mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 11 Oct 2022

309 papers

  1. Detecting Backdoors in Deep Text ClassifiersLLM safety and security → Backdoor and data poisoning attacks
  2. SaiT: Sparse Vision Transformers through Adaptive Token PruningEfficient LLM inference and serving → Token pruning and merging for ViTs
  3. Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASRKnowledge distillation → Speech and audio distillation
  4. Visual Language Maps for Robot NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  5. A generic diffusion-based approach for 3D human pose prediction in the wildDiffusion models → 3D, point cloud and scene generation
  6. Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and GuidanceDiffusion models → Diffusion foundations and sampling
  7. Multi-Agent Distributed and Decentralized Geometric Task AllocationLLM agents and tool use → General LLM agent frameworks and benchmarks
  8. GENIE: Higher-Order Denoising Diffusion SolversDiffusion models → Diffusion foundations and sampling
  9. Mind's Eye: Grounded Language Model Reasoning through SimulationLLM reasoning → Reasoning benchmarks and evaluation
  10. MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training ModelMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  11. Equivariant 3D-Conditional Diffusion Models for Molecular Linker DesignDiffusion models → Flow matching, time series and science
  12. GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion ModelsDiffusion models → Audio, speech and music
  13. How Well Do Multi-hop Reading Comprehension Models Understand Date Information?LLM reasoning → Knowledge- and tool-augmented reasoning
  14. Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of TrialsOffline RL and imitation learning from data → Real-world robot offline RL
  15. Reliable Conditioning of Behavioral Cloning for Offline Reinforcement LearningOffline RL and imitation learning from data → Imitation learning methods
  16. DiffRoll: Diffusion-based Generative Music Transcription with Unsupervised Pretraining CapabilityDiffusion models → Audio, speech and music
  17. Markup-to-Image Diffusion Models with Scheduled SamplingDiffusion models → Image generation, text-to-image and editing
  18. Mixture of Attention Heads: Selecting Attention Heads Per TokenMixture-of-experts → Expert routing strategies
  19. Human-AI Coordination via Human-Regularized Search and LearningOffline RL and imitation learning from data → Imitation learning methods
  20. Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear SystemsLLM reasoning → Mathematical reasoning
  21. Improving Robustness of Retrieval Augmented Translation via Shuffling of SuggestionsRetrieval-augmented generation → Generation and context integration
  22. Chinese Discourse Annotation Reference Manual
  23. Alzheimer's Diagnosis and Generation-Based Chatbot Using Hierarchical Attention and Transformer
  24. Stock Trading Volume Prediction with Dual-Process Meta-Learning
  25. PromptEHR: Conditional Electronic Healthcare Records Generation with Prompt Learning
  26. MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library
  27. Near Real-time CO2 Emissions Based on Carbon Satellite and Artificial Intelligence
  28. Story Designer: Towards a Mixed-Initiative Tool to Create Narrative Structures
  29. Optimal AdaBoost Converges
  30. Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Text
  31. Adversarial Attack Against Image-Based Localization Neural Networks
  32. Efficient Deep Unfolding for SISO-OFDM Channel Estimation
  33. Automatic Real-time Vehicle Classification by Image Colour Component Based Template Matching
  34. Scenario-based Evaluation of Prediction Models for Automated Vehicles
  35. Inner speech recognition through electroencephalographic signals
  36. The evolution of AI approaches for motor imagery EEG-based BCIs
  37. Learning to Optimize Quasi-Newton Methods
  38. Contrastive Neural Ratio Estimation for Simulation-based Inference
  39. The Role of Exploration for Task Transfer in Reinforcement Learning
  40. Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning
  41. SEAL : Interactive Tool for Systematic Error Analysis and Labeling
  42. A composable machine-learning approach for steady-state simulations on high-resolution grids
  43. CLIP also Understands Text: Prompting CLIP for Phrase Understanding
  44. Synthetic Power Analyses: Empirical Evaluation and Application to Cognitive Neuroimaging
  45. Effectiveness of the Recent Advances in Capsule Networks
  46. Parameter estimation of the homodyned K distribution based on neural networks and trainable fractional-order moments
  47. Social-Group-Agnostic Word Embedding Debiasing via the Stereotype Content Model
  48. AMICO: Amodal Instance Composition
  49. Controllable Radiance Fields for Dynamic Face Synthesis
  50. Short-term prediction of stream turbidity using surrogate data and a meta-model approach
  51. Finding and Listing Front-door Adjustment Sets
  52. Underspecification in Scene Description-to-Depiction Tasks
  53. Deep Counterfactual Estimation with Categorical Background Variables
  54. A unified model for continuous conditional video prediction
  55. Exploration via Elliptical Episodic Bonuses
  56. Linkless Link Prediction via Relational Distillation
  57. Designing Robust Transformers using Robust Kernel Density Estimation
  58. Transfer Learning with Joint Fine-Tuning for Multimodal Sentiment Analysis
  59. Trading Off Resource Budgets for Improved Regret Bounds
  60. Scaling Up Deliberation for Multilingual ASR
  61. Towards Discriminative and Transferable One-Stage Few-Shot Object Detectors
  62. Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models
  63. Cross-Lingual Speaker Identification Using Distant Supervision
  64. C-Mixup: Improving Generalization in Regression
  65. Bil-DOS: A Bi-lingual Dialogue Ordering System (for Subway)
  66. Applying FrameNet to Chinese(Poetry)
  67. Deep Active Ensemble Sampling For Image Classification
  68. Vote'n'Rank: Revision of Benchmarking with Social Choice Theory
  69. Match Cutting: Finding Cuts with Smooth Visual Transitions
  70. Joint localization and classification of breast tumors on ultrasound images using a novel auxiliary attention-based framework
  71. Detecting Propagators of Disinformation on Twitter Using Quantitative Discursive Analysis
  72. Decoupled Context Processing for Context Augmented Language Modeling
  73. Streaming Punctuation for Long-form Dictation with Transformers
  74. Toward Sustainable Continual Learning: Detection and Knowledge Repurposing of Similar Tasks
  75. On RKHS Choices for Assessing Graph Generators via Kernel Stein Statistics
  76. Curved Representation Space of Vision Transformers
  77. Stochastic Constrained DRO with a Complexity Independent of Sample Size
  78. Distance Map Supervised Landmark Localization for MR-TRUS Registration
  79. Context-aware Bayesian Mixed Multinomial Logit Model
  80. TetGAN: A Convolutional Neural Network for Tetrahedral Mesh Generation
  81. DeepMend: Learning Occupancy Functions to Represent Shape for Repair
  82. Automatic Speech Recognition of Low-Resource Languages Based on Chukchi
  83. Measuring and Improving Semantic Diversity of Dialogue Generation
  84. Embeddings as Epistemic States: Limitations on the Use of Pooling Operators for Accumulating Knowledge
  85. Analyzing Text Representations under Tight Annotation Budgets: Measuring Structural Alignment
  86. Language Independent Stance Detection: Social Interaction-based Embeddings and Large Language Models
  87. Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers
  88. Dynamic Ensemble Size Adjustment for Memory Constrained Mondrian Forest
  89. Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inference
  90. Application of Deep Learning on Single-Cell RNA-sequencing Data Analysis: A Review
  91. Towards Consistency and Complementarity: A Multiview Graph Information Bottleneck Approach
  92. Transformers generalize differently from information stored in context vs in weights
  93. Semi-supervised detection of structural damage using Variational Autoencoder and a One-Class Support Vector Machine
  94. Performance Deterioration of Deep Learning Models after Clinical Deployment: A Case Study with Auto-segmentation for Definitive Prostate Cancer Radiotherapy
  95. Understanding Embodied Reference with Touch-Line Transformer
  96. Human Body Measurement Estimation with Adversarial Augmentation
  97. Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
  98. HiFECap: Monocular High-Fidelity and Expressive Capture of Human Performances
  99. Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Tasks
  100. CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory
All 309
  1. Understanding or Manipulation: Rethinking Online Performance Gains of Modern Recommender Systems
  2. The Typical Behavior of Bandit Algorithms
  3. The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes
  4. Regret Bounds for Risk-Sensitive Reinforcement Learning
  5. Entity Disambiguation with Entity Definitions
  6. A Kernel-Based View of Language Model Fine-Tuning
  7. Discovered Policy Optimisation
  8. APSNet: Attention Based Point Cloud Sampling
  9. Oflib: Facilitating Operations with and on Optical Flow Fields in Python
  10. Habitat-Matterport 3D Semantics Dataset
  11. SEE-Few: Seed, Expand and Entail for Few-shot Named Entity Recognition
  12. EllipsoNet: Deep-learning-enabled optical ellipsometry for complex thin films
  13. Semantic Segmentation under Adverse Conditions: A Weather and Nighttime-aware Synthetic Data-based Approach
  14. Multilingual BERT has an accent: Evaluating English influences on fluency in multilingual models
  15. Zero-Order One-Point Estimate with Distributed Stochastic Gradient-Tracking Technique
  16. Neural Shape Deformation Priors
  17. An Experimental Study on Private Aggregation of Teacher Ensemble Learning for End-to-End Speech Recognition
  18. Contrastive Training Improves Zero-Shot Classification of Semi-structured Documents
  19. MTet: Multi-domain Translation for English and Vietnamese
  20. Divergence Results and Convergence of a Variance Reduced Version of ADAM
  21. Improving Sample Efficiency of Deep Learning Models in Electricity Market
  22. Enriching Biomedical Knowledge for Low-resource Language Through Large-Scale Translation
  23. Digitization of Raster Logs: A Deep Learning Approach
  24. Geometry of Radial Basis Neural Networks for Safety Biased Approximation of Unsafe Regions
  25. Navigating Ensemble Configurations for Algorithmic Fairness
  26. Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection
  27. On Adaptivity in Non-stationary Stochastic Optimization With Bandit Feedback
  28. Digital Twin-Based Multiple Access Optimization and Monitoring via Model-Driven Bayesian Learning
  29. Aggregating Crowdsourced and Automatic Judgments to Scale Up a Corpus of Anaphoric Reference for Fiction and Wikipedia Texts
  30. Benefits of Permutation-Equivariance in Auction Mechanisms
  31. What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?
  32. Motion Aware Self-Supervision for Generic Event Boundary Detection
  33. Knowledge-Driven New Drug Recommendation
  34. Misspecified Phase Retrieval with Generative Priors
  35. Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learning
  36. Global Spectral Filter Memory Network for Video Object Segmentation
  37. The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition
  38. Hypergraph Convolutional Networks for Weakly-Supervised Semantic Segmentation
  39. Schedule-Robust Online Continual Learning
  40. Causal and Counterfactual Views of Missing Data Models
  41. OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions
  42. ViLPAct: A Benchmark for Compositional Generalization on Multimodal Human Activities
  43. Evaluating Unsupervised Denoising Requires Unsupervised Metrics
  44. Continual Training of Language Models for Few-Shot Learning
  45. What does a deep neural network confidently perceive? The effective dimension of high certainty class manifolds and their low confidence boundaries
  46. Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentation
  47. Style-Guided Inference of Transformer for High-resolution Image Synthesis
  48. An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification
  49. Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems
  50. An efficient neural-network and finite-difference hybrid method for elliptic interface problems with applications
  51. Hybrid Inverted Index Is a Robust Accelerator for Dense Retrieval
  52. Robust and Controllable Object-Centric Learning through Energy-based Models
  53. Autonomous Asteroid Characterization Through Nanosatellite Swarming
  54. DeepMLE: A Robust Deep Maximum Likelihood Estimator for Two-view Structure from Motion
  55. ViFiCon: Vision and Wireless Association Via Self-Supervised Contrastive Learning
  56. Finding the global semantic representation in GAN through Frechet Mean
  57. Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data
  58. Follow-up Attention: An Empirical Study of Developer and Neural Model Code Exploration
  59. Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network
  60. Adversarial Contrastive Learning for Evidence-aware Fake News Detection with Graph Neural Networks
  61. Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models
  62. MAgNet: Mesh Agnostic Neural PDE Solver
  63. Map-free Visual Relocalization: Metric Pose Relative to a Single Image
  64. Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning
  65. Pooling Strategies for Simplicial Convolutional Networks
  66. Like a bilingual baby: The advantage of visually grounding a bilingual language model
  67. Equivariance-aware Architectural Optimization of Neural Networks
  68. Better Than Whitespace: Information Retrieval for Languages without Custom Tokenizers
  69. T5 for Hate Speech, Augmented Data and Ensemble
  70. Frequency-Aware Self-Supervised Monocular Depth Estimation
  71. Aggregating Layers for Deepfake Detection
  72. Instance Regularization for Discriminative Language Model Pre-training
  73. Block Format Error Bounds and Optimal Block Size Selection
  74. High-precision Density Mapping of Marine Debris and Floating Plastics via Satellite Imagery
  75. Large-to-small Image Resolution Asymmetry in Deep Metric Learning
  76. FreGAN: Exploiting Frequency Components for Training GANs under Limited Data
  77. Are Pretrained Multilingual Models Equally Fair Across Languages?
  78. Unlabelled Sample Compression Schemes for Intersection-Closed Classes and Extremal Classes
  79. Low Complexity Convolutional Neural Networks for Equalization in Optical Fiber Transmission
  80. Enabling ISP-less Low-Power Computer Vision
  81. A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning
  82. Disentangling Causal Effects from Sets of Interventions in the Presence of Unobserved Confounders
  83. QuCNN : A Quantum Convolutional Neural Network with Entanglement Based Backpropagation
  84. CIRCA: comprehensible online system in support of chest X-rays-based COVID-19 diagnosis
  85. Parallel Augmentation and Dual Enhancement for Occluded Person Re-identification
  86. DPANET:Dual Pooling Attention Network for Semantic Segmentation
  87. Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Framework
  88. Non-Asymptotic Analysis of a UCB-based Top Two Algorithm
  89. COVID-19-related Nepali Tweets Classification in a Low Resource Setting
  90. Learning to Locate Visual Answer in Video Corpus Using Question
  91. Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization
  92. Exploring Interactions and Regulations in Collaborative Learning: An Interdisciplinary Multimodal Dataset
  93. Class-Specific Explainability for Deep Time Series Classifiers
  94. LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward
  95. Code Librarian: A Software Package Recommendation System
  96. Machine Translation between Spoken Languages and Signed Languages Represented in SignWriting
  97. MiDe22: An Annotated Multi-Event Tweet Dataset for Misinformation Detection
  98. Continual Learning by Modeling Intra-Class Variation
  99. Computationally-efficient initialisation of GPs: The generalised variogram method
  100. TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learning
  101. PP-StructureV2: A Stronger Document Analysis System
  102. Stable and Efficient Adversarial Training through Local Linearization
  103. Race Bias Analysis of Bona Fide Errors in face anti-spoofing
  104. Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment
  105. Multi-User Reinforcement Learning with Low Rank Rewards
  106. A new perspective on Digital Twins: Imparting intelligence and agency to entities
  107. Printing variability of copy detection patterns
  108. FusionDeepMF: A Dual Embedding based Deep Fusion Model for Recommendation
  109. SGD with Large Step Sizes Learns Sparse Features
  110. Gender Stereotyping Impact in Facial Expression Recognition
  111. Generalization Analysis on Learning with a Concurrent Verifier
  112. Label Noise-Robust Learning using a Confidence-Based Sieving Strategy
  113. A Causal Analysis of Harm
  114. Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning
  115. CASAPose: Class-Adaptive and Semantic-Aware Multi-Object Pose Estimation
  116. Client Error Clustering Approaches in Content Delivery Networks (CDN)
  117. Memory transformers for full context and high-resolution 3D Medical Segmentation
  118. CD-FSOD: A Benchmark for Cross-domain Few-shot Object Detection
  119. Learning Control Policies for Stochastic Systems with Reach-avoid Guarantees
  120. Learning Provably Stabilizing Neural Controllers for Discrete-Time Stochastic Systems
  121. Towards Structure-aware Paraphrase Identification with Phrase Alignment Using Sentence Encoders
  122. Intrinsic Dimension for Large-Scale Geometric Learning
  123. Weakly-Supervised Optical Flow Estimation for Time-of-Flight
  124. Natural Language Processing for Cognitive Analysis of Emotions
  125. On the Use of Semantically-Aligned Speech Representations for Spoken Language Understanding
  126. Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training
  127. Computer Vision based inspection on post-earthquake with UAV synthetic dataset
  128. ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning
  129. Zeroth-Order Hard-Thresholding: Gradient Error vs. Expansivity
  130. EnsembleMOT: A Step towards Ensemble Learning of Multiple Object Tracking
  131. RoHNAS: A Neural Architecture Search Framework with Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networks
  132. Component-Wise Natural Gradient Descent -- An Efficient Neural Network Optimization
  133. Factors of Influence of the Overestimation Bias of Q-Learning
  134. Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling
  135. EOCSA: Predicting Prognosis of Epithelial Ovarian Cancer with Whole Slide Histopathological Images
  136. Rethinking the Event Coding Pipeline with Prompt Entailment
  137. Deep Spectro-temporal Artifacts for Detecting Synthesized Speech
  138. Constrained Deployment Optimization in Integrated Access and Backhaul Networks
  139. Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues
  140. Self-supervised debiasing using low rank regularization
  141. Training Debiased Subnetworks with Contrastive Weight Pruning
  142. Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition
  143. PatternRank: Leveraging Pretrained Language Models and Part of Speech for Unsupervised Keyphrase Extraction
  144. Leveraging the Video-level Semantic Consistency of Event for Audio-visual Event Localization
  145. STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networks
  146. Multi-site Diagnostic Classification Of Schizophrenia Using 3D CNN On Aggregated Task-based fMRI Data
  147. Planning Assembly Sequence with Graph Transformer
  148. It Takes Two: Masked Appearance-Motion Modeling for Self-supervised Video Transformer Pre-training
  149. DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation
  150. From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models
  151. Stochastic Direct Search Method for Blind Resource Allocation
  152. CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions
  153. On Scrambling Phenomena for Randomly Initialized Recurrent Networks
  154. A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models
  155. Robust Human Matting via Semantic Guidance
  156. Kernelized multi-graph matching
  157. CTC Alignments Improve Autoregressive Translation
  158. Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA
  159. DIGAT: Modeling News Recommendation with Dual-Graph Interaction
  160. Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation
  161. Neural Networks are Decision Trees
  162. Legal Element-oriented Modeling with Multi-view Contrastive Learning for Legal Case Retrieval
  163. Broad-persistent Advice for Interactive Reinforcement Learning Scenarios
  164. Meta-Learning with Self-Improving Momentum Target
  165. Edge-Cloud Cooperation for DNN Inference via Reinforcement Learning and Supervised Learning
  166. Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach
  167. Fine-Grained Image Style Transfer with Visual Transformers
  168. Variability Matters : Evaluating inter-rater variability in histopathology for robust cell detection
  169. BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation
  170. On Explainability in AI-Solutions: A Cross-Domain Survey
  171. Deep Fourier Up-Sampling
  172. LARF: Two-level Attention-based Random Forests with a Mixture of Contamination Models
  173. The Fast and Accurate Approach to Detection and Segmentation of Melanoma Skin Cancer using Fine-tuned Yolov3 and SegNet Based on Deep Transfer Learning
  174. Combining datasets to increase the number of samples and improve model fitting
  175. Can Language Models Be Specific? How?
  176. Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering
  177. Contrastive Trajectory Similarity Learning with Dual-Feature Attention
  178. Understanding the Failure of Batch Normalization for Transformers in NLP
  179. TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency
  180. UGformer for Robust Left Atrium and Scar Segmentation Across Scanners
  181. DHRL: A Graph-Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning
  182. CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking
  183. Retrieval Augmentation for T5 Re-ranker using External Sources
  184. Time-aware topic identification in social media with pre-trained language models: A case study of electric vehicles
  185. X-NeRF: Explicit Neural Radiance Field for Multi-Scene 360circ Insufficient RGB-D Views
  186. ACRNet: Attention Cube Regression Network for Multi-view Real-time 3D Human Pose Estimation in Telemedicine
  187. Multi-Object Navigation with dynamically learned neural implicit representations
  188. Tackling Instance-Dependent Label Noise with Dynamic Distribution Calibration
  189. Exploring CNN-based models for image's aesthetic score prediction with using ensemble
  190. Boosting Adversarial Robustness From The Perspective of Effective Margin Regularization
  191. DA-VSR: Domain Adaptable Volumetric Super-Resolution For Medical Images
  192. HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient Korea
  193. Deep learning model compression using network sensitivity and gradients
  194. BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset
  195. Projection-Free Functional Constrained Optimization for Risk Aversion and Sparsity Control
  196. 3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography
  197. Leveraging Artificial Intelligence on Binary Code Comprehension
  198. Pre-Training Representations of Binary Code Using Contrastive Learning
  199. IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
  200. Repainting and Imitating Learning for Lane Detection
  201. Checks and Strategies for Enabling Code-Switched Machine Translation
  202. Approximation of nearly-periodic symplectic maps via structure-preserving neural networks
  203. How to construct the symmetric cycle of length 5 using Haj'os construction with an adapted Rank Genetic Algorithm
  204. Self-supervised Model Based on Masked Autoencoders Advance CT Scans Classification
  205. VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement
  206. Improving Dense Contrastive Learning with Dense Negative Pairs
  207. Relational Attention: Generalizing Transformers for Graph-Structured Tasks
  208. InQMAD: Incremental Quantum Measurement Anomaly Detection
  209. AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization