mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 14 Oct 2024

429 papers

  1. How to Backdoor Consistency Models?Diffusion models → Robustness, privacy and adversarial aspects
  2. FLARE: Faithful Logic-Aided Reasoning and ExplorationLLM reasoning → Prompting and chain-of-thought reasoning
  3. LLM Unlearning via Loss Adjustment with Only Forget DataLLM safety and security → Machine unlearning
  4. Mimetic Initialization Helps State Space Models Learn to RecallState-space sequence models (S4, Mamba) → Core SSM architectures for language
  5. DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech SynthesisDiffusion models → Audio, speech and music
  6. Locality Alignment Improves Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  7. Simplifying, Stabilizing and Scaling Continuous-Time Consistency ModelsDiffusion models → Diffusion foundations and sampling
  8. CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel PruningState-space sequence models (S4, Mamba) → Speech and audio SSMs
  9. Varying Shades of Wrong: Aligning LLMs with Wrong Answers OnlyLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  10. Action Gaps and Advantages in Continuous-Time Distributional Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  11. Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning TasksLLM reasoning → Reasoning benchmarks and evaluation
  12. Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with GraphsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  13. Agent-as-a-Judge: Evaluate Agents with AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. Cultural Heritage 3D Reconstruction with Diffusion NetworksDiffusion models → Image generation, text-to-image and editing
  15. Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without DisclosureLLM safety and security → Federated unlearning and poisoning
  16. Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive LearningRetrieval-augmented generation → Multimodal RAG
  17. Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  18. DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming HeadsEfficient LLM inference and serving → KV cache optimization
  19. Depth Any Video with Scalable Synthetic DataDiffusion models → 3D, point cloud and scene generation
  20. Your Mixture-of-Experts LLM Is Secretly an Embedding Model For FreeMixture-of-experts → MoE large language models
  21. HART: Efficient Visual Generation with Hybrid Autoregressive TransformerDiffusion models → Image generation, text-to-image and editing
  22. Deep Linear Probe Generators for Weight Space LearningMechanistic interpretability → Circuits and mechanistic analysis
  23. TrajDiffuse: A Conditional Diffusion Model for Environment-Aware Trajectory PredictionDiffusion models → Diffusion and flow policies for robotics
  24. Generalizable Humanoid Manipulation with 3D Diffusion PoliciesDiffusion models → Diffusion and flow policies for robotics
  25. Boosting Camera Motion Control for Video Diffusion TransformersDiffusion models → Video generation
  26. MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic ModelingMultimodal LLMs / vision-language models → Image editing and quality assessment
  27. Semantic Image Inversion and Editing using Rectified Stochastic Differential EquationsDiffusion models → Image generation, text-to-image and editing
  28. When Attention Sink Emerges in Language Models: An Empirical ViewEfficient LLM inference and serving → KV cache optimization
  29. MaskControl: Spatio-Temporal Control for Masked Motion SynthesisDiffusion models → Video generation
  30. Focused ReAct: Improving ReAct through Reiterate and Early StopLLM reasoning → Test-time compute and efficient thinking
  31. Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated AttentionDiffusion models → Video generation
  32. Adaptive Diffusion Terrain Generator for Autonomous Uneven Terrain NavigationDiffusion models → Diffusion and flow policies for robotics +1
  33. AFlow: Automating Agentic Workflow GenerationLLM reasoning → Reasoning for agents, planning and code +1
  34. DragEntity: Trajectory Guided Video Generation using Entity and Positional RelationshipsDiffusion models → Video generation
  35. DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World ModelWorld models → World models for autonomous driving +1
  36. Asymptotic Analysis of Sample-averaged Q-learningDeep reinforcement learning methods → RL theory and sample complexity
  37. Embedding Self-Correction as an Inherent Ability in Large Language Models for Enhanced Mathematical ReasoningLLM reasoning → Test-time compute and efficient thinking
  38. Deep Compression Autoencoder for Efficient High-Resolution Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  39. TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion ModelDiffusion models → Audio, speech and music
  40. Both Ears Wide Open: Towards Language-Driven Spatial Audio GenerationDiffusion models → Audio, speech and music
  41. Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent ApproachDeep reinforcement learning methods → RL theory and sample complexity
  42. Transforming Game Play: A Comparative Study of DCQN and DTQN Architectures in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  43. Thinking LLMs: General Instruction Following with Thought GenerationLLM reasoning → Prompting and chain-of-thought reasoning
  44. SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  45. Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family ExpertsMixture-of-experts → Medical and biomedical MoE
  46. SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity RecognitionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  47. VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality DocumentsRetrieval-augmented generation → Multimodal RAG
  48. Online waveform selection for cognitive radarDeep reinforcement learning methods → RL for robot navigation and UAV control
  49. STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBackRetrieval-augmented generation → Agentic RAG, agents and memory +1
  50. Burning RED: Unlocking Subtask-Driven Reinforcement Learning and Risk-Awareness in Average-Reward Markov Decision ProcessesDeep reinforcement learning methods → RL theory and sample complexity
  51. Words to Wheels: Vision-Based Autonomous Driving Understanding Human Language Instructions Using Foundation ModelsEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  52. Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image ClassificationMultimodal LLMs / vision-language models → Medical vision-language models
  53. Regularized Robustly Reliable Learners and Instance Targeted AttacksLLM safety and security → Backdoor and data poisoning attacks
  54. Rethinking Legal Judgement Prediction in a Realistic Scenario in the Era of Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  55. Continual Deep Reinforcement Learning to Prevent Catastrophic Forgetting in Jamming MitigationDeep reinforcement learning methods → Deep RL algorithms and representations
  56. Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image EditingDiffusion models → Image generation, text-to-image and editing
  57. TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free TuningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  58. TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMsLLM reasoning → Reasoning for agents, planning and code
  59. The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean LabelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
  60. Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of ExpertsMixture-of-experts → MoE for time series and graphs
  61. Ada-K Routing: Boosting the Efficiency of MoE-based LLMsMixture-of-experts → Expert routing strategies
  62. QUITE: Quantifying Uncertainty in Natural Language Text in Bayesian Reasoning ScenariosLLM reasoning → Test-time compute and efficient thinking
  63. Reinforcement Learning For Quadrupedal Locomotion: Current Advancements And Future PerspectivesDeep reinforcement learning methods → RL for robot locomotion and manipulation
  64. Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  65. Diversity-Aware Reinforcement Learning for de novo Drug DesignDeep reinforcement learning methods → RL for energy, networks and operations
  66. DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World ModelWorld models → World models for autonomous driving +1
  67. On Calibration of LLM-based Guard Models for Reliable Content ModerationLLM safety and security → Safety alignment, refusal and guardrails
  68. Tighter Risk Bounds for Mixtures of ExpertsMixture-of-experts → Expert routing strategies
  69. PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic ManipulationWorld models → Embodied and robot world models
  70. Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree SearchLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  71. V2M: Visual 2-Dimensional Mamba for Image Representation LearningState-space sequence models (S4, Mamba) → Vision Mamba backbones
  72. Learning Sub-Second Routing Optimization in Computer Networks requires Packet-Level DynamicsDeep reinforcement learning methods → RL for energy, networks and operations
  73. Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought LeapsLLM reasoning → Multimodal reasoning
  74. Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored TuningRetrieval-augmented generation → RAG robustness and adaptive retrieval
  75. FasterDiT: Towards Faster Diffusion Transformers Training without Architecture ModificationDiffusion models → Diffusion foundations and sampling
  76. Augmenting In-Context-Learning in LLMs via Automatic Data Labeling and RefinementLLM reasoning → Reasoning benchmarks and evaluation
  77. A Unified Approach to Routing and Cascading for LLMsLLM agents and tool use → General LLM agent frameworks and benchmarks
  78. CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical ReasoningLLM reasoning → Mathematical reasoning
  79. Spatial-Aware Efficient Projector for MLLMs via Multi-Layer Feature AggregationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  80. GlobalMamba: Global Image Serialization for Vision MambaState-space sequence models (S4, Mamba) → Vision Mamba backbones
  81. EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network OperationsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  82. LG-CAV: Train Any Concept Activation Vector with Language GuidanceMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  83. FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAGRetrieval-augmented generation → RAG pipeline design and evaluation
  84. Saliency Guided Optimization of Diffusion LatentsDiffusion models → Image generation, text-to-image and editing
  85. LPT: Less-overfitting Prompt Tuning for Vision-Language ModelMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  86. ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and LocalizationLLM reasoning → Multimodal reasoning +1
  87. QE-EBM: Using Quality Estimators as Energy Loss for Machine TranslationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  88. MagicEraser: Erasing Any Objects via Semantics-Aware ControlDiffusion models → 3D, point cloud and scene generation
  89. Identity-Focused Inference and Extraction Attacks on Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  90. First Creating Backgrounds Then Rendering Texts: A New Paradigm for Visual Text BlendingDiffusion models → Image generation, text-to-image and editing
  91. Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
  92. Improved Regret Bound for Safe Reinforcement Learning via Tighter Cost Pessimism and Reward OptimismDeep reinforcement learning methods → RL theory and sample complexity
  93. Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weightingLLM safety and security → Jailbreaking
  94. AlphaDPO: Adaptive Reward Margin for Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  95. Temperature-Centric Investigation of Speculative Decoding with Knowledge DistillationEfficient LLM inference and serving → Speculative decoding +1
  96. Hi-Mamba: Hierarchical Mamba for Efficient Image Super-ResolutionState-space sequence models (S4, Mamba) → Vision Mamba backbones
  97. MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  98. Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  99. Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained DevicesLLM safety and security → Machine unlearning
  100. Evaluating of Machine Unlearning: Robustness Verification Without Prior ModificationsLLM safety and security → Machine unlearning
All 429
  1. Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
  2. Can We Predict Performance of Large Models across Vision-Language Tasks?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  3. High-Precision Dichotomous Image Segmentation via Probing Diffusion CapacityDiffusion models → Medical imaging and segmentation
  4. How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning PerspectiveLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  5. The Ingredients for Robotic Diffusion TransformersDiffusion models → Diffusion and flow policies for robotics
  6. Dreaming to Assist: Learning to Align with Human Objectives for Shared Control in High-Speed RacingLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  7. Learning to Customize Text-to-Image Diffusion In Diverse ContextDiffusion models → Image generation, text-to-image and editing
  8. AlphaLoRA: Assigning LoRA Experts Based on Layer Training QualityMixture-of-experts → Mixture of LoRA experts
  9. DINTR: Tracking via Diffusion-based InterpolationDiffusion models → Video generation
  10. News-Driven Stock Price Forecasting in Indian Markets: A Comparative Study of Advanced Deep Learning Models
  11. GleanVec: Accelerating vector search with minimalist nonlinear dimensionality reduction
  12. Representation Learning for Regime detection in Block Hierarchical Financial Markets
  13. Enhancing Apple's Defect Classification: Insights from Visible Spectrum and Narrow Spectral Band Imaging
  14. Data-Driven Uncertainty-Aware Forecasting of Sea Ice Conditions in the Gulf of Ob Based on Satellite Radar Imagery
  15. Feasibility Analysis of Federated Neural Networks for Explainable Detection of Atrial Fibrillation
  16. Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamics
  17. BrainGPT: Unleashing the Potential of EEG Generalist Foundation Model by Autoregressive Pre-training
  18. A Human-Centered Approach for Improving Supervised Learning
  19. Deep Learning-driven Mobile Traffic Measurement Collection and Analysis
  20. Real-Time Stress Detection via Photoplethysmogram Signals: Implementation of a Combined Continuous Wavelet Transform and Convolutional Neural Network on Resource-Constrained Microcontrollers
  21. Gender Bias of LLM in Economics: An Existentialism Perspective
  22. Copula-Linked Parallel ICA: A Method for Coupling Structural and Functional MRI brain Networks
  23. Developing Gridded Emission Inventory from High-Resolution Satellite Object Detection for Improved Air Quality Forecasts
  24. The Representation of Meaningful Precision, and Accuracy
  25. SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models
  26. Deep Learning Based XIoT Malware Analysis: A Comprehensive Survey, Taxonomy, and Research Challenges
  27. On Debiasing Text Embeddings Through Context Injection
  28. Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing
  29. AI-Driven Autonomous Control of Proton-Boron Fusion Reactors Using Backpropagation Neural Networks
  30. Skill Learning Using Process Mining for Large Language Model Plan Generation
  31. Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators
  32. A Scalable Communication Protocol for Networks of Large Language Models
  33. Personalised Feedback Framework for Online Education Programmes Using Generative AI
  34. A Structural Text-Based Scaling Model for Analyzing Political Discourse
  35. Study on the Helpfulness of Explainable Artificial Intelligence
  36. Automated Discovery of Operable Dynamics from Videos
  37. LCD-Net: A Lightweight Remote Sensing Change Detection Network Combining Feature Fusion and Gating Mechanism
  38. Can Structured Data Reduce Epistemic Uncertainty?
  39. 3D-Prover: Diversity Driven Theorem Proving With Determinantal Point Processes
  40. IsoChronoMeter: A simple and effective isochronic translation evaluation metric
  41. UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles
  42. Real-Time Localization and Bimodal Point Pattern Analysis of Palms Using UAV Imagery
  43. A Systematic Review on Prompt Engineering in Large Language Models for K-12 STEM Education
  44. Audio-based Kinship Verification Using Age Domain Conversion
  45. ChuLo: Chunk-Level Key Information Representation for Long Document Understanding
  46. MoonMetaSync: Lunar Image Registration Analysis
  47. Which Spaces can be Embedded in Lp-type Reproducing Kernel Banach Space? A Characterization via Metric Entropy
  48. Active Learning for Robust and Representative LLM Generation in Safety-Critical Scenarios
  49. Statistical Properties of Deep Neural Networks with Dependent Data
  50. Differentiable Weightless Neural Networks
  51. Classifying Healthy and Defective Fruits with a Multi-Input Architecture and CNN Models
  52. Emulators for stellar profiles in binary population modeling
  53. A Two-Stage Federated Learning Approach for Industrial Prognostics Using Large-Scale High-Dimensional Signals
  54. SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI
  55. EchoApex: A General-Purpose Vision Foundation Model for Echocardiography
  56. JOOCI: a Framework for Learning Comprehensive Speech Representations
  57. Gender Bias in Decision-Making with Large Language Models: A Study of Relationship Conflicts
  58. Few-shot Novel View Synthesis using Depth Aware 3D Gaussian Splatting
  59. Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs' Code-Mixing Capabilities
  60. Predicting Chess Puzzle Difficulty with Transformers
  61. PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries
  62. An Annotated Dataset of Errors in Premodern Greek and Baselines for Detecting Them
  63. Character-aware audio-visual subtitling in context
  64. Variational Inference in Location-Scale Families: Exact Recovery of the Mean and Correlation Matrix
  65. Time Series Viewmakers for Robust Disruption Prediction
  66. Parsing altered brain connectivity in neurodevelopmental disorders by integrating graph-based normative modeling and deep generative networks
  67. Towards the methodology for solving the minimum enclosing ball and related problems
  68. Learning to Optimize for Mixed-Integer Non-linear Programming with Feasibility Guarantees
  69. Assessing Bias in Metric Models for LLM Open-Ended Generation Bias Benchmarks
  70. Beyond Human-Only: Evaluating Human-Machine Collaboration for Collecting High-Quality Translation Data
  71. SGUQ: Staged Graph Convolution Neural Network for Alzheimer's Disease Diagnosis using Multi-Omics Data
  72. Personality Differences Drive Conversational Dynamics: A High-Dimensional NLP Approach
  73. Persistent Topological Features in Large Language Models
  74. Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Heads
  75. Towards a More Complete Theory of Function Preserving Transforms
  76. NAR-*ICP: Neural Execution of Classical ICP-based Pointcloud Registration Algorithms
  77. Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning
  78. ET-Former: Efficient Triplane Deformable Attention for 3D Semantic Scene Completion From Monocular Camera
  79. Enhancing AI Assisted Writing with One-Shot Implicit Negative Feedback
  80. Assessing the Human Likeness of AI-Generated Counterspeech
  81. Effective Self-Mining of In-Context Examples for Unsupervised Machine Translation with LLMs
  82. Generating Global and Local Explanations for Tree-Ensemble Learning Methods by Answer Set Programming
  83. Exploring the Dynamics of Lotka-Volterra Systems: Efficiency, Extinction Order, and Predictive Machine Learning
  84. WILT: A Multi-Turn, Memorization-Robust Inductive Logic Benchmark for LLMs
  85. Stationary Velocity Fields on Matrix Groups for Deformable Image Registration
  86. Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation
  87. Performance in a dialectal profiling task of LLMs for varieties of Brazilian Portuguese
  88. Liger Kernel: Efficient Triton Kernels for LLM Training
  89. What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis
  90. Data-Aware Training Quality Monitoring and Certification for Reliable Deep Learning
  91. Hybrid Spatial Representations for Species Distribution Modeling
  92. Combining Observational Data and Language for Species Range Estimation
  93. ASTM :Autonomous Smart Traffic Management System Using Artificial Intelligence CNN and LSTM
  94. Federated Data-Efficient Instruction Tuning for Large Language Models
  95. A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured Datasets
  96. ATLAS: Adapter-Based Multi-Modal Continual Learning with a Two-Stage Learning Strategy
  97. Dissecting embedding method: learning higher-order structures from data
  98. HGAurban: Heterogeneous Graph Autoencoding for Urban Spatial-Temporal Learning
  99. Towards Better Multi-head Attention via Channel-wise Sample Permutation
  100. AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
  101. The State of Julia for Scientific Machine Learning
  102. TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models
  103. When Does Perceptual Alignment Benefit Vision Representations?
  104. LVD-2M: A Long-take Video Dataset with Temporally Dense Captions
  105. LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
  106. Local and Global Decoding in Text Generation
  107. HardNet: Hard-Constrained Neural Networks with Universal Approximation Guarantees
  108. TL-PCA: Transfer Learning of Principal Component Analysis
  109. Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning
  110. Towards Foundation Models for 3D Vision: How Close Are We?
  111. Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance
  112. CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic Perception of Driving Scenes
  113. Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes
  114. On Information-Theoretic Measures of Predictive Uncertainty
  115. LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content
  116. 3DArticCyclists: Generating Synthetic Articulated 8D Pose-Controllable Cyclist Data for Computer Vision Applications
  117. UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
  118. Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning
  119. Denial-of-Service Poisoning Attacks against Large Language Models
  120. SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization
  121. Arrhythmia Classification Using Graph Neural Networks Based on Correlation Matrix
  122. Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification
  123. FlexGen: Flexible Multi-View Generation from Text and Image Inputs
  124. Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings
  125. From Anchors to Answers: A Novel Node Tokenizer for Integrating Graph Structure into Large Language Models
  126. SensorBench: Benchmarking LLMs in Coding-Based Sensor Processing
  127. Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs
  128. Towards Calibrated Losses for Adversarial Robust Reject Option Classification
  129. Towards LLM-guided Efficient and Interpretable Multi-linear Tensor Network Rank Selection
  130. A Counterexample in Image Registration
  131. Large Language Models Are Active Critics in NLG Evaluation
  132. 4-LEGS: 4D Language Embedded Gaussian Splatting
  133. SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators
  134. Benefiting from Quantum? A Comparative Study of Q-Seg, Quantum-Inspired Techniques, and U-Net for Crack Segmentation
  135. Ensemble of ConvNeXt V2 and MaxViT for Long-Tailed CXR Classification with View-Based Aggregation
  136. Early Diagnosis of Acute Lymphoblastic Leukemia Using YOLOv8 and YOLOv11 Deep Learning Models
  137. LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts
  138. Fast Convergence of Phi-Divergence Along the Unadjusted Langevin Algorithm and Proximal Sampler
  139. Separation of Neural Drives to Muscles from Transferred Polyfunctional Nerves using Implanted Micro-electrode Arrays
  140. Dynamical loss functions shape landscape topography and improve learning in artificial neural networks
  141. Building a Multivariate Time Series Benchmarking Datasets Inspired by Natural Language Processing (NLP)
  142. SAMPa: Sharpness-aware Minimization Parallelized
  143. Combinatorial Multi-armed Bandits: Arm Selection via Group Testing
  144. Large Language Model Evaluation via Matrix Nuclear-Norm
  145. Double Jeopardy and Climate Impact in the Use of Large Language Models: Socio-economic Disparities and Reduced Utility for Non-English Speakers
  146. Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework
  147. PCF-Lift: Panoptic Lifting by Probabilistic Contrastive Fusion
  148. Navigation under uncertainty: Trajectory prediction and occlusion reasoning with switching dynamical systems
  149. Querying structural and functional niches on spatial transcriptomics data
  150. Generative AI and Its Impact on Personalized Intelligent Tutoring Systems
  151. A Simple Baseline for Predicting Events with Auto-Regressive Tabular Transformers
  152. DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigation
  153. Echo State Networks for Spatio-Temporal Area-Level Data
  154. High-Dimensional Differential Parameter Inference in Exponential Family using Time Score Matching
  155. Adapt-∞: Scalable Continual Multimodal Instruction Tuning via Dynamic Data Selection
  156. Robust Gradient Descent for Phase Retrieval
  157. Modeling News Interactions and Influence for Financial Market Prediction
  158. Intelligent prospector v2.0: exploration drill planning under epistemic model uncertainty
  159. Lambda-Skip Connections: the architectural component that prevents Rank Collapse
  160. Multi-modal Vision Pre-training for Medical Image Analysis
  161. Overcoming classic challenges for artificial neural networks by providing incentives and practice
  162. MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
  163. TRESTLE: A Model of Concept Formation in Structured Domains
  164. TopoFR: A Closer Look at Topology Alignment on Face Recognition
  165. T"ubingen-CL at SemEval-2024 Task 1:Ensemble Learning for Semantic Relatedness Estimation
  166. Multilingual Controlled Generation And Gold-Standard-Agnostic Evaluation of Code-Mixed Sentences
  167. Recipe for Zero-shot POS Tagging: Is It Useful in Realistic Scenarios?
  168. When Precedents Clash
  169. MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
  170. Is Structure Dependence Shaped for Efficient Communication?: A Case Study on Coordination
  171. ROSAR: An Adversarial Re-Training Framework for Robust Side-Scan Sonar Object Detection
  172. SLaNC: Static LayerNorm Calibration
  173. Preserving Cardiac Integrity: A Topology-Infused Approach to Whole Heart Segmentation
  174. RICASSO: Reinforced Imbalance Learning with Class-Aware Self-Supervised Outliers Exposure
  175. Hybrid Transformer for Early Alzheimer's Detection: Integration of Handwriting-Based 2D Images and 1D Signal Features
  176. Graph Classification Gaussian Processes via Hodgelet Spectral Features
  177. Data-Driven Approaches for Modelling Target Behaviour
  178. Reproducible Machine Learning-based Voice Pathology Detection: Introducing the Pitch Difference Feature
  179. Transparent Networks for Multivariate Time Series
  180. Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent optimization provably fail to converge to global minimizers in the training of deep neural networks with ReLU activation
  181. Adaptive Probabilistic ODE Solvers Without Adaptive Memory Requirements
  182. Motion-guided small MAV detection in complex and non-planar scenes
  183. Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework
  184. Machine Learning for Inverse Problems and Data Assimilation
  185. AI-based particle track identification in scintillating fibres read out with imaging sensors
  186. UniGEM: A Unified Approach to Generation and Property Prediction for Molecules
  187. Do we need more complex representations for structure? A comparison of note duration representation for Music Transformers
  188. Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling
  189. Exploiting Local Features and Range Images for Small Data Real-Time Point Cloud Semantic Segmentation
  190. Artificial Intelligence-Based Triaging of Cutaneous Melanocytic Lesions
  191. Everyday Speech in the Indian Subcontinent
  192. Comparison of deep learning and conventional methods for disease onset prediction
  193. A Kernelizable Primal-Dual Formulation of the Multilinear Singular Value Decomposition
  194. A Practical Approach to Causal Inference over Time
  195. Continual Learning Improves Zero-Shot Action Recognition
  196. Cultural Fidelity in Large-Language Models: An Evaluation of Online Language Resources as a Driver of Model Performance in Value Representation
  197. A Novel No-Reference Image Quality Metric For Assessing Sharpness In Satellite Imagery
  198. Advancing Newborn Care: Precise Birth Time Detection Using AI-Driven Thermal Imaging with Adaptive Normalization
  199. Model-based Large Language Model Customization as Service
  200. Will LLMs Replace the Encoder-Only Models in Temporal Relation Classification?
  201. ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-training
  202. Information propagation dynamics in Deep Graph Networks
  203. TABCF: Counterfactual Explanations for Tabular Data Using a Transformer-Based VAE
  204. Compositional Shielding and Reinforcement Learning for Multi-Agent Systems
  205. Advancing Academic Knowledge Retrieval via LLM-enhanced Representation Similarity Fusion
  206. Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the Tasks
  207. Self-Assessed Generation: Trustworthy Label Generation for Optical Flow and Stereo Matching in Real-world
  208. Principled Bayesian Optimisation in Collaboration with Human Experts
  209. Mobility-Aware Federated Learning: Multi-Armed Bandit Based Selection in Vehicular Network
  210. KBLaM: Knowledge Base augmented Language Model
  211. Domain-Conditioned Transformer for Fully Test-time Adaptation
  212. Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs
  213. LKASeg:Remote-Sensing Image Semantic Segmentation with Large Kernel Attention and Full-Scale Skip Connections
  214. Unified Breakdown Analysis for Byzantine Robust Gossip
  215. A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning
  216. Coupled autoregressive active inference agents for control of multi-joint dynamical systems
  217. 4DStyleGaussian: Zero-shot 4D Style Transfer with Gaussian Splatting
  218. Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion
  219. MMCFND: Multimodal Multilingual Caption-aware Fake News Detection for Low-resource Indic Languages
  220. Deterministic Apple Tasting
  221. Parameterize Structure with Differentiable Template for 3D Shape Generation
  222. Are LLMs Socially Adaptive? Contrasting Belief Evolution in Large Language Models and Humans
  223. Improved Depth Estimation of Bayesian Neural Networks
  224. GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
  225. Stein Variational Evolution Strategies
  226. Reverse Refinement Network for Narrow Rural Road Detection in High-Resolution Satellite Imagery
  227. Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal
  228. Collaborative filtering based on nonnegative/binary matrix factorization
  229. Class Balancing Diversity Multimodal Ensemble for Alzheimer's Disease Diagnosis and Early Detection
  230. Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training
  231. BookWorm: A Dataset for Character Description and Analysis
  232. Groningen: Spatial Prediction of Rock Gas Saturation by Leveraging Selected and Augmented Well and Seismic Data with Classifier Ensembles
  233. Optimal Time Complexity Algorithms for Computing General Random Walk Graph Kernels on Sparse Graphs
  234. Affinity-Graph-Guided Contractive Learning for Pretext-Free Medical Image Segmentation with Minimal Annotation
  235. SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samples
  236. Pubic Symphysis-Fetal Head Segmentation Network Using BiFormer Attention Mechanism and Multipath Dilated Convolution
  237. On Representation of 3D Rotation in the Context of Deep Learning
  238. LLM-based Code-Switched Text Generation for Grammatical Error Correction
  239. Locking Down the Finetuned LLMs Safety
  240. Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach
  241. Disentangling Hate Across Target Identities
  242. GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphs
  243. Anatomical feature-prioritized loss for enhanced MR to CT translation
  244. MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media
  245. Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
  246. DiRW: Path-Aware Digraph Learning for Heterophily
  247. QIANets: Quantum-Integrated Adaptive Networks for Reduced Latency and Improved Inference Times in CNN Models
  248. Optimal and computationally tractable lower bounds for logistic log-likelihoods
  249. Animate-X: Universal Character Image Animation with Enhanced Motion Representation
  250. A Comparative Study of Translation Bias and Accuracy in Multilingual Large Language Models for Cross-Language Claim Verification
  251. ROA-BEV: 2D Region-Oriented Attention for BEV-based 3D Object Detection
  252. A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration
  253. Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective
  254. A Multi-Task Text Classification Pipeline with Natural Language Explanations: A User-Centric Evaluation in Sentiment Analysis and Offensive Language Identification in Greek Tweets
  255. Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection
  256. Manifold-Aware Local Feature Modeling for Semi-Supervised Medical Image Segmentation
  257. Back-of-the-Book Index Automation for Arabic Documents
  258. ABBA-VSM: Time Series Classification using Symbolic Representation on the Edge
  259. Trust or Bust: Ensuring Trustworthiness in Autonomous Weapon Systems
  260. Exploring Semi-Supervised Learning for Online Mapping
  261. Machine Translation Evaluation Benchmark for Wu Chinese: Workflow and Analysis
  262. QUIS: Question-guided Insights Generation for Automated Exploratory Data Analysis
  263. Two-Stage Approach for Brain MR Image Synthesis: 2D Image Synthesis and 3D Refinement
  264. big.LITTLE Vision Transformer for Efficient Visual Recognition
  265. Slide-based Graph Collaborative Training for Histopathology Whole Slide Image Analysis
  266. Revisiting Matrix Sketching in Linear Bandits: Achieving Sublinear Regret via Dyadic Block Sketching
  267. LoLCATs: On Low-Rank Linearizing of Large Language Models
  268. Feedback Favors the Generalization of Neural ODEs
  269. Automated extraction of 4D aircraft trajectories from video recordings
  270. Capture Artifacts via Progressive Disentangling and Purifying Blended Identities for Deepfake Detection
  271. Measurability in the Fundamental Theorem of Statistical Learning
  272. Revisiting Graph Autoencoders as Implicit Contrastive Learners
  273. LADMIM: Logical Anomaly Detection with Masked Image Modeling in Discrete Latent Space
  274. Learning via Surrogate PAC-Bayes
  275. BanglaQuAD: A Bengali Open-domain Question Answering Dataset
  276. KNN Transformer with Pyramid Prompts for Few-Shot Learning
  277. Detecting Unforeseen Data Properties with Diffusion Autoencoder Embeddings using Spine MRI data
  278. ChakmaNMT: Machine Translation for a Low-Resource and Endangered Language via Transliteration
  279. Neural Quasiprobabilistic Likelihood Ratio Estimation with Negatively Weighted Data
  280. SkillAggregation: Reference-free LLM-Dependent Aggregation
  281. Large Language Model-Enhanced Reinforcement Learning for Generic Bus Holding Control Strategies
  282. Minimum Tuning to Unlock Long Output from LLMs with High Quality Data as the Key
  283. EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning
  284. Fed-pilot: Optimizing LoRA Allocation for Efficient Federated Fine-Tuning with Heterogeneous Clients
  285. Language Model Embeddings Can Be Sufficient for Bayesian Optimization
  286. Eliminating the Language Bias for Visual Question Answering with fine-grained Causal Intervention
  287. Hamiltonian Neural Networks for Robust Out-of-Time Credit Scoring
  288. Scalable Multi-Domain Adaptation of Language Models using Modular Experts
  289. Gaussian Mixture Vector Quantization with Aggregated Categorical Posterior
  290. Is Parameter Collision Hindering Continual Learning in LLMs?
  291. GUISE: Graph GaUssIan Shading watErmark
  292. Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations
  293. Generative Human Video Compression with Multi-granularity Temporal Trajectory Factorization
  294. X-Fi: A Modality-Invariant Foundation Model for Multimodal Human Sensing
  295. HSR-Enhanced Sparse Attention Acceleration
  296. Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?
  297. Tracing Human Stress from Physiological Signals using UWB Radar
  298. Diagnosing Hate Speech Classification: Where Do Humans and Machines Disagree, and Why?
  299. Fast and Accurate Neural Rendering Using Semi-Gradients
  300. Performance Evaluation of Deep Learning and Transformer Models Using Multimodal Data for Breast Cancer Classification
  301. Unified Representation of Genomic and Biomedical Concepts through Multi-Task, Multi-Source Contrastive Learning
  302. Variational autoencoders with latent high-dimensional steady geometric flows for dynamics
  303. Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations
  304. FormalAlign: Automated Alignment Evaluation for Autoformalization
  305. TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
  306. MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling
  307. Interaction-Guided Two-Branch Image Dehazing Network
  308. Physical Consistency Bridges Heterogeneous Data in Molecular Multi-Task Learning
  309. StegaINR4MIH: steganography by implicit neural representation for multi-image hiding
  310. How to Construct Random Unitaries
  311. Learning Linear Attention in Polynomial Time
  312. Queueing Matching Bandits with Preference Feedback
  313. REHRSeg: Unleashing the Power of Self-Supervised Super-Resolution for Resource-Efficient 3D MRI Segmentation
  314. Innovative Deep Learning Techniques for Obstacle Recognition: A Comparative Study of Modern Detection Algorithms
  315. Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors
  316. PromptGCN: Bridging Subgraph Gaps in Lightweight GCNs
  317. NeRF-enabled Analysis-Through-Synthesis for ISAR Imaging of Small Everyday Objects with Sparse and Noisy UWB Radar Data
  318. PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets
  319. Beyond Graphs: Can Large Language Models Comprehend Hypergraphs?
  320. fastHDMI: Fast Mutual Information Estimation for High-Dimensional Data
  321. VideoAgent: Self-Improving Video Generation
  322. RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates
  323. Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning
  324. Self-Organizing Recurrent Stochastic Configuration Networks for Nonstationary Data Modelling
  325. Ukrainian-to-English folktale corpus: Parallel corpus creation and augmentation for machine translation in low-resource languages
  326. The Epochal Sawtooth Phenomenon: Unveiling Training Loss Oscillations in Adam and Other Optimizers
  327. Towards Bridging Generalization and Expressivity of Graph Neural Networks
  328. XAI-based Feature Selection for Improved Network Intrusion Detection Systems
  329. StatioCL: Contrastive Learning for Time Series via Non-Stationary and Temporal Contrast