mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 15 Dec 2024

165 papers

  1. Active Large Language Model-based Knowledge Distillation for Session-based RecommendationKnowledge distillation → Distillation for recommender systems
  2. Data Laundering: Artificially Boosting Benchmark Results through Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
  3. IPS: In-Prompt Process Supervision for Short Video Content ModerationMultimodal LLMs / vision-language models → Video understanding with MLLMs
  4. Segment-Level Diffusion: A Framework for Controllable Long-Form Generation with Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  5. A Comparative Study on Dynamic Graph Embedding based on Mamba and TransformersState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  6. Are Expressive Models Truly Necessary for Offline RL?Offline RL and imitation learning from data → Offline RL algorithms
  7. Wasserstein Bounds for generative diffusion models with Gaussian tail targetsDiffusion models → Diffusion foundations and sampling
  8. TrimLLM: Progressive Layer Dropping for Domain-Specific LLMsEfficient LLM inference and serving → Serving systems and request scheduling
  9. GenLit: Reformulating Single-Image Relighting as Video GenerationDiffusion models → 3D, point cloud and scene generation
  10. GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition ControlWorld models → Embodied and robot world models
  11. Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of RefusalMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  12. OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene GenerationDiffusion models → 3D, point cloud and scene generation
  13. Cultural Palette: Pluralising Culture Alignment via Multi-agent PaletteLLM agents and tool use → Social simulation and multi-agent debate
  14. Partial Identifiability in Inverse Reinforcement Learning For Agents With Non-Exponential DiscountingOffline RL and imitation learning from data → Inverse reinforcement learning +1
  15. Dual-Schedule Inversion: Training- and Tuning-Free Inversion for Real Image EditingDiffusion models → Image generation, text-to-image and editing
  16. Redefining Normal: A Novel Object-Level Approach for Multi-Object Novelty DetectionKnowledge distillation → Detection and dense prediction distillation
  17. The Superalignment of Superhuman Intelligence with Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  18. Safe Reinforcement Learning using Finite-Horizon Gradient-based EstimationDeep reinforcement learning methods → Safe and constrained RL
  19. Combating Multimodal LLM Hallucination via Bottom-Up Holistic ReasoningLLM reasoning → Hallucination detection and mitigation +1
  20. DynamicScaler: Seamless and Scalable Video Generation for Panoramic ScenesDiffusion models → 3D, point cloud and scene generation
  21. Seeing the Forest and the Trees: Solving Visual Graph and Tree Based Data Structure Problems using Large Multimodal ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  22. Leveraging Large Vision-Language Model as User Intent-aware Encoder for Composed Image RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  23. BarcodeMamba: State Space Models for Biodiversity AnalysisState-space sequence models (S4, Mamba) → Core SSM architectures for language
  24. EquiFlow: Equivariant Conditional Flow Matching with Optimal Transport for 3D Molecular Conformation PredictionDiffusion models → Flow matching, time series and science
  25. Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image RetrievalLLM reasoning → Multimodal reasoning
  26. LAW: Legal Agentic Workflows for Custody and Fund Services ContractsLLM agents and tool use → Social simulation and multi-agent debate
  27. SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  28. RAC3: Retrieval-Augmented Corner Case Comprehension for Autonomous Driving with Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +2
  29. Understanding and Mitigating Memorization in Diffusion Models for Tabular DataDiffusion models → Flow matching, time series and science
  30. Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  31. SceneLLM: Implicit Language Reasoning in LLM for Dynamic Scene Graph GenerationLLM reasoning → Spatial and embodied reasoning
  32. Exploring Diffusion and Flow Matching Under Generator MatchingDiffusion models → Flow matching, time series and science
  33. Exploring Enhanced Contextual Information for Video-Level Object TrackingState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  34. On Distilling the Displacement Knowledge for Few-Shot Class-Incremental LearningKnowledge distillation → Distillation for continual learning
  35. CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog GenerationLLM agents and tool use → Software engineering coding agents
  36. Dual Traits in Probabilistic Reasoning of Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  37. Entropy-Regularized Process Reward ModelLLM reasoning → Reinforcement learning for reasoning +1
  38. Decoding OTC Government Bond Market Liquidity: An ABM Model for Market Dynamics
  39. FSTA-SNN:Frequency-based Spatial-Temporal Attention Module for Spiking Neural Networks
  40. Predicting Crack Nucleation and Propagation in Brittle Materials Using Deep Operator Networks with Diverse Trunk Architectures
  41. Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models
  42. GaLore+: Boosting Low-Rank Adaptation for LLMs with Cross-Head Projection
  43. ChipAlign: Instruction Alignment in Large Language Models for Chip Design via Geodesic Interpolation
  44. EEG-GMACN: Interpretable EEG Graph Mutual Attention Convolutional Network
  45. RIRO: Reshaping Inputs, Refining Outputs Unlocking the Potential of Large Language Models in Data-Scarce Contexts
  46. Using Machine Learning to Distinguish Human-written from Machine-generated Creative Fiction
  47. NER- RoBERTa: Fine-Tuning RoBERTa for Named Entity Recognition (NER) within low-resource languages
  48. An Enhanced Text Compression Approach Using Transformer-based Language Models
  49. LitLLMs, LLMs for Literature Review: Are we there yet?
  50. Imagined Speech State Classification for Robust Brain-Computer Interface
  51. DLSOM: A Deep learning-based strategy for liver cancer subtyping
  52. Finance-Informed Neural Network: Learning the Geometry of Option Pricing
  53. Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization
  54. AI-Driven Innovations in Volumetric Video Streaming: A Review
  55. Provably Secure Robust Image Steganography via Cross-Modal Error Correction
  56. SEE: Sememe Entanglement Encoding for Transformer-bases Models Compression
  57. A multi-theoretical kernel-based approach to social network-based recommendation
  58. Embracing Large Language Models in Traffic Flow Forecasting
  59. One-Shot Multilingual Font Generation Via ViT
  60. Coupling-based Convergence Diagnostic and Stepsize Scheme for Stochastic Gradient Descent
  61. Modality-Driven Design for Multi-Step Dexterous Manipulation: Insights from Neuroscience
  62. Sonicmesh: Enhancing 3D Human Mesh Reconstruction in Vision-Impaired Environments With Acoustic Signals
  63. Generics are puzzling. Can language models find the missing piece?
  64. RoLargeSum: A Large Dialect-Aware Romanian News Dataset for Summary, Headline, and Keyword Generation
  65. Reliable, Reproducible, and Really Fast Leaderboards with Evalica
  66. From XAI to MLOps: Explainable Concept Drift Detection with Profile Drift Detection
  67. Unimodal and Multimodal Static Facial Expression Recognition for Virtual Reality Users with EmoHeVRDB
  68. An Empirical Study of Fault Localisation Techniques for Deep Learning
  69. Regularized Dikin Walks for Sampling Truncated Logconcave Measures, Mixed Isoperimetry and Beyond Worst-Case Analysis
  70. Sequence-Level Leakage Risk of Training Data in Large Language Models
  71. Semi-Implicit Neural Ordinary Differential Equations
  72. How not to Stitch Representations to Measure Similarity: Task Loss Matching versus Direct Matching
  73. Grassmannian Geometry Meets Dynamic Mode Decomposition in DMD-GEN: A New Metric for Mode Collapse in Time Series Generative Models
  74. Detecting Daily Living Gait Amid Huntington's Disease Chorea using a Foundation Deep Learning Model
  75. Learning Normal Flow Directly From Event Neighborhoods
  76. VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping
  77. Macro2Micro: A Rapid and Precise Cross-modal Magnetic Resonance Imaging Synthesis using Multi-scale Structural Brain Similarity
  78. Wearable Accelerometer Foundation Models for Health via Knowledge Distillation
  79. Bayesian inference of mean velocity fields and turbulence models from flow MRI
  80. CATER: Leveraging LLM to Pioneer a Multidimensional, Reference-Independent Paradigm in Translation Quality Evaluation
  81. GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs
  82. Prediction-Enhanced Monte Carlo: A Machine Learning View on Control Variate
  83. Do Tutors Learn from Equity Training and Can Generative AI Assess It?
  84. Beyond Discrete Personas: Personality Modeling Through Journal Intensive Conversations
  85. Multimodal Class-aware Semantic Enhancement Network for Audio-Visual Video Parsing
  86. Transformer-Based Bearing Fault Detection using Temporal Decomposition Attention Mechanism
  87. Volumetric Mapping with Panoptic Refinement via Kernel Density Estimation for Mobile Robots
  88. Learning Set Functions with Implicit Differentiation
  89. On the Generalizability of Iterative Patch Selection for Memory-Efficient High-Resolution Image Classification
  90. Smaller Language Models Are Better Instruction Evolvers
  91. Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition
  92. Distribution-Consistency-Guided Multi-modal Hashing
  93. Neural Port-Hamiltonian Differential Algebraic Equations for Compositional Learning of Electrical Networks
  94. Image Forgery Localization with State Space Models
  95. Deep Learning-based Approaches for State Space Models: A Selective Review
  96. ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction
  97. ProFe: Communication-Efficient Decentralized Federated Learning via Distillation and Prototypes
  98. Concept Learning in the Wild: Towards Algorithmic Understanding of Neural Networks
  99. Task-Oriented Dialog Systems for the Senegalese Wolof Language
  100. Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points
All 165
  1. Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation
  2. From Votes to Volatility Predicting the Stock Market on Election Day
  3. Leveraging Large Language Models for Active Merchant Non-player Characters
  4. Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models
  5. Efficient Quantization-Aware Training on Segment Anything Model in Medical Images and Its Deployment
  6. Transliterated Zero-Shot Domain Adaptation for Automatic Speech Recognition
  7. TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation
  8. A Progressive Transformer for Unifying Binary Code Embedding and Knowledge Transfer
  9. Knowledge Migration Framework for Smart Contract Vulnerability Detection
  10. Semi-Supervised Risk Control via Prediction-Powered Inference
  11. Unpacking the Resilience of SNLI Contradiction Examples to Attacks
  12. Learning Latent Spaces for Domain Generalization in Time Series Forecasting
  13. Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generation
  14. PGD-Imp: Rethinking and Unleashing Potential of Classic PGD with Dual Strategies for Imperceptible Adversarial Attacks
  15. OTLRM: Orthogonal Learning-based Low-Rank Metric for Multi-Dimensional Inverse Problems
  16. Missing data imputation for noisy time-series data and applications in healthcare
  17. Why and How: Knowledge-Guided Learning for Cross-Spectral Image Patch Matching
  18. Early Concept Drift Detection via Prediction Uncertainty
  19. From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision
  20. A Comprehensive Survey of Action Quality Assessment: Method and Benchmark
  21. AD-LLM: Benchmarking Large Language Models for Anomaly Detection
  22. ViSymRe: Vision Multimodal Symbolic Regression
  23. Decoding Drug Discovery: Exploring A-to-Z In silico Methods for Beginners
  24. Minimax Regret Estimation for Generalizing Heterogeneous Treatment Effects with Multisite Data
  25. Modeling the Heterogeneous Duration of User Interest in Time-Dependent Recommendation: A Hidden Semi-Markov Approach
  26. Feature engineering vs. deep learning for paper section identification: Toward applications in Chinese medical literature
  27. Hierarchical Bidirectional Transition Dispersion Entropy-based Lempel-Ziv Complexity and Its Application in Fault-Bearing Diagnosis
  28. Paid with Models: Optimal Contract Design for Collaborative Machine Learning
  29. Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning
  30. Impact of Adversarial Attacks on Deep Learning Model Explainability
  31. Plug-and-Play Priors as a Score-Based Method
  32. Unpaired Multi-Domain Histopathology Virtual Staining using Dual Path Prompted Inversion
  33. Multi-Graph Co-Training for Capturing User Intent in Session-based Recommendation
  34. ABC3: Active Bayesian Causal Inference with Cohn Criteria in Randomized Experiments
  35. Empowering LLMs to Understand and Generate Complex Vector Graphics
  36. Dynamic Graph Attention Networks for Travel Time Distribution Prediction in Urban Arterial Roads
  37. Hanprome: Modified Hangeul for Expression of foreign language pronunciation
  38. GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Experts
  39. Deep Spectral Clustering via Joint Spectral Embedding and Kmeans
  40. MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation
  41. Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Model
  42. Adapter-Enhanced Semantic Prompting for Continual Learning
  43. Navigating Towards Fairness with Data Selection
  44. HC-LLM: Historical-Constrained Large Language Models for Radiology Report Generation
  45. RecSys Arena: Pair-wise Recommender System Evaluation with Large Language Models
  46. CFSynthesis: Controllable and Free-view 3D Human Video Synthesis
  47. Learning Robust and Privacy-Preserving Representations via Information Theory
  48. Representation learning of dynamic networks
  49. Classification Drives Geographic Bias in Street Scene Segmentation
  50. DPA: A one-stop metric to measure bias amplification in classification datasets
  51. Set-Valued Sensitivity Analysis of Deep Neural Networks
  52. Overview of TREC 2024 Medical Video Question Answering (MedVidQA) Track
  53. NITRO: LLM Inference on Intel Laptop NPUs
  54. DisCo-DSO: Coupling Discrete and Continuous Optimization for Efficient Generative Design in Hybrid Spaces
  55. Deployment Pipeline from Rockpool to Xylo for Edge Computing
  56. Facial Surgery Preview Based on the Orthognathic Treatment Prediction
  57. AirMorph: Topology-Preserving Deep Learning for Pulmonary Airway Analysis
  58. SAM-IF: Leveraging SAM for Incremental Few-Shot Instance Segmentation
  59. AURORA: Automated Unleash of 3D Room Outlines for VR Applications
  60. From Simple to Professional: A Combinatorial Controllable Image Captioning Agent
  61. A Contextualized BERT model for Knowledge Graph Completion
  62. FBSJNN: A Theoretically Interpretable and Efficiently Deep Learning method for Solving Partial Integro-Differential Equations
  63. Towards Context-aware Convolutional Network for Image Restoration
  64. FlashSparse: Minimizing Computation Redundancy for Fast Sparse Matrix Multiplications on Tensor Cores
  65. Optimal Rates for Robust Stochastic Convex Optimization