mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 12 Aug 2023

71 papers

  1. A new solution and concrete implementation steps for Artificial General IntelligenceWorld models → World models for language agents
  2. Accelerating Diffusion-based Combinatorial Optimization Solvers by Progressive DistillationDiffusion models → Diffusion foundations and sampling
  3. VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World UseMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  4. ModelScope Text-to-Video Technical ReportDiffusion models → Video generation
  5. EquiDiff: A Conditional Equivariant Diffusion Model For Trajectory PredictionDiffusion models → Diffusion and flow policies for robotics
  6. Learning Abstract Visual Reasoning via Task Decomposition: A Case Study in Raven Progressive MatricesLLM reasoning → Multimodal reasoning
  7. GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via CipherLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  8. Multi-Label Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  9. Ground Truth Or Dare: Factors Affecting The Creation Of Medical Datasets For Training AI
  10. Advances in Self-Supervised Learning for Synthetic Aperture Sonar Data Processing, Classification, and Pattern Recognition
  11. Stationary Algorithmic Balancing For Dynamic Email Re-Ranking Problem
  12. One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training
  13. Emergent communication for AR
  14. Smart Knowledge Transfer using Google-like Search
  15. 3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking
  16. Fusion-GRU: A Deep Learning Model for Future Bounding Box Prediction of Traffic Agents in Risky Driving Videos
  17. ADRMX: Additive Disentanglement of Domain Features with Remix Loss
  18. Polyp-SAM++: Can A Text Guided SAM Perform Better for Polyp Segmentation?
  19. DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning
  20. Can Unstructured Pruning Reduce the Depth in Deep Neural Networks?
  21. On the Interplay of Convolutional Padding and Adversarial Robustness
  22. Bio-SIEVE: Exploring Instruction Tuning Large Language Models for Systematic Review Automation
  23. LadleNet: A Two-Stage UNet for Infrared Image to Visible Image Translation Guided by Semantic Segmentation
  24. CoverNav: Cover Following Navigation Planning in Unstructured Outdoor Environment with Deep Reinforcement Learning
  25. Value-Distributional Model-Based Reinforcement Learning
  26. Approximate Answering of Graph Queries
  27. 4DRVO-Net: Deep 4D Radar-Visual Odometry Using Multi-Modal and Multi-Scale Adaptive Fusion
  28. Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction
  29. MT4CrossOIE: Multi-stage Tuning for Cross-lingual Open Information Extraction
  30. Human Behavior-based Personalized Meal Recommendation and Menu Planning Social System
  31. Revisiting Vision Transformer from the View of Path Ensemble
  32. Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition
  33. MC-DRE: Multi-Aspect Cross Integration for Drug Event/Entity Extraction
  34. Digital elevation model correction in urban areas using extreme gradient boosting, land cover and terrain parameters
  35. Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical Imaging
  36. SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learning
  37. BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation
  38. With a Little Help from the Authors: Reproducing Human Evaluation of an MT Error Detector
  39. SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models
  40. Seed Feature Maps-based CNN Models for LEO Satellite Remote Sensing Services
  41. HyperFormer: Enhancing Entity and Relation Interaction for Hyper-Relational Knowledge Graph Completion
  42. AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models
  43. Three Ways of Using Large Language Models to Evaluate Chat
  44. NewsDialogues: Towards Proactive News Grounded Conversation
  45. Latent Emission-Augmented Perspective-Taking (LEAPT) for Human-Robot Interaction
  46. Performance Analysis for Resource Constrained Decentralized Federated Learning Over Wireless Networks
  47. EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere
  48. Generating Faithful Text From a Knowledge Graph with Noisy Reference Text
  49. Out-of-distribution multi-view auto-encoders for prostate cancer lesion detection
  50. Leveraging multi-view data without annotations for prostate MRI segmentation: A contrastive approach
  51. Flexible Keyword Spotting based on Homogeneous Audio-Text Embedding
  52. Volterra Accentuated Non-Linear Dynamical Admittance (VANYA) to model Deforestation: An Exemplification from the Amazon Rainforest
  53. Tiny and Efficient Model for the Edge Detection Generalization
  54. Not So Robust After All: Evaluating the Robustness of Deep Neural Networks to Unseen Adversarial Attacks
  55. A One-dimensional HEVC video steganalysis method using the Optimality of Predicted Motion Vectors
  56. Text-to-Video: a Two-stage Framework for Zero-shot Identity-agnostic Talking-head Generation
  57. Demonstration-based learning for few-shot biomedical named entity recognition under machine reading comprehension
  58. Improved YOLOv8 Detection Algorithm in Security Inspection Image
  59. Semantic Equivariant Mixup
  60. ERNetCL: A novel emotion recognition network in textual conversation based on curriculum learning strategy
  61. Latent Random Steps as Relaxations of Max-Cut, Min-Cut, and More
  62. A Sequential Meta-Transfer (SMT) Learning to Combat Complexities of Physics-Informed Neural Networks: Application to Composites Autoclave Processing
  63. TongueSAM: An Universal Tongue Segmentation Model Based on SAM with Zero-Shot
  64. Neural Latent Aligner: Cross-trial Alignment for Learning Representations of Complex, Naturalistic Neural Data
  65. A Domain-adaptive Physics-informed Neural Network for Inverse Problems of Maxwell's Equations in Heterogeneous Media
  66. Distributionally Robust Optimization and Invariant Representation Learning for Addressing Subgroup Underrepresentation: Mechanisms and Limitations
  67. Learn Single-horizon Disease Evolution for Predictive Generation of Post-therapeutic Neovascular Age-related Macular Degeneration
  68. Performance Prediction for Multi-hop Questions
  69. Genetic heterogeneity analysis using genetic algorithm and network science
  70. Multiclass Learnability Does Not Imply Sample Compression
  71. Sensitivity-Aware Mixed-Precision Quantization and Width Optimization of Deep Neural Networks Through Cluster-Based Tree-Structured Parzen Estimation