3/2/2026
Mode Seeking meets Mean Seeking for Fast Long Video Generation
Proposes training paradigm decoupling local fidelity from long-term coherence for scaling video generation from seconds to minutes.
3/2/2026
TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders
TimeMAE: self-supervised framework for learning transferable time series representations using decoupled masked autoencoders.
3/2/2026
Gradient is All You Need? How Consensus-Based Optimization can be Interpreted as a Stochastic Relaxation of Gradient Descent
Interprets consensus-based optimization as stochastic relaxation of gradient descent, providing theoretical understanding of derivative-free methods.
3/2/2026
Geometric structure of shallow neural networks and constructive ${\mathcal L}^2$ cost minimization
Analyzes geometric structure of shallow ReLU networks and constructs upper bounds for L2 cost minimization without gradient descent.
3/2/2026
DRL-ORA: Distributional Reinforcement Learning with Online Risk Adaption
Framework for distributional reinforcement learning with online risk adaptation for safer decision-making in uncertain environments.
3/2/2026
Less is more -- the Dispatcher/ Executor principle for multi-task Reinforcement Learning
Proposes dispatcher/executor principle for multi-task reinforcement learning that abstracts unnecessary details for better generalization.
3/2/2026
DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Vartiations
Addresses long-tail recognition with unknown test distributions using hierarchical label variation decomposition.
3/2/2026
Joint Distribution-Informed Shapley Values for Sparse Counterfactual Explanations
Introduces COLA framework for generating sparse counterfactual explanations using optimal transport and Shapley-based attribution methods.
3/2/2026
Revisiting Matrix Sketching in Linear Bandits: Achieving Sublinear Regret via Dyadic Block Sketching
Analyzes matrix sketching for linear bandits to reduce computational complexity in high-dimensional online learning problems.
3/2/2026
Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure
Proposes label unlearning method for vertical federated learning using representation-level manifold mixup. Addresses privacy in distributed ML.
3/2/2026
Quantifying Climate Change Impacts on Renewable Energy Generation: A Super-Resolution Recurrent Diffusion Model
Super-resolution recurrent diffusion model for renewable energy generation under climate change impacts.
3/2/2026
Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure
Single-sequence uncertainty estimation method for LLMs addressing computational expense of multi-sequence approaches.
3/2/2026
The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective
Sample complexity analysis for online reinforcement learning in nonlinear continuous state/action spaces.
3/2/2026
InfoBridge: Mutual Information estimation via Bridge Matching
Mutual information estimation method using diffusion bridge models for improved domain transfer problems.
3/2/2026
Semantic Parallelism: Redefining Efficient MoE Inference via Model-Data Co-Scheduling
Novel semantic parallelism approach for efficient MoE model inference via co-scheduling of model and data placement.
3/2/2026
Probabilistic Neural Networks (PNNs) with t-Distributed Outputs: Adaptive Prediction Intervals Beyond Gaussian Assumptions
Probabilistic neural networks using t-distribution outputs for improved prediction intervals beyond Gaussian assumptions.
3/2/2026
What Makes a Reward Model a Good Teacher? An Optimization Perspective
Optimization perspective on reward model quality for RLHF, analyzing factors beyond accuracy that make effective teachers.
3/2/2026
Operator Learning with Domain Decomposition for Geometry Generalization in PDE Solving
Domain decomposition approach for neural operators solving PDEs with improved geometry generalization capabilities.
3/2/2026
Sparsity Forcing: Reinforcing Token Sparsity of MLLMs
Research on enforcing token sparsity in multimodal LLMs to reduce computational overhead while maintaining accuracy.
3/2/2026
PAPN: Proximity Attention Encoder and Pointer Network Decoder for Parcel Pickup Route Prediction
Novel attention mechanism and pointer network for parcel pickup route prediction in logistics optimization.
3/2/2026
Manifold Learning with Normalizing Flows: Towards Regularity, Expressivity and Iso-Riemannian Geometry
Theoretical research on manifold learning with normalizing flows for Riemannian geometry in high-dimensional data.
3/2/2026
Continuous Optimization for Feature Selection with Permutation-Invariant Embedding and Policy-Guided Search
Research on feature selection using permutation-invariant embeddings and policy-guided search with generative models.
3/2/2026
Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows
Lightweight prediction model for LLM-based agentic workflow performance across agent configurations and prompting strategies.
3/2/2026
Apprenticeship learning with prior beliefs using inverse optimization
Framework connecting inverse optimization and inverse reinforcement learning for apprenticeship learning with prior cost function beliefs.
3/2/2026
On the Lipschitz Continuity of Set Aggregation Functions and Neural Networks for Sets
Analysis of Lipschitz continuity properties for neural networks operating on set-valued data.
3/2/2026
Bridging the Performance Gap Between Target-Free and Target-Based Reinforcement Learning
Method bridging target-free and target-based reinforcement learning to reduce memory overhead while maintaining learning stability.
3/2/2026
From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model
Framework converting multimodal LLM generative capabilities into zero-shot discriminative embedding models without extensive pre-training.
3/2/2026
DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
Model merging technique using task vector distillation to improve robustness of multi-task learning across diverse settings.
3/2/2026
Physics-Informed Time-Integrated DeepONet: Temporal Tangent Space Operator Learning for High-Accuracy Inference
Physics-informed DeepONet operator learning combining full rollout and autoregressive approaches for PDE inference.
3/2/2026
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
Theoretically motivated improvement to supervised fine-tuning for LLMs by rectifying reward structure to match RL generalization.
3/2/2026
OM2P: Offline Multi-Agent Mean-Flow Policy
Offline multi-agent reinforcement learning using efficient flow-based policies for time-sensitive deployment.
3/2/2026
Beyond Na\"ive Prompting: Strategies for Improved Context-aided Forecasting with LLMs
Framework of strategies for improving LLM-based forecasting by integrating historical data and textual context with reduced computational cost.
3/2/2026
Federated Nonlinear System Identification
Federated learning approach for nonlinear system identification with theoretical convergence guarantees.
3/2/2026
Efficient Ensemble Conditional Independence Test Framework for Causal Discovery
Ensemble framework for conditional independence testing to improve computational efficiency in constraint-based causal discovery.
3/2/2026
Context and Diversity Matter: The Emergence of In-Context Learning in World Models
Investigation of in-context learning in world models for embodied AI to adapt to novel environmental configurations.
3/2/2026
Activation Function Design Sustains Plasticity in Continual Learning
Study of how activation function design affects plasticity in continual learning to prevent loss of model adaptation.
3/2/2026
ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series Forecasting
Interpretable time series forecasting method using hierarchical prototypes to explain model decision-making.
3/2/2026
Deep Learning for Subspace Regression
Deep learning approach for reduced order modeling via parameter-dependent linear subspace regression.
3/2/2026
In-Context Learning of Temporal Point Processes with Foundation Inference Models
Foundation inference model using in-context learning to predict marked temporal point process event sequences across different systems.
3/2/2026
Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning
Process Reward Models that capture step-by-step reasoning dependencies in LLMs to improve reasoning alignment with final outcomes.
3/2/2026
CMT-Benchmark: A Benchmark for Condensed Matter Theory Built by Expert Researchers
Benchmark dataset of 50 condensed matter theory problems for evaluating LLMs on advanced research-level physics problem-solving.
3/2/2026
Permutation-Invariant Representation Learning for Robust and Privacy-Preserving Feature Selection
Permutation-invariant representation learning for privacy-preserving feature selection using generative intelligence.
3/2/2026
Carr\'e du champ flow matching: better quality-generalisation tradeoff in generative models
Carré du champ flow matching: geometry-aware regularization technique for generative models improving quality-generalization tradeoff.
3/2/2026
Learning Mixtures of Linear Dynamical Systems via Hybrid Tensor-EM Method
Hybrid tensor-EM method for learning mixtures of linear dynamical systems with improved performance on noisy time-series data.
3/2/2026
The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operators
Evaluation of zero-shot super-resolution capabilities in machine-learned operators for modeling continuous physical phenomena.
3/2/2026
Thompson Sampling via Fine-Tuning of LLMs
ToSFiT: Thompson sampling via LLM fine-tuning for Bayesian optimization in large discrete spaces without acquisition function maximization.
3/2/2026
Asymptotically Stable Quaternion-valued Hopfield-structured Neural Network with Periodic Projection-based Supervised Learning Rules
Quaternion-valued Hopfield neural network with supervised learning rules for representing rotations in neural computation.
3/2/2026
Uncertainty-aware data assimilation through variational inference
Variational inference approach for data assimilation combining dynamical models with noisy observations using Gaussian distributions.
3/2/2026
Unified Privacy Guarantees for Decentralized Learning via Matrix Factorization
Differential privacy framework for decentralized learning using matrix factorization to enable collaborative training while preserving privacy.
3/2/2026
FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning
FAPO method for LLM reasoning via reinforcement learning that filters flawed positive rollouts to improve policy optimization with verifiable rewards.