Papers

New on arXiv

Tue 12 Nov 2024

242 papers

Mediffusion: Joint Diffusion for Self-Explainable Semi-Supervised Classification and Medical Image GenerationDiffusion models → Medical imaging and segmentation
Structured Pattern Expansion with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
Aligning Visual Contrastive learning models via Preference OptimizationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
Retrieval Augmented Time Series ForecastingRetrieval-augmented generation → Time series and agricultural RAG
Imitation Learning from Observations: An Autoregressive Mixture of Experts ApproachMixture-of-experts → MoE in reinforcement learning and robotics +1
Joint Diffusion models in Continual LearningDiffusion models → Robustness, privacy and adversarial aspects
PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert ModelMixture-of-experts → Expert routing strategies
Latent Space Disentanglement in Diffusion Transformers Enables Precise Zero-shot Semantic EditingDiffusion models → Image generation, text-to-image and editing
Challenges in Guardrailing Large Language Models for ScienceLLM safety and security → Safety alignment, refusal and guardrails
Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph CompletionLLM reasoning → Knowledge- and tool-augmented reasoning
Large Language Models Can Self-Improve in Long-context ReasoningLLM reasoning → Reasoning benchmarks and evaluation +1
A Tale of Two Cities: Pessimism and Opportunism in Offline Dynamic PricingOffline RL and imitation learning from data → Offline RL algorithms
Scaling Properties of Diffusion Models for Perceptual TasksDiffusion models → Image generation, text-to-image and editing
GaussianAnything: Interactive Point Cloud Flow Matching For 3D Object GenerationDiffusion models → 3D, point cloud and scene generation
Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled DataKnowledge distillation → Knowledge distillation for LLMs
LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics EnginesLLM reasoning → Spatial and embodied reasoning
Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet EncodingsDiffusion models → 3D, point cloud and scene generation
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and GenerationDiffusion models → Image generation, text-to-image and editing
Doubly Mild Generalization for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
CT-Mamba: A Hybrid Convolutional State Space Model for Low-Dose CT DenoisingState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Diverse capability and scaling of diffusion and auto-regressive models when learning abstract rulesDiffusion models → Diffusion foundations and sampling
Leveraging Multimodal Models for Enhanced Neuroimaging Diagnostics in Alzheimer's DiseaseMultimodal LLMs / vision-language models → Medical vision-language models
Towards Vision Mixture of Experts for Wildlife Monitoring on the EdgeMixture-of-experts → Vision mixture-of-experts
Scaling policy iteration based reinforcement learning for unknown discrete-time linear systemsDeep reinforcement learning methods → RL theory and sample complexity
Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language ModelsRetrieval-augmented generation → RAG robustness and adaptive retrieval
RedCode: Risky Code Execution and Generation Benchmark for Code AgentsLLM agents and tool use → Agent threats, guardrails and governance
Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
Novel View Synthesis with Pixel-Space Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
Optimizing Traffic Signal Control using High-Dimensional State Representation and Efficient Deep Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space ModelState-space sequence models (S4, Mamba) → Speech and audio SSMs
Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document UnderstandingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
EMPERROR: A Flexible Generative Perception Error Model for Probing Self-Driving PlannersEnd-to-end autonomous driving → Adversarial scenarios and safety testing
OWLed: Outlier-weighed Layerwise Pruning for Efficient Autonomous Driving FrameworkEnd-to-end autonomous driving → VLMs for autonomous driving
Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
World Models: The Safety PerspectiveWorld models → World models for language agents
What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?LLM reasoning → Reasoning benchmarks and evaluation
Mitigating Bias in Queer Representation within Large Language Models: A Collaborative Agent ApproachLLM agents and tool use → Social simulation and multi-agent debate
Leveraging Previous Steps: A Training-free Fast Solver for Flow DiffusionDiffusion models → Diffusion foundations and sampling
Flow Matching Posterior Sampling: A Training-free Conditional Generation for Flow MatchingDiffusion models → Flow matching, time series and science
Constrain Alignment with Sparse AutoencodersLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language ModelsLLM reasoning → Clinical and biomedical applications
Entropy Controllable Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate FactorizationDeep reinforcement learning methods → RL theory and sample complexity
Reinforcement Learning Framework for Quantitative TradingDeep reinforcement learning methods → Adversarial robustness and RL in finance
Zer0-Jack: A Memory-efficient Gradient-based Jailbreaking Method for Black-box Multi-modal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Learning Autonomous Docking Operation of Fully Actuated Autonomous Surface Vessel from Expert dataOffline RL and imitation learning from data → Inverse reinforcement learning
Contrastive Language Prompting to Ease False Positives in Medical Anomaly DetectionMultimodal LLMs / vision-language models → Medical vision-language models
Harmonizing Pixels and Melodies: Maestro-Guided Film Score Generation and Composition Style TransferDiffusion models → Audio, speech and music
Robust Offline Reinforcement Learning for Non-Markovian Decision ProcessesOffline RL and imitation learning from data → Offline RL algorithms
FlowTS: Time Series Generation via Rectified FlowDiffusion models → Flow matching, time series and science
MaDiNet: Mamba Diffusion Network for SAR Target DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Rapid Response: Mitigating LLM Jailbreaks with a Few ExamplesLLM safety and security → Jailbreaking
DiffOP: Reinforcement Learning of Optimization-Based Control Policies via Implicit Policy GradientsDeep reinforcement learning methods → RL theory and sample complexity
Quantifying Knowledge Distillation Using Partial Information DecompositionKnowledge distillation → General knowledge distillation methods
Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectorsDiffusion models → Image generation, text-to-image and editing
BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
BLIP3-KALE: Knowledge Augmented Large-Scale Dense CaptionsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin AttributionDiffusion models → Diffusion foundations and sampling +1
Saving GPU Hours in LLM Inference System Development and Online Workloads with Simulation and DBMS-Inspired Cache Replacement PoliciesLLM agents and tool use → Software engineering coding agents +1
All-in-one Weather-degraded Image Restoration via Adaptive Degradation-aware Self-prompting ModelDiffusion models → Inverse problems and image restoration
Topological Approach for Data Assimilation
EEG-DCNet: A Fast and Accurate MI-EEG Dilated CNN Classification Method
Public Health Advocacy Dataset: A Dataset of Tobacco Usage Videos from Social Media
DG-PPU: Dynamical Graphs based Post-processing of Point Clouds extracted from Knee Ultrasounds
Retrieval of sun-induced plant fluorescence in the O2-A absorption band from DESIS imagery
Deceiving Question-Answering Models: A Hybrid Word-Level Adversarial Approach
NVCiM-PT: An NVCiM-assisted Prompt Tuning Framework for Edge LLMs
Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset
A Social Outcomes and Priorities centered (SOP) Framework for AI policy
DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection
SynapsNet: Enhancing Neuronal Population Dynamics Modeling via Learning Functional Connectivity
GTA: Global Tracklet Association for Multi-Object Tracking in Sports
What Representational Similarity Measures Imply about Decodable Information
An Explainable Machine Learning Approach for Age and Gender Estimation in Living Individuals Using Dental Biometrics
TractoEmbed: Modular Multi-level Embedding framework for white matter tract segmentation
SCORE: Syntactic Code Representations for Static Script Malware Detection
Fault Localization in Deep Learning-based Software: A System-level Approach
Comprehensive and Comparative Analysis between Transfer Learning and Custom Built VGG and CNN-SVM Models for Wildfire Detection
Multi-Agent Stochastic Bandits Robust to Adversarial Corruptions
Tackling Polysemanticity with Neuron Embeddings
EAPCR: A Universal Feature Extractor for Scientific Data without Explicit Feature Relation Patterns
TomoGRAF: A Robust and Generalizable Reconstruction Network for Single-View Computed Tomography
Targeted Maximum Likelihood Estimation for Integral Projection Models in Population Ecology
Adaptive Meta-Learning for Robust Deepfake Detection: A Multi-Agent Framework to Data Drift and Model Generalization
Probably approximately correct high-dimensional causal effect estimation given a valid adjustment set
Emergent field theories from neural networks
On the Role of Speech Data in Reducing Toxicity Detection Bias
Impactful Bit-Flip Search on Full-precision Models
CameraHMR: Aligning People with Perspective
TIPO: Text to Image with Text Presampling for Prompt Optimization
Deep Learning 2.0: Artificial Neurons That Matter -- Reject Correlation, Embrace Orthogonality
Explainable Deep Learning Framework for SERS Bio-quantification
Material Transforms from Disentangled NeRF Representations
Leonardo vindicated: Pythagorean trees for minimal reconstruction of the natural branching structures
Language Models as Causal Effect Generators
Artistic Neural Style Transfer Algorithms with Activation Smoothing
Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech
ExpressivityBench: Can LLMs Communicate Implicitly?
Can adversarial attacks by large language models be attributed?

All 242