Papers

New on arXiv

Sat 28 Sep 2024

132 papers

Large Language Model-Driven Cross-Domain Orchestration Using Multi-Agent WorkflowLLM agents and tool use → General LLM agent frameworks and benchmarks
Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience RegularizationDiffusion models → Diffusion and flow policies for robotics +1
Spatial Reasoning and Planning for Deep Embodied AgentsLLM reasoning → Spatial and embodied reasoning +1
Overriding Safety protections of Open-source ModelsLLM safety and security → Safety alignment, refusal and guardrails
FairPIVARA: Reducing and Assessing Biases in CLIP-Based Multimodal ModelsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
Trigger-Based Fragile Model Watermarking for Image Transformation NetworksLLM safety and security → Watermarking generated content and models
Strongly-polynomial time and validation analysis of policy gradient methodsDeep reinforcement learning methods → RL theory and sample complexity
Energy-Efficient Computation with DVFS using Deep Reinforcement Learning for Multi-Task Systems in Edge ComputingDeep reinforcement learning methods → RL for energy, networks and operations
Harnessing Frozen Unimodal Encoders for Flexible Multimodal AlignmentMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory GraphsRetrieval-augmented generation → Agentic RAG, agents and memory +1
HYBRIDMIND: Meta Selection of Natural Language and Symbolic Language for Enhanced LLM ReasoningLLM reasoning → Reasoning benchmarks and evaluation
DOTA: Distributional Test-Time Adaptation of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Efficient Semantic Diffusion Architectures for Model Training on Synthetic EchocardiogramsDiffusion models → Medical imaging and segmentation
MambaEviScrib: Mamba and Evidence-Guided Consistency Enhance CNN Robustness for Scribble-Based Weakly Supervised Ultrasound Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Conditional Image Synthesis with Diffusion Models: A SurveyDiffusion models → Diffusion foundations and sampling
Learning Strategy Representation for Imitation Learning in Multi-Agent GamesOffline RL and imitation learning from data → Imitation learning methods
Visual Question Decomposition on Multimodal Large Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
3D-CT-GPT: Generating 3D Radiology Reports through Integration of Large Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet UpcyclingMixture-of-experts → Multimodal MoE models
FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Perception Compressor: A Training-Free Prompt Compression Framework in Long Context ScenariosEfficient LLM inference and serving → Prompt and context compression
HybridFlow: A Flexible and Efficient RLHF FrameworkLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
TrojVLM: Backdoor Attack Against Vision Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Double Actor-Critic with TD Error-Driven Regularization in Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
Learning to Bridge the Gap: Efficient Novelty Recovery with Planning and Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
RAIL: Reachability-Aided Imitation Learning for Safe Policy ExecutionOffline RL and imitation learning from data → Safe offline RL
Disaggregating Embedding Recommendation Systems with FlexEMR
Environment Scan of Generative AI Infrastructure for Clinical and Translational Science
Test Case-Informed Knowledge Tracing for Open-ended Coding Tasks
Investigating the Impact of Text Summarization on Topic Modeling
Improvement of Spiking Neural Network with Bit Planes and Color Models
Multi-Atlas Brain Network Classification through Consistency Distillation and Complementary Information Fusion
Evaluating Financial Relational Graphs: Interpretation Before Prediction
Thematic Analysis with Open-Source Generative AI and Machine Learning: A New Method for Inductive Qualitative Codebook Development
NeuralQP: A General Hypergraph-based Optimization Framework for Large-scale QCQPs
FluentEditor2: Text-based Speech Editing by Modeling Multi-Scale Acoustic and Prosody Consistency
Performance Evaluation of Tokenizers in Large Language Models for the Assamese Language
Public interest in science or bots? Selective amplification of scientific articles on Twitter
Transferable Unsupervised Outlier Detection Framework for Human Semantic Trajectories
Frequency-adaptive Multi-scale Deep Neural Networks
DelayPTC-LLM: Metro Passenger Travel Choice Prediction under Train Delays with Large Language Models
CycleBNN: Cyclic Precision Training in Binary Neural Networks
Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph
HealthQ: Unveiling Questioning Capabilities of LLM Chains in Healthcare Conversations
MedCLIP-SAMv2: Towards Universal Text-Driven Medical Image Segmentation
Hedging and Approximate Truthfulness in Traditional Forecasting Competitions
Towards Croppable Implicit Neural Representations
INSIGHTBUDDY-AI: Medication Extraction and Entity Linking using Large Language Models and Ensemble Learning
Accelerating Malware Classification: A Vision Transformer Solution
On the universality of neural encodings in CNNs
Language-guided Robust Navigation for Mobile Robots in Dynamically-changing Environments
Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach
See Where You Read with Eye Gaze Tracking and Large Language Model
Secret Use of Large Language Model (LLM)
Advanced Clustering Techniques for Speech Signal Enhancement: A Review and Metanalysis of Fuzzy C-Means, K-Means, and Kernel Fuzzy C-Means Methods
HTML-LSTM: Information Extraction from HTML Tables in Web Pages using Tree-Structured LSTM
Contrastive ground-level image and remote sensing pre-training improves representation learning for natural world imagery
Introducing SDICE: An Index for Assessing Diversity of Synthetic Medical Datasets
Simulation-based Inference with the Python Package sbijax
RMLR: Extending Multinomial Logistic Regression into General Geometries
MicroFlow: An Efficient Rust-Based Inference Engine for TinyML
Generalization and Robustness of the Tilted Empirical Risk
'Simulacrum of Stories': Examining Large Language Models as Qualitative Research Participants
Fast Encoding and Decoding for Implicit Video Representation
A Proximal Modified Quasi-Newton Method for Nonsmooth Regularized Optimization
Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures
Multi-sensor Learning Enables Information Transfer across Different Sensory Data and Augments Multi-modality Imaging
Subject Data Auditing via Source Inference Attack in Cross-Silo Federated Learning
Machine Learning Operations: A Mapping Study
Bridging the Gap in Hybrid Decision-Making Systems
Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks
Membership Privacy Evaluation in Deep Spiking Neural Networks
Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking
G3R: Gradient Guided Generalizable Reconstruction
Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration
Projected Tensor-Tensor Products for Efficient Computation of Optimal Multiway Data Representations
The co-varying ties between networks and item responses via latent variables
Canonical Correlation Guided Deep Neural Network
Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training
Efficient Federated Intrusion Detection in 5G ecosystem using optimized BERT-based model
Co-design of a novel CMOS highly parallel, low-power, multi-chip neural network accelerator
Zero-Shot Multi-Hop Question Answering via Monte-Carlo Tree Search with Large Language Models
Automated conjecturing with TxGraffiti
Interpretable, multi-dimensional Evaluation Framework for Causal Discovery from observational i.i.d. Data
Mind the Gap: Promoting Missing Modality Brain Tumor Segmentation with Alignment
1st Place Solution of Multiview Egocentric Hand Tracking Challenge ECCV2024
Sparse Modelling for Feature Learning in High Dimensional Data
Quantum delegated and federated learning via quantum homomorphic encryption
Steering Prediction via a Multi-Sensor System for Autonomous Racing
Toward Deep Learning-based Segmentation and Quantitative Analysis of Cervical Spinal Cord Magnetic Resonance Images
Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation
Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networks
A Generalized Model for Multidimensional Intransitivity
Scalable Cloud-Native Pipeline for Efficient 3D Model Reconstruction from Monocular Smartphone Images
Fairness Analysis with Shapley-Owen Effects
Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models
Model X-Ray: Detection of Hidden Malware in AI Model Weights using Few Shot Learning
Designing Domain-Specific Large Language Models: The Critical Role of Fine-Tuning in Public Opinion Simulation

All 132