Papers

New on arXiv

Thu 26 Dec 2024

130 papers

Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
How Do Artificial Intelligences Think? The Three Mathematico-Cognitive Factors of Categorical Segmentation Operated by Synthetic NeuronsLLM reasoning → Reasoning benchmarks and evaluation
Large Language Models for Market Research: A Data-augmentation ApproachSynthetic data and self-improvement for LLMs → LLM synthetic data generation
Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge NetworksKnowledge distillation → Federated, robust and private distillation
On the Expressiveness and Length Generalization of Selective State-Space Models on Regular LanguagesState-space sequence models (S4, Mamba) → Core SSM architectures for language
CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task AlignmentMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller OnesEfficient LLM inference and serving → Early exit and edge inference
xSRL: Safety-Aware Explainable Reinforcement Learning -- Safety as a Product of ExplainabilityDeep reinforcement learning methods → Safe and constrained RL
Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal QueriesLLM reasoning → Multimodal reasoning
RAG with Differential PrivacyRetrieval-augmented generation → Privacy and security of RAG
VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech SynthesisDiffusion models → Audio, speech and music
Multi-matrix Factorization AttentionEfficient LLM inference and serving → KV cache optimization
Latenrgy: Model Agnostic Latency and Energy Consumption Prediction for Binary ClassifiersLLM safety and security → Membership inference attacks
Optimizing Fantasy Sports Team Selection with Deep Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
NADER: Neural Architecture Design via Multi-Agent CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
Provably Efficient Exploration in Reward Machines with Low RegretDeep reinforcement learning methods → RL theory and sample complexity
Mask Approximation Net: A Novel Diffusion Model Approach for Remote Sensing Change CaptioningDiffusion models → Inverse problems and image restoration
Mobile Robots through Task-Based Human Instructions using Incremental Curriculum LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
Advanced Knowledge Transfer: Refined Feature Distillation for Zero-Shot Quantization in Edge ComputingKnowledge distillation → Knowledge distillation for LLMs
Discrete vs. Continuous Trade-offs for Generative ModelsDiffusion models → Diffusion foundations and sampling
Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly DetectionMixture-of-experts → MoE for time series and graphs
MoPD: Mixture-of-Prompts Distillation for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral AnalysisKnowledge distillation → General knowledge distillation methods
Jasper and Stella: distillation of SOTA embedding modelsRetrieval-augmented generation → Generation and context integration
CL-Attack: Textual Backdoor Attacks via Cross-Lingual TriggersLLM safety and security → Backdoor and data poisoning attacks
Beyond Questionnaires: Video Analysis for Social Anxiety Detection
Explanatory Debiasing: Involving Domain Experts in the Data Generation Process to Mitigate Representation Bias in AI Systems
UniAvatar: Taming Lifelike Audio-Driven Talking Head Generation with Comprehensive Motion and Lighting Control
Minimal Batch Adaptive Learning Policy Engine for Real-Time Mid-Price Forecasting in High-Frequency Trading
BeSplat: Gaussian Splatting from a Single Blurry Image and Event Stream
Constructive approximate transport maps with normalizing flows
Evaluating Convolutional Neural Networks for COVID-19 classification in chest X-ray images
Dynamic Skill Adaptation for Large Language Models
Improving the network traffic classification using the Packet Vision approach
ETTA: Elucidating the Design Space of Text-to-Audio Models
Semi-Supervised Learning from Small Annotated Data and Large Unlabeled Data for Fine-grained PICO Entity Recognition
A Reinforcement Learning-Based Task Mapping Method to Improve the Reliability of Clustered Manycores
Deep learning and whole-brain networks for biomarker discovery: modeling the dynamics of brain fluctuations in resting-state and cognitive tasks
Resolving the Ambiguity of Complete-to-Partial Point Cloud Registration for Image-Guided Liver Surgery with Patches-to-Partial Matching
A novel framework for MCDM based on Z numbers and soft likelihood function
Adaptive Conformal Inference by Betting
From Interests to Insights: An LLM Approach to Course Recommendations Using Natural Language Queries
Manga Generation via Layout-controllable Diffusion
When SAM2 Meets Video Shadow and Mirror Detection
ViPCap: Retrieval Text-Based Visual Prompts for Lightweight Image Captioning
Time Series Foundational Models: Their Role in Anomaly Detection and Prediction
PearSAN: A Machine Learning Method for Inverse Design using Pearson Correlated Surrogate Annealing
Reflective Gaussian Splatting
Improving Generalization for AI-Synthesized Voice Detection
Optimizing Multi-Stage Language Models for Effective Text Retrieval
MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes
Leveraging Self-Training and Variational Autoencoder for Agitation Detection in People with Dementia Using Wearable Sensors
Localized exploration in contextual dynamic pricing achieves dimension-free regret
Sentiment trading with large language models
FineVQ: Fine-Grained User Generated Content Video Quality Assessment
SeaMo: A Season-Aware Multimodal Foundation Model for Remote Sensing
Are Two Hidden Layers Still Enough for the Physics-Informed Neural Networks?
Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning
Learning Cross-Domain Representations for Transferable Drug Perturbations on Single-Cell Transcriptional Responses
Multi-view Fake News Detection Model Based on Dynamic Hypergraph
VINEVI: A Virtualized Network Vision Architecture for Smart Monitoring of Heterogeneous Applications and Infrastructures
Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion
Transformer-Based Wireless Capsule Endoscopy Bleeding Tissue Detection and Classification
Applying the maximum entropy principle to neural networks enhances multi-species distribution models
Towards Better Spherical Sliced-Wasserstein Distance Learning with Data-Adaptive Discriminative Projection Direction
Large Language Models Meet Graph Neural Networks: A Perspective of Graph Mining
Context-Aware Deep Learning for Multi Modal Depression Detection
Developing Explainable Machine Learning Model using Augmented Concept Activation Vector
GAIS: A Novel Approach to Instance Selection with Graph Attention Networks
Multi-Attribute Constraint Satisfaction via Language Model Rewriting
Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models
An End-to-End Depth-Based Pipeline for Selfie Image Rectification
Multi-Head Attention Driven Dynamic Visual-Semantic Embedding for Enhanced Image-Text Matching
Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval
GFG -- Gender-Fair Generation: A CALAMITA Challenge
Revisiting Monocular 3D Object Detection with Depth Thickness Field
Master Stability Functions in Complex Networks
A Lightweight Transformer with Phase-Only Cross-Attention for Illumination-Invariant Biometric Authentication
Referencing Where to Focus: Improving VisualGrounding with Referential Query
To Predict or Not To Predict? Proportionally Masked Autoencoders for Tabular Data Imputation
Generating Editable Head Avatars with 3D Gaussian GANs
AskChart: Universal Chart Understanding through Textual Enhancement
Impact of color and mixing proportion of synthetic point clouds on semantic segmentation
CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting
How Panel Layouts Define Manga: Insights from Visual Ablation Experiments
SILC-EFSA: Self-aware In-context Learning Correction for Entity-level Financial Sentiment Analysis
PlanLLM: Video Procedure Planning with Refinable Large Language Models
SUTrack: Towards Simple and Unified Single Object Tracking
Extended Cross-Modality United Learning for Unsupervised Visible-Infrared Person Re-identification
A Rhetorical Relations-Based Framework for Tailored Multimedia Document Summarization
MVS-GS: High-Quality 3D Gaussian Splatting Mapping via Online Multi-View Stereo
Semantic Residual for Multimodal Unified Discrete Representation
Evaluating Self-Supervised Learning in Medical Imaging: A Benchmark for Robustness, Generalizability, and Multi-Domain Impact
SketchFill: Sketch-Guided Code Generation for Imputing Derived Missing Values
Future Success Prediction in Open-Vocabulary Object Manipulation Tasks Based on End-Effector Trajectories
Spectral Enhancement and Pseudo-Anchor Guidance for Infrared-Visible Person Re-Identification
Stochastic normalizing flows for Effective String Theory
ERGNN: Spectral Graph Neural Network With Explicitly-Optimized Rational Graph Filters
Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models

All 130