mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 25 Mar 2025

340 papers

  1. Rosetta-PL: Propositional Logic as a Benchmark for Large Language Model ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  2. LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object IntegrationLLM reasoning → Multimodal reasoning
  3. Why Representation Engineering Works: A Theoretical and Empirical Study in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  4. LLM-based Agent Simulation for Maternal Health Interventions: Uncertainty Estimation and Decision-focused EvaluationLLM agents and tool use → Social simulation and multi-agent debate
  5. LLM-ABM for Transportation: Assessing the Potential of LLM Agents in System AnalysisLLM agents and tool use → Multimodal and embodied agents
  6. IPGO: Indirect Prompt Gradient Optimization for Parameter-Efficient Prompt-level Fine-Tuning on Text-to-Image ModelsDiffusion models → Image generation, text-to-image and editing
  7. LERO: LLM-driven Evolutionary framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  8. Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Models Using Implicit Feedback from Pre-training DemonstrationsLLM agents and tool use → Reinforcement learning for LLM agents +1
  9. Bigger But Not Better: Small Neural Language Models Outperform Large Language Models in Detection of Thought DisorderLLM reasoning → Hallucination detection and mitigation
  10. Can Multi-modal (reasoning) LLMs work as deepfake detectors?LLM reasoning → Multimodal reasoning +1
  11. Universal Cross-Tokenizer Distillation via Approximate Likelihood MatchingKnowledge distillation → Knowledge distillation for LLMs
  12. Abstracting Geo-specific Terrains to Scale Up Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  13. Poor Alignment and Steerability of Large Language Models: Evidence from College Admission EssaysLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  14. Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image AnalysisMultimodal LLMs / vision-language models → Medical vision-language models
  15. Agents in the Sandbox: End-to-End Crash Bug Reproduction for MinecraftLLM agents and tool use → Software engineering coding agents
  16. OmniNova:A General Multimodal Agent FrameworkLLM agents and tool use → General LLM agent frameworks and benchmarks
  17. Gemini Robotics: Bringing AI into the Physical WorldMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  18. LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?LLM reasoning → Spatial and embodied reasoning
  19. ExCoT: Optimizing Reasoning for Text-to-SQL with Execution FeedbackLLM reasoning → Knowledge- and tool-augmented reasoning +1
  20. Audio-centric Video Understanding Benchmark without Text ShortcutMultimodal LLMs / vision-language models → Video understanding with MLLMs
  21. LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy PreservationEfficient LLM inference and serving → KV cache quantization
  22. Test-Time Reasoning Through Visual Human Preferences with VLMs and Soft RewardsLLM reasoning → Multimodal reasoning +2
  23. VisualQuest: A Benchmark for Abstract Visual Reasoning in MLLMsLLM reasoning → Multimodal reasoning +1
  24. Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  25. PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction ModelWorld models → Latent predictive world models
  26. AvatarArtist: Open-Domain 4D AvatarizationDiffusion models → 3D, point cloud and scene generation
  27. ICE: Intrinsic Concept Extraction from a Single Image via Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  28. CAFe: Unifying Representation and Generation with Contrastive-Autoregressive FinetuningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  29. Scaling Down Text Encoders of Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  30. A Multi-Agent Framework Integrating Large Language Models and Generative AI for Accelerated Metamaterial DesignLLM agents and tool use → Medical and scientific domain agents
  31. Mask2DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video GenerationDiffusion models → Video generation
  32. CausalRAG: Integrating Causal Graphs into Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  33. Scaling Evaluation-time Compute with Reasoning Models as EvaluatorsLLM reasoning → Test-time compute and efficient thinking
  34. Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time ThinkingLLM reasoning → Test-time compute and efficient thinking
  35. FALCONEye: Finding Answers and Localizing Content in ONE-hour-long videos with multi-modal LLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  36. FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language ModelMultimodal LLMs / vision-language models → Image editing and quality assessment +1
  37. AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion TransformersDiffusion models → Audio, speech and music
  38. Unpaired Object-Level SAR-to-Optical Image Translation for Aircraft with Keypoints-Guided Diffusion ModelsDiffusion models → Inverse problems and image restoration
  39. PAVE: Patching and Adapting Video Large Language ModelsLLM reasoning → Multimodal reasoning
  40. Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  41. BiPrompt-SAM: Enhancing Image Segmentation via Explicit Selection between Point and Text PromptsMixture-of-experts → Medical and biomedical MoE
  42. Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action PolicyVision-language-action models → Efficient VLA inference and adaptation +1
  43. ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action GenerationLLM reasoning → Chain-of-thought reasoning for driving +1
  44. Inducing Personality in LLM-Based Honeypot Agents: Measuring the Effect on Human-Like Agenda GenerationLLM agents and tool use → Social simulation and multi-agent debate
  45. PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  46. EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video ReconstructionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  47. Semi-SMD: Semi-Supervised Metric Depth Estimation via Surrounding Cameras for Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
  48. Writing as a testbed for open ended agentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  49. Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  50. Risk-Aware Reinforcement Learning for Autonomous Driving: Improving Safety When Driving through IntersectionEnd-to-end autonomous driving → Reinforcement learning for driving +1
  51. fine-CLIP: Enhancing Zero-Shot Fine-Grained Surgical Action Recognition with Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  52. CoSimGen: Controllable Diffusion Model for Simultaneous Image and Mask GenerationDiffusion models → Image generation, text-to-image and editing
  53. RGB-Th-Bench: A Dense benchmark for Visual-Thermal Understanding of Vision Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  54. Show or Tell? Effectively prompting Vision-Language Models for semantic segmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  55. 1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model TrainingLLM reasoning → Reasoning benchmarks and evaluation +1
  56. Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and MitigationLLM reasoning → Hallucination detection and mitigation +1
  57. Enabling Rapid Shared Human-AI Mental Model Alignment via the After-Action ReviewLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  58. Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less OverthinkingLLM reasoning → Prompting and chain-of-thought reasoning
  59. HoarePrompt: Structural Reasoning About Program Correctness in Natural LanguageLLM reasoning → Reasoning for agents, planning and code
  60. Prompt-Guided Dual-Path UNet with Mamba for Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  61. Scaling Laws of Synthetic Data for Language ModelsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  62. Agent-Initiated Interaction in Phone UI AutomationLLM agents and tool use → GUI and mobile agents
  63. One Framework to Rule Them All: Unifying RL-Based and RL-Free Methods in RLHFLLM reasoning → Reinforcement learning for reasoning +1
  64. Boosting Robotic Manipulation Generalization with Minimal Costly DataVision-language-action models → Generalist VLA models and benchmarks
  65. RoboFlamingo-Plus: Fusion of Depth and RGB Perception with Vision-Language Models for Enhanced Robotic ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  66. Improved Alignment of Modalities in Large Vision Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  67. Single-Step Latent Consistency Model for Remote Sensing Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  68. DomainCQA: Crafting Knowledge-Intensive QA from Domain-Specific ChartsLLM reasoning → Multimodal reasoning +1
  69. ReSearch: Learning to Reason with Search for LLMs via Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning
  70. AccVideo: Accelerating Video Diffusion Model with Synthetic DatasetDiffusion models → Video generation
  71. SparseGS-W: Sparse-View 3D Gaussian Splatting in the Wild with Generative PriorsDiffusion models → 3D, point cloud and scene generation
  72. Towards Robust Time-of-Flight Depth Denoising with Confidence-Aware Diffusion ModelDiffusion models → 3D, point cloud and scene generation
  73. Quantifying the Ease of Reproducing Training Data in Unconditional Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  74. ASP-VMUNet: Atrous Shifted Parallel Vision Mamba U-Net for Skin Lesion SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  75. Multi-Agent Deep Reinforcement Learning for Safe Autonomous Driving with RICS-Assisted MECEnd-to-end autonomous driving → Cooperative and V2X driving
  76. M2CD: A Unified MultiModal Framework for Optical-SAR Change Detection with Mixture of Experts and Self-DistillationKnowledge distillation → Detection and dense prediction distillation
  77. LangBridge: Interpreting Image as a Combination of Language EmbeddingsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  78. Exploring Textual Semantics Diversity for Image Transmission in Semantic Communication Systems using Visual Language ModelMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  79. Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget ForcingLLM reasoning → Diffusion reasoning and test-time scaling +1
  80. DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single ImageDiffusion models → 3D, point cloud and scene generation
  81. Flow to Learn: Flow Matching on Neural Network ParametersDiffusion models → Flow matching, time series and science
  82. EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-to-Video Diffusion ModelsDiffusion models → Video generation
  83. Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly DetectionDiffusion models → Flow matching, time series and science
  84. Can Vision-Language Models Answer Face to Face Questions in the Real-World?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  85. ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  86. Data-driven Mesoscale Weather Forecasting Combining Swin-Unet and Diffusion ModelsDiffusion models → Flow matching, time series and science
  87. BADGR: Bundle Adjustment Diffusion Conditioned by GRadients for Wide-Baseline Floor Plan ReconstructionDiffusion models → 3D, point cloud and scene generation
  88. Membership Inference Attacks on Large-Scale Models: A SurveyMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  89. Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning StepsLLM reasoning → Reasoning for agents, planning and code
  90. RGL: A Graph-Centric, Modular Framework for Efficient Retrieval-Augmented Generation on GraphsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  91. ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought ReasoningLLM reasoning → Multimodal reasoning
  92. DGTRSD & DGTRS-CLIP: A Dual-Granularity Remote Sensing Image-Text Dataset and Vision Language Foundation Model for AlignmentMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  93. A Comprehensive Analysis of Mamba for 3D Volumetric Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  94. ISPDiffuser: Learning RAW-to-sRGB Mappings with Texture-Aware Diffusion Models and Histogram-Guided Color ConsistencyDiffusion models → Image generation, text-to-image and editing
  95. CubeRobot: Grounding Language in Rubik's Cube Manipulation via Vision-Language ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  96. MARS: Memory-Enhanced Agents with Reflective Self-improvementLLM agents and tool use → Agent memory systems +1
  97. NeoRL-2: Near Real-World Benchmarks for Offline Reinforcement Learning with Extended Realistic ScenariosOffline RL and imitation learning from data → Offline RL algorithms
  98. DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking TuningLLM reasoning → Multimodal reasoning
  99. Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image DehazingDiffusion models → Inverse problems and image restoration
  100. MIRAGE: Multi-model Interface for Reviewing and Auditing Generative Text-to-Image AILLM safety and security → Vision-language and text-to-image safety
All 340
  1. Bridging the Sim-to-real Gap: A Control Framework for Imitation Learning of Model Predictive ControlOffline RL and imitation learning from data → Imitation learning methods
  2. GPT Meets Graphs and KAN Splines: Testing Novel Frameworks on Multitask Fine-Tuned GPT-2 with LoRA
  3. Reservoir Computing with a Single Oscillating Gas Bubble: Emphasizing the Chaotic Regime
  4. RP-SAM2: Refining Point Prompts for Stable Surgical Instrument Segmentation
  5. Hierarchical Attention Network for Interpretable ECG-based Heart Disease Classification
  6. Chemistry-aware battery degradation prediction under simulated real-world cyclic protocols
  7. SAFE: Self-Adjustment Federated Learning Framework for Remote Sensing Collaborative Perception
  8. Enhancing Clinical Decision-Making: Integrating Multi-Agent Systems with Ethical AI Governance
  9. Mapping Technological Futures: Anticipatory Discourse Through Text Mining
  10. Deep Learning-Based Hypoglycemia Classification Across Multiple Prediction Horizons
  11. Tensor Generalized Approximate Message Passing
  12. Hierarchical Adaptive Expert for Multimodal Sentiment Analysis
  13. TRIDIS: A Comprehensive Medieval and Early Modern Corpus for HTR and NER
  14. Unsupervised Ordering for Maximum Clique
  15. OAEI-LLM-T: A TBox Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching
  16. Taxonomy Inference for Tabular Data Using Large Language Models
  17. Enhancing Predictive Accuracy in Tennis: Integrating Fuzzy Logic and CV-GRNN for Dynamic Match Outcome and Player Momentum Analysis
  18. Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across Languages
  19. ImF: Implicit Fingerprint for Large Language Models
  20. Comparison of Metadata Representation Models for Knowledge Graph Embeddings
  21. Forecasting Volcanic Radiative Power (VPR) at Fuego Volcano Using Bayesian Regularized Neural Network
  22. Structured and sparse partial least squares coherence for multivariate cortico-muscular analysis
  23. CoMapGS: Covisibility Map-based Gaussian Splatting for Sparse Novel View Synthesis
  24. Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for Federated Continual Learning
  25. MindfulLIME: A Stable Solution for Explanations of Machine Learning Models with Enhanced Localization Precision -- A Medical Image Case Study
  26. Zero-Shot Human-Object Interaction Synthesis with Multimodal Priors
  27. Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable
  28. Domain Adaptation Framework for Turning Movement Count Estimation with Limited Data
  29. Efficient Model Development through Fine-tuning Transfer
  30. Peepers & Pixels: Human Recognition Accuracy on Low Resolution Faces
  31. "Is There Anything Else?'': Examining Administrator Influence on Linguistic Features from the Cookie Theft Picture Description Cognitive Test
  32. Extendable Planning via Multiscale Diffusion
  33. EBS-EKF: Accurate and High Frequency Event-based Star Tracking
  34. AI Identity, Empowerment, and Mindfulness in Mitigating Unethical AI Use
  35. Fundamental Limits of Perfect Concept Erasure
  36. Generative Linguistics, Large Language Models, and the Social Nature of Scientific Success
  37. Random feature-based double Vovk-Azoury-Warmuth algorithm for online multi-kernel learning
  38. Peer Disambiguation in Self-Reported Surveys using Graph Attention Networks
  39. Adaptive Orchestration for Large-Scale Inference on Heterogeneous Accelerator Systems Balancing Cost, Performance, and Resilience
  40. iNatAg: Multi-Class Classification Models Enabled by a Large-Scale Benchmark Dataset with 4.7M Images of 2,959 Crop and Weed Species
  41. Learning Scene-Level Signed Directional Distance Function with Ellipsoidal Priors and Neural Residuals
  42. Deep Learning Approaches for Blood Disease Diagnosis Across Hematopoietic Lineages
  43. A scalable gene network model of regulatory dynamics in single cells
  44. Experience Replay Addresses Loss of Plasticity in Continual Learning
  45. Hyperdimensional Uncertainty Quantification for Multimodal Uncertainty Fusion in Autonomous Vehicles Perception
  46. Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair
  47. Unsupervised Learning for Quadratic Assignment
  48. The Coralscapes Dataset: Semantic Scene Understanding in Coral Reefs
  49. SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining
  50. Untangling the Influence of Typology, Data and Model Architecture on Ranking Transfer Languages for Cross-Lingual POS Tagging
  51. Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields
  52. Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
  53. Automated Video-EEG Analysis in Epilepsy Studies: Advances and Challenges
  54. Vanishing Depth: Training Generalized Depth Adapters with Sinusoidal Depth Preprocessing for Pretrained RGB Encoders
  55. Optimizing Breast Cancer Detection in Mammograms: A Comprehensive Study of Transfer Learning, Resolution Reduction, and Multi-View Classification
  56. A Spatiotemporal Radar-Based Precipitation Model for Water Level Prediction and Flood Forecasting
  57. A stochastic gradient descent algorithm with random search directions
  58. Body Discovery of Embodied AI
  59. FuXi-RTM: A Physics-Guided Prediction Framework with Radiative Transfer Modeling
  60. Continual Learning With Quasi-Newton Methods
  61. Reverse Prompt: Cracking the Recipe Inside Text-to-Image Generation
  62. EventFly: Event Camera Perception from Ground to the Sky
  63. Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretraining
  64. CoLLM: A Large Language Model for Composed Image Retrieval
  65. FullDiT: Multi-Task Video Generative Foundation Model with Full Attention
  66. Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better
  67. Scaling Vision Pre-Training to 4K Resolution
  68. TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization
  69. Visuo-Tactile Object Pose Estimation for a Multi-Finger Robot Hand with Low-Resolution In-Hand Tactile Sensing
  70. AI threats to national security can be countered through an incident regime
  71. RCC-PFL: Robust Client Clustering under Noisy Labels in Personalized Federated Learning
  72. Dynamics of Structured Complex-Valued Hopfield Neural Networks
  73. Extensions of the regret-minimization algorithm for optimal design
  74. Identification of Average Treatment Effects in Nonparametric Panel Models
  75. GENIUS: A Generative Framework for Universal Multimodal Search
  76. Geometric Meta-Learning via Coupled Ricci Flow: Unifying Knowledge Representation and Quantum Entanglement
  77. Unpaired Translation of Chest X-ray Images for Lung Opacity Diagnosis via Adaptive Activation Masks and Cross-Domain Alignment
  78. An Overview of Low-Rank Structures in the Training and Adaptation of Large Models
  79. Capacity-Constrained Online Learning with Delays: Scheduling Frameworks and Regret Trade-offs
  80. Towards Online Multi-Modal Social Interaction Understanding
  81. Guarding against artificial intelligence--hallucinated citations: the case for full-text reference deposit
  82. Ab-initio simulation of excited-state potential energy surfaces with transferable deep quantum Monte Carlo
  83. Attention IoU: Examining Biases in CelebA using Attention Maps
  84. A Comparative Analysis of Word Segmentation, Part-of-Speech Tagging, and Named Entity Recognition for Historical Chinese Sources, 1900-1950
  85. Contextual Metric Meta-Evaluation by Measuring Local Metric Accuracy
  86. GyralNet Subnetwork Partitioning via Differentiable Spectral Modularity Optimization
  87. IgCraft: A versatile sequence generation framework for antibody discovery and engineering
  88. A Systematic Review of EEG-based Machine Intelligence Algorithms for Depression Diagnosis, and Monitoring
  89. Domain-incremental White Blood Cell Classification with Privacy-aware Continual Learning
  90. Bitstream Collisions in Neural Image Compression via Adversarial Perturbations
  91. Thinking agents for zero-shot generalization to qualitatively novel tasks
  92. Guidelines For The Choice Of The Baseline in XAI Attribution Methods
  93. Simulating Tracking Data to Advance Sports Analytics Research
  94. LENVIZ: A High-Resolution Low-Exposure Night Vision Benchmark Dataset
  95. SeLIP: Similarity Enhanced Contrastive Language Image Pretraining for Multi-modal Head MRI
  96. SemEval-2025 Task 9: The Food Hazard Detection Challenge
  97. In the Blink of an Eye: Instant Game Map Editing using a Generative-AI Smart Brush
  98. SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generation
  99. Gemma 3 Technical Report
  100. PyGraph: Robust Compiler Support for CUDA Graphs in PyTorch
  101. LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation
  102. Resilient Sensor Fusion under Adverse Sensor Failures via Multi-Modal Expert Fusion
  103. OpenLex3D: A Tiered Evaluation Benchmark for Open-Vocabulary 3D Scene Representations
  104. Interpretable Deep Regression Models with Interval-Censored Failure Time Data
  105. Splitting Answer Set Programs with respect to Intensionality Statements (Extended Version)
  106. A Survey on Event-driven 3D Reconstruction: Development under Different Categories
  107. LEMON: A Large Endoscopic MONocular Dataset and Foundation Model for Perception in Surgical Settings
  108. FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion
  109. GRN+: A Simplified Generative Reinforcement Network for Tissue Layer Analysis in 3D Ultrasound Images for Chronic Low-back Pain
  110. InterSliceBoost: Identifying Tissue Layers in Three-dimensional Ultrasound Images for Chronic Lower Back Pain (cLBP) Assessment
  111. How to RETIRE Tabular Data in Favor of Discrete Digital Signal Representation
  112. CamSAM2: Segment Anything Accurately in Camouflaged Videos
  113. On What Depends the Robustness of Multi-source Models to Missing Data in Earth Observation?
  114. Invertible Koopman neural operator for data-driven modeling of partial differential equations
  115. Rigid-Deformation Decomposition AI Framework for 3D Spatio-Temporal Prediction of Vehicle Collision Dynamics
  116. Fast localized urban microclimate emulator: wind and temperatures in unseen urban morphologies
  117. Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations
  118. High-Quality Spatial Reconstruction and Orthoimage Generation Using Efficient 2D Gaussian Splatting
  119. HausaNLP at SemEval-2025 Task 2: Entity-Aware Fine-tuning vs. Prompt Engineering in Entity-Aware Machine Translation
  120. Optimization of MedSAM model based on bounding box adaptive perturbation algorithm
  121. Optimal Path Planning and Cost Minimization for a Drone Delivery System Via Model Predictive Control
  122. AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation
  123. Unlocking the Hidden Potential of CLIP in Generalizable Deepfake Detection
  124. Deep Learning for Speech Emotion Recognition: A CNN Approach Utilizing Mel Spectrograms
  125. MultimodalStudio: A Heterogeneous Sensor Dataset and Framework for Neural Rendering across Multiple Imaging Modalities
  126. A multitask transformer to sign language translation using motion gesture primitives
  127. Towards Efficient Training of Graph Neural Networks: A Multiscale Approach
  128. BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction
  129. Towards Reliable Time Series Forecasting under Future Uncertainty: Ambiguity and Novelty Rejection Mechanisms
  130. OpenSDI: Spotting Diffusion-Generated Images in the Open World
  131. Enhancing Graphical Lasso: A Robust Scheme for Non-Stationary Mean Data
  132. HausaNLP at SemEval-2025 Task 3: Towards a Fine-Grained Model-Aware Hallucination Detection
  133. Recover from Horcrux: A Spectrogram Augmentation Method for Cardiac Feature Monitoring from Radar Signal Components
  134. Exploring Cultural Nuances in Emotion Perception Across 15 African Languages
  135. An Efficient Data Reuse with Tile-Based Adaptive Stationary for Transformer Accelerators
  136. Kernel Learning Assisted Synthesis Condition Exploration for Ternary Spinel
  137. Keyframe-Centric State-Space Modeling for Burst Image Super-Resolution
  138. Red Teaming with Artificial Intelligence-Driven Cyberattacks: A Scoping Review
  139. DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera Scenarios
  140. Optimization through In-Context Learning and Iterative LLM Prompting for Nuclear Engineering Design Problems
  141. Beyond Verifiable Rewards: Scaling Reinforcement Learning for Language Models to Unverifiable Data
  142. RL-finetuning LLMs from on- and off-policy data with a single algorithm
  143. Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation
  144. Single Shot AI-assisted quantification of KI-67 proliferation index in breast cancer
  145. Lean Formalization of Generalization Error Bound by Rademacher Complexity and Dudley's Entropy Integral
  146. GIViC: Generative Implicit Video Compression
  147. The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral Dilemmas
  148. Optimizing Language Models for Inference Time Objectives using Reinforcement Learning
  149. SACB-Net: Spatial-awareness Convolutions for Medical Image Registration
  150. Boosting the Transferability of Audio Adversarial Examples with Acoustic Representation Optimization
  151. Video Anomaly Detection with Contours -- A Study
  152. Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment
  153. Multi-agent Application System in Office Collaboration Scenarios
  154. Post-Hoc Calibrated Anomaly Detection
  155. SINR: Sparsity Driven Compressed Implicit Neural Representations
  156. Context-Efficient Retrieval with Factual Decomposition
  157. Improved tissue sodium concentration quantification in breast cancer by reducing partial volume effects: a preliminary study
  158. FedMM-X: A Trustworthy and Interpretable Framework for Federated Multi-Modal Learning in Dynamic Environments
  159. Dance Like a Chicken: Low-Rank Stylization for Human Motion Diffusion
  160. Causal Bayesian Optimization with Unknown Graphs
  161. Noise Resilient Over-The-Air Federated Learning In Heterogeneous Wireless Networks
  162. Practical Fine-Tuning of Autoregressive Models on Limited Handwritten Texts
  163. Tiling artifacts and trade-offs of feature normalization in the segmentation of large biological images
  164. Scene-agnostic Pose Regression for Visual Localization
  165. FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models
  166. VectorFit : Adaptive Singular & Bias Vector Fine-Tuning of Pre-trained Foundation Models
  167. Adaptive Weighted Parameter Fusion with CLIP for Class-Incremental Learning
  168. Towards Long-Range ENSO Prediction with an Explainable Deep Learning Model
  169. Pose-Based Fall Detection System: Efficient Monitoring on Standard CPUs
  170. SMT-EX: An Explainable Surrogate Modeling Toolbox for Mixed-Variables Design Exploration
  171. End-to-End Semantic Preservation in Text-Aware Image Compression Systems
  172. Exploring Disentangled and Controllable Human Image Synthesis: From End-to-End to Stage-by-Stage
  173. KSHSeek: Data-Driven Approaches to Mitigating and Detecting Knowledge-Shortcut Hallucinations in Generative Models
  174. GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers
  175. Bayesian Optimization of a Lightweight and Accurate Neural Network for Aerodynamic Performance Prediction
  176. TeLL Me what you cant see
  177. LogicXGNN: Grounded Logical Rules for Explaining Graph Neural Networks
  178. A-MESS: Anchor based Multimodal Embedding with Semantic Synchronization for Multimodal Intent Recognition
  179. Enhancing Small Language Models for Cross-Lingual Generalized Zero-Shot Classification with Soft Prompt Tuning
  180. Noisier2Inverse: Self-Supervised Learning for Image Reconstruction with Correlated Noise
  181. A Probabilistic Neuro-symbolic Layer for Algebraic Constraint Satisfaction
  182. GaussianUDF: Inferring Unsigned Distance Functions through 3D Gaussian Splatting
  183. G-DexGrasp: Generalizable Dexterous Grasping Synthesis Via Part-Aware Prior Retrieval and Prior-Assisted Generation
  184. Data-centric Federated Graph Learning with Large Language Models
  185. VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations
  186. COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian Splitting
  187. DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models
  188. A novel forecasting framework combining virtual samples and enhanced Transformer models for tourism demand forecasting
  189. EmoHead: Emotional Talking Head via Manipulating Semantic Expression Parameters
  190. A Prototype-Guided Coarse Annotations Refining Approach for Whole Slide Images
  191. Multi-modal 3D Pose and Shape Estimation with Computed Tomography
  192. Quantifying Symptom Causality in Clinical Decision Making: An Exploration Using CausaLM
  193. TraF-Align: Trajectory-aware Feature Alignment for Asynchronous Multi-agent Perception
  194. MVPortrait: Text-Guided Motion and Emotion Control for Multi-view Vivid Portrait Animation
  195. Causal invariant geographic network representations with feature and structural distribution shifts
  196. Towards Build Optimization Using Digital Twins
  197. Social Network User Profiling for Anomaly Detection Based on Graph Neural Networks
  198. Interpretable Generative Models through Post-hoc Concept Bottlenecks
  199. VGAT: A Cancer Survival Analysis Framework Transitioning from Generative Visual Question Answering to Genomic Reconstruction
  200. ImageSet2Text: Describing Sets of Images through Text
  201. Show and Segment: Universal Medical Image Segmentation via In-Context Learning
  202. From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting
  203. QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition
  204. Multi-Object Sketch Animation by Scene Decomposition and Motion Planning
  205. Optimal Parameter Adaptation for Safety-Critical Control via Safe Barrier Bayesian Optimization
  206. Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent
  207. Efficient IoT Intrusion Detection with an Improved Attention-Based CNN-BiLSTM Architecture
  208. E-PINNs: Epistemic Physics-Informed Neural Networks
  209. Divide-and-Conquer: Dual-Hierarchical Optimization for Semantic 4D Gaussian Spatting
  210. ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning
  211. MATT-GS: Masked Attention-based 3DGS for Robot Perception and Object Detection
  212. Wavelet-based Global-Local Interaction Network with Cross-Attention for Multi-View Diabetic Retinopathy Detection
  213. Substance over Style: Evaluating Proactive Conversational Coaching Agents
  214. Long-Context Autoregressive Video Modeling with Next-Frame Prediction
  215. How to optimize K-means?
  216. Iterative Hypothesis Generation for Scientific Discovery with Monte Carlo Nash Equilibrium Self-Refining Trees
  217. Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation
  218. Centroid Decision Forest
  219. BIMII-Net: Brain-Inspired Multi-Iterative Interactive Network for RGB-T Road Scene Semantic Segmentation
  220. Observation Adaptation via Annealed Importance Resampling for Partially Observable Markov Decision Processes
  221. UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design
  222. Fine-grained Textual Inversion Network for Zero-Shot Composed Image Retrieval
  223. Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment
  224. Adaptive Wavelet Filters as Practical Texture Feature Amplifiers for Parkinson's Disease Screening in OCT
  225. No Black Box Anymore: Demystifying Clinical Predictive Modeling with Temporal-Feature Cross Attention Mechanism
  226. LogicLearner: A Tool for the Guided Practice of Propositional Logic Proofs
  227. Machine-assisted writing evaluation: Exploring pre-trained language models in analyzing argumentative moves
  228. Multiscale Feature Importance-based Bit Allocation for End-to-End Feature Coding for Machines
  229. Context-Aware Semantic Segmentation: Enhancing Pixel-Level Understanding with Large Language Models for Advanced Vision Applications
  230. CoMAC: Conversational Agent for Multi-Source Auxiliary Context with Sparse and Symmetric Latent Interactions
  231. PHEONA: An Evaluation Framework for Large Language Model-based Approaches to Computational Phenotyping
  232. Linguistic Blind Spots of Large Language Models
  233. Adaptive Multi-Order Graph Regularized NMF with Dual Sparsity for Hyperspectral Unmixing
  234. SCI-IDEA: Context-Aware Scientific Ideation Using Token and Sentence Embeddings
  235. Data-Driven, ML-assisted Approaches to Problem Well-Posedness
  236. L2FMamba: Lightweight Light Field Image Super-Resolution with State Space Model
  237. Limited-angle x-ray nano-tomography with machine-learning enabled iterative reconstruction engine
  238. Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Grounding
  239. HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting
  240. Face Spoofing Detection using Deep Learning