mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 22 Mar 2026

214 papers

  1. Cross-Family Speculative Decoding for Polish Language Models on Apple~Silicon: An Empirical Evaluation of Bielik~11B with UAG-Extended MLX-LMEfficient LLM inference and serving → Speculative decoding
  2. Knowledge Packs: Zero-Token Knowledge Delivery via KV Cache InjectionEfficient LLM inference and serving → KV cache optimization
  3. SleepVLM: A Rule-Grounded Vision-Language Model for Auditable Sleep StagingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  4. Demystifying Low-Rank Knowledge Distillation in Large Language Models: Convergence, Generalization, and Information-Theoretic GuaranteesKnowledge distillation → Knowledge distillation for LLMs
  5. WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning ImprovementLLM reasoning → Reinforcement learning for reasoning +1
  6. Deliberative multi-agent large language models improve clinical reasoning in ophthalmologyLLM agents and tool use → Medical and scientific domain agents
  7. KG-Hopper: Empowering Compact Open LLMs with Knowledge Graph Reasoning via Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning
  8. DomAgent: Leveraging Knowledge Graphs and Case-Based Reasoning for Domain-Specific Code GenerationLLM reasoning → Reasoning for agents, planning and code
  9. Uncertainty-Aware Knowledge Distillation for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  10. Mechanisms of Introspective AwarenessMechanistic interpretability → Activation steering methods
  11. Mitigating Objectness Bias and Region-to-Text Misalignment for Open-Vocabulary Panoptic SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  12. PivotRL: High Accuracy Agentic Post-Training at Low Compute CostLLM agents and tool use → Reinforcement learning for LLM agents
  13. A transformer architecture alteration to incentivise externalised reasoningLLM reasoning → Test-time compute and efficient thinking
  14. Relax Forcing: Relaxed KV-Memory for Consistent Long Video GenerationDiffusion models → Video generation
  15. TIDE: Token-Informed Depth Execution for Per-Token Early Exit in LLM InferenceEfficient LLM inference and serving → Early exit and edge inference
  16. AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward LearningLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  17. Benchmarking Bengali Dialectal Bias: A Multi-Stage Framework Integrating RAG-Based Translation and Human-Augmented RLAIFLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  18. Personality-Driven Student Agent-Based Modeling in Mathematics Education: How Well Do Student Agents Align with Human Learners?LLM agents and tool use → Educational agents and math problem solving
  19. AgentHER: Hindsight Experience Replay for LLM Agent Trajectory RelabelingLLM agents and tool use → Software engineering coding agents
  20. The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router ProjectLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  21. Beyond Memorization: Distinguishing Between Pattern-Based and Epistemic Reasoning in LLMs Using Epistemic PuzzlesLLM reasoning → Reasoning benchmarks and evaluation
  22. Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence RedistributionDiffusion models → Diffusion foundations and sampling
  23. The AI Scientific Community: Agentic Virtual Lab SwarmsLLM agents and tool use → Web, search, and research agents
  24. Generalized Discrete Diffusion from SnapshotsDiffusion models → Diffusion foundations and sampling
  25. RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action ModelsLLM reasoning → Spatial and embodied reasoning +1
  26. ARYA: A Physics-Constrained Composable & Deterministic World Model ArchitectureWorld models → World models for language agents +1
  27. COINBench: Moving Beyond Individual Perspectives to Collective Intent UnderstandingLLM reasoning → Reasoning benchmarks and evaluation
  28. Improving Coherence and Persistence in Agentic AI for System OptimizationLLM agents and tool use → General LLM agent frameworks and benchmarks
  29. Active Inference Agency Formalization, Metrics, and Convergence AssessmentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  30. HELIX: Scaling Raw Audio Understanding with Hybrid Mamba-Attention Beyond the Quadratic LimitState-space sequence models (S4, Mamba) → Speech and audio SSMs
  31. FluidWorld: Reaction-Diffusion Dynamics as a Predictive Substrate for World ModelsWorld models → Latent predictive world models
  32. Enhancing reasoning accuracy in large language models during inference timeLLM reasoning → Test-time compute and efficient thinking
  33. DeepXplain: XAI-Guided Autonomous Defense Against Multi-Stage APT CampaignsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  34. Closed-form conditional diffusion models for data assimilationDiffusion models → Flow matching, time series and science
  35. When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
  36. When the Chain Breaks: Interactive Diagnosis of LLM Chain-of-Thought Reasoning ErrorsLLM reasoning → Prompting and chain-of-thought reasoning
  37. Aggregation Alignment for Federated Learning with Mixture-of-Experts under Data HeterogeneityMixture-of-experts → Federated mixture-of-experts
  38. The Library Theorem: How External Organization Governs Agentic Reasoning CapacityLLM reasoning → Knowledge- and tool-augmented reasoning +1
  39. CALVO: Improve Serving Efficiency for LLM Inferences with Intense Network DemandsEfficient LLM inference and serving → Serving systems and request scheduling
  40. Graph of States: Solving Abductive Tasks with Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  41. QMoP: Query Guided Mixture-of-Projector for Efficient Visual Token CompressionMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  42. JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution OptimizationDiffusion models → Robustness, privacy and adversarial aspects +1
  43. LLM-based Automated Architecture View Generation: Where Are We Now?LLM agents and tool use → Software engineering coding agents
  44. Prompt replay: speeding up grpo with on-policy reuse of high-signal promptsLLM reasoning → Reinforcement learning for reasoning
  45. Reward Sharpness-Aware Fine-Tuning for Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
  46. Rethinking Plasticity in Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  47. Revisiting Tree Search for LLMs: Gumbel and Sequential Halving for Budget-Scalable ReasoningLLM reasoning → Test-time compute and efficient thinking
  48. ORACLE: Optimizing Reasoning Abilities of Large Language Models via Constraint-Led Synthetic Data ElicitationLLM reasoning → Reasoning benchmarks and evaluation +1
  49. Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual CuesDeep reinforcement learning methods → RL with diffusion and flow models
  50. MS-CustomNet: Controllable Multi-Subject Customization with Hierarchical Relational SemanticsDiffusion models → Image generation, text-to-image and editing
  51. ReDiffuse: Rotation Equivariant Diffusion Model for Multi-focus Image FusionDiffusion models → Image generation, text-to-image and editing
  52. VisFly-Lab: Unified Differentiable Framework for First-Order Reinforcement Learning of Quadrotor ControlDeep reinforcement learning methods → RL for robot navigation and UAV control
  53. CVT-Bench: Probing Spatial-State Integrity through Counterfactual Viewpoint TransformationsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  54. ResPrune: Text-Conditioned Subspace Reconstruction for Visual Token Pruning in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  55. CounterScene: Counterfactual Causal Reasoning in Generative World Models for Safety-Critical Closed-Loop EvaluationWorld models → Latent predictive world models +1
  56. ReasonScaffold: A Scaffolded Reasoning-based Annotation Protocol for Human-AI Co-AnnotationLLM reasoning → Audio-language model reasoning
  57. Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  58. CoVFT: Context-aware Visual Fine-tuning for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  59. NoOVD: Novel Category Discovery and Embedding for Open-Vocabulary Object DetectionKnowledge distillation → Detection and dense prediction distillation
  60. LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement LearningLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  61. Single-Eye View: Monocular Real-time Perception Package for Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
  62. LPNSR: Learnable Noise Prediction for Diffusion-Based Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  63. KLDrive: Fine-Grained 3D Scene Reasoning for Autonomous Driving based on Knowledge GraphLLM reasoning → Chain-of-thought reasoning for driving +1
  64. SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent CollaborationLLM agents and tool use → Agent threats, guardrails and governance
  65. Dreaming the Unseen: World Model-regularized Diffusion Policy for Out-of-Distribution RobustnessWorld models → World models for navigation +1
  66. Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPOLLM reasoning → Reinforcement learning for reasoning
  67. CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution GraphsMechanistic interpretability → Knowledge and representations inside LLMs
  68. SkinCLIP-VL: Consistency-Aware Vision-Language Learning for Multimodal Skin Cancer DiagnosisMultimodal LLMs / vision-language models → Medical vision-language models
  69. When Does Content-Based Routing Work? Representation Requirements for Selective Attention in Hybrid Sequence ModelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
  70. Interpreting the Synchronization Gap: The Hidden Mechanism Inside Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  71. AutoMOOSE: An Agentic AI for Autonomous Phase-Field SimulationLLM agents and tool use → Medical and scientific domain agents
  72. Consistent but Dangerous: Per-Sample Safety Classification Reveals False Reliability in Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  73. LLM-Based Intelligent Notification Composition: From Static Personalization to Context-Aware Persuasive Messaging
  74. WorkflowGen:an adaptive workflow generation mechanism driven by trajectory experience
  75. Explainable AML Triage with LLMs: Evidence Retrieval and Counterfactual Checks
  76. Why AI Readiness Is an Organizational Learning Problem, Not a Technology Purchase
  77. Talk, Walk, and Market Response: Multimodal Measurement of AI Washing and Its Capital Market Consequences in China
  78. Decoding AI Tutor Effects for Educational Measurement: Temporal, Multi-Outcome, and Behavior-Cognitive Analysis
  79. Compressed-Sensing-Guided, Inference-Aware Structured Reduction for Large Language Models
  80. 3D Multi-View Stylization with Pose-Free Correspondences Matching for Robust 3D Geometry Preservation
  81. CIPHER: Conformer-based Inference of Phonemes from High-density EEG
  82. When and Where: A Model Hippocampal Network Unifies Formation of Time Cells and Place Cells
  83. Quantum Fuzzy Sets Revisited: Density Matrices, Decoherence, and the Q-Matrix Framework
  84. Relational graph-driven differential denoising and diffusion attention fusion for multimodal conversation emotion recognition
  85. STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems
  86. Bridging neuroscience and AI: adaptive, culturally sensitive technologies transforming aphasia rehabilitation
  87. Session Risk Memory (SRM): Temporal Authorization for Deterministic Pre-Execution Safety Gates
  88. Learning Safely Without Knowing the World:COMPASS-Hedge
  89. Intelligence Inertia: Physical Isomorphism and Applications
  90. First-Mover Bias in Gradient Boosting Explanations: Mechanism, Detection, and Resolution
  91. Dynamic Fusion-Aware Graph Convolutional Neural Network for Multimodal Emotion Recognition in Conversations
  92. Safety as Computation: Certified Answer Reuse via Capability Closure in Task-Oriented Dialogue
  93. LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study
  94. PROMPT2BOX:Improving LLM Weakness Discovery and Specificity Estimation by Uncovering Entailment Structure among Prompts
  95. Pooling and Semantic Shift: The Fundamental Challenges in Long Text Embedding and Retrieval
  96. PAS3R: Pose-Adaptive Streaming 3D Reconstruction for Long Video Sequences
  97. Behavioural feasible set: Value alignment constraints on AI decision support
  98. Image-Based Structural Analysis Using Computer Vision and LLMs: PhotoBeamSolver
  99. HyReach: Vision-Guided Hybrid Manipulator Reaching in Unseen Cluttered Environments
  100. Is the future of AI green? What can innovation diffusion models say about generative AI's environmental impact?
All 214
  1. Efficient Fine-Tuning Methods for Portuguese Question Answering: A Comparative Study of PEFT on BERTimbau and Exploratory Evaluation of Generative LLMs
  2. Silent Commitment Failure in Instruction-Tuned Language Models: Evidence of Governability Divergence Across Architectures
  3. Fingerprinting Deep Neural Networks for Ownership Protection: An Analytical Approach
  4. Multi-Perspective LLM Annotations for Valid Analyses in Subjective Tasks
  5. The Myhill-Nerode Theorem for Bounded Interaction: Canonical Abstractions via Agent-Bounded Indistinguishability
  6. Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors
  7. A Generalised Exponentiated Gradient Approach to Enhance Fairness in Binary and Multi-class Classification Tasks
  8. Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models
  9. Knowledge Priors for Identity-Disentangled Open-Set Privacy-Preserving Video FER
  10. An InSAR Phase Unwrapping Framework for Large-scale and Complex Events
  11. HamVision: Hamiltonian Dynamics as Inductive Bias for Medical Image Analysis
  12. Constrained Online Convex Optimization with Memory and Predictions
  13. PLR: Plackett-Luce for Reordering In-Context Learning Examples
  14. Conspiracy Frame: a Semiotically-Driven Approach for Conspiracy Theories Detection
  15. FluidGaussian: Propagating Simulation-Based Uncertainty Toward Functionally-Intelligent 3D Reconstruction
  16. Respiratory Status Detection with Video Transformers
  17. TimeTox: An LLM-Based Pipeline for Automated Extraction of Time Toxicity from Clinical Trial Protocols
  18. EmoTaG: Emotion-Aware Talking Head Synthesis on Gaussian Splatting with Few-Shot Personalization
  19. AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search
  20. FinRL-X: An AI-Native Modular Infrastructure for Quantitative Trading
  21. KHMP: Frequency-Domain Kalman Refinement for High-Fidelity Human Motion Prediction
  22. B-jet Tagging Using a Hybrid Edge Convolution and Transformer Architecture
  23. Which Alert Removals are Beneficial?
  24. Stream separation improves Bregman conditioning in transformers
  25. Test-Time Adaptation via Cache Personalization for Facial Expression Recognition in Videos
  26. Direct Interval Propagation Methods using Neural-Network Surrogates for Uncertainty Quantification in Physical Systems Surrogate Model
  27. Privacy-Preserving Federated Action Recognition via Differentially Private Selective Tuning and Efficient Communication
  28. F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting
  29. The Average Relative Entropy and Transpilation Depth determines the noise robustness in Variational Quantum Classifiers
  30. Identity-Consistent Video Generation under Large Facial-Angle Variations
  31. More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection
  32. Text-Image Conditioned 3D Generation
  33. Focus on Background: Exploring SAM's Potential in Few-shot Medical Image Segmentation with Background-centric Prompting
  34. Sonny: Breaking the Compute Wall in Medium-Range Weather Forecasting
  35. Fusing Memory and Attention: A study on LSTM, Transformer and Hybrid Architectures for Symbolic Music Generation
  36. WARBENCH: A Comprehensive Benchmark for Evaluating LLMs in Military Decision-Making
  37. Conversation Tree Architecture: A Structured Framework for Context-Aware Multi-Branch LLM Conversations
  38. Graph Fusion Across Languages using Large Language Models
  39. Accelerate Vector Diffusion Maps by Landmarks
  40. CornOrb: A Multimodal Dataset of Orbscan Corneal Topography and Clinical Annotations for Keratoconus Detection
  41. Amortized Variational Inference for Logistic Regression with Missing Covariates
  42. ConsRoute:Consistency-Aware Adaptive Query Routing for Cloud-Edge-Device Large Language Models
  43. Posterior-Calibrated Causal Circuits in Variational Autoencoders: Why Image-Domain Interpretability Fails on Tabular Data
  44. Domain Elastic Transform: Bayesian Function Registration for High-Dimensional Scientific Data
  45. Enhancing Brain Tumor Classification Using Vision Transformers with Colormap-Based Feature Representation on BRISC2025 Dataset
  46. DepthTCM: High Efficient Depth Compression via Physics-aware Transformer-CNN Mixed Architecture
  47. When Convenience Becomes Risk: A Semantic View of Under-Specification in Host-Acting Agents
  48. Plant Taxonomy Meets Plant Counting: A Fine-Grained, Taxonomic Dataset for Counting Hundreds of Plant Species
  49. Does AI Homogenize Student Thinking? A Multi-Dimensional Analysis of Structural Convergence in AI-Augmented Essays
  50. A Large-Scale Remote Sensing Dataset and VLM-based Algorithm for Fine-Grained Road Hierarchy Classification
  51. Reframing Long-Tailed Learning via Loss Landscape Geometry
  52. Positional Segmentor-Guided Counterfactual Fine-Tuning for Spatially Localized Image Synthesis
  53. Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows
  54. Boundary-Aware Instance Segmentation in Microscopy Imaging
  55. Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions
  56. Context Selection for Hypothesis and Statistical Evidence Extraction from Full-Text Scientific Articles
  57. DSCSNet: A Dynamic Sparse Compression Sensing Network for Closely-Spaced Infrared Small Target Unmixing
  58. On the Role of Batch Size in Stochastic Conditional Gradient Methods
  59. Architecture for Multi-Unmanned Aerial Vehicles based Autonomous Precision Agriculture Systems
  60. ALMAB-DC: Active Learning, Multi-Armed Bandits, and Distributed Computing for Sequential Experimental Design and Black-Box Optimization
  61. GIDE: Unlocking Diffusion LLMs for Precise Training-Free Image Editing
  62. Explainable Semantic Textual Similarity via Dissimilar Span Detection
  63. Entropy Alone is Insufficient for Safe Selective Prediction in LLMs
  64. Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation Models
  65. Model Evolution Under Zeroth-Order Optimization: A Neural Tangent Kernel Perspective
  66. Training-Free Instance-Aware 3D Scene Reconstruction and Diffusion-Based View Synthesis from Sparse Images
  67. Many Dialects, Many Languages, One Cultural Lens: Evaluating Multilingual VLMs for Bengali Culture Understanding Across Historically Linked Languages and Regional Dialects
  68. Beyond a Single Signal: SPECTREG2, A Unified MultiExpert Anomaly Detector for Unknown Unknowns
  69. Can LLMs Fool Graph Learning? Exploring Universal Adversarial Attacks on Text-Attributed Graphs
  70. Learning from Label Proportions with Dual-proportion Constraints
  71. TRACE: A Multi-Agent System for Autonomous Physical Reasoning for Seismology
  72. Emergent Formal Verification: How an Autonomous AI Ecosystem Independently Discovered SMT-Based Safety Across Six Domains
  73. NeSy-Edge: Neuro-Symbolic Trustworthy Self-Healing in the Computing Continuum
  74. Time-adaptive infinite-dimensional Gaussian process regression on manifolds
  75. Ontology-driven personalized information retrieval for XML documents
  76. One Pool Is Not Enough: Multi-Cluster Memory for Practical Test-Time Adaptation
  77. Anatomical Prior-Driven Framework for Autonomous Robotic Cardiac Ultrasound Standard View Acquisition
  78. LiFR-Seg: Anytime High-Frame-Rate Segmentation via Event-Guided Propagation
  79. Frequency Switching Mechanism for Parameter-E!cient Multi-Task Learning
  80. DMMRL: Disentangled Multi-Modal Representation Learning via Variational Autoencoders for Molecular Property Prediction
  81. Learning Progressive Adaptation for Multi-Modal Tracking
  82. Learning to Optimize Joint Source and RIS-assisted Channel Encoding for Multi-User Semantic Communication Systems
  83. Mixture of Chapters: Scaling Learnt Memory in Transformers
  84. Representation-Level Adversarial Regularization for Clinically Aligned Multitask Thyroid Ultrasound Assessment
  85. Stochastic approximation in non-markovian environments revisited
  86. DGRNet: Disagreement-Guided Refinement for Uncertainty-Aware Brain Tumor Segmentation
  87. ViCLSR: A Supervised Contrastive Learning Framework with Natural Language Inference for Natural Language Understanding Tasks
  88. Hierarchical Text-Guided Brain Tumor Segmentation via Sub-Region-Aware Prompts
  89. Assessing the Ability of Neural TTS Systems to Model Consonant-Induced F0 Perturbation
  90. SqueezeComposer: Temporal Speed-up is A Simple Trick for Long-form Music Composing
  91. CTFS : Collaborative Teacher Framework for Forward-Looking Sonar Image Semantic Segmentation with Extremely Limited Labels
  92. 2Xplat: Decoupling Geometry and Appearance Modeling for Feed-Forward 3D Gaussian Splatting
  93. Gradient Descent with Projection Finds Over-Parameterized Neural Networks for Learning Low-Degree Polynomials with Nearly Minimax Optimal Rate
  94. Semi-Supervised Learning with Balanced Deep Representation Distributions
  95. SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM
  96. Harmful Visual Content Manipulation Matters in Misinformation Detection Under Multimedia Scenarios
  97. A Two-stage Transformer Framework for Temporal Localization of Distracted Driver Behaviors
  98. When Minor Edits Matter: LLM-Driven Prompt Attack for Medical VLM Robustness in Ultrasound
  99. SpatialFly: Implicit 3D Prior-Guided Visual Reparameterization for Continuous UAV Vision-and-Language Navigation
  100. Confidence Freeze: Early Success Induces a Metastable Decoupling of Metacognition and Behaviour
  101. Statistical Learning for Latent Embedding Alignment with Application to Brain Encoding and Decoding
  102. Benchmarking Scientific Machine Learning Models for Air Quality Data
  103. Reading Between the Lines: How Electronic Nonverbal Cues shape Emotion Decoding
  104. Left Behind: Cross-Lingual Transfer as a Bridge for Low-Resource Languages in Large Language Models
  105. Fuel Consumption Prediction: A Comparative Analysis of Machine Learning Paradigms
  106. TabPFN Extensions for Interpretable Geotechnical Modelling
  107. Deep Attention-based Sequential Ensemble Learning for BLE-Based Indoor Localization in Care Facilities
  108. Training-Free Adaptive 360-degree Video Streaming via Semantic Potential Fields
  109. The Intelligent Disobedience Game: Formulating Disobedience in Stackelberg Games and Markov Decision Processes
  110. Long-Term Outlier Prediction Through Outlier Score Modeling
  111. Structural Sensitivity in Compressed Transformers: Relative Error Propagation and Layer Removal
  112. What Tracks Hard-Negative Transfer? A Study of Lexical and Semantic Signals
  113. Toward an automated science of the mind
  114. Joint Surrogate Learning of Objectives, Constraints, and Sensitivities for Efficient Multi-objective Optimization of Neural Dynamical Systems