mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 24 Feb 2025

378 papers

  1. Improving Interactive Diagnostic Ability of a Large Language Model Agent Through Clinical Experience LearningLLM agents and tool use → Medical and scientific domain agents
  2. LogitLens4LLMs: Extending Logit Lens Analysis to Modern Large Language ModelsMechanistic interpretability → Knowledge and representations inside LLMs
  3. Vision Language Models in MedicineMultimodal LLMs / vision-language models → Medical vision-language models
  4. RSPO: Regularized Self-Play Alignment of Large Language ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  5. Streaming Looking Ahead with Token-level Self-rewardLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  6. Evaluating Large Language Models on the Spanish Medical Intern Resident (MIR) Examination 2024/2025:A Comparative Analysis of Clinical Reasoning and Knowledge ApplicationLLM reasoning → Clinical and biomedical applications
  7. KVCrush: Key value cache size-reduction using similarity in head-behaviourEfficient LLM inference and serving → KV cache optimization
  8. ARACNE: An LLM-Based Autonomous Shell Pentesting AgentLLM agents and tool use → Agent threats, guardrails and governance
  9. Reinforcement Learning-based Approach for Vehicle-to-Building Charging with Heterogeneous Agents and Long Term RewardsDeep reinforcement learning methods → RL for energy, networks and operations
  10. Programming with Pixels: Can Computer-Use Agents do Software Engineering?LLM agents and tool use → Software engineering coding agents
  11. LLM Inference Acceleration via Efficient Operation FusionEfficient LLM inference and serving → Early exit and edge inference
  12. Aligning Compound AI Systems via System-level DPOLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  13. Spontaneous Giving and Calculated Greed in Language ModelsLLM reasoning → Reasoning for agents, planning and code
  14. Knowledge Distillation with Training WheelsKnowledge distillation → Knowledge distillation for LLMs
  15. Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up QuestionsKnowledge distillation → Knowledge distillation for LLMs
  16. Contrastive Visual Data AugmentationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  17. Towards Human Cognition: Visual Context Guides Syntactic Priming in Fusion-Encoded ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  18. Yes, Q-learning Helps Offline In-Context RLOffline RL and imitation learning from data → Offline RL algorithms
  19. METAL: A Multi-Agent Framework for Chart Generation with Test-Time ScalingLLM reasoning → Multimodal reasoning +1
  20. Towards Robust Legal Reasoning: Harnessing Logical LLMs in LawLLM reasoning → Reasoning for agents, planning and code
  21. Hierarchical Imitation Learning of Team Behavior from Heterogeneous DemonstrationsOffline RL and imitation learning from data → Imitation learning methods
  22. Evaluating the Effect of Retrieval Augmentation on Social BiasesRetrieval-augmented generation → RAG robustness and adaptive retrieval
  23. Representation Engineering for Large-Language Models: Survey and Research ChallengesMechanistic interpretability → Knowledge and representations inside LLMs
  24. MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context InferenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  25. End-to-End Chart Summarization via Visual Chain-of-Thought in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  26. How Do Large Language Monkeys Get Their Power (Laws)?LLM safety and security → Jailbreaking
  27. Training a Generally Curious AgentLLM agents and tool use → General LLM agent frameworks and benchmarks
  28. PosterSum: A Multimodal Benchmark for Scientific Poster SummarizationMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  29. Policy Learning with a Natural Language Action Space: A Causal ApproachDeep reinforcement learning methods → RL training of language and agent models
  30. Rethinking the Vulnerability of Concept Erasure and a New MethodDiffusion models → Robustness, privacy and adversarial aspects
  31. The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?LLM reasoning → Test-time compute and efficient thinking +1
  32. Towards Hierarchical Rectified FlowDiffusion models → Flow matching, time series and science
  33. GCC: Generative Color Constancy via Diffusing a Color CheckerDiffusion models → Image generation, text-to-image and editing
  34. Introducing Visual Perception Token into Multimodal Large Language ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  35. Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsLLM safety and security → Safety alignment, refusal and guardrails
  36. S4S: Solving for a Diffusion Model SolverDiffusion models → Diffusion foundations and sampling
  37. MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  38. LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and VerificationLLM agents and tool use → Software engineering coding agents +1
  39. The Geometry of Refusal in Large Language Models: Concept Cones and Representational IndependenceLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  40. From System 1 to System 2: A Survey of Reasoning Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  41. Reasoning with Latent Thoughts: On the Power of Looped TransformersLLM reasoning → Test-time compute and efficient thinking
  42. Linguistic Generalizability of Test-Time Scaling in Mathematical ReasoningLLM reasoning → Test-time compute and efficient thinking
  43. The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoEMixture-of-experts → MoE theory and gating functions
  44. Mitigating Bias in RAG: Controlling the EmbedderRetrieval-augmented generation → RAG robustness and adaptive retrieval
  45. Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language ModelsLLM reasoning → Reinforcement learning for reasoning
  46. Distributed Coordination for Heterogeneous Non-Terrestrial NetworksDeep reinforcement learning methods → RL for robot navigation and UAV control
  47. KV-Edit: Training-Free Image Editing for Precise Background PreservationEfficient LLM inference and serving → Fast autoregressive visual generation
  48. DIS-CO: Discovering Copyrighted Content in VLMs Training DataMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  49. Tokenized SAEs: Disentangling SAE ReconstructionsMechanistic interpretability → SAE features and their applications
  50. When to Forget? Complexity Trade-offs in Machine UnlearningLLM safety and security → Machine unlearning
  51. TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot ControlDeep reinforcement learning methods → RL for robot locomotion and manipulation
  52. HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference OptimizationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  53. Implicit Word Reordering with Knowledge Distillation for Cross-Lingual Dependency ParsingKnowledge distillation → Knowledge distillation for LLMs
  54. Survey on Strategic Mining in Blockchain: A Reinforcement Learning ApproachDeep reinforcement learning methods → Adversarial robustness and RL in finance
  55. Delta Decompression for MoE-based LLMs CompressionMixture-of-experts → MoE large language models
  56. Benchmarking Retrieval-Augmented Generation in Multi-Modal ContextsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  57. VideoGrain: Modulating Space-Time Attention for Multi-grained Video EditingDiffusion models → Video generation
  58. MDN: Mamba-Driven Dualstream Network For Medical Hyperspectral Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  59. REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic ObjectiveLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  60. A Reinforcement Learning Approach to Non-prehensile Manipulation through SlidingDeep reinforcement learning methods → RL for robot locomotion and manipulation
  61. Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  62. Intermediate Languages Matter: Formal Choice Drives Neurosymbolic LLM ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  63. CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-ThoughtLLM reasoning → Test-time compute and efficient thinking
  64. Dimitra: Audio-driven Diffusion model for Expressive Talking Head GenerationDiffusion models → Audio, speech and music
  65. IGDA: Interactive Graph Discovery through Large Language Model AgentsLLM agents and tool use → Web, search, and research agents
  66. Evaluating Expert Contributions in a MoE LLM for Quiz-Based TasksMixture-of-experts → MoE large language models
  67. Unsupervised Accelerated MRI Reconstruction via Ground-Truth-Free Flow MatchingDiffusion models → Medical imaging and segmentation
  68. Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from ScratchLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  69. Logic Haystacks: Probing LLMs Long-Context Logical Reasoning (Without Easily Identifiable Unrelated Padding)LLM reasoning → Reasoning benchmarks and evaluation
  70. JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal ReasoningLLM reasoning → Reasoning for agents, planning and code
  71. MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  72. DICEPTION: A Generalist Diffusion Model for Visual Perceptual TasksDiffusion models → Image generation, text-to-image and editing
  73. FastCoder: Accelerating Repository-level Code Generation via Efficient Retrieval and VerificationEfficient LLM inference and serving → Speculative decoding
  74. LettuceDetect: A Hallucination Detection Framework for RAG ApplicationsRetrieval-augmented generation → Hallucination detection in RAG
  75. Diffusion and Flow Matching Models for Tabular Data: A SurveyDiffusion models → Flow matching, time series and science
  76. Improved Diffusion-based Generative Model with Better Adversarial RobustnessDiffusion models → Diffusion foundations and sampling
  77. Shakti-VLMs: Scalable Vision-Language Models for Enterprise AIMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  78. Forgetting Any Data at Any Time: A Theoretically Certified Unlearning Framework for Vertical Federated LearningLLM safety and security → Federated unlearning and poisoning
  79. SpecDM: Hyperspectral Dataset Synthesis with Pixel-level Semantic AnnotationsDiffusion models → Inverse problems and image restoration
  80. Language Model Re-rankers are Fooled by Lexical SimilaritiesRetrieval-augmented generation → Generation and context integration
  81. Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning TopologyLLM reasoning → Knowledge- and tool-augmented reasoning
  82. Quantifying Logical Consistency in Transformers via Query-Key AlignmentLLM reasoning → Reasoning benchmarks and evaluation
  83. FADE: Why Bad Descriptions Happen to Good FeaturesMechanistic interpretability → SAE features and their applications
  84. All-in-one: Understanding and Generation in Multimodal Reasoning with the MAIA BenchmarkLLM reasoning → Multimodal reasoning +1
  85. Muon is Scalable for LLM TrainingMixture-of-experts → Efficient MoE training and inference systems
  86. SCoT: Unifying Consistency Models and Rectified Flows via Straight-Consistent TrajectoriesDiffusion models → Flow matching, time series and science
  87. Autoregressive Image Generation with Vision Full-view PromptDiffusion models → Image generation, text-to-image and editing
  88. Pretrain Value, Not Reward: Decoupled Value Policy OptimizationLLM reasoning → Reinforcement learning for reasoning +1
  89. MAD-AD: Masked Diffusion for Unsupervised Brain Anomaly DetectionDiffusion models → Medical imaging and segmentation
  90. Reasoning Does Not Necessarily Improve Role-Playing AbilityLLM reasoning → Reasoning benchmarks and evaluation
  91. BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and InferenceMixture-of-experts → MoE large language models
  92. Benchmarking Temporal Reasoning and Alignment Across Chinese DynastiesLLM reasoning → Knowledge- and tool-augmented reasoning
  93. Multi-Dimensional Quality Assessment for Text-to-3D Assets: Dataset and ModelDiffusion models → 3D, point cloud and scene generation
  94. SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  95. MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow EstimationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  96. AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  97. GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak MethodsLLM safety and security → Jailbreaking
  98. Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt RefinementDiffusion models → Image generation, text-to-image and editing
  99. Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMsLLM safety and security → Backdoor and data poisoning attacks
  100. Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization AlignmentMixture-of-experts → Mixture of LoRA experts
All 378
  1. ReFreeKV: Towards Threshold-Free KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
  2. CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative DrafterEfficient LLM inference and serving → Speculative decoding
  3. A Multi-LLM-Agent-Based Framework for Economic and Public Policy AnalysisLLM agents and tool use → Social simulation and multi-agent debate
  4. Mitigating Hallucinations in Diffusion Models through Adaptive Attention ModulationDiffusion models → Medical imaging and segmentation
  5. Graphy'our Data: Towards End-to-End Modeling, Exploring and Generating Report from Raw DataRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  6. Toward Agentic AI: Generative Information Retrieval Inspired Intelligent Communications and NetworkingLLM agents and tool use → Web, search, and research agents
  7. Leveraging Large Language Models for Effective and Explainable Multi-Agent Credit AssignmentLLM agents and tool use → Reinforcement learning for LLM agents
  8. Improving LLM General Preference Alignment via Optimistic Online Mirror DescentLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  9. Exploring Causes and Mitigation of Hallucinations in Large Vision Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  10. Finding the Sweet Spot: Preference Data Construction for Scaling Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  11. Posterior Inference with Diffusion Models for High-dimensional Black-box OptimizationDiffusion models → Diffusion foundations and sampling
  12. Fast, Accurate Manifold Denoising by Tunneling Riemannian OptimizationDiffusion models → Diffusion foundations and sampling
  13. Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  14. AI Realtor: Towards Grounded Persuasive Language Generation for Automated CopywritingLLM agents and tool use → General LLM agent frameworks and benchmarks
  15. CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different TokenizersLLM reasoning → Prompting and chain-of-thought reasoning +2
  16. Multi-Agent Autonomous Driving Systems with Large Language Models: A Survey of Recent AdvancesEnd-to-end autonomous driving → Large language models for driving +1
  17. Model-Based Exploration in Monitored Markov Decision ProcessesDeep reinforcement learning methods → RL theory and sample complexity
  18. DiffKAN-Inpainting: KAN-based Diffusion model for brain tumor inpaintingDiffusion models → Medical imaging and segmentation
  19. A Transformer-in-Transformer Network Utilizing Knowledge Distillation for Image RecognitionKnowledge distillation → General knowledge distillation methods
  20. Towards Reinforcement Learning for Exploration of Speculative Execution VulnerabilitiesDeep reinforcement learning methods → RL training of language and agent models
  21. Document clustering with evolved multiword search queries
  22. Diagnostic Method for Hydropower Plant Condition-based Maintenance combining Autoencoder with Clustering Algorithms
  23. Rank-O-ToM: Unlocking Emotional Nuance Ranking to Enhance Affective Theory-of-Mind
  24. Mesters'eges Intelligencia Kutat'asok Magyarorsz'agon
  25. Encoding Inequity: Examining Demographic Bias in LLM-Driven Robot Caregiving
  26. GMLM: Bridging Graph Neural Networks and Language Models for Heterophilic Node Classification
  27. Geometric Properties and Graph-Based Optimization of Neural Networks: Addressing Non-Linearity, Dimensionality, and Scalability
  28. Bangla Fake News Detection Based On Multichannel Combined CNN-LSTM
  29. Towards Enterprise-Ready Computer Using Generalist Agent
  30. Genetics-Driven Personalized Disease Progression Model
  31. Do Emotions Really Affect Argument Convincingness? A Dynamic Approach with LLM-based Manipulation Checks
  32. AniGaussian: Animatable Gaussian Avatar with Pose-guided Deformation
  33. GOD model: Privacy Preserved AI School for Personal Assistant
  34. Moderation Matters:Measuring Conversational Moderation Impact in English as a Second Language Group Discussion
  35. Correlating and Predicting Human Evaluations of Language Models from Natural Language Processing Benchmarks
  36. Can Score-Based Generative Modeling Effectively Handle Medical Image Classification?
  37. The GigaMIDI Dataset with Features for Expressive Music Performance Detection
  38. Solving the Traveling Salesman Problem via Different Quantum Computing Architectures
  39. On the usability of generative AI: Human generative AI
  40. Learning Backbones: Sparsifying Graphs through Zero Forcing for Effective Graph-Based Learning
  41. Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures
  42. IBURD: Image Blending for Underwater Robotic Detection
  43. To Patch or Not to Patch: Motivations, Challenges, and Implications for Cybersecurity
  44. From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMs
  45. Robust Federated Learning with Global Sensitivity Estimation for Financial Risk Management
  46. Predictive Response Optimization: Using Reinforcement Learning to Fight Online Social Network Abuse
  47. Identifying Stochastic Dynamics from Non-Sequential Data (DyNoSeD)
  48. Semi-Supervised Weed Detection in Vegetable Fields: In-domain and Cross-domain Experiments
  49. Optimal Recovery Meets Minimax Estimation
  50. Semantics drives analogical change in Germanic strong verb paradigms: a phylogenetic study
  51. Renormalization-Inspired Effective Field Neural Networks for Scalable Modeling of Classical and Quantum Many-Body Systems
  52. Towards Typologically Aware Rescoring to Mitigate Unfaithfulness in Lower-Resource Languages
  53. StatLLM: A Dataset for Evaluating the Performance of Large Language Models in Statistical Analysis
  54. Wearable Meets LLM for Stress Management: A Duoethnographic Study Integrating Wearable-Triggered Stressors and LLM Chatbots for Personalized Interventions
  55. CalibRefine: Deep Learning-Based Online Automatic Targetless LiDAR-Camera Calibration with Iterative and Attention-Driven Post-Refinement
  56. Architecting Digital Twins for Intelligent Transportation Systems
  57. Socratic: Enhancing Human Teamwork via AI-enabled Coaching
  58. Requirements for Quality Assurance of AI Models for Early Detection of Lung Cancer
  59. The Power of Graph Signal Processing for Chip Placement Acceleration
  60. Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback
  61. Theory-guided Pseudo-spectral Full Waveform Inversion via Deep Neural Networks
  62. A Priori Generalizability Estimate for a CNN
  63. Provable Model-Parallel Distributed Principal Component Analysis with Parallel Deflation
  64. Scalable Graph Condensation with Evolving Capabilities
  65. Flexible Counterfactual Explanations with Generative Models
  66. Learning Decentralized Swarms Using Rotation Equivariant Graph Neural Networks
  67. SynthRAD2025 Grand Challenge dataset: generating synthetic CTs for radiotherapy
  68. Data-Driven Pseudo-spectral Full Waveform Inversion via Deep Neural Networks
  69. Synthetic Text Generation for Training Large Language Models via Gradient Matching
  70. PICASO: Permutation-Invariant Context Composition with State Space Models
  71. A stochastic smoothing framework for nonconvex-nonconcave minEmax problems with applications to Wasserstein distributionally robust optimization
  72. Hallucination Detection in LLMs Using Spectral Features of Attention Maps
  73. Unraveling particle dark matter with Physics-Informed Neural Networks
  74. Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
  75. Synergizing Deep Learning and Full-Waveform Inversion: Bridging Data-Driven and Theory-Guided Approaches for Enhanced Seismic Imaging
  76. Multi-Year-to-Decadal Temperature Prediction using a Machine Learning Model-Analog Framework
  77. Intention Recognition in Real-Time Interactive Navigation Maps
  78. Towards Conditioning Clinical Text Generation for User Control
  79. Utilizing Machine Learning to Predict Host Stars and the Key Elemental Abundances of Small Planets
  80. Expressive equivalence of classical and quantum restricted Boltzmann machines
  81. Dataset Featurization: Uncovering Natural Language Features through Unsupervised Data Reconstruction
  82. CLEP-GAN: An Innovative Approach to Subject-Independent ECG Reconstruction from PPG Signals
  83. A Machine Learning Approach for Design of Frequency Selective Surface based Radar Absorbing Material via Image Prediction
  84. From Euler to AI: Unifying Formulas for Mathematical Constants
  85. Laplace-Beltrami Operator for Gaussian Splatting
  86. Perceptual Noise-Masking with Music through Deep Spectral Envelope Shaping
  87. FedSV: Byzantine-Robust Federated Learning via Shapley Value
  88. Fractal Generative Models
  89. V-HOP: Visuo-Haptic 6D Object Pose Tracking
  90. FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning
  91. CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentation
  92. Stronger Neyman Regret Guarantees for Adaptive Experimental Design
  93. X-Dancer: Expressive Music to Human Dance Video Generation
  94. COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs
  95. Function-Space Learning Rates
  96. Large Language Models are Powerful Electronic Health Record Encoders
  97. Robust Confinement State Classification with Uncertainty Quantification through Ensembled Data-Driven Methods
  98. SNaRe: Domain-aware Data Generation for Low-Resource Event Detection
  99. Emoti-Attack: Zero-Perturbation Adversarial Attacks on NLP Systems via Emoji Sequences
  100. On Traceability in ℓp Stochastic Convex Optimization
  101. Which Questions Improve Learning the Most? Utility Estimation of Questions with LM-based Simulations
  102. Unraveling the geometry of visual relational reasoning
  103. Low-Rank and Sparse Model Merging for Multi-Lingual Speech Recognition and Translation
  104. Continuous Integration Practices in Machine Learning Projects: The Practitioners` Perspective
  105. Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting
  106. A Concise Lyapunov Analysis of Nesterov's Accelerated Gradient Method
  107. Experimental validation of UAV search and detection system in real wilderness environment
  108. Sustainable Greenhouse Microclimate Modeling: A Comparative Analysis of Recurrent and Graph Neural Networks
  109. A Refined Analysis of UCBVI
  110. Bridging Gaps in Natural Language Processing for Yor`ub'a: A Systematic Review of a Decade of Progress and Prospects
  111. A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities
  112. RELICT: A Replica Detection Framework for Medical Image Generation
  113. An Explainable AI Model for Binary LJ Fluids
  114. Random Scaling of Emergent Capabilities
  115. On Relation-Specific Neurons in Large Language Models
  116. Leveraging Procedural Knowledge and Task Hierarchies for Efficient Instructional Video Pre-training
  117. HybridLinker: Topology-Guided Posterior Sampling for Enhanced Diversity and Validity in 3D Molecular Linker Generation
  118. Time series forecasting based on optimized LLM for fault prediction in distribution power grid insulators
  119. Low-rank bias, weight decay, and model merging in neural networks
  120. Unveiling ECC Vulnerabilities: LSTM Networks for Operation Recognition in Side-Channel Attacks
  121. Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization
  122. AnyTop: Character Animation Diffusion with Any Topology
  123. Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents
  124. `Generalization is hallucination' through the lens of tensor completions
  125. Child vs. machine language learning: Can the logical structure of human language unleash LLMs?
  126. Joint Value Estimation and Bidding in Repeated First-Price Auctions
  127. A novel approach to navigate the taxonomic hierarchy to address the Open-World Scenarios in Medicinal Plant Classification
  128. GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow
  129. Improving the Inclusivity of Dutch Speech Recognition by Fine-tuning Whisper on the JASMIN-CGN Corpus
  130. Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routing
  131. Extracting domain-specific terms using contextual word embeddings
  132. MonoTODia: Translating Monologue Requests to Task-Oriented Dialogues
  133. Continuous Wrist Control on the Hannes Prosthesis: a Vision-based Shared Autonomy Framework
  134. Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional Coverage
  135. Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective
  136. Robust Federated Learning in Unreliable Wireless Networks: A Client Selection Approach
  137. Detecting Benchmark Contamination Through Watermarking
  138. MULTITAT: Benchmarking Multilingual Table-and-Text Question Answering
  139. CAR-LOAM: Color-Assisted Robust LiDAR Odometry and Mapping
  140. Overconfident Oracles: Limitations of In Silico Sequence Design Benchmarking
  141. A dataset of high-resolution plantar pressures for gait analysis across varying footwear and walking speeds
  142. Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction
  143. MegaLoc: One Retrieval to Place Them All
  144. Tidiness Score-Guided Monte Carlo Tree Search for Visual Tabletop Rearrangement
  145. Electrical Load Forecasting over Multihop Smart Metering Networks with Federated Learning
  146. Deep Learning-Powered Electrical Brain Signals Analysis: Advancing Neurological Diagnostics
  147. A Tractable Two-Step Linear Mixing Model Solved with Second-Order Optimization for Spectral Unmixing under Variability
  148. Motion-Robust T2* Quantification from Gradient Echo MRI with Physics-Informed Deep Learning
  149. Neural Attention: A Novel Mechanism for Enhanced Expressive Power in Transformer Models
  150. Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following
  151. Disentangling Visual Transformers: Patch-level Interpretability for Image Classification
  152. Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric
  153. Joint multiband deconvolution for Euclid and Vera C. Rubin images
  154. Linear Bandits on Ellipsoids: Minimax Optimal Algorithms
  155. Teleology-Driven Affective Computing: A Causal Framework for Sustained Well-Being
  156. Real-time Monitoring of Economic Shocks using Company Websites
  157. A Pragmatic Note on Evaluating Generative Models with Fr'echet Inception Distance for Retinal Image Synthesis
  158. RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness
  159. MaxGlaViT: A novel lightweight vision transformer-based approach for early diagnosis of glaucoma stages from fundus images
  160. Differential privacy guarantees of Markov chain Monte Carlo algorithms
  161. Sentiment analysis of texts from social networks based on machine learning methods for monitoring public sentiment
  162. The feasibility of multi-graph alignment: a Bayesian approach
  163. On Quantile Regression Forests for Modelling Mixed-Frequency and Longitudinal Data
  164. Evaluating the Effectiveness of Large Language Models in Automated News Article Summarization
  165. Gabor-Enhanced Physics-Informed Neural Networks for Fast Simulations of Acoustic Wavefields
  166. Applications of Large Models in Medicine
  167. Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space
  168. Thus Spake Long-Context Large Language Model
  169. Sparse Hyperparametric Itakura-Saito Nonnegative Matrix Factorization via Bi-Level Optimization
  170. Adversarial Training for Defense Against Label Poisoning Attacks
  171. Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation
  172. Strength Estimation and Human-Like Strength Adjustment in Games
  173. SFLD: Reducing the content bias for AI-generated Image Detection
  174. Generative Models in Decision Making: A Survey
  175. Enhancing Image Matting in Real-World Scenes with Mask-Guided Iterative Refinement
  176. Comparing the Framing Effect in Humans and LLMs on Naturally Occurring Texts
  177. Imprinto: Enhancing Infrared Inkjet Watermarking for Human and Machine Perception
  178. Conditional Diffusion-Flow models for generating 3D cosmic density fields: applications to f(R) cosmologies
  179. Mind the Blind Spots: A Focus-Level Evaluation Framework for LLM Reviews
  180. Pleno-Generation: A Scalable Generative Face Video Compression Framework with Bandwidth Intelligence
  181. VR-Pipe: Streamlining Hardware Graphics Pipeline for Volume Rendering
  182. A comparative analysis of rank aggregation methods for the partial label ranking problem
  183. Systematic Weight Evaluation for Pruning Large Language Models: Enhancing Performance and Sustainability
  184. DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications
  185. Random Projections and Natural Sparsity in Time-Series Classification: A Theoretical Analysis
  186. Analytics Modelling over Multiple Datasets using Vector Embeddings
  187. ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance
  188. GradientStabilizer:Fix the Norm, Not the Gradient
  189. PointSea: Point Cloud Completion via Self-structure Augmentation
  190. TabulaTime: A Novel Multimodal Deep Learning Framework for Advancing Acute Coronary Syndrome Prediction through Environmental and Clinical Data Integration
  191. PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance
  192. LCV2I: Communication-Efficient and High-Performance Collaborative Perception Framework with Low-Resolution LiDAR
  193. Your Assumed DAG is Wrong and Here's How To Deal With It
  194. M3DA: Benchmark for Unsupervised Domain Adaptation in 3D Medical Image Segmentation
  195. Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence
  196. Towards Auto-Regressive Next-Token Prediction: In-Context Learning Emerges from Generalization
  197. Advancing Eurasia Fire Understanding Through Machine Learning Techniques
  198. Class-Dependent Perturbation Effects in Evaluating Time Series Attributions
  199. Moving Past Single Metrics: Exploring Short-Text Clustering Across Multiple Resolutions
  200. Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems
  201. Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation
  202. Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs
  203. Uncertainty Quantification as a Principled Foundation for Explainable Artificial Intelligence: A Case Study of Counterfactual Explanations
  204. Information-Geometric Inverse Distillation for Enhancing Adversarial Transferability
  205. An Enhanced Large Language Model For Cross Modal Query Understanding System Using DL-KeyBERT Based CAZSSCL-MPGPT
  206. PQDAST: Depth-Aware Arbitrary Style Transfer for Games via Perceptual Quality-Guided Distillation
  207. Semantic Neural Radiance Fields for Multi-Date Satellite Data
  208. Hotter and Colder: A New Approach to Annotating Sentiment, Emotions, and Bias in Icelandic Blog Comments
  209. Active Learning for Conditional Inverse Design with Crystal Generation and Foundation Atomic Models
  210. Convergence of Shallow ReLU Networks on Weakly Interacting Data
  211. Task-Oriented 6-DoF Grasp Pose Detection in Clutters
  212. LongSafety: Evaluating Long-Context Safety of Large Language Models
  213. UrduLLaMA 1.0: Dataset Curation, Preprocessing, and Evaluation in Low-Resource Settings
  214. TGT: A Temporal Gating Transformer for Smartphone App Usage Prediction
  215. MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation
  216. A survey of datasets for computer vision in agriculture
  217. SparseTransX: Efficient Training of Translation-Based Knowledge Graph Embeddings Using Sparse Matrix Operations
  218. Deep Minimax Classifiers for Imbalanced Datasets with a Small Number of Minority Samples
  219. Using Machine Learning to Detect Fraudulent SMSs in Chichewa
  220. NUTSHELL: A Dataset for Abstract Generation from Scientific Talks
  221. Gaussian Difference: Find Any Change Instance in 3D Scenes
  222. Supervised contrastive learning from weakly-labeled audio segments for musical version matching
  223. SUSTeR: Sparse Unstructured Spatio Temporal Reconstruction on Traffic Prediction
  224. Achieving Fair PCA Using Joint Eigenvalue Decomposition
  225. Machine learning and high dimensional vector search
  226. A Systematic Survey of Automatic Prompt Optimization Techniques
  227. SS-MPC: A Sequence-Structured Multi-Party Conversation System
  228. Dependency Parsing with the Structuralized Prompt Template
  229. ENACT-Heart -- ENsemble-based Assessment Using CNN and Transformer on Heart Sounds
  230. HVIS: A Human-like Vision and Inference System for Human Motion Prediction
  231. When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?
  232. Zero-shot Load Forecasting for Integrated Energy Systems: A Large Language Model-based Framework with Multi-task Learning
  233. Applying LLMs to Active Learning: Towards Cost-Efficient Cross-Task Text Classification without Manually Labeled Data
  234. ReFocus: Reinforcing Mid-Frequency and Key-Frequency Modeling for Multivariate Time Series Forecasting
  235. Beyond Diagnostic Performance: Revealing and Quantifying Ethical Risks in Pathology Foundation Models
  236. Functional BART with Shape Priors: A Bayesian Tree Approach to Constrained Functional Regression
  237. Utilizing Social Media Analytics to Detect Trends in Saudi Arabias Evolving Market
  238. Distributionally Robust Active Learning for Gaussian Process Regression
  239. A Survey of fMRI to Image Reconstruction
  240. LongAttn: Selecting Long-context Training Data via Token-level Attention
  241. Sarang at DEFACTIFY 4.0: Detecting AI-Generated Text Using Noised Data and an Ensemble of DeBERTa Models
  242. Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models
  243. PulseBat: A field-accessible dataset for second-life battery diagnostics from realistic histories using multidimensional rapid pulse test
  244. Characterizing Structured versus Unstructured Environments based on Pedestrians' and Vehicles' Motion Trajectories
  245. Fair Foundation Models for Medical Image Analysis: Challenges and Perspectives
  246. In-context Learning of Evolving Data Streams with Tabular Foundational Models
  247. "Actionable Help" in Crises: A Novel Dataset and Resource-Efficient Models for Identifying Request and Offer Social Media Posts
  248. REGen: A Reliable Evaluation Framework for Generative Event Argument Extraction
  249. A Novel Multi-Task Teacher-Student Architecture with Self-Supervised Pretraining for 48-Hour Vasoactive-Inotropic Trend Analysis in Sepsis Mortality Prediction
  250. FedBM: Stealing Knowledge from Pre-trained Language Models for Heterogeneous Federated Learning
  251. Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learning
  252. Noise2Score3D:Unsupervised Tweedie's Approach for Point Cloud Denoising
  253. Uncertainty Quantification of Large Language Models through Multi-Dimensional Responses
  254. CLIP-SENet: CLIP-based Semantic Enhancement Network for Vehicle Re-identification
  255. Snoopy: Effective and Efficient Semantic Join Discovery via Proxy Columns
  256. CRTrack: Low-Light Semi-Supervised Multi-object Tracking Based on Consistency Regularization
  257. Topic Over Source: The Key to Effective Data Mixing for Language Models Pre-training
  258. Hierarchical Semantic Compression for Consistent Image Semantic Restoration
  259. Forecasting Rare Language Model Behaviors
  260. MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructions
  261. Continuous Patch Stitching for Block-wise Image Compression
  262. AAD-LLM: Neural Attention-Driven Auditory Scene Understanding
  263. VGFL-SA: Vertical Graph Federated Learning Structure Attack Based on Contrastive Learning
  264. The Role of Sparsity for Length Generalization in Transformers
  265. Are Large Language Models Good Data Preprocessors?
  266. AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay
  267. SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding
  268. CipherPrune: Efficient and Scalable Private Transformer Inference
  269. Evaluating Robustness of LLMs in Question Answering on Multilingual Noisy OCR Data
  270. Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model
  271. The Robustness of Structural Features in Species Interaction Networks
  272. AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement
  273. LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
  274. A Hybrid Approach to Information Retrieval and Answer Generation for Regulatory Texts
  275. ATEB: Evaluating and Improving Advanced NLP Tasks for Text Embedding Models
  276. Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks
  277. Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions
  278. Entailment-Preserving First-order Logic Representations in Natural Language Entailment