Papers
Wed 29 Jun 2022
145 papers
- Solving Quantitative Reasoning Problems with Language ModelsLLM reasoning → Mathematical reasoning
- Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?Knowledge distillation → General knowledge distillation methods
- SPI-GAN: Denoising Diffusion GANs with Straight-Path InterpolationsDiffusion models → Diffusion foundations and sampling
- Knowledge Distillation of Transformer-based Language Models RevisitedKnowledge distillation → Knowledge distillation for LLMs
- Extreme compression of sentence-transformer ranker models: faster inference, longer battery life, and less storage on edge devices
- STOP: A dataset for Spoken Task Oriented Semantic Parsing
- OASYS: Domain-Agnostic Automated System for Constructing Knowledge Base from Unstructured Text
- A Robustly Optimized Long Text to Math Models for Numerical Reasoning On FinQA
- The Lepto-Variance of Stock Returns
- Dynamic Community Detection via Adversarial Temporal Graph Representation Learning
- Automatic Synthesis of Neurons for Recurrent Neural Nets
- Feature-selected Graph Spatial Attention Network for Addictive Brain-Networks Identification
- Turbo: Opportunistic Enhancement for Edge Video Analytics
- Off-the-grid learning of mixtures from a continuous dictionary
- Variational Inference for Additive Main and Multiplicative Interaction Effects Models
- Continual Learning for Human State Monitoring
- Ensemble CNN models for Covid-19 Recognition and Severity Perdition From 3D CT-scan
- CLTS-GAN: Color-Lighting-Texture-Specular Reflection Augmentation for Colonoscopy
- Decision Forest Based EMG Signal Classification with Low Volume Dataset Augmented with Random Variance Gaussian Noise
- Regularization of NeRFs using differential geometry
- Manifold Interpolating Optimal-Transport Flows for Trajectory Inference
- AFAFed -- Protocol analysis
- ComDensE : Combined Dense Embedding of Relation-aware and Common Features for Knowledge Graph Completion
- On Non-Random Missing Labels in Semi-Supervised Learning
- Identifying and Combating Bias in Segmentation Networks by leveraging multiple resolutions
- Towards out of distribution generalization for problems in mechanics
- The Hiatus Between Organism and Machine Evolution: Contrasting Mixed Microbial Communities with Robots
- GPTs at Factify 2022: Prompt Aided Fact-Verification
- Best of Both Worlds Model Selection
- A Best-of-Both-Worlds Algorithm for Bandits with Delayed Feedback
- CIRDataset: A large-scale Dataset for Clinically-Interpretable lung nodule Radiomics and malignancy prediction
- Discrete Langevin Sampler via Wasserstein Gradient Flow
- Semantic Unfolding of StyleGAN Latent Space
- Space-Efficient Representation of Entity-centric Query Language Models
- LIDL: Local Intrinsic Dimension Estimation Using Approximate Likelihood
- Teach me how to Interpolate a Myriad of Embeddings
- Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks
- Two-Stage COVID19 Classification Using BERT Features
- Neural Motion Fields: Encoding Grasp Trajectories as Implicit Value Functions
- Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale
- Deep Reinforcement Learning for Small Bowel Path Tracking using Different Types of Annotations
- Provably Efficient Reinforcement Learning for Online Adaptive Influence Maximization
- Causality for Inherently Explainable Transformers: CAT-XPLAIN
- Strong Lensing Source Reconstruction Using Continuous Neural Fields
- Visual Foresight With a Local Dynamics Model
- Meta-Learning over Time for Destination Prediction Tasks
- Understanding Generalization via Leave-One-Out Conditional Mutual Information
- Generalized Permutants and Graph GENEOs
- 3D-Aware Video Generation
- On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based Method
- ENS-10: A Dataset For Post-Processing Ensemble Weather Forecasts
- TweetNLP: Cutting-Edge Natural Language Processing for Social Media
- IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound
- Distilling Model Failures as Directions in Latent Space
- An Auto-Regressive Formulation for Smoothing and Moving Mean with Exponentially Tapered Windows
- Placenta Segmentation in Ultrasound Imaging: Addressing Sources of Uncertainty and Limited Field-of-View
- Modeling Teams Performance Using Deep Representational Learning on Graphs
- GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction
- longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks
- Private Graph Extraction via Feature Explanations
- DrumGAN VST: A Plugin for Drum Sound Analysis/Synthesis With Autoencoding Generative Adversarial Networks
- Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision
- LViT: Language meets Vision Transformer in Medical Image Segmentation
- Improving Deliberation by Text-Only and Semi-Supervised Training
- CONVIQT: Contrastive Video Quality Estimator
- An extensible Benchmarking Graph-Mesh dataset for studying Steady-State Incompressible Navier-Stokes Equations
- An Embedding Framework for the Design and Analysis of Consistent Polyhedral Surrogates
- Interventional Contrastive Learning with Meta Semantic Regularizer
- Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios
- Multi-scale Physical Representations for Approximating PDE Solutions with Graph Neural Operators
- Computer-aided diagnosis and prediction in brain disorders
- BiometryNet: Landmark-based Fetal Biometry Estimation from Standard Ultrasound Planes
- Signature Methods in Machine Learning
- Not Cheating on the Turing Test: Towards Grounded Language Learning in Artificial Intelligence
- Towards a Data-Driven Requirements Engineering Approach: Automatic Analysis of User Reviews
- Score Matching for Truncated Density Estimation on a Manifold
- Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning
- Online vs. Offline Adaptive Domain Randomization Benchmark
- The THUEE System Description for the IARPA OpenASR21 Challenge
- Language-Based Audio Retrieval with Converging Tied Layers and Contrastive Loss
- Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs
- BoT-SORT: Robust Associations Multi-Pedestrian Tracking
- Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody
- DDKtor: Automatic Diadochokinetic Speech Analysis
- From Kernel Methods to Neural Networks: A Unifying Variational Formulation
- Contextual Density Ratio for Language Model Biasing of Sequence to Sequence ASR Systems
- On the Prediction Network Architecture in RNN-T for ASR
- Treatment Effect Estimation with Observational Network Data using Machine Learning
- Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models
- Language-specific Characteristic Assistance for Code-switching Speech Recognition
- Technical Report for CVPR 2022 LOVEU AQTC Challenge
- Uncertainty-aware Panoptic Segmentation
- SALO: An Efficient Spatial Accelerator Enabling Hybrid Sparse Attention Mechanisms for Long Sequences
- Comparative Study of Inference Methods for Interpolative Decomposition
- Why patient data cannot be easily forgotten?
- vMFNet: Compositionality Meets Domain-generalised Segmentation
- When Does Group Invariant Learning Survive Spurious Correlations?
- Deep Active Visual Attention for Real-time Robot Motion Generation: Emergence of Tool-body Assimilation and Adaptive Tool-use
- Procrustes Analysis with Deformations: A Closed-Form Solution by Eigenvalue Decomposition
- Imaging the time series of one single referenced EEG electrode for Epileptic Seizures Risk Analysis
All 145
- Variational Quantum Approximate Support Vector Machine with Inference Transfer
- An extension of process calculus for asynchronous communications between agents with epistemic states
- GERNERMED++: Transfer Learning in German Medical NLP
- RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness
- Auto-Encoder-Extreme Learning Machine Model for Boiler NOx Emission Concentration Prediction
- Beyond neural scaling laws: beating power law scaling via data pruning
- Data augmentation for learning predictive models on EEG: a systematic comparison
- Representation and Synthesis of C++ Programs for Generalized Planning
- Adversarial Ensemble Training by Jointly Learning Label Dependencies and Member Models
- Can Push-forward Generative Models Fit Multimodal Distributions?
- Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning
- Single-domain Generalization in Medical Image Segmentation via Test-time Adaptation from Shape Dictionary
- Deep Multiple Instance Learning For Forecasting Stock Trends Using Financial News
- SRCN3D: Sparse R-CNN 3D for Compact Convolutional Multi-View 3D Object Detection and Tracking
- Conditioned Human Trajectory Prediction using Iterative Attention Blocks
- Approximate Data Deletion in Generative Models
- MaNi: Maximizing Mutual Information for Nuclei Cross-Domain Unsupervised Segmentation
- Open Problem: Properly learning decision trees in polynomial time?
- Collaborative Navigation and Manipulation of a Cable-towed Load by Multiple Quadrupedal Robots
- Cyclical Kernel Adaptive Metropolis
- Optimization-Induced Graph Implicit Nonlinear Diffusion
- The Lighter The Better: Rethinking Transformers in Medical Image Segmentation Through Adaptive Pruning
- BATFormer: Towards Boundary-Aware Lightweight Transformer for Efficient Medical Image Segmentation
- Fair Machine Learning in Healthcare: A Review
- Data Redaction from Pre-trained GANs
- Chinese Word Sense Embedding with SememeWSD and Synonym Set
- Framing Algorithmic Recourse for Anomaly Detection
- Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems
- Exploiting Semantic Role Contextualized Video Features for Multi-Instance Text-Video Retrieval EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022
- Theoretical Perspectives on Deep Learning Methods in Inverse Problems
- Formalizing and Evaluating Requirements of Perception Systems for Automated Vehicles using Spatio-Temporal Perception Logic
- Matryoshka: Stealing Functionality of Private ML Data by Hiding Models in Model
- TE2Rules: Explaining Tree Ensembles using Rules
- Using Twitter Data to Understand Public Perceptions of Approved versus Off-label Use for COVID-19-related Medications
- EBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answering
- Hardness and Algorithms for Robust and Sparse Optimization
- Convolutional Neural Network Based Partial Face Detection
- Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision
- What Can Secondary Predictions Tell Us? An Exploration on Question-Answering with SQuAD-v2.0
- A New Adjacency Matrix Configuration in GCN-based Models for Skeleton-based Action Recognition
- Intrinsic Anomaly Detection for Multi-Variate Time Series
- CoAP-DoS: An IoT Network Intrusion Dataset
- Deformable Graph Transformer
- Active Exploration via Experiment Design in Markov Chains
- Spherical Channels for Modeling Atomic Interactions