3/25/2026
Contextual Graph Matching with Correlated Gaussian Features
Information-theoretic analysis of contextual graph matching with correlated Gaussian features deriving recovery thresholds.
3/25/2026
ARGENT: Adaptive Hierarchical Image-Text Representations
ARGENT: vision-language model using hyperbolic geometry to capture hierarchical structure of visual and linguistic concepts.
3/25/2026
Contrastive Metric Learning for Point Cloud Segmentation in Highly Granular Detectors
Supervised contrastive metric learning for point cloud segmentation in particle detectors using density-based clustering.
3/25/2026
VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs
VTAM: video-tactile-action model for embodied AI combining visual and tactile signals for contact-rich physical interaction.
3/25/2026
VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions
VISOR: efficiency method for vision-language models using sparse dynamically selected interactions instead of visual token reduction.
3/25/2026
Reliable OOD Virtual Screening with Extrapolatory Pseudo-Label Matching
ML model for virtual screening in drug discovery handling out-of-distribution regions with extrapolatory pseudo-label matching.
3/25/2026
Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency
Minimal Frame Averaging: framework for constructing provably minimal frames achieving exact equivariance in ML systems efficiently.
3/25/2026
Addressing Large Action Spaces in 3D Floorplanning via Spatial Generalization
Continuous action representation for 3D floorplanning addressing scalability bottlenecks from discrete canvas coordinates.
3/25/2026
Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features
Convergence analysis of linear temporal difference learning in reinforcement learning without requiring linearly independent features.
3/25/2026
Dataset Distillation-based Hybrid Federated Learning on Non-IID Data
HFLDD: hybrid federated learning framework using dataset distillation to address non-IID data heterogeneity and label distribution skew.
3/25/2026
DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA
DART-Eval: benchmark for evaluating DNA language models on regulatory DNA prediction, interpretation and design tasks.
3/25/2026
MSA-CNN: A Lightweight Multi-Scale CNN with Attention for Sleep Stage Classification
MSA-CNN: lightweight multi-scale CNN with attention mechanism for automatic sleep stage classification from signal data.
3/25/2026
Streaming Attention Approximation via Discrepancy Theory
BalanceKV: streaming algorithm for approximating attention computations in LLMs using geometric process to reduce memory requirements for long-context generation.
3/25/2026
Federated Learning for Data-Driven Feedforward Control: A Case Study on Vehicle Lateral Dynamics
Federated learning approach for designing data-driven feedforward control in vehicle lateral dynamics using distributed data across multiple systems.
3/25/2026
Multiplicative learning from observation-prediction ratios
Expectation Reflection: multiplicative parameter update paradigm for ML optimization using observation-prediction ratios instead of additive gradient descent.
3/25/2026
Architecture-Aware Minimization (A$^2$M): How to Find Flat Minima in Neural Architecture Search
Analysis of geometric properties and flatness in neural architecture search spaces.
3/25/2026
Leakage and Interpretability in Concept-Based Models
Information-theoretic framework for characterizing and measuring information leakage in concept-based models.
3/25/2026
Two Stage Wireless Federated LoRA Fine-Tuning with Sparsified Orthogonal Updates
Federated LoRA fine-tuning method for large language models with communication-efficient sparsified updates.
3/25/2026
Generalizable Heuristic Generation Through LLMs with Meta-Optimization
Meta-optimization approach for generating generalizable heuristics using LLMs for combinatorial optimization.
3/25/2026
Enhancing generalizability of model discovery across parameter space with multi-experiment equation learning (ME-EQL)
Multi-experiment equation learning method for deriving analytical models from agent-based simulation data.
3/25/2026
Learning The Minimum Action Distance
State representation learning from trajectories using minimum action distance metric for MDPs.
3/25/2026
UniCA: Unified Covariate Adaptation for Time Series Foundation Model
Foundation model adapter for time series forecasting with heterogeneous covariates and multimodal data.
3/25/2026
RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models
Red teaming framework for systematically discovering diverse vulnerabilities in large language models.
3/25/2026
Graph Structure Learning with Privacy Guarantees for Open Graph Data
Privacy-preserving graph structure learning using differential privacy at data publishing stage.
3/25/2026
Reinforcement-Guided Hyper-Heuristic Hyperparameter Optimization for Fair and Explainable Spiking Neural Network-Based Financial Fraud Detection
Spiking neural network framework with hyperparameter optimization for fraud detection.
3/25/2026
TopoMap: A Feature-based Semantic Discriminator of the Topographical Regions in the Test Input Space
Testing framework for deep learning systems using topographical feature discrimination.
3/25/2026
FTTE: Enabling Federated and Resource-Constrained Deep Edge Intelligence
Federated learning framework for training deep models on resource-constrained edge devices.
3/25/2026
Guided Star-Shaped Masked Diffusion
Novel sampling algorithm for masked diffusion models improving generation quality and efficiency.
3/25/2026
On-device Semantic Selection Made Low Latency and Memory Efficient with Monolithic Forwarding
Optimizes on-device semantic selection with cross-encoder rerankers for retrieval, agent memory, and recommendations via monolithic forwarding.
3/25/2026
GUIrilla: A Scalable Framework for Automated Desktop UI Exploration
Scalable framework for automated desktop UI exploration to generate training data for LLM-based GUI understanding and automation.
3/25/2026
Parameter-Free Clustering via Self-Supervised Consensus Maximization (Extended Version)
Parameter-free clustering framework using self-supervised consensus maximization without requiring hyperparameter tuning.
3/25/2026
Data-Efficient and Robust Trajectory Generation through Pathlet Dictionary Learning
Pathlet dictionary learning approach for robust and interpretable trajectory generation in privacy-preserving urban mobility applications.
3/25/2026
Latent Diffusion Inversion Requires Understanding the Latent Space
Studies model inversion attacks on latent diffusion models, showing non-uniform memorization patterns in latent space.
3/25/2026
DP-FedSOFIM: Differentially Private Federated Stochastic Optimization using Regularized Fisher Information Matrix
Proposes differentially private federated learning optimization using regularized Fisher information matrix for faster convergence under privacy constraints.
3/25/2026
Representational Homomorphism Predicts and Improves Compositional Generalization In Transformer Language Model
Introduces homomorphism error metric to measure representational inconsistencies and predict compositional generalization failures in transformers.
3/25/2026
How Understanding Forecast Uncertainty Resolves the Explainability Problem in Machine Learning Models
Analyzes forecast uncertainty in ML model explainability, arguing uncertainty at decision boundaries explains LIME/SHAP instability.
3/25/2026
FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning
Brain-inspired routing method with temporal-ensemble experts for general continual learning from non-stationary data streams.
3/25/2026
T1: One-to-One Channel-Head Binding for Multivariate Time-Series Imputation
Proposes one-to-one channel-head binding method for imputing missing values in multivariate time series data.
3/25/2026
When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift
Studies robustness of PPO reinforcement learning under sensor drift using temporal sequence models to handle partial observability.
3/25/2026
MJ1: Multimodal Judgment via Grounded Verification
arXiv paper MJ1: multimodal judge trained with RL enforcing visual grounding through structured verification chains and counterfactual consistency rewards.
3/25/2026
Rethinking Machine Unlearning: Models Designed to Forget via Key Deletion
arXiv paper proposing key deletion approach for machine unlearning designed at model development stage rather than post-hoc, addressing privacy regulations and data errors.
3/25/2026
PRISM: Demystifying Retention and Interaction in Mid-Training
arXiv paper PRISM: empirical study of mid-training design choices across 7 LLM base models showing consistent +15 to +40 point gains from 27B token sequences.
3/25/2026
Elastic Weight Consolidation Done Right for Continual Learning
arXiv paper systematically analyzing Elastic Weight Consolidation for continual learning, revealing suboptimal importance estimation and proposing improvements.
3/25/2026
MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels
arXiv paper presenting MemReward, graph-based experience memory framework reducing human labeling needs for LLM reward prediction in RL post-training.
3/25/2026
Global Convergence of Multiplicative Updates for the Matrix Mechanism: A Collaborative Proof with Gemini 3
arXiv paper analyzing fixed-point iterations for nuclear norm optimization in private machine learning, proved with Gemini 3 collaboration.
3/25/2026
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
arXiv paper presenting FIPO reinforcement learning algorithm for improving reasoning in LLMs through fine-grained credit assignment beyond outcome-based rewards.
3/25/2026
MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning
arXiv paper proposing Memory-Keyed Attention (MKA) to reduce KV cache memory costs in long-context LLM inference without sacrificing representation quality.
3/25/2026
mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT
Algorithm for optimal multi-task dataset mixture selection in LLM supervised fine-tuning. Addresses heterogeneous learning dynamics and overfitting.
3/25/2026
Uncertainty Quantification for Distribution-to-Distribution Flow Matching in Scientific Imaging
Uncertainty quantification methods for distribution-to-distribution generative models in scientific imaging. Ensures trustworthy cell and medical image generation.
3/25/2026
CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning
Reinforcement learning post-training for virtual cell models to enforce biological constraints. Improves generative model reliability for drug discovery.