3/26/2026
Multi-Agent Reasoning with Consistency Verification Improves Uncertainty Calibration in Medical MCQA
Multi-agent framework with verification for improving calibration and accuracy in medical multiple-choice question answering.
3/26/2026
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Study evaluating RAG systems on AI policy analysis showing retrieval improvements don't guarantee better answers on complex regulatory documents.
3/26/2026
Moonwalk: Inverse-Forward Differentiation
Inverse-forward differentiation method to reduce memory requirements for backpropagation by avoiding activation storage.
3/26/2026
Coded Computing for Resilient Distributed Computing: A Learning-Theoretic Framework
Learning-theoretic framework for coded computing in distributed systems to handle slow, faulty, or compromised servers.
3/26/2026
Multiway Multislice PHATE: Visualizing Hidden Dynamics of RNNs through Training
Visualization technique for understanding RNN internal dynamics during training using multislice PHATE algorithm.
3/26/2026
An efficient wavelet-based physics-informed neural network for multiscale problems
Physics-informed neural networks using wavelet decomposition to improve training on differential equations with rapid oscillations and steep gradients.
3/26/2026
Symmetry-Guided Memory Augmentation for Efficient Locomotion Learning
arXiv paper on Symmetry-Guided Memory Augmentation (SGMA) improving efficiency of RL-based legged locomotion training.
3/26/2026
Learning to Localize Leakage of Cryptographic Sensitive Variables
arXiv paper on machine learning techniques to detect and localize power/radiation leakage of cryptographic keys from hardware implementations.
3/26/2026
Unicorn: A Universal and Collaborative Reinforcement Learning Approach Towards Generalizable Network-Wide Traffic Signal Control
arXiv paper on multi-agent reinforcement learning for adaptive traffic signal control in heterogeneous urban networks.
3/26/2026
GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks
arXiv paper: GraphOmni benchmark framework evaluating LLM reasoning on graph-theoretic tasks with diverse formats and serializations.
3/26/2026
Explainable embeddings with Distance Explainer
arXiv paper introducing Distance Explainer method for post-hoc interpretability of embedded vector spaces in ML models.
3/26/2026
Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning
arXiv paper on Bottlenecked Transformers: KV cache consolidation technique for scaling inference-time reasoning in LLMs.
3/26/2026
Navigating the Latent Space Dynamics of Neural Models
arXiv paper interpreting neural networks as dynamical systems on latent manifolds, analyzing autoencoder vector fields.
3/26/2026
EHR2Path: Scalable Modeling of Longitudinal Patient Pathways from Multimodal Electronic Health Records
arXiv paper on scalable longitudinal patient pathway modeling from multimodal EHR data using neural networks for condition forecasting.
3/26/2026
Reward Is Enough: LLMs Are In-Context Reinforcement Learners
Research paper demonstrating LLMs perform in-context reinforcement learning during inference. ICRL prompting framework enables inference-time self-improvement.
3/26/2026
TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness
TimeRecipe benchmarks module-level effectiveness of components in time-series forecasting architectures.
3/26/2026
DART: A Server-side Plug-in for Resource-efficient Robust Federated Learning
DART adds server-side robustness to federated learning for edge devices without expensive client-side computation.
3/26/2026
Who to Trust? Aggregating Client Predictions in Federated Distillation
Theoretical analysis of federated distillation with weighted aggregation of client predictions under class mismatch.
3/26/2026
PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment
PromptLoop refines prompts for diffusion models using sequential reinforcement learning feedback during sampling.
3/26/2026
Fiaingen: A financial time series generative method matching real-world data quality
Generative method for synthetic financial time series data to address data shortage in ML models for trading and investment.
3/26/2026
Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries
Proposes future summary pretraining for LLMs as alternative to next-token prediction, addressing limitations in long-horizon reasoning and planning tasks.
3/26/2026
Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift
Addresses distribution shift in time-series forecasting by identifying concept drift and temporal shift, proposing mitigation strategies for generalization.
3/26/2026
OffSim: Offline Simulator for Model-based Offline Inverse Reinforcement Learning
OffSim proposes model-based offline inverse RL framework to learn environmental dynamics and reward functions from offline data without manual definition.
3/26/2026
Deep Reinforcement Learning for Dynamic Origin-Destination Matrix Estimation in Microscopic Traffic Simulations Considering Credit Assignment
Applies deep RL to dynamic origin-destination matrix estimation in traffic simulations, addressing credit assignment across temporal vehicle dynamics.
3/26/2026
Uncertainty Makes It Stable: Curiosity-Driven Quantized Mixture-of-Experts
Proposes curiosity-driven quantized Mixture-of-Experts framework using Bayesian uncertainty for deploying neural networks on resource-constrained devices.
3/26/2026
Reward Engineering for Spatial Epidemic Simulations: A Reinforcement Learning Platform for Individual Behavioral Learning
ContagionRL is a Gymnasium-compatible RL platform for reward engineering in spatial epidemic simulations, enabling systematic study of learned behavioral strategies.
3/26/2026
A Hessian-Free Actor-Critic Algorithm for Bi-Level Reinforcement Learning with Applications to LLM Fine-Tuning
Develops Hessian-free actor-critic algorithm for bi-level RL optimization with applications to LLM fine-tuning, addressing second-order information requirements in policy optimization.
3/26/2026
Continual GUI Agents
Introduces continual learning task for GUI agents that must adapt to shifting domains and resolutions over time, identifying failure modes in existing agent methods.
3/26/2026
On Randomness in Agentic Evals
Study of variance in agentic system evaluations using 60,000 trajectories on SWE-Bench-Verified, showing pass@1 estimates vary significantly across runs, questioning single-run reliability assumptions.
3/26/2026
AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering
AceGRPO proposes adaptive curriculum learning with group relative policy optimization for autonomous ML engineering agents, addressing behavioral stagnation in LLM-based agents through RL with efficient data selection.
3/26/2026
Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignment
Framework for learning inspectable alignment through inverse RL without direct policy modification, improving reusability and transparency.
3/26/2026
Smooth Gate Functions for Soft Advantage Policy Optimization
Soft advantage policy optimization using smooth gate functions instead of hard clipping for stable LLM training and reasoning.
3/26/2026
Benchmarking State Space Models, Transformers, and Recurrent Networks for US Grid Forecasting
Comprehensive benchmark comparing state space models, transformers, and recurrent networks for US power grid electricity demand forecasting.
3/26/2026
Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns
Continual learning architecture for LLMs preventing catastrophic forgetting during sequential updates using thalamically routed cortical columns.
3/26/2026
Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parametric Policies
Offline reinforcement learning with parametric policies under general function approximation beyond state-wise mirror descent.
3/26/2026
FedPBS: Proximal-Balanced Scaling Federated Learning Model for Robust Personalized Training for Non-IID Data
Federated learning algorithm addressing statistical heterogeneity and non-IID data with proximal-balanced scaling for privacy-preserving training.
3/26/2026
Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning
Sample-efficient hypergradient estimation for decentralized bi-level reinforcement learning in strategic decision-making and environment design.
3/26/2026
Self-Aware Markov Models for Discrete Reasoning
Masked discrete diffusion model with self-aware Markov transition kernels enabling adaptive reasoning and error correction in discrete tasks.
3/26/2026
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Stable end-to-end joint embedding predictive architecture learning world models from raw pixels without representation collapse.
3/26/2026
MRMS-Net and LMRMS-Net: Scalable Multi-Representation Multi-Scale Networks for Time Series Classification
Multi-scale convolutional architectures for time series classification using diverse input representations and multi-representation learning.
3/26/2026
Two-Time-Scale Learning Dynamics: A Population View of Neural Network Training
Theoretical framework for population-based neural network training combining fast within-model optimization with slower population-level adaptation.
3/26/2026
mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT
Multi-task supervised fine-tuning algorithm addressing heterogeneous overfitting across dataset mixtures with overfitting-aware data allocation.
3/26/2026
Extending Precipitation Nowcasting Horizons via Spectral Fusion of Radar Observations and Foundation Model Priors
Precipitation nowcasting model combining radar observations with weather foundation model priors to improve long-lead forecasting accuracy.
3/26/2026
Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits
Analysis of systematic biases in Chinchilla scaling law fitting method applied to LLM training, showing parameter allocation errors in compute-optimal estimates.
3/26/2026
Cloud-Edge Collaborative Large Models for Robust Photovoltaic Power Forecasting
Cloud-edge collaborative system for photovoltaic power forecasting using large models with latency constraints and robustness to weather distribution shifts.
3/26/2026
DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Models
Method for routing prompts to optimal LLMs/generative models using diversity-aware adaptive selection beyond fidelity scores.
3/26/2026
A Comprehensive Survey on Enterprise Financial Risk Analysis from Big Data and LLMs Perspective
Survey on enterprise financial risk prediction using big data and LLMs, covering AI/computer science approaches to finance and management risk analysis.
3/26/2026
Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets
Theoretical study of feature learning in Leaky ResNets via Hamiltonian mechanics. Analyzes representation geodesics and bottleneck structures in infinite-depth limits.
3/26/2026
Set2Seq Transformer: Temporal and Position-Aware Set Representations for Sequential Multiple-Instance Learning
Set2Seq Transformer for temporal multiple-instance learning with permutation-invariant set representations. Models internal structure and temporal relationships across timesteps.
3/26/2026
General Coded Computing in a Probabilistic Straggler Regime
Coded computing schemes for distributed systems with probabilistic stragglers. Extends exact computation frameworks to handle approximate recovery scenarios.