3/17/2026
M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling
M²RNN introduces matrix-valued hidden states in RNNs to achieve greater expressive power than transformers for language modeling tasks.
3/17/2026
From Specification to Architecture: A Theory Compiler for Knowledge-Guided Machine Learning
Theory compiler framework automates translation of formal domain knowledge into neural network architectural constraints with correctness guarantees.
3/17/2026
SPARQ: Spiking Early-Exit Neural Networks for Energy-Efficient Edge AI
SPARQ framework combines spiking neural networks with quantization-aware training and RL-guided early exits for energy-efficient edge AI deployment.
3/17/2026
From $\boldsymbol{\log\pi}$ to $\boldsymbol{\pi}$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight
Bilateral Decoupled Decay improves soft clipping in LLM reasoning with RLVR, addressing gradient divergence and enabling better exploration during policy optimization.
3/17/2026
ES-Merging: Biological MLLM Merging via Embedding Space Signals
ES-Merging merges biological multimodal LLMs using embedding space signals to enable cross-modal scientific discovery beyond single-modality specialization.
3/17/2026
Graph-Based Deep Learning for Intelligent Detection of Energy Losses, Theft, and Operational Inefficiencies in Oil & Gas Production Networks
Spatiotemporal graph-based deep learning for detecting energy losses, theft, and inefficiencies in oil and gas production networks under distribution shifts.
3/17/2026
Towards One-for-All Anomaly Detection for Tabular Data
OFA-TAD proposes generalist one-for-all anomaly detection for tabular data with cross-domain generalization, replacing dataset-specific training approaches.
3/17/2026
MBD: A Model-Based Debiasing Framework Across User, Content, and Model Dimensions
Model-based debiasing framework for recommendation systems addressing heterogeneous biases across user, content, and model dimensions in ranking aggregation.
3/17/2026
Zoom to Essence: Trainless GUI Grounding by Inferring upon Interface Elements
Trainless GUI grounding for MLLM-based agents using element-level inference to map natural language to UI components without fine-tuning or large datasets.
3/17/2026
STAG-CN: Spatio-Temporal Apiary Graph Convolutional Network for Disease Onset Prediction in Beehive Sensor Networks
Graph convolutional network for disease prediction in beehives using spatio-temporal modeling of inter-hive relationships from sensor networks.
3/17/2026
On the (Generative) Linear Sketching Problem
Addresses linear sketching problem for data streaming, achieving near-perfect recovery from compact sketch summaries with lightweight computational procedures.
3/17/2026
Geometric and Topological Deep Learning for Predicting Thermo-mechanical Performance in Cold Spray Deposition Process Modeling
Geometric deep learning framework using GNNs to predict cold spray particle impact responses from simulation data for deposition process modeling.
3/17/2026
Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention
Combines causal representation learning with local sparse attention for system identification, enabling interpretable deep learning of dynamical systems without predefined function libraries.
3/17/2026
Unlearning-based sliding window for continual learning under concept drift
Unlearning-based sliding window approach for continual learning under concept drift, enabling models to adapt to non-stationary data streams without explicit task boundaries.
3/17/2026
Predicting Stress-strain Behaviors of Additively Manufactured Materials via Loss-based and Activation-based Physics-informed Machine Learning
Physics-informed ML framework predicts stress-strain behavior of additively manufactured materials by combining data-driven models with physical constraints.
3/17/2026
Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models
Proposes trust-region search algorithm for aligning diffusion and flow models to target rewards at inference time without requiring differentiable reward models.
3/17/2026
Visualizing Critic Match Loss Landscapes for Interpretation of Online Reinforcement Learning Control Algorithms
Visualizes critic loss landscapes in online actor-critic reinforcement learning to improve interpretability of algorithm performance under changing system dynamics.
3/17/2026
Learning to Order: Task Sequencing as In-Context Optimization
Demonstrates deep neural networks can meta-learn task sequencing from few demonstrations, enabling generalization to new sequencing problems without task-specific training.
3/17/2026
CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad
CausalEvolve improves LLM-based AI agents for open-ended scientific discovery by adding causal guidance and knowledge organization mechanisms to program evolution.
3/17/2026
Adapting Critic Match Loss Landscape Visualization to Off-policy Reinforcement Learning
Extends critic match loss landscape visualization from online to off-policy reinforcement learning to reveal optimization geometry in critic learning.
3/17/2026
FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference
FlashHead provides efficient drop-in replacement for classification head in language model inference, reducing parameters and compute by ~50%.
3/17/2026
A Multi-Scale Graph Learning Framework with Temporal Consistency Constraints for Financial Fraud Detection in Transaction Networks under Non-Stationary Conditions
Multi-scale graph learning framework for fraud detection in transaction networks handling sparse anomalies and temporal drift.
3/17/2026
A Loss Landscape Visualization Framework for Interpreting Reinforcement Learning: An ADHDP Case Study
Loss landscape visualization framework for interpreting reinforcement learning algorithms, demonstrated on critic-based control methods.
3/17/2026
Delightful Policy Gradient
Delightful policy gradient method that addresses variance issues in policy gradient updates by accounting for action likelihood under current policy.
3/17/2026
Proactive Routing to Interpretable Surrogates with Distribution-Free Safety Guarantees
Proactive routing system that selects between black-box models and interpretable surrogates with distribution-free safety guarantees.
3/17/2026
Anterior's Approach to Fairness Evaluation of Automated Prior Authorization System
Fairness evaluation framework for automated prior authorization systems addressing demographic differences in clinical decision-making.
3/17/2026
A Methodology for Thermal Limit Bias Predictability Through Artificial Intelligence
Deep learning methodology to predict and correct thermal limit bias in boiling water reactors for nuclear power plant operations.
3/17/2026
EARCP: Self-Regulating Coherence-Aware Ensemble Architecture for Sequential Decision Making -- Ensemble Auto-Regule par Coherence et Performance
EARCP ensemble architecture dynamically weights heterogeneous expert models based on performance and inter-model coherence for sequential decision making.
3/17/2026
AgentTrace: Causal Graph Tracing for Root Cause Analysis in Deployed Multi-Agent Systems
AgentTrace provides causal graph tracing for post-hoc failure diagnosis in deployed multi-agent systems through execution log analysis.
3/17/2026
Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic Planning
Chain-of-Trajectories framework enables content-aware sampling schedules in diffusion models via graph-theoretic planning without additional training.
3/17/2026
Cross-RAG: Zero-Shot Retrieval-Augmented Time Series Forecasting via Cross-Attention
Cross-RAG applies retrieval-augmented generation with cross-attention to improve zero-shot time series forecasting using foundation models.
3/17/2026
Training-Free Generation of Protein Sequences from Small Family Alignments via Stochastic Attention
Training-free protein sequence generation using stochastic attention over Hopfield energy without requiring training or pretraining data.
3/17/2026
Multimodal Deep Learning for Early Prediction of Patient Deterioration in the ICU: Integrating Time-Series EHR Data with Clinical Notes
Multimodal deep learning approach combining time-series EHR data and clinical notes for predicting patient deterioration in ICU settings.
3/17/2026
DeFRiS: Silo-Cooperative IoT Applications Scheduling via Decentralized Federated Reinforcement Learning
DeFRiS applies decentralized federated reinforcement learning for IoT application scheduling across heterogeneous devices while preserving privacy.
3/17/2026
GNNVerifier: Graph-based Verifier for LLM Task Planning
GNNVerifier uses graph neural networks to verify and correct task plans generated by LLMs in autonomous agent systems, reducing hallucinations.
3/17/2026
CAMD: Coverage-Aware Multimodal Decoding for Efficient Reasoning of Multimodal Large Language Models
CAMD proposes coverage-aware decoding for multimodal LLMs to allocate compute efficiently by identifying easy vs hard reasoning cases.
3/17/2026
Understanding the geometry of deep learning with decision boundary volume
Method to measure decision boundary geometry of neural networks using local surface volumes to analyze model accuracy and robustness properties.
3/17/2026
POLCA: Stochastic Generative Optimization with LLM
POLCA framework uses LLMs as optimizers to automatically improve complex systems like prompts and multi-turn agents through numerical rewards and text feedback.
3/17/2026
HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregation
HO-SFL proposes hybrid-order split federated learning to reduce memory costs of backpropagation on edge devices while maintaining convergence speed.
3/17/2026
Orthogonal Subspace Clustering: Enhancing High-Dimensional Data Analysis through Adaptive Dimensionality Reduction and Efficient Clustering
Orthogonal Subspace Clustering method for high-dimensional data using matrix decomposition and factor analysis with theoretical guarantees.
3/17/2026
LaPro-DTA: Latent Dual-View Drug Representations and Salient Protein Feature Extraction for Generalizable Drug--Target Affinity Prediction
LaPro-DTA framework for generalizable drug-target affinity prediction using latent dual-view drug representations and salient protein features.
3/17/2026
GARCH-FIS: A Hybrid Forecasting Model with Dynamic Volatility-Driven Parameter Adaptation
GARCH-FIS hybrid model combining fuzzy inference with GARCH for financial time series forecasting with dynamic parameter adaptation.
3/17/2026
Multi-Task Genetic Algorithm with Multi-Granularity Encoding for Protein-Nucleotide Binding Site Prediction
Multi-task genetic algorithm with multi-granularity encoding for protein-nucleotide binding site prediction.
3/17/2026
Universe Routing: Why Self-Evolving Agents Need Epistemic Control
Universe Routing framework addressing epistemic control in self-evolving agents by managing epistemologically incompatible reasoning frameworks.
3/17/2026
OpenReservoirComputing: GPU-Accelerated Reservoir Computing in JAX
OpenReservoirComputing: Python library for GPU-accelerated reservoir computing in JAX with automatic differentiation and JIT compilation.
3/17/2026
Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks
Theoretical analysis of dataset distillation showing how gradient-based learning extracts and encodes task-relevant information into synthetic data.
3/17/2026
Ablate and Rescue: A Causal Analysis of Residual Stream Hyper-Connections
Mechanistic analysis of multi-stream transformer architectures with manifold-constrained hyper-connections using ablation and causal methods.
3/17/2026
Real-Time Driver Safety Scoring Through Inverse Crash Probability Modeling
SafeDriver-IQ framework for real-time driver safety scoring using inverse crash probability modeling with continuous risk quantification.
3/17/2026
IntegratingWeather Foundation Model and Satellite to Enable Fine-Grained Solar Irradiance Forecasting
Two-stage multimodal framework combining weather foundation models and satellite data for fine-grained solar irradiance forecasting.
3/17/2026
Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning
Sample-efficient hypergradient estimation method for decentralized bi-level reinforcement learning with leader-follower agents.