mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 8 Oct 2024

391 papers

  1. O1 Replication Journey: A Strategic Progress Report -- Part 1LLM reasoning → Test-time compute and efficient thinking
  2. Improving Embedding Accuracy for Document Retrieval Using Entity Relationship Maps and Model-Aware Contrastive SamplingRetrieval-augmented generation → Generation and context integration
  3. ENWAR: A RAG-empowered Multi-Modal LLM Framework for Wireless Environment PerceptionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  4. RRADistill: Distilling LLMs' Passage Ranking Ability for Long-Tail Queries Document Re-Ranking on a Search EngineKnowledge distillation → Knowledge distillation for LLMs
  5. Applying Refusal-Vector Ablation to Llama 3.1 70B AgentsLLM agents and tool use → Agent threats, guardrails and governance
  6. Application of NotebookLM, a Large Language Model with Retrieval-Augmented Generation, for Lung Cancer StagingRetrieval-augmented generation → Medical and biomedical RAG
  7. CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete ConceptLLM safety and security → Machine unlearning
  8. Generating Synthetic Datasets for Few-shot Prompt TuningSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  9. Automating Bibliometric Analysis with Sentence Transformers and Retrieval-Augmented Generation (RAG): A Pilot Study in Semantic and Contextual Search for Customized Literature Characterization for High-Impact Urban ResearchRetrieval-augmented generation → Agentic RAG, agents and memory
  10. Toward generalizable learning of all (linear) first-order methods via memory augmented TransformersMixture-of-experts → Expert routing strategies
  11. ERVQA: A Dataset to Benchmark the Readiness of Large Vision Language Models in Hospital EnvironmentsMultimodal LLMs / vision-language models → Medical vision-language models
  12. Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and ObjectsLLM reasoning → Multimodal reasoning
  13. MLissard: Multilingual Long and Simple Sequential Reasoning BenchmarksLLM reasoning → Reasoning benchmarks and evaluation
  14. Generative Artificial Intelligence (GAI) for Mobile Communications: A Diffusion Model PerspectiveDiffusion models → Diffusion for compression and wireless
  15. Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
  16. Auto-Evolve: Enhancing Large Language Model's Performance via Self-Reasoning FrameworkLLM reasoning → Prompting and chain-of-thought reasoning
  17. Learning in complex action spaces without policy gradientsDeep reinforcement learning methods → RL theory and sample complexity
  18. FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical ReasoningLLM reasoning → Hallucination detection and mitigation
  19. Accelerated Preference Optimization for Large Language Model AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  20. PREDICT: Preference Reasoning by Evaluating Decomposed preferences Inferred from Candidate TrajectoriesLLM reasoning → Reinforcement learning for reasoning
  21. The Mystery of Compositional Generalization in Graph-based Generative Commonsense ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  22. Probing the Robustness of Theory of Mind in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  23. Mixture Compressor for Mixture-of-Experts LLMs Gains MoreMixture-of-experts → MoE large language models
  24. Think While You Generate: Discrete Diffusion with Planned DenoisingLLM reasoning → Diffusion reasoning and test-time scaling +1
  25. SymDiff: Equivariant Diffusion via Stochastic SymmetrisationDiffusion models → Flow matching, time series and science
  26. EVOLvE: Evaluating and Optimizing LLMs For In-Context ExplorationLLM reasoning → Reinforcement learning for reasoning
  27. BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile ManipulationLLM reasoning → Spatial and embodied reasoning +1
  28. A Timeline and Analysis for Representation Plasticity in Large Language ModelsMechanistic interpretability → Probing deception, bias and beliefs
  29. DataEnvGym: Data Generation Agents in Teacher Environments with Student FeedbackLLM agents and tool use → Educational agents and math problem solving
  30. RL, but don't do anything I wouldn't doDeep reinforcement learning methods → Safe and constrained RL
  31. Solving robust MDPs as a sequence of static RL problemsDeep reinforcement learning methods → RL theory and sample complexity
  32. LeanAgent: Lifelong Learning for Formal Theorem ProvingLLM reasoning → Mathematical reasoning
  33. Multimodal Situational SafetyMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  34. Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to SeeMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  35. Temporal Reasoning Transfer from Text to VideoLLM reasoning → Multimodal reasoning
  36. GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  37. AgentSquare: Automatic LLM Agent Search in Modular Design SpaceLLM agents and tool use → General LLM agent frameworks and benchmarks
  38. Diversifying Policy Behaviors with Extrinsic Behavioral CuriosityOffline RL and imitation learning from data → Imitation learning methods +1
  39. Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based ApproachDiffusion models → Diffusion for compression and wireless
  40. Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQARetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  41. Optimizing the Training Schedule of Multilingual NMT using Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  42. Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  43. Interpretability for Time Series Transformers using A Concept Bottleneck FrameworkMechanistic interpretability → Interpreting time-series and weather models
  44. LLM-based SPARQL Query Generation from Natural Language over Federated Knowledge GraphsRetrieval-augmented generation → RAG pipeline design and evaluation
  45. RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image GenerationDiffusion models → Diffusion foundations and sampling
  46. Shielded Diffusion: Generating Novel and Diverse Images using Sparse RepellencyDiffusion models → Diffusion foundations and sampling
  47. An Eye for an Ear: Zero-shot Audio Description Leveraging an Image Captioner using Audiovisual Distribution AlignmentMultimodal LLMs / vision-language models → Video understanding with MLLMs
  48. Aria: An Open Multimodal Native Mixture-of-Experts ModelMixture-of-experts → Multimodal MoE models
  49. Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGRetrieval-augmented generation → RAG pipeline design and evaluation
  50. PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse SamplingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  51. Pyramidal Flow Matching for Efficient Video Generative ModelingDiffusion models → Video generation
  52. EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical AlignmentState-space sequence models (S4, Mamba) → Vision Mamba backbones
  53. Beyond Captioning: Task-Specific Prompting for Improved VLM Performance in Mathematical ReasoningLLM reasoning → Multimodal reasoning +1
  54. TIMBA: Time series Imputation with Bi-directional Mamba Blocks and Diffusion modelsDiffusion models → Flow matching, time series and science +1
  55. Give me a hint: Can LLMs take a hint to solve math problems?LLM reasoning → Mathematical reasoning
  56. Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusionDiffusion models → Diffusion foundations and sampling
  57. Communicating with Speakers and Listeners of Different Pragmatic LevelsLLM reasoning → Reasoning benchmarks and evaluation
  58. ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided PromptMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  59. Towards Zero-Shot, Controllable Dialog Planning with LLMsLLM reasoning → Reasoning for agents, planning and code
  60. PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness ModelingDiffusion models → Flow matching, time series and science
  61. CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object DetectionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  62. Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  63. SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  64. Reinforcement Learning From Imperfect Corrective Actions And Proxy RewardsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  65. LightRAG: Simple and Fast Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  66. Training-free Diffusion Model Alignment with Sampling DemonsDiffusion models → Diffusion and flow policies for robotics +1
  67. KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from ServerKnowledge distillation → Federated, robust and private distillation
  68. Demonstration Based Explainable AI for Learning from Demonstration MethodsOffline RL and imitation learning from data → Robot learning from demonstration
  69. PixLens: A Novel Framework for Disentangled Evaluation in Diffusion-Based Image Editing with Object Detection + SAMDiffusion models → Image generation, text-to-image and editing
  70. Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  71. DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image EditingDiffusion models → Robustness, privacy and adversarial aspects
  72. T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance DesignDiffusion models → Video generation +1
  73. Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization ProblemDeep reinforcement learning methods → RL for games and combinatorial optimization
  74. ACPBench: Reasoning about Action, Change, and PlanningLLM reasoning → Reasoning for agents, planning and code
  75. Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model UnlearningDiffusion models → Robustness, privacy and adversarial aspects +1
  76. Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language ModelsMixture-of-experts → MoE large language models
  77. On the Modeling Capabilities of Large Language Models for Sequential Decision MakingLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  78. Efficient Policy Evaluation with Safety Constraint for Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  79. ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion SamplerDiffusion models → Video generation
  80. A Unified Framework for Motion Reasoning and Generation in Human InteractionLLM reasoning → Spatial and embodied reasoning
  81. Remote Sensing Image Segmentation Using Vision Mamba and Multi-Scale Multi-Frequency Feature FusionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  82. Structural Reasoning Improves Molecular Understanding of LLMLLM reasoning → Clinical and biomedical applications
  83. Multimodal Large Language Models and Tunings: Vision, Language, Sensors, Audio, and BeyondMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  84. Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in SuperpositionMechanistic interpretability → Knowledge and representations inside LLMs
  85. TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video GenerationDiffusion models → Video generation
  86. ParallelSpec: Parallel Drafter for Efficient Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  87. Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?LLM reasoning → Reinforcement learning for reasoning +1
  88. NegMerge: Sign-Consensual Weight Merging for Machine UnlearningLLM safety and security → Machine unlearning
  89. Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-tuningDiffusion models → Diffusion and flow policies for robotics +2
  90. Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
  91. Learning Force Distribution Estimation for the GelSight Mini Optical Tactile Sensor Based on Finite Element Analysis
  92. Wearable-Based Real-time Freezing of Gait Detection in Parkinson's Disease Using Self-Supervised Learning
  93. Data Efficiency for Large Recommendation Models
  94. NaVIP: An Image-Centric Indoor Navigation Solution for Visually Impaired People
  95. A Deep Learning Approach to Estimate Canopy Height and Uncertainty by Integrating Seasonal Optical, SAR and Limited GEDI LiDAR Data over Northern Forests
  96. In-Context Code-Text Learning for Bimodal Software Engineering
  97. A Hybrid Graph Neural Network for Enhanced EEG-Based Depression Detection
  98. Multiple Global Peaks Big Bang-Big Crunch Algorithm for Multimodal Optimization
  99. Molecular Dynamics and Machine Learning Unlock Possibilities in Beauty Design -- A Perspective
  100. RingGesture: A Ring-Based Mid-Air Gesture Typing System Powered by a Deep-Learning Word Prediction Framework
All 391
  1. Gesture2Text: A Generalizable Decoder for Word-Gesture Keyboards in XR Through Trajectory Coarse Discretization and Pre-training
  2. A Case Study of Next Portfolio Prediction for Mutual Funds
  3. M3EL: A Multi-task Multi-topic Dataset for Multi-modal Entity Linking
  4. Ethical Leadership in the Age of AI Challenges, Opportunities and Framework for Ethical Leadership
  5. Self-supervised inter-intra period-aware ECG representation learning for detecting atrial fibrillation
  6. Two-Stage Radio Map Construction with Real Environments and Sparse Measurements
  7. Predicting Fine-grained Behavioral and Psychological Symptoms of Dementia Based on Machine Learning and Smart Wearable Devices
  8. Liver Cancer Knowledge Graph Construction based on dynamic entity replacement and masking strategies RoBERTa-BiLSTM-CRF model
  9. Empowering Cognitive Digital Twins with Generative Foundation Models: Developing a Low-Carbon Integrated Freight Transportation System
  10. CUPID: A Real-Time Session-Based Reciprocal Recommendation System for a One-on-One Social Discovery Platform
  11. Evaluating Performance and Bias of Negative Sampling in Large-Scale Sequential Recommendation Models
  12. Automated Quality Control System for Canned Tuna Production using Artificial Vision
  13. FACMIC: Federated Adaptative CLIP Model for Medical Image Classification
  14. Neuropsychology of AI: Relationship Between Activation Proximity and Categorical Proximity Within Neural Categories of Synthetic Cognition
  15. An Innovative Solution: AI-Based Digital Screen-Integrated Tables for Educational Settings
  16. ToolBridge: An Open-Source Dataset to Equip LLMs with External Tool Capabilities
  17. PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches
  18. Large Continual Instruction Assistant
  19. Mitigating the Impact of Reference Quality on Evaluation of Summarization Systems with Reference-Free Metrics
  20. Reflections on Disentanglement and the Latent Space
  21. Different Cybercrimes and their Solution for Common People
  22. The Solution for Temporal Action Localisation Task of Perception Test Challenge 2024
  23. A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models
  24. Precision Cancer Classification and Biomarker Identification from mRNA Gene Expression via Dimensionality Reduction and Explainable AI
  25. Lightweight Deep Learning Framework for Accurate Particle Flow Energy Reconstruction
  26. AAAI Workshop on AI Planning for Cyber-Physical Systems -- CAIPI24
  27. Stress Detection on Code-Mixed Texts in Dravidian Languages using Machine Learning
  28. NLP Case Study on Predicting the Before and After of the Ukraine-Russia and Hamas-Israel Conflicts
  29. Restructuring Vector Quantization with the Rotation Trick
  30. FAIREDU: A Multiple Regression-Based Method for Enhancing Fairness in Machine Learning Models for Educational Applications
  31. Predicting Battery Capacity Fade Using Probabilistic Machine Learning Models With and Without Pre-Trained Priors
  32. MIRACLE3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model Construction
  33. Biased AI can Influence Political Decision-Making
  34. Stochastic Sparse Sampling: A Framework for Variable-Length Medical Time Series Classification
  35. BEVLoc: Cross-View Localization and Matching via Birds-Eye-View Synthesis
  36. Automating Data Science Pipelines with Tensor Completion
  37. A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery
  38. Topology-Agnostic Graph U-Nets for Scalar Field Prediction on Unstructured Meshes
  39. Reliable Heading Tracking for Pedestrian Road Crossing Prediction Using Commodity Devices
  40. Adaptive Random Fourier Features Training Stabilized By Resampling With Applications in Image Regression
  41. Provable Accuracy Bounds for Hybrid Dynamical Optimization and Sampling
  42. Multimodal Representation Learning using Adaptive Graph Construction
  43. Counterfactual Causal Inference in Natural Language with Large Language Models
  44. Skin Cancer Machine Learning Model Tone Bias
  45. Validation of the Scientific Literature via Chemputation Augmented by Large Language Models
  46. Adver-City: Open-Source Multi-Modal Dataset for Collaborative Perception Under Adverse Weather Conditions
  47. Covering Numbers for Deep ReLU Networks with Applications to Function Approximation and Nonparametric Regression
  48. Riemannian Optimization for Non-convex Euclidean Distance Geometry with Global Recovery Guarantees
  49. Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
  50. Cooperative and Asynchronous Transformer-based Mission Planning for Heterogeneous Teams of Mobile Robots
  51. HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid
  52. Communication-Efficient Federated Group Distributionally Robust Optimization
  53. Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling
  54. Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation
  55. UNCOM: Zero-shot Context-Aware Command Understanding for Tabletop Scenarios
  56. Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation
  57. Tree-Based Leakage Inspection and Control in Concept Bottleneck Models
  58. Robust Domain Generalisation with Causal Invariant Bayesian Neural Networks
  59. Harnessing the Power of Noise: A Survey of Techniques and Applications
  60. FedGraph: A Research Library and Benchmark for Federated Graph Learning
  61. Filtered Randomized Smoothing: A New Defense for Robust Modulation Classification
  62. Are Large Language Models State-of-the-art Quality Estimators for Machine Translation of User-generated Content?
  63. Batched Bayesian optimization by maximizing the probability of including the optimum
  64. Boolean Nearest Neighbor Language in the Knowledge Compilation Map
  65. Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
  66. Joint Bayesian Parameter and Model Order Estimation for Low-Rank Probability Mass Tensors
  67. Towards a GENEA Leaderboard -- an Extended, Living Benchmark for Evaluating and Advancing Conversational Motion Synthesis
  68. Convex Estimation of Gaussian Graphical Regression Models with Covariates
  69. Differentiation Through Black-Box Quadratic Programming Solvers
  70. Temporal Image Caption Retrieval Competition -- Description and Results
  71. A Comparative Study of Hybrid Models in Health Misinformation Text Classification
  72. Quantifying Training Difficulty and Accelerating Convergence in Neural Network-Based PDE Solvers
  73. Model Predictive Control is Almost Optimal for Restless Bandit
  74. Benchmarking of a new data splitting method on volcanic eruption data
  75. Compositional Risk Minimization
  76. SHAP values via sparse Fourier representation
  77. A Taxonomy of Collectible Card Games from a Game-Playing AI Perspective
  78. Conformal Structured Prediction
  79. A New Architecture for Neural Enhanced Multiobject Tracking
  80. Score Design for Multi-Criteria Incentivization
  81. Non-Halting Queries: Exploiting Fixed Points in LLMs
  82. Monocular Visual Place Recognition in LiDAR Maps via Cross-Modal State Space Model and Multi-View Matching
  83. Solving Functional Optimization with Deep Networks and Variational Principles
  84. SHADE: Deep Density-based Clustering
  85. HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction
  86. Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization
  87. Unsupervised Model Diagnosis
  88. ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality in a Training-free Way
  89. Using Crank-Nikolson Scheme to Solve the Korteweg-de Vries (KdV) Equation
  90. SD-πXL: Generating Low-Resolution Quantized Imagery via Score Distillation
  91. Parameter Choice and Neuro-Symbolic Approaches for Deep Domain-Invariant Learning
  92. TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data
  93. Range, not Independence, Drives Modularity in Biologically Inspired Representations
  94. RelitLRM: Generative Relightable Radiance for Large Reconstruction Models
  95. Gaussian Variational Schemes on Bounded and Unbounded Domains
  96. Fair-OBNC: Correcting Label Noise for Fairer Datasets
  97. A mechanistically interpretable neural network for regulatory genomics
  98. Round and Round We Go! What makes Rotary Positional Encodings useful?
  99. Integrating Planning into Single-Turn Long-Form Text Generation
  100. EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective
  101. Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing Images
  102. Benign Overfitting for Regression with Trained Two-Layer ReLU Networks
  103. Neural-Bayesian Program Learning for Few-shot Dialogue Intent Parsing
  104. Beyond the Alphabet: Deep Signal Embedding for Enhanced DNA Clustering
  105. A column generation algorithm with dynamic constraint aggregation for minimum sum-of-squares clustering
  106. The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
  107. SC-Bench: A Large-Scale Dataset for Smart Contract Auditing
  108. Manual Verbalizer Enrichment for Few-Shot Text Classification
  109. Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines
  110. QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers
  111. Markov Equivalence and Consistency in Differentiable Structure Learning
  112. Automated quality assessment using appearance-based simulations and hippocampus segmentation on low-field paediatric brain MR images
  113. GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
  114. Estimating the Number of HTTP/3 Responses in QUIC Using Deep Learning
  115. Adaptive Label Smoothing for Out-of-Distribution Detection
  116. Towards Unsupervised Eye-Region Segmentation for Eye Tracking
  117. Amortized Inference of Causal Models via Conditional Fixed-Point Iterations
  118. De-VertiFL: A Solution for Decentralized Vertical Federated Learning
  119. X2-DFD: A framework for eXplainable and eXtendable Deepfake Detection
  120. Learning AND-OR Templates for Professional Photograph Parsing and Guidance
  121. Uncertainty estimation via ensembles of deep learning models and dropout layers for seismic traces
  122. E3STO: Orbital Inspired SE(3)-Equivariant Molecular Representation for Electron Density Prediction
  123. UnSeGArmaNet: Unsupervised Image Segmentation using Graph Neural Networks with Convolutional ARMA Filters
  124. SwiftQueue: Optimizing Low-Latency Applications with Swift Packet Queuing
  125. Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
  126. ConceptAgent: LLM-Driven Precondition Grounding and Tree Search for Robust Task Planning and Execution
  127. Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmap
  128. RefineStyle: Dynamic Convolution Refinement for StyleGAN
  129. Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation
  130. Listening to Patients: A Framework of Detecting and Mitigating Patient Misreport for Medical Dialogue Generation
  131. TOWER: Tree Organized Weighting for Evaluating Complex Instructions
  132. Diversity-Rewarded CFG Distillation
  133. Scalable Mechanistic Neural Networks for Differential Equations and Machine Learning
  134. Training-free LLM-generated Text Detection by Mining Token Probability Sequences
  135. Contrastive Learning to Fine-Tune Feature Extraction Models for the Visual Cortex
  136. Posets and Bounded Probabilities for Discovering Order-inducing Features in Event Knowledge Graphs
  137. Hierarchical Matrix Completion for the Prediction of Properties of Binary Mixtures
  138. Gaussian-Based and Outside-the-Box Runtime Monitoring Join Forces
  139. Extracting Moore Machines from Transformers using Queries and Counterexamples
  140. HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAs
  141. Weighted Embeddings for Low-Dimensional Graph Representation
  142. Block Induced Signature Generative Adversarial Network (BISGAN): Signature Spoofing Using GANs and Their Evaluation
  143. QERA: an Analytical Framework for Quantization Error Reconstruction
  144. Data Quality Issues in Vulnerability Detection Datasets
  145. SpecTrack: Learned Multi-Rotation Tracking via Speckle Imaging
  146. Jet Expansions of Residual Computation
  147. Can Language Models Induce Grammatical Knowledge from Indirect Evidence?
  148. QT-DoG: Quantization-aware Training for Domain Generalization
  149. Unveiling Transformer Perception by Exploring Input Manifolds
  150. Variable Bitrate Residual Vector Quantization for Audio Coding
  151. SplaTraj: Camera Trajectory Generation with Semantic Gaussian Splatting
  152. Generalized Sparse Additive Model with Unknown Link Function
  153. A large collection of bioinformatics question-query pairs over federated knowledge graphs: methodology and applications
  154. Motion Forecasting in Continuous Driving
  155. Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization
  156. TapType: Ten-finger text entry on everyday surfaces via Bayesian inference
  157. Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision
  158. Utilizing Lyapunov Exponents in designing deep neural networks
  159. LAYUP: Asynchronous decentralized gradient descent with LAYer-wise UPdates
  160. Are Minimal Radial Distortion Solvers Necessary for Relative Pose Estimation?
  161. DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States
  162. Generalizing to any diverse distribution: uniformity, gentle finetuning and rebalancing
  163. Learning to Learn with Contrastive Meta-Objective
  164. Deep neural network-based detection of counterfeit products from smartphone images
  165. FLOPS: Forward Learning with OPtimal Sampling
  166. STNet: Deep Audio-Visual Fusion Network for Robust Speaker Tracking
  167. Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts
  168. Active Evaluation Acquisition for Efficient LLM Benchmarking
  169. Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models
  170. Single Point-Based Distributed Zeroth-Order Optimization with a Non-Convex Stochastic Objective Function
  171. TouchInsight: Uncertainty-aware Rapid Touch and Text Input for Mixed Reality from Egocentric Vision
  172. Athanor: Local Search over Abstract Constraint Specifications
  173. Learning Gaussian Data Augmentation in Feature Space for One-shot Object Detection in Manga
  174. Fortify Your Foundations: Practical Privacy and Security for Foundation Model Deployments In The Cloud
  175. FINALLY: fast and universal speech enhancement with studio-like quality
  176. Accelerating Error Correction Code Transformers
  177. MedUniSeg: 2D and 3D Medical Image Segmentation via a Prompt-driven Universal Model
  178. Automatic Summarization of Long Documents
  179. Mini-Batch Kernel k-means
  180. MTFL: Multi-Timescale Feature Learning for Weakly-Supervised Anomaly Detection in Surveillance Videos
  181. Brain-inspired continual pre-trained learner via silent synaptic consolidation
  182. DimINO: Dimension-Informed Neural Operator Learning
  183. Towards an Autonomous Surface Vehicle Prototype for Artificial Intelligence Applications of Water Quality Monitoring
  184. Ordering-Based Causal Discovery for Linear and Nonlinear Relations
  185. Deep learning-based fault identification in condition monitoring
  186. Frame forecasting in cine MRI using the PCA respiratory motion model: comparing recurrent neural networks trained online and transformers
  187. Edit Distances and Their Applications to Downstream Tasks in Research and Commercial Contexts
  188. Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization
  189. MDAP: A Multi-view Disentangled and Adaptive Preference Learning Framework for Cross-Domain Recommendation
  190. MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment
  191. A second-order-like optimizer with adaptive gradient scaling for deep learning
  192. Heuristics for Partially Observable Stochastic Contingent Planning
  193. Believing is Seeing: Unobserved Object Detection using Generative Models
  194. From Tokens to Words: On the Inner Lexicon of LLMs
  195. MelissaDL x Breed: Towards Data-Efficient On-line Supervised Training of Multi-parametric Surrogates with Active Learning
  196. Stochastic Bandits for Egalitarian Assignment
  197. Bottom-up Anytime Discovery of Generalised Multimodal Graph Patterns for Knowledge Graphs
  198. Time Transfer: On Optimal Learning Rate and Batch Size In The Infinite Data Limit
  199. A noise-corrected Langevin algorithm and sampling by half-denoising
  200. Towards an Operational Responsible AI Framework for Learning Analytics in Higher Education
  201. Multi-Session Client-Centered Treatment Outcome Evaluation in Psychotherapy
  202. IncSAR: A Dual Fusion Incremental Learning Framework for SAR Target Recognition
  203. CAP: Detecting Unauthorized Data Usage in Generative Models via Prompt Generation
  204. Probing Language Models on Their Knowledge Source
  205. Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filtering
  206. Uncertainty-Aware Fairness-Adaptive Classification Trees
  207. Vision Transformer based Random Walk for Group Re-Identification
  208. Extended convexity and smoothness and their applications in deep learning
  209. A Parameter Update Balancing Algorithm for Multi-task Ranking Models in Recommendation Systems
  210. Gradual Learning: Optimizing Fine-Tuning with Partially Mastered Knowledge in Large Language Models
  211. Core Tokensets for Data-efficient Sequential Training of Transformers
  212. CodeCipher: Learning to Obfuscate Source Code Against LLMs
  213. F"urElise: Capturing and Physically Synthesizing Hand Motions of Piano Performance
  214. Enhanced Feature Based Granular Ball Twin Support Vector Machine
  215. Contextual Bandits with Non-Stationary Correlated Rewards for User Association in MmWave Vehicular Networks
  216. GlucoBench: Curated List of Continuous Glucose Monitoring Datasets with Prediction Benchmarks
  217. Song Emotion Classification of Lyrics with Out-of-Domain Data under Label Scarcity
  218. Integrated Encoding and Quantization to Enhance Quanvolutional Neural Networks
  219. ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition
  220. GLRT-Based Metric Learning for Remote Sensing Object Retrieval
  221. Comparative Analysis of Novel View Synthesis and Photogrammetry for 3D Forest Stand Reconstruction and extraction of individual tree parameters
  222. Cefdet: Cognitive Effectiveness Network Based on Fuzzy Inference for Action Detection
  223. Efficient Few-shot Learning for Multi-label Classification of Scientific Documents with Many Classes
  224. Grounding is All You Need? Dual Temporal Grounding for Video Dialog
  225. Information Discovery in e-Commerce
  226. Guided Self-attention: Find the Generalized Necessarily Distinct Vectors for Grain Size Grading
  227. Temperature Optimization for Bayesian Deep Learning
  228. Learning the Generalizable Manipulation Skills on Soft-body Tasks via Guided Self-attention Behavior Cloning Policy
  229. Simple Relative Deviation Bounds for Covariance and Gram Matrices
  230. Pathwise Gradient Variance Reduction with Control Variates in Variational Inference
  231. Exploring the Meaningfulness of Nearest Neighbor Search in High-Dimensional Space
  232. Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label Setting
  233. Label Confidence Weighted Learning for Target-level Sentence Simplification
  234. Wolf2Pack: The AutoFusion Framework for Dynamic Parameter Fusion
  235. Learning to Drift in Extreme Turning with Active Exploration and Gaussian Process Based MPC
  236. End-to-end multi-channel speaker extraction and binaural speech synthesis
  237. CUBE360: Learning Cubic Field Representation for Monocular 360 Depth Estimation for Virtual Reality
  238. Diminishing Exploration: A Minimalist Approach to Piecewise Stationary Multi-Armed Bandits
  239. Private and Communication-Efficient Federated Learning based on Differentially Private Sketches
  240. Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration
  241. Reducing fuzzy relation equations via concept lattices
  242. Less is more: Embracing sparsity and interpolation with Esiformer for time series forecasting
  243. Mero Nagarikta: Advanced Nepali Citizenship Data Extractor with Deep Learning-Powered Text Detection and OCR
  244. Advancements in Road Lane Mapping: Comparative Fine-Tuning Analysis of Deep Learning-based Semantic Segmentation Methods Using Aerial Imagery
  245. Enhancing Temporal Modeling of Video LLMs via Time Gating
  246. TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation
  247. Network Topology Inference from Smooth Signals Under Partial Observability
  248. Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk
  249. A Two-Step Approach for Data-Efficient French Pronunciation Learning
  250. Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning
  251. Long-Context Linear System Identification
  252. Extreme Value Modelling of Feature Residuals for Anomaly Detection in Dynamic Graphs
  253. Copiloting Diagnosis of Autism in Real Clinical Scenarios via LLMs
  254. Convolutional neural networks applied to modification of images
  255. Understanding with toy surrogate models in machine learning
  256. Improving Disease Comorbidity Prediction Based on Human Interactome with Biologically Supervised Graph Embedding
  257. Diversity and Inclusion Index with Networks and Similarity: Analysis and its Application
  258. Edge-Cloud Collaborative Satellite Image Analysis for Efficient Man-Made Structure Recognition
  259. Communication-Efficient Federated Learning under Dynamic Device Arrival and Departure: Convergence Analysis and Algorithm Design
  260. Robust Transfer Learning for Active Level Set Estimation with Locally Adaptive Gaussian Process Prior
  261. SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection
  262. Does RoBERTa Perform Better than BERT in Continual Learning: An Attention Sink Perspective
  263. Score-Based Variational Inference for Inverse Problems
  264. TRACE: Temporal Grounding Video LLM via Causal Event Modeling
  265. DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models
  266. Time Series Classification of Supraglacial Lakes Evolution over Greenland Ice Sheet
  267. Federated Neural Nonparametric Point Processes
  268. Identification and estimation for matrix time series CP-factor models
  269. Navigating Inflation in Ghana: How Can Machine Learning Enhance Economic Stability and Growth Strategies
  270. Vector-ICL: In-context Learning with Continuous Vector Representations
  271. CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning
  272. On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
  273. Understanding Gradient Boosting Classifier: Training, Prediction, and the Role of γj
  274. Stereotype or Personalization? User Identity Biases Chatbot Recommendations
  275. A Bayesian Model Selection Criterion for Selecting Pretraining Checkpoints
  276. The Breakdown of Gaussian Universality in Classification of High-dimensional Linear Factor Mixtures
  277. Accelerating the discovery of low-energy structure configurations: a computational approach that integrates first-principles calculations, Monte Carlo sampling, and Machine Learning
  278. Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series
  279. ReFIR: Grounding Large Restoration Models with Retrieval Augmentation
  280. Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learning
  281. SMART: A Flexible Approach to Regression using Spline-Based Multivariate Adaptive Regression Trees
  282. When Graph Neural Networks Meet Dynamic Mode Decomposition
  283. Training Stiff Neural Ordinary Differential Equations with Implicit Single-Step Methods
  284. TeaserGen: Generating Teasers for Long Documentaries
  285. Towards Robust Spacecraft Trajectory Optimization via Transformers
  286. Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?
  287. Swift Sampler: Efficient Learning of Sampler by 10 Parameters
  288. Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future
  289. ClaimBrush: A Novel Framework for Automated Patent Claim Refinement Based on Large Language Models
  290. TaeBench: Improving Quality of Toxic Adversarial Examples
  291. Improved deep learning of chaotic dynamical systems with multistep penalty losses