Papers

New on arXiv

Sun 1 Sep 2024

133 papers

SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression SegmentationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Sample-Efficient Diffusion for Text-To-Speech SynthesisDiffusion models → Audio, speech and music
TrajWeaver: Trajectory Recovery with State Propagation Diffusion ModelDiffusion models → Diffusion and flow policies for robotics
Self-evolving Agents with reflective and memory-augmented abilitiesLLM agents and tool use → Agent memory systems +1
Trustworthy Human-AI Collaboration: Reinforcement Learning with Human Feedback and Physics Knowledge for Safe Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving +2
LanguaShrink: Reducing Token Overhead with PsycholinguisticsEfficient LLM inference and serving → Prompt and context compression
JaxLife: An Open-Ended Agentic SimulatorLLM agents and tool use → General LLM agent frameworks and benchmarks
Diffusion based multi-domain neuroimaging harmonization method with preservation of anatomical detailsDiffusion models → Medical imaging and segmentation
The Dark Side of Human Feedback: Poisoning Large Language Models via User InputsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Generating Media Background Checks for Automated Source Critical ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
ReMOVE: A Reference-free Metric for Object ErasureDiffusion models → 3D, point cloud and scene generation
Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene ClassificationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Accurate Forgetting for All-in-One Image Restoration ModelLLM safety and security → Machine unlearning
Seed-to-Seed: Unpaired Image Translation in Diffusion Seed SpaceDiffusion models → Image generation, text-to-image and editing
A Learnable Agent Collaboration Network Framework for Personalized Multimodal AI Search EngineRetrieval-augmented generation → Agentic RAG, agents and memory +1
Make Your ViT-based Multi-view 3D Detectors Faster via Token CompressionEfficient LLM inference and serving → Token pruning and merging for ViTs
RegTrack: Simplicity Beneath Complexity in Robust Multi-Modal 3D Multi-Object TrackingMixture-of-experts → Vision mixture-of-experts
TinyAgent: Function Calling at the EdgeLLM agents and tool use → Tool learning and function calling
Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
Online Temporal Fusion for Vectorized Map Construction in Mapless Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
Diffusion Policy Policy OptimizationDiffusion models → Diffusion and flow policies for robotics +1
FLUX that Plays MusicDiffusion models → Audio, speech and music
McCaD: Multi-Contrast MRI Conditioned, Adaptive Adversarial Diffusion Model for High-Fidelity MRI SynthesisDiffusion models → Medical imaging and segmentation
Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment
NoPhish: Efficient Chrome Extension for Phishing Detection Using Machine Learning Techniques
ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition
OxML Challenge 2023: Carcinoma classification using data augmentation
Adapting to the AI Disruption: Reshaping the IT Landscape and Educational Paradigms
Redefining Data-Centric Design: A New Approach with a Domain Model and Core Data Ontology for Computational Systems
LIPIDS: Learning-based Illumination Planning In Discretized (Light) Space for Photometric Stereo
Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach
How does the brain compute with probabilities?
From Predictive Importance to Causality: Which Machine Learning Model Reflects Reality?
The Application of Artificial Neural Network Model to Predicting the Acid Mine Drainage from Long-Term Lab Scale Kinetic Test
Enabling Trustworthy Federated Learning in Industrial IoT: Bridging the Gap Between Interpretability and Robustness
Detecting Homeomorphic 3-manifolds via Graph Neural Networks
PuYun: Medium-Range Global Weather Forecasting Using Large Kernel Attention Convolutional Networks
Deep Knowledge-Infusion For Explainable Depression Detection
Equitable Skin Disease Prediction Using Transfer Learning and Domain Adaptation
Detection, Recognition and Pose Estimation of Tabletop Objects
Fisher Information guided Purification against Backdoor Attacks
Harnessing the Power of Semi-Structured Knowledge and LLMs with Triplet-Based Prefiltering for Question Answering
Benchmarking LLM Code Generation for Audio Programming with Visual Dataflow Languages
Dissecting Temporal Understanding in Text-to-Audio Retrieval
Federated Aggregation of Mallows Rankings: A Comparative Analysis of Borda and Lehmer Coding
The Design of an LLM-powered Unstructured Analytics System
Image-to-Lidar Relational Distillation for Autonomous Driving Data
Report Cards: Qualitative Evaluation of Language Models Using Natural Language Summaries
Global Public Sentiment on Decentralized Finance: A Spatiotemporal Analysis of Geo-tagged Tweets from 150 Countries
Universal Approximation of Operators with Transformers and Neural Integral Operators
Entropy Loss: An Interpretability Amplifier of 3D Object Detection Network for Intelligent Driving
You-Only-Randomize-Once: Shaping Statistical Properties in Constraint-based PCG
Building FKG.in: a Knowledge Graph for Indian Food
Curvy: A Parametric Cross-section based Surface Reconstruction
Accelerating Hybrid Agent-Based Models and Fuzzy Cognitive Maps: How to Combine Agents who Think Alike?
Real-Time Weather Image Classification with SVM
LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization
Structural adaptation and rate accelerated estimation in bivariate functional data
Serialized Speech Information Guidance with Overlapped Encoding Separation for Multi-Speaker Automatic Speech Recognition
A Novel Self-Attention-Enabled Weighted Ensemble-Based Convolutional Neural Network Framework for Distributed Denial of Service Attack Classification
Leveraging SeNet and ResNet Synergy within an Encoder-Decoder Architecture for Glioma Detection
Comparing Discrete and Continuous Space LLMs for Speech Recognition
Analysis of a mathematical model for malaria using data-driven approach
Modeling Text-Label Alignment for Hierarchical Text Classification
Unbalanced Fingerprint Classification for Hybrid Fingerprint Orientation Maps
VDPI: Video Deblurring with Pseudo-inverse Modeling
SITUATE: Indoor Human Trajectory Prediction through Geometric Features and Self-Supervised Vision Representation
Rethinking Image Super-Resolution from Training Data Perspectives
Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification
Cooperative Path Planning with Asynchronous Multiagent Reinforcement Learning
Generalized Multi-hop Traffic Pressure for Heterogeneous Traffic Perimeter Control
Self-Supervised Vision Transformers for Writer Retrieval
MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer
Assessing UHD Image Quality from Aesthetics, Distortions, and Saliency
DSLO: Deep Sequence LiDAR Odometry Based on Inconsistent Spatio-temporal Propagation
Interpretable Clustering: A Survey
Simulation of Social Media-Driven Bubble Formation in Financial Markets using an Agent-Based Model with Hierarchical Influence Network
Trust And Balance: Few Trusted Samples Pseudo-Labeling and Temperature Scaled Loss for Effective Source-Free Unsupervised Domain Adaptation
MoManifold: Learning to Measure 3D Human Motion via Decoupled Joint Acceleration Manifolds
AgGym: An agricultural biotic stress simulation environment for ultra-precision management planning
Benign Overfitting under Learning Rate Conditions for α Sub-exponential Input
A Critical Analysis on Machine Learning Techniques for Video-based Human Activity Recognition of Surveillance Systems: A Review
Generating Physical Dynamics under Priors
ContextCite: Attributing Model Generation to Context
Hound: Hunting Supervision Signals for Few and Zero Shot Node Classification on Text-attributed Graph
LPUWF-LDM: Enhanced Latent Diffusion Model for Precise Late-phase UWF-FA Generation on Limited Dataset
BUET Multi-disease Heart Sound Dataset: A Comprehensive Auscultation Dataset for Developing Computer-Aided Diagnostic Systems
Who Would Chatbots Vote For? Political Preferences of ChatGPT and Gemini in the 2024 European Union Elections
Multiscale Color Guided Attention Ensemble Classifier for Age-Related Macular Degeneration using Concurrent Fundus and Optical Coherence Tomography Images
Preference-Based Multi-Agent Reinforcement Learning: Data Coverage and Algorithmic Techniques
Abstaining Machine Learning -- Philosophical Considerations
Seeing Your Speech Style: A Novel Zero-Shot Identity-Disentanglement Face-based Voice Conversion
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation
Curriculum Prompting Foundation Models for Medical Image Segmentation
IAFI-FCOS: Intra- and across-layer feature interaction FCOS model for lesion detection of CT images
Decoupled and Interactive Regression Modeling for High-performance One-stage 3D Object Detection
When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning
MERLiN: Single-Shot Material Estimation and Relighting for Photometric Stereo
Study of Dropout in PointPillars with 3D Object Detection

All 133