Papers

New on arXiv

Tue 14 May 2024

205 papers

Contextual Emotion Recognition using Large Vision Language ModelsMultimodal LLMs / vision-language models → Multimodal emotion understanding
Challenges in Deploying Long-Context Transformers: A Theoretical Peak Performance AnalysisLLM agents and tool use → Software engineering coding agents +1
Self-supervised vision-langage alignment of deep learning representations for bone X-rays analysisMultimodal LLMs / vision-language models → Medical vision-language models
Efficient Vision-Language Pre-training by Cluster MaskingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure InterpretationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Stable Inverse Reinforcement Learning: Policies from Control Lyapunov LandscapesOffline RL and imitation learning from data → Inverse reinforcement learning +1
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese UnderstandingDiffusion models → Image generation, text-to-image and editing
Reinformer: Max-Return Sequence Modeling for Offline RLOffline RL and imitation learning from data → Decision transformers and sequence modeling
I-CTRL: Imitation to Control Humanoid Robots Through Constrained Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
Enhancing Reinforcement Learning in Sensor Fusion: A Comparative Analysis of Cubature and Sampling-based Integration Methods for Rover Search PlanningDeep reinforcement learning methods → RL for robot navigation and UAV control
Promoting AI Equity in Science: Generalized Domain Prompt Learning for Accessible VLM ResearchMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Thinking Tokens for Language ModelingLLM reasoning → Mathematical reasoning
vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy ImprovementDeep reinforcement learning methods → RL theory and sample complexity
ALMol: Aligned Language-Molecule Translation LLMs through Offline Preference Contrastive OptimisationLLM alignment / RLHF / preference optimisation → Preference optimization for molecular design
A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in MedicineMultimodal LLMs / vision-language models → Medical vision-language models
Optimizing Deep Reinforcement Learning for American Put Option HedgingDeep reinforcement learning methods → Adversarial robustness and RL in finance
Python-Based Reinforcement Learning on Simulink ModelsDeep reinforcement learning methods → Deep RL algorithms and representations
Exploring Graph-based Knowledge: Multi-Level Feature Distillation via Channels Relational GraphKnowledge distillation → Graph neural network distillation
Self-Distillation Improves DNA Sequence InferenceKnowledge distillation → Knowledge distillation for LLMs
Rethinking Scanning Strategies with Vision Mamba in Semantic Segmentation of Remote Sensing Imagery: An Experimental StudyState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Understanding the performance gap between online and offline alignment algorithmsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Stylometric Watermarks for Large Language ModelsLLM safety and security → Watermarking generated content and models
CIER: A Novel Experience Replay Approach with Causal Inference in Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Towards Principled Evaluations of Sparse Autoencoders for Interpretability and ControlMechanistic interpretability → Sparse autoencoder training and evaluation
Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed BenchmarkLLM agents and tool use → Tool learning and function calling +1
SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Deep Reinforcement Learning for Real-Time Ground Delay Program Revision and Corresponding Flight Delay AssignmentsOffline RL and imitation learning from data → Imitation and offline RL for driving +1
Improving Health Information Access in the World's Largest Maternal Mobile Health Program via Bandit Algorithms
Filtering After Shading With Stochastic Texture Filtering
MetaFruit Meets Foundation Models: Leveraging a Comprehensive Multi-Fruit Dataset for Advancing Agricultural Foundation Models
Harnessing XGBoost for Robust Biomarker Selection of Obsessive-Compulsive Disorder (OCD) from Adolescent Brain Cognitive Development (ABCD) data
Navigating LLM Ethics: Advancements, Challenges, and Future Directions
A Prompt-driven Task Planning Method for Multi-drones based on Large Language Model
Sonos Voice Control Bias Assessment Dataset: A Methodology for Demographic Bias Assessment in Voice Assistants
When Large Language Models Meet Optical Networks: Paving the Way for Automation
The Evolution of Darija Open Dataset: Introducing Version 2
Assisted Debate Builder with Large Language Models
QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models
Amplifying Aspect-Sentence Awareness: A Novel Approach for Aspect-Based Sentiment Analysis
Hypergraph: A Unified and Uniform Definition with Application to Chemical Hypergraph and More
Joint Prediction Regions for time-series models
Error-margin Analysis for Hidden Neuron Activation Labels
Scalable Sparse Regression for Model Discovery: The Fast Lane to Insight
Robust Approximate Sampling via Stochastic Gradient Barker Dynamics
LLM-Assisted Rule Based Machine Translation for Low/No-Resource Languages
Learning Correspondence for Deformable Objects
Theoretical Analysis for Expectation-Maximization-Based Multi-Model 3D Registration
What is it for a Machine Learning Model to Have a Capability?
Impact of Design Decisions in Scanpath Modeling
drGT: Attention-Guided Gene Assessment of Drug Response Utilizing a Drug-Cell-Gene Heterogeneous Network
A distribution-free valid p-value for finite samples of bounded random variables
An adaptive approach to Bayesian Optimization with switching costs
Computation-Aware Kalman Filtering and Smoothing
Wearable Sensor-Based Few-Shot Continual Learning on Hand Gestures for Motor-Impaired Individuals via Latent Embedding Exploitation
Gradient-Free Training of Recurrent Neural Networks using Random Perturbations
MTP: A Meaning-Typed Language Abstraction for AI-Integrated Programming
Bird Eye-View to Street-View: A Survey
Learned radio interferometric imaging for varying visibility coverage
Dynamical systems and complex networks: A Koopman operator perspective
Neural Active Learning Meets the Partial Monitoring Framework
Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning
Feature Importance and Explainability in Quantum Machine Learning
CLIP with Quality Captions: A Strong Pretraining for Vision Tasks
ADA-Track++: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association
RS-Reg: Probabilistic and Robust Certified Regression Through Randomized Smoothing
Language-Guided Self-Supervised Video Summarization Using Text Semantic Matching Considering the Diversity of the Video
Large Language Models for Human-Machine Collaborative Particle Accelerator Tuning through Natural Language
The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
A Click-Through Rate Prediction Method Based on Cross-Importance of Multi-Order Features
Automated Repair of AI Code with Large Language Models and Formal Verification
FLEXIBLE: Forecasting Cellular Traffic by Leveraging Explicit Inductive Graph-Based Learning
Automated Deep Learning for Load Forecasting
PromptMind Team at EHRSQL-2024: Improving Reliability of SQL Generation using Ensemble LLMs
PolyGlotFake: A Novel Multilingual and Multimodal DeepFake Dataset
Adversarial Machine Learning Threats to Spacecraft
The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
CinePile: A Long Video Question Answering Dataset and Benchmark
Prospects of Privacy Advantage in Quantum Machine Learning
Ambiguous Annotations: When is a Pedestrian not a Pedestrian?
A Brief Introduction to Causal Inference in Machine Learning
Towards Enhanced RAC Accessibility: Leveraging Datasets and LLMs
Kolmogorov-Arnold Networks (KANs) for Time Series Analysis
Incorporating Clinical Guidelines through Adapting Multi-modal Large Language Model for Prostate Cancer PI-RADS Scoring
Refinement of an Epilepsy Dictionary through Human Annotation of Health-related posts on Instagram
Harnessing the power of longitudinal medical imaging for eye disease prognosis using Transformer-based sequence modeling
Jacobian Regularizer-based Neural Granger Causality
FolkTalent: Enhancing Classification and Tagging of Indian Folk Paintings
EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
Energy-based Hopfield Boosting for Out-of-Distribution Detection
Image to Pseudo-Episode: Boosting Few-Shot Segmentation by Unlabeled Data
Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMs
Distributed Threat Intelligence at the Edge Devices: A Large Language Model-Driven Approach
Hierarchical Resource Partitioning on Modern GPUs: A Reinforcement Learning Approach
From Text to Context: An Entailment Approach for News Stakeholder Classification
Enhancing Blind Video Quality Assessment with Rich Quality-aware Features
A Simple Approach to Differentiable Rendering of SDFs
Targeted Augmentation for Low-Resource Event Extraction
Addressing Misspecification in Simulation-based Inference through Data-driven Calibration
Data-driven Force Observer for Human-Robot Interaction with Series Elastic Actuators using Gaussian Processes
Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory

All 205