mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 27 Dec 2024

170 papers

  1. Long Context vs. RAG for LLMs: An Evaluation and RevisitsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  2. Numerical solutions of fixed points in two-dimensional Kuramoto-Sivashinsky equation expedited by reinforcement learningDeep reinforcement learning methods → RL theory and sample complexity
  3. Motion Planning Diffusion: Learning and Adapting Robot Motion Planning with Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  4. Zero-shot Hazard Identification in Autonomous Driving: A Case Study on the COOOL BenchmarkEnd-to-end autonomous driving → VLMs for autonomous driving
  5. HADES: Hardware Accelerated Decoding for Efficient Speculation in Large Language ModelsEfficient LLM inference and serving → Speculative decoding
  6. Image Classification with Deep Reinforcement Active LearningDeep reinforcement learning methods → RL theory and sample complexity
  7. Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable ScalesDiffusion models → Diffusion foundations and sampling
  8. MVTamperBench: Evaluating Robustness of Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  9. InfAlign: Inference-aware language model alignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  10. Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent IntegrationLLM agents and tool use → Software engineering coding agents
  11. Adaptive Context-Aware Multi-Path Transmission Control for VR/AR Content: A Deep Reinforcement Learning ApproachDeep reinforcement learning methods → RL for energy, networks and operations
  12. OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task SynthesisLLM agents and tool use → GUI and mobile agents
  13. Toward Adaptive Reasoning in Large Language Models with Thought RollbackLLM reasoning → Prompting and chain-of-thought reasoning
  14. Boosting Private Domain Understanding of Efficient MLLMs: A Tuning-free, Adaptive, Universal Prompt Optimization FrameworkMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  15. CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMsLLM reasoning → Spatial and embodied reasoning +1
  16. VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion ModelsDiffusion models → Video generation
  17. Xmodel-2 Technical ReportLLM reasoning → Reasoning benchmarks and evaluation
  18. ReNeg: Learning Negative Embedding with Reward GuidanceLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  19. Let Watermarks Speak: A Robust and Unforgeable Watermark for Language ModelsLLM safety and security → Watermarking generated content and models
  20. Goal-oriented Communications based on Recursive Early Exit Neural NetworksEfficient LLM inference and serving → Early exit and edge inference
  21. A Comparative Study of Machine Unlearning Techniques for Image and Text Classification ModelsLLM safety and security → Machine unlearning
  22. Graph-attention-based Casual Discovery with Trust Region-navigated Clipping Policy OptimizationDeep reinforcement learning methods → Deep RL algorithms and representations
  23. TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured DataSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  24. Scalable Hierarchical Reinforcement Learning for Hyper Scale Multi-Robot Task PlanningDeep reinforcement learning methods → Deep RL algorithms and representations
  25. Is Your Text-to-Image Model Robust to Caption Noise?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  26. Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMsLLM reasoning → Test-time compute and efficient thinking
  27. MBQ: Modality-Balanced Quantization for Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  28. DrivingWorld: Constructing World Model for Autonomous Driving via Video GPTWorld models → World models for autonomous driving +1
  29. RobotDiffuse: Diffusion-Based Motion Planning for Redundant Manipulators with the ROP Obstacle Avoidance DatasetDiffusion models → Diffusion and flow policies for robotics
  30. Multi-PA: A Multi-perspective Benchmark on Privacy Assessment for Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  31. Retrieval-augmented Generation for GenAI-enabled Semantic CommunicationsRetrieval-augmented generation → RAG pipeline design and evaluation
  32. RAIN: Real-time Animation of Infinite Video StreamDiffusion models → Video generation
  33. Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language ModelsKnowledge distillation → Knowledge distillation for LLMs
  34. A Survey on Large Language Model Acceleration based on KV Cache ManagementLLM reasoning → Test-time compute and efficient thinking +1
  35. DeepSeek-V3 Technical ReportLLM reasoning → Reasoning benchmarks and evaluation +1
  36. Low-Rank Contextual Reinforcement Learning from Heterogeneous Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  37. Multi-scale Latent Point Consistency Models for 3D Shape GenerationDiffusion models → 3D, point cloud and scene generation
  38. MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic ScenariosMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  39. Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-WolfeLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  40. A Novel Method for Pignistic Information Fusion in the View of Z-number
  41. Evaluation of data driven low-rank matrix factorization for accelerated solutions of the Vlasov equation
  42. Approximation Rates in Fr'echet Metrics: Barron Spaces, Paley-Wiener Spaces, and Fourier Multipliers
  43. Seq2Seq Model-Based Chatbot with LSTM and Attention Mechanism for Enhanced User Interaction
  44. Stroke Prediction using Clinical and Social Features in Machine Learning
  45. Improving Low-Resource Machine Translation via Cross-Linguistic Transfer from Typologically Similar High-Resource Languages
  46. ErgoChat: a Visual Query System for the Ergonomic Risk Assessment of Construction Workers
  47. Data-driven tool wear prediction in milling, based on a process-integrated single-sensor approach
  48. Standard-Deviation-Inspired Regularization for Improving Adversarial Robustness
  49. Towards Strong AI: Transformational Beliefs and Scientific Creativity
  50. Hidformer: Transformer-Style Neural Network in Stock Price Forecasting
  51. Pivoting B2B platform business models: From platform experimentation to multi-platform integration to ecosystem envelopment
  52. Assessing Text Classification Methods for Cyberbullying Detection on Social Media Platforms
  53. Modeling Continuous Spatial-temporal Dynamics of Turbulent Flow with Test-time Refinement
  54. Right vs. Right: Can LLMs Make Tough Choices?
  55. Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models
  56. Char-SAM: Turning Segment Anything Model into Scene Text Segmentation Annotator with Character-level Visual Prompts
  57. On the Convergence of DP-SGD with Adaptive Clipping
  58. Identifying Cocoa Pollinators: A Deep Learning Dataset
  59. Leveraging Scene Geometry and Depth Information for Robust Image Deraining
  60. Mouth Articulation-Based Anchoring for Improved Cross-Corpus Speech Emotion Recognition
  61. Evaluate Summarization in Fine-Granularity: Auto Evaluation with LLM
  62. Surrogate Modeling for Explainable Predictive Time Series Corrections
  63. A Neural Network-Based Search for Unmodeled Transients in LIGO-Virgo-KAGRA's Third Observing Run
  64. YOLO-MST: Multiscale deep learning method for infrared small target detection based on super-resolution and YOLO
  65. Minimax-Optimal Multi-Agent Robust Reinforcement Learning
  66. Neighbor Does Matter: Density-Aware Contrastive Learning for Medical Semi-supervised Segmentation
  67. A Fully Hardware Implemented Accelerator Design in ReRAM Analog Computing without ADCs
  68. A new approach to locally adaptive polynomial regression
  69. Generalized Grade-of-Membership Estimation for High-dimensional Locally Dependent Data
  70. Enhancing Whisper's Accuracy and Speed for Indian Languages through Prompt-Tuning and Tokenization
  71. Can AI Help with Your Personal Finances?
  72. Machine Learning for Sentiment Analysis of Imported Food in Trinidad and Tobago
  73. Tensor Network Estimation of Distribution Algorithms
  74. Symbolic Approximations to Ricci-flat Metrics Via Extrinsic Symmetries of Calabi-Yau Hypersurfaces
  75. Improved image display by identifying the RGB family color space
  76. Analysis of Premature Death Rates in Texas Counties: The Impact of Air Quality, Socioeconomic Factors, and COPD Prevalence
  77. From Ceilings to Walls: Universal Dynamic Perching of Small Aerial Robots on Surfaces with Variable Orientations
  78. Generative Video Propagation
  79. Enhancing Cognitive Diagnosis by Modeling Learner Cognitive Structure State
  80. Can MLLMs generate human-like feedback in grading multimodal short answers?
  81. Complement or substitute? How AI increases the demand for human skills
  82. IMAGINE: An 8-to-1b 22nm FD-SOI Compute-In-Memory CNN Accelerator With an End-to-End Analog Charge-Based 0.15-8POPS/W Macro Featuring Distribution-Aware Data Reshaping
  83. Enhancing Adversarial Robustness of Deep Neural Networks Through Supervised Contrastive Learning
  84. Generative Pretrained Embedding and Hierarchical Irregular Time Series Representation for Daily Living Activity Recognition
  85. Learning to Forget: Bayesian Time Series Forecasting using Recurrent Sparse Spectrum Signature Gaussian Processes
  86. Position: Theory of Mind Benchmarks are Broken for Large Language Models
  87. EEG-Reptile: An Automatized Reptile-Based Meta-Learning Library for BCIs
  88. Sharpening Neural Implicit Functions with Frequency Consolidation Priors
  89. Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture
  90. ProKAN: Progressive Stacking of Kolmogorov-Arnold Networks for Efficient Liver Segmentation
  91. From Elements to Design: A Layered Approach for Automatic Graphic Design Composition
  92. Causal machine learning for heterogeneous treatment effects in the presence of missing outcome data
  93. An Integrated Optimization and Deep Learning Pipeline for Predicting Live Birth Success in IVF Using Feature Optimization and Transformer-Based Models
  94. A Review on the Integration of Artificial Intelligence and Medical Imaging in IVF Ovarian Stimulation
  95. Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline
  96. Combining Machine Learning with Recurrence Analysis for resonance detection
  97. A Hybrid Technique for Plant Disease Identification and Localisation in Real-time
  98. Deep ReLU networks -- injectivity capacity upper bounds
  99. Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimation
  100. DLScanner: A parameter space scanner package assisted by deep learning methods
All 170
  1. Toward Scalable Multirobot Control: Fast Policy Learning in Distributed MPC
  2. Asymmetrical Reciprocity-based Federated Learning for Resolving Disparities in Medical Diagnosis
  3. Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP
  4. Enhancing Vision-Language Tracking by Effectively Converting Textual Cues into Visual Cues
  5. Chimera: A Block-Based Neural Architecture Search Framework for Event-Based Object Detection
  6. Deep Continuous-Time State-Space Models for Marked Event Sequences
  7. RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations
  8. Gradient Weight-normalized Low-rank Projection for Efficient LLM Training
  9. Machine Generated Product Advertisements: Benchmarking LLMs Against Human Performance
  10. Bidding Games on Markov Decision Processes with Quantitative Reachability Objectives
  11. Enhancing Fine-grained Image Classification through Attentive Batch Training
  12. SocRATES: Towards Automated Scenario-based Testing of Social Navigation Algorithms
  13. ViDTA: Enhanced Drug-Target Affinity Prediction via Virtual Graph Nodes and Attention-based Feature Fusion
  14. Ultralight Signal Classification Model for Automatic Modulation Recognition
  15. DAS3R: Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction
  16. Reinforced Label Denoising for Weakly-Supervised Audio-Visual Video Parsing
  17. Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following
  18. Structural Similarity in Deep Features: Image Quality Assessment Robust to Geometrically Disparate Reference
  19. Learning states enhanced knowledge tracing: Simulating the diversity in real-world learning process
  20. Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multi-Task Learning Perspective
  21. Diverse Rare Sample Generation with Pretrained GANs
  22. Interacted Object Grounding in Spatio-Temporal Human-Object Interactions
  23. Finger in Camera Speaks Everything: Unconstrained Air-Writing for Real-World
  24. StyleRWKV: High-Quality and High-Efficiency Style Transfer with RWKV-like Architecture
  25. P3S-Diffusion:A Selective Subject-driven Generation Framework via Point Supervision
  26. The Value of AI Advice: Personalized and Value-Maximizing AI Advisors Are Necessary to Reliably Benefit Experts and Organizations
  27. Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping
  28. PLN and NARS Often Yield Similar strength × confidence Given Highly Uncertain Term Probabilities
  29. Attribution for Enhanced Explanation with Transferable Adversarial eXploration
  30. Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translation
  31. Dust to Tower: Coarse-to-Fine Photo-Realistic Scene Reconstruction from Sparse Uncalibrated Images
  32. Estimation of System Parameters Including Repeated Cross-Sectional Data through Emulator-Informed Deep Generative Model
  33. Real-time classification of EEG signals using Machine Learning deployment
  34. Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
  35. Uncertainty quantification for improving radiomic-based models in radiation pneumonitis prediction
  36. Hybrid Local Causal Discovery
  37. Hear the Scene: Audio-Enhanced Text Spotting
  38. Disparate Model Performance and Stability in Machine Learning Clinical Support for Diabetes and Heart Diseases
  39. Towards Open-Vocabulary Remote Sensing Image Semantic Segmentation
  40. Multi-label Classification using Deep Multi-order Context-aware Kernel Networks
  41. User Willingness-aware Sales Talk Dataset
  42. UniBrain: A Unified Model for Cross-Subject Brain Decoding
  43. Learning Radiance Fields from a Single Snapshot Compressive Image
  44. Pre-training, Fine-tuning and Re-ranking: A Three-Stage Framework for Legal Question Answering
  45. Generative Adversarial Network on Motion-Blur Image Restoration
  46. Meta-Learning-Based Delayless Subband Adaptive Filter using Complex Self-Attention for Active Noise Control
  47. Optimizing Helmet Detection with Hybrid YOLO Pipelines: A Detailed Analysis
  48. MNet-SAt: A Multiscale Network with Spatial-enhanced Attention for Segmentation of Polyps in Colonoscopy
  49. A Prototype Unit for Image De-raining using Time-Lapse Data
  50. DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes
  51. Focusing Image Generation to Mitigate Spurious Correlations
  52. NijiGAN: Transform What You See into Anime with Contrastive Semi-Supervised Learning and Neural Ordinary Differential Equations
  53. Find the Intention of Instruction: Comprehensive Evaluation of Instruction Understanding for Large Language Models
  54. Towards Simple and Provable Parameter-Free Adaptive Gradient Methods
  55. Comparative Performance Analysis of Quantum Machine Learning Architectures for Credit Card Fraud Detection
  56. Paleoinspired Vision: From Exploring Colour Vision Evolution to Inspiring Camera Design
  57. Residual Feature-Reutilization Inception Network for Image Classification
  58. A Self-Efficacy Theory-based Study on the Teachers Readiness to Teach Artificial Intelligence in Public Schools in Sri Lanka
  59. Temporal Context Consistency Above All: Enhancing Long-Term Anticipation by Learning and Enforcing Temporal Constraints
  60. Revisiting PCA for time series reduction in temporal dimension
  61. De Novo Generation of Hit-like Molecules from Gene Expression Profiles via Deep Learning
  62. Introduction to Graph Neural Networks for Machine Learning Engineers
  63. Generalized Uncertainty-Based Evidential Fusion with Hybrid Multi-Head Attention for Weak-Supervised Temporal Action Localization
  64. KALAHash: Knowledge-Anchored Low-Resource Adaptation for Deep Hashing
  65. MINIMA: Modality Invariant Image Matching
  66. Spectral-Temporal Fusion Representation for Person-in-Bed Detection
  67. Fully Data-driven but Interpretable Human Behavioural Modelling with Differentiable Discrete Choice Model
  68. An Engorgio Prompt Makes Large Language Model Babble on
  69. Asymptotically Optimal Search for a Change Point Anomaly under a Composite Hypothesis Model
  70. An In-Depth Analysis of Adversarial Discriminative Domain Adaptation for Digit Classification