mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 16 Jul 2025

318 papers

  1. From Black Box to Biomarker: Sparse Autoencoders for Interpreting Speech Models of Parkinson's DiseaseMechanistic interpretability → Interpreting biomedical and science models
  2. MADI: Masking-Augmented Diffusion with Inference-Time Scaling for Visual EditingLLM reasoning → Diffusion reasoning and test-time scaling +1
  3. DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  4. DLSF: Dual-Layer Synergistic Fusion for High-Fidelity Image Syn-thesisDiffusion models → Image generation, text-to-image and editing
  5. Distributional Reinforcement Learning on Path-dependent OptionsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  6. Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular VideosDiffusion models → 3D, point cloud and scene generation
  7. VLMgineer: Vision Language Models as Robotic ToolsmithsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  8. Reasoning-Finetuning Repurposes Latent Representations in Base ModelsLLM reasoning → Test-time compute and efficient thinking
  9. NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian SplattingLLM agents and tool use → Multimodal and embodied agents
  10. A Survey of Explainable Reinforcement Learning: Targets, Methods and NeedsDeep reinforcement learning methods → Interpretable and logic-guided RL
  11. Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  12. MindJourney: Test-Time Scaling with World Models for Spatial ReasoningWorld models → World models for language agents +1
  13. Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged TrainingLLM reasoning → Reinforcement learning for reasoning
  14. ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +1
  15. CytoSAE: Interpretable Cell Embeddings for HematologyMechanistic interpretability → Interpreting biomedical and science models
  16. Mitigating Object Hallucinations via Sentence-Level Early InterventionMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  17. Describe Anything Model for Visual Question Answering on Text-rich ImagesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  18. EgoVLA: Learning Vision-Language-Action Models from Egocentric Human VideosVision-language-action models → Human-video and latent-action pretraining +1
  19. Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning ModelsLLM reasoning → Prompting and chain-of-thought reasoning +2
  20. Advancing Retrieval-Augmented Generation for Structured Enterprise and Internal DataRetrieval-augmented generation → RAG pipeline design and evaluation
  21. Mixture of Raytraced ExpertsMixture-of-experts → MoE theory and gating functions
  22. AutoVDC: Automated Vision Data Cleaning Using Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  23. ROC-n-reroll: How verifier imperfection affects test-time scalingLLM reasoning → Test-time compute and efficient thinking
  24. Assessing the Value of Visual Input: A Benchmark of Multimodal Large Language Models for Robotic Path PlanningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  25. Improving Reinforcement Learning Sample-Efficiency using Local ApproximationDeep reinforcement learning methods → RL theory and sample complexity
  26. Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-rankerMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  27. Improving Lightweight Weed Detection via Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
  28. Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
  29. Compositional Discrete Latent Code for High Fidelity, Productive Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  30. Thought Purity: A Defense Framework For Chain-of-Thought AttackLLM reasoning → Reasoning for agents, planning and code
  31. FADE: Adversarial Concept Erasure in Flow ModelsDiffusion models → Robustness, privacy and adversarial aspects
  32. Infherno: End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical NotesLLM agents and tool use → Medical and scientific domain agents
  33. Generate to Ground: Multimodal Text Conditioning Boosts Phrase Grounding in Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models +1
  34. Xiangqi-R1: Enhancing Spatial Strategic Reasoning in LLMs for Chinese Chess via Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code
  35. Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible ControlMechanistic interpretability → SAE features and their applications
  36. RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative ModelsDiffusion models → Medical imaging and segmentation
  37. BenchRL-QAS: Benchmarking reinforcement learning algorithms for quantum architecture searchDeep reinforcement learning methods → Quantum reinforcement learning
  38. Jailbreaking Generative AI: Multivector Phishing Threats and Transformer based DefensesLLM safety and security → Prompt injection and agent security
  39. SmokeSVD: Smoke Reconstruction from A Single View via Progressive Novel View Synthesis and Refinement with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  40. Findings of MEGA: Maths Explanation with LLMs using the Socratic Method for Active LearningLLM reasoning → Mathematical reasoning
  41. InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofingMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  42. Evaluating the Ability of Large Language Models to Reason about Cardinal Directions, RevisitedLLM reasoning → Reasoning benchmarks and evaluation
  43. Granular feedback merits sophisticated aggregationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  44. Towards Ultra-Reliable 6G in-X Subnetworks: Dynamic Link Adaptation by Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  45. 3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question AnsweringLLM reasoning → Spatial and embodied reasoning
  46. Robust Planning for Autonomous Vehicles with Diffusion-Based Failure SamplersDiffusion models → Diffusion and flow policies for robotics +1
  47. Aime: Towards Fully-Autonomous Multi-Agent FrameworkLLM agents and tool use → General LLM agent frameworks and benchmarks
  48. Style Composition within Distinct LoRA modules for Traditional ArtDiffusion models → Image generation, text-to-image and editing
  49. EC-Diff: Fast and High-Quality Edge-Cloud Collaborative Inference for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  50. Value-Based Large Language Model Agent Simulation for Mutual Evaluation of Trust and Interpersonal ClosenessLLM agents and tool use → Social simulation and multi-agent debate
  51. Online Training and Pruning of Deep Reinforcement Learning NetworksDeep reinforcement learning methods → Deep RL algorithms and representations
  52. GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  53. Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness EvaluationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  54. The benefits of query-based KGQA systems for complex and temporal questions in LLM eraLLM reasoning → Knowledge- and tool-augmented reasoning
  55. IAM: Efficient Inference through Attention Mapping between Different-scale LLMsEfficient LLM inference and serving → KV cache optimization
  56. DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt CompressionEfficient LLM inference and serving → Prompt and context compression
  57. POLYCHARTQA: Benchmarking Large Vision-Language Models with Multilingual Chart Question AnsweringMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  58. A Survey of Deep Learning for Geometry Problem SolvingLLM reasoning → Spatial and embodied reasoning
  59. Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  60. From Generative to Episodic: Sample-Efficient Replicable Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  61. Schr"odinger Bridge Consistency Trajectory Models for Speech EnhancementDiffusion models → Audio, speech and music
  62. Context-Aware Search and Retrieval Over Erasure ChannelsRetrieval-augmented generation → Generation and context integration
  63. LLMs Encode Harmfulness and Refusal SeparatelyLLM safety and security → Safety alignment, refusal and guardrails
  64. DualReward: A Dynamic Reinforcement Learning Framework for Cloze Tests Distractor GenerationDeep reinforcement learning methods → RL training of language and agent models
  65. SimDiffRec: Semantic Similarity-Guided Diffusion for Contrastive Sequential RecommendationDiffusion models → Diffusion recommenders
  66. CosmoFlow: Scale-Aware Representation Learning for Cosmology with Flow MatchingDiffusion models → Inverse problems and image restoration
  67. CorrMoE: Mixture of Experts with De-stylization Learning for Cross-Scene and Cross-Domain Correspondence PruningMixture-of-experts → Vision mixture-of-experts
  68. MNIST-Gen: A Modular MNIST-Style Dataset Generation Using Hierarchical Semantics, Reinforcement Learning, and Category TheoryDeep reinforcement learning methods → RL with diffusion and flow models
  69. Deploying Geospatial Foundation Models in the Real World: Lessons from WorldCereal
  70. A Compute-Matched Re-Evaluation of TroVE on MATH
  71. Incentivised Orchestrated Training Architecture (IOTA): A Technical Primer for Release
  72. Domain Generalization via Pareto Optimal Gradient Matching
  73. Diffusion-based translation between unpaired spontaneous premature neonatal EEG and fetal MEG
  74. Multi-Granular Discretization for Interpretable Generalization in Precise Cyberattack Identification
  75. Fair Representation in Parliamentary Summaries: Measuring and Mitigating Inclusion Bias
  76. Advanced Space Mapping Technique Integrating a Shared Coarse Model for Multistate Tuning-Driven Multiphysics Optimization of Tunable Filters
  77. Artificial Intelligence for Green Hydrogen Yield Prediction and Site Suitability using SHAP-Based Composite Index: Focus on Oman
  78. Cognitive Castes: Artificial Intelligence, Epistemic Stratification, and the Dissolution of Democratic Discourse
  79. Geometry-Aware Active Learning of Pattern Rankings via Choquet-Based Aggregation
  80. Distributed Machine Learning Approach for Low-Latency Localization in Cell-Free Massive MIMO Systems
  81. Developing an AI-Guided Assistant Device for the Deaf and Hearing Impaired
  82. UL-DD: A Multimodal Drowsiness Dataset Using Video, Biometric Signals, and Behavioral Data
  83. Selective Embedding for Deep Learning
  84. Trustworthy Pedestrian Trajectory Prediction via Pattern-Aware Interaction Modeling
  85. Mitigating Stylistic Biases of Machine Translation Systems via Monolingual Corpora Only
  86. Enhanced DeepLab Based Nerve Segmentation with Optimized Tuning
  87. Improving KAN with CDF normalization to quantiles
  88. TopicImpact: Improving Customer Feedback Analysis with Opinion Units for Topic Modeling and Star-Rating Prediction
  89. PARAM-1 BharatGen 2.9B Model
  90. From Binary to Semantic: Utilizing Large-Scale Binary Occupancy Data for 3D Semantic Occupancy Prediction
  91. Minimalist Concept Erasure in Generative Models
  92. Benchmarking Deception Probes via Black-to-White Performance Boosts
  93. TRIQA: Image Quality Assessment by Contrastive Pretraining on Ordered Distortion Triplets
  94. Finite-Dimensional Gaussian Approximation for Deep Neural Networks: Universality in Random Weights
  95. Improving Drug Identification in Overdose Death Surveillance using Large Language Models
  96. Data Transformation Strategies to Remove Heterogeneity
  97. FORTRESS: Function-composition Optimized Real-Time Resilient Structural Segmentation via Kolmogorov-Arnold Enhanced Spatial Attention Networks
  98. ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluation
  99. The first open machine translation system for the Chechen language
  100. InSight: AI Mobile Screening Tool for Multiple Eye Disease Detection using Multimodal Fusion
All 318
  1. Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models
  2. Single Conversation Methodology: A Human-Centered Protocol for AI-Assisted Software Development
  3. Integrated Oculomics and Lipidomics Reveal Microvascular Metabolic Signatures Associated with Cardiovascular Health in a Healthy Cohort
  4. Physics constrained learning of stochastic characteristics
  5. Improving physics-informed neural network extrapolation via transfer learning and adaptive activation functions
  6. A Fuzzy Approach to Project Success: Measuring What Matters
  7. Federated Learning in Offline and Online EMG Decoding: A Privacy and Performance Perspective
  8. A Novel Data Augmentation Strategy for Robust Deep Learning Classification of Biomedical Time-Series Data: Application to ECG and EEG Analysis
  9. QSpark: Towards Reliable Qiskit Code Generation
  10. Achieving Robust Channel Estimation Neural Networks by Designed Training Data
  11. Funnel-HOI: Top-Down Perception for Zero-Shot HOI Detection
  12. Pathology-Guided Virtual Staining Metric for Evaluation and Training
  13. BootSeer: Analyzing and Mitigating Initialization Bottlenecks in Large-Scale LLM Training
  14. Predicting Soccer Penalty Kick Direction Using Human Action Recognition
  15. Learning Task Mixtures from Task Affinities: A Probabilistic Graphical Model for Supervised Fine-Tuning
  16. Are encoders able to learn landmarkers for warm-starting of Hyperparameter Optimization?
  17. MS-DGCNN++: Multi-Scale Dynamic Graph Convolution with Scale-Dependent Normalization for Robust LiDAR Tree Species Classification
  18. HairFormer: Transformer-Based Dynamic Neural Hair Simulation
  19. CT-ScanGaze: A Dataset and Baselines for 3D Volumetric Scanpath Modeling
  20. From Time-series Generation, Model Selection to Transfer Learning: A Comparative Review of Pixel-wise Approaches for Large-scale Crop Mapping
  21. Second-Order Bounds for [0,1]-Valued Regression via Betting Loss
  22. Ranking Vectors Clustering: Theory and Applications
  23. Cross-World Assumption and Refining Prediction Intervals for Individual Treatment Effects
  24. Deep Bilinear Koopman Model for Real-Time Vehicle Control in Frenet Frame
  25. Assay2Mol: large language model-based drug design using BioAssay context
  26. IncA-DES: An incremental and adaptive dynamic ensemble selection approach using online K-d tree neighborhood search for data streams with concept drift
  27. Safeguarding Federated Learning-based Road Condition Classification
  28. Evaluation of Neural Surrogates for Physical Modelling Synthesis of Nonlinear Elastic Plates
  29. Rel-HNN: Split Parallel Hypergraph Neural Network for Learning on Relational Databases
  30. Can Mental Imagery Improve the Thinking Capabilities of AI Systems?
  31. Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility
  32. The Serial Scaling Hypothesis
  33. Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models
  34. Transforming Football Data into Object-centric Event Logs with Spatial Context Information
  35. Complex non-backtracking matrix for directed graphs
  36. GLOMIA-Pro: A Generalizable Longitudinal Medical Image Analysis Framework for Disease Progression Prediction
  37. Language Models Improve When Pretraining Data Matches Target Tasks
  38. PhysX-3D: Physical-Grounded 3D Asset Generation
  39. MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding
  40. SpatialTrackerV2: 3D Point Tracking Made Easy
  41. Interpreting Radiologist's Intention from Eye Movements in Chest X-ray Diagnosis
  42. Cost-aware Stopping for Bayesian Optimization
  43. S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic Modeling
  44. Vision-based Perception for Autonomous Vehicles in Obstacle Avoidance Scenarios
  45. LLM-Based Config Synthesis requires Disambiguation
  46. Characterizing State Space Model and Hybrid Language Model Performance with Long Context
  47. A Bayesian Incentive Mechanism for Poison-Resilient Federated Learning
  48. Targeted Deep Architectures: A TMLE-Based Framework for Robust Causal Inference in Neural Networks
  49. Traffic-Aware Pedestrian Intention Prediction
  50. Unit-Based Histopathology Tissue Segmentation via Multi-Level Feature Representation
  51. DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition
  52. InterpIoU: Rethinking Bounding Box Regression with Interpolation-Based IoU Optimization
  53. Spontaneous Spatial Cognition Emerges during Egocentric Video Viewing through Non-invasive BCI
  54. QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval
  55. NOCTA: Non-Greedy Objective Cost-Tradeoff Acquisition for Longitudinal Data
  56. Neural Network-Guided Symbolic Regression for Interpretable Descriptor Discovery in Perovskite Catalysts
  57. OD-VIRAT: A Large-Scale Benchmark for Object Detection in Realistic Surveillance Environments
  58. Trustworthy Tree-based Machine Learning by MoS2 Flash-based Analog CAM with Inherent Soft Boundaries
  59. Text-driven Multiplanar Visual Interaction for Semi-supervised Medical Image Segmentation
  60. Heat Kernel Goes Topological
  61. Probing for Arithmetic Errors in Language Models
  62. Web-Browsing LLMs Can Access Social Media Profiles and Infer User Demographics
  63. Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate
  64. GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities
  65. FactorHD: A Hyperdimensional Computing Model for Multi-Object Multi-Class Representation and Factorization
  66. Cluster Contrast for Unsupervised Visual Representation Learning
  67. Surrogate modeling for uncertainty quantification in nonlinear dynamics
  68. Exploring Gender Bias in Alzheimer's Disease Detection: Insights from Mandarin and Greek Speech Perception
  69. Nonlinear Concept Erasure: a Density Matching Approach
  70. Neural Polar Decoders for Deletion Channels
  71. Chain-of-Descriptions: Improving Code LLMs for VHDL Code Generation and Summarization
  72. PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning
  73. RegCL: Compact Continual SAM Adaptation for Visual Grounding in Multi-Sensorial Media
  74. Text-ADBench: Text Anomaly Detection Benchmark Based on LLM Embeddings
  75. Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation
  76. SHACL Validation in the Presence of Ontologies: Semantics and Rewriting Techniques
  77. MERA Code: A Unified Framework for Evaluating Code Generation Across Tasks
  78. Site-Level Fine-Tuning with Progressive Layer Freezing: Towards Robust Prediction of Bronchopulmonary Dysplasia from Day-1 Chest Radiographs in Extremely Preterm Infants
  79. A Framework for Nonstationary Gaussian Processes with Neural Network Parameters
  80. Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese
  81. Robust Causal Discovery in Real-World Time Series with Power-Laws
  82. Surrogate Quantum Circuit Design for the Lattice Boltzmann Collision Operator
  83. Improving Contextual ASR via Multi-grained Fusion with Large Language Models
  84. Fast Variational Bayes for Large Spatial Data
  85. Comparative Analysis of CNN Performance in Keras, PyTorch and JAX on PathMNIST
  86. Designing Algorithms for Entropic Optimal Transport from an Optimisation Perspective
  87. Calisthenics Skills Temporal Video Segmentation
  88. Looking for Fairness in Recommender Systems
  89. Universal Fourier Neural Operators for periodic homogenization problems in linear elasticity
  90. MGFFD-VLM: Multi-Granularity Prompt Learning for Face Forgery Detection with VLM
  91. Optimizers Qualitatively Alter Solutions And We Should Leverage This
  92. Physics-Informed Linear Model (PILM): Analytical Representations and Application to Crustal Strain Rate Estimation
  93. Towards few-shot isolated word reading assessment
  94. Draw an Ugly Person An Exploration of Generative AIs Perceptions of Ugliness
  95. The Behavioural Translation Style Space: Towards simulating the temporal dynamics of affect, behaviour, and cognition in human translation production
  96. BuildEvo: Designing Building Energy Consumption Forecasting Heuristics via LLM-driven Evolution
  97. Quantize More, Lose Less: Autoregressive Generation from Residually Quantized Speech Representations
  98. A Selective Quantization Tuner for ONNX Models
  99. Revealing the Ancient Beauty: Digital Reconstruction of Temple Tiles using Computer Vision
  100. Explainable Evidential Clustering
  101. Wavelet-based Decoupling Framework for low-light Stereo Image Enhancement
  102. Partially Observable Reference Policy Programming: Solving POMDPs Sans Numerical Optimisation
  103. Asymptotic behavior of eigenvalues of large rank perturbations of large random matrices
  104. Hybrid Ensemble Approaches: Optimal Deep Feature Fusion and Hyperparameter-Tuned Classifier Ensembling for Enhanced Brain Tumor Classification
  105. RUMAA: Repeat-Aware Unified Music Audio Analysis for Score-Performance Alignment, Transcription, and Mistake Detection
  106. RadioDiff-3D: A 3D×3D Radio Map Dataset and Generative Diffusion Based Benchmark for 6G Environment-Aware Communication
  107. Multi-Component VAE with Gaussian Markov Random Field
  108. Fine-Grained Image Recognition from Scratch with Teacher-Guided Data Augmentation
  109. PRISM: Distributed Inference for Foundation Models at Edge
  110. FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale
  111. Overview of the Sensemaking Task at the ELOQUENT 2025 Lab: LLMs as Teachers, Students and Evaluators
  112. LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters
  113. Neural Human Pose Prior
  114. AD-GS: Object-Aware B-Spline Gaussian Splatting for Self-Supervised Autonomous Driving
  115. Learning Pixel-adaptive Multi-layer Perceptrons for Real-time Image Enhancement
  116. HyDRA: A Hybrid Dual-Mode Network for Closed- and Open-Set RFFI with Optimized VMD
  117. DoRF: Doppler Radiance Fields for Robust Human Activity Recognition Using Wi-Fi
  118. Self-Adaptive and Robust Federated Spectrum Sensing without Benign Majority for Cellular Networks
  119. Iterative Augmentation with Summarization Refinement (IASR) Evaluation for Unstructured Survey data Modeling and Analysis
  120. Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers
  121. Open-Vocabulary Indoor Object Grounding with 3D Hierarchical Scene Graph
  122. Quantum Machine Learning in Multi-Qubit Phase-Space Part I: Foundations
  123. LidarPainter: One-Step Away From Any Lidar View To Novel Guidance
  124. Topology Enhanced MARL for Multi-Agent Cooperative Decision-Making of CAVs
  125. Multimodal Coordinated Online Behavior: Trade-offs and Strategies
  126. Non-Adaptive Adversarial Face Generation
  127. Out-of-distribution data supervision towards biomedical semantic segmentation
  128. From Static to Intelligent: Evolving SaaS Pricing with LLMs
  129. DeepShade: Enable Shade Simulation by Text-conditioned Image Generation
  130. A Privacy-Preserving Framework for Advertising Personalization Incorporating Federated Learning and Differential Privacy
  131. BRUM: Robust 3D Vehicle Reconstruction from 360 Sparse Images
  132. Is This Predictor More Informative than Another? A Decision-Theoretical Comparison
  133. Benchmarking and Explaining Deep Learning Cortical Lesion MRI Segmentation in Multiple Sclerosis
  134. Better Convergence Guarantees for Sign-Based Momentum Methods
  135. YOLOv8-SMOT: An Efficient and Robust Framework for Real-Time Small Object Tracking via Slice-Assisted Training and Adaptive Association
  136. Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics
  137. BOOKCOREF: Coreference Resolution at Book Scale
  138. Emergence of Quantised Representations Isolated to Anisotropic Functions
  139. StylOch at PAN: Gradient-Boosted Trees with Frequency-Based Stylometric Features
  140. MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning
  141. FloGAN: Scenario-Based Urban Mobility Flow Generation via Conditional GANs and Dynamic Region Decoupling
  142. IDFace: Face Template Protection for Efficient and Secure Identification
  143. MoViAD: A Modular Library for Visual Anomaly Detection
  144. Information-Theoretic Generalization Bounds of Replay-based Continual Learning
  145. Stereo Sound Event Localization and Detection with Onscreen/offscreen Classification
  146. A Comparative Approach to Assessing Linguistic Creativity of Large Language Models and Humans
  147. Intra-view and Inter-view Correlation Guided Multi-view Novel Class Discovery
  148. SGLoc: Semantic Localization System for Camera Pose Estimation from 3D Gaussian Splatting Representation
  149. MVAR: MultiVariate AutoRegressive Air Pollutants Forecasting Model
  150. Dataset Ownership Verification for Pre-trained Masked Models
  151. Incorporating Fairness Constraints into Archetypal Analysis
  152. SS-DC: Spatial-Spectral Decoupling and Coupling Across Visible-Infrared Gap for Domain Adaptive Object Detection
  153. Identifying Signatures of Image Phenotypes to Track Treatment Response in Liver Disease
  154. DUSE: A Data Expansion Framework for Low-resource Automatic Modulation Recognition based on Active Learning
  155. Deep Neural Encoder-Decoder Model to Relate fMRI Brain Activity with Naturalistic Stimuli
  156. Dual form Complementary Masking for Domain-Adaptive Image Segmentation
  157. Frequency-Dynamic Attention Modulation for Dense Prediction
  158. Improving Data and Parameter Efficiency of Neural Language Models Using Representation Analysis
  159. Expanding ML-Documentation Standards For Better Security
  160. Detecting In-Person Conversations in Noisy Real-World Environments with Smartwatch Audio and Motion Sensing
  161. AU-Blendshape for Fine-grained Stylized 3D Facial Expression Manipulation
  162. Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection
  163. SAMST: A Transformer framework based on SAM pseudo label filtering for remote sensing semi-supervised semantic segmentation
  164. Understanding visual attention beehind bee-inspired UAV navigation
  165. ID-EA: Identity-driven Text Enhancement and Adaptation with Textual Inversion for Personalized Text-to-Image Generation
  166. Formal Verification of Neural Certificates Done Dynamically
  167. Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints
  168. Dataset-Adaptive Dimensionality Reduction
  169. Simplifications are Absolutists: How Simplified Language Reduces Word Sense Awareness in LLM-Generated Definitions
  170. Recent results on searches with boosted Higgs bosons at CMS
  171. Graph Representations for Reading Comprehension Analysis using Large Language Model and Eye-Tracking Biomarker
  172. HPR3D: Hierarchical Proxy Representation for High-Fidelity 3D Reconstruction and Controllable Editing
  173. Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos
  174. Toxicity-Aware Few-Shot Prompting for Low-Resource Singlish Translation
  175. d-DQIVAR: Data-centric Visual Analytics and Reasoning for Data Quality Improvement
  176. PoTPTQ: A Two-step Power-of-Two Post-training for LLMs
  177. Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation
  178. RNAMunin: A Deep Machine Learning Model for Non-coding RNA Discovery
  179. MOSPA: Human Motion Generation Driven by Spatial Audio
  180. Kevin: Multi-Turn RL for Generating CUDA Kernels
  181. RaDL: Relation-aware Disentangled Learning for Multi-Instance Text-to-Image Generation
  182. Effective Fine-Tuning of Vision Transformers with Low-Rank Adaptation for Privacy-Preserving Image Classification
  183. BlockBPE: Parallel BPE Tokenization
  184. A Multi-Level Similarity Approach for Single-View Object Grasping: Matching, Planning, and Fine-Tuning
  185. AI-Native Open RAN for Non-Terrestrial Networks: An Overview
  186. Dark-EvGS: Event Camera as an Eye for Radiance Field in the Dark
  187. Accelerating RF Power Amplifier Design via Intelligent Sampling and ML-Based Parameter Tuning
  188. Enhancing Signal Proportion Estimation Through Leveraging Arbitrary Covariance Structures
  189. A Parallel CPU-GPU Framework for Batching Heuristic Operations in Depth-First Heuristic Search
  190. AFPM: Alignment-based Frame Patch Modeling for Cross-Dataset EEG Decoding
  191. SEPose: A Synthetic Event-based Human Pose Estimation Dataset for Pedestrian Monitoring
  192. Resampling strategies for imbalanced regression: a survey and empirical analysis
  193. Imbalanced Regression Pipeline Recommendation
  194. CompressedVQA-HDR: Generalized Full-reference and No-reference Quality Assessment Models for Compressed High Dynamic Range Videos
  195. Newfluence: Boosting Model interpretability and Understanding in High Dimensions
  196. Spatial Frequency Modulation for Semantic Segmentation
  197. From Coarse to Nuanced: Cross-Modal Alignment of Fine-Grained Linguistic Cues and Visual Salient Regions for Dynamic Emotion Recognition
  198. Choosing the Better Bandit Algorithm under Data Sharing: When Do A/B Experiments Work?
  199. Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language Models
  200. COLA-GEC: A Bidirectional Framework for Enhancing Grammatical Acceptability and Error Correction
  201. Optimizing Drivers' Discount Order Acceptance Strategies: A Policy-Improved Deep Deterministic Policy Gradient Framework
  202. Cross-Domain Transfer and Few-Shot Learning for Personal Identifiable Information Recognition
  203. OrdShap: Feature Position Importance for Sequential Black-Box Models
  204. A Spatial-Physics Informed Model for 3D Spiral Sample Scanned by SQUID Microscopy
  205. Towards Autonomous Riding: A Review of Perception, Planning, and Control in Intelligent Two-Wheelers
  206. Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential
  207. Interactive Hybrid Rice Breeding with Parametric Dual Projection
  208. Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update
  209. ProtoConNet: Prototypical Augmentation and Alignment for Open-Set Few-Shot Image Classification
  210. Protenix-Mini: Efficient Structure Predictor via Compact Architecture, Few-Step Diffusion and Switchable pLM
  211. HyperEvent: A Strong Baseline for Dynamic Link Prediction via Relative Structural Encoding
  212. ILID: Native Script Language Identification for Indian Languages
  213. Arctic Inference with Shift Parallelism: Fast and Efficient Open Source Inference System for Enterprise AI
  214. SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate Modeling
  215. Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator
  216. Tracing Facts or just Copies? A critical investigation of the Competitions of Mechanisms in Large Language Models
  217. CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy Labels
  218. MOFSimBench: Evaluating Universal Machine Learning Interatomic Potentials In Metal--Organic Framework Molecular Modeling