mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 7 Oct 2024

366 papers

  1. Temporal Relational Reasoning of Large Language Models for Detecting Stock Portfolio CrashesLLM reasoning → Reasoning for agents, planning and code
  2. Towards using Reinforcement Learning for Scaling and Data Replication in Cloud SystemsDeep reinforcement learning methods → RL for energy, networks and operations
  3. Fill In The Gaps: Model Calibration and Generalization with Synthetic DataSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  4. Superficial Safety Alignment HypothesisLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  5. Reasoning Paths Optimization: Learning to Reason and Explore From Diverse PathsLLM reasoning → Test-time compute and efficient thinking
  6. Mirror-Consistency: Harnessing Inconsistency in Majority VotingLLM reasoning → Test-time compute and efficient thinking
  7. Mechanistic?Mechanistic interpretability → Circuits and mechanistic analysis
  8. Learning-Based Shielding for Safe Autonomy under Unknown DynamicsDeep reinforcement learning methods → Safe and constrained RL
  9. Rational Metareasoning for Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  10. Narrative-of-Thought: Improving Temporal Reasoning of Large Language Models via Recounted NarrativesLLM reasoning → Knowledge- and tool-augmented reasoning
  11. DOPL: Direct Online Preference Learning for Restless Bandits with Preference FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  12. Generative Portrait Shadow RemovalDiffusion models → 3D, point cloud and scene generation
  13. Toward General Object-level Mapping from Sparse Views with 3D Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
  14. R-Bench: Are your Large Multimodal Model Robust to Real-world Corruptions?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  15. From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample EfficiencyLLM reasoning → Prompting and chain-of-thought reasoning
  16. SecAlign: Defending Against Prompt Injection with Preference OptimizationLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  17. A Deep Learning-Based Approach for Mangrove MonitoringState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  18. Better than Your Teacher: LLM Agents that learn from Privileged AI FeedbackLLM agents and tool use → General LLM agent frameworks and benchmarks
  19. Diffusion Imitation from ObservationDiffusion models → Diffusion and flow policies for robotics +1
  20. Designing a Classifier for Active Fire Detection from Multispectral Satellite Imagery Using Neural Architecture SearchDeep reinforcement learning methods → RL for robot navigation and UAV control
  21. Diffusion Model Predictive ControlDiffusion models → Diffusion and flow policies for robotics
  22. RespLLM: Unifying Audio and Text with Multimodal LLMs for Generalized Respiratory Health PredictionMultimodal LLMs / vision-language models → Medical vision-language models
  23. Falcon Mamba: The First Competitive Attention-free 7B Language ModelState-space sequence models (S4, Mamba) → Core SSM architectures for language
  24. AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  25. Proceedings of the First International Workshop on Next-Generation Language Models for Knowledge Representation and Reasoning (NeLaMKRR 2024)LLM reasoning → Reasoning benchmarks and evaluation
  26. CLIP's Visual Embedding Projector is a Few-shot CornucopiaMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  27. Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  28. TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer TokensMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  29. Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference OptimizationDiffusion models → Diffusion and flow policies for robotics +1
  30. Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  31. TuneVLSeg: Prompt Tuning Benchmark for Vision-Language Segmentation ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  32. DiffuseReg: Denoising Diffusion Model for Obtaining Deformation Fields in Unsupervised Deformable Image RegistrationDiffusion models → Medical imaging and segmentation
  33. GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language ModelsLLM reasoning → Mathematical reasoning
  34. ETGL-DDPG: A Deep Deterministic Policy Gradient Algorithm for Sparse Reward Continuous ControlDeep reinforcement learning methods → RL theory and sample complexity
  35. LADEV: A Language-Driven Testing and Evaluation Platform for Vision-Language-Action Models in Robotic ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  36. ReasoningRank: Teaching Student Models to Rank through Reasoning-Based Knowledge DistillationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  37. Presto! Distilling Steps and Layers for Accelerating Music GenerationDiffusion models → Audio, speech and music
  38. Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language ModelsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  39. VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding TasksMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  40. Editing Music with Melody and Text: Using ControlNet for Diffusion TransformerDiffusion models → Audio, speech and music
  41. Leveraging Multimodal Diffusion Models to Accelerate Imaging with Side InformationDiffusion models → Inverse problems and image restoration
  42. Scalable and Accurate Graph Reasoning with LLM-based Multi-AgentsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  43. HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model FinetuningDiffusion models → Diffusion and flow policies for robotics +2
  44. AlphaRouter: Quantum Circuit Routing with Reinforcement Learning and Tree SearchDeep reinforcement learning methods → Quantum reinforcement learning
  45. SparsePO: Controlling Preference Alignment of LLMs via Sparse Token MasksLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  46. IGroupSS-Mamba: Interval Group Spatial-Spectral Mamba for Hyperspectral Image ClassificationState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  47. Reinforcement Learning Control for Autonomous Hydraulic Material Handling Machines with Underactuated ToolsDeep reinforcement learning methods → RL for robot navigation and UAV control
  48. ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific DiscoveryLLM agents and tool use → Web, search, and research agents
  49. ZEBRA: Zero-Shot Example-Based Retrieval Augmentation for Commonsense Question AnsweringLLM reasoning → Reasoning benchmarks and evaluation
  50. ComDrive: Comfort-Oriented End-to-End Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics +1
  51. A test suite of prompt injection attacks for LLM-based machine translationLLM safety and security → Prompt injection and agent security
  52. Bi-Directional MS Lesion Filling and Synthesis Using Denoising Diffusion Implicit Model-based Lesion RepaintingDiffusion models → Medical imaging and segmentation
  53. Active Fine-Tuning of Multi-Task PoliciesOffline RL and imitation learning from data → Robot manipulation imitation learning
  54. Fast State Restoration in LLM Serving with HCacheRetrieval-augmented generation → Generation and context integration +1
  55. Efficient Model-Based Reinforcement Learning Through Optimistic Thompson SamplingDeep reinforcement learning methods → RL theory and sample complexity
  56. Training Interactive Agent in Large FPS Game Map with Rule-enhanced Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  57. Low-Rank Continual Personalization of Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  58. Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  59. Mastering Chinese Chess AI (Xiangqi) Without SearchDeep reinforcement learning methods → RL for games and combinatorial optimization
  60. Real-time cardiac cine MRI -- A comparison of a diffusion probabilistic model with alternative state-of-the-art image reconstruction techniques for undersampled spiral acquisitionsDiffusion models → Medical imaging and segmentation
  61. Strong Model CollapseSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  62. As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback LossLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  63. MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  64. FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  65. Data-driven Diffusion Models for Enhancing Safety in Autonomous Vehicle Traffic SimulationsDiffusion models → Diffusion and flow policies for robotics
  66. PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QARetrieval-augmented generation → RAG pipeline design and evaluation
  67. Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention CausalityMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  68. MM-R3: On (In-)Consistency of Vision-Language Models (VLMs)Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  69. Stochastic Runge-Kutta Methods: Provable Acceleration of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  70. Driving with Regulation: Trustworthy and Interpretable Decision-Making for Autonomous Driving with Retrieval-Augmented ReasoningLLM reasoning → Chain-of-thought reasoning for driving +2
  71. ImProver: Agent-Based Automated Proof OptimizationLLM agents and tool use → Educational agents and math problem solving
  72. LLaVA Needs More Knowledge: Retrieval Augmented Natural Language Generation with Knowledge Graph for Explaining Thoracic PathologiesRetrieval-augmented generation → Medical and biomedical RAG
  73. Diffusion Models in 3D Vision: A SurveyDiffusion models → 3D, point cloud and scene generation
  74. TLDR: Token-Level Detective Reward Model for Large Vision Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  75. ACDC: Autoregressive Coherent Multimodal Generation using Diffusion CorrectionDiffusion models → Image generation, text-to-image and editing
  76. Domains as Objectives: Domain-Uncertainty-Aware Policy Optimization through Explicit Multi-Domain Convex Coverage Set LearningDeep reinforcement learning methods → Safe and constrained RL
  77. Learning How Hard to Think: Input-Adaptive Allocation of LM ComputationLLM reasoning → Test-time compute and efficient thinking
  78. MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMsLLM reasoning → Mathematical reasoning
  79. On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data PoisoningLLM safety and security → Backdoor and data poisoning attacks
  80. CAR: Controllable Autoregressive Modeling for Visual GenerationDiffusion models → Image generation, text-to-image and editing
  81. KGARevion: An AI Agent for Knowledge-Intensive Biomedical QALLM agents and tool use → Medical and scientific domain agents
  82. ActiView: Evaluating Active Perception Ability for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  83. Wireless-Friendly Window Position Optimization for RIS-Aided Outdoor-to-Indoor Networks based on Multi-Modal Large Language Model
  84. Tourism destination events classifier based on artificial intelligence techniques
  85. Data Publishing in Mechanics and Dynamics: Challenges, Guidelines, and Examples from Engineering Design
  86. TextureMeDefect: LLM-based Defect Texture Generation for Railway Components on Mobile Devices
  87. Behavior Matters: An Alternative Perspective on Promoting Responsible Data Science
  88. Military Applications of Machine Learning: A Bibliometric Perspective
  89. Rules, Cases, and Reasoning: Positivist Legal Theory as a Framework for Pluralistic AI Alignment
  90. MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworks
  91. FairFML: Fair Federated Machine Learning with a Case Study on Reducing Gender Disparities in Cardiac Arrest Outcome Prediction
  92. SPikE-SSM: A Sparse, Precise, and Efficient Spiking State Space Model for Long Sequences Learning
  93. Zero-Shot Vision-and-Language Navigation with Collision Mitigation in Continuous Environment
  94. Federated brain tumor segmentation: an extensive benchmark
  95. Radio Map Prediction from Aerial Images and Application to Coverage Optimization
  96. An Effective Theory of Bias Amplification
  97. EmoGene: Audio-Driven Emotional 3D Talking-Head Generation
  98. Masked Autoencoder with Swin Transformer Network for Mitigating Electrode Shift in HD-EMG-based Gesture Recognition
  99. In-the-loop Hyper-Parameter Optimization for LLM-Based Automated Design of Heuristics
  100. Spatio-Temporal 3D Point Clouds from WiFi-CSI Data via Transformer Networks
All 366
  1. Computational design of target-specific linear peptide binders with TransformerBeta
  2. Intelligent Computing Social Modeling and Methodological Innovations in Political Science in the Era of Large Language Models
  3. Transformers are Efficient Compilers, Provably
  4. Optimizing Parking Space Classification: Distilling Ensembles into Lightweight Classifiers
  5. Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges
  6. Shifting the Human-AI Relationship: Toward a Dynamic Relational Learning-Partner Model
  7. ChatVis: Automating Scientific Visualization with a Large Language Model
  8. Investigating Role of Big Five Personality Traits in Audio-Visual Rapport Estimation
  9. Exploring the Personality Traits of LLMs through Latent Features Steering
  10. Translation Canvas: An Explainable Interface to Pinpoint and Analyze Translation Systems
  11. A Recipe For Building a Compliant Real Estate Chatbot
  12. FAME: Towards Factual Multi-Task Model Editing
  13. AI in Archival Science -- A Systematic Review
  14. A Recurrent Neural Network Approach to the Answering Machine Detection Problem
  15. Locally Measuring Cross-lingual Lexical Alignment: A Domain and Word Level Perspective
  16. Chain and Causal Attention for Efficient Entity Tracking
  17. Unsupervised Representation Learning from Sparse Transformation Analysis
  18. Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification
  19. Source-Free Domain Adaptive Object Detection with Semantics Compensation
  20. On Instruction-Finetuning Neural Machine Translation Models
  21. Optimal Adaptive Experimental Design for Estimating Treatment Effect
  22. Scalable Inference for Bayesian Multinomial Logistic-Normal Dynamic Linear Models
  23. Aiding Global Convergence in Federated Learning via Local Perturbation and Mutual Similarity Information
  24. Game of Coding: Sybil Resistant Decentralized Machine Learning with Minimal Trust Assumption
  25. Online Dynamic Pricing for Electric Vehicle Charging Stations with Reservations
  26. Accelerating Flood Warnings by 10 Hours: The Power of River Network Topology in AI-enhanced Flood Forecasting
  27. Optimizing Tensor Computation Graphs with Equality Saturation and Monte Carlo Tree Search
  28. Information Design with Unknown Prior
  29. VisDiff: SDF-Guided Polygon Generation for Visibility Reconstruction and Recognition
  30. Deep Learning Methods for S Shaped Utility Maximisation with a Random Reference Point
  31. Scalar Field Prediction on Meshes Using Interpolated Multi-Resolution Convolutional Neural Networks
  32. Structural Constraints for Physics-augmented Learning
  33. Privacy Vulnerabilities in Marginals-based Synthetic Data
  34. Residual Kolmogorov-Arnold Network for Enhanced Deep Learning
  35. Unitary convolutions for learning on graphs and groups
  36. EgoQR: Efficient QR Code Reading in Egocentric Settings
  37. Intuitions of Compromise: Utilitarianism vs. Contractualism
  38. Self-rationalization improves LLM as a fine-grained judge
  39. An Information-Theoretic Approach to Understanding Transformers' In-Context Learning of Variable-Order Markov Chains
  40. Pre-Ictal Seizure Prediction Using Personalized Deep Learning
  41. Neural Networks Decoded: Targeted and Robust Analysis of Neural Network Decisions via Causal Explanations and Reasoning
  42. fLSA: Learning Semantic Structures in Document Collections Using Foundation Models
  43. When Explanations Compete: Policy-Aware Selection Under Uncertainty
  44. Neural machine translation system for Lezgian, Russian and Azerbaijani languages
  45. Image Watermarks are Removable Using Controllable Regeneration from Clean Noise
  46. PH-Dropout: Practical Epistemic Uncertainty Quantification for View Synthesis
  47. Herd Mentality in Augmentation -- Not a Good Idea! A Robust Multi-stage Approach towards Deepfake Detection
  48. On the Expressive Power of Tree-Structured Probabilistic Circuits
  49. Progressive distillation induces an implicit curriculum
  50. LevAttention: Time, Space, and Streaming Efficient Algorithm for Heavy Attentions
  51. Testing Credibility of Public and Private Surveys through the Lens of Regression
  52. Dynamic HumTrans: Humming Transcription Using CNNs and Dynamic Programming
  53. Meta-Dynamical State Space Models for Integrative Neural Data Analysis
  54. Interconnected Kingdoms: Comparing 'A Song of Ice and Fire' Adaptations Across Media Using Complex Networks
  55. WearableMil: An End-to-End Framework for Military Activity Recognition and Performance Monitoring
  56. AI-Driven Early Mental Health Screening: Analyzing Selfies of Pregnant Women
  57. Task Diversity Shortens the ICL Plateau
  58. Stability of sorting based embeddings
  59. Data-Driven Discovery of Conservation Laws from Trajectories via Neural Deflation
  60. Online scalable Gaussian processes with conformal prediction for guaranteed coverage
  61. Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox
  62. Can LLMs Understand Time Series Anomalies?
  63. DAAL: Density-Aware Adaptive Line Margin Loss for Multi-Modal Deep Metric Learning
  64. ESPACE: Dimensionality Reduction of Activations for Model Compression
  65. Discovering distinctive elements of biomedical datasets for high-performance exploration
  66. Continuous Ensemble Weather Forecasting with Diffusion models
  67. A Functional Extension of Semi-Structured Networks
  68. Incorporating Talker Identity Aids With Improving Speech Recognition in Adversarial Environments
  69. Joint Distribution-Informed Shapley Values for Sparse Counterfactual Explanations
  70. Haste Makes Waste: A Simple Approach for Scaling Graph Neural Networks
  71. Implicitly Learned Neural Phase Functions for Basis-Free Point Spread Function Engineering
  72. Enhanced Super-Resolution Training via Mimicked Alignment for Real-World Scenes
  73. Improving Predictor Reliability with Selective Recalibration
  74. Synthesizing Interpretable Control Policies through Large Language Model Guided Search
  75. Deep learning-based Visual Measurement Extraction within an Adaptive Digital Twin Framework from Limited Data Using Transfer Learning
  76. Post-hoc Study of Climate Microtargeting on Social Media Ads with LLMs: Thematic Insights and Fairness Evaluation
  77. Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
  78. LLMs Are In-Context Bandit Reinforcement Learners
  79. Interactive Event Sifting using Bayesian Graph Neural Networks
  80. A Predictive and Optimization Approach for Enhanced Urban Mobility Using Spatiotemporal Data
  81. Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild
  82. BSG4Bot: Efficient Bot Detection based on Biased Heterogeneous Subgraphs
  83. Over-the-Air Federated Learning in Cell-Free MIMO with Long-term Power Constraint
  84. Towards a Categorical Foundation of Deep Learning: A Survey
  85. Recent Advances of Multimodal Continual Learning: A Comprehensive Survey
  86. Towards the generation of hierarchical attack models from cybersecurity vulnerabilities using language models
  87. GRU-D Characterizes Age-Specific Temporal Missingness in MIMIC-IV
  88. SoK: Towards Security and Safety of Edge AI
  89. Bridging Local and Global Knowledge via Transformer in Board Games
  90. Trained Models Tell Us How to Make Them Robust to Spurious Correlation without Group Annotation
  91. EgoOops: A Dataset for Mistake Action Detection from Egocentric Videos referring to Procedural Texts
  92. Multi-Stage Graph Learning for fMRI Analysis to Diagnose Neuro-Developmental Disorders
  93. NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping
  94. Generating CAD Code with Vision-Language Models for 3D Designs
  95. Grounding Partially-Defined Events in Multimodal Data
  96. Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers
  97. PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization
  98. Bias-Aware Conformal Prediction for Metric-Based Imaging Pipelines
  99. TurtleBench: Evaluating Top Language Models via Real-World Yes/No Puzzles
  100. DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control
  101. GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting
  102. Differential Transformer
  103. GLEE: A Unified Framework and Benchmark for Language-based Economic Environments
  104. Causal Micro-Narratives
  105. LoTLIP: Improving Language-Image Pre-training for Long Text Understanding
  106. SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe
  107. CasiMedicos-Arg: A Medical Question Answering Dataset Annotated with Explanatory Argumentative Structures
  108. SimO Loss: Anchor-Free Contrastive Loss for Fine-Grained Supervised Contrastive Learning
  109. SymmetryLens: Unsupervised Symmetry Learning via Locality and Density Preservation
  110. The Dawn of Video Generation: Preliminary Explorations with SORA-like Models
  111. Cookbook: A framework for improving LLM generative abilities via programmatic data generating templates
  112. Precise Model Benchmarking with Only a Few Observations
  113. Density estimation with LLMs: a geometric investigation of in-context learning trajectories
  114. Organizing Unstructured Image Collections using Natural Language
  115. The Informed Elastic Net for Fast Grouped Variable Selection and FDR Control in Genomics Research
  116. Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality
  117. Studying and Mitigating Biases in Sign Language Understanding Models
  118. Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality
  119. RevisEval: Improving LLM-as-a-Judge via Response-Adapted References
  120. Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective
  121. Matrix-weighted networks for modeling multidimensional dynamics
  122. Beyond Correlation: Interpretable Evaluation of Machine Translation Metrics
  123. MARs: Multi-view Attention Regularizations for Patch-based Feature Recognition of Space Terrain
  124. Mitigating the Risk of Health Inequity Exacerbated by Large Language Models
  125. Are causal effect estimations enough for optimal recommendations under multitreatment scenarios?
  126. Efficient Inference for Large Language Model-based Generative Recommendation
  127. An Efficient On-Policy Deep Learning Framework for Stochastic Optimal Control
  128. MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense
  129. PAMLR: A Passive-Active Multi-Armed Bandit-Based Solution for LoRa Channel Allocation
  130. CTC-GMM: CTC guided modality matching for fast and accurate streaming speech translation
  131. Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis
  132. LOTOS: Layer-wise Orthogonalization for Training Robust Ensembles
  133. A Digital Twin Framework for Liquid-cooled Supercomputers as Demonstrated at Exascale
  134. Last Iterate Convergence in Monotone Mean Field Games
  135. Agnostic Smoothed Online Learning without Knowledge of the Base Measure
  136. Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
  137. Synthetic Generation of Dermatoscopic Images with GAN and Closed-Form Factorization
  138. LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splatting
  139. Hyper-Representations: Learning from Populations of Neural Networks
  140. Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson-Romberg Extrapolation
  141. AI-Enhanced Ethical Hacking: A Linux-Focused Experiment
  142. MetaDD: Boosting Dataset Distillation with Neural Network Architecture-Invariant Generalization
  143. CR-CTC: Consistency regularization on CTC for improved speech recognition
  144. Investigating large language models for their competence in extracting grammatically sound sentences from transcribed noisy utterances
  145. DreamSat: Towards a General 3D Model for Novel View Synthesis of Space Objects
  146. Human-in-the-loop Reasoning For Traffic Sign Detection: Collaborative Approach Yolo With Video-llava
  147. On the Structure of Game Provenance and its Applications
  148. HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation
  149. Explanation sensitivity to the randomness of large language models: the case of journalistic text classification
  150. Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data
  151. TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  152. xLSTM-FER: Enhancing Student Expression Recognition with Extended Vision Long Short-Term Memory Network
  153. Function Gradient Approximation with Random Shallow ReLU Networks with Control Applications
  154. Control-oriented Clustering of Visual Latent Representation
  155. Improving Object Detection via Local-global Contrastive Learning
  156. SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification
  157. Transition of α-mixing in Random Iterations with Applications in Queuing Theory
  158. Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes
  159. FreSh: Frequency Shifting for Accelerated Neural Representation Learning
  160. Named Clinical Entity Recognition Benchmark
  161. Can LLMs plan paths with extra hints from solvers?
  162. PhotoReg: Photometrically Registering 3D Gaussian Splatting Models
  163. Systematic Literature Review of Vision-Based Approaches to Outdoor Livestock Monitoring with Lessons from Wildlife Studies
  164. ℓ1-norm rank-one symmetric matrix factorization has no spurious second-order stationary points
  165. On subdifferential chain rule of matrix factorization and beyond
  166. DEPT: Decoupled Embeddings for Pre-training Language Models
  167. FRIDA: Free-Rider Detection using Privacy Attacks
  168. RelUNet: Relative Channel Fusion U-Net for Multichannel Speech Enhancement
  169. On the Biased Assessment of Expert Finding Systems
  170. T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data
  171. SkillMatch: Evaluating Self-supervised Learning of Skill Relatedness
  172. Assumption-Lean Post-Integrated Inference with Surrogate Control Outcomes
  173. MC-QDSNN: Quantized Deep evolutionary SNN with Multi-Dendritic Compartment Neurons for Stress Detection using Physiological Signals
  174. Stage-Wise and Prior-Aware Neural Speech Phase Prediction
  175. Conditional Variational Autoencoders for Probabilistic Pose Regression
  176. RoWeeder: Unsupervised Weed Mapping through Crop-Row Detection
  177. Safe Learning-Based Optimization of Model Predictive Control: Application to Battery Fast-Charging
  178. On the Rigour of Scientific Writing: Criteria, Analysis, and Insights
  179. Comparison of marker-less 2D image-based methods for infant pose estimation
  180. 6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering
  181. L-C4: Language-Based Video Colorization for Creative and Consistent Color
  182. Collaboration! Towards Robust Neural Methods for Routing Problems
  183. Revealing Directions for Text-guided 3D Face Editing
  184. Activation Scaling for Steering and Interpreting Language Models
  185. On Efficient Variants of Segment Anything Model: A Survey
  186. Collapse-Proof Non-Contrastive Self-Supervised Learning
  187. Leverage Knowledge Graph and Large Language Model for Law Article Recommendation: A Case Study of Chinese Criminal Law
  188. Real-time Ship Recognition and Georeferencing for the Improvement of Maritime Situational Awareness
  189. TOAST: Transformer Optimization using Adaptive and Simple Transformations
  190. Next state prediction gives rise to entangled, yet compositional representations of objects
  191. PRFusion: Toward Effective and Robust Multi-Modal Place Recognition with Image and Point Cloud Fusion
  192. OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction
  193. The Role of Governments in Increasing Interconnected Post-Deployment Monitoring of AI
  194. Goal-Conditioned Terminal Value Estimation for Real-time and Multi-task Model Predictive Control
  195. Intent Classification for Bank Chatbots through LLM Fine-Tuning
  196. Random-projection ensemble dimension reduction
  197. Defense-as-a-Service: Black-box Shielding against Backdoored Graph Models
  198. Decomposition Polyhedra of Piecewise Linear Functions
  199. Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation
  200. D-PoSE: Depth as an Intermediate Representation for 3D Human Pose and Shape Estimation
  201. Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse
  202. Improving the Weighting Strategy in KernelSHAP
  203. Improved detection of discarded fish species through BoxAL active learning
  204. Leveraging Grammar Induction for Language Understanding and Generation
  205. TeX-NeRF: Neural Radiance Fields from Pseudo-TeX Vision
  206. On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
  207. Art Forgery Detection using Kolmogorov Arnold and Convolutional Neural Networks
  208. Unsupervised Skill Discovery for Robotic Manipulation through Automatic Task Generation
  209. TimeCNN: Refining Cross-Variable Interaction on Time Point for Time Series Forecasting
  210. Causal Context Adjustment Loss for Learned Image Compression
  211. PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing
  212. A Simple Image Segmentation Framework via In-Context Examples
  213. Rationale-Aware Answer Verification by Pairwise Self-Evaluation
  214. Multimodal Fusion Strategies for Mapping Biophysical Landscape Features
  215. Taming Gradient Oversmoothing and Expansion in Graph Neural Networks
  216. CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models
  217. Physics-Informed Graph Neural Networks for Robust AC-Optimal Power Flow
  218. Resource-Efficient Multiview Perception: Integrating Semantic Masking with Masked Autoencoders
  219. A Review of BioTree Construction in the Context of Information Fusion: Priors, Methods, Applications and Trends
  220. Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data
  221. Learning Efficient and Effective Trajectories for Differential Equation-based Image Restoration
  222. LPZero: Language Model Zero-cost Proxy Search from Zero
  223. Timer-XL: Long-Context Transformers for Unified Time Series Forecasting
  224. Building Damage Assessment in Conflict Zones: A Deep Learning Approach Using Geospatial Sub-Meter Resolution Data
  225. Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering
  226. Transforming Color: A Novel Image Colorization Method
  227. DAPE V2: Process Attention Score as Feature Map for Length Extrapolation
  228. Representing the Under-Represented: Cultural and Core Capability Benchmarks for Developing Thai Large Language Models
  229. Analysis of Hybrid Compositions in Animation Film with Weakly Supervised Learning
  230. Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge
  231. Fast Training of Sinusoidal Neural Fields via Scaling Initialization
  232. OmniBuds: A Sensory Earable Platform for Advanced Bio-Sensing and On-Device Machine Learning
  233. Granular Ball Twin Support Vector Machine
  234. From Transparency to Accountability and Back: A Discussion of Access and Evidence in AI Auditing
  235. Molecular topological deep learning for polymer property prediction
  236. Double Oracle Neural Architecture Search for Game Theoretic Deep Learning Models
  237. WTCL-Dehaze: Rethinking Real-world Image Dehazing via Wavelet Transform and Contrastive Learning
  238. Item Cluster-aware Prompt Learning for Session-based Recommendation
  239. Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answering
  240. Intriguing Properties of Large Language and Vision Models
  241. Smart energy management: process structure-based hybrid neural networks for optimal scheduling and economic predictive control in integrated systems
  242. Evaluating the Generalization Ability of Spatiotemporal Model in Urban Scenario
  243. TableRAG: Million-Token Table Understanding with Language Models
  244. Video Prediction Transformers without Recurrence or Convolution
  245. Efficient transformer with reinforced position embedding for language models
  246. Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models
  247. ProtoNAM: Prototypical Neural Additive Models for Interpretable Deep Tabular Learning
  248. A Strategy for Label Alignment in Deep Neural Networks
  249. Only-IF:Revealing the Decisive Effect of Instruction Diversity on Generalization
  250. H-SIREN: Improving implicit neural representations with hyperbolic periodic functions
  251. Selection of LLM Fine-Tuning Data based on Orthogonal Rules
  252. Tight Stability, Convergence, and Robustness Bounds for Predictive Coding Networks
  253. Modeling and Estimation of Vocal Tract and Glottal Source Parameters Using ARMAX-LF Model
  254. Neural Fourier Modelling: A Highly Compact Approach to Time-Series Analysis
  255. The LLM Effect: Are Humans Truly Using LLMs, or Are They Being Influenced By Them Instead?
  256. A Clifford Algebraic Approach to E(n)-Equivariant High-order Graph Neural Networks
  257. Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning
  258. SegINR: Segment-wise Implicit Neural Representation for Sequence Alignment in Neural Text-to-Speech
  259. Low-Rank Continual Pyramid Vision Transformer: Incrementally Segment Whole-Body Organs in CT with Light-Weighted Adaptation
  260. Combining Structural and Unstructured Data: A Topic-based Finite Mixture Model for Insurance Claim Prediction
  261. Towards Measuring Goal-Directedness in AI Systems
  262. Next Best Sense: Guiding Vision and Touch with FisherRF for 3D Gaussian Splatting
  263. The role of interface boundary conditions and sampling strategies for Schwarz-based coupling of projection-based reduced order models
  264. Debate, Deliberate, Decide (D3): A Cost-Aware Adversarial Framework for Reliable and Interpretable LLM Evaluation
  265. Federated Learning Nodes Can Reconstruct Peers' Image Data
  266. Contrastive Learning to Improve Retrieval for Real-world Fact Checking