Papers

New on arXiv

Sat 16 Nov 2024

130 papers

Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical ScenariosLLM agents and tool use → Medical and scientific domain agents
Reasoning over User Preferences: Knowledge Graph-Augmented LLMs for Explainable Conversational RecommendationsLLM reasoning → LLM reasoning for recommendation
Playing Language Game with LLMs Leads to JailbreakingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
LoRA Unlearns More and Retains More (Student Abstract)LLM safety and security → Machine unlearning
S3Mamba: Arbitrary-Scale Super-Resolution via Scaleable State Space ModelState-space sequence models (S4, Mamba) → Vision Mamba backbones
GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual GroundingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
DiHuR: Diffusion-Guided Generalizable Human ReconstructionDiffusion models → 3D, point cloud and scene generation
BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Generating Compositional Scenes via Text-to-image RGBA Instance GenerationDiffusion models → Image generation, text-to-image and editing
SPICA: Retrieving Scenarios for Pluralistic In-Context AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Efficient, Low-Regret, Online Reinforcement Learning for Linear MDPsDeep reinforcement learning methods → RL theory and sample complexity
Watermarking Generative Categorical DataLLM safety and security → Watermarking generated content and models
MetricGold: Leveraging Text-To-Image Latent Diffusion Models for Metric Depth EstimationDiffusion models → 3D, point cloud and scene generation
ViBe: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Improvement in Facial Emotion Recognition using Synthetic Data Generated by Diffusion ModelDiffusion models → Audio, speech and music
Large Vision-Language Models for Remote Sensing Visual Question AnsweringMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Stable Continual Reinforcement Learning via Diffusion-based Trajectory ReplayDiffusion models → Robustness, privacy and adversarial aspects +1
Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language ModelMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
Test-time Conditional Text-to-Image Synthesis Using Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
C-DiffSET: Leveraging Latent Diffusion for SAR-to-EO Image Translation with Confidence-Guided Reliable Object GenerationDiffusion models → Inverse problems and image restoration
Bag of Design Choices for Inference of High-Resolution Masked Generative TransformerDiffusion models → Discrete and text diffusion
Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action RecognitionDiffusion models → Video generation
Hybrid Attention Model Using Feature Decomposition and Knowledge Distillation for Glucose ForecastingKnowledge distillation → Distillation for medical imaging
Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution DetectionDiffusion models → Medical imaging and segmentation
Language Model Evolutionary Algorithms for Recommender Systems: Benchmarks and Algorithm ComparisonsLLM reasoning → LLM reasoning for recommendation
Multi-perspective Contrastive Logit DistillationKnowledge distillation → General knowledge distillation methods
MaskMedPaint: Masked Medical Image Inpainting with Diffusion Models for Mitigation of Spurious CorrelationsDiffusion models → Medical imaging and segmentation
Exploring Feature-based Knowledge Distillation for Recommender System: A Frequency PerspectiveKnowledge distillation → Distillation for recommender systems
Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of ExpertsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
SAM Decoding: Speculative Decoding via Suffix AutomatonEfficient LLM inference and serving → Speculative decoding
BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile DevicesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Empathic Coupling of Homeostatic States for Intrinsic Prosociality
Distributed Collaborative Inference System in Next-Generation Networks and Communication
Fine Tuning Swimming Locomotion Learned from Mosquito Larvae
Post-fusion monolithic hybrid recommender system for suggesting relevant movies to users
Partitioning Message Passing for Graph Fraud Detection
Un-mixing Test-time Adaptation under Heterogeneous Data Streams
LLaSA: Large Language and Structured Data Assistant
Improving training time and GPU utilization in geo-distributed language model training
Enhanced FIWARE-Based Architecture for Cyberphysical Systems With Tiny Machine Learning and Machine Learning Operations: A Case Study on Urban Mobility Systems
Deep Feature Response Discriminative Calibration
Browser Extension for Fake URL Detection
Education in the Era of Neurosymbolic AI
AI-Empowered Human Research Integrating Brain Science and Social Sciences Insights
VayuBuddy: an LLM-Powered Chatbot to Democratize Air Quality Insights
A Novel Approach to Eliminating Hallucinations in Large Language Model-Assisted Causal Discovery
Infrared-Assisted Single-Stage Framework for Joint Restoration and Fusion of Visible and Infrared Images under Hazy Conditions
LLM4DS: Evaluating Large Language Models for Data Science Code Generation
Bias in Large Language Models: Origin, Evaluation, and Mitigation
Constructing accurate machine-learned potentials and performing highly efficient atomistic simulations to predict structural and thermal properties
Attention-based U-Net Method for Autonomous Lane Detection
Targeting Negative Flips in Active Learning using Validation Sets
Evolution of IVR building techniques: from code writing to AI-powered automation
Deep BI-RADS Network for Improved Cancer Detection from Mammograms
ChannelDropBack: Forward-Consistent Stochastic Regularization for Deep Networks
Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms
MpoxVLM: A Vision-Language Model for Diagnosing Skin Lesions from Mpox Virus Infection
FIAS: Feature Imbalance-Aware Medical Image Segmentation with Dynamic Fusion and Mixing Attention
BanglaDialecto: An End-to-End AI-Powered Regional Speech Standardization
Empowering Meta-Analysis: Leveraging Large Language Models for Scientific Synthesis
Developer Perspectives on Licensing and Copyright Issues Arising from Generative AI for Software Development
Large Language Models (LLMs) as Traffic Control Systems at Urban Intersections: A New Paradigm
See-Saw Generative Mechanism for Scalable Recursive Code Generation with Generative AI
NeuroNURBS: Learning Efficient Surface Representations for 3D Solids
Automatic Discovery and Assessment of Interpretable Systematic Errors in Semantic Segmentation
A Novel Adaptive Hybrid Focal-Entropy Loss for Enhancing Diabetic Retinopathy Detection Using Convolutional Neural Networks
CODECLEANER: Elevating Standards with A Robust Data Contamination Mitigation Toolkit
Adaptive Learning of Design Strategies over Non-Hierarchical Multi-Fidelity Models via Policy Alignment
AnimateAnything: Consistent and Controllable Animation for Video Generation
Neighboring Slice Noise2Noise: Self-Supervised Medical Image Denoising from Single Noisy Image Volume
One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
Memory-Efficient Training for Text-Dependent SV with Independent Pre-trained Models
ARM: Appearance Reconstruction Model for Relightable 3D Generation
A Data-Efficient Sequential Learning Framework for Melt Pool Defect Classification in Laser Powder Bed Fusion
GeomCLIP: Contrastive Geometry-Text Pre-training for Molecules
An Oversampling-enhanced Multi-class Imbalanced Classification Framework for Patient Health Status Prediction Using Patient-reported Outcomes
FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations
Conformation Generation using Transformer Flows
DEAL: Decoupled Classifier with Adaptive Linear Modulation for Group Robust Early Diagnosis of MCI to AD Conversion
Information Anxiety in Large Language Models
Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolution
Image-based Outlier Synthesis With Training Data
Anatomy-Guided Radiology Report Generation with Pathology-Aware Regional Prompts
On Reductions and Representations of Learning Problems in Euclidean Spaces
Beyond Feature Mapping GAP: Integrating Real HDRTV Priors for Superior SDRTV-to-HDRTV Conversion
An End-to-End Real-World Camera Imaging Pipeline
MRI Parameter Mapping via Gaussian Mixture VAE: Breaking the Assumption of Independent Pixels
Building Interpretable Climate Emulators for Economics
Steam Turbine Anomaly Detection: An Unsupervised Learning Approach Using Enhanced Long Short-Term Memory Variational Autoencoder
ML2Tuner: Efficient Code Tuning via Multi-Level Machine Learning Models
Can Generic LLMs Help Analyze Child-adult Interactions Involving Children with Autism in Clinical Observation?
Diffusion-Based Semantic Segmentation of Lumbar Spine MRI Scans of Lower Back Pain Patients
Integrated Machine Learning and Survival Analysis Modeling for Enhanced Chronic Kidney Disease Risk Stratification
Chain-of-Programming (CoP) : Empowering Large Language Models for Geospatial Code Generation
Towards a Comprehensive Benchmark for Pathological Lymph Node Metastasis in Breast Cancer Sections
LTCXNet: Advancing Chest X-Ray Analysis with Solutions for Long-Tailed Multi-Label Classification and Fairness Challenges
Digital-Analog Quantum Machine Learning
It Takes Two: Accurate Gait Recognition in the Wild via Cross-granularity Alignment
MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
A Wearable Gait Monitoring System for 17 Gait Parameters Based on Computer Vision

All 130