mlsanityData to 7 Oct 2026

Papers

New on arXiv

Sat 21 Dec 2024

190 papers

  1. Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image ClassificationLLM safety and security → Machine unlearning
  2. RoomPainter: View-Integrated Diffusion for Consistent Indoor Scene TexturingDiffusion models → 3D, point cloud and scene generation
  3. HyperCLIP: Adapting Vision-Language models with HypernetworksMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  4. SilVar: Speech Driven Multimodal Model for Reasoning Visual Question Answering and Object LocalizationLLM reasoning → Multimodal reasoning +1
  5. Towards Selection and Transition Between Behavior-Based Neural Networks for Automated DrivingEnd-to-end autonomous driving → End-to-end system architecture
  6. ViM-Disparity: Bridging the Gap of Speed, Accuracy and Memory for Disparity Map GenerationState-space sequence models (S4, Mamba) → Vision Mamba backbones
  7. OpenAI o1 System CardLLM reasoning → Reasoning for agents, planning and code +1
  8. GANFusion: Feed-Forward Text-to-3D with Diffusion in GAN SpaceDiffusion models → 3D, point cloud and scene generation
  9. From Pixels to Gigapixels: Bridging Local Inductive Bias and Long-Range Dependencies with Pixel-MambaState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  10. Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning AttacksRetrieval-augmented generation → Privacy and security of RAG
  11. AlzheimerRAG: Multimodal Retrieval Augmented Generation for Clinical Use Cases using PubMed articlesRetrieval-augmented generation → Medical and biomedical RAG
  12. TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  13. Formal Language Knowledge Corpus for Retrieval Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory
  14. The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  15. Two-in-One: Unified Multi-Person Interactive Motion Generation by Latent Diffusion TransformerDiffusion models → Video generation
  16. TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented GenerationRetrieval-augmented generation → Time series and agricultural RAG
  17. Easier Said Than Done: Unpacking Intent-Behavior Gap in Jailbreaking LLM-Based RobotsLLM safety and security → Jailbreaking
  18. Mamba-SEUNet: Mamba UNet for Monaural Speech EnhancementState-space sequence models (S4, Mamba) → Speech and audio SSMs
  19. Large Language Model Can Be a Foundation for Hidden Rationale-Based RetrievalRetrieval-augmented generation → RAG pipeline design and evaluation
  20. Do Multimodal Language Models Really Understand Direction? A Benchmark for Compass Direction ReasoningLLM reasoning → Spatial and embodied reasoning +1
  21. REO-VLM: Transforming VLM to Meet Regression Challenges in Earth ObservationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  22. A Generalizable 3D Diffusion Framework for Low-Dose and Few-View Cardiac SPECTDiffusion models → Medical imaging and segmentation
  23. Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  24. Diffusion Prior Interpolation for Flexibility Real-World Face Super-ResolutionDiffusion models → Inverse problems and image restoration
  25. Self-guided Knowledgeable Network of Thoughts: Amplifying Reasoning with Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  26. HammerBench: Fine-Grained Function-Calling Evaluation in Real Mobile Device ScenariosLLM agents and tool use → Tool learning and function calling
  27. TrojFlow: Flow Models are Natural Targets for Trojan AttacksLLM safety and security → Backdoor and data poisoning attacks
  28. Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future DirectionsLLM safety and security → Membership inference attacks
  29. Speech Retrieval-Augmented Generation without Automatic Speech RecognitionRetrieval-augmented generation → Conversational and speech RAG
  30. Trusted Mamba Contrastive Network for Multi-View ClusteringState-space sequence models (S4, Mamba) → Vision Mamba backbones
  31. When Can Proxies Improve the Sample Complexity of Preference Learning?LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  32. The Road to Artificial SuperIntelligence: A Comprehensive Survey of SuperalignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  33. Correcting Large Language Model Behavior via Influence FunctionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  34. Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart UnderstandingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  35. Revisiting MLLMs: An In-Depth Analysis of Image Classification AbilitiesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  36. InfoTech Assistant: A Multimodal Conversational Agent for InfoTechnology Web Portal QueriesLLM agents and tool use → Web, search, and research agents
  37. Application of Multimodal Large Language Models in Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  38. MERaLiON-TextLLM: Cross-Lingual Understanding of Large Language Models in Chinese, Indonesian, Malay, and Singlish
  39. Distilling Large Language Models for Efficient Clinical Information Extraction
  40. Underutilization of Syntactic Processing by Chinese Learners of English in Comprehending English Sentences, Evidenced from Adapted Garden-Path Ambiguity Experiment
  41. Multi-atlas Ensemble Graph Neural Network Model For Major Depressive Disorder Detection Using Functional MRI Data
  42. Back To The Future: A Hybrid Transformer-XGBoost Model for Action-oriented Future-proofing Nowcasting
  43. BoostMD: Accelerating molecular sampling by leveraging ML force field features from previous time-steps
  44. Evaluating and Enhancing LLMs for Multi-turn Text-to-SQL with Multiple Question Types
  45. IMVB7t: A Multi-Modal Model for Food Preferences based on Artificially Produced Traits
  46. Quantum-Like Contextuality in Large Language Models
  47. Balls-and-Bins Sampling for DP-SGD
  48. Gradient-Based Non-Linear Inverse Learning
  49. Enhancing web traffic attacks identification through ensemble methods and feature selection
  50. DCOR: Anomaly Detection in Attributed Networks via Dual Contrastive Learning Reconstruction
  51. Symplectic Neural Flows for Modeling and Discovery
  52. SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs
  53. Fed-ZOE: Communication-Efficient Over-the-Air Federated Learning via Zeroth-Order Estimation
  54. DMesh++: An Efficient Differentiable Mesh for Complex Shapes
  55. Fast Multi-Group Gaussian Process Factor Models
  56. Assessing Social Alignment: Do Personality-Prompted Large Language Models Behave Like Humans?
  57. Does calibration mean what they say it means; or, the reference class problem rises again
  58. A Comparative Study on Machine Learning Models to Classify Diseases Based on Patient Behaviour and Habits
  59. A Protocol for KG Construction Tasks Involving Users
  60. Optimization Insights into Deep Diagonal Linear Networks
  61. Paraformer: Parameterization of Sub-grid Scale Processes Using Transformers
  62. A Method for the Runtime Validation of AI-based Environment Perception in Automated Driving System
  63. Training Set Augmentation and Biology-Aware Harmonization Improve Radiomic Models for Lung Cancer Prediction in Indeterminate Nodules
  64. Leveraging Highly Approximated Multipliers in DNN Inference
  65. The Master Key Filters Hypothesis: Deep Filters Are General
  66. Gradient-based Trajectory Optimization with Parallelized Differentiable Traffic Simulation
  67. Solving Inverse Problems via Diffusion Optimal Control
  68. Beyond Partisan Leaning: A Comparative Analysis of Political Bias in Large Language Models
  69. EasyVis2: A Real Time Multi-view 3D Visualization System for Laparoscopic Surgery Training Enhanced by a Deep Neural Network YOLOv8-Pose
  70. UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning
  71. KKANs: Kurkova-Kolmogorov-Arnold Networks and Their Learning Dynamics
  72. LUCES-MV: A Multi-View Dataset for Near-Field Point Light Source Photometric Stereo
  73. Reasoning about Actual Causes in Nondeterministic Domains -- Extended Version
  74. Enhancing Conflict Resolution in Language Models via Abstract Argumentation
  75. Coupling Neural Networks and Physics Equations For Li-Ion Battery State-of-Charge Prediction
  76. Divide and Conquer: Grounding a Bleeding Areas in Gastrointestinal Image with Two-Stage Model
  77. Lillama: Large Language Models Compression via Low-Rank Feature Distillation
  78. From Histopathology Images to Cell Clouds: Learning Slide Representations with Hierarchical Cell Transformer
  79. A Unifying Family of Data-Adaptive Partitioning Algorithms
  80. FAP-CD: Fairness-Driven Age-Friendly Community Planning via Conditional Diffusion Generation
  81. Interact with me: Joint Egocentric Forecasting of Intent to Interact, Attitude and Social Actions
  82. DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering
  83. From Correlation to Causation: Understanding Climate Change through Causal Analysis and LLM Interpretations
  84. Subgoal Discovery Using a Free Energy Paradigm and State Aggregations
  85. NILE: Internal Consistency Alignment in Large Language Models
  86. VAST 1.0: A Unified Framework for Controllable and Consistent Video Generation
  87. STAMPsy: Towards SpatioTemporal-Aware Mixed-Type Dialogues for Psychological Counseling
  88. On Enhancing Network Throughput using Reinforcement Learning in Sliced Testbeds
  89. Label Privacy in Split Learning for Large Models with Parameter-Efficient Training
  90. Transformer-based toxin-protein interaction analysis prioritizes airborne particulate matter components with potential adverse health effects
  91. Adversarial Attack Against Images Classification based on Generative Adversarial Networks
  92. Generalizable Articulated Object Perception with Superpoints
  93. IV-tuning: Parameter-Efficient Transfer Learning for Infrared-Visible Tasks
  94. Internalized Self-Correction for Large Language Models
  95. PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation
  96. Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising
  97. An explainable operator approximation framework under the guideline of Green's function
  98. L3TC: Leveraging RWKV for Learned Lossless Low-Complexity Text Compression
  99. A Systems Thinking Approach to Algorithmic Fairness
  100. Deep Learning for Spatio-Temporal Fusion in Land Surface Temperature Estimation: A Comprehensive Survey, Experimental Analysis, and Future Trends
All 190
  1. Automated Bleeding Detection and Classification in Wireless Capsule Endoscopy with YOLOv8-X
  2. Topology-Aware 3D Gaussian Splatting: Leveraging Persistent Homology for Optimized Structural Integrity
  3. Distributed Inference on Mobile Edge and Cloud: A Data-Cartography based Clustering Approach
  4. Automated Classification of Cybercrime Complaints using Transformer-based Language Models for Hinglish Texts
  5. Concept Guided Co-salient Object Detection
  6. OmniSplat: Taming Feed-Forward 3D Gaussian Splatting for Omnidirectional Images with Editable Capabilities
  7. V"Mean"ba: Visual State Space Models only need 1 hidden dimension
  8. AIGCodeSet: A New Annotated Dataset for AI Generated Code Detection
  9. Leveraging Contrastive Learning for Semantic Segmentation with Consistent Labels Across Varying Appearances
  10. Kernel Methods for the Approximation of the Eigenfunctions of the Koopman Operator
  11. FedGA: Federated Learning with Gradient Alignment for Error Asymmetry Mitigation
  12. Effective and Efficient Representation Learning for Flight Trajectories
  13. A Meta-Learning Approach to Bayesian Causal Discovery
  14. Open-Vocabulary Mobile Manipulation Based on Double Relaxed Contrastive Learning with Dense Labeling
  15. Breaking the Context Bottleneck on Long Time Series Forecasting
  16. Learning for Cross-Layer Resource Allocation in MEC-Aided Cell-Free Networks
  17. Predictive Monitoring of Black-Box Dynamical Systems
  18. SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis
  19. A learning-based approach to stochastic optimal control under reach-avoid constraint
  20. Metagoals Endowing Self-Modifying AGI Systems with Goal Stability or Moderated Goal Evolution: Toward a Formally Sound and Practical Approach
  21. CognTKE: A Cognitive Temporal Knowledge Extrapolation Framework
  22. Acquisition of Recursive Possessives and Recursive Locatives in Mandarin
  23. High-Dimensional Bayesian Optimization via Random Projection of Manifold Subspaces
  24. Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers
  25. ActPC-Chem: Discrete Active Predictive Coding for Goal-Guided Algorithmic Chemistry as a Potential Cognitive Kernel for Hyperon & PRIMUS-Based AGI
  26. Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models
  27. Mathematics and Machine Creativity: A Survey on Bridging Mathematics with AI
  28. FairDD: Enhancing Fairness with domain-incremental learning in dermatological disease diagnosis
  29. Prior2Posterior: Model Prior Correction for Long-Tailed Learning
  30. Towards Environmentally Equitable AI
  31. DOFEN: Deep Oblivious Forest ENsemble
  32. From Creation to Curriculum: Examining the role of generative AI in Arts Universities
  33. Improving Lip-synchrony in Direct Audio-Visual Speech-to-Speech Translation
  34. Text2midi: Generating Symbolic Music from Captions
  35. LLaVA-SLT: Visual Language Tuning for Sign Language Translation
  36. Physics-Guided Fair Graph Sampling for Water Temperature Prediction in River Networks
  37. Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"
  38. Batch Selection for Multi-Label Classification Guided by Uncertainty and Dynamic Label Correlations
  39. Anchor Learning with Potential Cluster Constraints for Multi-view Clustering
  40. VSFormer: Value and Shape-Aware Transformer with Prior-Enhanced Self-Attention for Multivariate Time Series Classification
  41. Context-Aware Outlier Rejection for Robust Multi-View 3D Tracking of Similar Small Birds in An Outdoor Aviary
  42. Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding
  43. Unsupervised Domain Adaptive Person Search via Dual Self-Calibration
  44. First-frame Supervised Video Polyp Segmentation via Propagative and Semantic Dual-teacher Network
  45. Spatial-Temporal Knowledge Distillation for Takeaway Recommendation
  46. Autonomous Crack Detection using Deep Learning on Synthetic Thermogram Datasets
  47. Real-time Bangla Sign Language Translator
  48. Follow-Your-MultiPose: Tuning-Free Multi-Character Text-to-Video Generation via Pose Guidance
  49. Cross-View Consistency Regularisation for Knowledge Distillation
  50. ImagePiece: Content-aware Re-tokenization for Efficient Image Recognition
  51. Deep Reinforcement Learning Based Systems for Safety Critical Applications in Aerospace
  52. Evaluating the Performance of Large Language Models in Scientific Claim Detection and Classification
  53. Automated CVE Analysis: Harnessing Machine Learning In Designing Question-Answering Models For Cybersecurity Information Extraction
  54. MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights
  55. Learn2Mix: Training Neural Networks Using Adaptive Data Integration
  56. Flash3D: Super-scaling Point Transformers through Joint Hardware-Geometry Locality
  57. Enhancing Nighttime Vehicle Detection with Day-to-Night Style Transfer and Labeling-Free Augmentation
  58. Query Quantized Neural SLAM
  59. Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling
  60. "ScatSpotter" -- A Dog Poop Detection Dataset
  61. Chained Tuning Leads to Biased Forgetting
  62. Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functions
  63. Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition
  64. Condensed Stein Variational Gradient Descent for Uncertainty Quantification of Neural Networks
  65. Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoising
  66. Rethinking Model Redundancy for Low-light Image Enhancement
  67. Robust Random Graph Matching in Dense Graphs via an Approximate Message Passing Type Algorithm
  68. Research on Violent Text Detection System Based on BERT-fasttext Model
  69. FACTS: Fine-Grained Action Classification for Tactical Sports
  70. The Evolving Usage of GenAI by Computing Students
  71. Sharp Results for Hypothesis Testing with Risk-Sensitive Agents
  72. CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inference
  73. A Generalizable Anomaly Detection Method in Dynamic Graphs
  74. Sensitive Image Classification by Vision Transformers
  75. Mixed geometry information regularization for image multiplicative denoising
  76. Effective Context Modeling Framework for Emotion Recognition in Conversations
  77. Has LLM Reached the Scaling Ceiling Yet? Unified Insights into LLM Regularities and Constraints
  78. Iterative Feature Exclusion Ranking for Deep Tabular Learning
  79. Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
  80. THeGCN: Temporal Heterophilic Graph Convolutional Network
  81. Object Detection Approaches to Identifying Hand Images with High Forensic Values
  82. LearnLM: Improving Gemini for Learning
  83. Data-Driven Fairness Generalization for Deepfake Detection
  84. Patherea: Cell Detection and Classification for the 2020s
  85. Technical Report: Small Language Model for Japanese Clinical and Medicine
  86. Identifying Cyberbullying Roles in Social Media
  87. Transport Quasi-Monte Carlo
  88. Accelerated Methods with Compressed Communications for Distributed Optimization Problems under Data Similarity
  89. Knowledge as a Breaking of Ergodicity
  90. Uncertainty Quantification in Continual Open-World Learning