Papers

New on arXiv

Wed 6 Dec 2023

257 papers

Understanding Representations Pretrained with Auxiliary Losses for Embodied Agent PlanningOffline RL and imitation learning from data → Imitation learning methods
Language Model Alignment with Elastic ResetLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Understanding (Un)Intended Memorization in Text-to-Image Generative ModelsDiffusion models → Diffusion foundations and sampling
Combating the effects of speed and delays in end-to-end self-drivingEnd-to-end autonomous driving → End-to-end system architecture +1
The Potential of Vision-Language Models for Content Moderation of Children's VideosMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Controllable Human-Object Interaction SynthesisDiffusion models → Video generation
Inpaint3D: 3D Scene Content Generation using 2D Inpainting DiffusionDiffusion models → 3D, point cloud and scene generation
LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction TuningDiffusion models → Diffusion and flow policies for robotics
AVID: Any-Length Video Inpainting with Diffusion ModelDiffusion models → 3D, point cloud and scene generation
LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent EcosystemLLM agents and tool use → GUI and mobile agents
Improving Activation Steering in Language Models with Mean-CentringMechanistic interpretability → Activation steering methods
SYNC-CLIP: Synthetic Data Make CLIP Generalize Better in Data-Limited ScenariosMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
AnimateZero: Video Diffusion Models are Zero-Shot Image AnimatorsDiffusion models → Video generation
On the Robustness of Large Multimodal Models Against Image Adversarial AttacksMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
FAAC: Facial Animation Generation with Anchor Frame and Conditional Control for Superior Fidelity and EditabilityDiffusion models → Audio, speech and music
OneLLM: One Framework to Align All Modalities with LanguageMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Memory Triggers: Unveiling Memorization in Text-To-Image Generative Models through Word-Level DuplicationDiffusion models → Diffusion foundations and sampling
WarpDiffusion: Efficient Diffusion Model for High-Fidelity Virtual Try-onDiffusion models → 3D, point cloud and scene generation
Generative agent-based modeling with actions grounded in physical, social, or digital space using ConcordiaLLM agents and tool use → Social simulation and multi-agent debate
Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
MACCA: Offline Multi-agent Reinforcement Learning with Causal Credit AssignmentOffline RL and imitation learning from data → Offline multi-agent RL
Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
TokenCompose: Text-to-Image Diffusion with Token-level SupervisionDiffusion models → Image generation, text-to-image and editing
Evaluation of Active Feature Acquisition Methods for Static Feature SettingsOffline RL and imitation learning from data → Offline RL algorithms
DreamComposer: Controllable 3D Object Generation via Multi-View ConditionsDiffusion models → 3D, point cloud and scene generation
DiffusionSat: A Generative Foundation Model for Satellite ImageryDiffusion models → Inverse problems and image restoration
Personalized Face Inpainting with Diffusion Models by Parallel Visual AttentionDiffusion models → Image generation, text-to-image and editing
GPT-4 Enhanced Multimodal Grounding for Autonomous Driving: Leveraging Cross-Modal Attention with Large Language ModelsEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
FoodFusion: A Latent Diffusion Model for Realistic Food Image GenerationDiffusion models → Image generation, text-to-image and editing
FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Kandinsky 3.0 Technical ReportDiffusion models → Image generation, text-to-image and editing
Task-Parameterized Imitation Learning with Time-Sensitive ConstraintsOffline RL and imitation learning from data → Robot learning from demonstration
Schrodinger Bridges Beat Diffusion Models on Text-to-Speech SynthesisDiffusion models → Audio, speech and music
F3-Pruning: A Training-Free and Generalized Pruning Strategy towards Faster and Finer Text-to-Video SynthesisDiffusion models → Video generation +1
Think from Words(TFW): Initiating Human-Like Cognition in Large Language Models Through Think from Words for Japanese Text-level ClassificationLLM reasoning → Prompting and chain-of-thought reasoning
Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative ModelsLLM safety and security → Backdoor and data poisoning attacks
Generalized Contrastive Divergence: Joint Training of Energy-Based Model and Diffusion Model through Inverse Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
Diffused Task-Agnostic Milestone PlannerDiffusion models → Diffusion and flow policies for robotics +1
VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Low-Cost High-Power Membership Inference AttacksLLM safety and security → Membership inference attacks
Cache Me if You Can: Accelerating Diffusion Models through Block CachingDiffusion models → Diffusion foundations and sampling
Who Leaked the Model? Tracking IP Infringers in Accountable Federated LearningLLM safety and security → Federated unlearning and poisoning
Wake-Sleep Consolidated Learning
Empowering ChatGPT-Like Large-Scale Language Models with Local Knowledge Base for Industrial Prognostics and Health Management
Assessing the Usability of GutGPT: A Simulation Study of an AI Clinical Decision Support System for Gastrointestinal Bleeding Risk
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
Make-A-Storyboard: A General Framework for Storyboard with Disentangled and Merged Control
Active Inference and Intentional Behaviour
Decoding Working-Memory Load During n-Back Task Performance from High Channel NIRS Data
An Association Test Based on Kernel-Based Neural Networks for Complex Genetic Association Analysis
Evaluating Self-supervised Speech Models on a Taiwanese Hokkien Corpus
Multimodal Group Emotion Recognition In-the-wild Using Privacy-Compliant Features
Haldane Bundles: A Dataset for Learning to Predict the Chern Number of Line Bundles on the Torus
TrustFed: A Reliable Federated Learning Framework with Malicious-Attack Resistance
Feature Analysis of Encrypted Malicious Traffic
Evaluating The Accuracy of Classification Algorithms for Detecting Heart Disease Risk
FedGeo: Privacy-Preserving User Next Location Prediction with Federated Learning
Understanding the Role of Optimization in Double Descent
A Scalable and Generalizable Pathloss Map Prediction
A Layer-Wise Tokens-to-Token Transformer Network for Improved Historical Document Image Enhancement
PECANN: Parallel Efficient Clustering with Graph-Based Approximate Nearest Neighbor Search
Adapting HouseDiffusion for conditional Floor Plan generation on Modified Swiss Dwellings dataset
Adaptive Weighted Co-Learning for Cross-Domain Few-Shot Learning
Collaboration or Corporate Capture? Quantifying NLP's Reliance on Industry Artifacts and Contributions
Improving Gradient-guided Nested Sampling for Posterior Inference
A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints
Adaptive Dependency Learning Graph Neural Networks
Revisiting the Optimality of Word Lengths
HLoOP -- Hyperbolic 2-space Local Outlier Probabilities
Evaluation of Infrastructure-based Warning System on Driving Behaviors-A Roundabout Study
A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systems
On The Fairness Impacts of Hardware Selection in Machine Learning
Gathering and Exploiting Higher-Order Information when Training Large Structured Models
WonderJourney: Going from Anywhere to Everywhere
FoMo Rewards: Can we cast foundation models as reward functions?
Domain constraints improve risk prediction when outcome data is missing
Scaling transformer neural networks for skillful and reliable medium-range weather forecasting
Optimizing CO2 Capture in Pressure Swing Adsorption Units: A Deep Neural Network Approach with Optimality Evaluation and Operating Maps for Decision-Making
The BigCode Project Governance Card
Hidden yet quantifiable: A lower bound for confounding strength using randomized trials
Multi-Group Fairness Evaluation via Conditional Value-at-Risk Testing
Learning Genomic Sequence Representations using Graph Neural Networks over De Bruijn Graphs
Efficient Large Language Models: A Survey
Dr. Jekyll and Mr. Hyde: Two Faces of LLMs
Exposing Disparities in Flood Adaptation for Equitable Future Interventions
nbi: the Astronomer's Package for Neural Posterior Estimation
High Pileup Particle Tracking with Object Condensation
Alpha-CLIP: A CLIP Model Focusing on Wherever You Want
Diffusion Illusions: Hiding Images in Plain Sight
Pearl: A Production-ready Reinforcement Learning Agent
Seeing the random forest through the decision trees. Supporting learning health systems from histopathology with machine learning models: Challenges and opportunities
SurfaceAug: Closing the Gap in Multimodal Ground Truth Sampling
Achieving O(ε-1.5) Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization
XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies
How Low Can You Go? Surfacing Prototypical In-Distribution Samples for Unsupervised Anomaly Detection
Generalization to New Sequential Decision Making Tasks with In-Context Learning
Low-power, Continuous Remote Behavioral Localization with Event Cameras
Single Image Reflection Removal with Patch Reflectance Prior
Multi-Scale and Multi-Modal Contrastive Learning Network for Biomedical Time Series
AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation

All 257