Papers
Mon 19 Dec 2022
200 papers
- Generalizing Multimodal Variational Methods to SetsMixture-of-experts → Multimodal MoE models
- Scalable Diffusion Models with TransformersWorld models → Video-generation world models and simulators +1
- Position-guided Text Prompt for Vision-Language Pre-trainingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- KNIFE: Distilling Reasoning Knowledge From Free-Text RationalesLLM reasoning → Reasoning benchmarks and evaluation +1
- MultiCoder: Multi-Programming-Lingual Pre-Training for Low-Resource Code CompletionMixture-of-experts → MoE large language models
- MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart DerenderingLLM reasoning → Multimodal reasoning +1
- Cross-Lingual Retrieval Augmented Prompt for Low-Resource LanguagesRetrieval-augmented generation → Generation and context integration
- Reasoning with Language Model Prompting: A SurveyLLM reasoning → Prompting and chain-of-thought reasoning
- Privacy Adhering Machine Un-learning in NLPLLM safety and security → Machine unlearning
- Large Language Models are Better Reasoners with Self-VerificationLLM reasoning → Prompting and chain-of-thought reasoning
- MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video GenerationDiffusion models → Audio, speech and music
- Latent Diffusion for Language GenerationDiffusion models → Discrete and text diffusion
- Empowering Diffusion Models on the Embedding Space for Text GenerationDiffusion models → Discrete and text diffusion
- Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action LocalizationMultimodal LLMs / vision-language models → Video understanding with MLLMs
- APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Discovering Language Model Behaviors with Model-Written EvaluationsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-ImitationKnowledge distillation → Knowledge distillation for LLMs
- Emergent Analogical Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
- Discrete Point-wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognition
- An overview of open source Deep Learning-based libraries for Neuroscience
- Leukemia detection based on microscopic blood smear images using deep learning
- Neuro-DynaStress: Predicting Dynamic Stress Distributions in Structural Components
- DGNet: Distribution Guided Efficient Learning for Oil Spill Image Segmentation
- Fully Probabilistic Design for Optimal Transport
- Material Property Prediction using Graphs based on Generically Complete Isometry Invariants
- Anticancer Peptides Classification using Kernel Sparse Representation Classifier
- Wind Power Scenario Generation Using Graph Convolutional Generative Adversarial Network
- Fixed-Weight Difference Target Propagation
- Steel Phase Kinetics Modeling using Symbolic Regression
- ARO-Net: Learning Implicit Fields from Anchored Radial Observations
- Managing Large Dataset Gaps in Urban Air Quality Prediction: DCU-Insight-AQ at MediaEval 2022
- Inverse Reinforcement Learning for Text Summarization
- Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks
- Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance
- Policy learning "without" overlap: Pessimism and generalized empirical Bernstein's inequality
- MetaCLUE: Towards Comprehensive Visual Metaphors Research
- Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training
- Improved Long-Form Spoken Language Translation with Large Language Models
- Python Code Generation by Asking Clarification Questions
- Unsigned Play by Milan Kundera? An Authorship Attribution Study
- LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer
- A Comparative Study on Textual Saliency of Styles from Eye Tracking, Annotations, and Language Models
- Detecting Contradictory COVID-19 Drug Efficacy Claims from Biomedical Literature
- Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations
- Synthetic Pre-Training Tasks for Neural Machine Translation
- Predicting Ejection Fraction from Chest X-rays Using Computer Vision for Diagnosing Heart Failure
- Continuous Semi-Supervised Nonnegative Matrix Factorization
- MANTIS at TSAR-2022 Shared Task: Improved Unsupervised Lexical Simplification with Pretrained Encoders
- Dataless Knowledge Fusion by Merging Weights of Language Models
- (Psycho-)Linguistic Features Meet Transformer Models for Improved Explainable and Controllable Text Simplification
- Robust Design and Evaluation of Predictive Algorithms under Unobserved Confounding
- Dynamic Sparse Network for Time Series Classification: Learning What to "see''
- Exploring Hybrid and Ensemble Models for Multiclass Prediction of Mental Health Status on Social Media
- Denoising instrumented mouthguard measurements of head impact kinematics with a convolutional neural network
- Fixed and adaptive landmark sets for finite pseudometric spaces
- What to Read in a Contract? Party-Specific Summarization of Legal Obligations, Entitlements, and Prohibitions
- Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model
- Training Trajectories of Language Models Across Scales
- Panoptic Lifting for 3D Scene Understanding with Neural Fields
- Human-in-the-loop Abstractive Dialogue Summarization
- Do CoNLL-2003 Named Entity Taggers Still Work Well in 2023?
- Evaluating Human-Language Model Interaction
- DSI++: Updating Transformer Memory with New Documents
- One Embedder, Any Task: Instruction-Finetuned Text Embeddings
- LENS: A Learnable Evaluation Metric for Text Simplification
- Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments
- Correspondence Distillation from NeRF-based GAN
- Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units
- Improving Faithfulness of Abstractive Summarization by Controlling Confounding Effect of Irrelevant Sentences
- A Retrieve-and-Read Framework for Knowledge Graph Link Prediction
- MANER: Mask Augmented Named Entity Recognition for Extreme Low-Resource Languages
- The case for 4-bit precision: k-bit Inference Scaling Laws
- A Probabilistic Framework for Lifelong Test-Time Adaptation
- Continual Learning for Instruction Following from Realtime Feedback
- On Event Individuation for Document-Level Information Extraction
- Graph-based Semantical Extractive Text Analysis
- Resolving Open-textured Rules with Templated Interpretive Arguments
- SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations
- Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor
- A Natural Bias for Language Generation Models
- Human-in-the-loop Evaluation for Early Misinformation Detection: A Case Study of COVID-19 Treatments
- Multilingual Sequence-to-Sequence Models for Hebrew NLP
- Annual field-scale maps of tall and short crops at the global scale using GEDI and Sentinel-2
- Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publications
- LR-Sum: Summarization for Less-Resourced Languages
- StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer
- Task-Oriented Communications for NextG: End-to-End Deep Learning and AI Security Aspects
- Foveate, Attribute, and Rationalize: Towards Physically Safe and Trustworthy AI
- Norm of Word Embedding Encodes Information Gain
- The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges
- Visconde: Multi-document QA with GPT-3 and Neural Reranking
- NusaCrowd: Open Source Initiative for Indonesian NLP Resources
- Uncovering the Origins of Instability in Dynamical Systems: How Attention Mechanism Can Help?
- A Sequential Concept Drift Detection Method for On-Device Learning on Low-End Edge Devices
- Towards Assessing Data Bias in Clinical Trials
- Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation
- Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding
- Taming Lagrangian Chaos with Multi-Objective Reinforcement Learning
- Optimizing Prompts for Text-to-Image Generation
- Discrimination, calibration, and point estimate accuracy of GRU-D-Weibull architecture for real-time individualized endpoint prediction
All 200
- Explanation Regeneration via Information Bottleneck
- Query-as-context Pre-training for Dense Passage Retrieval
- Unsupervised Summarization Re-ranking
- Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling
- Learning Latent Representations to Co-Adapt to Humans
- Reference-based Image and Video Super-Resolution via C2-Matching
- Exploring Interpretability of Independent Components of Word Embeddings with Automated Word Intruder Test
- CiteBench: A benchmark for Scientific Citation Text Generation
- Solving Quantified Modal Logic Problems by Translation to Classical Logics
- Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization
- Source-Free Domain Adaptation for Question Answering with Masked Self-training
- Interactive Cartoonization with Controllable Perceptual Factors
- Mu2SLAM: Multitask, Multilingual Speech and Language Models
- Positive-incentive Noise
- BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting
- HARP: Personalized Hand Reconstruction from a Monocular RGB Video
- FreeEnricher: Enriching Face Landmarks without Additional Cost
- MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering
- Mechanism Design With Predictions for Obnoxious Facility Location
- FedTADBench: Federated Time-Series Anomaly Detection Benchmark
- Fake it, Mix it, Segment it: Bridging the Domain Gap Between Lidar Sensors
- Stochastic Inexact Augmented Lagrangian Method for Nonconvex Expectation Constrained Optimization
- Rethinking Label Smoothing on Multi-hop Question Answering
- Near-optimal Policy Identification in Active Reinforcement Learning
- A note on the smallest eigenvalue of the empirical covariance of causal Gaussian processes
- VC dimensions of group convolutional neural networks
- Optimal Treatment Regimes for Proximal Causal Learning
- Adaptive Control of Client Selection and Gradient Compression for Efficient Federated Learning
- Performance assessment and exhaustive listing of 500+ nature inspired metaheuristic algorithms
- Improving the Generalizability of Text-Based Emotion Detection by Leveraging Transformers with Psycholinguistic Features
- Hardware Acceleration of Lane Detection Algorithm: A GPU Versus FPGA Comparison
- Exploring Optimal Substructure for Out-of-distribution Generalization via Feature-targeted Model Pruning
- Improving Pre-Trained Weights Through Meta-Heuristics Fine-Tuning
- Leveraging Road Area Semantic Segmentation with Auxiliary Steering Task
- Quasi-parametric rates for Sparse Multivariate Functional Principal Components Analysis
- On the Complexity of Representation Learning in Contextual Linear Bandits
- Multistep Multiappliance Load Prediction
- Trial-Based Dominance Enables Non-Parametric Tests to Compare both the Speed and Accuracy of Stochastic Optimizers
- Human in the loop: How to effectively create coherent topics by manually labeling only a few documents per class
- Large Language Models Meet NL2Code: A Survey
- Training Lightweight Graph Convolutional Networks with Phase-field Models
- Gradient Descent-Type Methods: Background and Simple Unified Convergence Analysis
- Less is More: Parameter-Free Text Classification with Gzip
- Aggregating Soft Labels from Crowd Annotations Improves Uncertainty Estimation Under Distribution Shift
- Universal Object Detection with Large Vision Model
- Medical Knowledge Graph QA for Drug-Drug Interaction Prediction based on Multi-hop Machine Reading Comprehension
- AI Art in Architecture
- Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization
- Exploring a multi_stage feedback teaching mode for graduate students of software engineering discipline based on project_driven competition
- Fast Converging Anytime Model Counting
- An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation
- Prediction of Auto Insurance Risk Based on t-SNE Dimensionality Reduction
- Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmark
- Flowstorm: Open-Source Platform with Hybrid Dialogue Architecture
- Enriching Relation Extraction with OpenIE
- TAS-NIR: A VIS+NIR Dataset for Fine-grained Semantic Segmentation in Unstructured Outdoor Environments
- AI Security for Geoscience and Remote Sensing: Challenges and Future Trends
- WACO: Word-Aligned Contrastive Learning for Speech Translation
- Bridging The Gap: Entailment Fused-T5 for Open-retrieval Conversational Machine Reading Comprehension
- Robust Anomaly Map Assisted Multiple Defect Detection with Supervised Classification Techniques
- Explaining Classifications to Non Experts: An XAI User Study of Post Hoc Explanations for a Classifier When People Lack Expertise
- StyleTRF: Stylizing Tensorial Radiance Fields
- SrTR: Self-reasoning Transformer with Visual-linguistic Knowledge for Scene Graph Generation
- Quantum policy gradient algorithms
- Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features
- Synthetic Data Augmentation Using GAN For Improved Automated Visual Inspection
- Multimodal CNN Networks for Brain Tumor Segmentation in MRI: A BraTS 2022 Challenge Solution
- Diffusing Surrogate Dreams of Video Scenes to Predict Video Memorability
- E-NER -- An Annotated Named Entity Recognition Corpus of Legal Text
- SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes
- From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration
- Transferring General Multimodal Pretrained Models to Text Recognition
- Unified, User and Task (UUT) Centered Artificial Intelligence for Metaverse Edge Computing
- ChatGPT: The End of Online Exam Integrity?
- XEngine: Optimal Tensor Rematerialization for Neural Networks in Heterogeneous Environments
- An Investigation of Indian Native Language Phonemic Influences on L2 English Pronunciations
- Boosting Automatic COVID-19 Detection Performance with Self-Supervised Learning and Batch Knowledge Ensembling
- MIGA: A Unified Multi-task Generation Framework for Conversational Text-to-SQL
- Building Height Prediction with Instance Segmentation
- COVID-19 Detection Based on Self-Supervised Transfer Learning Using Chest X-Ray Images
- Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection
- Statistical Dataset Evaluation: Reliability, Difficulty, and Validity
- Very Large Language Model as a Unified Methodology of Text Mining
- The One-Inclusion Graph Algorithm is not Always Optimal
- Focal-UNet: UNet-like Focal Modulation for Medical Image Segmentation
- Out-of-domain GAN inversion via Invertibility Decomposition for Photo-Realistic Human Face Manipulation
- CHAD: Charlotte Anomaly Dataset
- PromptBoosting: Black-Box Text Classification with Ten Forward Passes
- Multi hash embeddings in spaCy
- TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization
- Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systems
- Natural Language to Code Generation in Interactive Data Science Notebooks
- ColoristaNet for Photorealistic Video Style Transfer
- Probabilistic machine learning based predictive and interpretable digital twin for dynamical systems
- PAL: Persona-Augmented Emotional Support Conversation Generation
- OASum: Large-Scale Open Domain Aspect-based Summarization
- An Extension of Fisher's Criterion: Theoretical Results with a Neural Network Realization
- Segmentation Ability Map: Interpret deep features for medical image segmentation
- Spectral Regularized Kernel Two-Sample Tests
- Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning