Papers

New on arXiv

Sat 7 Dec 2024

133 papers

The Illusion-Illusion: Vision Language Models See Illusions Where There Are NoneMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
MDiFF: Exploiting Multimodal Score-based Diffusion Models for New Fashion Product Performance ForecastingDiffusion models → 3D, point cloud and scene generation
SLA Management in Reconfigurable Multi-Agent RAG: A Systems Approach to Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning +2
LeakAgent: RL-based Red-teaming Agent for LLM Privacy LeakageLLM agents and tool use → Agent threats, guardrails and governance +1
Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable EventsLLM reasoning → Multimodal reasoning +1
Evaluating Hallucination in Text-to-Image Diffusion Models with Scene-Graph based Question-Answering AgentDiffusion models → Medical imaging and segmentation +1
Learning Soft Driving Constraints from Vectorized Scene Embeddings while Imitating Expert TrajectoriesEnd-to-end autonomous driving → Imitation-learning end-to-end planners +2
Combining Genre Classification and Harmonic-Percussive Features with Diffusion Models for Music-Video GenerationDiffusion models → Audio, speech and music
Batch-Max: Higher LLM Throughput using Larger Batch Sizes and KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of ExpertsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
M3PC: Test-time Model Predictive Control for Pretrained Masked Trajectory ModelOffline RL and imitation learning from data → Decision transformers and sequence modeling +1
Efficient Continuous Video Flow Model for Video PredictionDiffusion models → Video generation
Remix-DiT: Mixing Diffusion Transformers for Multi-Expert DenoisingDiffusion models → Diffusion foundations and sampling
Do We Need to Design Specific Diffusion Models for Different Tasks? Try ONE-PICDiffusion models → Diffusion foundations and sampling
Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract ReasoningLLM reasoning → Mathematical reasoning
UMSPU: Universal Multi-Size Phase Unwrapping via Mutual Self-Distillation and Adaptive Boosting Ensemble SegmentersKnowledge distillation → Detection and dense prediction distillation
Neighborhood Commonality-aware Evolution Network for Continuous Generalized Category DiscoveryKnowledge distillation → General knowledge distillation methods
Dif4FF: Leveraging Multimodal Diffusion Models and Graph Neural Networks for Accurate New Fashion Product Performance ForecastingDiffusion models → 3D, point cloud and scene generation
SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of ExpertsMixture-of-experts → MoE in reinforcement learning and robotics
KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language ModelsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Towards 3D Acceleration for low-power Mixture-of-Experts and Multi-Head Attention Spiking TransformersMixture-of-experts → Efficient MoE training and inference systems
Upcycling Noise for Federated UnlearningLLM safety and security → Federated unlearning and poisoning
AI Planning: A Primer and Survey (Preliminary Report)Deep reinforcement learning methods → Deep RL algorithms and representations
Enhancing Sample Generation of Diffusion Models using Noise Level CorrectionDiffusion models → Diffusion foundations and sampling
LATTE: Learning to Think with Vision SpecialistsLLM reasoning → Multimodal reasoning +1
Efficient Distributed Training through Gradient Compression with Sparsification and Quantization Techniques
GAF-FusionNet: Multimodal ECG Analysis via Gramian Angular Fields and Split Attention
STEAM-EEG: Spatiotemporal EEG Analysis with Markov Transfer Fields and Attentive CNNs
LABIIUM: AI-Enhanced Zero-configuration Measurement Automation System
GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents
Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs
Partition of Unity Physics-Informed Neural Networks (POU-PINNs): An Unsupervised Framework for Physics-Informed Domain Decomposition and Mixtures of Experts
The Helicobacter pylori AI-Clinician: Harnessing Artificial Intelligence to Personalize H. pylori Treatment Recommendations
A Neural Model of Rule Discovery with Relatively Short-Term Sequence Memory
Hardware implementation of timely reliable Bayesian decision-making using memristors
Innovative Sentiment Analysis and Prediction of Stock Price Using FinBERT, GPT-4 and Logistic Regression: A Data-Driven Approach
GRUvader: Sentiment-Informed Stock Market Prediction
APS-LSTM: Exploiting Multi-Periodicity and Diverse Spatial Dependencies for Flood Forecasting
Investigating social alignment via mirroring in a system of interacting language models
Detecting Fake News on Social Media: A Novel Reliability Aware Machine-Crowd Hybrid Intelligence-Based Method
TransitGPT: A Generative AI-based framework for interacting with GTFS data using Large Language Models
Leveraging Black-box Models to Assess Feature Importance in Unconditional Distribution
Emulating Clinical Quality Muscle B-mode Ultrasound Images from Plane Wave Images Using a Two-Stage Machine Learning Model
Compositional Image Retrieval via Instruction-Aware Contrastive Learning
Can OpenAI o1 outperform humans in higher-order cognitive thinking?
A Comparative Study on Code Generation with Transformers
Constrained Control for Autonomous Spacecraft Rendezvous: Learning-Based Time Shift Governor
Charting the Shapes of Stories with Game Theory
REGE: A Method for Incorporating Uncertainty in Graph Embeddings
A Scoping Review of ChatGPT Research in Accounting and Finance
Integrating YOLO11 and Convolution Block Attention Module for Multi-Season Segmentation of Tree Trunks and Branches in Commercial Apple Orchards
Proximal Iteration for Nonlinear Adaptive Lasso
A Tiered GAN Approach for Monet-Style Image Generation
Training-Free Bayesianization for Low-Rank Adapters of Large Language Models
Impact of Sunglasses on One-to-Many Facial Identification Accuracy
Finite Element Neural Network Interpolation. Part I: Interpretable and Adaptive Discretization for Solving PDEs
RLZero: Direct Policy Inference from Language Without In-Domain Supervision
PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks
On the effective transfer of knowledge from English to Hindi Wikipedia
Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios
Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes
Jointly RS Image Deblurring and Super-Resolution with Adjustable-Kernel and Multi-Domain Attention
Local Linear Convergence of Infeasible Optimization with Orthogonal Constraints
Flow-based Detection of Botnets through Bio-inspired Optimisation of Machine Learning
Neural network interpretability with layer-wise relevance propagation: novel techniques for neuron selection and visualization
HMGIE: Hierarchical and Multi-Grained Inconsistency Evaluation for Vision-Language Data Cleansing
Leveraging Time-Series Foundation Model for Subsurface Well Logs Prediction and Anomaly Detection
Nearly Solved? Robust Deepfake Detection Requires More than Visual Forensics
No-Free-Lunch Theories for Tensor-Network Machine Learning Models
Graph with Sequence: Broad-Range Semantic Modeling for Fake News Detection
Detecting outliers by clustering algorithms
Training neural networks without backpropagation using particles
Early Diagnosis of Alzheimer's Diseases and Dementia from MRI Images Using an Ensemble Deep Learning
Multimodal Biometric Authentication Using Camera-Based PPG and Fingerprint Fusion
Model-Agnostic AI Framework with Explicit Time Integration for Long-Term Fluid Dynamics Prediction
Shifting NER into High Gear: The Auto-AdvER Approach
Mixture of Hidden-Dimensions Transformer
Hyperedge Anomaly Detection with Hypergraph Neural Network
Biological Brain Age Estimation using Sex-Aware Adversarial Variational Autoencoder with Multimodal Neuroimages
CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds
Rethinking Annotation for Object Detection: Is Annotating Small-size Instances Worth Its Cost?
RefSAM3D: Adapting SAM with Cross-modal Reference for 3D Medical Image Segmentation
Multispecies Animal Re-ID Using a Large Community-Curated Dataset
Global and Dense Embeddings of Earth: Major TOM Floating in the Latent Space
TB-HSU: Hierarchical 3D Scene Understanding with Contextual Affordances
Real-Time 3D Object Detection Using InnovizOne LiDAR and Low-Power Hailo-8 AI Accelerator
From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation
BERTCaps: BERT Capsule for Persian Multi-Domain Sentiment Analysis
Active Sequential Posterior Estimation for Sample-Efficient Simulation-Based Inference
GEE-OPs: An Operator Knowledge Base for Geospatial Code Generation on the Google Earth Engine Platform Powered by Large Language Models
UNet++ and LSTM combined approach for Breast Ultrasound Image Segmentation
Electrocardiogram (ECG) Based Cardiac Arrhythmia Detection and Classification using Machine Learning Algorithms
DM-SBL: Channel Estimation under Structured Interference
Self-Supervised Masked Mesh Learning for Unsupervised Anomaly Detection on 3D Cortical Surfaces
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
STONet: A neural operator for modeling solute transport in micro-cracked reservoirs
Rate-Distortion Optimized Skip Coding of Region Adaptive Hierarchical Transform Coefficients for MPEG G-PCC
From Deterministic to Probabilistic: A Novel Perspective on Domain Generalization for Medical Image Segmentation
A polar coordinate system represents syntax in large language models
Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis

All 133