mlsanityData to 7 Oct 2026

Papers

New on arXiv

Fri 21 Nov 2025

335 papers

  1. End-to-End Transformer Acceleration Through Processing-in-Memory ArchitecturesEfficient LLM inference and serving → Early exit and edge inference
  2. EduMod-LLM: A Modular Approach for Designing Flexible and Transparent Educational AssistantsLLM agents and tool use → Educational agents and math problem solving
  3. Polarity-Aware Probing for Quantifying Latent Alignment in Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  4. Asking LLMs to Verify First is Almost Free LunchLLM reasoning → Test-time compute and efficient thinking
  5. HUMORCHAIN: Theory-Guided Multi-Stage Reasoning for Interpretable Multimodal Humor GenerationLLM reasoning → Multimodal reasoning
  6. A Benchmark for Procedural Memory Retrieval in Language AgentsLLM agents and tool use → Agent memory systems
  7. Beyond Component Strength: Synergistic Integration and Adaptive Calibration in Multi-Agent RAG SystemsRetrieval-augmented generation → Agentic RAG, agents and memory
  8. Affective Multimodal Agents with Proactive Knowledge Grounding for Emotionally Aligned Marketing DialogueLLM agents and tool use → Social simulation and multi-agent debate
  9. Personalized Reward Modeling for Text-to-Image GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  10. Less is More: Data-Efficient Adaptation for Controllable Text-to-Video GenerationDiffusion models → Video generation
  11. Show Me: Unifying Instructional Image and Video Generation with Diffusion ModelsDiffusion models → Video generation
  12. Score-Regularized Joint Sampling with Importance Weights for Flow MatchingDiffusion models → Flow matching, time series and science
  13. Attention Guided Alignment in Efficient Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  14. Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?World models → Embodied and robot world models
  15. Episodic Memory in Agentic Frameworks: Suggesting Next TasksLLM agents and tool use → Agent memory systems
  16. Deepfake Geography: Detecting AI-Generated Satellite ImagesDiffusion models → Inverse problems and image restoration
  17. The Software Engineering Simulations Lab: Agentic AI for RE Quality SimulationsLLM agents and tool use → Software engineering coding agents
  18. CORA: Consistency-Guided Semi-Supervised Framework for Reasoning SegmentationLLM reasoning → Multimodal reasoning +1
  19. Diffusion Models are Molecular Dynamics SimulatorsDiffusion models → Diffusion foundations and sampling
  20. VisReason: A Large-Scale Dataset for Visual Chain-of-Thought ReasoningLLM reasoning → Multimodal reasoning
  21. M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent BenchmarkLLM agents and tool use → Tool learning and function calling
  22. Ternary Gamma Semirings as a Novel Algebraic Framework for Learnable Symbolic ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  23. The Potential and Limitations of Vision-Language Models for Human Motion Understanding: A Case Study in Data-Driven Stroke RehabilitationMultimodal LLMs / vision-language models → Medical vision-language models
  24. Can Vision-Language Models Count? A Synthetic Benchmark and Analysis of Attention-Based InterventionsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  25. Understanding Counting Mechanisms in Large Language and Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  26. Liberating Logic in the Age of AI: Going Beyond Programming with Computational ThinkingLLM reasoning → Reasoning for agents, planning and code
  27. ARISE: Agentic Rubric-Guided Iterative Survey Engine for Automated Scholarly Paper GenerationLLM agents and tool use → Web, search, and research agents
  28. LLM and Agent-Driven Data Analysis: A Systematic Approach for Enterprise Applications and System-level DeploymentLLM agents and tool use → Web, search, and research agents
  29. Bridging Symbolic Control and Neural Reasoning in LLM Agents -- The Structured Cognitive LoopLLM reasoning → Reasoning for agents, planning and code +1
  30. Cognitive Inception: Agentic Reasoning against Visual Deceptions by Injecting SkepticismLLM reasoning → Prompting and chain-of-thought reasoning +2
  31. MURMUR: Using cross-user chatter to break collaborative language agents in groupsLLM agents and tool use → Agent threats, guardrails and governance
  32. Evaluating Adversarial Vulnerabilities in Modern Large Language ModelsLLM safety and security → Jailbreaking
  33. RynnVLA-002: A Unified Vision-Language-Action and World ModelWorld models → Embodied and robot world models +1
  34. EvDiff: Event-Based Video Reconstruction using One-Step Diffusion ModelsDiffusion models → Video generation
  35. Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal ModelsLLM reasoning → Multimodal reasoning
  36. Counterfactual World Models via Digital Twin-conditioned Video DiffusionWorld models → Latent predictive world models +1
  37. Masked-and-Reordered Self-Supervision for Reinforcement Learning from Verifiable RewardsLLM reasoning → Reinforcement learning for reasoning
  38. MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  39. Beyond Multiple Choice: Verifiable OpenQA for Robust Vision-Language RFTMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  40. Sparse Mixture-of-Experts for Multi-Channel Imaging: Are All Channel Interactions Required?Mixture-of-experts → Vision mixture-of-experts
  41. MCMoE: Completing Missing Modalities with Mixture of Experts for Incomplete Multimodal Action Quality AssessmentMixture-of-experts → Multimodal MoE models
  42. IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial NavigationLLM reasoning → Spatial and embodied reasoning +1
  43. METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action ModelVision-language-action models → Human-video and latent-action pretraining
  44. UAM: A Unified Attention-Mamba Backbone of Multimodal Framework for Tumor Cell ClassificationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  45. Robot Confirmation Generation and Action Planning Using Long-context Q-Former Integrated with Multimodal LLMMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  46. Agentifying Agentic AILLM agents and tool use → General LLM agent frameworks and benchmarks
  47. Agentic Verification of Software SystemsLLM agents and tool use → Educational agents and math problem solving
  48. Humanlike Multi-user Agent (HUMA): Designing a Deceptively Human AI Facilitator for Group ChatsLLM agents and tool use → General LLM agent frameworks and benchmarks
  49. SpatialGeo:Boosting Spatial Reasoning in Multimodal LLMs via Geometry-Semantics FusionLLM reasoning → Spatial and embodied reasoning +1
  50. Estonian WinoGrande Dataset: Comparative Analysis of LLM Performance on Human and Machine TranslationLLM reasoning → Reasoning benchmarks and evaluation
  51. Cross-cultural value alignment frameworks for responsible AI governance: Evidence from China-West comparative analysisLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  52. A Little More Like This: Text-to-Image Retrieval with Vision-Language Models Using Relevance FeedbackMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  53. Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment FormatsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  54. FlexiFlow: decomposable flow matching for generation of flexible molecular ensembleDiffusion models → Flow matching, time series and science
  55. A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM AgentsLLM agents and tool use → Agent memory systems
  56. VLA-4D: Embedding 4D Awareness into Vision-Language-Action Models for SpatioTemporally Coherent Robotic ManipulationVision-language-action models → 3D and spatial-aware VLA
  57. Designing Domain-Specific Agents via Hierarchical Task Abstraction MechanismLLM agents and tool use → Multimodal and embodied agents
  58. FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought OracleLLM reasoning → Spatial and embodied reasoning
  59. Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language ModelsLLM reasoning → Hallucination detection and mitigation
  60. DiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics +1
  61. One-Step Diffusion Transformer for Controllable Real-World Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  62. UI-CUBE: Enterprise-Grade Computer Use Agent Benchmarking Beyond Task Accuracy to Operational ReliabilityLLM agents and tool use → GUI and mobile agents
  63. Training Foundation Models on a Full-Stack AMD Platform: Compute, Networking, and System DesignMixture-of-experts → Efficient MoE training and inference systems
  64. ChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and BetterLLM reasoning → Multimodal reasoning
  65. Geometric-disentangelment UnlearningLLM safety and security → Machine unlearning
  66. Sparse Reasoning is Enough: Biological-Inspired Framework for Video Anomaly Detection with Large Pre-trained ModelsLLM reasoning → Chain-of-thought reasoning for driving
  67. Why Do Language Model Agents Whistleblow?LLM agents and tool use → Agent threats, guardrails and governance
  68. Diversity Has Always Been There in Your Visual Autoregressive ModelsDiffusion models → Image generation, text-to-image and editing
  69. OmniPT: Unleashing the Potential of Large Vision Language Models for Pedestrian Tracking and UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  70. PathAgent: Toward Interpretable Analysis of Whole-slide Pathology Images via Large Language Model-based Agentic ReasoningLLM reasoning → Clinical and biomedical applications +1
  71. Parametric Retrieval-Augmented Generation using Latent Routing of LoRA AdaptersRetrieval-augmented generation → RAG pipeline design and evaluation
  72. Do Vision-Language Models Understand Visual Persuasiveness? A Diagnosis via Visual Persuasive FactorsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  73. Energy Scaling Laws for Diffusion Models: Quantifying Compute in Image GenerationDiffusion models → Diffusion foundations and sampling
  74. ReVul-CoT: Towards Effective Software Vulnerability Assessment with Retrieval-Augmented Generation and Chain-of-Thought PromptingLLM reasoning → Reasoning for agents, planning and code +1
  75. Budget-Aware Tool Use Enables Effective Agent ScalingLLM reasoning → Reasoning for agents, planning and code +1
  76. FLUID: Training-Free Face De-identification via Latent Identity SubstitutionDiffusion models → Image generation, text-to-image and editing
  77. Vision Language Models are Confused TouristsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  78. FIRM: Federated In-client Regularized Multi-objective Alignment for Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  79. RadioKMoE: Knowledge-Guided Radiomap Estimation with Kolmogorov-Arnold Networks and Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
  80. ToC: Tree-of-Claims Search with Multi-Agent Language ModelsLLM agents and tool use → Web, search, and research agents
  81. Optimizing PyTorch Inference with LLM-Based Multi-Agent SystemsLLM agents and tool use → Software engineering coding agents
  82. Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow ModelsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  83. Fine-grained MoE Load Balancing with Linear ProgrammingMixture-of-experts → Efficient MoE training and inference systems
  84. RASTP: Representation-Aware Semantic Token Pruning for Generative Recommendation with Semantic IdentifiersEfficient LLM inference and serving → Visual token pruning in multimodal models
  85. MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  86. Rethinking Diffusion Model-Based Video Super-Resolution: Leveraging Dense Guidance from Aligned FeaturesDiffusion models → Inverse problems and image restoration
  87. Diffusion-Inversion-Net (DIN): An End-to-End Direct Probabilistic Framework for Characterizing Hydraulic Conductivities and Quantifying UncertaintyDiffusion models → Flow matching, time series and science
  88. UniModel: A Visual-Only Framework for Unified Multimodal Understanding and GenerationDiffusion models → Image generation, text-to-image and editing
  89. Hybrid Differential Reward: Combining Temporal Difference and Action Gradients for Efficient Multi-Agent Reinforcement Learning in Cooperative DrivingEnd-to-end autonomous driving → Cooperative and V2X driving
  90. Warm Diffusion: Recipe for Blur-Noise Mixture Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  91. R-AVST: Empowering Video-LLMs with Fine-Grained Spatio-Temporal Reasoning in Complex Audio-Visual ScenariosLLM reasoning → Audio-language model reasoning +1
  92. Improving Latent Reasoning in LLMs via Soft Concept MixingLLM reasoning → Test-time compute and efficient thinking
  93. Parts-Mamba: Augmenting Joint Context with Part-Level Scanning for Occluded Human SkeletonState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  94. Enriching Taxonomies Using Large Language Models
  95. A Cloud-Based Cross-Modal Transformer for Emotion Recognition and Adaptive Human-Computer Interaction
  96. Modular AI-Powered Interviewer with Dynamic Question Generation and Expertise Profiling
  97. Artificial Intelligence as a Training Tool in Clinical Psychology: A Comparison of Text-Based and Avatar Simulations
  98. QoS-Aware Dynamic CU Selection in O-RAN with Graph-Based Reinforcement Learning
  99. MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms
  100. Physics-Informed Machine Learning for Steel Development: A Computational Framework and CCT Diagram Modelling
All 335
  1. A Multiscale Geometric Method for Capturing Relational Topic Alignment
  2. A cross-species neural foundation model for end-to-end speech decoding
  3. Science Is Falling Behind the Frontier: Foundation Model Adoption Across Half a Million Papers
  4. R2Q: Towards Robust 2-Bit Large Language Models via Residual Refinement Quantization
  5. Closing the Performance Gap Between AI and Radiologists in Chest X-Ray Reporting
  6. RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language Models
  7. Identifying Quantum Structure in AI Language: Evidence for Evolutionary Convergence of Human and Artificial Cognition
  8. Morality in AI. A plea to embed morality in LLM architectures and frameworks
  9. SG-OIF: A Stability-Guided Online Influence Framework for Reliable Vision Data
  10. Hidden markov model to predict tourists visited place
  11. Temperature in SLMs: Impact on Incident Categorization in On-Premises Environments
  12. Systemic approach for modeling a generic smart grid
  13. SparOA: Sparse and Operator-aware Hybrid Scheduling for Edge DNN Inference
  14. JigsawComm: Joint Semantic Feature Encoding and Transmission for Communication-Efficient Cooperative Perception
  15. Internalizing Tools as Morphisms in Graded Transformers
  16. Learning to Debug: LLM-Organized Knowledge Trees for Solving RTL Assertion Failures
  17. Unified Class and Domain Incremental Learning with Mixture of Experts for Indoor Localization
  18. Toward explainable AI approaches for breast imaging: adapting foundation models to diverse populations
  19. Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch
  20. Analog Physical Systems Can Exhibit Double Descent
  21. QAL: A Loss for Recall Precision Balance in 3D Reconstruction
  22. A novel k-means clustering approach using two distance measures for Gaussian data
  23. High-Accuracy List-Decodable Mean Estimation
  24. APRIL: Annotations for Policy evaluation with Reliable Inference from LLMs
  25. Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberation
  26. Adaptive Layer-Wise Transformations for Post-Training Quantization of Large Language Models
  27. PoETa v2: Toward More Robust Evaluation of Large Language Models in Portuguese
  28. REXO: Indoor Multi-View Radar Object Detection via 3D Bounding Box Diffusion
  29. A Stitch in Time: Learning Procedural Workflow via Self-Supervised Plackett-Luce Ranking
  30. Pillar-0: A New Frontier for Radiology Foundation Models
  31. Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models
  32. Semi-Supervised Federated Multi-Label Feature Selection with Fuzzy Information Measures
  33. Physical Reinforcement Learning
  34. Data-Driven Predictive Modeling of Microfluidic Cancer Cell Separation Using a Deterministic Lateral Displacement Device
  35. A Variance-Based Analysis of Sample Complexity for Grid Coverage
  36. Variational Estimators for Node Popularity Models
  37. Smoothed Agnostic Learning of Halfspaces over the Hypercube
  38. PrismSSL: One Interface, Many Modalities; A Single-Interface Library for Multimodal Self-Supervised Learning
  39. Weighted Birkhoff Averages Accelerate Data-Driven Methods
  40. LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation
  41. When Active Learning Fails, Uncalibrated Out of Distribution Uncertainty Quantification Might Be the Problem
  42. Latent Dirichlet Transformer VAE for Hyperspectral Unmixing with Bundled Endmembers
  43. Periodicity-Enforced Neural Network for Designing Deterministic Lateral Displacement Devices
  44. Delta-ML Ensembles for Selecting Quantum Chemistry Methods to Compute Intermolecular Interactions
  45. SPIDER: Spatial Image CorresponDence Estimator for Robust Calibration
  46. AEGIS: Preserving privacy of 3D Facial Avatars with Adversarial Perturbations
  47. Computational frame analysis revisited: On LLMs for studying news coverage
  48. Robust Detection of Retinal Neovascularization in Widefield Optical Coherence Tomography
  49. AI- and Ontology-Based Enhancements to FMEA for Advanced Systems Engineering: Current Developments and Future Directions
  50. Towards Open-Ended Visual Scientific Discovery with Sparse Autoencoders
  51. AngioDG: Interpretable Channel-informed Feature-modulated Single-source Domain Generalization for Coronary Vessel Segmentation in X-ray Angiography
  52. Prequential posteriors
  53. Learning the Value of Value Learning
  54. Quantum Fourier Transform Based Kernel for Solar Irrandiance Forecasting
  55. DeepCoT: Deep Continual Transformers for Real-Time Inference on Data Streams
  56. Enhancing Adversarial Transferability through Block Stretch and Shrink
  57. Boosting Brain-inspired Path Integration Efficiency via Learning-based Replication of Continuous Attractor Neurodynamics
  58. Dual-Path Knowledge-Augmented Contrastive Alignment Network for Spatially Resolved Transcriptomics
  59. Datacenters in the Desert: Feasibility and Sustainability of LLM Inference in the Middle East
  60. A Cross-Cultural Assessment of Human Ability to Detect LLM-Generated Fake News about South Africa
  61. Motion-Aware Vision-Reference Alignment for Referring Multi-Object Tracking
  62. Research and Prototyping Study of an LLM-Based Chatbot for Electromagnetic Simulations
  63. Chatbots to strengthen democracy: An interdisciplinary seminar to train identifying argumentation techniques of science denial
  64. A Hybrid Classical-Quantum Fine Tuned BERT for Text Classification
  65. Lane-Frame Quantum Multimodal Driving Forecasts for the Trajectory of Autonomous Vehicles
  66. Person Recognition in Aerial Surveillance: A Decade Survey
  67. Empa: An AI-Powered Virtual Mentor for Developing Global Collaboration Skills in HPC Education
  68. MedPEFT-CL: Dual-Phase Parameter-Efficient Continual Learning with Medical Semantic Adapter and Bidirectional Memory Consolidation
  69. GANGR: GAN-Assisted Scalable and Efficient Global Routing Parallelization
  70. CubeletWorld: A New Abstraction for Scalable 3D Modeling
  71. Native 3D Editing with Full Attention
  72. Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination
  73. Harnessing Data from Clustered LQR Systems: Personalized and Collaborative Policy Optimization
  74. An Artificial Intelligence Framework for Measuring Human Spine Aging Using MRI
  75. Radar2Shape: 3D Shape Reconstruction from High-Frequency Radar using Multiresolution Signed Distance Functions
  76. Enhancing Quranic Learning: A Multimodal Deep Learning Approach for Arabic Phoneme Recognition
  77. Addressing A Posteriori Performance Degradation in Neural Network Subgrid Stress Models
  78. PersonaAgent with GraphRAG: Community-Aware Knowledge Graphs for Personalized LLM
  79. SRA-CP: Spontaneous Risk-Aware Selective Cooperative Perception
  80. GPR-OdomNet: Difference and Similarity-Driven Odometry Estimation Network for Ground Penetrating Radar-Based Localization
  81. Improving Multimodal Distillation for 3D Semantic Segmentation under Domain Shift
  82. Illustrator's Depth: Monocular Layer Index Prediction for Image Decomposition
  83. Planning with Sketch-Guided Verification for Physics-Aware Video Generation
  84. Unmasking Airborne Threats: Guided-Transformers for Portable Aerosol Mass Spectrometry
  85. GRAPHIC--Guidelines for Reviewing Algorithmic Practices in Human-centred Design and Interaction for Creativity
  86. REMSA: Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent
  87. InTAct: Interval-based Task Activation Consolidation for Continual Learning
  88. A Framework for Adaptive Stabilisation of Nonlinear Stochastic Systems
  89. Multi-Agent Pointer Transformer: Seq-to-Seq Reinforcement Learning for Multi-Vehicle Dynamic Pickup-Delivery Problems
  90. SMILE: A Composite Lexical-Semantic Metric for Question-Answering Evaluation
  91. Towards fully differentiable neural ocean model with Veros
  92. Self-Supervised Learning by Curvature Alignment
  93. Preventing Shortcut Learning in Medical Image Analysis through Intermediate Layer Knowledge Distillation from Specialist Teachers
  94. DS-Span: Single-Phase Discriminative Subgraph Mining for Efficient Graph Embeddings
  95. CREST: Improving Interpretability and Effectiveness of Troubleshooting at Ericsson through Criterion-Specific Trouble Report Retrieval
  96. SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding
  97. The Impact of Off-Policy Training Data on Probe Generalisation
  98. PUCP-Metrix: An Open-source and Comprehensive Toolkit for Linguistic Analysis of Spanish Texts
  99. Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes
  100. Designing and Generating Diverse, Equitable Face Image Datasets for Face Verification Tasks
  101. MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration
  102. Selective Rotary Position Embedding
  103. Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation Distributions
  104. A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias
  105. Quantum Masked Autoencoders for Vision Learning
  106. R2PS: Worst-Case Robust Real-Time Pursuit Strategies under Partial Observability
  107. SVRecon: Sparse Voxel Rasterization for Surface Reconstruction
  108. ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP
  109. SuperQuadricOcc: Real-Time Self-Supervised Semantic Occupancy Estimation with Superquadric Volume Rendering
  110. Don't Learn, Ground: A Case for Natural Language Inference with Visual Grounding
  111. DSeq-JEPA: Discriminative Sequential Joint-Embedding Predictive Architecture
  112. Learning Latent Transmission and Glare Maps for Lens Veiling Glare Removal
  113. Convergence and stability of Q-learning in Hierarchical Reinforcement Learning
  114. Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networks
  115. Loomis Painter: Reconstructing the Painting Process
  116. Refracting Reality: Generating Images with Realistic Transparent Objects
  117. ReBaPL: Repulsive Bayesian Prompt Learning
  118. A new kid on the block: Distributional semantics predicts the word-specific tone signatures of monosyllabic words in conversational Taiwan Mandarin
  119. AI Workers, Geopolitics, and Algorithmic Collective Action
  120. MusicAIR: A Multimodal AI Music Generation Framework Powered by an Algorithm-Driven Core
  121. NoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Prior
  122. FORWARD: Dataset of a forwarder operating in rough terrain
  123. Self-supervised denoising of raw tomography detector data for improved image reconstruction
  124. MuM: Multi-View Masked Image Modeling for 3D Vision
  125. BiFingerPose: Bimodal Finger Pose Estimation for Touch Devices
  126. Large Language Models for Sentiment Analysis to Detect Social Challenges: A Use Case with South African Languages
  127. MolSight: Optical Chemical Structure Recognition with SMILES Pretraining, Multi-Granularity Learning and Reinforcement Learning
  128. SAVeD: Semantic Aware Version Discovery
  129. A First Full Physics Benchmark for Highly Granular Calorimeter Surrogates
  130. Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation
  131. Leveraging CVAE for Joint Configuration Estimation of Multifingered Grippers from Point Cloud Data
  132. Automobile demand forecasting: Spatiotemporal and hierarchical modeling, life cycle dynamics, and user-generated online information
  133. Range-Edit: Semantic Mask Guided Outdoor LiDAR Scene Editing
  134. DISCA: A Digital In-memory Stochastic Computing Architecture Using A Compressed Bent-Pyramid Format
  135. Enforcing governing equation constraints in neural PDE solvers via training-free projections
  136. Blind Deconvolution for Color Images Using Normalized Quaternion Kernels
  137. Equivariant-Aware Structured Pruning for Efficient Edge Deployment: A Comprehensive Framework with Adaptive Fine-Tuning
  138. Predicting Social Media User Actions: A Hybrid Approach for Common and Rare Behavior Prediction on Bluesky
  139. A Fast Binary Splitting Approach for Non-Adaptive Learning of ErdHos--R'enyi Graphs
  140. Lost in Translation and Noise: A Deep Dive into the Failure Modes of VLMs on Real-World Tables
  141. Algorithmic design and implementation considerations of deep MPC
  142. Generating transition states of chemical reactions via distance-geometry-based flow matching
  143. Intrinsic preservation of plasticity in continual quantum learning
  144. TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making
  145. QueryOcc: Query-based Self-Supervision for 3D Semantic Occupancy
  146. PARROT: Persuasion and Agreement Robustness Rating of Output Truth -- A Sycophancy Robustness Benchmark for LLMs
  147. DelTriC: A Novel Clustering Method with Accurate Outlier
  148. Dual-domain Adaptation Networks for Realistic Image Super-resolution
  149. FisheyeGaussianLift: BEV Feature Lifting for Surround-View Fisheye Camera Perception
  150. Scaling Self-Supervised and Cross-Modal Pretraining for Volumetric CT Transformers
  151. SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priors
  152. E3-Pruner: Towards Efficient, Economical, and Effective Layer Pruning for Large Language Models
  153. Continual Alignment for SAM: Rethinking Foundation Models for Medical Image Segmentation in Continual Learning
  154. Reconstruction of Surface EMG Signal using IMU data for Upper Limb Actions
  155. Real Noise Decoupling for Hyperspectral Image Denoising
  156. AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale
  157. PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention
  158. Attention-Guided Feature Fusion (AGFF) Model for Integrating Statistical and Semantic Features in News Text Classification
  159. Benchmarking Nighttime Traffic Sign Recognition with Illumination-Adaptive Detection and Semantic Attribute Reasoning
  160. Investigating self-supervised representations for audio-visual deepfake detection
  161. On the Predictive Skill of Artificial Intelligence-based Weather Models for Extreme Events using Uncertainty Quantification
  162. MIR: Efficient Exploration in Episodic Multi-Agent Reinforcement Learning via Mutual Intrinsic Reward
  163. The Belief-Desire-Intention Ontology for modelling mental reality and agency
  164. The PLLuM Instruction Corpus
  165. Exploring the added value of pretherapeutic MR descriptors in predicting breast cancer pathologic complete response to neoadjuvant chemotherapy
  166. UI-Styler: Ultrasound Image Style Transfer with Class-Aware Prompts for Cross-Device Diagnosis Using a Frozen Black-Box Inference Network
  167. LangMark: A Multilingual Dataset for Automatic Post-Editing
  168. A lightweight detector for real-time detection of remote sensing images
  169. Learning to Look Closer: A New Instance-Wise Loss for Small Cerebral Lesion Segmentation
  170. Device-Guided Music Transfer
  171. A Multi-Stage Optimization Framework for Deploying Learned Image Compression on FPGAs
  172. Four decades of circumpolar super-resolved satellite land surface temperature data
  173. Off the Planckian Locus: Using 2D Chromaticity to Improve In-Camera Color
  174. Learning to Compress: Unlocking the Potential of Large Language Models for Text Representation
  175. Towards Blind Lens Aberration Correction via Large LensLib Pre-training and Discrete Degradation Priors
  176. Layer-wise Weight Selection for Power-Efficient Neural Network Acceleration
  177. PEGS: Physics-Event Enhanced Large Spatiotemporal Motion Reconstruction via 3D Gaussian Splatting
  178. AutoGraphAD: Unsupervised network anomaly detection using Variational Graph Autoencoders
  179. Dissecting Quantum Reinforcement Learning: A Systematic Evaluation of Key Components
  180. Bridging Visual Affective Gap: Borrowing Textual Knowledge by Learning from Noisy Image-Text Pairs
  181. SPAGS: Sparse-View Articulated Object Reconstruction from Single State via Planar Gaussian Splatting
  182. Spanning Tree Autoregressive Visual Generation
  183. MUCH: A Multilingual Claim Hallucination Benchmark
  184. An Efficient Computational Framework for Discrete Fuzzy Numbers Based on Total Orders
  185. Hash Collisions in Molecular Fingerprints: Effects on Property Prediction and Bayesian Optimization
  186. Interpretability from the Ground Up: Stakeholder-Centric Design of Automated Scoring in Educational Assessments
  187. ReBrain: Brain MRI Reconstruction from Sparse CT Slice via Retrieval-Augmented Diffusion
  188. REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting
  189. Patient-level Information Extraction by Consistent Integration of Textual and Tabular Evidence with Bayesian Networks
  190. RL-AD-Net: Reinforcement Learning Guided Adaptive Displacement in Latent Space for Refined Point Cloud Completion
  191. RoomPlanner: Explicit Layout Planner for Easier LLM-Driven 3D Room Generation
  192. RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis
  193. MedImageInsight for Thoracic Cavity Health Classification from Chest X-rays
  194. CLLMRec: LLM-powered Cognitive-Aware Concept Recommendation via Semantic Alignment and Prerequisite Knowledge Distillation
  195. Step-E: A Differentiable Data Cleaning Framework for Robust Learning with Noisy Labels
  196. DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing
  197. Parameter-Free Neural Lens Blur Rendering for High-Fidelity Composites
  198. Supervised Fine Tuning of Large Language Models for Domain Specific Knowledge Graph Construction:A Case Study on Hunan's Historical Celebrities
  199. Mask the Redundancy: Evolving Masking Representation Learning for Multivariate Time-Series Clustering
  200. Self-Localizing MIMO Beam Mapping with Continuously Evolving Channel Memory
  201. VLM-Augmented Degradation Modeling for Image Restoration Under Adverse Weather Conditions
  202. MirrorMind: Empowering OmniScientist with the Expert Perspectives and Collective Knowledge of Human Scientists
  203. DepthFocus: Controllable Depth Estimation for See-Through Scenes
  204. DReX: Pure Vision Fusion of Self-Supervised and Convolutional Representations for Image Complexity Prediction
  205. ARQUSUMM: Argument-aware Quantitative Summarization of Online Conversations
  206. A Diversity-optimized Deep Ensemble Approach for Accurate Plant Leaf Disease Detection
  207. Gradient-Driven Natural Selection for Compact 3D Gaussian Splatting
  208. The Finer the Better: Towards Granular-aware Open-set Domain Generalization
  209. Gradient descent dynamics for deep equilibrium models
  210. Real-Time Cooked Food Image Synthesis and Visual Cooking Progress Monitoring on Edge Devices
  211. Two Heads Better than One: Dual Degradation Representation for Blind Super-Resolution
  212. Comparing verbal, visual and combined explanations for Bayesian Network inferences
  213. MatPedia: A Universal Generative Foundation for High-Fidelity Material Synthesis
  214. Point-Supervised Facial Expression Spotting with Gaussian-Based Instance-Adaptive Intensity Modeling
  215. FingerCap: Fine-grained Finger-level Hand Motion Captioning
  216. MobileOcc: A Human-Aware Semantic Occupancy Dataset for Mobile Robots
  217. Flow-Guided Implicit Neural Representation for Motion-Aware Dynamic MRI Reconstruction
  218. OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios
  219. Shape-preserving Tooth Segmentation from CBCT Images Using Deep Learning with Semantic and Shape Awareness
  220. A novel approach to classification of ECG arrhythmia types with latent ODEs
  221. OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists
  222. CroTad: A Contrastive Reinforcement Learning Framework for Online Trajectory Anomaly Detection
  223. A Hybrid Computational Intelligence Framework for scRNA-seq Imputation: Integrating scRecover and Random Forests
  224. DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attribution
  225. PepEVOLVE: Position-Aware Dynamic Peptide Optimization via Group-Relative Advantage
  226. Q-REAL: Towards Realism and Plausibility Evaluation for AI-Generated Content
  227. Predicting Talent Breakout Rate using Twitter and TV data
  228. Predicting the Emergence of Induction Heads in Language Model Pretraining
  229. Glass Surface Detection: Leveraging Reflection Dynamics in Flash/No-flash Imagery
  230. Latent Reasoning in TRMs is Secretly a Policy Improvement Operator
  231. Generative AI in Sociological Research: State of the Discipline
  232. PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling
  233. Aggregating Direct and Indirect Neighbors through Graph Linear Transformations
  234. Align & Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment
  235. The Joint Gromov Wasserstein Objective for Multiple Object Matching