Papers
Sat 7 Oct 2023
134 papers
- Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy ExplorationOffline RL and imitation learning from data → Offline RL algorithms
- Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLULLM reasoning → Reasoning benchmarks and evaluation
- Crystal: Introspective Reasoners Reinforced with Self-FeedbackLLM reasoning → Test-time compute and efficient thinking
- On Accelerating Diffusion-based Molecular Conformation Generation in SE(3)-invariant SpaceDiffusion models → Flow matching, time series and science
- Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding TasksMultimodal LLMs / vision-language models → Video understanding with MLLMs
- ILuvUI: Instruction-tuned LangUage-Vision modeling of UIs from Machine ConversationsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New LanguagesLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- Conditional Diffusion Model for Target Speaker ExtractionDiffusion models → Audio, speech and music
- DiffNAS: Bootstrapping Diffusion Models by Prompting for Better ArchitecturesDiffusion models → Diffusion foundations and sampling +1
- Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
- Offline Imitation Learning with Variational Counterfactual ReasoningOffline RL and imitation learning from data → Imitation learning methods
- SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food DetectionDiffusion models → Image generation, text-to-image and editing
- Targeted Attack Improves Protection against Unauthorized Diffusion CustomizationDiffusion models → Robustness, privacy and adversarial aspects
- VoiceExtender: Short-utterance Text-independent Speaker Verification with Guided Diffusion ModelDiffusion models → Audio, speech and music
- EasyPhoto: Your Smart AI Photo GeneratorDiffusion models → Image generation, text-to-image and editing
- Score-based Diffusion Models With Self-supervised Learning For Accelerated 3D Multi-contrast Cardiac Magnetic Resonance ImagingDiffusion models → Medical imaging and segmentation
- An Evaluation of State-of-the-Art Large Language Models for Sarcasm Detection
- Data-Centric Financial Large Language Models
- Digital Twin Assisted Deep Reinforcement Learning for Online Admission Control in Sliced Network
- Unit Commitment Predictor With a Performance Guarantee: A Support Vector Machine Classifier
- QE-BEV: Query Evolution for Bird's Eye View Object Detection in Varied Contexts
- Dual Latent State Learning: Exploiting Regional Network Similarities for QoS Prediction
- Transferable Deep Clustering Model
- Balancing Specialized and General Skills in LLMs: The Impact of Modern Tuning and Data Strategy
- Beyond Text: A Deep Dive into Large Language Models' Ability on Understanding Graph Data
- Large Language Models for Spatial Trajectory Patterns Mining
- Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
- Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory
- Diff-Transfer: Model-based Robotic Manipulation Skill Transfer via Differentiable Physics Simulation
- DISCOVER: Making Vision Networks Interpretable via Competition and Dissection
- Crystal-GFN: sampling crystals with desirable properties and constraints
- The Conditional Prediction Function: A Novel Technique to Control False Discovery Rate for Complex Models
- SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning
- Tight Certified Robustness via Min-Max Representations of ReLU Neural Networks
- Intelligent Sampling Consensus for Homography Estimation in Football Videos Using Featureless Unpaired Points
- Towards Faithful Knowledge Graph Explanation Through Deep Alignment in Commonsense Question Answering
- WAIT: Feature Warping for Animation to Illustration video Translation using GANs
- HowToCaption: Prompting LLMs to Transform Video Annotations at Scale
- Generative AI May Prefer to Present National-level Characteristics of Cities Based on Stereotypical Geographic Impressions at the Continental Level
- Cell Tracking-by-detection using Elliptical Bounding Boxes
- GradXKG: A Universal Explain-per-use Temporal Knowledge Graph Explainer
- Regret Analysis of Repeated Delegated Choice
- Question-focused Summarization by Decomposing Articles into Facts and Opinions and Retrieving Entities
- Hybrid Recommendation System using Graph Neural Network and BERT Embeddings
- Prompt-to-OS (P2OS): Revolutionizing Operating Systems and Human-Computer Interaction with Integrated AI Generative Models
- AirIMU: Learning Uncertainty Propagation for Inertial Odometry
- Machine Learning for Automated Mitral Regurgitation Detection from Cardiac Imaging
- Lemur: Integrating Large Language Models in Automated Program Verification
- Randomized Sparse Neural Galerkin Schemes for Solving Evolution Equations with Deep Networks
- ForeSeer: Product Aspect Forecasting Using Temporal Graph Embedding
- Uncovering hidden geometry in Transformers via disentangling position and context
- General Graph Random Features
- End-to-End Lip Reading in Romanian with Cross-Lingual Domain Adaptation and Lateral Inhibition
- LIPEx-Locally Interpretable Probabilistic Explanations-To Look Beyond The True Class
- Epsilon non-Greedy: A Bandit Approach for Unbiased Recommendation via Uniform Data
- Repelling Random Walks
- Balancing utility and cognitive cost in social representation
- Exploiting Facial Relationships and Feature Aggregation for Multi-Face Forgery Detection
- Sub-linear Regret in Adaptive Model Predictive Control
- Federated Self-Supervised Learning of Monocular Depth Estimators for Autonomous Vehicles
- Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM
- On the Evolution of Knowledge Graphs: A Survey and Perspective
- HyperSINDy: Deep Generative Modeling of Nonlinear Stochastic Governing Equations
- Extract-Transform-Load for Video Streams
- How To Effectively Train An Ensemble Of Faster R-CNN Object Detectors To Quantify Uncertainty
- Comparative study of multi-person tracking methods
- A New Baseline Assumption of Integated Gradients Based on Shaply value
- Hacking Generative Models with Differentiable Network Bending
- Critique Ability of Large Language Models
- Applications of Littlestone dimension to query learning and to compression
- Combining UPerNet and ConvNeXt for Contrails Identification to reduce Global Warming
- User's Position-Dependent Strategies in Consumer-Generated Media with Monetary Rewards
- Ten Challenges in Industrial Recommender Systems
- Parameterizing Context: Unleashing the Power of Parameter-Efficient Fine-Tuning and In-Context Tuning for Continual Table Semantic Parsing
- Towards Long-Range 3D Object Detection for Autonomous Vehicles
- Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning
- FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets
- HNS: An Efficient Hermite Neural Solver for Solving Time-Fractional Partial Differential Equations
- PMNN:Physical Model-driven Neural Network for solving time-fractional differential equations
- HI-SLAM: Monocular Real-time Dense Mapping with Hybrid Implicit Fields
- Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning
- IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers
- TransCC: Transformer Network for Coronary Artery CCTA Segmentation
- Optimal Sequential Decision-Making in Geosteering: A Reinforcement Learning Approach
- 1st Place Solution of Egocentric 3D Hand Pose Estimation Challenge 2023 Technical Report:A Concise Pipeline for Egocentric Hand Pose Reconstruction
- Online Corrupted User Detection and Regret Minimization
- Robust Low-Rank Matrix Completion via a New Sparsity-Inducing Regularizer
- CAD Models to Real-World Images: A Practical Approach to Unsupervised Domain Adaptation in Industrial Object Classification
- Pairwise GUI Dataset Construction Between Android Phones and Tablets
- A New Dataset for End-to-End Sign Language Translation: The Greek Elementary School Dataset
- A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization
- ConvNeXtv2 Fusion with Mask R-CNN for Automatic Region Based Coronary Artery Stenosis Detection for Disease Diagnosis
- Towards Dynamic and Small Objects Refinement for Unsupervised Domain Adaptative Nighttime Semantic Segmentation
- Parameter Efficient Multi-task Model Fusion with Partial Linearization
- Keep Moving: identifying task-relevant subspaces to maximise plasticity for newly learned tasks
- Task Aware Modulation using Representation Learning: An Approach for Few Shot Learning in Environmental Systems
- Zero-shot Cross-lingual Transfer without Parallel Corpus
- Activate and Reject: Towards Safe Domain Generalization under Category Shift
- Subspace Identification for Multi-Source Domain Adaptation
- A Holistic Evaluation of Piano Sound Quality
All 134
- Memory-Constrained Semantic Segmentation for Ultra-High Resolution UAV Imagery
- A Comprehensive Survey on Deep Neural Image Deblurring
- Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API
- Generalized Robust Test-Time Adaptation in Continuous Dynamic Scenarios
- UFD-PRiME: Unsupervised Joint Learning of Optical Flow and Stereo Depth through Pixel-Level Rigid Motion Estimation
- Multi-scale MRI reconstruction via dilated ensemble networks
- EdgeFD: An Edge-Friendly Drift-Aware Fault Diagnosis System for Industrial IoT
- Integrating Contrastive Learning into a Multitask Transformer Model for Effective Domain Adaptation
- Twin Graph-based Anomaly Detection via Attentive Multi-Modal Learning for Microservice System
- Tree-GPT: Modular Large Language Model Expert System for Forest Remote Sensing Image Understanding and Interactive Analysis
- Serving Deep Learning Model in Relational Databases
- Robustness-enhanced Uplift Modeling with Adversarial Feature Desensitization
- EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling
- PatchProto Networks for Few-shot Visual Anomaly Classification
- Tight Rates in Supervised Outlier Transfer Learning
- Automatic and Efficient Customization of Neural Networks for ML Applications
- The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning
- High Visual-Fidelity Learned Video Compression
- DORIS-MAE: Scientific Document Retrieval using Multi-level Aspect-based Queries
- AG-CRC: Anatomy-Guided Colorectal Cancer Segmentation in CT with Imperfect Anatomical Knowledge
- Surgical Gym: A high-performance GPU-based platform for reinforcement learning with surgical robots
- ReactionTeam: Teaming Experts for Divergent Thinking Beyond Typical Reaction Patterns
- LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT
- Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction
- Label-free Node Classification on Graphs with Large Language Models (LLMS)
- Learning to Rank Onset-Occurring-Offset Representations for Micro-Expression Recognition
- HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information
- VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
- Oracle Efficient Algorithms for Groupwise Regret
- Uncovering Model Processing Strategies with Non-Negative Per-Example Fisher Factorization
- Do self-supervised speech and language models extract similar representations as human brain?
- X-Transfer: A Transfer Learning-Based Framework for GAN-Generated Fake Image Detection
- Automatic Anonymization of Swiss Federal Supreme Court Rulings
- Metadata-Conditioned Generative Models to Synthesize Anatomically-Plausible 3D Brain MRIs