Papers

New on arXiv

Fri 8 Dec 2023

225 papers

A Red Teaming Framework for Securing AI in Maritime Autonomous SystemsLLM safety and security → Prompt injection and agent security
PaperQA: Retrieval-Augmented Generative Agent for Scientific ResearchRetrieval-augmented generation → Agentic RAG, agents and memory +1
CMMD: Contrastive Multi-Modal Diffusion for Video-Audio Conditional ModelingDiffusion models → Audio, speech and music
Towards Controlled Table-to-Text Generation with Scientific ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Cross Domain Generative Augmentation: Domain Generalization with Latent Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML ServingEfficient LLM inference and serving → Early exit and edge inference
Emergence and Function of Abstract Representations in Self-Supervised TransformersWorld models → World models for language agents
Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic ModelsDiffusion models → Flow matching, time series and science
GlitchBench: Can large multimodal models detect video game glitches?Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
MotionCrafter: One-Shot Motion Customization of Diffusion ModelsDiffusion models → Video generation
Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual ObjectsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Two Simple Principles for Diffusion-Based Test-Time AdaptationDiffusion models → Diffusion foundations and sampling
DiSK: A Diffusion Model for Structured KnowledgeDiffusion models → Discrete and text diffusion
SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score DistillationDiffusion models → Image generation, text-to-image and editing
Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and PlanningWorld models → World models for language agents +2
PathFinder: Guided Search over Multi-Step Reasoning PathsLLM reasoning → Test-time compute and efficient thinking
Membership Inference Attacks on Diffusion Models via Quantile RegressionDiffusion models → Robustness, privacy and adversarial aspects +1
DreaMoving: A Human Video Generation Framework based on Diffusion ModelsDiffusion models → Video generation
An Autonomous Driving Model Integrated with BEV-V2X Perception, Fusion Prediction of Motion and Occupancy, and Driving Planning, in Complex Traffic IntersectionsEnd-to-end autonomous driving → Cooperative and V2X driving
SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout ControlDiffusion models → 3D, point cloud and scene generation
SparQ Attention: Bandwidth-Efficient LLM InferenceEfficient LLM inference and serving → KV cache optimization
Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class ClassificationSynthetic data and self-improvement for LLMs → Self-training for few-shot NLP
MIMIR: Masked Image Modeling for Mutual Information-based Adversarial RobustnessMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D ParallelismEfficient LLM inference and serving → Early exit and edge inference
SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-AugmentationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
KwaiAgents: Generalized Information-seeking Agent System with Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
MVDD: Multi-View Depth Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
HandDiffuse: Generative Controllers for Two-Hand Interactions via Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate SystemLLM reasoning → Reasoning for agents, planning and code +1
DiffCMR: Fast Cardiac MRI Reconstruction with Diffusion Probabilistic ModelsDiffusion models → Medical imaging and segmentation
Localized Symbolic Knowledge Distillation for Visual Commonsense ModelsKnowledge distillation → Multimodal distillation
Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color ConsistencyDiffusion models → 3D, point cloud and scene generation
Learn to Optimize Denoising Scores for 3D Generation: A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian SplattingDiffusion models → 3D, point cloud and scene generation
Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link PredictionKnowledge distillation → Graph neural network distillation
RS-Corrector: Correcting the Racial Stereotypes in Latent Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
RL Dreams: Policy Gradient Optimization for Score Distillation based 3D GenerationDiffusion models → 3D, point cloud and scene generation
Development and Assessment of Autonomous Vehicles in Both Fully Automated and Mixed Traffic ConditionsEnd-to-end autonomous driving → Cooperative and V2X driving
MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion ModelDiffusion models → Robustness, privacy and adversarial aspects
Fine-Tuning InstructPix2Pix for Advanced Image ColorizationDiffusion models → Image generation, text-to-image and editing
Prospective Role of Foundation Models in Advancing Autonomous Vehicles
Immature Green Apple Detection and Sizing in Commercial Orchards using YOLOv8 and Shape Fitting Techniques
Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks
Emissions Reporting Maturity Model: supporting cities to leverage emissions-related processes through performance indicators and artificial intelligence
Generative Inverse Design of Metamaterials with Functional Responses by Interpretable Learning
TypeFly: Flying Drones with Large Language Model
LLM Interactive Optimization of Open Source Python Libraries -- Case Studies and Generalization
Assessing LLMs for Moral Value Pluralism
Data Scarcity in Recommendation Systems: A Survey
Partial Rewriting for Multi-Stage ASR
A global optimization SAR image segmentation model can be easily transformed to a general ROF denoising model
An Encoding of Abstract Dialectical Frameworks into Higher-Order Logic
Unsupervised Social Event Detection via Hybrid Graph Contrastive Learning and Reinforced Incremental Clustering
AI-driven Structure Detection and Information Extraction from Historical Cadastral Maps (Early 19th Century Franciscean Cadastre in the Province of Styria) and Current High-resolution Satellite and Aerial Imagery for Remote Sensing
Symptom-based Machine Learning Models for the Early Detection of COVID-19: A Narrative Review
An adversarial attack approach for eXplainable AI evaluation on deepfake detection models
Decoding Mean Field Games from Population and Environment Observations By Gaussian Processes
An Experimental Study: Assessing the Combined Framework of WavLM and BEST-RQ for Text-to-Speech Synthesis
Deep Bayes Factors
Rethinking materials simulations: Blending direct numerical simulations with neural operators
Large-scale Training of Foundation Models for Wearable Biosignals
ODES: Domain Adaptation with Expert Guidance for Online Medical Image Segmentation
Guaranteed Trust Region Optimization via Two-Phase KL Penalization
Disentangled Latent Representation Learning for Tackling the Confounding M-Bias Problem in Causal Inference
Generative Network Layer for Communication Systems with Artificial Intelligence
On the Performance of Temporal Difference Learning With Neural Networks
The logic of NTQR evaluations of noisy AI agents: Complete postulates and logically consistent error correlations
Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook
Higher-Order Equivariant Neural Networks for Charge Density Prediction in Materials
Model Extraction Attacks Revisited
Estimation Sample Complexity of a Class of Nonlinear Continuous-time Systems
Exploring Parity Challenges in Reinforcement Learning through Curriculum Learning with Noisy Labels
Rational Kriging
Toward Scalable and Transparent Multimodal Analytics to Study Standard Medical Procedures: Linking Hand Movement, Proximity, and Gaze Data
Learning 3D Particle-based Simulators from RGB-D Videos
Unmixing Optical Signals from Undersampled Volumetric Measurements by Filtering the Pixel Latent Variables
Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation
Neither hype nor gloom do DNNs justice
A Review of Machine Learning Methods Applied to Video Analysis Systems
PixLore: A Dataset-driven Approach to Rich Image Captioning
High-Quality Live Video Streaming via Transcoding Time Prediction and Preset Selection
Transition Path Sampling with Boltzmann Generator-based MCMC Moves
Artificial Neural Nets and the Representation of Human Concepts
ProsDectNet: Bridging the Gap in Prostate Cancer Detection via Transrectal B-mode Ultrasound Imaging
A Data-Driven Framework for Improving Public EV Charging Infrastructure: Modeling and Forecasting
MPC-Inspired Reinforcement Learning for Verifiable Model-Free Control
Multi-view Inversion for 3D-aware Generative Adversarial Networks
Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding
Better, Not Just More: Data-Centric Machine Learning for Earth Observation
360deg Volumetric Portrait Avatar
Learning to be Simple
AI Competitions and Benchmarks: The life cycle of challenges and benchmarks
Disentangled Clothed Avatar Generation from Text Descriptions
Noise Adaptor in Spiking Neural Networks
Human-in-the-Loop Visual Re-ID for Population Size Estimation
Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors
SlimSAM: 0.1% Data Makes Segment Anything Slim
Towards On-device Learning on the Edge: Ways to Select Neurons to Update under a Budget Constraint
X2-Softmax: Margin Adaptive Loss Function for Face Recognition

All 225