3/10/2026
NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks
Eigenspectral framework analyzing information flow in LLM feed-forward networks through lightweight spectral metrics.
3/10/2026
Swimba: Switch Mamba Model Scales State Space Models
Mixture-of-experts approach for state space models with expert specialization while maintaining computational efficiency.
3/10/2026
Physics-Consistent Neural Networks for Learning Deformation and Director Fields in Microstructured Media with Loss-Based Validation Criteria
Physics-consistent neural networks for Cosserat elasticity modeling deformation and director fields in microstructured materials.
3/10/2026
Joint MDPs and Reinforcement Learning in Coupled-Dynamics Environments
Reinforcement learning formalism for coupled-dynamics environments specifying joint distributions across counterfactual actions.
3/10/2026
Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN Pipelines
Study of graph sparsification impact on GNN pipeline performance and scalability for billion-node graphs.
3/10/2026
Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards
Reinforcement learning approach for chart comprehension in vision-language models using verifiable rewards for symbolic reasoning.
3/10/2026
Learning Quadruped Walking from Seconds of Demonstration
Imitation learning analysis for quadruped locomotion showing effectiveness in small data regimes via limit cycle structure.
3/10/2026
Conditional Unbalanced Optimal Transport Maps: An Outlier-Robust Framework for Conditional Generative Modeling
Optimal transport framework for conditional generative modeling robust to outliers using unbalanced transport.
3/10/2026
NePPO: Near-Potential Policy Optimization for General-Sum Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning algorithm for general-sum games with heterogeneous agent objectives and convergence guarantees.
3/10/2026
Diffusion Controller: Framework, Algorithms and Parameterization
Control-theoretic framework for controllable diffusion generation using linearly-solvable MDPs and reweighting pretrained models.
3/10/2026
RESCHED: Rethinking Flexible Job Shop Scheduling from a Transformer-based Architecture with Simplified States
Transformer-based approach to flexible job shop scheduling using simplified states instead of handcrafted features.
3/10/2026
Resource-Adaptive Federated Text Generation with Differential Privacy
Federated learning method for generating differentially private synthetic text datasets from LLMs for downstream task reuse.
3/10/2026
Interpretable Maximum Margin Deep Anomaly Detection
Deep SVDD improvement for anomaly detection addressing hypersphere collapse and interpretability via maximum margin approach.
3/10/2026
Entropy-Aware On-Policy Distillation of Language Models
On-policy distillation method using entropy-aware objectives for improved knowledge transfer between language models.
3/10/2026
Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction
Dreamer-CDP improves world models with continuous deterministic representation prediction without reconstruction.
3/10/2026
Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
Benchmark environment for studying reward hacking in RL agents through dual-access mathematical reasoning tasks.
3/10/2026
Combining Adam and its Inverse Counterpart to Enhance Generalization of Deep Learning Optimizers
InvAdam optimizer variant that improves generalization by finding flatter minima than standard Adam.
3/10/2026
Agentic Planning with Reasoning for Image Styling via Offline RL
AI agent framework using offline RL for structured planning and reasoning in image editing tasks.
3/10/2026
Making LLMs Optimize Multi-Scenario CUDA Kernels Like Experts
LLM-based system for automated CUDA kernel optimization across ML and scientific computing domains.
3/10/2026
Shaping Parameter Contribution Patterns for Out-of-Distribution Detection
Method to improve OOD detection by diversifying parameter contribution patterns in classifiers.
3/10/2026
A Dual-Graph Spatiotemporal GNN Surrogate for Nonlinear Response Prediction of Reinforced Concrete Beams under Four-Point Bending
GNN surrogate model for simulating reinforced concrete beams under bending using spatiotemporal graphs.
3/10/2026
wDPO: Winsorized Direct Preference Optimization for Robust LLM Alignment
wDPO improves DPO for LLM alignment by using winsorization to handle noisy preference data robustly.
3/10/2026
Margin in Abstract Spaces
Theoretical analysis of margin-based learning in metric spaces and generalization guarantees independent of parameter count.
3/10/2026
Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training
Empirical study on knowledge distillation and difficulty-aware training for improving LLM performance in finance domain.
3/10/2026
LightMedSeg: Lightweight 3D Medical Image Segmentation with Learned Spatial Anchors
Lightweight UNet-style architecture for 3D medical image segmentation with learned spatial anchors and anatomical priors.
3/10/2026
Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation
PT-RAG uses retrieval-augmented generation to predict cellular responses to gene perturbations with improved generalization.
3/10/2026
Rethinking Deep Research from the Perspective of Web Content Distribution Matching
WeDas framework improves web search agents by matching queries to web content distribution structures for better evidence retrieval.
3/10/2026
LF2L: Loss Fusion Horizontal Federated Learning Across Heterogeneous Feature Spaces Using External Datasets Effectively: A Case Study in Second Primary Cancer Prediction
Federated learning approach for predicting secondary cancer using heterogeneous features across hospitals.
3/10/2026
Turning Time Series into Algebraic Equations: Symbolic Machine Learning for Interpretable Modeling of Chaotic Time Series
Symbolic machine learning method to convert chaotic time series into interpretable algebraic equations for forecasting.
3/10/2026
Adaptive Double-Booking Strategy for Outpatient Scheduling Using Multi-Objective Reinforcement Learning
Multi-objective reinforcement learning applied to outpatient clinic scheduling with adaptive double-booking policies.
3/10/2026
AutoResearch-RL: Perpetual Self-Evaluating Reinforcement Learning Agents for Autonomous Neural Architecture Discovery
AutoResearch-RL is an RL agent that autonomously conducts perpetual neural architecture and hyperparameter search via code modification without human supervision.
3/10/2026
Retrieval-Augmented Multi-scale Framework for County-Level Crop Yield Prediction Across Large Regions
Retrieval-augmented multi-scale framework for county-level crop yield prediction addressing regional and temporal challenges in agricultural forecasting.
3/10/2026
Adversarial Latent-State Training for Robust Policies in Partially Observable Domains
Adversarial latent-state training framework for robust policies in partially observable MDPs under latent distribution shift with theoretical guarantees.
3/10/2026
ShakyPrepend: A Multi-Group Learner with Improved Sample Complexity
ShakyPrepend applies differential privacy-inspired tools to multi-group learning for improved sample complexity and adaptation to group structure.
3/10/2026
Norm-Hierarchy Transitions in Representation Learning: When and Why Neural Networks Abandon Shortcuts
Analyzes norm-hierarchy transitions explaining when neural networks transition from spurious shortcuts to structured representations during training.
3/10/2026
Learning Concept Bottleneck Models from Mechanistic Explanations
Learning concept bottleneck models from mechanistic explanations instead of pre-specified or LLM-prompted concepts for improved interpretability and predictive power.
3/10/2026
Learning Clinical Representations Under Systematic Distribution Shift
Addresses representation entanglement between physiologic signal and institutional artifacts in clinical ML under systematic distribution shift from heterogeneous practices.
3/10/2026
Latent Generative Models with Tunable Complexity for Compressed Sensing and other Inverse Problems
Develops tunable-complexity priors for diffusion models and normalizing flows to balance representation error and overfitting in inverse problem solving.
3/10/2026
N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting
N-Tree Diffusion enables efficient long-horizon wildfire risk forecasting by hierarchically extending diffusion models across multiple prediction steps.
3/10/2026
Scaling Laws in the Tiny Regime: How Small Models Change Their Mistakes
Examines neural scaling laws in sub-20M parameter regime for TinyML/edge AI, showing both ConvNets and MobileNetV2 follow power law error scaling.
3/10/2026
Learning to Reflect: Hierarchical Multi-Agent Reinforcement Learning for CSI-Free mmWave Beam-Focusing
Hierarchical multi-agent RL framework for controlling reconfigurable intelligent surfaces in mmWave systems without channel state information estimation overhead.
3/10/2026
Feed m Birds with One Scone: Accelerating Multi-task Gradient Balancing via Bi-level Optimization
Accelerates multi-task learning gradient balancing through bi-level optimization to improve MGDA-type methods for handling task conflicts.
3/10/2026
Deterministic Fuzzy Triage for Legal Compliance Classification and Evidence Retrieval
Deterministic fuzzy triage system for legal compliance classification using dual encoders and transparent bands, demonstrated on contractual evidence HIPAA/NERC-CIP alignment.
3/10/2026
Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic Loss
Generalizes linear autoencoder recommender systems by decoupling expected quadratic loss to improve hyperparameter flexibility beyond prior constraints.
3/10/2026
DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation
DualSpec accelerates LLM-based research agents by speculating on actions during reasoning to reduce latency in long-horizon information-seeking tasks with tool use.
3/10/2026
Data Agent: Learning to Select Data via End-to-End Dynamic Optimization
Data Agent uses end-to-end optimization to dynamically select informative samples during training acceleration.
3/10/2026
Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II
Cost-driven state representation learning for control tasks from high-dimensional partial observations.
3/10/2026
Discrete Tokenization Unlocks Transformers for Calibrated Tabular Forecasting
Tokenization approach enables transformers to outperform gradient boosting on tabular forecasting tasks.
3/10/2026
Contact-Guided 3D Genome Structure Generation of E. coli via Diffusion Transformers
Diffusion transformer framework generates 3D genome structures conditioned on Hi-C contact maps.
3/10/2026
A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling
Unified framework for knowledge transfer between models of different sizes, enabling bidirectional scaling.