Papers

New on arXiv

Sun 29 Dec 2024

125 papers

Dynamic Optimization of Storage Systems Using Reinforcement Learning TechniquesDeep reinforcement learning methods → RL for energy, networks and operations
Towards a Systematic Evaluation of Hallucinations in Large-Vision Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Do Current Video LLMs Have Strong OCR Abilities? A Preliminary StudyMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Zero-Shot Image Restoration Using Few-Step Guidance of Consistency Models (and Beyond)Diffusion models → Inverse problems and image restoration
The intrinsic motivation of reinforcement and imitation learning for sequential tasksOffline RL and imitation learning from data → Imitation learning methods +1
Diminishing Return of Value Expansion MethodsDeep reinforcement learning methods → RL theory and sample complexity
Goal-Conditioned Data Augmentation for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
DPBridge: Latent Diffusion Bridge for Dense PredictionDiffusion models → Diffusion foundations and sampling
LiPUP-MA: A Residential Experience-centric Multi-Agent Framework for Living-in-the-loop Participatory Urban PlanningLLM agents and tool use → Multimodal and embodied agents
ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video UnderstandingEfficient LLM inference and serving → Visual token pruning in multimodal models
Multimodal Variational Autoencoder: a Barycentric ViewMixture-of-experts → Multimodal MoE models
JADE: Joint-aware Latent Diffusion for 3D Human Generative ModelingDiffusion models → 3D, point cloud and scene generation
Single-image reflection removal via self-supervised diffusion modelsDiffusion models → Inverse problems and image restoration
Sub-optimal Learning in Meta-Classifier Attacks: A Study of Membership Inference on Differentially Private Location AggregatesLLM safety and security → Membership inference attacks
CoA-VLA: Improving Vision-Language-Action Models via Visual-Textual Chain-of-AffordanceVision-language-action models → Reasoning and chain-of-thought in VLA
Diff4MMLiTS: Advanced Multimodal Liver Tumor Segmentation via Diffusion-Based Image Synthesis and AlignmentDiffusion models → Medical imaging and segmentation
EraseAnything: Enabling Concept Erasure in Rectified Flow TransformersDiffusion models → Robustness, privacy and adversarial aspects
Multi-Objective Large Language Model UnlearningLLM safety and security → Machine unlearning
Open-Sora: Democratizing Efficient Video Production for AllWorld models → Video-generation world models and simulators
Defending Multimodal Backdoored Models by Repulsive Visual Prompt TuningLLM safety and security → Backdoor and data poisoning attacks
PTQ4VM: Post-Training Quantization for Visual MambaState-space sequence models (S4, Mamba) → Vision Mamba backbones
FairDiffusion: Enhancing Equity in Latent Diffusion Models via Fair Bayesian PerturbationDiffusion models → Medical imaging and segmentation
LLM2: Let Large Language Models Harness System 2 ReasoningLLM reasoning → Reasoning benchmarks and evaluation
Subconscious Robotic Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic ManipulationDeep reinforcement learning methods → Interpretable and logic-guided RL
GreenLLM: Disaggregating Large Language Model Serving on Heterogeneous GPUs for Lower Carbon EmissionsEfficient LLM inference and serving → Serving systems and request scheduling
Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical DomainRetrieval-augmented generation → RAG pipeline design and evaluation
The Synergy of Automated Pipelines with Prompt Engineering and Generative AI in Web Crawling
Dynamic Adaptation in Data Storage: Real-Time Machine Learning for Enhanced Prefetching
Optimizing SSD Caches for Cloud Block Storage Systems Using Machine Learning Approaches
Spin-Weighted Spherical Harmonics for Polarized Light Transport
Is Your Image a Good Storyteller?
Optical Character Recognition using Convolutional Neural Networks for Ashokan Brahmi Inscriptions
Polarimetric BSSRDF Acquisition of Dynamic Faces
ICLR: In-Context Learning of Representations
Adversarial Negotiation Dynamics in Generative Language Models
Ensemble of classifiers for speech evaluation
On Adversarial Robustness of Language Models in Transfer Learning
Predicting Preschoolers' Externalizing Problems with Mother-Child Interaction Dynamics and Deep Learning
Lungmix: A Mixup-Based Strategy for Generalization in Respiratory Sound Classification
"Generative Models for Financial Time Series Data: Enhancing Signal-to-Noise Ratio and Addressing Data Scarcity in A-Share Market
ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis
Training-free Heterogeneous Model Merging
FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition
Matrix Concentration for Random Signed Graphs and Community Recovery in the Signed Stochastic Block Model
Audiopedia: Audio QA with Knowledge
Converting Time Series Data to Numeric Representations Using Alphabetic Mapping and k-mer strategy
Hilbert Curve Based Molecular Sequence Analysis
Towards Explaining Uncertainty Estimates in Point Cloud Registration
Conformable Convolution for Topologically Aware Learning of Complex Anatomical Structures
LEARNER: A Transfer Learning Method for Low-Rank Matrix Estimation
NLP-based Regulatory Compliance -- Using GPT 4.0 to Decode Regulatory Documents
MATEY: multiscale adaptive foundation models for spatiotemporal physical systems
GliLem: Leveraging GliNER for Contextualized Lemmatization in Estonian
Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text Detection
Kryptonite-N: Machine Learning Strikes Back
Testing and Improving the Robustness of Amortized Bayesian Inference for Cognitive Models
Towards Neural No-Resource Language Translation: A Comparative Evaluation of Approaches
Bridging the Gap: A Decade Review of Time-Series Clustering Methods
A Survey on Time-Series Distance Measures
Segmentation of Muscularis Propria in Colon Histopathology Images Using Vision Transformers for Hirschsprung's Disease
Enhancing autonomous vehicle safety in rain: a data-centric approach for clear vision
Counterfactual Samples Constructing and Training for Commonsense Statements Estimation
Distributionally Robust Optimization via Iterative Algorithms in Continuous Probability Spaces
Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD
The Impact of Prompt Programming on Function-Level Code Generation
SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes
Exploiting Aggregation and Segregation of Representations for Domain Adaptive Human Pose Estimation
KVC-onGoing: Keystroke Verification Challenge
Attacks on the neural network and defense methods
Game Theory and Multi-Agent Reinforcement Learning : From Nash Equilibria to Evolutionary Dynamics
MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks
Can Robots "Taste" Grapes? Estimating SSC with Simple RGB Sensors
Dive into Time-Series Anomaly Detection: A Decade Review
Stratify: Unifying Multi-Step Forecasting Strategies
Stochastic gradient descent estimation of generalized matrix factorization models with application to single-cell RNA sequencing data
Random Matrix Theory for Stochastic Gradient Descent
A Multiparty Homomorphic Encryption Approach to Confidential Federated Kaplan Meier Survival Analysis
MR-Occ: Efficient Camera-LiDAR 3D Semantic Occupancy Prediction Using Hierarchical Multi-Resolution Voxel Representation
Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution
Toward Scene Graph and Layout Guided Complex 3D Scene Generation
On the Convergence of Min-Max Langevin Dynamics and Algorithm
A Comprehensive Framework for Reliable Legal AI: Combining Specialized Expert Systems and Adaptive Refinement
Utilizing Multimodal Data for Edge Case Robust Call-sign Recognition and Understanding
Cross-Modal Fusion and Attention Mechanism for Weakly Supervised Video Anomaly Detection
Enhancing Entertainment Translation for Indian Languages using Adaptive Context, Style and LLMs
Image Augmentation Agent for Weakly Supervised Semantic Segmentation
Integrating Natural Language Processing Techniques of Text Mining Into Financial System: Applications and Limitations
Treatment Effect Estimation for Graph-Structured Targets
Unlocking adaptive digital pathology through dynamic feature learning
Multi-Scenario Reasoning: Unlocking Cognitive Autonomy in Humanoid Robots for Multimodal Understanding
ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos
Bringing Objects to Life: training-free 4D generation from 3D objects through view consistent noise
Comparative Performance of Advanced NLP Models and LLMs in Multilingual Geo-Entity Detection
A Multidisciplinary Approach to Telegram Data Analysis
MetricDepth: Enhancing Monocular Depth Estimation with Deep Metric Learning
A Particle Algorithm for Mean-Field Variational Inference
Progressively Exploring and Exploiting Inference Data to Break Fine-Grained Classification Barrier
Natural Language Fine-Tuning
Prot'eg'e: Learn and Generate Basic Makeup Styles with Generative Adversarial Networks (GANs)

All 125