mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 3 Oct 2024

417 papers

  1. Joint Channel Selection using FedDRL in V2XDeep reinforcement learning methods → RL for energy, networks and operations
  2. Rethinking VLMs and LLMs for Image ClassificationLLM reasoning → Multimodal reasoning +1
  3. Leveraging Event Streams with Deep Reinforcement Learning for End-to-End UAV TrackingDeep reinforcement learning methods → RL for robot navigation and UAV control
  4. Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  5. A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future DirectionsRetrieval-augmented generation → RAG pipeline design and evaluation
  6. AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMsLLM safety and security → Jailbreaking
  7. CaLMFlow: Volterra Flow Matching using Causal Language ModelsDiffusion models → Flow matching, time series and science
  8. Reward-RAG: Enhancing RAG with Reward Driven SupervisionRetrieval-augmented generation → RAG pipeline design and evaluation +1
  9. Instance-Level Difficulty: A Missing Perspective in Machine UnlearningLLM safety and security → Machine unlearning
  10. Leveraging Model Guidance to Extract Training Data from Personalized Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  11. CPFD: Confidence-aware Privileged Feature Distillation for Short Video ClassificationKnowledge distillation → General knowledge distillation methods
  12. MLP-KAN: Unifying Deep Representation and Function LearningMixture-of-experts → MoE theory and gating functions
  13. Flow Matching with Gaussian Process Priors for Probabilistic Time Series ForecastingDiffusion models → Flow matching, time series and science
  14. FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language ModelEfficient LLM inference and serving → Audio and omni-modal token compression
  15. Finite-Sample Analysis of the Monte Carlo Exploring Starts Algorithm for Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  16. Learning to Better Search with Language Models via Guided Reinforced Self-TrainingSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  17. Learning Optimal Control and Dynamical Structure of Global Trajectory Search Problems with Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  18. AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoMLLLM agents and tool use → General LLM agent frameworks and benchmarks
  19. Unlocking Structured Thinking in Language Models with Cognitive PromptingLLM reasoning → Prompting and chain-of-thought reasoning
  20. SymmetricDiffusers: Learning Discrete Diffusion on Finite Symmetric GroupsDiffusion models → Diffusion foundations and sampling
  21. On Expert Estimation in Hierarchical Mixture of Experts: Beyond Softmax Gating FunctionsMixture-of-experts → MoE theory and gating functions
  22. Intrinsic Evaluation of RAG Systems for Deep-Logic QuestionsRetrieval-augmented generation → RAG pipeline design and evaluation
  23. LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service AttacksLLM safety and security → Jailbreaking
  24. Streamlining Conformal Information Retrieval via Score RefinementRetrieval-augmented generation → RAG robustness and adaptive retrieval
  25. NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the WildLLM agents and tool use → Web, search, and research agents
  26. Deep Reinforcement Learning for Reach-Avoid-Stay ProblemsDeep reinforcement learning methods → Safe and constrained RL
  27. The Role of Deductive and Inductive Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  28. Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive ApproachLLM safety and security → Watermarking generated content and models
  29. LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical ReasoningLLM reasoning → Mathematical reasoning +1
  30. Position: LLM Unlearning Benchmarks are Weak Measures of ProgressLLM safety and security → Machine unlearning
  31. Reconstructing Galaxy Cluster Mass Maps using Score-based Generative ModelingDiffusion models → Inverse problems and image restoration
  32. Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short VideosLLM reasoning → Multimodal reasoning +1
  33. Interpreting and Editing Vision-Language Representations to Mitigate HallucinationsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  34. FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  35. Erasing Conceptual Knowledge from Language ModelsLLM safety and security → Machine unlearning
  36. ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AIDeep reinforcement learning methods → RL for robot locomotion and manipulation
  37. Contrastive Localized Language-Image Pre-TrainingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  38. MA-RLHF: Reinforcement Learning from Human Feedback with Macro ActionsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  39. Grounding Large Language Models In Embodied Environment With Imperfect World ModelsWorld models → World models for language agents
  40. DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse ScenesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  41. Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-GenerationLLM reasoning → Test-time compute and efficient thinking +1
  42. Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor FactorizationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  43. UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  44. LLaVA-Video: Video Instruction Tuning With Synthetic DataMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  45. LLaVA-Critic: Learning to Evaluate Multimodal ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  46. SteerDiff: Steering towards Safe Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  47. ControlAR: Controllable Image Generation with Autoregressive ModelsDiffusion models → Image generation, text-to-image and editing
  48. Discovering Spoofing Attempts on Language Model WatermarksLLM safety and security → Watermarking generated content and models
  49. HiddenGuard: Fine-Grained Safe Generation with Specialized Representation RouterLLM safety and security → Safety alignment, refusal and guardrails
  50. Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  51. GUD: Generation with Unified DiffusionDiffusion models → Diffusion foundations and sampling
  52. Grounded Answers for Multi-agent Decision-making Problem through Generative World ModelWorld models → Latent dynamics models and model-based RL
  53. Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  54. Attention in Large Language Models Yields Efficient Zero-Shot Re-RankersRetrieval-augmented generation → Generation and context integration
  55. RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual DiffusionDiffusion models → Diffusion for compression and wireless
  56. ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  57. NL-Eye: Abductive NLI for ImagesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  58. Policy Gradients for Cumulative Prospect Theory in Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  59. Agents' Room: Narrative Generation through Multi-step CollaborationLLM agents and tool use → Multimodal and embodied agents
  60. Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM InteractionsLLM agents and tool use → Social simulation and multi-agent debate
  61. ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent CollaborationLLM agents and tool use → Medical and scientific domain agents
  62. Local Flow Matching Generative ModelsDiffusion models → Flow matching, time series and science
  63. Diffusion Models are Evolutionary AlgorithmsDiffusion models → Diffusion foundations and sampling
  64. Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent ExplorationLLM agents and tool use → Reinforcement learning for LLM agents
  65. Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent CollaborationLLM reasoning → Reasoning for agents, planning and code +1
  66. Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  67. Dual Active Learning for Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  68. Lightweight Diffusion Models for Resource-Constrained Semantic CommunicationDiffusion models → Diffusion for compression and wireless
  69. Cross-Embodiment Dexterous Grasping with Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  70. Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous GraspingMixture-of-experts → MoE in reinforcement learning and robotics
  71. SIDE: Surrogate Conditional Data Extraction from Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  72. Strong Preferences Affect the Robustness of Preference Models and Value AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  73. Optimizing Adaptive Attacks against Watermarks for Language ModelsLLM safety and security → Watermarking generated content and models
  74. IoT-LLM: a framework for enhancing Large Language Model reasoning from real-world sensor dataLLM reasoning → Reasoning benchmarks and evaluation
  75. PnP-Flow: Plug-and-Play Image Restoration with Flow MatchingDiffusion models → Inverse problems and image restoration
  76. Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  77. ELLMA-T: an Embodied LLM-agent for Supporting English Language Learning in Social VRLLM agents and tool use → Social simulation and multi-agent debate
  78. Unleashing the Potential of the Diffusion Model in Few-shot Semantic SegmentationDiffusion models → Medical imaging and segmentation
  79. SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference AccelerationEfficient LLM inference and serving → KV cache optimization
  80. A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and BeyondState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  81. How Much Can RAG Help the Reasoning of LLM?LLM reasoning → Knowledge- and tool-augmented reasoning +1
  82. Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time AnalysisDiffusion models → Diffusion foundations and sampling
  83. Post-edits Are Preferences TooLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  84. Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language ModelsLLM safety and security → Jailbreaking
  85. Optimal Strong Regret and Violation in Constrained MDPs via Policy OptimizationDeep reinforcement learning methods → RL theory and sample complexity
  86. Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit FeedbackDeep reinforcement learning methods → RL theory and sample complexity
  87. Unsupervised Meta-Learning via Dynamic Head and Heterogeneous Task Construction for Few-Shot ClassificationDeep reinforcement learning methods → Deep RL algorithms and representations
  88. From Imitation to Exploration: End-to-end Autonomous Driving based on World ModelWorld models → World models for autonomous driving +2
  89. SCA: Improve Semantic Consistent in Unrestricted Adversarial Attacks via DDPM InversionDiffusion models → Robustness, privacy and adversarial aspects
  90. C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto FrontDeep reinforcement learning methods → RL for games and combinatorial optimization
  91. SEAL: SEmantic-Augmented Imitation Learning via Language ModelOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  92. CodePMP: Scalable Preference Model Pretraining for Large Language Model ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  93. Doubly Optimal Policy Evaluation for Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  94. Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking AttacksLLM safety and security → Jailbreaking
  95. Stochastic Sampling from Deterministic Flow ModelsDiffusion models → Diffusion foundations and sampling
  96. Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  97. GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  98. Beyond Bradley-Terry Models: A General Preference Model for Language Model AlignmentLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  99. Guiding Long-Horizon Task and Motion Planning with Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  100. Agent-Oriented Planning in Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
All 417
  1. Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy EvaluationDeep reinforcement learning methods → RL theory and sample complexity
  2. Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series ForecastingDiffusion models → Flow matching, time series and science
  3. Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization AnalysisLLM reasoning → Prompting and chain-of-thought reasoning
  4. Adversarial Decoding: Generating Readable Documents for Adversarial ObjectivesLLM safety and security → Membership inference attacks
  5. Mitigating Memorization In Language ModelsLLM safety and security → Machine unlearning
  6. From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual ModalitiesMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  7. SoundMorpher: Perceptually-Uniform Sound Morphing with Diffusion ModelDiffusion models → Audio, speech and music
  8. MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound GenerationDiffusion models → Audio, speech and music
  9. SC-CDM: Enhancing Quality of Image Semantic Communication with a Compact Diffusion ModelDiffusion models → Diffusion for compression and wireless
  10. Searching for Efficient Linear Layers over a Continuous Space of Structured MatricesMixture-of-experts → MoE theory and gating functions
  11. Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-Training of Deep NetworksKnowledge distillation → General knowledge distillation methods
  12. Mamba Neural Operator: Who Wins? Transformers vs. State-Space Models for PDEsState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  13. ReGenesis: LLMs can Grow into Reasoning Generalists via Self-ImprovementLLM reasoning → Test-time compute and efficient thinking +1
  14. Uncovering Regional Defaults from Photorealistic Forests in Text-to-Image Generation with DALL-E 2
  15. BrainTransformers: SNN-LLM
  16. Achieving Generalization in Orchestrating GNSS Interference Monitoring Stations Through Pseudo-Labeling
  17. RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph
  18. Brain-Aware Readout Layers in GNNs: Advancing Alzheimer's early Detection and Neuroimaging
  19. Mixed-curvature decision trees and random forests
  20. EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing
  21. A Dutch Financial Large Language Model
  22. Online GPU Energy Optimization with Switching-Aware Bandits
  23. Repurposing Foundation Model for Generalizable Medical Time Series Classification
  24. People are poorly equipped to detect AI-powered voice clones
  25. Accelerating Deep Learning with Fixed Time Budget
  26. Reconstructing Human Mobility Pattern: A Semi-Supervised Approach for Cross-Dataset Transfer Learning
  27. CalliffusionV2: Personalized Natural Calligraphy Generation with Flexible Multi-modal Control
  28. AI-rays: Exploring Bias in the Gaze of AI Through a Multimodal Interactive Installation
  29. Improving Neural Optimal Transport via Displacement Interpolation
  30. DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation
  31. Towards the Pedagogical Steering of Large Language Models for Tutoring: A Case Study with Modeling Productive Failure
  32. EvoMesh: Adaptive Physical Simulation with Hierarchical Graph Evolutions
  33. SGW-based Multi-Task Learning in Vision Tasks
  34. Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling
  35. Parameter Estimation of Long Memory Stochastic Processes with Deep Neural Networks
  36. Beyond correlation: The Impact of Human Uncertainty in Measuring the Effectiveness of Automatic Evaluation and LLM-as-a-Judge
  37. Human-Based Risk Model for Improved Driver Support in Interactive Driving Scenarios
  38. Vehicle Suspension Recommendation System: Multi-Fidelity Neural Network-based Mechanism Design Optimization
  39. FedPeWS: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning
  40. Minmax Trend Filtering: Generalizations of Total Variation Denoising via a Local Minmax/Maxmin Formula
  41. Geometry is All You Need: A Unified Taxonomy of Matrix and Tensor Factorization for Compression of Generative Language Models
  42. Disentangling Textual and Acoustic Features of Neural Speech Representations
  43. SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments
  44. Designing Human-AI Collaboration to Support Learning in Counterspeech Writing
  45. Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness
  46. Estimating Privacy Leakage of Augmented Contextual Knowledge in Language Models
  47. PixelShuffler: A Simple Image Translation Through Pixel Rearrangement
  48. On Logical Extrapolation for Mazes with Recurrent and Implicit Networks
  49. Is Your Paper Being Reviewed by an LLM? Investigating AI Text Detectability in Peer Review
  50. Transforming Teachers' Roles and Agencies in the Era of Generative AI: Perceptions, Acceptance, Knowledge, and Practices
  51. Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise
  52. Learning a Fast Mixing Exogenous Block MDP using a Single Trajectory
  53. Towards Understanding the Universality of Transformers for Next-Token Prediction
  54. MMP: Towards Robust Multi-Modal Learning with Masked Modality Projection
  55. Formation of Representations in Neural Networks
  56. Can Transformers Learn n-gram Language Models?
  57. Towards Generalized Certified Robustness with Multi-Norm Training
  58. Q-SCALE: Quantum computing-based Sensor Calibration for Advanced Learning and Efficiency
  59. Task-agnostic Lifelong Robot Learning with Retrieval-based Weighted Local Adaptation
  60. Fully Automated CTC Detection, Segmentation and Classification for Multi-Channel IF Imaging
  61. Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient
  62. GABIC: Graph-based Attention Block for Image Compression
  63. DecTrain: Deciding When to Train a Monocular Depth DNN Online
  64. Optimization, Isoperimetric Inequalities, and Sampling via Lyapunov Potentials
  65. An explainable approach to detect case law on housing and eviction issues within the HUDOC database
  66. Harm Ratio: A Novel and Versatile Fairness Criterion
  67. F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI
  68. Label-Free Subjective Player Experience Modelling via Let's Play Videos
  69. Coal Mining Question Answering with LLMs
  70. AiBAT: Artificial Intelligence/Instructions for Build, Assembly, and Test
  71. Visual Editing with LLM-based Tool Chaining: An Efficient Distillation Approach for Real-Time Applications
  72. LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences
  73. Comparison of Autoencoder Encodings for ECG Representation in Downstream Prediction Tasks
  74. Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification
  75. RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions
  76. AirLetters: An Open Video Dataset of Characters Drawn in the Air
  77. Deep image-based Adaptive BRDF Measure
  78. Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation
  79. Convergence Guarantees for Neural Network-Based Hamilton-Jacobi Reachability
  80. Better Instruction-Following Through Minimum Bayes Risk
  81. FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs
  82. Cognitive Biases in Large Language Models for News Recommendation
  83. Task-Decoupled Image Inpainting Framework for Class-specific Object Remover
  84. Computational Modeling of Artistic Inspiration: A Framework for Predicting Aesthetic Preferences in Lyrical Lines Using Linguistic and Stylistic Features
  85. Real-World Cooking Robot System from Recipes Based on Food State Recognition Using Foundation Models and PDDL
  86. Individuation of 3D perceptual units from neurogeometry of binocular cells
  87. FAIR Universe HiggsML Uncertainty Dataset and Competition
  88. Deep Signature: Characterization of Large-Scale Molecular Dynamics
  89. A Spatio-Temporal Machine Learning Model for Mortgage Credit Risk: Default Probabilities and Loan Portfolios
  90. Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradients
  91. CAnDOIT: Causal Discovery with Observational and Interventional Data from Time-Series
  92. Neural delay differential equations: learning non-Markovian closures for partially known dynamical systems
  93. Overcoming Representation Bias in Fairness-Aware data Repair using Optimal Transport
  94. Modelling the longevity of complex living systems
  95. Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats
  96. Forecasting Smog Clouds With Deep Learning
  97. Loong: Generating Minute-level Long Videos with Autoregressive Language Models
  98. CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text
  99. GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data
  100. An Online Automatic Modulation Classification Scheme Based on Isolation Distributional Kernel
  101. Training Language Models on Synthetic Edit Sequences Improves Code Synthesis
  102. CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation
  103. Neutral Residues: Revisiting Adapters for Model Extension
  104. Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization
  105. Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models
  106. Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
  107. OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?
  108. Data Similarity-Based One-Shot Clustering for Multi-Task Hierarchical Federated Learning
  109. Custom Non-Linear Model Predictive Control for Obstacle Avoidance in Indoor and Outdoor Environments
  110. Unified Multimodal Interleaved Document Representation for Retrieval
  111. Large Language Models as Markov Chains
  112. Curvature Diversity-Driven Deformation and Domain Alignment for Point Cloud
  113. SynthFormer: Equivariant Pharmacophore-based Generation of Synthesizable Molecules for Ligand-Based Drug Design
  114. Measurements with Noise: Bayesian Optimization for Co-optimizing Noise and Property Discovery in Automated Experiments
  115. AlzhiNet: Traversing from 2DCNN to 3DCNN, Towards Early Detection and Diagnosis of Alzheimer's Disease
  116. NETS: A Non-Equilibrium Transport Sampler
  117. LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
  118. Selective Attention Improves Transformer
  119. Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups
  120. HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly
  121. On the Proper Treatment of Tokenization in Psycholinguistics
  122. User-centric Immersive Communications in 6G: A Data-oriented Framework via Digital Twin
  123. DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life
  124. Highly Adaptive Ridge
  125. Distilling an End-to-End Voice Assistant Without Instruction Training Data
  126. CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming
  127. FAN: Fourier Analysis Networks
  128. Examining Language Modeling Assumptions Using an Annotated Literary Dialect Corpus
  129. Unsupervised Point Cloud Completion through Unbalanced Optimal Transport
  130. AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofs
  131. How to Train Long-Context Language Models (Effectively)
  132. Hate Personified: Investigating the role of LLMs in content moderation
  133. Scalable Simulation-free Entropic Unbalanced Optimal Transport
  134. Deconstructing Recurrence, Attention, and Gating: Investigating the transferability of Transformers and Gated Recurrent Neural Networks in forecasting of dynamical systems
  135. Measuring and Improving Persuasiveness of Large Language Models
  136. CAX: Cellular Automata Accelerated in JAX
  137. Undesirable Memorization in Large Language Models: A Survey
  138. Immunogenicity Prediction with Dual Attention Enables Vaccine Target Selection
  139. Learning 3D Perception from Others' Predictions
  140. Why Sample Space Matters: Keyframe Sampling Optimization for LiDAR-based Place Recognition
  141. Labor Migration Modeling through Large-scale Job Query Data
  142. Spatial-Temporal Multi-Cuts for Online Multiple-Camera Vehicle Tracking
  143. Plots Unlock Time-Series Understanding in Multimodal Models
  144. Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning
  145. Understanding implementation pitfalls of distance-based metrics for image segmentation
  146. Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression
  147. Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization
  148. Online Learning Guided Quasi-Newton Methods with Global Non-Asymptotic Convergence
  149. Ranking Perspective for Tree-based Methods with Applications to Symbolic Feature Selection
  150. Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic Transforms
  151. GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering
  152. Achieving Fairness in Predictive Process Analytics via Adversarial Learning (Extended Version)
  153. IndicSentEval: How Effectively do Multilingual Transformer Models encode Linguistic Properties for Indic Languages?
  154. Ethio-Fake: Cutting-Edge Approaches to Combat Fake News in Under-Resourced Languages Using Explainable AI
  155. Long-Sequence Recommendation Models Need Decoupled Embeddings
  156. Diffusion & Adversarial Schr"odinger Bridges via Iterative Proportional Markovian Fitting
  157. High-Efficiency Neural Video Compression via Hierarchical Predictive Learning
  158. HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR
  159. Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks
  160. IC3M: In-Car Multimodal Multi-object Monitoring for Abnormal Status of Both Driver and Passengers
  161. Generalization emerges from local optimization in a self-organized learning network
  162. An Improved Variational Method for Image Denoising
  163. Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance
  164. Deep Regression 2D-3D Ultrasound Registration for Liver Motion Correction in Focal Tumor Thermal Ablation
  165. Combining Pre- and Post-Demosaicking Noise Removal for RAW Video
  166. SuperGS: Super-Resolution 3D Gaussian Splatting Enhanced by Variational Residual Features and Uncertainty-Augmented Learning
  167. Deep Learning-Based Prediction of Suspension Dynamics Performance in Multi-Axle Vehicles
  168. The Benefit of Being Bayesian in Online Conformal Prediction
  169. Convolutional Variational Autoencoders for Spectrogram Compression in Automatic Speech Recognition
  170. Obtaining Lower Query Complexities through Lightweight Zeroth-Order Proximal Gradient Algorithms
  171. Improving Unsupervised Constituency Parsing via Maximizing Semantic Information
  172. NestedMorph: Enhancing Deformable Medical Image Registration with Nested Attention Mechanisms
  173. Personalized Quantum Federated Learning for Privacy Image Classification
  174. Fair Decentralized Learning
  175. Algorithms For Automatic Accentuation And Transcription Of Russian Texts In Speech Recognition Systems
  176. Intelligence at the Edge of Chaos
  177. Pseudo-Stereo Inputs: A Solution to the Occlusion Challenge in Self-Supervised Stereo Matching
  178. A Schema-aware Logic Reformulation for Graph Reachability
  179. A Foundation Model for the Solar Dynamics Observatory
  180. HiFiSeg: High-Frequency Information Enhanced Polyp Segmentation with Global-Local Vision Transformer
  181. Learning from Offline Foundation Features with Tensor Augmentations
  182. Contextual Document Embeddings
  183. Med-TTT: Vision Test-Time Training model for Medical Image Segmentation
  184. Methods of Automatic Matrix Language Determination for Code-Switched Speech
  185. Semantic-Guided RL for Interpretable Feature Engineering
  186. Learning Emergence of Interaction Patterns across Independent RL Agents in Multi-Agent Environments
  187. Minimax Group Fairness in Strategic Classification
  188. SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
  189. Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment
  190. Mixed-Session Conversation with Egocentric Memory
  191. Defining Knowledge: Bridging Epistemology and Large Language Models
  192. Dynamic Gradient Alignment for Online Data Mixing
  193. Efficient learning of differential network in multi-source non-paranormal graphical models
  194. DTVLT: A Multi-modal Diverse Text Benchmark for Visual Language Tracking Based on LLM
  195. Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold
  196. Encryption-Friendly LLM Architecture
  197. Event-Customized Image Generation
  198. Temporal Predictive Coding for Gradient Compression in Distributed Learning
  199. Learning Diverse Bimanual Dexterous Manipulation Skills from Human Demonstrations
  200. Online Convex Optimization with a Separation Oracle
  201. Meta-Models: An Architecture for Decoding LLM Behaviors Through Interpreted Embeddings and Natural Language
  202. Revealing the Inherent Instructability of Pre-Trained Language Models
  203. MedVisionLlama: Leveraging Pre-Trained Large Language Model Layers to Enhance Medical Image Segmentation
  204. Recurrent Few-Shot model for Document Verification
  205. Quantifying User Coherence: A Unified Framework for Analyzing Recommender Systems Across Domains
  206. Personalized Federated Learning for Generative AI-Assisted Semantic Communications
  207. Clinnova Federated Learning Proof of Concept: Key Takeaways from a Cross-border Collaboration
  208. Embedded Topic Models Enhanced by Wikification
  209. Learning K-U-Net with constant complexity: An Application to time series forecasting
  210. Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization
  211. Predictive Attractor Models
  212. Collective Critics for Creative Story Generation
  213. Learning the Latent Rules of a Game from Data: A Chess Story
  214. LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services
  215. LoGDesc: Local geometric features aggregation for robust point cloud registration
  216. MenakBERT -- Hebrew Diacriticizer
  217. SynCo: Synthetic Hard Negatives for Contrastive Visual Representation Learning
  218. An Online Feasible Point Method for Benign Generalized Nash Equilibrium Problems
  219. Parameter Competition Balancing for Model Merging
  220. Online Multi-Label Classification under Noisy and Changing Label Distribution
  221. MANTRA: The Manifold Triangulations Assemblage
  222. Diffusion Meets Options: Hierarchical Generative Skill Composition for Temporally-Extended Tasks
  223. BiSSL: Enhancing the Alignment Between Self-Supervised Pretraining and Downstream Fine-Tuning via Bilevel Optimization
  224. Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors
  225. MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences
  226. Towards Comprehensive Detection of Chinese Harmful Memes
  227. Distributed Learning with Discretely Observed Functional Data
  228. NTU-NPU System for Voice Privacy 2024 Challenge
  229. From Concrete to Abstract: A Multimodal Generative Approach to Abstract Concept Learning
  230. Source Data Selection for Brain-Computer Interfaces based on Simple Features
  231. AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
  232. ProtoSeg: A Prototype-Based Point Cloud Instance Segmentation Method
  233. Simplicity bias and optimization threshold in two-layer ReLU networks
  234. EntryPrune: Neural Network Feature Selection using First Impressions
  235. Listening to the Wise Few: Query-Key Alignment Unlocks Latent Correct Answers in Large Language Models
  236. Data Optimisation of Machine Learning Models for Smart Irrigation in Urban Parks
  237. Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks
  238. Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection
  239. Autonomous Self-Trained Channel State Prediction Method for mmWave Vehicular Communications
  240. Automated Tone Transcription and Clustering with Tone2Vec
  241. RESSCAL3D++: Joint Acquisition and Semantic Segmentation of 3D Point Clouds
  242. QDGset: A Large Scale Grasping Dataset Generated with Quality-Diversity
  243. CTARR: A fast and robust method for identifying anatomical regions on CT images via atlas registration
  244. A novel neural network-based approach to derive a geomagnetic baseline for robust characterization of geomagnetic indices at mid-latitude
  245. Decoupling Layout from Glyph in Online Chinese Handwriting Generation
  246. Traffic Light or Light Traffic? Investigating Phrasal Semantics in Large Language Models
  247. The Comparison of Individual Cat Recognition Using Neural Networks
  248. A Novel Method for Accurate & Real-time Food Classification: The Synergistic Integration of EfficientNetB7, CBAM, Transfer Learning, and Data Augmentation
  249. Semantic Communication and Control Co-Design for Multi-Objective Distinct Dynamics
  250. Make Compound Sentences Simple to Analyze: Learning to Split Sentences for Aspect-based Sentiment Analysis
  251. How to Make LMs Strong Node Classifiers?
  252. Efficient Second-Order Neural Network Optimization via Adaptive Trust Region Methods
  253. Density based Spatial Clustering of Lines via Probabilistic Generation of Neighbourhood
  254. Computer-aided Colorization State-of-the-science: A Survey
  255. Correlation and Navigation in the Vocabulary Key Representation Space of Language Models
  256. Morphological evaluation of subwords vocabulary used by BETO language model
  257. Annotation Guidelines for Corpus Novelties: Part 1 -- Named Entity Recognition
  258. On Lai's Upper Confidence Bound in Multi-Armed Bandits
  259. Perfect Counterfactuals in Imperfect Worlds: Modelling Noisy Implementation of Actions in Sequential Algorithmic Recourse
  260. CoLLAP: Contrastive Long-form Language-Audio Pretraining with Musical Temporal Structure Augmentation
  261. Structural-Entropy-Based Sample Selection for Efficient and Effective Learning
  262. Can Capacitive Touch Images Enhance Mobile Keyboard Decoding?
  263. FedScalar: Federated Learning with Scalar Communication for Bandwidth-Constrained Networks
  264. Probabilistic road classification in historical maps using synthetic data and deep learning
  265. Spiking Neural Network as Adaptive Event Stream Slicer
  266. Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization
  267. PFGuard: A Generative Framework with Privacy and Fairness Safeguards
  268. Visual Prompting in LLMs for Enhancing Emotion Recognition
  269. Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis
  270. A Pilot Study of Applying Sequence-to-Sequence Voice Conversion to Evaluate the Intelligibility of L2 Speech Using a Native Speaker's Shadowings
  271. Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features
  272. Mitigating Downstream Model Risks via Model Provenance
  273. Efficient Semantic Segmentation via Lightweight Multiple-Information Interaction Network
  274. EmbedLLM: Learning Compact Representations of Large Language Models
  275. Capturing complex hand movements and object interactions using machine learning-powered stretchable smart textile gloves
  276. Multi-modal clothing recommendation model based on large model and VAE enhancement
  277. Hard Negative Sample Mining for Whole Slide Image Classification
  278. Calibrate to Discriminate: Improve In-Context Learning with Label-Free Comparative Inference
  279. Nonparametric IPSS: Fast, flexible feature selection with false discovery control
  280. Adapting Segment Anything Model to Melanoma Segmentation in Microscopy Slide Images
  281. Can Language Models Take A Hint? Prompting for Controllable Contextualized Commonsense Inference
  282. Remember and Recall: Associative-Memory-based Trajectory Prediction
  283. Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts
  284. Deep Koopman-layered Model with Universal Property Based on Toeplitz Matrices
  285. G2T-LLM: Graph-to-Tree Text Encoding for Molecule Generation with Fine-Tuned Large Language Models
  286. BACKTIME: Backdoor Attacks on Multivariate Time Series Forecasting
  287. A Survey on Point-of-Interest Recommendation: Models, Architectures, and Security
  288. POSIX: A Prompt Sensitivity Index For Large Language Models
  289. CodeJudge: Evaluating Code Generation with Large Language Models
  290. BadCM: Invisible Backdoor Attack Against Cross-Modal Learning
  291. HATFormer: Historic Handwritten Arabic Text Recognition with Transformers
  292. Towards Better Generalization: Weight Decay Induces Low-rank Bias for Neural Networks
  293. Efficiently Deploying LLMs with Controlled Risk
  294. A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization
  295. Universality in Transfer Learning for Linear Models
  296. Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1
  297. RiskSEA : A Scalable Graph Embedding for Detecting On-chain Fraudulent Activities on the Ethereum Blockchain
  298. SCNode: Spatial and Contextual Coordinates for Graph Representation Learning
  299. The why, what, and how of AI-based coding in scientific research
  300. An Evaluation of Large Pre-Trained Models for Gesture Recognition using Synthetic Videos
  301. Quantitative Approximation for Neural Operators in Nonlinear Parabolic Equations
  302. Matrix and Relative Weak Crossover in Japanese: An Experimental Investigation
  303. Reducing Warning Errors in Driver Support with Personalized Risk Maps
  304. Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement
  305. Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes
  306. Plug-and-Play Controllable Generation for Discrete Masked Models
  307. A Formal Framework for Understanding Length Generalization in Transformers
  308. Disentangled Representation Learning for Parametric Partial Differential Equations
  309. TrajGPT: Irregular Time-Series Representation Learning for Health Trajectory Analysis
  310. Nonuniform random feature models using derivative information
  311. Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners
  312. DMC-Net: Lightweight Dynamic Multi-Scale and Multi-Resolution Convolution Network for Pancreas Segmentation in CT Images
  313. Breaking the mold: The challenge of large scale MARL specialization
  314. BayesCNS: A Unified Bayesian Approach to Address Cold Start and Non-Stationarity in Search Systems at Scale
  315. Lossy Cooperative UAV Relaying Networks: Outage Probability Analysis and Location Optimization
  316. L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?
  317. Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environments