mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 29 Apr 2025

301 papers

  1. An Ontology-Driven Graph RAG for Legal Norms: A Structural, Temporal, and Deterministic ApproachRetrieval-augmented generation → Legal and financial RAG
  2. HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis GenerationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  3. T2ID-CAS: Diffusion Model and Class Aware Sampling to Mitigate Class Imbalance in Neck Ultrasound Anatomical Landmark DetectionDiffusion models → Medical imaging and segmentation
  4. CachePrune: Teaching LLMs What Not to Follow via KV-Cache EditingEfficient LLM inference and serving → KV cache optimization +1
  5. SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World RepositoriesLLM agents and tool use → Agent threats, guardrails and governance
  6. TT-LoRA MoE: Unifying Parameter-Efficient Fine-Tuning and Sparse Mixture-of-ExpertsMixture-of-experts → Mixture of LoRA experts
  7. Erased but Not Forgotten: How Backdoors Compromise Concept ErasureDiffusion models → Robustness, privacy and adversarial aspects
  8. Automated Parking Trajectory Generation Using Deep Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
  9. A 3D pocket-aware and affinity-guided diffusion model for lead optimizationDiffusion models → Flow matching, time series and science
  10. Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain GeneralizationMixture-of-experts → Expert routing strategies
  11. NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  12. Multimodal Large Language Models for Medicine: A Comprehensive SurveyMultimodal LLMs / vision-language models → Medical vision-language models
  13. YoChameleon: Personalized Vision and Language GenerationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  14. Toward Efficient Exploration by Large Language Model AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  15. TesserAct: Learning 4D Embodied World ModelsWorld models → Embodied and robot world models
  16. XPG-RL: Reinforcement Learning with Explainable Priority Guidance for Efficiency-Boosted Mechanical SearchDeep reinforcement learning methods → RL for robot locomotion and manipulation
  17. AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM SecurityLLM agents and tool use → Agent threats, guardrails and governance +1
  18. DS_FusionNet: Dynamic Dual-Stream Fusion with Bidirectional Knowledge Distillation for Plant Disease RecognitionKnowledge distillation → Detection and dense prediction distillation
  19. Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question DecompositionLLM reasoning → Prompting and chain-of-thought reasoning +1
  20. Towards Understanding the Nature of Attention with Low-Rank Sparse DecompositionMechanistic interpretability → Circuits and mechanistic analysis
  21. ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step VerificationLLM reasoning → Clinical and biomedical applications
  22. Exploiting inter-agent coupling information for efficient reinforcement learning of cooperative LQRDeep reinforcement learning methods → RL for games and combinatorial optimization
  23. Domain-Agnostic Scalable AI Safety Ensuring FrameworkDeep reinforcement learning methods → Safe and constrained RL
  24. DYNAMAX: Dynamic computing for Transformers and Mamba based architecturesState-space sequence models (S4, Mamba) → Core SSM architectures for language +1
  25. Leveraging Generative AI Through Prompt Engineering and Rigorous Validation to Create Comprehensive Synthetic Datasets for AI Training in HealthcareSynthetic data and self-improvement for LLMs → Medical synthetic data and agents
  26. When Testing AI Tests Us: Safeguarding Mental Health on the Digital FrontlinesLLM safety and security → Prompt injection and agent security
  27. CBM-RAG: Demonstrating Enhanced Interpretability in Radiology Report Generation with Multi-Agent RAG and Concept Bottleneck ModelsRetrieval-augmented generation → Medical and biomedical RAG
  28. Return Capping: Sample-Efficient CVaR Policy Gradient OptimisationDeep reinforcement learning methods → RL theory and sample complexity
  29. FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  30. Token-Efficient RL for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  31. GaussTrap: Stealthy Poisoning Attacks on 3D Gaussian Splatting for Targeted Scene ConfusionLLM safety and security → Backdoor and data poisoning attacks
  32. Ascendra: Dynamic Request Prioritization for Efficient LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  33. A Teacher-Student MPC-PPO Coupled Reinforcement Learning Framework for Winter Temperature Control of Solar Greenhouses in Northern ChinaDeep reinforcement learning methods → RL for energy, networks and operations
  34. SoccerDiffusion: Toward Learning End-to-End Humanoid Robot Soccer from Gameplay RecordingsDiffusion models → Diffusion and flow policies for robotics
  35. Integrating Human Feedback into a Reinforcement Learning-Based Framework for Adaptive User InterfacesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  36. Computational Reasoning of Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  37. JTreeformer: Graph-Transformer via Latent-Diffusion Model for Molecular GenerationDiffusion models → Flow matching, time series and science
  38. Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference CorruptionLLM reasoning → Reasoning for agents, planning and code
  39. DDPS: Discrete Diffusion Posterior Sampling for Paths in Layered GraphsDiffusion models → Flow matching, time series and science
  40. Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with TransformersLLM reasoning → Test-time compute and efficient thinking
  41. Intelligent Task Offloading in VANETs: A Hybrid AI-Driven Approach for Low-Latency and Energy EfficiencyDeep reinforcement learning methods → RL for energy, networks and operations
  42. UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and GranularitiesRetrieval-augmented generation → Multimodal RAG
  43. Beyond the Last Answer: Your Reasoning Trace Uncovers More than You ThinkLLM reasoning → Reasoning benchmarks and evaluation
  44. In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion TransformerDiffusion models → Image generation, text-to-image and editing
  45. Quantum-Enhanced Hybrid Reinforcement Learning Framework for Dynamic Path Planning in Autonomous SystemsDeep reinforcement learning methods → Quantum reinforcement learning
  46. SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic DataLLM reasoning → Spatial and embodied reasoning +2
  47. LDPoly: Latent Diffusion for Polygonal Road Outline Extraction in Large-Scale Topographic MappingDiffusion models → Diffusion and flow policies for robotics
  48. AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech GenerationDiffusion models → Audio, speech and music
  49. DiffusionRIR: Room Impulse Response Interpolation using Diffusion ModelsDiffusion models → Audio, speech and music
  50. ReasonIR: Training Retrievers for Reasoning TasksLLM reasoning → Knowledge- and tool-augmented reasoning
  51. Independent Learning in Performative Markov Potential GamesDeep reinforcement learning methods → RL theory and sample complexity
  52. Reinforcement Learning for Reasoning in Large Language Models with One Training ExampleLLM reasoning → Reinforcement learning for reasoning
  53. TriniMark: A Robust Generative Speech Watermarking Method for Trinity-Level TraceabilityDiffusion models → Robustness, privacy and adversarial aspects +1
  54. PRISM: Projection-based Reward Integration for Scene-Aware Real-to-Sim-to-Real Transfer with Few DemonstrationsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  55. Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  56. MambaMoE: Mixture-of-Spectral-Spatial-Experts State Space Model for Hyperspectral Image ClassificationMixture-of-experts → Vision mixture-of-experts +1
  57. MuRAL: A Multi-Resident Ambient Sensor Dataset Annotated with Natural Language for Activities of Daily LivingLLM reasoning → Spatial and embodied reasoning
  58. Token-Efficient Prompt Injection Attack: Provoking Cessation in LLM Reasoning via Adaptive Token CompressionLLM reasoning → Reasoning for agents, planning and code +2
  59. Group Relative Knowledge Distillation: Learning from Teacher's Relational Inductive BiasKnowledge distillation → General knowledge distillation methods
  60. Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed InstructionLLM safety and security → Prompt injection and agent security
  61. The Estimation of Continual Causal Effect for Dataset Shifting StreamsKnowledge distillation → General knowledge distillation methods
  62. Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object PerceptionMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  63. A Survey on GUI Agents with Foundation Models Enhanced by Reinforcement LearningLLM agents and tool use → GUI and mobile agents +1
  64. TAMO: Fine-Grained Root Cause Analysis via Tool-Assisted LLM Agent with Multi-Modality Observation Data in Cloud-Native SystemsLLM agents and tool use → Software engineering coding agents
  65. Search-Based Interaction For Conversation Recommendation via Generative Reward Model Based Simulated UserLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  66. Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative DecodingEfficient LLM inference and serving → Diffusion LLM and MoE inference
  67. FT-MoE: Sustainable-learning Mixture of Experts for Fault-Tolerant ComputingMixture-of-experts → Efficient MoE training and inference systems
  68. Head-Tail-Aware KL Divergence in Knowledge Distillation for Spiking Neural NetworksKnowledge distillation → Distillation for spiking neural networks
  69. ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative RefinementRetrieval-augmented generation → RAG for code +1
  70. RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function LibraryLLM reasoning → Mathematical reasoning +1
  71. kAgent: An execution-guided crash resolution agent for the Linux kernelLLM agents and tool use → Software engineering coding agents
  72. ADiff4TPP: Asynchronous Diffusion Models for Temporal Point ProcessesDiffusion models → Flow matching, time series and science
  73. When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation SystemsLLM safety and security → Vision-language and text-to-image safety
  74. PRISM-DP: Spatial Pose-based Observations for Diffusion-Policies via Segmentation, Mesh Generation, and Pose TrackingDiffusion models → Diffusion and flow policies for robotics
  75. CarbonCall: Sustainability-Aware Function Calling for Large Language Models on Edge DevicesLLM agents and tool use → General LLM agent frameworks and benchmarks
  76. MicarVLMoE: A Modern Gated Cross-Aligned Vision-Language Mixture of Experts Model for Medical Image Captioning and Report GenerationMixture-of-experts → Medical and biomedical MoE
  77. Towards Flow-Matching-based TTS without Classifier-Free GuidanceDiffusion models → Audio, speech and music
  78. Decentralized AI-driven IoT Architecture for Privacy-Preserving and Latency-Optimized Healthcare in Pandemic and Critical Care Scenarios
  79. Unveiling the Underwater World: CLIP Perception Model-Guided Underwater Image Enhancement
  80. Spatiotemporal Emotional Synchrony in Dyadic Interactions: The Role of Speech Conditions in Facial and Vocal Affective Alignment
  81. An Optimized Evacuation Plan for an Active-Shooter Situation Constrained by Network Capacity
  82. Blockbuster, Part 1: Block-level AI Operator Fusion
  83. AI-Based Crypto Tokens: The Illusion of Decentralized AI?
  84. DeltaDPD: Exploiting Dynamic Temporal Sparsity in Recurrent Neural Networks for Energy-Efficient Wideband Digital Predistortion
  85. An Early Warning Model for Forced Displacement
  86. Data extraction and processing methods to aid the study of driving behaviors at intersections in naturalistic driving
  87. Out-of-Distribution Detection in Heterogeneous Graphs via Energy Propagation
  88. Floating Car Observers in Intelligent Transportation Systems: Detection Modeling and Temporal Insights
  89. Feature Staleness Aware Incremental Learning for CTR Prediction
  90. Explainable AI for Correct Root Cause Analysis of Product Quality in Injection Moulding
  91. Leveraging Depth Maps and Attention Mechanisms for Enhanced Image Inpainting
  92. Unconstrained Large-scale 3D Reconstruction and Rendering across Altitudes
  93. ROSA: A Knowledge-based Solution for Robot Self-Adaptation
  94. Convolutional Autoencoders for Data Compression and Anomaly Detection in Small Satellite Technologies
  95. Can a Quantum Support Vector Machine algorithm be utilized to identify Key Biomarkers from Multi-Omics data of COVID19 patients?
  96. A Framework to Assess the Persuasion Risks Large Language Model Chatbots Pose to Democratic Societies
  97. Linguistic Complexity and Socio-cultural Patterns in Hip-Hop Lyrics
  98. Improving Phishing Email Detection Performance of Small Large Language Models
  99. From Attention to Atoms: Spectral Dictionary Learning for Fast, Interpretable Language Models
  100. Gradient Attention Map Based Verification of Deep Convolutional Neural Networks with Application to X-ray Image Datasets
All 301
  1. MemeBLIP2: A novel lightweight multimodal system to detect harmful memes
  2. Theoretical Foundations for Semantic Cognition in Artificial Intelligence
  3. Pretraining Large Brain Language Model for Active BCI: Silent Speech
  4. A Cost-Effective LLM-based Approach to Identify Wildlife Trafficking in Online Marketplaces
  5. Generalised Label-free Artefact Cleaning for Real-time Medical Pulsatile Time Series
  6. FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphs
  7. Automatic Legal Writing Evaluation of LLMs
  8. Generate-then-Verify: Reconstructing Data from Limited Published Statistics
  9. Graph Synthetic Out-of-Distribution Exposure with Large Language Models
  10. Turning Up the Heat: Assessing 2-m Temperature Forecast Errors in AI Weather Prediction Models During Heat Waves
  11. ISS-Geo142: A Benchmark for Geolocating Astronaut Photography from the International Space Station
  12. Small or Large? Zero-Shot or Finetuned? Guiding Language Model Choice for Specialized Applications in Healthcare
  13. Artificial Intelligence for Personalized Prediction of Alzheimer's Disease Progression: A Survey of Methods, Data Challenges, and Future Directions
  14. Light Weight CNN for classification of Brain Tumors from MRI Images
  15. LIFT: LLM-Based Pragma Insertion for HLS via GNN Supervised Fine-Tuning
  16. GLIP-OOD: Zero-Shot Graph OOD Detection with Graph Foundation Model
  17. AffectEval: A Modular and Customizable Framework for Affective Computing
  18. Federated One-Shot Learning with Data Privacy and Objective-Hiding
  19. Efficient LLMs with AMP: Attention Heads and MLP Pruning
  20. Dance Style Recognition Using Laban Movement Analysis
  21. Detecting Manipulated Contents Using Knowledge-Grounded Inference
  22. Evaluation and Verification of Physics-Informed Neural Models of the Grad-Shafranov Equation
  23. Emotion Recognition in Contemporary Dance Performances Using Laban Movement Analysis
  24. SMOGAN: Synthetic Minority Oversampling with GAN Refinement for Imbalanced Regression
  25. Legilimens: Performant Video Analytics on the System-on-Chip Edge
  26. QAOA Parameter Transferability for Maximum Independent Set using Graph Attention Networks
  27. LLM Enhancer: Merged Approach using Vector Embedding for Reducing Large Language Model Hallucinations with External Knowledge
  28. A Formalism for Optimal Search with Dynamic Heuristics (Extended Version)
  29. A Hybrid Mixture of t-Factor Analyzers for Clustering High-dimensional Data
  30. Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts
  31. A Survey on Parameter-Efficient Fine-Tuning for Foundation Models in Federated Learning
  32. On the Potential of Large Language Models to Solve Semantics-Aware Process Mining Tasks
  33. R^2VFL: A Robust Random Vector Functional Link Network with Huber-Weighted Framework
  34. GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D Reconstruction
  35. A Brief Review for Compression and Transfer Learning Techniques in DeepFake Detection
  36. Frequency Feature Fusion Graph Network For Depression Diagnosis Via fNIRS
  37. A Hamiltonian Higher-Order Elasticity Framework for Dynamic Diagnostics(2HOED)
  38. Modeling and Performance Analysis for Semantic Communications Based on Empirical Results
  39. FFCBA: Feature-based Full-target Clean-label Backdoor Attacks
  40. SFIBA: Spatial-based Full-target Invisible Backdoor Attacks
  41. Phishing URL Detection using Bi-LSTM
  42. Multi-Agent Reinforcement Learning for Resources Allocation Optimization: A Survey
  43. Model Connectomes: A Generational Approach to Data-Efficient Language Models
  44. X-Fusion: Introducing New Modality to Frozen Large Language Models
  45. Hubs and Spokes Learning: Efficient and Scalable Collaborative Machine Learning
  46. ACE: A Security Architecture for LLM-Integrated App Systems
  47. LTLf Adaptive Synthesis for Multi-Tier Goals in Nondeterministic Domains
  48. Provably faster randomized and quantum algorithms for k-means clustering via uniform sampling
  49. Jekyll-and-Hyde Tipping Point in an AI's Behavior
  50. Equivariant non-linear maps for neural networks on homogeneous spaces
  51. SetKE: Knowledge Editing for Knowledge Elements Overlap
  52. SVD Based Least Squares for X-Ray Pneumonia Classification Using Deep Features
  53. Softpick: No Attention Sink, No Massive Activations with Rectified Softmax
  54. OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification
  55. Information Gravity: A Field-Theoretic Model for Token Selection in Large Language Models
  56. Deep Learning Characterizes Depression and Suicidal Ideation from Eye Movements
  57. Scenario-based Compositional Verification of Autonomous Systems with Neural Perception
  58. Energy-Based Coarse-Graining in Molecular Dynamics: A Flow-Based Framework without Data
  59. Improvements of Dark Experience Replay and Reservoir Sampling towards Better Balance between Consolidation and Plasticity
  60. End-to-end Audio Deepfake Detection from RAW Waveforms: a RawNet-Based Approach with Cross-Dataset Evaluation
  61. Statistical and Predictive Analysis to Identify Risk Factors and Effects of Post COVID-19 Syndrome
  62. MOSIC: Model-Agnostic Optimal Subgroup Identification with Multi-Constraint for Improved Reliability
  63. A Giant-Step Baby-Step Classifier For Scalable and Real-Time Anomaly Detection In Industrial Control Systems and Water Treatment Systems
  64. Dual Explanations via Subgraph Matching for Malware Detection
  65. When Should AI Follow? Task Structure and Joint Adaptation by Human and AI Agents
  66. Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers
  67. Evaluating Generative Models for Tabular Data: Novel Metrics and Benchmarking
  68. Does Feedback Help in Bandits with Arm Erasures?
  69. Guessing Efficiently for Constrained Subspace Approximation
  70. The Leaderboard Illusion
  71. Preference-centric Bandits: Optimality of Mixtures and Regret-efficient Algorithms
  72. FLIM-based Salient Object Detection Networks with Adaptive Decoders
  73. Quantifying the Noise of Structural Perturbations on Graph Adversarial Attacks
  74. AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detection
  75. Tabular Data Adapters: Improving Outlier Detection for Unlabeled Private Data
  76. X-Cross: Dynamic Integration of Language Models for Cross-Domain Sequential Recommendation
  77. Towards Easy and Realistic Network Infrastructure Testing for Large-scale Machine Learning
  78. Fostering Self-Directed Growth with Generative AI: Toward a New Learning Analytics Framework
  79. JaccDiv: A Metric and Benchmark for Quantifying Diversity of Generated Marketing Text in the Music Industry
  80. Mitigating the Structural Bias in Graph Adversarial Defenses
  81. Disjunctive and Conjunctive Normal Form Explanations of Clusters Using Auxiliary Information
  82. Universal language model with the intervention of quantum theory
  83. RadSAM: Segmenting 3D radiological images with a 2D promptable model
  84. CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation
  85. Hybrid quantum recurrent neural network for remaining useful life prediction of turbofan engines
  86. An approach to melodic segmentation and classification based on filtering with the Haar-wavelet
  87. The When and How of Target Variable Transformations
  88. Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretraining
  89. Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges
  90. Partitioned Memory Storage Inspired Few-Shot Class-Incremental learning
  91. Q-Fusion: Diffusing Quantum Circuits
  92. Evaluating Effects of Augmented SELFIES for Molecular Understanding Using QK-LSTM
  93. Approximate Lifted Model Construction
  94. Using LLMs in Generating Design Rationale for Software Architecture Decisions
  95. ECOSoundSet: a finely annotated dataset for the automated acoustic identification of Orthoptera and Cicadidae in North, Central and temperate Western Europe
  96. Graph-Based Fault Diagnosis for Rotating Machinery: Adaptive Segmentation and Structural Feature Integration
  97. In defence of post-hoc explanations in medical AI
  98. Event-based Optical Marker Systems: A survey
  99. Unsupervised Surrogate Anomaly Detection
  100. Enhancing Vulnerability Reports with Automated and Augmented Description Summarization
  101. Learning a General Model: Folding Clothing with Topological Dynamics
  102. BrightCookies at SemEval-2025 Task 9: Exploring Data Augmentation for Food Hazard Classification
  103. Can LLMs Detect Intrinsic Hallucinations in Paraphrasing and Machine Translation?
  104. What's Wrong with Your Synthetic Tabular Data? Using Explainable AI to Evaluate Generative Models
  105. Efficient Listener: Dyadic Facial Motion Synthesis via Action Diffusion
  106. OG-HFYOLO :Orientation gradient guidance and heterogeneous feature fusion for deformation table cell instance segmentation
  107. Are Information Retrieval Approaches Good at Harmonising Longitudinal Survey Questions in Social Science?
  108. Non-native Children's Automatic Speech Assessment Challenge (NOCASA)
  109. Occlusion-aware Driver Monitoring System using the Driver Monitoring Dataset
  110. The Limits of AI Explainability: An Algorithmic Information Theory Approach
  111. CoCo-Bench: A Comprehensive Code Benchmark For Multi-task Large Language Model Evaluation
  112. FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection
  113. Advance Fake Video Detection via Vision Transformers
  114. A Generative-AI-Driven Claim Retrieval System Capable of Detecting and Retrieving Claims from Social Media Platforms in Multiple Languages
  115. Explanations Go Linear: Post-hoc Explainability for Tabular Data with Interpretable Meta-Encoding
  116. SFi-Former: Sparse Flow Induced Attention for Graph Transformer
  117. TrueFake: A Real World Case Dataset of Last Generation Fake Images also Shared on Social Networks
  118. Image deidentification in the XNAT ecosystem: use cases and solutions
  119. Federated learning, ethics, and the double black box problem in medical AI
  120. Learning and Generalization with Mixture Data
  121. RuleKit 2: Faster and simpler rule learning
  122. Combatting Dimensional Collapse in LLM Pre-Training Data via Diversified File Selection
  123. Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination
  124. Decision-centric fairness: Evaluation and optimization for resource allocation problems
  125. Bridging the Generalisation Gap: Synthetic Data Generation for Multi-Site Clinical Model Validation
  126. On Stochastic Rounding with Few Random Bits
  127. Cognitive maps are generative programs
  128. PaRT: Enhancing Proactive Social Chatbots with Personalized Real-Time Retrieval
  129. Data Driven Deep Learning for Correcting Global Climate Model Projections of SST and DSL in the Bay of Bengal
  130. Sobolev norm inconsistency of kernel interpolation
  131. The Hidden Risks of LLM-Generated Web Application Code: A Security-Centric Evaluation of Code Generation Capabilities in Large Language Models
  132. Information Retrieval in the Age of Generative AI: The RGB Model
  133. WenyanGPT: A Large Language Model for Classical Chinese Tasks
  134. EfficientHuman: Efficient Training and Reconstruction of Moving Human using Articulated 2D Gaussian
  135. TF1-EN-3M: Three Million Synthetic Moral Fables for Training Small, Open Language Models
  136. Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection
  137. PartHOI: Part-based Hand-Object Interaction Transfer via Generalized Cylinders
  138. Hydra: Marker-Free RGB-D Hand-Eye Calibration
  139. ClonEval: An Open Voice Cloning Benchmark
  140. Representation Learning Preserving Ignorability and Covariate Matching for Treatment Effects
  141. Digital Shielding for Cross-Domain Wi-Fi Signal Adaptation using Relativistic Average Generative Adversarial Network
  142. Balanced Online Class-Incremental Learning via Dual Classifiers
  143. Generate more than one child in your co-evolutionary semi-supervised learning GAN
  144. BrAIcht, a theatrical agent that speaks like Bertolt Brecht's characters
  145. Revisiting the MIMIC-IV Benchmark: Experiments Using Language Models for Electronic Health Records
  146. Autoencoder Models for Point Cloud Environmental Synthesis from WiFi Channel State Information: A Preliminary Study
  147. DeeP-Mod: Deep Dynamic Programming based Environment Modelling using Feature Extraction
  148. Beyond the Horizon: Decoupling Multi-View UAV Action Recognition via Partial Order Transfer
  149. Adaptive Replication Strategies in Trust-Region-Based Bayesian Optimization of Stochastic Functions
  150. Breaking Down Monocular Ambiguity: Exploiting Temporal Evolution for 3D Lane Detection
  151. Wavelet-Filtering of Symbolic Music Representations for Folk Tune Segmentation and Classification
  152. SteelBlastQC: Shot-blasted Steel Surface Dataset with Interpretable Detection of Surface Defects
  153. Quality-factor inspired deep neural network solver for solving inverse scattering problems
  154. SAM-Guided Robust Representation Learning for One-Shot 3D Medical Image Segmentation
  155. UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation
  156. Style-Adaptive Detection Transformer for Single-Source Domain Generalized Object Detection
  157. Large-scale visual SLAM for in-the-wild videos
  158. Enhancing LLM Language Adaption through Cross-lingual In-Context Pre-training
  159. Full-field surrogate modeling of cardiac function encoding geometric variability
  160. Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models
  161. LMME3DHF: Benchmarking and Evaluating Multimodal 3D Human Face Generation with LMMs
  162. LymphAtlas- A Unified Multimodal Lymphoma Imaging Repository Delivering AI-Enhanced Diagnostic Insight
  163. Enhancing News Recommendation with Hierarchical LLM Prompting
  164. Team ACK at SemEval-2025 Task 2: Beyond Word-for-Word Machine Translation for English-Korean Pairs
  165. APG-MOS: Auditory Perception Guided-MOS Predictor for Synthetic Speech
  166. On Psychology of AI -- Does Primacy Effect Affect ChatGPT and Other LLMs?
  167. Multidimensional precipitation index prediction based on CNN-LSTM hybrid framework
  168. PixelHacker: Image Inpainting with Structural and Semantic Consistency
  169. GaLore 2: Large-Scale LLM Pre-Training by Gradient Low-Rank Projection
  170. AI Assisted Cervical Cancer Screening for Cytology Samples in Developing Countries
  171. Learning Laplacian Positional Encodings for Heterophilous Graphs
  172. Understanding GNNs and Homophily in Dynamic Node Classification
  173. Plant Disease Detection through Multimodal Large Language Models and Convolutional Neural Networks
  174. GarmentX: Autoregressive Parametric Representations for High-Fidelity 3D Garment Generation
  175. FourierSpecNet: Neural Collision Operator Approximation Inspired by the Fourier Spectral Method for Solving the Boltzmann Equation
  176. Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs
  177. SCOPE-MRI: Bankart Lesion Detection as a Case Study in Data Curation and Deep Learning for Challenging Diagnoses
  178. Creating Your Editable 3D Photorealistic Avatar with Tetrahedron-constrained Gaussian Splatting
  179. Nonlinear Computation with Linear Optics via Source-Position Encoding
  180. Evolution of Gaussians in the Hellinger-Kantorovich-Boltzmann gradient flow
  181. Partial Answer of How Transformers Learn Automata
  182. Manifold Clustering with Schatten p-norm Maximization
  183. FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding
  184. Neural Stereo Video Compression with Hybrid Disparity Compensation
  185. GSFeatLoc: Visual Localization Using Feature Correspondence on 3D Gaussian Splatting
  186. Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views
  187. Generative Learning for Slow Manifolds and Bifurcation Diagrams
  188. DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translation
  189. AKIBoards: A Structure-Following Multiagent System for Predicting Acute Kidney Injury
  190. TTTFusion: A Test-Time Training-Based Strategy for Multimodal Medical Image Fusion in Surgical Robots
  191. Automated Unit Test Case Generation: A Systematic Literature Review
  192. What Causes Knowledge Loss in Multilingual Language Models?
  193. Local Prompt Optimization
  194. Sparse mixed linear modeling with anchor-based guidance for high-entropy alloy discovery
  195. Narrative-Centered Emotional Reflection: An Early Prototype for AI-Supported Emotional Self-Reflection
  196. A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks
  197. DRO: Doppler-Aware Direct Radar Odometry
  198. Labeling Case Similarity based on Co-Citation of Legal Articles in Judgment Documents with Empirical Dispute-Based Evaluation
  199. Fine-Grained Classification: Connecting Metadata via Cross-Contrastive Pre-Training
  200. Bayesian Experimental Design for Model Discrepancy Calibration: An Auto-Differentiable Ensemble Kalman Inversion Approach
  201. Leveraging Action Relational Structures for Integrated Learning and Planning