mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 4 Nov 2024

337 papers

  1. QCG-Rerank: Chunks Graph Rerank with Query Expansion in Retrieval-Augmented LLMs for Tourism DomainRetrieval-augmented generation → RAG pipeline design and evaluation
  2. Benchmarking Vision, Language, & Action Models on Robotic Learning TasksVision-language-action models → Generalist VLA models and benchmarks
  3. Enhancing Table Representations with LLM-powered Synthetic Data GenerationSynthetic data and self-improvement for LLMs → Privacy-preserving tabular data synthesis
  4. RuAG: Learned-rule-augmented Generation for Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  5. Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language AttackMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  6. From Twitter to Reasoner: Understand Mobility Travel Modes and Sentiment Using Large Language ModelsLLM reasoning → Spatial and embodied reasoning
  7. Extracting Unlearned Information from LLMs with Activation SteeringLLM safety and security → Machine unlearning +1
  8. Learning to Assist Humans without Inferring RewardsDeep reinforcement learning methods → Deep RL algorithms and representations
  9. AdaProb: Efficient Machine Unlearning via Adaptive ProbabilityLLM safety and security → Machine unlearning
  10. TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for NetworkRetrieval-augmented generation → RAG robustness and adaptive retrieval
  11. Context-Informed Machine Translation of Manga using Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  12. MM-Embed: Universal Multimodal Retrieval with Multimodal LLMsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  13. TI-PREGO: Chain of Thought and In-Context Learning for Online Mistake Detection in PRocedural EGOcentric VideosLLM reasoning → Spatial and embodied reasoning
  14. Continual LLaVA: Continual Instruction Tuning in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  15. Dynamic Weight Adjusting Deep Q-Networks for Real-Time Environmental AdaptationDeep reinforcement learning methods → Deep RL algorithms and representations
  16. INQUIRE: A Natural World Text-to-Image Retrieval BenchmarkMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  17. What Goes Into a LM Acceptability Judgment? Rethinking the Impact of Frequency and LengthLLM reasoning → Reasoning benchmarks and evaluation
  18. Dr. SoW: Density Ratio of Strong-over-weak LLMs for Reducing the Cost of Human Annotation in Preference TuningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  19. Benchmarking XAI Explanations with Human-Aligned EvaluationsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  20. A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic StylesLLM agents and tool use → Social simulation and multi-agent debate
  21. Adaptive Caching for Faster Video Generation with Diffusion TransformersDiffusion models → Video generation
  22. Training-free Regional Prompting for Diffusion TransformersDiffusion models → Image generation, text-to-image and editing
  23. Attacking Vision-Language Computer Agents via Pop-upsLLM agents and tool use → Agent threats, guardrails and governance
  24. How Far is Video Generation from World Model: A Physical Law PerspectiveWorld models → Latent predictive world models
  25. DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot ExecutionLLM reasoning → Spatial and embodied reasoning +1
  26. Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  27. WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement LearningLLM agents and tool use → Web, search, and research agents +1
  28. Communicate Less, Synthesize the Rest: Latency-aware Intent-based Generative Semantic Multicasting with Diffusion ModelsDiffusion models → Diffusion for compression and wireless
  29. PPLLaVA: Varied Video Sequence Understanding With Prompt GuidanceEfficient LLM inference and serving → Visual token pruning in multimodal models
  30. LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph GenerationDiffusion models → Flow matching, time series and science
  31. On Targeted Manipulation and Deception when Optimizing LLMs for User FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  32. CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic EnvironmentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  33. Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D GenerationDiffusion models → 3D, point cloud and scene generation
  34. The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant UnitsLLM reasoning → Reasoning benchmarks and evaluation
  35. Combining Induction and Transduction for Abstract ReasoningLLM reasoning → Multimodal reasoning
  36. Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by TencentMixture-of-experts → MoE large language models
  37. Positive Experience Reflection for Agents in Interactive Text EnvironmentsLLM agents and tool use → Reinforcement learning for LLM agents
  38. One VLM to Keep it Learning: Generation and Balancing for Data-free Continual Visual Question AnsweringMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  39. Improving Steering Vectors by Targeting Sparse Autoencoder FeaturesMechanistic interpretability → SAE features and their applications
  40. Digi2Real: Bridging the Realism Gap in Synthetic Data Face Recognition via Foundation ModelsSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
  41. Adaptive Sparse Allocation with Mutual Choice & Feature Choice Sparse AutoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
  42. FedMoE-DA: Federated Mixture of Experts via Domain Aware Fine-grained AggregationMixture-of-experts → Federated mixture-of-experts
  43. Do Advanced Language Models Eliminate the Need for Prompt Engineering in Software Engineering?LLM reasoning → Reasoning for agents, planning and code
  44. GraphVL: Graph-Enhanced Semantic Modeling via Vision-Language Models for Generalized Class DiscoveryMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  45. Model Integrity when Unlearning with T2I Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  46. TableGPT2: A Large Multimodal Model with Tabular Data IntegrationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  47. Zero-Shot Voice Conversion via Content-Aware Timbre Ensemble and Conditional Flow MatchingDiffusion models → Audio, speech and music
  48. Foundations and Recent Trends in Multimodal Mobile Agents: A SurveyLLM agents and tool use → GUI and mobile agents
  49. N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data NeedsDeep reinforcement learning methods → Deep RL algorithms and representations
  50. Exploring the Landscape for Generative Sequence Models for Specialized Data SynthesisSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  51. RoboCrowd: Scaling Robot Data Collection through CrowdsourcingOffline RL and imitation learning from data → Robot manipulation imitation learning
  52. LE-PDE++: Mamba for accelerating PDEs SimulationsState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  53. Efficient Active Imitation Learning with Random Network DistillationOffline RL and imitation learning from data → Imitation learning methods
  54. Can Language Models Learn to Skip Steps?LLM reasoning → Reasoning benchmarks and evaluation
  55. KptLLM: Unveiling the Power of Large Language Model for Keypoint ComprehensionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  56. Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI FeedbackLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  57. Formal Theorem Proving by Rewarding LLMs to Decompose Proofs HierarchicallyLLM reasoning → Mathematical reasoning
  58. Risk-sensitive control as inference with R'enyi divergenceDeep reinforcement learning methods → RL theory and sample complexity
  59. Free-Mask: A Novel Paradigm of Integration Between the Segmentation Diffusion Model and Image EditingDiffusion models → Medical imaging and segmentation
  60. Bootstrapping Top-down Information for Self-modulating Slot AttentionLLM reasoning → Multimodal reasoning
  61. SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHFLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  62. Thinking Forward and Backward: Effective Backward Planning with Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  63. ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language ModelMultimodal LLMs / vision-language models → Video understanding with MLLMs
  64. RAGViz: Diagnose and Visualize Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  65. Show, Don't Tell: Learning Reward Machines from Demonstrations for Reinforcement Learning-Based Cardiac Pacemaker SynthesisDeep reinforcement learning methods → Interpretable and logic-guided RL
  66. DynaSaur: Large Language Agents Beyond Predefined ActionsLLM agents and tool use → General LLM agent frameworks and benchmarks
  67. xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive ParallelismDiffusion models → Diffusion foundations and sampling
  68. Taking AI Welfare SeriouslyLLM agents and tool use → General LLM agent frameworks and benchmarks
  69. CSP-Net: Common Spatial Pattern Empowered Neural Networks for EEG-Based Motor Imagery Classification
  70. Exploring Optimal Transport-Based Multi-Grained Alignments for Text-Molecule Retrieval
  71. User-wise Perturbations for User Identity Protection in EEG-Based BCIs
  72. Detecting Student Disengagement in Online Classes Using Deep Learning: A Review
  73. Ozone level forecasting in Mexico City with temporal features and interactions
  74. PMPNet: Pixel Movement Prediction Network for Monocular Depth Estimation in Dynamic Scenes
  75. Exploring Feature Importance and Explainability Towards Enhanced ML-Based DoS Detection in AI Systems
  76. Tabular Data Synthesis with Differential Privacy: A Survey
  77. A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness
  78. Geometry of naturalistic object representations in recurrent neural network models of working memory
  79. Towards Intelligent Augmented Reality (iAR): A Taxonomy of Context, an Architecture for iAR, and an Empirical Study
  80. Wave Network: An Ultra-Small Language Model
  81. Multi-Transmotion: Pre-trained Model for Human Motion Prediction
  82. Multi-modal deformable image registration using untrained neural networks
  83. Fair In-Context Learning via Latent Concept Variables
  84. Visually Analyze SHAP Plots to Diagnose Misclassifications in ML-based Intrusion Detection
  85. A Trust-Region Algorithm for Noisy Equality Constrained Optimization
  86. Explanations that reveal all through the definition of encoding
  87. Pricing and Competition for Generative AI
  88. Zebra-Llama: A Context-Aware Large Language Model for Democratizing Rare Disease Knowledge
  89. Fair and Welfare-Efficient Constrained Multi-matchings under Uncertainty
  90. Deep operator neural network applied to efficient computation of asteroid surface temperature and the Yarkovsky effect
  91. M-CELS: Counterfactual Explanation for Multivariate Time Series Data Guided by Learned Saliency Maps
  92. Fine Grained Insider Risk Detection
  93. A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers
  94. Active Prompt Tuning Enables Gpt-40 To Do Efficient Classification Of Microscopy Images
  95. Classifier Chain Networks for Multi-Label Classification
  96. FUSECAPS: Investigating Feature Fusion Based Framework for Capsule Endoscopy Image Classification
  97. Data-Driven Hierarchical Open Set Recognition
  98. Intelligent Video Recording Optimization using Activity Detection for Surveillance Systems
  99. Towards more efficient agricultural practices via transformer-based crop type classification
  100. EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector
All 337
  1. Enhancing Indoor Mobility with Connected Sensor Nodes: A Real-Time, Delay-Aware Cooperative Perception Approach
  2. Tracking Tumors under Deformation from Partial Point Clouds using Occupancy Networks
  3. Divergent Domains, Convergent Grading: Enhancing Generalization in Diabetic Retinopathy Grading
  4. Advanced XR-Based 6-DOF Catheter Tracking System for Immersive Cardiac Intervention Training
  5. Investigating Idiomaticity in Word Representations
  6. Computing critical exponents in 3D Ising model via pattern recognition/deep learning approach
  7. FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees
  8. Vocal Sandbox: Continual Learning and Adaptation for Situated Human-Robot Collaboration
  9. A Risk Taxonomy and Reflection Tool for Large Language Model Adoption in Public Health
  10. Geometry of orofacial neuromuscular signals: speech articulation decoding using surface electromyography
  11. TileTracker: Tracking Based Vector HD Mapping using Top-Down Road Images
  12. Multi-Agent Decision Transformers for Dynamic Dispatching in Material Handling Systems Leveraging Enterprise Big Data
  13. Social Support Detection from Social Media Texts
  14. Optimization Algorithm Design via Electric Circuits
  15. ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy
  16. The Intersectionality Problem for Algorithmic Fairness
  17. Segment Anything for Dendrites from Electron Microscopy
  18. Enhancing Risk Assessment in Transformers with Loss-at-Risk Functions
  19. A Directional Rockafellar-Uryasev Regression
  20. Leveraging Transformer-Based Models for Predicting Inflection Classes of Words in an Endangered Sami Language
  21. Map++: Towards User-Participatory Visual SLAM Systems with Efficient Map Expansion and Sharing
  22. PIAST: A Multimodal Piano Dataset with Audio, Symbolic and Text
  23. Distributionally Robust Optimization
  24. Modeling Uncertainty in 3D Gaussian Splatting through Continuous Semantic Splatting
  25. TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
  26. Pretrained transformer efficiently learns low-dimensional target functions in-context
  27. Enhancing Graph Neural Networks in Large-scale Traffic Incident Analysis with Concurrency Hypothesis
  28. GraphXAIN: Narratives to Explain Graph Neural Networks
  29. MILU: A Multi-task Indic Language Understanding Benchmark
  30. Towards Leveraging News Media to Support Impact Assessment of AI Technologies
  31. SPACE: 3D Spatial Co-operation and Exploration Framework for Robust Mapping and Coverage with Multi-Robot Systems
  32. Generative Unfolding with Distribution Mapping
  33. NeRF-Aug: Data Augmentation for Robotics with Neural Radiance Fields
  34. Digitizing Touch with an Artificial Multimodal Fingertip
  35. Imagining and building wise machines: The centrality of AI metacognition
  36. Building a Synthetic Vascular Model: Evaluation in an Intracranial Aneurysms Detection Scenario
  37. A Comparative Analysis of Instruction Fine-Tuning LLMs for Financial Text Classification
  38. Energy-Aware Dynamic Neural Inference
  39. First observations of the seiche that shook the world
  40. Modeling and Simulation of a Multi Robot System Architecture
  41. Towards Harmless Rawlsian Fairness Regardless of Demographic Prior
  42. Weakly supervised deep learning model with size constraint for prostate cancer detection in multiparametric MRI and generalization to unseen domains
  43. See it, Think it, Sorted: Large Multimodal Models are Few-shot Time Series Anomaly Analyzers
  44. You are out of context!
  45. Parameter-Efficient Fine-Tuning of Large Language Models for Unit Test Generation: An Empirical Study
  46. Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
  47. Code-Switching Curriculum Learning for Multilingual Transfer in LLMs
  48. A Study of Data Augmentation Techniques to Overcome Data Scarcity in Wound Classification using Deep Learning
  49. Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languages
  50. AutoVFX: Physically Realistic Video Editing from Natural Language Instructions
  51. Adaptive Length Image Tokenization via Recurrent Allocation
  52. Linear Causal Bandits: Unknown Graph and Soft Interventions
  53. Improving Scientific Hypothesis Generation with Knowledge Grounded Large Language Models
  54. Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI
  55. Learning General-Purpose Biomedical Volume Representations using Randomized Synthesis
  56. "Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization
  57. Machine learning identification of maternal inflammatory response and histologic choroamnionitis from placental membrane whole slide images
  58. Can Large Language Models generalize analogy solving like children can?
  59. Physically Based Neural Bidirectional Reflectance Distribution Function
  60. Simulation of Nanorobots with Artificial Intelligence and Reinforcement Learning for Advanced Cancer Cell Detection and Tracking
  61. Boulder2Vec: Modeling Climber Performances in Professional Bouldering Competitions
  62. MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D
  63. Sparsing Law: Towards Large Language Models with Greater Activation Sparsity
  64. Disrupting Test Development with AI Assistants
  65. GenXD: Generating Any 3D and 4D Scenes
  66. Evaluating the Ability of Large Language Models to Generate Verifiable Specifications in VeriFast
  67. Defining and Evaluating Physical Safety for Large Language Models
  68. Evaluating Creative Short Story Generation in Humans and Large Language Models
  69. Information plane and compression-gnostic feedback in quantum machine learning
  70. MdEval: Massively Multilingual Code Debugging
  71. Grid-Based Projection of Spatial Data into Knowledge Graphs
  72. Nash Equilibria via Stochastic Eigendecomposition
  73. Grouped Discrete Representation for Object-Centric Learning
  74. Sample-Efficient Private Learning of Mixtures of Gaussians
  75. ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence
  76. Federated GNNs for EEG-Based Stroke Assessment
  77. Conformal-in-the-Loop for Learning with Imbalanced Noisy Data
  78. Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks
  79. Breaking the Reclustering Barrier in Centroid-based Deep Clustering
  80. On the Utilization of Unique Node Identifiers in Graph Neural Networks
  81. Counterfactual Explanations via Riemannian Latent Space Traversal
  82. Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs
  83. The Enhancement of Software Delivery Performance through Enterprise DevSecOps and Generative Artificial Intelligence in Chinese Technology Firms
  84. Towards safe Bayesian optimization with Wiener kernel regression
  85. Powerful batch conformal prediction for classification
  86. 3D Audio-Visual Segmentation
  87. FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training
  88. Sparse Max-Affine Regression
  89. Predicting the Temperature-Dependent CMC of Surfactant Mixtures with Graph Neural Networks
  90. Targeted Learning for Variable Importance
  91. SIRA: Scalable Inter-frame Relation and Association for Radar Perception
  92. Recursive Learning of Asymptotic Variational Objectives
  93. The Role of DevOps in Enhancing Enterprise Software Delivery Success through R&D Efficiency and Source Code Management
  94. Collective Model Intelligence Requires Compatible Specialization
  95. Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
  96. Metric properties of partial and robust Gromov-Wasserstein distances
  97. DiffSim2Real: Deploying Quadrupedal Locomotion Policies Purely Trained in Differentiable Simulation
  98. Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the role of model complexity
  99. Vehicles, Pedestrians, and E-bikes: a Three-party Game at Right-turn-on-red Crossroads Revealing the Dual and Irrational Role of E-bikes that Risks Traffic Safety
  100. Detect an Object At Once without Fine-tuning
  101. CleAR: Robust Context-Guided Generative Lighting Estimation for Mobile Augmented Reality
  102. Physics-informed neural networks viewpoint for solving the Dyson-Schwinger equations of quantum electrodynamics
  103. SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
  104. Behavioral Sequence Modeling with Ensemble Learning
  105. Do graph neural network states contain graph properties?
  106. Learning Multiple Initial Solutions to Optimization Problems
  107. FedPID: An Aggregation Method for Federated Learning
  108. Cooperative and Collaborative Multi-Task Semantic Communication for Distributed Sources
  109. Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Training
  110. Training Compute-Optimal Protein Language Models
  111. Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks
  112. Generalizable and Robust Spectral Method for Multi-view Representation Learning
  113. Finite-sample performance of the maximum likelihood estimator in logistic regression
  114. Advanced computer vision for extracting georeferenced vehicle trajectories from drone imagery
  115. Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using Earth Observation and Computer Vision: Applications to Two Anti-Poverty RCTs
  116. Generating the Traces You Need: A Conditional Generative Model for Process Mining Data
  117. Supervised Transfer Learning Framework for Fault Diagnosis in Wind Turbines
  118. Unsupervised detection of semantic correlations in big data
  119. Revisiting K-mer Profile for Effective and Scalable Genome Representation Learning
  120. Bridge-IF: Learning Inverse Protein Folding with Markov Bridges
  121. Grounding Emotional Descriptions to Electrovibration Haptic Signals
  122. AVSS: Layer Importance Evaluation in Large Language Models via Activation Variance-Sparsity Analysis
  123. Advancements and limitations of LLMs in replicating human color-word associations
  124. Semiparametric conformal prediction
  125. Multi-modal biometric authentication: Leveraging shared layer architectures for enhanced security
  126. One protein is all you need
  127. Deep Learning on 3D Semantic Segmentation: A Detailed Review
  128. Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-based Human Activity Recognition
  129. Low-Rank Tensors for Multi-Dimensional Markov Models
  130. The evolution of volumetric video: A survey of smart transcoding and compression approaches
  131. Alignment-Based Adversarial Training (ABAT) for Improving the Robustness and Accuracy of EEG-Based BCIs
  132. An Exponential Separation Between Quantum and Quantum-Inspired Classical Algorithms for Linear Systems
  133. Real-time and Downtime-tolerant Fault Diagnosis for Railway Turnout Machines (RTMs) Empowered with Cloud-Edge Pipeline Parallelism
  134. Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models
  135. Towards certification: A complete statistical validation pipeline for supervised learning in industry
  136. Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling
  137. AM Flow: Adapters for Temporal Processing in Action Recognition
  138. Amortized Bayesian Experimental Design for Decision-Making
  139. Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention
  140. Intrinsic Dimensionality of Fermi-Pasta-Ulam-Tsingou High-Dimensional Trajectories Through Manifold Learning: A Linear Approach
  141. Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation
  142. R+R:Understanding Hyperparameter Effects in DP-SGD
  143. Theory-inspired Label Shift Adaptation via Aligned Distribution Mixture
  144. Enhancing ID-based Recommendation with Large Language Models
  145. Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
  146. Explainable cognitive decline detection in free dialogues with a Machine Learning approach based on pre-trained Large Language Models
  147. SibylSat: Using SAT as an Oracle to Perform a Greedy Search on TOHTN Planning
  148. Optimal Classification under Performative Distribution Shift
  149. Modulating State Space Model with SlowFast Framework for Compute-Efficient Ultra Low-Latency Speech Enhancement
  150. Shortcut Learning in In-Context Learning: A Survey
  151. Tree level change detection over Ahmedabad city using very high resolution satellite images and Deep Learning
  152. Against Multifaceted Graph Heterogeneity via Asymmetric Federated Prompt Learning
  153. Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation
  154. Culinary Class Wars: Evaluating LLMs using ASH in Cuisine Transfer Task
  155. Ask, and it shall be given: On the Turing completeness of prompting
  156. QCS: Feature Refining from Quadruplet Cross Similarity for Facial Expression Recognition
  157. Learning Controlled Stochastic Differential Equations
  158. Typicalness-Aware Learning for Failure Detection
  159. Understanding Variational Autoencoders with Intrinsic Dimension and Information Imbalance
  160. SPECTRUM: Semantic Processing and Emotion-informed video-Captioning Through Retrieval and Understanding Modalities
  161. On the phase diagram of extensive-rank symmetric matrix denoising beyond rotational invariance
  162. The Certainty Ratio Cρ: a novel metric for assessing the reliability of classifier predictions
  163. Toddlers' Active Gaze Behavior Supports Self-Supervised Object Learning
  164. UnSegMedGAT: Unsupervised Medical Image Segmentation using Graph Attention Networks Clustering
  165. V-CAS: A Realtime Vehicle Anti Collision System Using Vision Transformer on Multi-Camera Streams
  166. Deep Learning for Leopard Individual Identification: An Adaptive Angular Margin Approach
  167. EXAGREE: Mitigating Explanation Disagreement with Stakeholder-Aligned Models
  168. Robust plug-and-play methods for highly accelerated non-Cartesian MRI reconstruction
  169. RobPy: a Python Package for Robust Statistical Methods
  170. Evaluating the quality of published medical research with ChatGPT
  171. Learning Where to Edit Vision Transformers
  172. HACD: Harnessing Attribute Semantics and Mesoscopic Structure for Community Detection
  173. Differentially private and decentralized randomized power method
  174. Exploiting Contextual Uncertainty of Visual Data for Efficient Training of Deep Models
  175. Fairness-Utilization Trade-off in Wireless Networks with Explainable Kolmogorov-Arnold Networks
  176. Real-Time Polygonal Semantic Mapping for Humanoid Robot Stair Climbing
  177. Masked Autoencoders are Parameter-Efficient Federated Continual Learners
  178. Traffic and Safety Rule Compliance of Humans in Diverse Driving Situations
  179. FPPL: An Efficient and Non-IID Robust Federated Continual Learning Framework
  180. Best-Arm Identification in Unimodal Bandits
  181. MBDRes-U-Net: Multi-Scale Lightweight Brain Tumor Segmentation Network
  182. A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding
  183. LiDAttack: Robust Black-box Attack on LiDAR-based Object Detection
  184. Stein Variational Newton Neural Network Ensembles
  185. Causal Discovery and Classification Using Lempel-Ziv Complexity
  186. Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration
  187. Improving Trust Estimation in Human-Robot Collaboration Using Beta Reputation at Fine-grained Timescales
  188. A Novel Deep Learning Tractography Fiber Clustering Framework for Functionally Consistent White Matter Parcellation Using Multimodal Diffusion MRI and Functional MRI
  189. MeToken: Uniform Micro-environment Token Boosts Post-Translational Modification Prediction
  190. GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes
  191. Silver medal Solution for Image Matching Challenge 2024
  192. ManiBox: Enhancing Embodied Spatial Generalization via Scalable Simulation Data Generations
  193. DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorship
  194. ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer
  195. Leveraging Label Semantics and Meta-Label Refinement for Multi-Label Question Classification
  196. TriG-NER: Triplet-Grid Framework for Discontinuous Named Entity Recognition
  197. OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning
  198. FedReMa: Improving Personalized Federated Learning via Leveraging the Most Relevant Clients
  199. Distribution alignment based transfer fusion frameworks on quantum devices for seeking quantum advantages
  200. IRS-Enhanced Secure Semantic Communication Networks: Cross-Layer and Context-Awared Resource Allocation
  201. Shrinking the Giant : Quasi-Weightless Transformers for Low Energy Inference
  202. High-Pass Graph Convolutional Network for Enhanced Anomaly Detection: A Novel Approach
  203. So You Think You Can Scale Up Autonomous Robot Data Collection?
  204. Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification
  205. Can Language Models Enable In-Context Database?
  206. Gradient Methods with Online Scaling
  207. Expanding Sparse Tuning for Low Memory Usage
  208. AIWR: Aerial Image Water Resource Dataset for Segmentation Analysis
  209. Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge
  210. Fast Semi-supervised Learning on Large Graphs: An Improved Green-function Method
  211. Minder: Faulty Machine Detection for Large-scale Distributed Model Training
  212. Generating executable oracles to check conformance of client code to requirements of JDK Javadocs using LLMs
  213. Non rigid geometric distortions correction -- Application to atmospheric turbulence stabilization
  214. Transferable Sequential Recommendation via Vector Quantized Meta Learning
  215. Context Parallelism for Scalable Million-Token Inference
  216. MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation
  217. Clustering Based on Density Propagation and Subcluster Merging
  218. Learning predictable and robust neural representations by straightening image sequences
  219. Eurekaverse: Environment Curriculum Generation via Large Language Models
  220. ARN-LSTM: A Multi-Stream Fusion Model for Skeleton-based Action Recognition
  221. A Theoretical Characterization of Optimal Data Augmentations in Self-Supervised Learning
  222. Towards Pedagogical LLMs with Supervised Fine Tuning for Computing Education
  223. How Analysis Can Teach Us the Optimal Way to Design Neural Operators
  224. Automatic Structured Pruning for Efficient Architecture in Federated Learning
  225. Disentangled PET Lesion Segmentation
  226. Mitigating Spurious Correlations via Disagreement Probability
  227. Multi-task Geometric Estimation of Depth and Surface Normal from Monocular 360deg Images
  228. Rotation Perturbation Robustness in Point Cloud Analysis: A Perspective of Manifold Distillation
  229. Entropy stable conservative flux form neural networks
  230. Learning from Convolution-based Unlearnable Datasets
  231. Not Just Object, But State: Compositional Incremental Learning without Forgetting
  232. Next Best View For Point-Cloud Model Acquisition: Bayesian Approximation and Uncertainty Analysis
  233. A Probabilistic Formulation of LiDAR Mapping with Neural Radiance Fields
  234. Computational Lower Bounds for Regret Minimization in Normal-Form Games
  235. Barriers to Welfare Maximization with No-Regret Learning
  236. LES-SINDy: Laplace-Enhanced Sparse Identification of Nonlinear Dynamical Systems
  237. A General Recipe for Contractive Graph Neural Networks -- Technical Report