mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 8 Mar 2025

193 papers

  1. Dynamic Evaluation Framework for Personalized and Trustworthy Agents: A Multi-Session Approach to Preference AdaptabilityLLM agents and tool use → Agentic recommender systems
  2. AI-Facilitated Episodic Future Thinking For Adults with ObesityLLM reasoning → Clinical and biomedical applications
  3. CeTAD: Towards Certified Toxicity-Aware Distance in Vision Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  4. Text-to-3D Generation using Jensen-Shannon Score DistillationDiffusion models → 3D, point cloud and scene generation
  5. Exploiting Edited Large Language Models as General Scientific OptimizersLLM reasoning → Test-time compute and efficient thinking
  6. Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  7. Research Superalignment Should Advance Now with Alternating Competence and Conformity OptimizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  8. Deep Reinforcement Learning-Based Semi-Autonomous Control for Magnetic Micro-robot Navigation with Immersive ManipulationDeep reinforcement learning methods → RL for clinical treatment and surgery
  9. Language Model Personalization via Reward FactorizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  10. Studying the Interplay Between the Actor and Critic Representations in Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  11. Backdoor Attacks on Discrete Graph Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  12. Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine UnlearningLLM safety and security → Machine unlearning
  13. Advancing Autonomous Vehicle Intelligence: Deep Learning and Multimodal LLM for Traffic Sign Recognition and Robust Lane DetectionEnd-to-end autonomous driving → VLMs for autonomous driving
  14. DOFA-CLIP: Multimodal Vision-Language Foundation Models for Earth ObservationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  15. On the Fly Adaptation of Behavior Tree-Based Policies through Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  16. ACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
  17. MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal AnsweringMixture-of-experts → Multimodal MoE models
  18. Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual GroundingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  19. Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language ModelsMechanistic interpretability → Steering and probing for LLM safety
  20. From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  21. Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented GenerationLLM reasoning → Reasoning for agents, planning and code +2
  22. MAD-MAX: Modular And Diverse Malicious Attack MiXtures for Automated LLM Red TeamingLLM safety and security → Prompt injection and agent security
  23. Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?LLM reasoning → Multimodal reasoning +1
  24. Integrating Chain-of-Thought for Multimodal Alignment: A Study on 3D Vision-Language LearningLLM reasoning → Multimodal reasoning
  25. WaveStitch: Flexible and Fast Conditional Time Series Generation with Diffusion ModelsDiffusion models → Flow matching, time series and science
  26. RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced DiffusionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  27. SCoRE: Benchmarking Long-Chain Reasoning in Commonsense ScenariosLLM reasoning → Reasoning benchmarks and evaluation
  28. Explainable Synthetic Image Detection through Diffusion Timestep EnsemblingDiffusion models → Image generation, text-to-image and editing
  29. PTDiffusion: Free Lunch for Generating Optical Illusion Hidden Pictures with Phase-Transferred Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  30. ROCM: RLHF on consistency modelsDiffusion models → Diffusion and flow policies for robotics +1
  31. Object-Centric World Model for Language-Guided ManipulationWorld models → Embodied and robot world models +1
  32. Treble Counterfactual VLMs: A Causal Approach to HallucinationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  33. UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban SpacesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  34. Biomechanics-Guided Residual Approach to Generalizable Human Motion Generation and EstimationDiffusion models → Diffusion and flow policies for robotics
  35. VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  36. Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language ModelMultimodal LLMs / vision-language models → Image editing and quality assessment
  37. GSV3D: Gaussian Splatting-based Geometric Distillation with Stable Video Diffusion for Single-Image 3D Object GenerationDiffusion models → 3D, point cloud and scene generation
  38. FlowMP: Learning Motion Fields for Robot Planning with Conditional Flow MatchingDiffusion models → Diffusion and flow policies for robotics
  39. X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention DistillationMultimodal LLMs / vision-language models → Image editing and quality assessment +1
  40. USP: Unified Self-Supervised Pretraining for Image Generation and UnderstandingDiffusion models → Diffusion foundations and sampling
  41. ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  42. PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic SegmentationDiffusion models → 3D, point cloud and scene generation
  43. A Survey on Post-training of Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  44. A Novel Trustworthy Video Summarization Algorithm Through a Mixture of LoRA ExpertsMixture-of-experts → Vision mixture-of-experts
  45. Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best PracticesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  46. MANDARIN: Mixture-of-Experts Framework for Dynamic Delirium and Coma Prediction in ICU Patients: Development and Validation of an Acute Brain Dysfunction Prediction ModelMixture-of-experts → Medical and biomedical MoE
  47. DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making EnvironmentsLLM agents and tool use → Reinforcement learning for LLM agents
  48. Mitigating Memorization in LLMs using Activation SteeringMechanistic interpretability → Activation steering methods
  49. Vairiational Stochastic GamesDeep reinforcement learning methods → RL for games and combinatorial optimization
  50. Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning
  51. Zero-Shot Peg Insertion: Identifying Mating Holes and Estimating SE(2) Poses with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  52. GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile DevicesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  53. Integrating Frequency-Domain Representations with Low-Rank Adaptation in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  54. Learning to Drive by Imitating Surrounding VehiclesOffline RL and imitation learning from data → Imitation and offline RL for driving
  55. Semantic Communication-Enabled Cloud-Edge-End-collaborative Metaverse Services Architecure
  56. From Interaction to Collaboration: How Hybrid Intelligence Enhances Chatbot Feedback
  57. Optimizing Generative AI's Accuracy and Transparency in Inductive Thematic Analysis: A Human-AI Comparison
  58. FloPE: Flower Pose Estimation for Precision Pollination
  59. Evaluation of the Automated Labeling Method for Taxonomic Nomenclature Through Prompt-Optimized Large Language Model
  60. MARRO: Multi-headed Attention for Rhetorical Role Labeling in Legal Documents
  61. LimTopic: LLM-based Topic Modeling and Text Summarization for Analyzing Scientific Articles limitations
  62. RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs
  63. The Computational Complexity of Positive Non-Clashing Teaching in Graphs
  64. Antibiotic Resistance Microbiology Dataset (ARMD): A Resource for Antimicrobial Resistance from EHRs
  65. Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy
  66. Adversarial Robustness of Discriminative Self-Supervised Learning in Vision
  67. The AI Pentad, the CHARME2D Model, and an Assessment of Current-State AI Regulation
  68. GIN-Graph: A Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks
  69. AI-Driven Optimization of Hardware Overlay Configurations
  70. Curriculum Learning-Driven PIELMs for Fluid Flow Simulations
  71. Exploring the Performance Improvement of Tensor Processing Engines through Transformation in the Bit-weight Dimension of MACs
  72. Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation
  73. Phraselette: A Poet's Procedural Palette
  74. A quantum annealing approach to graph node embedding
  75. States of LLM-generated Texts and Phase Transitions between them
  76. Understanding the role of autoencoders for stiff dynamical systems using information theory
  77. Higher-Order Belief in Incomplete Information MAIDs
  78. Enhanced Pediatric Dental Segmentation Using a Custom SegUNet with VGG19 Backbone on Panoramic Radiographs
  79. Learning and discovering multiple solutions using physics-informed neural networks with random initialization and deep ensemble
  80. Accurate and Efficient Two-Stage Gun Detection in Video
  81. End-to-End Action Segmentation Transformer
  82. Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling
  83. Synergizing AI and Digital Twins for Next-Generation Network Optimization, Forecasting, and Security
  84. IteRABRe: Iterative Recovery-Aided Block Reduction
  85. Single Domain Generalization with Adversarial Memory
  86. From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learning
  87. Applied Machine Learning Methods with Long-Short Term Memory Based Recurrent Neural Networks for Multivariate Temperature Prediction
  88. STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification
  89. Exploring Adversarial Transferability between Kolmogorov-arnold Networks
  90. Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations
  91. SplatTalk: 3D VQA with Gaussian Splatting
  92. Get In Video: Add Anything You Want to the Video
  93. Critical Foreign Policy Decisions (CFPD)-Benchmark: Measuring Diplomatic Preferences in Large Language Models
  94. Segment Anything, Even Occluded
  95. Infant Cry Detection Using Causal Temporal Representation
  96. LapSum -- One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection
  97. A Noise-Robust Turn-Taking System for Real-World Dialogue Robots: A Field Experiment
  98. Token-Efficient Item Representation via Images for LLM Recommender Systems
  99. Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection
  100. Dynamically evolving segment anything model with continuous learning for medical image segmentation
All 193
  1. StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams
  2. A Frank System for Co-Evolutionary Hybrid Decision-Making
  3. Optimal Output Feedback Learning Control for Discrete-Time Linear Quadratic Regulation
  4. Vision-based 3D Semantic Scene Completion via Capture Dynamic Representations
  5. StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition
  6. VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene Completion
  7. Lifelong Learning with Task-Specific Adaptation: Addressing the Stability-Plasticity Dilemma
  8. GraphGen+: Advancing Distributed Subgraph Generation and Graph Learning On Industrial Graphs
  9. LF2AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models
  10. Distributed Graph Neural Network Inference With Just-In-Time Compilation For Industry-Scale Graphs
  11. CUPCase: Clinically Uncommon Patient Cases and Diagnoses Dataset
  12. Generation of Optimized Solidity Code for Machine Learning Models using LLMs
  13. Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization
  14. Removing Multiple Hybrid Adverse Weather in Video via a Unified Model
  15. NeuroADDA: Active Discriminative Domain Adaptation in Connectomic
  16. Human-AI Experience in Integrated Development Environments: A Systematic Literature Review
  17. Attention on the Wires (AttWire): A Foundation Model for Detecting Devices and Catheters in X-ray Fluoroscopic Images
  18. Attackers Can Do Better: Over- and Understated Factors of Model Stealing Attacks
  19. MSConv: Multiplicative and Subtractive Convolution for Face Recognition
  20. Sample-aware Adaptive Structured Pruning for Large Language Models
  21. Lightweight Software Kernels and Hardware Extensions for Efficient Sparse Deep Neural Networks on Microcontrollers
  22. FORESCENE: FOREcasting human activity via latent SCENE graphs diffusion
  23. Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks
  24. ForestSplats: Deformable transient field for Gaussian Splatting in the Wild
  25. Minion Gated Recurrent Unit for Continual Learning
  26. Secure On-Device Video OOD Detection Without Backpropagation
  27. VACT: A Video Automatic Causal Testing System and a Benchmark
  28. Feature-EndoGaussian: Feature Distilled Gaussian Splatting in Surgical Deformable Scene Reconstruction
  29. Invariant Federated Learning for Edge Intelligence: Mitigating Heterogeneity and Asynchrony via Exit Strategy and Invariant Penalty
  30. Double Debiased Machine Learning for Mediation Analysis with Continuous Treatments
  31. SRM-Hair: Single Image Head Mesh Reconstruction via 3D Morphable Hair
  32. Do Fairness Interventions Come at the Cost of Privacy: Evaluations for Binary Classifiers
  33. OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images
  34. Adaptive UAV-Assisted Hierarchical Federated Learning: Optimizing Energy, Latency, and Resilience for Dynamic Smart IoT
  35. Exploring the usage of Probabilistic Neural Networks for Ionospheric electron density estimation
  36. Boosting the Local Invariance for Better Adversarial Transferability
  37. GRP: Goal-Reversed Prompting for Zero-Shot Evaluation with LLMs
  38. System 0/1/2/3: Quad-process theory for multi-timescale embodied collective cognitive systems
  39. Evaluating Discourse Cohesion in Pre-trained Language Models
  40. Viewport-Unaware Blind Omnidirectional Image Quality Assessment: A Flexible and Effective Paradigm
  41. RGB-Phase Speckle: Cross-Scene Stereo 3D Reconstruction via Wrapped Pre-Normalization
  42. BlackGoose Rimer: Harnessing RWKV-7 as a Simple yet Superior Replacement for Transformers in Large-Scale Time Series Modeling
  43. Unlocking Pretrained LLMs for Motion-Related Multimodal Generation: A Fine-Tuning Approach to Unify Diffusion and Next-Token Prediction
  44. SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography
  45. NeuraLoc: Visual Localization in Neural Implicit Map with Dual Complementary Features
  46. On Statistical Estimation of Edge-Reinforced Random Walks
  47. Pathology-Guided AI System for Accurate Segmentation and Diagnosis of Cervical Spondylosis
  48. AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learning
  49. Multi-modal expressive personality recognition in data non-ideal audiovisual based on multi-scale feature enhancement and modal augment
  50. Feature Fusion Attention Network with CycleGAN for Image Dehazing, De-Snowing and De-Raining
  51. Vision-aware Multimodal Prompt Tuning for Uploadable Multi-source Few-shot Domain Adaptation
  52. Handwritten Digit Recognition: An Ensemble-Based Approach for Superior Performance
  53. High-Precision Dichotomous Image Segmentation via Depth Integrity-Prior and Fine-Grained Patch Strategy
  54. Attention-Based Synthetic Data Generation for Calibration-Enhanced Survival Analysis: A Case Study for Chronic Kidney Disease Using Electronic Health Records
  55. Clustering-based Meta Bayesian Optimization with Theoretical Guarantee
  56. ZO-DARTS++: An Efficient and Size-Variable Zeroth-Order Neural Architecture Search Algorithm
  57. Theta Theory: operads and coloring
  58. Fish2Mesh Transformer: 3D Human Mesh Recovery from Egocentric Vision
  59. Multi-Attribute Multi-Grained Adaptation of Pre-Trained Language Models for Text Understanding from Bayesian Perspective
  60. Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts
  61. T-CBF: Traversability-based Control Barrier Function to Navigate Vertically Challenging Terrain
  62. Fixing the Pitfalls of Probabilistic Time-Series Forecasting Evaluation by Kernel Quadrature
  63. Biased Federated Learning under Wireless Heterogeneity
  64. An Empirical Study of Causal Relation Extraction Transfer: Design and Data
  65. Towards Conversational AI for Disease Management
  66. GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images
  67. TransParking: A Dual-Decoder Transformer Framework with Soft Localization for End-to-End Automatic Parking
  68. Multi-view Spectral Clustering on the Grassmannian Manifold With Hypergraph Representation
  69. STAR: A Foundation Model-driven Framework for Robust Task Planning and Failure Recovery in Robotic Systems
  70. Pathological Prior-Guided Multiple Instance Learning For Mitigating Catastrophic Forgetting in Breast Cancer Whole Slide Image Classification
  71. Fine-Grained Bias Detection in LLM: Enhancing detection mechanisms for nuanced biases
  72. DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation
  73. Interpretable High-order Knowledge Graph Neural Network for Predicting Synthetic Lethality in Human Cancers
  74. Constructions are Revealed in Word Distributions
  75. Improving SAM for Camouflaged Object Detection via Dual Stream Adapters
  76. Randomized Quasi-Monte Carlo Features for Kernel Approximation
  77. A Label-Free High-Precision Residual Moveout Picking Method for Travel Time Tomography based on Deep Learning
  78. Towards Universal Text-driven CT Image Segmentation
  79. SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?
  80. Data-Free Black-Box Federated Learning via Zeroth-Order Gradient Estimation
  81. Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models
  82. FedEM: A Privacy-Preserving Framework for Concurrent Utility Preservation in Federated Learning
  83. Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity
  84. End-to-End HOI Reconstruction Transformer with Graph-based Encoding
  85. Intent-Aware Self-Correction for Mitigating Social Biases in Large Language Models
  86. Nearly Optimal Differentially Private ReLU Regression
  87. Analyzing the Role of Permutation Invariance in Linear Mode Connectivity
  88. Towards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitioners
  89. SODAs: Sparse Optimization for the Discovery of Differential and Algebraic Equations
  90. Psycholinguistic Analyses in Software Engineering Text: A Systematic Literature Review
  91. GrInAdapt: Scaling Retinal Vessel Structural Map Segmentation Through Grounding, Integrating and Adapting Multi-device, Multi-site, and Multi-modal Fundus Domains
  92. HealthiVert-GAN: A Novel Framework of Pseudo-Healthy Vertebral Image Synthesis for Interpretable Compression Fracture Grading
  93. Bimodal Connection Attention Fusion for Speech Emotion Recognition