mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 9 Jan 2025

232 papers

  1. Contextual Bandit Optimization with Pre-Trained Neural NetworksLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  2. Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous WordsLLM reasoning → Reasoning benchmarks and evaluation +1
  3. Vision-Language Models for Autonomous Driving: CLIP-Based Dynamic Scene UnderstandingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  4. LLMQuoter: Enhancing RAG Capabilities Through Efficient Quote Extraction From Large ContextsRetrieval-augmented generation → RAG pipeline design and evaluation
  5. Strategy Masking: A Method for Guardrails in Value-based Reinforcement Learning AgentsLLM safety and security → Prompt injection and agent security +1
  6. ReFocus: Visual Editing as a Chain of Thought for Structured Image UnderstandingLLM reasoning → Multimodal reasoning +1
  7. Decentralized Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  8. Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning BenchmarkLLM reasoning → Multimodal reasoning +1
  9. Progressive Growing of Video Tokenizers for Temporally Compact Latent SpacesDiffusion models → Video generation
  10. Zero-1-to-G: Taming Pretrained 2D Diffusion Model for Direct 3D GenerationDiffusion models → 3D, point cloud and scene generation
  11. Adaptive Path-Planning for Autonomous Robots: A UCH-Enhanced Q-Learning ApproachDeep reinforcement learning methods → RL for robot navigation and UAV control
  12. Accelerated Diffusion Models via Speculative SamplingDiffusion models → Discrete and text diffusion +1
  13. Search-o1: Agentic Search-Enhanced Large Reasoning ModelsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  14. SC-Pro: Training-Free Framework for Defending Unsafe Image Synthesis AttackDiffusion models → Robustness, privacy and adversarial aspects
  15. Stream Aligner: Efficient Sentence-Level Alignment via Distribution InductionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  16. Knowledge Transfer in Model-Based Reinforcement Learning Agents for Efficient Multi-Task LearningWorld models → Latent dynamics models and model-based RL +1
  17. Optimizing Distributed Deployment of Mixture-of-Experts Model Inference in Serverless ComputingMixture-of-experts → Efficient MoE training and inference systems
  18. CallNavi, A Challenge and Empirical Study on LLM Function Calling and RoutingLLM agents and tool use → Tool learning and function calling
  19. RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language ModelsRetrieval-augmented generation → Privacy and security of RAG +1
  20. Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution DetectionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  21. Light Transport-aware Diffusion Posterior Sampling for Single-View Reconstruction of 3D VolumesDiffusion models → 3D, point cloud and scene generation
  22. Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  23. FaceMe: Robust Blind Face Restoration with Personal IdentificationDiffusion models → Inverse problems and image restoration
  24. Emergence of polarization in networks of large language model agentsLLM agents and tool use → Social simulation and multi-agent debate
  25. Biomedical Relation Extraction via Adaptive Document-Relation Cross-Mapping and Concept Unique IdentifierRetrieval-augmented generation → Medical and biomedical RAG
  26. Centurio: On Drivers of Multilingual Ability of Large Vision-Language ModelMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  27. EquiBoost: An Equivariant Boosting Approach to Molecular Conformation GenerationDiffusion models → Flow matching, time series and science
  28. ResPanDiff: Diffusion Model for Pansharpening by Inferring Residual InferenceDiffusion models → Inverse problems and image restoration
  29. DriVLM: Domain Adaptation of Vision-Language Models in Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  30. Commonsense Video Question Answering through Video-Grounded Entailment Tree ReasoningLLM reasoning → Multimodal reasoning
  31. D3RM: A Discrete Denoising Diffusion Refinement Model for Piano TranscriptionDiffusion models → Audio, speech and music
  32. LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  33. LearningFlow: Automated Policy Learning Workflow for Urban Driving with Large Language ModelsEnd-to-end autonomous driving → Reinforcement learning for driving
  34. ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition BenchmarkMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  35. A General Retrieval-Augmented Generation Framework for Multimodal Case-Based Reasoning ApplicationsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  36. TreeKV: Smooth Key-Value Cache Compression with Tree StructuresEfficient LLM inference and serving → KV cache optimization
  37. CuRLA: Curriculum Learning Based Deep Reinforcement Learning for Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving +1
  38. Open Problems in Machine Unlearning for AI SafetyLLM safety and security → Machine unlearning
  39. MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image ClassificationState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  40. Jailbreaking Multimodal Large Language Models via Shuffle InconsistencyMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  41. FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow MatchingDiffusion models → Audio, speech and music
  42. JELLY: Joint Emotion Recognition and Context Reasoning with LLMs for Conversational Speech SynthesisLLM reasoning → Audio-language model reasoning
  43. SUGAR: Leveraging Contextual Confidence for Smarter RetrievalRetrieval-augmented generation → RAG robustness and adaptive retrieval
  44. World of ScoreCraft: Novel Multi Scorer Experiment on the Impact of a Decision Support System in Sleep Staging
  45. Large language models streamline automated systematic review: A preliminary study
  46. Explore Activation Sparsity in Recurrent LLMs for Energy-Efficient Neuromorphic Computing
  47. Runtime Analysis of Evolutionary Algorithms for Multi-party Multi-objective Optimization
  48. Towards Dynamic Neural Communication and Speech Neuroprosthesis Based on Viseme Decoding
  49. A Multi-Layer CNN-GRUSKIP model based on transformer for spatial TEMPORAL traffic flow prediction
  50. OpenAI ChatGPT interprets Radiological Images: GPT-4 as a Medical Doctor for a Fast Check-Up
  51. Clustering with Uniformity- and Neighbor-Based Random Geometric Graphs
  52. AgoraSpeech: A multi-annotated comprehensive dataset of political discourse through the lens of humans and AI
  53. GelBelt: A Vision-based Tactile Sensor for Continuous Sensing of Large Surfaces
  54. Towards smart and adaptive agents for active sensing on edge devices
  55. CAMs as Shapley Value-based Explainers
  56. Quantum Down Sampling Filter for Variational Auto-encoder
  57. Unlocking In-Context Learning for Natural Datasets Beyond Language Modelling
  58. Progressive Supervision via Label Decomposition: An Long-Term and Large-Scale Wireless Traffic Forecasting Method
  59. The State of Post-Hoc Local XAI Techniques for Image Processing: Challenges and Motivations
  60. Transformer-Squared: Self-adaptive LLMs
  61. Watermarking Graph Neural Networks via Explanations for Ownership Protection
  62. Bit-depth color recovery via off-the-shelf super-resolution models
  63. Towards Probabilistic Inference of Human Motor Intentions by Assistive Mobile Robots Controlled via a Brain-Computer Interface
  64. Harmonizing Metadata of Language Resources for Enhanced Querying and Accessibility
  65. Advancing Personalized Learning Analysis via an Innovative Domain Knowledge Informed Attention-based Knowledge Tracing Method
  66. Exploring Large Language Models for Translating Romanian Computational Problems into English
  67. Session-Level Dynamic Ad Load Optimization using Offline Robust Reinforcement Learning
  68. Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations
  69. Learned Discrepancy Reconstruction and Benchmark Dataset for Magnetic Particle Imaging
  70. Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics
  71. Approximate Supervised Object Distance Estimation on Unmanned Surface Vehicles
  72. Analog Bayesian neural networks are insensitive to the shape of the weight distribution
  73. Prediction-Assisted Online Distributed Deep Learning Workload Scheduling in GPU Clusters
  74. Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives
  75. Improving Zero-Shot Object-Level Change Detection by Incorporating Visual Correspondence
  76. The dynamics of meaning through time: Assessment of Large Language Models
  77. Emergent weight morphologies in deep neural networks
  78. Customizable LLM-Powered Chatbot for Behavioral Science Research
  79. OmniJet-αC: Learning point cloud calorimeter simulations using generative transformers
  80. Outlyingness Scores with Cluster Catch Digraphs
  81. Neural Architecture Codesign for Fast Physics Applications
  82. OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?
  83. The more polypersonal the better -- a short look on space geometry of fine-tuned layers
  84. Shrink the longest: improving latent space isotropy with symplicial geometry
  85. Generalization of Urban Wind Environment Using Fourier Neural Operator Across Different Wind Directions and Cities
  86. Generative Flow Networks: Theory and Applications to Structure Learning
  87. Spatial Information Integration in Small Language Models for Document Layout Generation and Classification
  88. FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning
  89. LSEBMCL: A Latent Space Energy-Based Model for Continual Learning
  90. Soft Computing Approaches for Predicting Shade-Seeking Behaviour in Dairy Cattle under Heat Stress: A Comparative Study of Random Forests and Neural Networks
  91. Monotonic Learning in the PAC Framework: A New Perspective
  92. Interpretable deep learning illuminates multiple structures fluorescence imaging: a path toward trustworthy artificial intelligence in microscopy
  93. An Empirical Study of Autoregressive Pre-training from Videos
  94. Explainable AI-Enhanced Deep Learning for Pumpkin Leaf Disease Detection: A Comparative Analysis of CNN Architectures
  95. Relative Pose Estimation through Affine Corrections of Monocular Depth Priors
  96. Consistent Flow Distillation for Text-to-3D Generation
  97. A survey of textual cyber abuse detection using cutting-edge language models and large language models
  98. The GAN is dead; long live the GAN! A Modern GAN Baseline
  99. From Simple to Complex Skills: The Case of In-Hand Object Reorientation
  100. Scale-invariant brain morphometry: application to sulcal depth
All 232
  1. Neuro-Symbolic AI in 2024: A Systematic Review
  2. From Images to Insights: Transforming Brain Cancer Diagnosis with Explainable AI
  3. Entangled Mean Estimation in High-Dimensions
  4. Using LLMs to Infer Non-Binary COVID-19 Sentiments of Chinese Micro-bloggers
  5. Uncertainty-aware Knowledge Tracing
  6. LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation
  7. Seeing Sound: Assembling Sounds from Visuals for Audio-to-Image Generation
  8. Atlas: A Novel Pathology Foundation Model by Mayo Clinic, Charit'e, and Aignostics
  9. Tempo: Compiled Dynamic Deep Learning with Symbolic Dependence Graphs
  10. On-line Policy Improvement using Monte-Carlo Search
  11. TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts
  12. BRATI: Bidirectional Recurrent Attention for Time-Series Imputation
  13. Performance of YOLOv7 in Kitchen Safety While Handling Knife
  14. Mechanistic understanding and validation of large AI models with SemanticLens
  15. FairCoder: Probing LLM Bias in High-Stakes Decision Making via Coding Tasks
  16. The global consensus on the risk management of autonomous driving
  17. Integrating Explainable AI for Effective Malware Detection in Encrypted Network Traffic
  18. Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models
  19. Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance
  20. 1-2-1: Renaissance of Single-Network Paradigm for Virtual Try-On
  21. Developing a Foundation of Vector Symbolic Architectures Using Category Theory
  22. No-Regret Linear Bandits under Gap-Adjusted Misspecification
  23. On Corrigibility and Alignment in Multi Agent Games
  24. JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration
  25. The Bakers and Millers Game with Restricted Locations
  26. Stability and List-Replicability for Agnostic Learners
  27. AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder
  28. The explanation dialogues: an expert focus study to understand requirements towards explanations within the GDPR
  29. Distributed Learning and Inference Systems: A Networking Perspective
  30. Private Selection with Heterogeneous Sensitivities
  31. Comparison Study: Glacier Calving Front Delineation in Synthetic Aperture Radar Images With Deep Learning
  32. Learning convolution operators on compact Abelian groups
  33. Off-Policy Evaluation and Counterfactual Methods in Dynamic Auction Environments
  34. Solving the Catastrophic Forgetting Problem in Generalized Category Discovery
  35. CellViT++: Energy-Efficient and Adaptive Cell Segmentation and Classification Using Foundation Models
  36. Patch-GAN Transfer Learning with Reconstructive Models for Cloud Removal
  37. Towards Balanced Multi-Modal Learning in 3D Human Pose Estimation
  38. Enhancing Plagiarism Detection in Marathi with a Weighted Ensemble of TF-IDF and BERT Embeddings for Low-Resource Language Processing
  39. Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues
  40. From Scientific Texts to Verifiable Code: Automating the Process with Transformers
  41. Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning
  42. Online Prompt Selection for Program Synthesis
  43. Domain-Incremental Semantic Segmentation for Autonomous Driving under Adverse Driving Conditions
  44. Optimized Sampling for Non-Line-of-Sight Imaging Using Modified Fast Fourier Transforms
  45. SEGS-SLAM: Structure-enhanced 3D Gaussian Splatting SLAM with Appearance Embedding
  46. Contrast-Free Myocardial Scar Segmentation in Cine MRI using Motion and Texture Fusion
  47. Is Your Autonomous Vehicle Safe? Understanding the Threat of Electromagnetic Signal Injection Attacks on Traffic Scene Perception
  48. FOCUS: Towards Universal Foreground Segmentation
  49. Automated external cervical resorption segmentation in cone-beam CT using local texture features
  50. Optimizing Estonian TV Subtitles with Semi-supervised Learning and LLMs
  51. Leveraging Large Language Models for Zero-shot Lay Summarisation in Biomedicine and Beyond
  52. EVA-S2PLoR: Decentralized Secure 2-party Logistic Regression with A Subtly Hadamard Product Protocol (Full Version)
  53. ParaRev: Building a dataset for Scientific Paragraph Revision annotated with revision instruction
  54. A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education
  55. GLaM-Sign: Greek Language Multimodal Lip Reading with Integrated Sign Language Accessibility
  56. MHAFF: Multi-Head Attention Feature Fusion of CNN and Transformer for Cattle Identification
  57. CoDe: Communication Delay-Tolerant Multi-Agent Collaboration via Dual Alignment of Intent and Timeliness
  58. Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning
  59. Design and Control of a Bipedal Robotic Character
  60. An Algorithmic Approach for Causal Health Equity: A Look at Race Differentials in Intensive Care Unit (ICU) Outcomes
  61. HipyrNet: Hypernet-Guided Feature Pyramid network for mixed-exposure correction
  62. RMTransformer: Accurate Radio Map Construction and Coverage Prediction
  63. De-centering the (Traditional) User: Multistakeholder Evaluation of Recommender Systems
  64. Bringing Order Amidst Chaos: On the Role of Artificial Intelligence in Secure Software Engineering
  65. Explainable AI based System for Supply Air Temperature Forecast
  66. A Systematic Literature Review on Deep Learning-based Depth Estimation in Computer Vision
  67. CorrDiff: Adaptive Delay-aware Detector with Temporal Cue Inputs for Real-time Object Detection
  68. 3DIS-FLUX: simple and efficient multi-instance generation with DiT rendering
  69. Contrastive Representation Modeling for Anomaly Detection
  70. Improving the U-Net Configuration for Automated Delineation of Head and Neck Cancer on MRI
  71. Constrained Optimization of Charged Particle Tracking with Multi-Agent Reinforcement Learning
  72. Optimizing Multitask Industrial Processes with Predictive Action Guidance
  73. Robust Score Matching
  74. Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset
  75. A 1Mb mixed-precision quantized encoder for image classification and patch-based compression
  76. Advancing ALS Applications with Large-Scale Pre-training: Dataset Development and Downstream Assessment
  77. Hierarchical Decomposed Dual-domain Deep Learning for Sparse-View CT Reconstruction
  78. Supervised Learning with Evolving Tasks and Performance Guarantees
  79. Enhanced Quantile Regression with Spiking Neural Networks for Long-Term System Health Prognostics
  80. End-to-End Deep Learning for Interior Tomography with Low-Dose X-ray CT
  81. Comparison of Feature Learning Methods for Metadata Extraction from PDF Scholarly Documents
  82. Multimodal-to-Text Prompt Engineering in Large Language Models Using Feature Embeddings for GNSS Interference Characterization
  83. Analyzing Memorization in Large Language Models through the Lens of Model Attribution
  84. TipSegNet: Fingertip Segmentation in Contactless Fingerprint Imaging
  85. A Text-Based Knowledge-Embedded Soft Sensing Modeling Approach for General Industrial Process Tasks Based on Large Language Model
  86. A Flexible and Scalable Framework for Video Moment Search
  87. Improving Skeleton-based Action Recognition with Interactive Object Information
  88. Simultaneous emulation and downscaling with physically-consistent deep learning-based regional ocean emulators
  89. TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learning
  90. SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution
  91. LongViTU: Instruction Tuning for Long-Form Video Understanding
  92. Towards Fingerprint Mosaicking Artifact Detection: A Self-Supervised Deep Learning Approach
  93. Enhancing Human-Like Responses in Large Language Models
  94. Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representation
  95. Finding Needles in Emb(a)dding Haystacks: Legal Document Retrieval via Bagging and SVR Ensembles
  96. Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning
  97. On Measuring Unnoticeability of Graph Adversarial Attacks: Observations, New Measure, and Applications
  98. UAV-VLA: Vision-Language-Action System for Large Scale Aerial Mission Generation
  99. A Scalable System for Visual Analysis of Ocean Data
  100. Quantum-enhanced causal discovery for a small number of samples
  101. A High-accuracy Calibration Method of Transient TSEPs for Power Semiconductor Devices
  102. Load Forecasting for Households and Energy Communities: Are Deep Learning Models Worth the Effort?
  103. GiNet: Integrating Sequential and Context-Aware Learning for Battery Capacity Prediction
  104. A CT Image Classification Network Framework for Lung Tumors Based on Pre-trained MobileNetV2 Model and Transfer learning, And Its Application and Market Analysis in the Medical field
  105. IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression Segmentation
  106. V2C-CBM: Building Concept Bottlenecks with Vision-to-Concept Tokenizer
  107. SensorQA: A Question Answering Benchmark for Daily-Life Monitoring
  108. Self-Adaptive Ising Machines for Constrained Optimization
  109. Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation
  110. Self-Supervised Representation Learning with Joint Embedding Predictive Architecture for Automotive LiDAR Object Detection
  111. Targeted Adversarial Denoising Autoencoders (TADA) for Neural Time Series Filtration
  112. Emergence of Painting Ability via Recognition-Driven Evolution
  113. VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models
  114. Demystifying Domain-adaptive Post-training for Financial LLMs
  115. Addressing Domain Shift via Imbalance-Aware Domain Adaptation in Embryo Development Assessment
  116. MORDA: A Synthetic Dataset to Facilitate Adaptation of Object Detectors to Unseen Real-target Domain While Preserving Performance on Real-source Domain
  117. Seeing with Partial Certainty: Conformal Prediction for Robotic Scene Recognition in Built Environments
  118. Non-asymptotic analysis of the performance of the penalized least trimmed squares in sparse models
  119. Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models
  120. A New Perspective on Privacy Protection in Federated Learning with Granular-Ball Computing
  121. Multi-Context Temporal Consistent Modeling for Referring Video Object Segmentation
  122. Plug-and-Play DISep: Separating Dense Instances for Scene-to-Pixel Weakly-Supervised Change Detection in High-Resolution Remote Sensing Images
  123. Image2CADSeq: Computer-Aided Design Sequence and Knowledge Inference from Product Images
  124. Investigating Numerical Translation with Large Language Models
  125. SpecTf: Transformers Enable Data-Driven Imaging Spectroscopy Cloud Detection
  126. From Mesh Completion to AI Designed Crown
  127. A Machine Learning Model for Crowd Density Classification in Hajj Video Frames
  128. Analyzing decision tree bias towards the minority class
  129. Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression
  130. Online Continual Learning: A Systematic Literature Review of Approaches, Challenges, and Benchmarks
  131. Quantifying Itch and its Impact on Sleep Using Machine Learning and Radio Signals
  132. A Look into How Machine Learning is Reshaping Engineering Models: the Rise of Analysis Paralysis, Optimal yet Infeasible Solutions, and the Inevitable Rashomon Paradox