mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 25 Dec 2024

128 papers

  1. Efficiently Serving Large Multimodal Models Using EPD DisaggregationMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  2. Speech Recognition With LLMs Adapted to Disordered Speech Using Reinforcement LearningLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  3. Conditional Balance: Improving Multi-Conditioning Trade-Offs in Image GenerationDiffusion models → Image generation, text-to-image and editing
  4. TravelAgent: Generative Agents in the Built EnvironmentLLM agents and tool use → Multimodal and embodied agents
  5. Injecting Bias into Text Classification Models using Backdoor AttacksLLM safety and security → Backdoor and data poisoning attacks
  6. Constraint-Adaptive Policy Switching for Offline Safe Reinforcement LearningOffline RL and imitation learning from data → Safe offline RL
  7. Single Trajectory Distillation for Accelerating Image and Video Style TransferDiffusion models → Video generation
  8. Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inferenceEfficient LLM inference and serving → Speculative decoding
  9. UNIC-Adapter: Unified Image-instruction Adapter with Multi-modal Transformer for Image GenerationDiffusion models → Image generation, text-to-image and editing
  10. HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMsLLM reasoning → Clinical and biomedical applications
  11. Open-Vocabulary Panoptic Segmentation Using BERT Pre-Training of Vision-Language Multiway Transformer ModelMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  12. PRISM: Efficient Long-Range Reasoning With Short-Context LLMsLLM reasoning → Test-time compute and efficient thinking
  13. Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature CachingDiffusion models → Diffusion foundations and sampling
  14. AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft StructuresEfficient LLM inference and serving → Speculative decoding
  15. GAI: Generative Agents for InnovationLLM agents and tool use → Web, search, and research agents
  16. Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  17. Bootstrap Your Own Context LengthSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  18. Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RLOffline RL and imitation learning from data → Offline RL algorithms
  19. DiFiC: Your Diffusion Model Holds the Secret to Fine-Grained ClusteringDiffusion models → Diffusion foundations and sampling
  20. RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive PromptingMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  21. FairGen: Enhancing Fairness in Text-to-Image Diffusion Models via Self-Discovering Latent DirectionsDiffusion models → Image generation, text-to-image and editing
  22. DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person ImagesDiffusion models → 3D, point cloud and scene generation
  23. Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image GenerationDiffusion models → Robustness, privacy and adversarial aspects
  24. Robustness Evaluation of Offline Reinforcement Learning for Robot Control Against Action PerturbationsOffline RL and imitation learning from data → Offline RL algorithms
  25. Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-box Neural Ranking ModelsLLM reasoning → Reasoning for agents, planning and code +1
  26. Elucidating Flow Matching ODE Dynamics with Respect to Data Geometries and DenoisersDiffusion models → Flow matching, time series and science
  27. MRI Reconstruction with Regularized 3D Diffusion Model (R3DM)Diffusion models → Medical imaging and segmentation
  28. Renaissance of Literate Programming in the Era of LLMs: Enhancing LLM-Based Code Generation in Large-Scale Projects
  29. Generative Models with ELBOs Converging to Entropy Sums
  30. Probabilistic Mission Design for Neuro-Symbolic Unmanned Aircraft Systems
  31. Resource-Efficient Transformer Architecture: Optimizing Memory and Execution Time for Real-Time Applications
  32. Fusion of Deep Learning and GIS for Advanced Remote Sensing Image Analysis
  33. 3D Face Reconstruction With Geometry Details From a Single Color Image Under Occluded Scenes
  34. Generative Landmarks Guided Eyeglasses Removal 3D Face Reconstruction
  35. Symbolic Disentangled Representations for Images
  36. Unveiling Secrets of Brain Function With Generative Modeling: Motion Perception in Primates & Cortical Network Organization in Mice
  37. Tempus Core: Area-Power Efficient Temporal-Unary Convolution Core for Low-Precision Edge DLAs
  38. MGAN-CRCM: A Novel Multiple Generative Adversarial Network and Coarse-Refinement Based Cognizant Method for Image Inpainting
  39. WaveDiffUR: A diffusion SDE-based solver for ultra magnification super-resolution in remote sensing images
  40. MiTREE: Multi-input Transformer Ecoregion Encoder for Species Distribution Modelling
  41. Geospatial Data Fusion: Combining Lidar, SAR, and Optical Imagery with AI for Enhanced Urban Mapping
  42. Optimal Federated Learning for Functional Mean Estimation under Heterogeneous Privacy Constraints
  43. Detection and classification of DDoS flooding attacks by machine learning method
  44. How Propense Are Large Language Models at Producing Code Smells? A Benchmarking Study
  45. MTCAE-DFER: Multi-Task Cascaded Autoencoder for Dynamic Facial Expression Recognition
  46. HAND: Hierarchical Attention Network for Multi-Scale Handwritten Document Recognition and Layout Analysis
  47. Evaluating deep learning models for fault diagnosis of a rotating machinery with epistemic and aleatoric uncertainty
  48. CGCOD: Class-Guided Camouflaged Object Detection
  49. Derandomized shallow shadows: Efficient Pauli learning with bounded-depth circuits
  50. Recommending Pre-Trained Models for IoT Devices
  51. Adopting Trustworthy AI for Sleep Disorder Prediction: Deep Time Series Analysis with Temporal Attention Mechanism and Counterfactual Explanations
  52. ModelGrow: Continual Text-to-Video Pre-training with Model Expansion and Language Understanding Enhancement
  53. Bridging Interpretability and Robustness Using LIME-Guided Model Refinement
  54. TopoBDA: Towards Bezier Deformable Attention for Road Topology Understanding
  55. MedHallBench: A New Benchmark for Assessing Hallucination in Medical Large Language Models
  56. Label-free SERS Discrimination of Proline from Hydroxylated Proline at Single-molecule Level Assisted by a Deep Learning Model
  57. Temporal Inconsistency Guidance for Super-resolution Video Quality Assessment
  58. Malware Classification using a Hybrid Hidden Markov Model-Convolutional Neural Network
  59. Graph Cut-guided Maximal Coding Rate Reduction for Learning Image Embedding and Clustering
  60. Exemplar-condensed Federated Class-incremental Learning
  61. Generative Face Parsing Map Guided 3D Face Reconstruction Under Occluded Scenes
  62. An Attentive Dual-Encoder Framework Leveraging Multimodal Visual and Semantic Information for Automatic OSAHS Diagnosis
  63. BCR-Net: Boundary-Category Refinement Network for Weakly Semi-Supervised X-Ray Prohibited Item Detection with Points
  64. Research Experiment on Multi-Model Comparison for Chinese Text Classification Tasks
  65. EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation
  66. FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learning
  67. Stationary Processes, Wiener-Granger Causality, and Matrix Spectral Factorization
  68. Comprehensive Study on Lumbar Disc Segmentation Techniques Using MRI Data
  69. CoEvo: Continual Evolution of Symbolic Solutions Using Large Language Models
  70. Adversarial Training for Graph Neural Networks via Graph Subspace Energy Optimization
  71. HV-BEV: Decoupling Horizontal and Vertical Feature Sampling for Multi-View 3D Object Detection
  72. MotionMap: Representing Multimodality in Human Pose Forecasting
  73. A Culturally-Aware Benchmark for Person Re-Identification in Modest Attire
  74. Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework
  75. TSceneJAL: Joint Active Learning of Traffic Scenes for 3D Object Detection
  76. Overview of MWE history, challenges, and horizons: standing at the 20th anniversary of the MWE workshop series via MWE-UD2024
  77. WeatherGS: 3D Scene Reconstruction in Adverse Weather Conditions via Gaussian Splatting
  78. Few-shot Metric Domain Adaptation: Practical Learning Strategies for an Automated Plant Disease Diagnosis
  79. Computing Approximate Graph Edit Distance via Optimal Transport
  80. Cross-View Image Set Geo-Localization
  81. SWAG: Long-term Surgical Workflow Prediction with Generative-based Anticipation
  82. TPCH: Tensor-interacted Projection and Cooperative Hashing for Multi-view Clustering
  83. Enhancing Federated Graph Learning via Adaptive Fusion of Structural and Node Characteristics
  84. Improving Integrated Gradient-based Transferable Adversarial Examples by Refining the Integration Path
  85. Context-Based Semantic-Aware Alignment for Semi-Supervised Multi-Label Learning
  86. Implicit factorized transformer approach to fast prediction of turbulent channel flows
  87. Advancing NAM-to-Speech Conversion with Novel Methods and the MultiNAM Dataset
  88. MRI2Speech: Speech Synthesis from Articulatory Movements Recorded by Real-time MRI
  89. Adaptive Rate Control for Deep Video Compression with Rate-Distortion Prediction
  90. Federated Learning with Partially Labeled Data: A Conditional Distillation Approach
  91. PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation
  92. CausalTAD: Causal Implicit Generative Model for Debiased Online Trajectory Anomaly Detection
  93. LLM-assisted Vector Similarity Search
  94. GSAVS: Gaussian Splatting-based Autonomous Vehicle Simulator
  95. Distortion-Aware Adversarial Attacks on Bounding Boxes of Object Detectors
  96. DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor Search
  97. Provable Uncertainty Decomposition via Higher-Order Calibration
  98. FOR: Finetuning for Object Level Open Vocabulary Image Retrieval
  99. Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generation
  100. Ister: Linear Transformer for Efficient Multivariate Time Series Forecasting
All 128
  1. Torque-Aware Momentum
  2. On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise
  3. Thermal-Mechanical Physics Informed Deep Learning For Fast Prediction of Thermal Stress Evolution in Laser Metal Deposition
  4. Simultaneously Recovering Multi-Person Meshes and Multi-View Cameras with Human Semantics
  5. ArtNVG: Content-Style Separated Artistic Neighboring-View Gaussian Stylization
  6. Skeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence Criterion
  7. Unified Local and Global Attention Interaction Modeling for Vision Transformers
  8. ObitoNet: Multimodal High-Resolution Point Cloud Reconstruction
  9. Embodied Image Quality Assessment for Robotic Intelligence
  10. Learning Broken Symmetries with Approximate Invariance
  11. Hierarchical Multi-Graphs Learning for Robust Group Re-Identification
  12. Data clustering: a fundamental method in data science and management
  13. Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories
  14. Order Matters! An Empirical Study on Large Language Models' Input Order Bias in Software Fault Localization
  15. Towards Expressive Video Dubbing with Multiscale Multimodal Context Interaction
  16. Successes and Limitations of Object-centric Models at Compositional Generalisation
  17. HELPNet: Hierarchical Perturbations Consistency and Entropy-guided Ensemble for Scribble Supervised Medical Image Segmentation
  18. Automatic Self-supervised Learning for Social Recommendations
  19. Predicting Time Series of Networked Dynamical Systems without Knowing Topology
  20. Intra- and Inter-modal Context Interaction Modeling for Conversational Speech Synthesis
  21. Optimizing Large Language Models with an Enhanced LoRA Fine-Tuning Algorithm for Efficiency and Robustness in NLP Tasks
  22. SAFLITE: Fuzzing Autonomous Systems via Large Language Models
  23. Effective and Lightweight Representation Learning for Link Sign Prediction in Signed Bipartite Graphs
  24. Using Large Language Models for Automated Grading of Student Writing about Science
  25. Evaluating the Adversarial Robustness of Detection Transformers
  26. Variational Bayesian Inference for Tensor Robust Principal Component Analysis
  27. Optimization and Scalability of Collaborative Filtering Algorithms in Large Language Models
  28. Enhanced Recommendation Combining Collaborative Filtering and Large Language Models