3/2/2026
Actor-Critic Pretraining for Proximal Policy Optimization
Actor-critic pretraining approach for PPO that leverages expert data to reduce environment interactions required for RL training.
3/2/2026
Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parameteric Policies
Theoretical investigation of offline reinforcement learning with general function approximation and parametric policies beyond state-wise methods.
3/2/2026
Learning to maintain safety through expert demonstrations in settings with unknown constraints: A Q-learning perspective
Q-learning approach for learning safe policies from expert demonstrations with unknown constraints in constrained MDPs.
3/2/2026
FedNSAM:Consistency of Local and Global Flatness for Federated Learning
FedNSAM addresses sharpness-aware minimization in federated learning under high data heterogeneity, ensuring both local and global model flatness.
3/2/2026
LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding
LK Losses directly optimize acceptance rate in speculative decoding for LLM inference, improving upon KL divergence proxy objectives for draft model training.
3/2/2026
Hierarchical Concept-based Interpretable Models
Hierarchical Concept Embedding Models improve interpretability of deep neural networks by mapping inputs to human-interpretable concept representations with inter-concept relationships.
3/2/2026
Learning Generation Orders for Masked Discrete Diffusion Models via Variational Inference
Learns optimal generation orders for masked discrete diffusion models via variational inference to balance parallel generation and sample quality.
3/2/2026
Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments
Outlines vision for foundation world models as persistent compositional representations enabling agents to learn and adapt in open worlds.
3/2/2026
RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models
Proposes RewardUQ framework for uncertainty-aware reward models in LLM alignment that reduces annotation costs and prevents overoptimization.
3/2/2026
pathsig: A GPU-Accelerated Library for Truncated and Projected Path Signatures
Introduces pathsig, a PyTorch-native GPU-accelerated library for computing path signatures as trainable features for sequential data.
3/2/2026
Adaptive Correlation-Weighted Intrinsic Rewards for Reinforcement Learning
Proposes ACWI framework that adaptively balances intrinsic and extrinsic rewards online for sparse reward reinforcement learning exploration.
3/2/2026
Agentic AI-RAN: Enabling Intent-Driven, Explainable and Self-Evolving Open RAN Intelligence
Surveys agentic AI systems with planning, tool use, and self-management capabilities applied to Open RAN network control and optimization.
3/2/2026
Learning with a Budget: Identifying the Best Arm with Resource Constraints
Studies best arm identification problem with heterogeneous resource costs and constraints across multiple resource types.
3/2/2026
What You Read is What You Classify: Highlighting Attributions to Text and Text-Like Inputs
Proposes explainable AI method for discrete token inputs like text using attribution highlighting to identify important tokens in transformers.
3/2/2026
Multi-Objective Reinforcement Learning for Large-Scale Tote Allocation in Human-Robot Collaborative Fulfillment Centers
Applies multi-objective reinforcement learning to optimize container consolidation in human-robot collaborative fulfillment centers.
3/2/2026
An Efficient Unsupervised Federated Learning Approach for Anomaly Detection in Heterogeneous IoT Networks
Proposes federated learning approach for anomaly detection in heterogeneous IoT networks while preserving privacy through distributed training.
3/2/2026
Adaptive Combinatorial Experimental Design: Pareto Optimality for Decision-Making and Inference
Investigates trade-off between regret minimization and statistical power in combinatorial multi-armed bandits using Pareto optimality framework.
3/2/2026
Time Series Foundation Models as Strong Baselines in Transportation Forecasting: A Large-Scale Benchmark Analysis
arXiv paper benchmarking general-purpose time-series foundation models for zero-shot transportation forecasting across multiple datasets.
3/2/2026
Histopathology Image Normalization via Latent Manifold Compaction
arXiv paper on Latent Manifold Compaction for unsupervised harmonization of histopathology images across different batch effects and scanners.
3/2/2026
Coverage-Aware Web Crawling for Domain-Specific Supplier Discovery via a Web--Knowledge--Web Pipeline
arXiv paper proposing Web-Knowledge-Web pipeline for discovering suppliers in specialized industries via iterative web crawling and knowledge base integration.
3/2/2026
Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations
Analyzes limitations of standard identifiability metrics (MCC, DCI, R²) on synthetic benchmarks, revealing implicit structural assumptions in representation learning evaluation.
3/2/2026
Memory Caching: RNNs with Growing Memory
Memory caching architecture enabling RNNs with growing memory capacity and subquadratic complexity as alternative to Transformers for sequence modeling.
3/2/2026
Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation
Low-rank approximation method (LoRA-Pre) for optimizer memory efficiency in Adam and Muon, reducing overhead for large language model training.
3/2/2026
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
Agentic RL system using LLMs for high-performance CUDA kernel generation at scale, outcompeting traditional compiler-based approaches.
3/2/2026
Pacing Opinion Polarization via Graph Reinforcement Learning
Graph reinforcement learning approach to moderate opinion polarization in social networks under Friedkin-Johnsen model with improved scalability.
3/2/2026
On De-Individuated Neurons: Continuous Symmetries Enable Dynamic Topologies
Methodology for dynamic neural networks using isotropic activation functions enabling real-time architectural growth and shrinkage via symmetry-principled primitives.
3/2/2026
Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory
Improves Laplace mechanism for differentially private SGD in high-dimensional models using majorization theory, applicable to LLM fine-tuning.
3/2/2026
Few-Shot Continual Learning for 3D Brain MRI with Frozen Foundation Models
Few-shot continual learning approach for 3D brain MRI using frozen foundation models with task-specific LoRA modules for tumor segmentation and brain age estimation.
3/2/2026
Causal Identification from Counterfactual Data: Completeness and Bounding Results
Completeness and bounding results for causal identification using counterfactual data from Layer 3 of Pearl's Causal Hierarchy.
3/2/2026
VaSST: Variational Inference for Symbolic Regression using Soft Symbolic Trees
Probabilistic framework for symbolic regression using variational inference over soft symbolic trees for scientific discovery with uncertainty quantification.
3/2/2026
Construct, Merge, Solve & Adapt with Reinforcement Learning for the min-max Multiple Traveling Salesman Problem
Hybrid reinforcement learning approach (RL-CMSA) for solving min-max multiple traveling salesman problems with iterative construction and adaptation.
3/2/2026
Hyperdimensional Cross-Modal Alignment of Frozen Language and Image Models for Efficient Image Captioning
Efficient image captioning via hyperdimensional cross-modal alignment of frozen language and vision models without multimodal fine-tuning.
3/2/2026
Moment Matters: Mean and Variance Causal Graph Discovery from Heteroscedastic Observational Data
Causal discovery method distinguishing whether variables influence the mean versus variance of other variables in heteroscedastic data.
3/2/2026
Geodesic Semantic Search: Learning Local Riemannian Metrics for Citation Graph Retrieval
Retrieval system learning node-specific Riemannian metrics for geometry-aware semantic search on citation graphs.
3/2/2026
General Bayesian Policy Learning
General Bayes framework for policy learning where decision rules are the target rather than outcome prediction.
3/2/2026
Any Model, Any Place, Any Time: Get Remote Sensing Foundation Model Embeddings On Demand
Platform for standardized access to remote sensing foundation model embeddings across heterogeneous model formats and interfaces.
3/2/2026
From Static Benchmarks to Dynamic Protocol: Agent-Centric Text Anomaly Detection for Evaluating LLM Reasoning
Dynamic benchmarking protocol where AI agents autonomously generate, validate, and solve problems to evaluate LLM reasoning capabilities beyond static datasets.
3/2/2026
GLUScope: A Tool for Analyzing GLU Neurons in Transformer Language Models
Open-source interpretability tool for analyzing gated activation functions (SwiGLU) in transformer neurons across recent language models.
3/2/2026
Enhancing Continual Learning for Software Vulnerability Prediction: Addressing Catastrophic Forgetting via Hybrid-Confidence-Aware Selective Replay for Temporal LLM Fine-Tuning
Addresses catastrophic forgetting in continual fine-tuning of LLMs for vulnerability detection in source code, using selective replay with LoRA on temporal distribution shifts.
3/2/2026
MI$^2$DAS: A Multi-Layer Intrusion Detection Framework with Incremental Learning for Securing Industrial IoT Networks
MI²DAS: multi-layer intrusion detection framework for IIoT with incremental learning to detect novel attacks in dynamic environments.
3/2/2026
Exploring Robust Intrusion Detection: A Benchmark Study of Feature Transferability in IoT Botnet Attack Detection
Benchmark study evaluating cross-domain transferability of flow-based feature sets across IoT and IIoT datasets for intrusion detection.
3/2/2026
RF-Agent: Automated Reward Function Design via Language Agent Tree Search
RF-Agent: automated reward function design for reinforcement learning using LLM-based tree search to optimize low-level control tasks.
3/2/2026
Experience-Guided Self-Adaptive Cascaded Agents for Breast Cancer Screening and Diagnosis with Reduced Biopsy Referrals
BUSD-Agent: cascaded multi-agent framework for breast ultrasound screening and diagnosis reducing biopsy referrals through selective decision-making.
3/2/2026
Learning to Build: Autonomous Robotic Assembly of Stable Structures Without Predefined Plans
Autonomous robotic assembly framework using reinforcement learning for constructing stable structures without predefined plans.
3/2/2026
Benchmarking BERT-based Models for Sentence-level Topic Classification in Nepali Language
Benchmarking 10 BERT variants for Nepali sentence-level topic classification, evaluating multilingual and Indic-specific models.
3/2/2026
Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
Jailbreak Foundry: multi-agent system translating jailbreak papers into executable modules for unified benchmarking and reproducible LLM robustness evaluation.
3/2/2026
Data Driven Optimization of GPU efficiency for Distributed LLM Adapter Serving
Data-driven optimization pipeline for GPU efficiency in distributed LLM adapter serving, maximizing throughput with concurrent adapter hosting.
3/2/2026
Unsupervised Baseline Clustering and Incremental Adaptation for IoT Device Traffic Profiling
Two-stage unsupervised pipeline for IoT device traffic profiling with incremental model adaptation using density-based clustering.
3/2/2026
The Subjectivity of Monoculture
Analysis of monoculture in LLMs showing agreement metrics depend on subjective baseline assumptions for independence.
3/2/2026
Artificial Agency Program: Curiosity, compression, and communication in agents
Artificial Agency Program: research agenda for building resource-bounded AI agents driven by curiosity-as-learning-progress and human-tool integration.