3/31/2026
Mitigating Backdoor Attacks in Federated Learning Using PPA and MiniMax Game Theory
Federated learning defense using PPA and game theory minimax approaches against backdoor attacks from malicious clients.
3/31/2026
AMIGO: Agentic Multi-Image Grounding Oracle Benchmark
AMIGO benchmark for evaluating agentic vision-language models on long-horizon multi-image grounding tasks through sequential attribute-focused queries.
3/31/2026
FL-PBM: Pre-Training Backdoor Mitigation for Federated Learning
FL-PBM method for detecting and mitigating backdoor attacks in federated learning during pre-training phases.
3/31/2026
Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation
PACE system for backpropagation-free test-time adaptation by optimizing normalization layer parameters using covariance matrix approaches.
3/31/2026
GPU-Accelerated Optimization of Transformer-Based Neural Networks for Real-Time Inference
GPU-accelerated TensorRT inference pipeline for BERT and GPT-2 with mixed-precision optimization achieving 64.4x CPU speedup.
3/31/2026
Stepwise Credit Assignment for GRPO on Flow-Matching Models
Stepwise credit assignment method for GRPO on flow models that differentiates early composition steps from late detail-refinement steps.
3/31/2026
See it to Place it: Evolving Macro Placements with Vision-Language Models
VeoPlace uses vision-language models for chip floorplanning macro placement by leveraging VLM spatial reasoning abilities to complement learning-based approaches.
3/31/2026
Expectation Error Bounds for Transfer Learning in Linear Regression and Linear Neural Networks
Theoretical analysis of transfer learning in linear regression and neural networks with closed-form generalization error bounds.
3/31/2026
Rethinking Language Model Scaling under Transferable Hypersphere Optimization
HyperP introduces hypersphere parameterization for language model scaling with improved training stability compared to first-order optimizer approaches.
3/31/2026
Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation
Analysis of why linear probes and sparse autoencoders fail at compositional generalization under superposition, proposing iterative coding alternatives.
3/31/2026
Temporal Credit Is Free
Research on recurrent network training using temporal credit through hidden states without Jacobian propagation, addressing gradient normalization in online adaptation.
3/31/2026
SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs
SimulCost benchmark evaluates LLM agents on physics simulation tasks with cost-aware metrics, accounting for simulation time and experimental resource usage beyond token costs.
3/31/2026
ReCQR: Incorporating conversational query rewriting to improve Multimodal Image Retrieval
Conversational query rewriting approach for multimodal image retrieval with multi-turn dialogue dataset.
3/31/2026
GeoBlock: Inferring Block Granularity from Dependency Geometry in Diffusion Language Models
GeoBlock infers optimal block sizes for diffusion language models by analyzing token dependency geometry to enable efficient parallel decoding.
3/31/2026
Contextual Graph Representations for Task-Driven 3D Perception and Planning
Method for extracting task-relevant contextual representations from 3D scene graphs for robot planning and perception.
3/31/2026
EVNextTrade: Learning-to-Rank-Based Recommendation of Next Charging Nodes for EV-EV Energy Trading
Learning-to-rank system for recommending charging nodes in peer-to-peer EV energy trading networks.
3/31/2026
Complementarity-Preserving Generative Theory for Multimodal ECG Synthesis: A Quantum-Inspired Approach
Generative theory for synthesizing physiologically consistent multimodal ECG data using quantum-inspired approach.
3/31/2026
EMPD: An Event-based Multimodal Physiological Dataset for Remote Pulse Wave Detection
Benchmark dataset for remote pulse wave detection using event cameras and multimodal physiological sensing.
3/31/2026
PI-Mamba: Linear-Time Protein Backbone Generation via Spectrally Initialized Flow Matching
Physics-informed generative model using Mamba architecture for efficient protein backbone design with linear-time complexity and improved structural fidelity.
3/31/2026
FEMBA on the Edge: Physiologically-Aware Pre-Training, Quantization, and Deployment of a Bidirectional Mamba EEG Foundation Model on an Ultra-low Power Microcontroller
FEMBA: bidirectional Mamba state-space model pre-trained on 21k hours EEG with physiologically-aware objectives for microcontroller deployment.
3/31/2026
Stress Classification from ECG Signals Using Vision Transformer
Vision Transformer applied to stress classification from ECG signals using STFT spectrograms for physiological signal analysis.
3/31/2026
Mixture of Experts with Soft Nearest Neighbor Loss: Resolving Expert Collapse via Representation Disentanglement
Enhanced mixture-of-experts architecture using soft nearest neighbor loss to prevent expert collapse and redundant representations.
3/31/2026
Do Multilingual VLMs Reason Equally? A Cross-Lingual Visual Reasoning Audit for Indian Languages
Cross-lingual evaluation of vision-language models on visual reasoning tasks across Indian languages, revealing performance disparities.
3/31/2026
Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract)
Framework integrating sparse autoencoders with dynamic head pruning in Vision Transformers for interpretable and controllable efficiency.
3/31/2026
TDEC: Deep Embedded Image Clustering with Transformer and Distribution Information
Deep image clustering using Transformers with distribution information fusion to improve clustering on high-dimensional multimedia data.
3/31/2026
From Diffusion To Flow: Efficient Motion Generation In MotionGPT3
MotionGPT3 replaces diffusion with rectified flow objectives for efficient text-driven motion generation with improved convergence.
3/31/2026
Evolutionary Warm-Starts for Reinforcement Learning in Industrial Continuous Control
Evolution strategies warm-start reinforcement learning agents for industrial continuous control using CMA-ES-generated demonstrations.
3/31/2026
LogicDiff: Logic-Guided Denoising Improves Reasoning in Masked Diffusion Language Models
LogicDiff improves reasoning in masked diffusion language models by prioritizing logical connective tokens during inference-time denoising.
3/31/2026
Robot Arm Control via Cognitive Map Learners
Application of cognitive map learners for hierarchical, compositional robot arm control without task-specific retraining.
3/31/2026
BHCast: Unlocking Black Hole Plasma Dynamics from a Single Blurry Image with Long-Term Forecasting
Deep learning framework for forecasting black hole plasma accretion dynamics from single telescope images using long-term sequence modeling.
3/31/2026
Efficient Encrypted Computation in Convolutional Spiking Neural Networks with TFHE
Privacy-preserving inference for spiking neural networks using fully homomorphic encryption to enable encrypted computation.
3/31/2026
Multiverse: Language-Conditioned Multi-Game Level Blending via Shared Representation
Language-conditioned multi-game procedural level generation using shared neural representations across different game domains.
3/31/2026
A Firefly Algorithm for Mixed-Variable Optimization Based on Hybrid Distance Modeling
Adaptation of Firefly Algorithm metaheuristic for optimization problems with mixed continuous, ordinal, and categorical variables.
3/31/2026
Dictionary-based Pathology Mining with Hard-instance-assisted Classifier Debiasing for Genetic Biomarker Prediction from WSIs
Deep learning method for genetic biomarker prediction from pathology images using dictionary-based representations and classifier debiasing.
3/31/2026
Implicit neural representations for larval zebrafish brain microscopy: a reproducible benchmark on the MapZebrain atlas
Benchmark evaluating implicit neural representations for zebrafish brain atlas registration and microscopy reconstruction tasks.
3/31/2026
Calorimeter Shower Superresolution with Conditional Normalizing Flows: Implementation and Statistical Evaluation
Data-driven superresolution technique using conditional normalizing flows to recover fine-grained calorimeter information in high energy physics simulations.
3/31/2026
Arithmetic OOD Failure Unfolds in Stages in Minimal GPTs
Study of why minimal GPTs fail at out-of-distribution arithmetic generalization, revealing staged failures from layout barriers to positional encoding limits.
3/31/2026
Concerning Uncertainty -- A Systematic Survey of Uncertainty-Aware XAI
Survey of uncertainty-aware explainable AI methods, examining integration of uncertainty quantification (Bayesian, Monte Carlo, Conformal) into explanatory pipelines.
3/31/2026
Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation
Controlled evaluation of LLM implementation choices for political text annotation, testing model selection, size, and prompt engineering best practices.
3/31/2026
Comparing Physics-Informed and Neural ODE Approaches for Modeling Nonlinear Biological Systems: A Case Study Based on the Morris-Lecar Model
Comparative evaluation of physics-informed neural networks and neural ODEs for modeling nonlinear neuronal dynamics on Morris-Lecar model.
3/31/2026
Koopman Operator Identification of Model Parameter Trajectories for Temporal Domain Generalization (KOMET)
KOMET: model-agnostic framework using Koopman operators to track parameter evolution and handle temporal domain drift in non-stationary environments.
3/31/2026
Static and Dynamic Approaches to Computing Barycenters of Probability Measures on Graphs
Graph-supported barycenter computation for probability measures using Riemannian geometry for signal processing and machine learning applications.
3/31/2026
Multimodal Deep Learning for Diabetic Foot Ulcer Staging Using Integrated RGB and Thermal Imaging
Multimodal deep learning combining RGB and thermal imaging on Raspberry Pi for diabetic foot ulcer staging classification and monitoring.
3/31/2026
ASTER -- Agentic Science Toolkit for Exoplanet Research
ASTER: agentic toolkit using LLMs for exoplanet research workflows, combining archival queries, literature search, and radiative transfer models.
3/31/2026
Graph Attention Network-Based Detection of Autism Spectrum Disorder
Graph attention network classifier for autism spectrum disorder detection using fMRI brain imaging data and graph convolutional networks.
3/31/2026
Online Statistical Inference of Constant Sample-averaged Q-Learning
Online statistical inference framework for sample-averaged Q-learning to reduce variance and improve stability in reinforcement learning.
3/31/2026
On the Reliability Limits of LLM-Based Multi-Agent Planning
Analysis of reliability limits in LLM-based multi-agent planning systems modeled as decision networks with language-based communication constraints.
3/31/2026
FormalProofBench: Can Models Write Graduate Level Math Proofs That Are Formally Verified?
FormalProofBench: benchmark evaluating whether LLMs can produce formally verified graduate-level mathematical proofs using Lean 4.
3/31/2026
Beyond Freshness and Semantics: A Coupon-Collector Framework for Effective Status Updates
Status update systems for wireless channels with energy constraints, modeling information freshness as expiring coupons for control applications.
3/31/2026
PHONOS: PHOnetic Neutralization for Online Streaming Applications
Speaker anonymization system that neutralizes non-native accents to sound native-like while preserving timbre for real-time streaming applications.