Demajh Dossier

Knowledge-based Automated Generation of Text Synthetics for Improving Text Classification

Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMs

Adversarial Attack on Partial Suppression

Segmentation-Driven Actor-Critic for Visual Reinforcement Learning

Dynamic Mixture-of-Experts for Incremental Graph Learning

Score Augmentation for Diffusion Models

Adaptive Fine-Tuning via Pattern Specialization for Deep Time Series Forecasting

From Traditional ML to Dual-Channel GAT-MLP

A Novel Backdoor Threat to Prompt-based Federated Learning in Multimodal Models

On Understanding of the Dynamics of Model Capacity in Continual Learning

Embedding Is (Almost) All You Need: Retrieval-Augmented Inference for Generalizable Genomic Prediction Tasks

Differentially Private Model-X Knockoffs via Johnson-Lindenstrauss Transform

A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off

Keyword Spotting with Hyper-Matched Filters for Small Footprint Devices

Can SGD Handle Heavy-Tailed Noise?

Data Itself Implicitly Provides Cues to Improve Machine Unlearning

Pre-trained Models Perform the Best When Token Distributions Follow Zipf’s Law

Weighted Conditional Flow Matching

Parametrized Multi-Agent Routing via Deep Attention Models

Robust Active Learning for Noisy Network Alignment

An Interactive World Generation Model

Nonintrusive Watermarking as a Service for X-to-Image DNN

Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

Adaptive Geometrical Gaussian Splatting for 3D Head Avatar

Robust Learning with Noisy Labels via Dynamics Temporal Memory

Dynamic Knowledge Graph Augmented Search Agent via Multi-Reward Reinforcement Learning

Variational Inference and Distribution Trilateration for Long-Tailed Continual Representation Learning

Rethinking the Combination of Channel-independence and Channel-mixing from Representation Learning

A Hierarchical Attention Network for Accurate and Fair Decision Assessment on Semi-Structured Profiles

Hamiltonian framework for Optimal Transport Advection

Unleashing the Potential of Momentum-based Federated Learning in Long-Tailed Scenarios

Robust Adversary-aware Local-Global Attended Bad Actor Detection Sequential Model

Advancing Scalable and Safe Analog Circuit Topology Generation via Federated Learning

Real-Time Emotion Recognition via Multimodal Federated Learning

A Recurrent Neural Operator for Rapid River Forecasting

A Multitasking Few-Shot Learning Approach for Loop Closure in Large Scale SLAM

A Multimodal ECG Dataset from MIMIC-IV-ECG with Signals, Images, Features and Interpretations

Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators

Conditional GAN-Based Mixup for Improved Medical Image Augmentation

Vision-Language-Action Pretraining from Large-Scale Human Videos

Spatio-Temporal Graph Transformer For Internal Ice Layer Thickness Prediction

Scaling Prover-Verifier Games via Concept Encodings

Conditional Handovers via Meta-Learning

Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation

Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing

An Application to Groundwater Heat Transport

Enhancing Metacognition with Label-free Self-evaluation in LRMs

Topic Modeling and Link-Prediction for Material Property Discovery

Differential Mamba

A Quantum-Classical Hybrid Poisoning Attack Detection Method

A Real-Time Digital Twin for Type 1 Diabetes using Simulation-Based Inference

Revisiting Learning Rate Control

Variational Graph Convolutional Neural Networks

Exactly Inverting Language Model Outputs

A ConvLSTM-based approach to automated rhythm-game choreography generation

Test-Time Scaling with Reflective Generative Model

Foundation Auto-Encoders for Time-Series Anomaly Detection

Addressing Label Scarcity through Semi-Supervised Anomaly Detection

Provable Privacy and Generalization Bounds for LLM Post-Training

Distilling Model-Based Multi-Task Reinforcement Learning Agents

ARMOR: Robust Reinforcement Learning-based Control for UAVs under Physical Attacks

M3PO: Massively Multi-Task Model-Based Policy Optimization

Transformers are Graph Neural Networks

ReDeLEx: A Framework for Relational Deep Learning Exploration

EFRame: Deeper Reasoning via Exploration-Filtering-Replay Reinforcement Learning Framework

Where to find Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test

Process mining-driven modeling and simulation to enhance fault diagnosis in cyber-physical systems

Devising a solution to the problems of Cancer awareness in Telangana

Optimizing 4th-Order Runge-Kutta Methods: A Dynamic Heuristic Approach for Efficiency and Low Storage

A Keyword-Based Technique to Evaluate Broad Question Answer Script

mTSBench: Benchmarking Multivariate Time Series Anomaly Detection and Model Selection at Scale