Papers
Wed 16 Mar 2022
196 papers
- Diffusion Probabilistic Modeling for Video GenerationDiffusion models → Video generation
- AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading ComprehensionLLM reasoning → Knowledge- and tool-augmented reasoning
- Latent-Variable Advantage-Weighted Policy Optimization for Offline RLOffline RL and imitation learning from data → Offline RL algorithms
- Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training DataLLM reasoning → Reasoning benchmarks and evaluation
- Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech TranslationKnowledge distillation → Speech and audio distillation
- Decoupled Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- An Independently Learnable Hierarchical Model for Bilateral Control-Based Imitation Learning ApplicationsOffline RL and imitation learning from data → Robot manipulation imitation learning
- E-KAR: A Benchmark for Rationalizing Natural Language Analogical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Thinking about GPT-3 In-Context Learning for Biomedical IE? Think AgainLLM reasoning → Clinical and biomedical applications
- How to Learn from Risk: Explicit Risk-Utility Reinforcement Learning for Efficient and Safe Driving StrategiesEnd-to-end autonomous driving → Reinforcement learning for driving
- COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning AttacksOffline RL and imitation learning from data → Offline RL algorithms
- Iteratively Prompt Pre-trained Language Models for Chain of ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
- Dual Diffusion Implicit Bridges for Image-to-Image TranslationDiffusion models → Image generation, text-to-image and editing
- Domain Adaptive Hand Keypoint and Pixel Localization in the WildKnowledge distillation → Detection and dense prediction distillation
- A Deep Reinforcement Learning-Based Caching Strategy for IoT Networks with Transient Data
- Continuous Detection, Rapidly React: Unseen Rumors Detection based on Continual Prompt-Tuning
- EEG based Emotion Recognition: A Tutorial and Review
- A New Quantum CNN Model for Image Classification
- Linking Theories and Methods in Cognitive Sciences via Joint Embedding of the Scientific Literature: The Example of Cognitive Control
- On the sensitivity of pose estimation neural networks: rotation parameterizations, Lipschitz constants, and provable bounds
- Computer Vision Algorithm for Predicting the Welding Efficiency of Friction Stir Welded Copper Joints from its Microstructures
- AdapLeR: Speeding up Inference by Adaptive Length Reduction
- Label Semantics for Few Shot Named Entity Recognition
- Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching
- Adaptive n-ary Activation Functions for Probabilistic Boolean Logic
- A Survey of Multi-Agent Deep Reinforcement Learning with Communication
- Extensive Threat Analysis of Vein Attack Databases and Attack Detection by Fusion of Comparison Scores
- 3D-UCaps: 3D Capsules Unet for Volumetric Image Segmentation
- Point-Unet: A Context-aware Point-based Neural Network for Volumetric Segmentation
- On the Convergence of Certified Robust Training with Interval Bound Propagation
- Robustness through Cognitive Dissociation Mitigation in Contrastive Adversarial Training
- On the Usefulness of the Fit-on-the-Test View on Evaluating Calibration of Classifiers
- Risk-Averse No-Regret Learning in Online Convex Games
- BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages
- Meta-Learning of NAS for Few-shot Learning in Medical Image Applications
- CapsNet for Medical Image Segmentation
- Provable Adversarial Robustness for Fractional Lp Threat Models
- ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation
- Backpropagation through Time and Space: Learning Numerical Methods with Multi-Agent Reinforcement Learning
- ℓp Slack Norm Support Vector Data Description
- Creating Multimedia Summaries Using Tweets and Videos
- An Analysis of Negation in Natural Language Understanding Corpora
- C-MORE: Pretraining to Answer Open-Domain Questions by Consulting Millions of References
- Synthetic Question Value Estimation for Domain Adaptation of Question Answering
- Towards True Detail Restoration for Super-Resolution: A Benchmark and a Quality Metric
- Hybrid Pixel-Unshuffled Network for Lightweight Image Super-Resolution
- Knee arthritis severity measurement using deep learning: a publicly available algorithm with a multi-institutional validation showing radiologist-level performance
- Memorizing Transformers
- Morphological Processing of Low-Resource Languages: Where We Are and What's Next
- Adversarial Support Alignment
- Neural network processing of holographic images
- Gate-Shift-Fuse for Video Action Recognition
- Sat-NeRF: Learning Multi-View Satellite Photogrammetry With Transient Objects and Shadow Modeling Using RPC Cameras
- Explaining Preference-driven Schedules: the EXPRES Framework
- Multimodal Learning on Graphs for Disease Relation Extraction
- The Mathematics of Artificial Intelligence
- On Redundancy and Diversity in Cell-based Neural Architecture Search
- Hyperbolic Uncertainty Aware Semantic Segmentation
- Layer Ensembles: A Single-Pass Uncertainty Estimation in Deep Learning for Segmentation
- SC2 Benchmark: Supervised Compression for Split Computing
- A Real-Time Region Tracking Algorithm Tailored to Endoscopic Video with Open-Source Implementation
- Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks
- Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation?
- Discovering the building blocks of dark matter halo density profiles with neural networks
- Understanding robustness and generalization of artificial neural networks through Fourier masks
- DePS: An improved deep learning model for de novo peptide sequencing
- Hierarchical Clustering and Matrix Completion for the Reconstruction of World Input-Output Tables
- Example Perplexity
- Self-Supervised Deep Learning to Enhance Breast Cancer Detection on Screening Mammography
- A Continual Learning Framework for Adaptive Defect Classification and Inspection
- Zero Pixel Directional Boundary by Vector Transform
- PosePipe: Open-Source Human Pose Estimation Pipeline for Clinical Research
- Are Shortest Rationales the Best Explanations for Human Understanding?
- Exploring Variational Graph Auto-Encoders for Extract Class Refactoring Recommendation
- Object discovery and representation networks
- Practical Conditional Neural Processes Via Tractable Dependent Predictions
- CUE Vectors: Modular Training of Language Models Conditioned on Diverse Contextual Signals
- Efficient conditioned face animation using frontally-viewed embedding
- X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation
- UnseenNet: Fast Training Detector for Any Unseen Concept
- Multi-Stage Prompting for Knowledgeable Dialogue Generation
- What Do Adversarially trained Neural Networks Focus: A Fourier Domain-based Study
- Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey
- Learning Where To Look -- Generative NAS is Surprisingly Efficient
- Tangles and Hierarchical Clustering
- Attacking deep networks with surrogate-based adversarial black-box methods is easy
- Weak Augmentation Guided Relational Self-Supervised Learning
- Multiscale Sensor Fusion and Continuous Control with Neural CDEs
- DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation
- High dimensional change-point detection: a complete graph approach
- Turning Stocks into Memes: A Dataset for Understanding How Social Communities Can Drive Wall Street
- Learning video retrieval models with relevance-aware online mining
- A Feasibility Study of Answer-Agnostic Question Generation for Education
- Know your sensORs -- A Modality Study For Surgical Action Classification
- Measuring Fairness of Text Classifiers via Prediction Sensitivity
- MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clients
- Graph Flow: Cross-layer Graph Flow Distillation for Dual Efficient Medical Image Segmentation
- Occlusion Fields: An Implicit Representation for Non-Line-of-Sight Surface Reconstruction
- Learning Representation for Bayesian Optimization with Collision-free Regularization
- Unraveled Multilevel Transformation Networks for Predicting Sparsely-Observed Spatiotemporal Dynamics
All 196
- Graph Neural Networks for Multiparallel Word Alignment
- Counterfactual Inference of Second Opinions
- Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow
- Complexity Reduction of Learned In-Loop Filtering in Video Coding
- Artificial Intelligence Enables Real-Time and Intuitive Control of Prostheses via Nerve Interface
- The Structured Abstain Problem and the Lov'asz Hinge
- Context-Aware Drift Detection
- Adversarial Learned Fair Representations using Dampening and Stacking
- Coverage Optimization of Camera Network for Continuous Deformable Object
- Extended vehicle energy dataset (eVED): an enhanced large-scale dataset for deep learning on vehicle trip energy consumption
- Conditional Measurement Density Estimation in Sequential Monte Carlo via Normalizing Flow
- Scientific and Technological Information Oriented Semantics-adversarial and Media-adversarial Cross-media Retrieval
- CtlGAN: Few-shot Artistic Portraits Generation with Contrastive Transfer Learning
- Less is More: Summary of Long Instructions is Better for Program Synthesis
- MIMO-GAN: Generative MIMO Channel Modeling
- Deep vanishing point detection: Geometric priors make dataset variations vanish
- A Survey on Infrared Image and Video Sets
- Whither the Priors for (Vocal) Interactivity?
- Undersmoothing Causal Estimators with Generative Trees
- PMAL: Open Set Recognition via Robust Prototype Mining
- In-Context Learning for Few-Shot Dialogue State Tracking
- EDTER: Edge Detection with Transformer
- Geographic Adaptation of Pretrained Language Models
- An elementary analysis of ridge regression with random design
- MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection
- Learning to Generate Synthetic Training Data using Gradient Matching and Implicit Differentiation
- LEVEN: A Large-Scale Chinese Legal Event Detection Dataset
- Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning
- PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
- Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer
- Is it all a cluster game? -- Exploring Out-of-Distribution Detection based on Clustering in the Embedding Space
- Non-isotropy Regularization for Proxy-based Deep Metric Learning
- Integrating Language Guidance into Vision-based Deep Metric Learning
- Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act
- Scribble-Supervised LiDAR Semantic Segmentation
- Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video
- Morphological Reinflection with Multiple Arguments: An Extended Annotation schema and a Georgian Case Study
- Towards Practical Certifiable Patch Defense with Vision Transformer
- TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge
- Fantastic Style Channels and Where to Find Them: A Submodular Framework for Discovering Diverse Directions in GANs
- Multi-focus thermal image fusion
- ConTinTin: Continual Learning from Task Instructions
- Differentiable DAG Sampling
- A Survey of Historical Document Image Datasets
- Monte Carlo PINNs: deep learning approach for forward and inverse problems involving high dimensional fractional partial differential equations
- HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversations
- Resilient Neural Forecasting Systems
- Deepchecks: A Library for Testing and Validating Machine Learning Models and Data
- Learning Audio Representations with MLPs
- Pushing the limits of raw waveform speaker recognition
- PointAttN: You Only Need Attention for Point Cloud Completion
- QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation
- Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding
- Data Efficient 3D Learner via Knowledge Transferred from 2D Model
- Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects
- Building AI Innovation Labs together with Companies
- KinyaBERT: a Morphology-aware Kinyarwanda Language Model
- PPCD-GAN: Progressive Pruning and Class-Aware Distillation for Large-Scale Conditional GANs Compression
- Coach-assisted Multi-Agent Reinforcement Learning Framework for Unexpected Crashed Agents
- Can Pre-trained Language Models Interpret Similes as Smart as Human?
- The Devil Is in the Details: Window-based Attention for Image Compression
- Playing with blocks: Toward re-usable deep learning models for side-channel profiled attacks
- Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive Evaluation
- Panini-Net: GAN Prior Based Degradation-Aware Feature Interpolation for Face Restoration
- Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation
- Open Set Recognition using Vision Transformer with an Additional Detection Head
- Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search
- DiFT: Differentiable Differential Feature Transform for Multi-View Stereo
- Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling
- Cross-Lingual Ability of Multilingual Masked Language Models: A Study of Language Structure
- Attribute Group Editing for Reliable Few-shot Image Generation
- WegFormer: Transformers for Weakly Supervised Semantic Segmentation
- On the Use of Fine-grained Vulnerable Code Statements for Software Vulnerability Assessment Models
- Unsupervised Semantic Segmentation by Distilling Feature Correspondences
- CTDS: Centralized Teacher with Decentralized Student for Multi-Agent Reinforcement Learning
- FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction
- Multi-Scale Context-Guided Lumbar Spine Disease Identification with Coarse-to-fine Localization and Classification
- RBC: Rectifying the Biased Context in Continual Semantic Segmentation
- Privacy-preserving Online AutoML for Domain-Specific Face Detection
- Towards Formalizing HRI Data Collection Processes
- Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation
- Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?
- Reducing Flipping Errors in Deep Neural Networks
- MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages
- Transforming Sequence Tagging Into A Seq2Seq Task
- Multi-View Document Representation Learning for Open-Domain Dense Retrieval
- Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance
- Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scene
- Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting
- Towards Afrocentric NLP for African Languages: Where We Are and Where We Can Go
- A Multi-parameter Updating Fourier Online Gradient Descent Algorithm for Large-scale Nonlinear Classification
- Gradient Correction beyond Gradient Descent
- Adaptive Noisy Matrix Completion
- NURD: Negative-Unlabeled Learning for Online Datacenter Straggler Prediction
- WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection
- Motif Mining: Finding and Summarizing Remixed Image Content