise linear nonlinearity using dynamic mode decomposition
Data-driven model order reduction method for piecewise-linear nonlinear systems using dynamic mode decomposition.
3/19/2026
ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression
Hardware-aware lossless compression technique (ZipServ) for efficient LLM inference with reduced memory and bandwidth requirements.
3/19/2026
Learning When to Attend: Conditional Memory Access for Long-Context LLMs
Research on conditional attention mechanism (L2A) that reduces computational costs for long-context LLM inference by selectively attending to relevant tokens.
3/19/2026
Mirror Descent on Riemannian Manifolds
arXiv paper proposing Riemannian Mirror Descent, generalizing first-order optimization methods to Riemannian manifolds with convergence guarantees.
3/19/2026
A Unified Language Model for Large Scale Search, Recommendation, and Reasoning
Unified LLM for search, recommendation, and reasoning over large heterogeneous catalogs generating unambiguous item references under latency constraints.
3/19/2026
Informative Semi-Factuals for XAI: The Elaborated Explanations that People Prefer
Studies semi-factual explanations in XAI showing elaborated counterfactuals are preferred by users for understanding ML predictions and exploring alternatives.
3/19/2026
Deploying Semantic ID-based Generative Retrieval for Large-Scale Podcast Discovery at Spotify
Semantic ID-based generative retrieval system deployed at Spotify balancing long-term preferences with intent-aware podcast discovery using contextual signals.
3/19/2026
Per-Domain Generalizing Policies: On Learning Efficient and Robust Q-Value Functions (Extended Version with Technical Appendix)
Per-domain Q-value functions using graph neural networks for efficient policy learning in planning, cheaper than state-value alternatives.
3/19/2026
Consistency of the $k$-Nearest Neighbor Regressor under Complex Survey Designs
Theoretical consistency analysis of k-nearest neighbor regressor under complex survey designs with derived convergence rate bounds.
3/19/2026
In Trust We Survive: Emergent Trust Learning
Emergent Trust Learning: lightweight trust-based control algorithm for AI agents enabling cooperation in competitive multi-agent environments with shared resources.
3/19/2026
Gaussian Process Limit Reveals Structural Benefits of Graph Transformers
Theoretical analysis proving graph transformers have structural benefits over GCNs for node-level prediction via Gaussian process limits.
3/19/2026
HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness
HeiSD: Hybrid speculative decoding for Vision-Language-Action robot control models combining drafter-based and retrieval-based acceleration with kinematic awareness.
3/19/2026
rSDNet: Unified Robust Neural Learning against Label Noise and Adversarial Attacks
rSDNet: Robust neural learning framework defending against both label noise and adversarial attacks using alternative loss functions to standard cross-entropy.
3/19/2026
Atomic Trajectory Modeling with State Space Models for Biomolecular Dynamics
State space models for biomolecular dynamics modeling, accelerating MD simulations while preserving temporal relationships for drug discovery applications.
3/19/2026
Inhibitory normalization of error signals improves learning in neural circuits
Inhibitory normalization in neural circuits improves learning when handling complex input distributions, bridging biological and artificial neural networks.
3/19/2026
Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models
Adaptive guidance mechanism for RAG-enhanced masked diffusion models to handle retrieval-prior conflicts when context is noisy or inconsistent.
3/19/2026
Sensi: Learn One Thing at a Time -- Curriculum-Based Test-Time Learning for LLM Game Agents
Sensi: LLM agent architecture for ARC-AGI-3 using curriculum-based test-time learning with perception-action separation and active hypothesis testing.
3/19/2026
Stochastic set-valued optimization and its application to robust learning
Stochastic set-valued optimization framework for robust machine learning using multi-objective optimization with hyperbox set representations.
3/19/2026
Modeling Overlapped Speech with Shuffles
Uses shuffle products and finite-state automata to model overlapped speech for alignment and speaker-attributed transcription via marginalizing serializations.
3/19/2026
CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution
CoVerRL framework escapes consensus trap in label-free LLM reasoning by using generator-verifier co-evolution to maintain output diversity and avoid reinforced systematic errors.
3/19/2026
ResNet-50 with Class Reweighting and Anatomy-Guided Temporal Decoding for Gastrointestinal Video Analysis
ResNet-50 pipeline for gastrointestinal video analysis using class reweighting and temporal decoding to handle severe class imbalance in pathology detection.
3/19/2026
The Convergence Frontier: Integrating Machine Learning and High Performance Quantum Computing for Next-Generation Drug Discovery
Framework integrating HPC, ML, and quantum computing for drug discovery, replacing trial-and-error with quantitative precision in molecular dynamics.
3/19/2026
ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation
ChopGrad reduces memory costs in video diffusion model training by using truncated backpropagation with pixel-wise losses instead of accumulating activations.
3/19/2026
Text-to-Stage: Spatial Layouts from Long-form Narratives
Language model infers stage-play layouts (scenes, positions, movements) from narrative text without explicit spatial cues, testing spatial reasoning capabilities.
3/19/2026
Verification and Validation of Physics-Informed Surrogate Component Models for Dynamic Power-System Simulation
Text-to-Stage: LLM-based spatial reasoning from narratives to generate stage-play layouts. Probes compositional reasoning in language models.
3/19/2026
How do LLMs Compute Verbal Confidence
Physics-informed ML surrogates for power grid simulation validation. Application of ML to scientific computing.
3/19/2026
scicode-lint: Detecting Methodology Bugs in Scientific Python Code with LLM-Generated Patterns
Research on how LLMs generate verbal confidence scores. Investigates timing and computation of uncertainty estimates in black-box models.
3/19/2026
A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models
scicode-lint: LLM-generated patterns for detecting methodology bugs in scientific Python code. Addresses sustainability of ML-specific linters.
3/19/2026
LoST: Level of Semantics Tokenization for 3D Shapes
LoST: level-of-semantics tokenization method for 3D shape generation improving autoregressive 3D generative models.
3/19/2026
Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
Token pruning framework for efficient video vision-language models reducing computational cost via temporal token scoring.
3/19/2026
HighAir: A Hierarchical Graph Neural Network-Based Air Quality Forecasting Method
Graph neural network method for air quality forecasting modeling pollution diffusion between cities and monitoring stations.
3/19/2026
Aergia: Leveraging Heterogeneity in Federated Learning Systems
Aergia: federated learning system leveraging client heterogeneity in computing power to reduce training time.
3/19/2026
Feature Space Renormalization for Semi-supervised Learning
Feature space renormalization mechanism for semi-supervised learning improving consistency regularization on unlabeled data.
3/19/2026
Soft Dice Confidence: A Near-Optimal Confidence Estimator for Selective Prediction in Semantic Segmentation
Soft Dice Confidence: confidence estimator for selective prediction in semantic segmentation enabling model abstention.
3/19/2026
Hi-GMAE: Hierarchical Graph Masked Autoencoders
Hi-GMAE: hierarchical graph masked autoencoders for multi-scale self-supervised learning on graph-structured data.
3/19/2026
Demystifying amortized causal discovery with transformers
Analyzes transformer-based amortized causal discovery on observational data, bridging supervised learning with identifiability theory.
3/19/2026
Den-TP: A Density-Balanced Data Curation and Evaluation Framework for Trajectory Prediction
Den-TP: data curation framework addressing long-tail distribution in trajectory prediction datasets for autonomous driving.
3/19/2026
ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning
ACT-JEPA: joint-embedding predictive architecture for efficient policy representation learning via self-supervised learning from unlabeled data.