3/10/2026
Soft Equivariance Regularization for Invariant Self-Supervised Learning
Soft equivariance regularization augments invariance-based self-supervised learning to preserve transformation-dependent structure for robustness.
3/10/2026
On the Generalization Capacities of MLLMs for Spatial Intelligence
Analysis of multimodal LLM generalization showing RGB-only approaches fail to generalize across cameras due to camera parameter entanglement.
3/10/2026
Uncertainty-Aware Solar Flare Regression
Conformal prediction framework for solar flare regression with uncertainty quantification and false alarm reduction.
3/10/2026
PolyBlocks: A Compiler Infrastructure for AI Chips and Programming Frameworks
PolyBlocks MLIR-based compiler infrastructure for AI chips and frameworks using analytical cost models for automated high-performance code generation.
3/10/2026
Calibrated Credit Intelligence: Shift-Robust and Fair Risk Scoring with Bayesian Uncertainty and Gradient Boosting
Calibrated Credit Intelligence combines Bayesian uncertainty with gradient boosting for fair credit risk scoring under distribution shift.
3/10/2026
Prediction of Steady-State Flow through Porous Media Using Machine Learning Models
ML surrogate models for predicting steady-state flow through porous media in cold plate topology optimization.
3/10/2026
Best-of-Tails: Bridging Optimism and Pessimism in Inference-Time Alignment
Best-of-Tails method for inference-time alignment balancing optimism and pessimism in LLM candidate selection with imperfect reward models.
3/10/2026
CREDO: Epistemic-Aware Conformalized Credal Envelopes for Regression
CREDO combines conformal prediction with credal methods for regression with distribution-free coverage and epistemic uncertainty quantification.
3/10/2026
Bilateral Trade Under Heavy-Tailed Valuations: Minimax Regret with Infinite Variance
Theoretical analysis of contextual bilateral trade with heavy-tailed valuations and infinite variance using epoch-based pricing.
3/10/2026
Symmetry-Constrained Language-Guided Program Synthesis for Discovering Governing Equations from Noisy and Partial Observations
SymLang framework uses language-guided program synthesis with symmetry constraints to discover governing equations from noisy experimental data.
3/10/2026
Fairness May Backfire: When Leveling-Down Occurs in Fair Machine Learning
Analysis of fairness constraints in ML systems showing when enforcing fairness leads to worse outcomes for affected groups.
3/10/2026
A Dynamic Self-Evolving Extraction System
Self-evolving NLP extraction system that adapts to domain-specific taxonomies and emerging terminology in specialized fields like medical and legal.
3/10/2026
How Private Are DNA Embeddings? Inverting Foundation Model Representations of Genomic Sequences
Privacy analysis of DNA foundation model embeddings showing inversion attacks can reconstruct genomic sequences from shared embeddings.
3/10/2026
Post-Training with Policy Gradients: Optimality and the Base Model Barrier
Theoretical analysis of post-training linear autoregressive models with policy gradients, proving convergence properties under margin conditions.
3/10/2026
A SISA-based Machine Unlearning Framework for Power Transformer Inter-Turn Short-Circuit Fault Localization
SISA-based machine unlearning framework for removing poisoned training data influence in power transformer fault diagnosis models without full retraining.
3/10/2026
Topology-Aware Reinforcement Learning over Graphs for Resilient Power Distribution Networks
Graph-based reinforcement learning framework for power distribution network resilience incorporating topological features for outage management.
3/10/2026
Masked Unfairness: Hiding Causality within Zero ATE
Analyzes causal masking problem in fairness frameworks where zero average treatment effect hides underlying causal relationships.
3/10/2026
Adaptive Discovery of Interpretable Audio Attributes with Multimodal LLMs for Low-Resource Classification
Method for discovering interpretable audio attributes using multimodal LLMs for low-resource audio classification with high reliability.
3/10/2026
Can Safety Emerge from Weak Supervision? A Systematic Analysis of Small Language Models
Analysis of safety alignment in small language models using weak supervision and Self-MOA approach for reducing human annotation costs while maintaining usefulness.
3/10/2026
TEA-Time: Transporting Effects Across Time
Framework for temporal transportation of treatment effects from randomized trials to different time periods.
3/10/2026
VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness
Token caching optimization for vision-language navigation models accounting for visual and semantic dynamics to reduce inference cost.
3/10/2026
Statistical Contraction for Chance-Constrained Trajectory Optimization of Non-Gaussian Stochastic Systems
Distribution-free trajectory optimization for non-Gaussian stochastic systems using conformal inference with closed-loop guarantees.
3/10/2026
Deep Generative Spatiotemporal Engression for Probabilistic Forecasting of Epidemics
Deep generative spatiotemporal model for probabilistic epidemic forecasting with uncertainty quantification.
3/10/2026
Towards Objective Gastrointestinal Auscultation: Automated Segmentation and Annotation of Bowel Sound Patterns
Automated segmentation and annotation of bowel sounds for objective clinical auscultation using digital acoustic sensors.
3/10/2026
Conditional Rank-Rank Regression via Deep Conditional Transformation Models
Deep learning method for conditional rank-rank regression to measure intergenerational socio-economic mobility with covariate adjustment.
3/10/2026
Variational Flow Maps: Make Some Noise for One-Step Conditional Generation
Framework for conditional image generation with flow maps using variational approach for solving inverse problems and adding constraints.
3/10/2026
StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models
Token merging optimization for Segment Anything Model to improve inference speed while preserving segmentation quality and handling SAM's attention architecture.
3/10/2026
Shutdown Safety Valves for Advanced AI
Proposes giving advanced AI systems a primary goal of accepting shutdown to address control concerns.
3/10/2026
Explainable and Hardware-Efficient Jamming Detection for 5G Networks Using the Convolutional Tsetlin Machine
Lightweight and explainable jamming detection for 5G networks using Tsetlin machines for RF interference identification.
3/10/2026
AgrI Challenge: A Data-Centric AI Competition for Cross-Team Validation in Agricultural Vision
Agricultural vision competition focused on data-centric AI and model generalization under real-world distribution shifts rather than model design alone.
3/10/2026
Domain-Specific Quality Estimation for Machine Translation in Low-Resource Scenarios
Quality estimation for machine translation in low-resource scenarios across multiple domains and language pairs using prompting techniques.
3/10/2026
Generalization in Online Reinforcement Learning for Mobile Agents
Research on generalization of RL-trained vision-language mobile agents for GUI automation. Addresses lack of standardized benchmarks and open-source RL systems for interactive task learning.
3/10/2026
Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning
Method for preserving LLM safety alignment during fine-tuning by constraining safety-critical tokens, addressing alignment drift.
3/10/2026
Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System
Knowledge-grounded NL2SQL system handling heterogeneous SQL dialects with semantic correctness and dialect-specific syntax compliance.
3/10/2026
SLNet: A Super-Lightweight Geometry-Adaptive Network for 3D Point Cloud Recognition
Lightweight backbone for 3D point cloud recognition using nonparametric adaptive embeddings and geometric modulation.
3/10/2026
The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling
Transformer variant decomposing residual stream into token and context components for interpretable language modeling.
3/10/2026
Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
Framework for auditable fine-tuning and inference of proprietary LLMs on cloud platforms with cryptographic verification.
3/10/2026
Probabilistic Inference and Learning with Stein's Method
Monograph on probabilistic inference and learning theory using Stein's method with applications to variational gradient descent.
3/10/2026
Towards Lightweight Adaptation of Speech Enhancement Models in Real-World Environments
Lightweight on-device adaptation framework for speech enhancement models addressing dynamic acoustic scene changes with frozen backbone.
3/10/2026
Pushing Bistatic Wireless Sensing toward High Accuracy at the Sub-Wavelength Scale
Wireless sensing system addressing bistatic phase offset calibration for sub-wavelength scale contactless sensing.
3/10/2026
DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration
World model learning approach using symmetry exploration to capture physical invariances and conservation laws for extrapolative generalization.
3/10/2026
COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenance
Tool for verifying and explaining RL policies for multi-bridge network maintenance with formal safety guarantees and interpretability.
3/10/2026
GRD-Net: Generative-Reconstructive-Discriminative Anomaly Detection with Region of Interest Attention Module
Generative-reconstructive-discriminative network with ROI attention for industrial surface defect detection and localization.
3/10/2026
Revisiting the LiRA Membership Inference Attack Under Realistic Assumptions
Re-evaluation of LiRA membership inference attacks under realistic assumptions, questioning prior effectiveness claims with realistic threat models.
3/10/2026
A Systematic Comparison of Training Objectives for Out-of-Distribution Detection in Image Classification
Systematic comparison of four training objectives (cross-entropy, prototype, triplet, AP loss) for out-of-distribution detection in image classification.
3/10/2026
Analysis-Driven Procedural Generation of an Engine Sound Dataset with Embedded Control Annotations
Procedural dataset generation framework for engine sounds with embedded control annotations for automotive audio synthesis.
3/10/2026
Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints
Security analysis of large vision-language models vulnerable to semantic slot filling attacks that elicit unsafe outputs.
3/10/2026
MetaSort: An Accelerated Approach for Non-uniform Compression and Few-shot Classification of Neural Spike Waveforms
Algorithm for neural spike waveform compression and classification using adaptive level crossing and latent feature representation.
3/10/2026
MAS-H2: A Hierarchical Multi-Agent System for Holistic Cloud-Native Autoscaling
Hierarchical multi-agent system for Kubernetes autoscaling addressing resource waste through coordinated pod and node scaling policies.
3/10/2026
SMAT: Staged Multi-Agent Training for Co-Adaptive Exoskeleton Control
arXiv paper on Staged Multi-Agent Training (SMAT) for co-adaptive exoskeleton control, using curriculum learning to mirror human motor adaptation.