Papers

New on arXiv

Sun 4 Aug 2024

113 papers

Mamba-Spike: Enhancing the Mamba Architecture with a Spiking Front-End for Efficient Temporal Data ProcessingState-space sequence models (S4, Mamba) → Core SSM architectures for language
Leveraging Large Language Models with Chain-of-Thought and Prompt Engineering for Traffic Crash Severity Analysis and InferenceLLM reasoning → Chain-of-thought reasoning for driving
User-in-the-loop Evaluation of Multimodal LLMs for Activity AssistanceLLM reasoning → Multimodal reasoning +1
SelfBC: Self Behavior Cloning for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
Environment Complexity and Nash Equilibria in a Sequential Social DilemmaDeep reinforcement learning methods → RL for games and combinatorial optimization
Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
LDFaceNet: Latent Diffusion-based Network for High-Fidelity Deepfake GenerationDiffusion models → Image generation, text-to-image and editing
Step Saver: Predicting Minimum Denoising Steps for Diffusion Model Image GenerationDiffusion models → Image generation, text-to-image and editing
Latency-Aware Resource Allocation for Mobile Edge Generation and Computing via Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
Robustness of Watermarking on Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image PyramidMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Faster Diffusion Action SegmentationDiffusion models → Video generation
Scenario-based Thermal Management Parametrization Through Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate DiagnosisMultimodal LLMs / vision-language models → Medical vision-language models
Reinforcement Learning for an Efficient and Effective Malware Investigation during Cyber Incident ResponseDeep reinforcement learning methods → Adversarial robustness and RL in finance
DeMansia: Mamba Never Forgets Any TokensState-space sequence models (S4, Mamba) → Vision Mamba backbones
RVI-SAC: Average Reward Off-Policy Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Top K Enhanced Reinforcement Learning Attacks on Heterogeneous Graph Node ClassificationDeep reinforcement learning methods → Adversarial robustness and RL in finance
AnomalySD: Few-Shot Multi-Class Anomaly Detection with Stable Diffusion ModelDiffusion models → Flow matching, time series and science
Dataset Scale and Societal Consistency Mediate Facial Impression Bias in Vision-Language AIDiffusion models → Image generation, text-to-image and editing
Why Perturbing Symbolic Music is Necessary: Fitting the Distribution of Never-used Notes through a Joint Probabilistic Diffusion ModelDiffusion models → Audio, speech and music
Visual Grounding for Object-Level Generalization in Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language ModelsLLM reasoning → Clinical and biomedical applications
MAO: A Framework for Process Model Generation with Multi-Agent OrchestrationLLM agents and tool use → Software engineering coding agents
Re-ENACT: Reinforcement Learning for Emotional Speech Generation using Actor-Critic StrategyDeep reinforcement learning methods → RL training of language and agent models
Cross-layer Attention Sharing for Pre-trained Large Language ModelsEfficient LLM inference and serving → KV cache optimization
AID-DTI: Accelerating High-fidelity Diffusion Tensor Imaging with Detail-preserving Model-based Deep Learning
Multi-Source EEG Emotion Recognition via Dynamic Contrastive Domain Adaptation
Knowledge AI: Fine-tuning NLP Models for Facilitating Scientific Knowledge Extraction and Understanding
Randomized Transport Plans via Hierarchical Fully Probabilistic Design
Inventory problems and the parametric measure mλ
Applications of Scientific Machine Learning for the Analysis of Functionally Graded Porous Beams
Why Rectified Power Unit Networks Fail and How to Improve It: An Effective Field Theory Perspective
Distribution-Level Memory Recall for Continual Learning: Preserving Knowledge and Avoiding Confusion
KAN based Autoencoders for Factor Models
Embedding generalization within the learning dynamics: An approach based-on sample path large deviation theory
Rethinking Affect Analysis: A Protocol for Ensuring Fairness and Consistency
Distilling Machine Learning's Added Value: Pareto Fronts in Atmospheric Applications
SPINEX-TimeSeries: Similarity-based Predictions with Explainable Neighbors Exploration for Time Series and Forecasting Problems
PanoFree: Tuning-Free Holistic Multi-view Image Generation with Cross-view Self-Guidance
Calibration-Disentangled Learning and Relevance-Prioritized Reranking for Calibrated Sequential Recommendation
ARVO: Atlas of Reproducible Vulnerabilities for Open-Source Software
Generative Retrieval with Few-shot Indexing
Video-based Pedestrian and Vehicle Traffic Analysis During Football Games
Analyzing Cultural Representations of Emotions in LLMs through Mixed Emotion Survey
VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces
RICA2: Rubric-Informed, Calibrated Assessment of Actions
A First Look at Chebyshev-Sobolev Series for Digital Ink
Model Hijacking Attack in Federated Learning
Table Transformers for Imputing Textual Attributes
FovEx: Human-Inspired Explanations for Vision Transformers and Convolutional Neural Networks
Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study
Recent Advances in Multi-Choice Machine Reading Comprehension: A Survey on Methods and Datasets
Dise~no de sonido para producciones audiovisuales e historias sonoras en el aula. Hacia una docencia creativa mediante el uso de herramientas inteligentes
Understanding Deep Learning via Notions of Rank
AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos
Effective Demonstration Annotation for In-Context Learning via Language Model-Based Determinantal Point Process
View-consistent Object Removal in Radiance Fields
MoReFun: Past-Movement Guided Motion Representation Learning for Future Motion Prediction and Understanding
KAN-RCBEVDepth: A multi-modal fusion algorithm in object detection for autonomous driving
Improving Neural Surface Reconstruction with Feature Priors from Multi-View Image
A Multi-class Ride-hailing Service Subsidy System Utilizing Deep Causal Networks
ParkingE2E: Camera-based End-to-end Parking Network, from Images to Planning
Winners with Confidence: Discrete Argmin Inference with an Application to Model Selection
MedSyn: LLM-based Synthetic Medical Text Generation Framework
PanicleNeRF: low-cost, high-precision in-field phenotypingof rice panicles with smartphone
EOL: Transductive Few-Shot Open-Set Recognition by Enhancing Outlier Logits
Recovering the state and dynamics of autonomous system with partial states solution using neural networks
3D Single-object Tracking in Point Clouds with High Temporal Variation
DNA-SE: Towards Deep Neural-Nets Assisted Semiparametric Estimation
Fine-tuning multilingual language models in Twitter/X sentiment analysis: a study on Eastern-European V4 languages
Deep Spectral Methods for Unsupervised Ultrasound Image Interpretation
Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation
LEGO: Self-Supervised Representation Learning for Scene Text Images
Enhancing Human Action Recognition and Violence Detection Through Deep Learning Audiovisual Fusion
Mining Path Association Rules in Large Property Graphs (with Appendix)
Contrastive Learning-based Chaining-Cluster for Multilingual Voice-Face Association
Personalized Federated Learning on Heterogeneous and Long-Tailed Data via Expert Collaborative Learning
Individualized multi-horizon MRI trajectory prediction for Alzheimer's Disease
Unsupervised Representation Learning by Balanced Self Attention Matching
Decision Support System to triage of liver trauma
Joint Learning of Emotions in Music and Generalized Sounds
LLaSA: Large Language and E-Commerce Shopping Assistant
What Happens Without Background? Constructing Foreground-Only Data for Fine-Grained Tasks
Towards Automatic Hands-on-Keyboard Attack Detection Using LLMs in EDR Solutions
MetaWearS: A Shortcut in Wearable Systems Lifecycle with Only a Few Shots
Multiview learning with twin parametric margin SVM
Shaping Rewards, Shaping Routes: On Multi-Agent Deep Q-Networks for Routing in Satellite Constellation Networks
AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning
Label Augmentation for Neural Networks Robustness
Single-Point Supervised High-Resolution Dynamic Network for Infrared Small Target Detection
SR-CIS: Self-Reflective Incremental System with Decoupled Memory and Reasoning
Optimal and efficient text counterfactuals using Graph Neural Networks
A multi-task deep learning approach for lane-level pavement performance prediction with segment-level data
ML-EAT: A Multilevel Embedding Association Test for Interpretable and Transparent Social Science
A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios
The Implications of Open Generative Models in Human-Centered Data Science Work: A Case Study with Fact-Checking Organizations
Representation Bias of Adolescents in AI: A Bilingual, Bicultural Study
EqvAfford: SE(3) Equivariance for Point-Level Affordance Learning

All 113