mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 1 Dec 2023

232 papers

  1. Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank ExpertsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  2. Enhancing Diffusion Models with 3D Perspective Geometry ConstraintsDiffusion models → 3D, point cloud and scene generation
  3. Nash Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  4. Grounding Everything: Emerging Localization Properties in Vision-Language TransformersMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  5. 3DiFACE: Diffusion-based Speech-driven 3D Facial Animation and EditingDiffusion models → Audio, speech and music
  6. DeepCache: Accelerating Diffusion Models for FreeDiffusion models → Diffusion foundations and sampling
  7. Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolutionDiffusion models → Inverse problems and image restoration
  8. Beyond First-Order Tweedie: Solving Inverse Problems using Latent DiffusionDiffusion models → Inverse problems and image restoration
  9. RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human FeedbackMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  10. VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion ModelsDiffusion models → Video generation
  11. ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual PromptsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  12. VideoBooth: Diffusion-based Video Generation with Image PromptsDiffusion models → Video generation
  13. Context Retrieval via Normalized Contextual Latent Interaction for Conversational AgentLLM agents and tool use → Agent memory systems
  14. Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model ResponsesLLM reasoning → Reasoning benchmarks and evaluation
  15. Deep Unlearning: Fast and Efficient Gradient-free Approach to Class ForgettingLLM safety and security → Machine unlearning
  16. Mamba: Linear-Time Sequence Modeling with Selective State SpacesState-space sequence models (S4, Mamba) → Core SSM architectures for language
  17. Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery GamesLLM agents and tool use → Reinforcement learning for LLM agents
  18. LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  19. Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language AlignmentMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  20. TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion ModelsWorld models → Video-generation world models and simulators +1
  21. Domain Adaptive Imitation Learning with Visual ObservationOffline RL and imitation learning from data → Imitation learning methods
  22. Dolphins: Multimodal Language Model for DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  23. Vision-Language Models Learn Super Images for Efficient Partially Relevant Video RetrievalMultimodal LLMs / vision-language models → Video understanding with MLLMs
  24. LinguaLinked: A Distributed Large Language Model Inference System for Mobile DevicesEfficient LLM inference and serving → Serving systems and request scheduling
  25. Text-Guided 3D Face Synthesis -- From Generation to EditingDiffusion models → 3D, point cloud and scene generation
  26. On Exploring the Reasoning Capability of Large Language Models with Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
  27. Agent-OM: Leveraging LLM Agents for Ontology MatchingLLM agents and tool use → Web, search, and research agents
  28. Mark My Words: Analyzing and Evaluating Language Model WatermarksLLM safety and security → Watermarking generated content and models
  29. Sample Efficient Preference Alignment in LLMs via Active ExplorationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  30. Location Sensitive Embedding for Knowledge Graph Reasoning
  31. Knowledge Graph Driven Recommendation System Algorithm
  32. Online Anomaly Detection over Live Social Video Streaming
  33. Semantic Parsing for Question Answering over Knowledge Graphs
  34. Minuet: Accelerating 3D Sparse Convolutions on GPUs
  35. DISTWAR: Fast Differentiable Rendering on Raster-based Rendering Pipelines
  36. Rule-Guided Joint Embedding Learning over Knowledge Graphs
  37. aoip.ai: An Open-Source P2P SDK
  38. Agglomerative Federated Learning: Empowering Larger Model Training via End-Edge-Cloud Collaboration
  39. Clustering Students According to their Academic Achievement Using Fuzzy Logic
  40. Deep Metric Learning for Computer Vision: A Brief Overview
  41. Interpretable Knowledge Tracing via Response Influence-based Counterfactual Reasoning
  42. Deep Learning Models for Arrhythmia Classification Using Stacked Time-frequency Scalogram Images from ECG Signals
  43. Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignment
  44. zkDFL: An efficient and privacy-preserving decentralized federated learning with zero-knowledge proof
  45. Towards a Psychological Generalist AI: A Survey of Current Applications of Large Language Models and Future Prospects
  46. Analyzing the Impact of Fake News on the Anticipated Outcome of the 2024 Election Ahead of Time
  47. Conceptual Engineering Using Large Language Models
  48. Video Summarization: Towards Entity-Aware Captions
  49. Identifying Spurious Correlations using Counterfactual Alignment
  50. Virtual Fusion with Contrastive Learning for Single Sensor-based Activity Recognition
  51. Consistent Mesh Diffusion
  52. Spectral Temporal Contrastive Learning
  53. Spatiotemporal Transformer for Imputing Sparse Data: A Deep Learning Approach
  54. The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models
  55. Improve Supervised Representation Learning with Masked Image Modeling
  56. Hyperparameter Optimization for Large Language Model Instruction-Tuning
  57. FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation models
  58. WATonoBus: Field-Tested All-Weather Autonomous Shuttle Technology
  59. Zero-Shot Video Question Answering with Procedural Programs
  60. Understanding Unimodal Bias in Multimodal Deep Linear Networks
  61. Label Delay in Online Continual Learning
  62. PACE: A Program Analysis Framework for Continuous Performance Prediction
  63. Quick Back-Translation for Unsupervised Machine Translation
  64. Effectiveness of probabilistic contact tracing in epidemic containment: the role of super-spreaders and transmission path reconstruction
  65. LLM-TAKE: Theme Aware Keyword Extraction Using Large Language Models
  66. Extreme Event Prediction with Multi-agent Reinforcement Learning-based Parametrization of Atmospheric and Oceanic Turbulence
  67. Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining
  68. Segment and Caption Anything
  69. EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
  70. Segment Any 3D Gaussians
  71. Latent Space Explorer: Visual Analytics for Multimodal Latent Space Exploration
  72. QAFE-Net: Quality Assessment of Facial Expressions with Landmark Heatmaps
  73. Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction
  74. A Probabilistic Neural Twin for Treatment Planning in Peripheral Pulmonary Artery Stenosis
  75. Physics Inspired Criterion for Pruning-Quantization Joint Learning
  76. NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance
  77. Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion
  78. Exploring the Robustness of Decentralized Training for Large Language Models
  79. ESM-NBR: fast and accurate nucleic acid-binding residue prediction via protein language model feature representation and multi-task learning
  80. Towards Redundancy-Free Sub-networks in Continual Learning
  81. PipeOptim: Ensuring Effective 1F1B Schedule with Optimizer-Dependent Weight Prediction
  82. Adaptive Correspondence Scoring for Unsupervised Medical Image Registration
  83. Heteroscedastic Uncertainty Estimation Framework for Unsupervised Registration
  84. Dense Optical Tracking: Connecting the Dots
  85. Sequential Modeling Enables Scalable Learning for Large Vision Models
  86. MorpheuS: Neural Dynamic 360deg Surface Reconstruction from Monocular RGB-D Video
  87. Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans
  88. Automated Material Properties Extraction For Enhanced Beauty Product Discovery and Makeup Virtual Try-on
  89. Explaining Knock-on Effects of Bias Mitigation
  90. Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals
  91. Scalable Meta-Learning with Gaussian Processes
  92. Adversarial Score Distillation: When score distillation meets GAN
  93. SeaLLMs -- Large Language Models for Southeast Asia
  94. Gaussian Grouping: Segment and Edit Anything in 3D Scenes
  95. Safe Reinforcement Learning in Tensor Reproducing Kernel Hilbert Space
  96. Removing Biases from Molecular Representations via Information Maximization
  97. SpaCE: The Spatial Confounding Environment
  98. PointBeV: A Sparse Approach to BeV Predictions
  99. WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models
  100. Rethinking Detection Based Table Structure Recognition for Visually Rich Document Images
All 232
  1. Object Detector Differences when using Synthetic and Real Training Data
  2. VisionaryVR: An Optical Simulation Tool for Evaluating and Optimizing Vision Correction Solutions in Virtual Reality
  3. Open-vocabulary object 6D pose estimation
  4. Infrared Image Super-Resolution via GAN
  5. Towards Transparency in Coreference Resolution: A Quantum-Inspired Approach
  6. Contextualized word senses: from attention to compositionality
  7. The Efficiency Spectrum of Large Language Models: An Algorithmic Survey
  8. Unsupervised Adaptive Implicit Neural Representation Learning for Scan-Specific MRI Reconstruction
  9. CellMixer: Annotation-free Semantic Cell Segmentation of Heterogeneous Cell Populations
  10. Nonparametric Variational Regularisation of Pretrained Transformers
  11. Dual-Domain Multi-Contrast MRI Reconstruction with Synthesis-based Fusion Network
  12. Resource-constrained knowledge diffusion processes inspired by human peer learning
  13. Simple Transferability Estimation for Regression Tasks
  14. Machine Learning for Health symposium 2023 -- Findings track
  15. SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers
  16. Hashmarks: Privacy-Preserving Benchmarks for High-Stakes AI Evaluation
  17. One to beat them all: "RYU" -- a unifying framework for the construction of safe balls
  18. RefinedFields: Radiance Fields Refinement for Planar Scene Representations
  19. A Recent Survey of Vision Transformers for Medical Image Segmentation
  20. Towards Efficient 3D Object Detection in Bird's-Eye-View Space for Autonomous Driving: A Convolutional-Only Approach
  21. Rethinking the Domain Gap in Near-infrared Face Recognition
  22. Forecasting trends in food security with real time data
  23. Practical Path-based Bayesian Optimization
  24. Weighted Riesz Particles
  25. Investigating a domain adaptation approach for integrating different measurement instruments in a longitudinal clinical registry
  26. Improving Plasticity in Online Continual Learning via Collaborative Learning
  27. Learning from One Continuous Video Stream
  28. UAVs and Birds: Enhancing Short-Range Navigation through Budgerigar Flight Studies
  29. BCN: Batch Channel Normalization for Image Classification
  30. Event Recognition in Laparoscopic Gynecology Videos with Hybrid Transformers
  31. Tracking Object Positions in Reinforcement Learning: A Metric for Keypoint Detection (extended version)
  32. Less is More: Learning Reference Knowledge Using No-Reference Image Quality Assessment
  33. Explainable Fraud Detection with Deep Symbolic Classification
  34. Adaptive Robust Learning using Latent Bernoulli Variables
  35. The Ethics of Automating Legal Actors
  36. Pathway to a fully data-driven geotechnics: lessons from materials informatics
  37. Instruction-tuning Aligns LLMs to the Human Brain
  38. Generative models for visualising abstract social processes: Guiding streetview image synthesis of StyleGAN2 with indices of deprivation
  39. Explanatory Argument Extraction of Correct Answers in Resident Medical Exams
  40. A safe exploration approach to constrained Markov decision processes
  41. Questioning Biases in Case Judgment Summaries: Legal Datasets or Large Language Models?
  42. Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence Pairs
  43. Target-agnostic Source-free Domain Adaptation for Regression Tasks
  44. A Preconditioned Interior Point Method for Support Vector Machines Using an ANOVA-Decomposition and NFFT-Based Matrix-Vector Products
  45. Trained MT Metrics Learn to Cope with Machine-translated References
  46. RIS-Based On-the-Air Semantic Communications -- a Diffractional Deep Neural Network Approach
  47. LiDAR-based curb detection for ground truth annotation in automated driving validation
  48. DeepDR: Deep Structure-Aware RGB-D Inpainting for Diminished Reality
  49. Algorithm-based diagnostic application for diabetic retinopathy detection
  50. SurreyAI 2023 Submission for the Quality Estimation Shared Task
  51. Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting
  52. Summarization-based Data Augmentation for Document Classification
  53. Bayesian causal discovery from unknown general interventions
  54. VEXIR2Vec: An Architecture-Neutral Embedding Framework for Binary Similarity
  55. Generative artificial intelligence enhances creativity but reduces the diversity of novel content
  56. Which Augmentation Should I Use? An Empirical Investigation of Augmentations for Self-Supervised Phonocardiogram Representation Learning
  57. Global Localization: Utilizing Relative Spatio-Temporal Geometric Constraints from Adjacent and Distant Cameras
  58. Explainable AI in Diagnosing and Anticipating Leukemia Using Transfer Learning Method
  59. REDUCR: Robust Data Downsampling Using Class Priority Reweighting
  60. Backbone-based Dynamic Graph Spatio-Temporal Network for Epidemic Forecasting
  61. MultiView Independent Component Analysis with Delays
  62. Japanese Tort-case Dataset for Rationale-supported Legal Judgment Prediction
  63. Interpretable Meta-Learning of Physical Systems
  64. A Bayesian approach for prompt optimization in pre-trained language models
  65. Unfolder: Fast localization and image rectification of a document with a crease from folding in half
  66. Learning Unorthogonalized Matrices for Rotation Estimation
  67. Auto-encoding GPS data to reveal individual and collective behaviour
  68. Meta-Diversity Search in Complex Systems, A Recipe for Artificial Open-Endedness ?
  69. An Encoding Framework for Binarized Images using HyperDimensional Computing
  70. Towards Generalizable Referring Image Segmentation via Target Prompt and Visual Coherence
  71. FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting
  72. Enhancing Image Captioning with Neural Models
  73. PEFTDebias : Capturing debiasing information using PEFTs
  74. From Mutual Information to Expected Dynamics: New Generalization Bounds for Heavy-Tailed SGD
  75. Retina : Low-Power Eye Tracking with Event Camera and Spiking Hardware
  76. Towards Explaining Satellite Based Poverty Predictions with Convolutional Neural Networks
  77. Abstract Syntax Tree for Programming Language Understanding and Representation: How Far Are We?
  78. SCHEME: Scalable Channel Mixer for Vision Transformers
  79. A framework for mining lifestyle profiles through multi-dimensional and high-order mobility feature clustering
  80. CoLLiE: Collaborative Training of Large Language Models in an Efficient Way
  81. A Causality-Aware Pattern Mining Scheme for Group Activity Recognition in a Pervasive Sensor Space
  82. VIoTGPT: Learning to Schedule Vision Tools in LLMs towards Intelligent Video Internet of Things
  83. Learning to Estimate Critical Gait Parameters from Single-View RGB Videos with Transformer-Based Attention Network
  84. GFN-SR: Symbolic Regression with Generative Flow Networks
  85. Study and Survey on Gesture Recognition Systems
  86. Partition-based K-space Synthesis for Multi-contrast Parallel Imaging
  87. Local monotone operator learning using non-monotone operators: MnM-MOL
  88. Enhancing Explainability in Mobility Data Science through a combination of methods
  89. Optimal Sample Complexity of Contrastive Learning
  90. SynFundus-1M: A High-quality Million-scale Synthetic fundus images Dataset with Fifteen Types of Annotation
  91. Streaming Bayesian Modeling for predicting Fat-Tailed Customer Lifetime Value
  92. Event-driven Real-time Retrieval in Web Search
  93. Benchmarking Multi-Domain Active Learning on Image Classification
  94. Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement
  95. Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning
  96. Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training
  97. Impact of Data Augmentation on QCNNs
  98. A Generalizable Deep Learning System for Cardiac MRI
  99. Transfer learning for predicting source terms of principal component transport in chemically reactive flow
  100. Quantum Kernel t-Distributed Stochastic Neighbor Embedding
  101. Manipulating the Label Space for In-Context Classification
  102. The Case for Scalable, Data-Driven Theory: A Paradigm for Scientific Progress in NLP
  103. Student Activity Recognition in Classroom Environments using Transfer Learning
  104. RTQ: Rethinking Video-language Understanding Based on Image-text Model
  105. TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning
  106. OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline
  107. Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value at Risk
  108. Hypergraph Node Representation Learning with One-Stage Message Passing
  109. Learning Anatomically Consistent Embedding for Chest Radiography
  110. Green Edge AI: A Contemporary Survey
  111. Matching Weak Informative Ontologies
  112. StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter
  113. Improving Efficiency of DNN-based Relocalization Module for Autonomous Driving with Server-side Computing
  114. Improving Normalization with the James-Stein Estimator
  115. Segment Anything Model-guided Collaborative Learning Network for Scribble-supervised Polyp Segmentation
  116. 3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation
  117. A knowledge-based data-driven (KBDD) framework for all-day identification of cloud types using satellite remote sensing
  118. RadioGalaxyNET: Dataset and Novel Computer Vision Algorithms for the Detection of Extended Radio Galaxies and Infrared Hosts
  119. Multiple Testing of Linear Forms for Noisy Matrix Completion
  120. Developmental Pretraining (DPT) for Image Classification Networks
  121. QIENet: Quantitative irradiance estimation network using recurrent neural network based on satellite remote sensing data
  122. Towards Aligned Canonical Correlation Analysis: Preliminary Formulation and Proof-of-Concept Results
  123. PsyAttention: Psychological Attention Model for Personality Detection
  124. SEPSIS: I Can Catch Your Lies -- A New Paradigm for Deception Detection
  125. Learning to forecast diagnostic parameters using pre-trained weather embedding
  126. Age-Based Scheduling for Mobile Edge Computing: A Deep Reinforcement Learning Approach
  127. Text Attribute Control via Closed-Loop Disentanglement
  128. Metalearning Continual Learning Algorithms
  129. Towards Clinical Prediction with Transparency: An Explainable AI Approach to Survival Modelling in Residential Aged Care
  130. Adaptability of Computer Vision at the Tactical Edge: Addressing Environmental Uncertainty
  131. Academic competitions
  132. Skipper: Improving the Reach and Fidelity of Quantum Annealers by Skipping Long Chains