mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 16 Apr 2025

273 papers

  1. ToolRL: Reward is All Tool Learning NeedsLLM agents and tool use → Reinforcement learning for LLM agents
  2. Evaluating Menu OCR and Translation: A Benchmark for Aligning Human and Automated Evaluations in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  3. On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering AttacksMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  4. Generalization through variance: how noise shapes inductive biases in diffusion modelsDiffusion models → Diffusion foundations and sampling
  5. MOM: Memory-Efficient Offloaded Mini-Sequence Inference for Long Context Language ModelsEfficient LLM inference and serving → KV cache optimization
  6. Memorization vs. Reasoning: Updating LLMs with New KnowledgeLLM reasoning → Reasoning benchmarks and evaluation
  7. Evaluating the Diversity and Quality of LLM Generated ContentLLM reasoning → Reinforcement learning for reasoning +1
  8. Multimodal LLM Augmented Reasoning for Interpretable Visual Perception AnalysisLLM reasoning → Multimodal reasoning +1
  9. Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  10. Agentic AI Optimisation (AAIO): what it is, how it works, why it matters, and how to deal with itLLM agents and tool use → Web, search, and research agents
  11. Dense Backpropagation Improves Training for Sparse Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
  12. Sparsity Outperforms Low-Rank Projections in Few-Shot AdaptationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  13. InstantCharacter: Personalize Any Characters with a Scalable Diffusion Transformer FrameworkDiffusion models → Image generation, text-to-image and editing
  14. WorldMem: Long-term Consistent World Simulation with MemoryWorld models → Video-generation world models and simulators
  15. Unveiling Hidden Collaboration within Mixture-of-Experts in Large Language ModelsMixture-of-experts → MoE large language models
  16. Adapting a World Model for Trajectory Following in a 3D GameWorld models → Video-generation world models and simulators +1
  17. VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame RateDiffusion models → Video generation
  18. FLIP Reasoning ChallengeLLM reasoning → Multimodal reasoning
  19. Coding-Prior Guided Diffusion Network for Video DeblurringDiffusion models → Inverse problems and image restoration
  20. d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement LearningLLM reasoning → Diffusion reasoning and test-time scaling
  21. ARCeR: an Agentic RAG for the Automated Definition of Cyber RangesLLM agents and tool use → Agent threats, guardrails and governance
  22. Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  23. Anti-Aesthetics: Protecting Facial Privacy against Customized Text-to-Image SynthesisDiffusion models → Robustness, privacy and adversarial aspects
  24. Entropy-Guided Watermarking for LLMs: A Test-Time Framework for Robust and Traceable Text GenerationLLM safety and security → Watermarking generated content and models
  25. Generalized Visual Relation Detection with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  26. Reasoning-Based AI for Startup Evaluation (R.A.I.S.E.): A Memory-Augmented, Multi-Step Decision FrameworkLLM reasoning → Test-time compute and efficient thinking
  27. Self-alignment of Large Video Language Models with Refined Regularized Preference OptimizationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  28. Modular-Cam: Modular Dynamic Camera-view Video Generation with LLMDiffusion models → Video generation
  29. pix2pockets: Shot Suggestions in 8-Ball Pool from a Single Image in the WildDeep reinforcement learning methods → RL for robot locomotion and manipulation
  30. RadMamba: Efficient Human Activity Recognition through Radar-based Micro-Doppler-Oriented Mamba State-Space ModelState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  31. Understanding Attention Mechanism in Video Diffusion ModelsDiffusion models → Video generation
  32. Evolutionary Reinforcement Learning for Interpretable Decision-Making in Supply Chain ManagementDeep reinforcement learning methods → RL for energy, networks and operations
  33. Instruction-augmented Multimodal Alignment for Image-Text and Element MatchingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  34. Active Human Feedback Collection via Neural Contextual Dueling BanditsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  35. Control of Rayleigh-B'enard Convection: Effectiveness of Reinforcement Learning in the Turbulent RegimeDeep reinforcement learning methods → RL with diffusion and flow models
  36. A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPsDeep reinforcement learning methods → RL theory and sample complexity
  37. Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream DatasetsLLM safety and security → Backdoor and data poisoning attacks
  38. R-Meshfusion: Reinforcement Learning Powered Sparse-View Mesh Reconstruction with Diffusion PriorsDiffusion models → 3D, point cloud and scene generation +1
  39. VIPO: Value Function Inconsistency Penalized Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  40. Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  41. SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  42. Rethinking the Generation of High-Quality CoT Data from the Perspective of LLM-Adaptive Question Difficulty GradingLLM reasoning → Prompting and chain-of-thought reasoning
  43. AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly DetectionLLM reasoning → Chain-of-thought reasoning for driving
  44. A Graph-Based Reinforcement Learning Approach with Frontier Potential Based Reward for Safe Cluttered Environment ExplorationDeep reinforcement learning methods → Safe and constrained RL
  45. Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole DetectionLLM reasoning → Reasoning benchmarks and evaluation
  46. Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel IntegrationLLM reasoning → LLM reasoning for recommendation
  47. ACE: Attentional Concept Erasure in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  48. A Visual RAG Pipeline for Few-Shot Fine-Grained Product ClassificationRetrieval-augmented generation → Multimodal RAG
  49. Could Thinking Multilingually Empower LLM Reasoning?LLM reasoning → Reasoning benchmarks and evaluation
  50. TextDiffSeg: Text-guided Latent Diffusion Model for 3d Medical Images SegmentationDiffusion models → Medical imaging and segmentation
  51. Cost-Efficient LLM Serving in the Cloud: VM Selection with KV Cache OffloadingEfficient LLM inference and serving → Serving systems and request scheduling
  52. WebRollback: Enhancing Web Agents with Explicit Rollback MechanismsLLM agents and tool use → Web, search, and research agents
  53. PCDiff: Proactive Control for Ownership Protection in Diffusion Models with Watermark CompatibilityDiffusion models → Robustness, privacy and adversarial aspects +1
  54. Shared Disk KV Cache Management for Efficient Multi-Instance Inference in RAG-Powered LLMsEfficient LLM inference and serving → KV cache optimization
  55. Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?LLM reasoning → Mathematical reasoning
  56. The Devil is in the Prompts: Retrieval-Augmented Prompt Optimization for Text-to-Video GenerationRetrieval-augmented generation → Generation and context integration
  57. DVLTA-VQA: Decoupled Vision-Language Modeling with Text-Guided Adaptation for Blind Video Quality AssessmentMultimodal LLMs / vision-language models → Image editing and quality assessment
  58. Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint MatchingDiffusion models → Flow matching, time series and science
  59. A Library of LLM Intrinsics for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  60. Progent: Securing AI Agents with Privilege ControlLLM agents and tool use → Agent threats, guardrails and governance +1
  61. H3GNNs: Harmonizing Heterophily and Homophily in GNNs via Joint Structural Node Encoding and Self-Supervised LearningKnowledge distillation → Graph neural network distillation
  62. Interpreting the linear structure of vision-language model embedding spacesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  63. Can GPT tell us why these images are synthesized? Empowering Multimodal Large Language Models for ForensicsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  64. DM-OSVP++: One-Shot View Planning Using 3D Diffusion Models for Active RGB-Based Object ReconstructionDiffusion models → 3D, point cloud and scene generation
  65. InjectLab: A Tactical Framework for Adversarial Threat Modeling Against Large Language Models
  66. A Scoping Review of Natural Language Processing in Addressing Medically Inaccurate Information: Errors, Misinformation, and Hallucination
  67. Waking Up an AI: A Quantitative Framework for Prompt-Induced Phase Transition in Large Language Models
  68. RDI: An adversarial robustness evaluation metric for deep neural networks based on model statistical features
  69. Scalability Optimization in Cloud-Based AI Inference Services: Strategies for Real-Time Load Balancing and Automated Scaling
  70. AI Safety Should Prioritize the Future of Work
  71. Naming is framing: How cybersecurity's language problems are repeating in AI governance
  72. Prognosis Of Lithium-Ion Battery Health with Hybrid EKF-CNN+LSTM Model Using Differential Capacity
  73. Thousand Voices of Trauma: A Large-Scale Synthetic Dataset for Modeling Prolonged Exposure Therapy Conversations
  74. Generative System Dynamics in Recurrent Neural Networks
  75. Open-Medical-R1: How to Choose Data for RLVR Training at Medicine Domain
  76. On Revealing the Hidden Problem Structure in Real-World and Theoretical Problems Using Walsh Coefficient Influence
  77. Using customized GPT to develop prompting proficiency in architectural AI-generated images
  78. From job titles to jawlines: Using context voids to study generative AI systems
  79. The Balancing Act of Policies in Developing Machine Learning Explanations
  80. Mixer Metaphors: audio interfaces for non-musical applications
  81. Intelligence of Things: A Spatial Context-Aware Control System for Smart Devices
  82. Wavelet-based Variational Autoencoders for High-Resolution Image Generation
  83. MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance
  84. Graphical Models for Decision-Making: Integrating Causality and Game Theory
  85. Intelligent road crack detection and analysis based on improved YOLOv8
  86. Decision-based AI Visual Navigation for Cardiac Ultrasounds
  87. Is Trust Correlated With Explainability in AI? A Meta-Analysis
  88. Robust and Scalable Variational Bayes
  89. Corner Gradient Descent
  90. BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
  91. Event Quality Score (EQS): Assessing the Realism of Simulated Event Camera Streams via Distances in Latent Space
  92. AdaVid: Adaptive Video-Language Pretraining
  93. Continual Learning Strategies for 3D Engineering Regression Problems: A Benchmarking Study
  94. Requirements for Recognition and Rapid Response to Unfamiliar Events Outside of Agent Design Scope
  95. Beyond Text: Characterizing Domain Expert Needs in Document Research
  96. Accelerating Clinical NLP at Scale with a Hybrid Framework with Reduced GPU Demands: A Case Study in Dementia Identification
  97. MobilePoser: Real-Time Full-Body Pose Estimation and 3D Human Translation from IMUs in Mobile Consumer Devices
  98. Can Pre-training Indicators Reliably Predict Fine-tuning Outcomes of LLMs?
  99. Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process
  100. Boosting Reservoir Computing with Brain-inspired Adaptive Dynamics
All 273
  1. Towards Conversational AI for Human-Machine Collaborative MLOps
  2. What do people expect from Artificial Intelligence? Public opinion on alignment in AI moderation from Germany and the United States
  3. Integrating Structural and Semantic Signals in Text-Attributed Graphs with BiGTex
  4. You Don't Need All Attentions: Distributed Dynamic Fine-Tuning for Foundation Models
  5. SLURG: Investigating the Feasibility of Generating Synthetic Online Fallacious Discourse
  6. Geometric Generality of Transformer-Based Gr"obner Basis Computation
  7. On Linear Representations and Pretraining Data Frequency in Language Models
  8. M2FGB: A Min-Max Gradient Boosting Framework for Subgroup Fairness
  9. DG-MVP: 3D Domain Generalization via Multiple Views of Point Clouds for Classification
  10. Can Moran Eigenvectors Improve Machine Learning of Spatial Data? Insights from Synthetic Data Validation
  11. Deriving Equivalent Symbol-Based Decision Models from Feedforward Neural Networks
  12. Enhanced Battery Capacity Estimation in Data-Limited Scenarios through Swarm Learning
  13. 3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap
  14. Learning Transferable Friction Models and LuGre Identification Via Physics-Informed Neural Networks
  15. Position: The Most Expensive Part of an LLM should be its Training Data
  16. Don't Just Translate, Agitate: Using Large Language Models as Devil's Advocates for AI Explanations
  17. Mitigating LLM Hallucinations with Knowledge Graphs: A Case Study
  18. Standardization of Multi-Objective QUBOs
  19. Interpretable AI-driven Guidelines for Type 2 Diabetes Treatment from Observational Data
  20. Diffusion Based Robust LiDAR Place Recognition
  21. A Human-AI Comparative Analysis of Prompt Sensitivity in LLM-Based Relevance Judgment
  22. NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results
  23. Activated LoRA: Fine-tuned LLMs for Intrinsics
  24. A Survey on Archetypal Analysis
  25. Predictive control of blast furnace temperature in steelmaking with hybrid depth-infused quantum neural networks
  26. Resonances in reflective Hamiltonian Monte Carlo
  27. Geographical Context Matters: Bridging Fine and Coarse Spatial Information to Enhance Continental Land Cover Mapping
  28. Themisto: Jupyter-Based Runtime Benchmark
  29. DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging
  30. A Method for Handling Negative Similarities in Explainable Graph Spectral Clustering of Text Documents -- Extended Version
  31. Towards an AI Observatory for the Nuclear Sector: A tool for anticipatory governance
  32. Replicating ReLM Results: Validating Large Language Models with ReLM
  33. Regist3R: Incremental Registration with Stereo Foundation Model
  34. Leveraging Large Language Models for Multi-Class and Multi-Label Detection of Drug Use and Overdose Symptoms on Social Media
  35. SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians
  36. Trend Filtered Mixture of Experts for Automated Gating of High-Frequency Flow Cytometry Data
  37. BitNet b1.58 2B4T Technical Report
  38. How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions
  39. Dysarthria Normalization via Local Lie Group Transformations for Robust ASR
  40. The Tenth NTIRE 2025 Image Denoising Challenge Report
  41. Beyond Reconstruction: A Physics Based Neural Deferred Shader for Photo-realistic Rendering
  42. HLS-Eval: A Benchmark and Framework for Evaluating LLMs on High-Level Synthesis Design Tasks
  43. Towards Learning to Complete Anything in Lidar
  44. SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields
  45. Human Aligned Compression for Robust Models
  46. Advancing Arabic Speech Recognition Through Large-Scale Weakly Supervised Learning
  47. Comparative Evaluation of Radiomics and Deep Learning Models for Disease Detection in Chest Radiography
  48. SIDME: Self-supervised Image Demoir'eing via Masked Encoder-Decoder Reconstruction
  49. Cobra: Efficient Line Art COlorization with BRoAder References
  50. Watermarking Needs Input Repetition Masking
  51. Uncertainty-Guided Coarse-to-Fine Tumor Segmentation with Anatomy-Aware Post-Processing
  52. Communication Optimization for Decentralized Learning atop Bandwidth-limited Edge Networks
  53. Towards Realistic Low-Light Image Enhancement via ISP Driven Data Modeling
  54. Modality-Independent Explainable Detection of Inaccurate Organ Segmentations Using Denoising Autoencoders
  55. Beyond Patches: Mining Interpretable Part-Prototypes for Explainable AI
  56. From Requirements to Architecture: Semi-Automatically Generating Software Architectures
  57. Leave-One-Out Stable Conformal Prediction
  58. What Do Large Language Models Know? Tacit Knowledge as a Potential Causal-Explanatory Structure
  59. CoMotion: Concurrent Multi-person 3D Motion
  60. SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data
  61. Battery-aware Cyclic Scheduling in Energy-harvesting Federated Learning
  62. Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification
  63. Mapping Controversies Using Artificial Intelligence: An Analysis of the Hamas-Israel Conflict on YouTube
  64. Approximation Bounds for Transformer Networks with Application to Regression
  65. Poem Meter Classification of Recited Arabic Poetry: Integrating High-Resource Systems for a Low-Resource Task
  66. Towards a General-Purpose Zero-Shot Synthetic Low-Light Image and Video Pipeline
  67. RADLER: Radar Object Detection Leveraging Semantic 3D City Models and Self-Supervised Radar-Image Learning
  68. CodingHomo: Bootstrapping Deep Homography With Video Coding
  69. FocusedAD: Character-centric Movie Audio Description
  70. Predictive Multiplicity in Survival Models: A Method for Quantifying Model Uncertainty in Predictive Maintenance Applications
  71. Towards Explainable Fusion and Balanced Learning in Multimodal Sentiment Analysis
  72. Multilingual Contextualization of Large Language Models for Document-Level Machine Translation
  73. Weakly Semi-supervised Whole Slide Image Classification by Two-level Cross Consistency Supervision
  74. Remote sensing colour image semantic segmentation of trails created by large herbivorous Mammals
  75. A Diffusion-Based Framework for Terrain-Aware Remote Sensing Image Reconstruction
  76. Towards LLM Agents for Earth Observation
  77. Logits DeConfusion with CLIP for Few-Shot Learning
  78. Metric-Solver: Sliding Anchored Metric Depth Estimation from a Single Image
  79. Gauging Overprecision in LLMs: An Empirical Study
  80. AttentionDrop: A Novel Regularization Method for Transformer Models
  81. Neural Contextual Bandits Under Delayed Feedback Constraints
  82. Selective Demonstration Retrieval for Improved Implicit Hate Speech Detection
  83. DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency
  84. Single-shot Star-convex Polygon-based Instance Segmentation for Spatially-correlated Biomedical Objects
  85. A Generative Deep Learning Workflow for Inverse Molecular Design of Fuels
  86. Optimizing Compound Retrieval Systems
  87. Semantic Similarity-Informed Bayesian Borrowing for Quantitative Signal Detection of Adverse Events
  88. On the calibration of Just-in-time Defect Prediction
  89. Proof-Carrying Neuro-Symbolic Code
  90. Object Placement for Anything
  91. FedEPA: Enhancing Personalization and Modality Alignment in Multimodal Federated Learning
  92. Action Anticipation from SoccerNet Football Video Broadcasts
  93. Graph Network for Sign Language Tasks
  94. Purposefully Induced Psychosis (PIP): Embracing Hallucination as Imagination in Large Language Models
  95. Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition
  96. Diffusion Generative Recommendation with Continuous Tokens
  97. Voice Conversion with Diverse Intonation using Conditional Variational Auto-Encoder
  98. A Complex-valued SAR Foundation Model Based on Physically Inspired Representation Learning
  99. A Review of YOLOv12: Attention-Based Enhancements vs. Previous Versions
  100. Analysis of Pseudo-Labeling for Online Source-Free Universal Domain Adaptation
  101. Large Language Models as Quasi-crystals: Coherence Without Repetition in Generative Text
  102. Efficient identification of linear, parameter-varying, and nonlinear systems with noise models
  103. Hardware-Friendly Delayed-Feedback Reservoir for Multivariate Time-Series Classification
  104. Leveraging Machine Learning Models to Predict the Outcome of Digital Medical Triage Interviews
  105. SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes
  106. Reassessing Extractive QA Datasets at Scale: LLM-as-a-Judge and In-Depth Analyses
  107. Securing the Skies: A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directions
  108. Exploring Video-Based Driver Activity Recognition under Noisy Labels
  109. Novel-view X-ray Projection Synthesis through Geometry-Integrated Deep Learning
  110. Robust and Fine-Grained Detection of AI Generated Texts
  111. Flow Intelligence: Robust Feature Matching via Temporal Signature Correlation
  112. ADAT: Time-Series-Aware Adaptive Transformer Architecture for Sign Language Translation
  113. An LLM-as-a-judge Approach for Scalable Gender-Neutral Translation Evaluation
  114. Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification Approach
  115. FedCanon: Non-Convex Composite Federated Learning with Efficient Proximal Operation on Heterogeneous Data
  116. Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments
  117. Learning Physics-Informed Color-Aware Transforms for Low-Light Image Enhancement
  118. Search is All You Need for Few-shot Anomaly Detection
  119. CAGS: Open-Vocabulary 3D Scene Understanding with Context-Aware Gaussian Splatting
  120. HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems
  121. Seeking and leveraging alternative variable dependency concepts in gray-box-elusive bimodal land-use allocation problems
  122. Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval
  123. Benchmarking Mutual Information-based Loss Functions in Federated Learning
  124. Factor-MCLS: Multi-agent learning system with reward factor matrix and multi-critic framework for dynamic portfolio optimization
  125. Transferable Deployment of Semantic Edge Inference Systems via Unsupervised Domain Adaption
  126. A Category-Fragment Segmentation Framework for Pelvic Fracture Segmentation in X-ray Images
  127. On the Problem of Best Arm Retention
  128. Moving between high-quality optima using multi-satisfiability characteristics in hard-to-solve Max3Sat instances
  129. Synthetic Data for Blood Vessel Network Extraction
  130. Cross-Frequency Collaborative Training Network and Dataset for Semi-supervised First Molar Root Canal Segmentation
  131. EngramNCA: a Neural Cellular Automaton Model of Memory Transfer
  132. Proximal Inference for Indirect and Intervening Effects in Population Interventions
  133. Boosting Multi-View Stereo with Depth Foundation Model in the Absence of Real-World Labels
  134. Evaluating the Goal-Directedness of Large Language Models
  135. GT-SNT: A Linear-Time Transformer for Large-Scale Graphs via Spiking Node Tokenization
  136. EmoFSM: A Finite State Machine for Emotional Support Conversation
  137. Support is All You Need for Certified VAE Training
  138. Emergence of Computational Structure in a Neural Network Physics Simulator
  139. D'ej`a Vu: Multilingual LLM Evaluation through the Lens of Machine Translation Evaluation
  140. Real-World Depth Recovery via Structure Uncertainty Modeling and Inaccurate GT Depth Fitting
  141. ARWI: Arabic Write and Improve
  142. Learning Strategies in Particle Swarm Optimizer: A Critical Review and Performance Analysis
  143. Manifold meta-learning for reduced-complexity neural system identification
  144. Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture
  145. Federated Spectral Graph Transformers Meet Neural Ordinary Differential Equations for Non-IID Graphs
  146. Neighbor-Based Feature and Index Enhancement for Person Re-Identification
  147. Selective Attention Federated Learning: Improving Privacy and Efficiency for Clinical Text Classification
  148. Large Language Models for Drug Overdose Prediction from Longitudinal Medical Records
  149. DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generation
  150. ACMamba: Fast Unsupervised Anomaly Detection via An Asymmetrical Consensus State Space Model
  151. Agile Retrospectives: What went well? What didn't go well? What should we do?
  152. Multimodal Spatio-temporal Graph Learning for Alignment-free RGBT Video Object Detection
  153. Bridging the Semantic Gaps: Improving Medical VQA Consistency with LLM-Augmented Question Sets
  154. Discrimination-free Insurance Pricing with Privatized Sensitive Attributes
  155. TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion
  156. Unsupervised Classification of English Words Based on Phonological Information: Discovery of Germanic and Latinate Clusters
  157. Extended Short- and Long-Range Mesh Learning for Fast and Generalized Garment Simulation
  158. Dynamics and Computational Principles of Echo State Networks: A Mathematical Perspective
  159. GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision
  160. Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures
  161. SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation
  162. Recent Advances in 3D Object and Scene Generation: A Survey
  163. EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos
  164. Saga: Capturing Multi-granularity Semantics from Massive Unlabelled IMU Data for User Perception
  165. Unravelling Technical debt topics through Time, Programming Languages and Repository
  166. The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMs
  167. Towards Safe Synthetic Image Generation On the Web: A Multimodal Robust NSFW Defense and Million Scale Dataset
  168. FiGO: Fine-Grained Object Counting without Annotations
  169. Clustering and analysis of user behaviour in blockchain: A case study of Planet IX
  170. Non-uniform Point Cloud Upsampling via Local Manifold Distribution
  171. An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World
  172. Deep Binding of Language Model Virtual Personas: a Study on Approximating Political Partisan Misperceptions
  173. Computational Basis of LLM's Decision Making in Social Simulation