mlsanityData to 7 Oct 2026

Papers

New on arXiv

Tue 13 Feb 2024

264 papers

  1. GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local RefinementsLLM reasoning → Reinforcement learning for reasoning
  2. Hybrid Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
  3. Rethinking Machine Unlearning for Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  4. InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference AlignmentLLM reasoning → Knowledge- and tool-augmented reasoning +1
  5. LDTrack: Dynamic People Tracking by Service Robots using Diffusion ModelsDiffusion models → Video generation
  6. PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
  7. AMEND: A Mixture of Experts Framework for Long-tailed Trajectory PredictionMixture-of-experts → MoE for time series and graphs
  8. Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded GuidanceMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  9. COLD-Attack: Jailbreaking LLMs with Stealthiness and ControllabilityLLM safety and security → Jailbreaking
  10. Graph Mamba: Towards Learning on Graphs with State Space ModelsState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  11. Rec-GPT4V: Multimodal Recommendation with Large Vision-Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  12. Target Score MatchingDiffusion models → Diffusion foundations and sampling
  13. PIN: Positional Insert Unlocks Object Localisation Abilities in VLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  14. Learning Continuous 3D Words for Text-to-Image GenerationDiffusion models → 3D, point cloud and scene generation
  15. Inference of Abstraction for a Unified Account of Symbolic Reasoning from DataLLM reasoning → Reasoning benchmarks and evaluation
  16. Tandem Transformers for Inference Efficient LLMsEfficient LLM inference and serving → Speculative decoding
  17. Mixtures of Experts Unlock Parameter Scaling for Deep RLMixture-of-experts → MoE in reinforcement learning and robotics
  18. Latent Inversion with Timestep-aware Sampling for Training-free Non-rigid EditingDiffusion models → Image generation, text-to-image and editing
  19. Mixture of Link Predictors on GraphsMixture-of-experts → MoE for time series and graphs
  20. Test-Time Backdoor Attacks on Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  21. Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially FastMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  22. Denoising Diffusion Restoration Tackles Forward and Inverse Problems for the Laplace OperatorDiffusion models → Inverse problems and image restoration
  23. Higher Layers Need More LoRA ExpertsMixture-of-experts → Mixture of LoRA experts
  24. Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy BiasesDiffusion models → Diffusion and flow policies for robotics +1
  25. P-Mamba: Marrying Perona Malik Diffusion with Mamba for Efficient Pediatric Echocardiographic Left Ventricular SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  26. "Reasoning" with Rhetoric: On the Style-Evidence Tradeoff in LLM-Generated Counter-ArgumentsLLM reasoning → Reasoning benchmarks and evaluation
  27. Conditional Neural Expert Processes for Learning Movement Primitives from DemonstrationOffline RL and imitation learning from data → Robot learning from demonstration
  28. Conservative and Risk-Aware Offline Multi-Agent Reinforcement LearningOffline RL and imitation learning from data → Offline multi-agent RL
  29. Pandora: Jailbreak GPTs by Retrieval Augmented Generation PoisoningRetrieval-augmented generation → Privacy and security of RAG +1
  30. Large Language Models as Minecraft AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  31. Visual Question Answering Instruction: Unlocking Multimodal Large Language Model To Domain-Specific Visual MultitasksMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  32. PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal RetrieversMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  33. The Effect of Data Poisoning on Counterfactual ExplanationsLLM safety and security → Backdoor and data poisoning attacks
  34. Logic of Awareness for Nested KnowledgeLLM reasoning → Prompting and chain-of-thought reasoning
  35. World Model on Million-Length Video And Language With Blockwise RingAttentionWorld models → Video-generation world models and simulators
  36. A Dense Reward View on Aligning Text-to-Image Diffusion with PreferenceDiffusion models → Diffusion and flow policies for robotics +1
  37. A Survey of Table Reasoning with Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  38. BBSEA: An Exploration of Brain-Body Synchronization for Embodied AgentsLLM agents and tool use → Multimodal and embodied agents
  39. Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature GenerationDiffusion models → Image generation, text-to-image and editing
  40. Simulating Human Strategic Behavior: Comparing Single and Multi-agent LLMsLLM agents and tool use → Social simulation and multi-agent debate
  41. LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied AgentsLLM agents and tool use → Multimodal and embodied agents
  42. PFCM: Poisson flow consistency models for low-dose CT image denoisingDiffusion models → Medical imaging and segmentation
  43. VerMCTS: Synthesizing Multi-Step Programs using a Verifier, a Large Language Model, and Tree SearchLLM reasoning → Reasoning for agents, planning and code
  44. Sugarcane Health Monitoring With Satellite Spectroscopy and Machine Learning: A Review
  45. Floralens: a Deep Learning Model for the Portuguese Native Flora
  46. Misconduct in Post-Selections and Deep Learning
  47. Transductive Active Learning: Theory and Applications
  48. Active Few-Shot Fine-Tuning
  49. Optimal feature rescaling in machine learning based on neural networks
  50. Measuring and Controlling Instruction (In)Stability in Language Model Dialogs
  51. Oracle-Efficient Differentially Private Learning with Public Data
  52. Data Reconstruction Attacks and Defenses: A Systematic Evaluation
  53. Approximation of relation functions and attention mechanisms
  54. GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agency
  55. Space-Time Diffusion Bridge
  56. An Embarrassingly Simple Approach for LLM with Strong ASR Capacity
  57. Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
  58. Learning to Generate Context-Sensitive Backchannel Smiles for Embodied AI Agents with Applications in Mental Health Dialogues
  59. Intelligent Agricultural Management Considering N2O Emission and Climate Variability with Uncertainties
  60. eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data
  61. Sequence graphs realizations and ambiguity in language models
  62. Fusing Individualized Treatment Rules Using Secondary Outcomes
  63. Disambiguated Node Classification with Graph Neural Networks
  64. Random Representations Outperform Online Continually Learned Representations
  65. Corridor Geometry in Gradient-Based Optimization
  66. Model approximation in MDPs with unbounded per-step cost
  67. Intelligent Canvas: Enabling Design-Like Exploratory Visual Data Analysis with Generative AI through Rapid Prototyping, Iteration and Curation
  68. Deep and shallow data science for multi-scale optical neuroscience
  69. Depth Separation in Norm-Bounded Infinite-Width Neural Networks
  70. Combining Insights From Multiple Large Language Models Improves Diagnostic Accuracy
  71. LLMs and Stack Overflow Discussions: Reliability, Impact, and Challenges
  72. Projection-Free Online Convex Optimization with Time-Varying Constraints
  73. BEFUnet: A Hybrid CNN-Transformer Architecture for Precise Medical Image Segmentation
  74. Improving Molecule Generation and Drug Discovery with a Knowledge-enhanced Generative Model
  75. Leveraging cough sounds to optimize chest x-ray usage in low-resource settings
  76. Syllable based DNN-HMM Cantonese Speech to Text System
  77. Preconditioners for the Stochastic Training of Neural Fields
  78. Enhanced Deep Q-Learning for 2D Self-Driving Cars: Implementation and Evaluation on a Custom Track Environment
  79. DNABERT-S: Pioneering Species Differentiation with Species-Aware DNA Embeddings
  80. Optimal Task Assignment and Path Planning using Conflict-Based Search with Precedence and Temporal Constraints
  81. FLASH: Federated Learning Across Simultaneous Heterogeneities
  82. Adversarially Robust Feature Learning for Breast Cancer Diagnosis
  83. A Dataset for the Detection of Dehumanizing Language
  84. Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks
  85. JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models
  86. Bayesian Strategic Classification
  87. Learning How To Ask: Cycle-Consistency Refines Prompts in Multimodal Foundation Models
  88. LLM-driven Imitation of Subrational Behavior : Illusion or Reality?
  89. Forecasting for Swap Regret for All Downstream Agents
  90. Nearest Neighbor Representations of Neural Circuits
  91. Towards the Detection of AI-Synthesized Human Face Images
  92. Automated detection of motion artifacts in brain MR images using deep learning and explainable artificial intelligence
  93. Nearest Neighbor Representations of Neurons
  94. ADS: Approximate Densest Subgraph for Novel Image Discovery
  95. Unveiling Hidden Energy Anomalies: Harnessing Deep Learning to Optimize Energy Management in Sports Facilities
  96. Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs
  97. Trained quantum neural networks are Gaussian processes
  98. BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation
  99. Correction to "Wasserstein distance estimates for the distributions of numerical approximations to ergodic stochastic differential equations"
  100. Zero Shot Molecular Generation via Similarity Kernels
All 264
  1. A Survey of Generative AI for de novo Drug Design: New Frontiers in Molecule and Protein Generation
  2. PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling
  3. Primal-Dual Algorithms with Predictions for Online Bounded Allocation and Ad-Auctions Problems
  4. Unsupervised Evaluation of Code LLMs with Round-Trip Correctness
  5. IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation
  6. A Convergence Analysis of Approximate Message Passing with Non-Separable Functions and Applications to Multi-Class Classification
  7. The dynamic interplay between in-context and in-weight learning in humans and neural networks
  8. Model Assessment and Selection under Temporal Distribution Shift
  9. Are Semi-Dense Detector-Free Methods Good at Matching Local Features?
  10. Improving Generalization in Semantic Parsing by Increasing Natural Language Variation
  11. Learning Emergent Gaits with Decentralized Phase Oscillators: on the role of Observations, Rewards, and Feedback
  12. The Last JITAI? Exploring Large Language Models for Issuing Just-in-Time Adaptive Interventions: Fostering Physical Activity in a Conceptual Cardiac Rehabilitation Setting
  13. SAGMAN: Stability Analysis of Graph Neural Networks on the Manifolds
  14. Generating Universal Adversarial Perturbations for Quantum Classifiers
  15. Peeking Behind the Curtains of Residual Learning
  16. Learned Image Compression with Text Quality Enhancement
  17. Forecasting high-impact research topics via machine learning on evolving knowledge graphs
  18. SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages
  19. Strategizing against No-Regret Learners in First-Price Auctions
  20. BdSLW60: A Word-Level Bangla Sign Language Dataset
  21. Knowledge Editing on Black-box Large Language Models
  22. NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs
  23. A Unified Framework for Analyzing Meta-algorithms in Online Convex Optimization
  24. Adjustment Identification Distance: A gadjid for Causal Structure Learning
  25. Arbitrary Polynomial Separations in Trainable Quantum Machine Learning
  26. Globally-Optimal Greedy Experiment Selection for Active Sequential Estimation
  27. Homomorphism Counts for Graph Neural Networks: All About That Basis
  28. Bayesian Multi-Task Transfer Learning for Soft Prompt Tuning
  29. Graph Feature Preprocessor: Real-time Subgraph-based Feature Extraction for Financial Crime Detection
  30. Convolutional Neural Networks Towards Facial Skin Lesions Detection
  31. Faster Repeated Evasion Attacks in Tree Ensembles
  32. FESS Loss: Feature-Enhanced Spatial Segmentation Loss for Optimizing Medical Image Analysis
  33. Improving Factual Error Correction for Abstractive Summarization via Data Distillation and Conditional-generation Cloze
  34. FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing
  35. Regret Minimization in Stackelberg Games with Side Information
  36. Two Tales of Single-Phase Contrastive Hebbian Learning
  37. Glass Segmentation with Multi Scales and Primary Prediction Guiding
  38. Online Foundation Model Selection in Robotics
  39. Artificial Intelligence for Literature Reviews: Opportunities and Challenges
  40. Dueling Over Dessert, Mastering the Art of Repeated Cake Cutting
  41. Theoretical Analysis of Leave-one-out Cross Validation for Non-differentiable Penalties under High-dimensional Settings
  42. Generative VS non-Generative Models in Engineering Shape Optimization
  43. Intelligent Diagnosis of Alzheimer's Disease Based on Machine Learning
  44. A Distributional Analogue to the Successor Representation
  45. Approximately Piecewise E(3) Equivariant Point Networks
  46. Can LLMs Learn New Concepts Incrementally without Forgetting?
  47. Fairness Auditing with Multi-Agent Collaboration
  48. Counterfactual Influence in Markov Decision Processes
  49. Amplifying Exploration in Monte-Carlo Tree Search by Focusing on the Unknown
  50. From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries (Extended Version)
  51. A PAC-Bayesian Link Between Generalisation and Flat Minima
  52. Provable Traffic Rule Compliance in Safe Reinforcement Learning on the Open Sea
  53. A Systematic Review of Data-to-Text NLG
  54. Sparsity via Sparse Group k-max Regularization
  55. The Application of ChatGPT in Responding to Questions Related to the Boston Bowel Preparation Scale
  56. Deep Reinforcement Learning for Controlled Traversing of the Attractor Landscape of Boolean Models in the Context of Cellular Reprogramming
  57. Revealing Decurve Flows for Generalized Graph Propagation
  58. Plausible Extractive Rationalization through Semi-Supervised Entailment Signal
  59. Intriguing Differences Between Zero-Shot and Systematic Evaluations of Vision-Language Transformer Models
  60. Large Language Models for the Automated Analysis of Optimization Algorithms
  61. Parallel-friendly Spatio-Temporal Graph Learning for Photovoltaic Degradation Analysis at Scale
  62. ROSpace: Intrusion Detection Dataset for a ROS2-Based Cyber-Physical System
  63. Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claims
  64. Taking Training Seriously: Human Guidance and Management-Based Regulation of Artificial Intelligence
  65. Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products
  66. Latent space configuration for improved generalization in supervised autoencoder neural networks
  67. JeFaPaTo -- A joint toolbox for blinking analysis and facial features extraction
  68. Camera Calibration through Geometric Constraints from Rotation and Projection Matrices
  69. Analyzing Prompt Influence on Automated Method Generation: An Empirical Study with Copilot
  70. Leveraging Self-Supervised Instance Contrastive Learning for Radar Object Detection
  71. Frequency-aware Graph Signal Processing for Collaborative Filtering
  72. Transfer Operators from Batches of Unpaired Points via Entropic Transport Kernels
  73. Vehicle Behavior Prediction by Episodic-Memory Implanted NDT
  74. Distribution Estimation under the Infinity Norm
  75. Interacting Particle Systems on Networks: joint inference of the network and the interaction kernel
  76. Transferring Ultrahigh-Field Representations for Intensity-Guided Brain Segmentation of Low-Field Magnetic Resonance Imaging
  77. Transition Constrained Bayesian Optimization via Markov Decision Processes
  78. A Novel Approach to Regularising 1NN classifier for Improved Generalization
  79. LLMs and the Human Condition
  80. LOSS-GAT: Label Propagation and One-Class Semi-Supervised Graph Attention Network for Fake News Detection
  81. Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing
  82. A Neural-network Enhanced Video Coding Framework beyond ECM
  83. Selective Learning: Towards Robust Calibration with Dynamic Regularization
  84. Uncertainty Quantification for Forward and Inverse Problems of PDEs via Latent Global Evolution
  85. Punctuation Restoration Improves Structure Understanding Without Supervision
  86. The Duet of Representations and How Explanations Exacerbate It
  87. Time-Series Classification for Dynamic Strategies in Multi-Step Forecasting
  88. Helping university students to choose elective courses by using a hybrid multi-criteria recommendation system with genetic optimization
  89. One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill
  90. RBF-PINN: Non-Fourier Positional Embedding in Physics-Informed Neural Networks
  91. Learning Better Representations From Less Data For Propositional Satisfiability
  92. Learning to Produce Semi-dense Correspondences for Visual Localization
  93. Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queries
  94. Visually Dehallucinative Instruction Generation
  95. Conditional Information Gain Trellis
  96. Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training
  97. Eliciting Personality Traits in Large Language Models
  98. Scribble-based fast weak-supervision and interactive corrections for segmenting whole slide images
  99. Uncertainty Quantification via Stable Distribution Propagation
  100. Mapping the Ethics of Generative AI: A Comprehensive Scoping Review
  101. Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
  102. The Paradox of Motion: Evidence for Spurious Correlations in Skeleton-based Gait Recognition Models
  103. Values That Are Explicitly Present in Fairy Tales: Comparing Samples from German, Italian and Portuguese Traditions
  104. CrossGaze: A Strong Method for 3D Gaze Estimation in the Wild
  105. Approximating Families of Sharp Solutions to Fisher's Equation with Physics-Informed Neural Networks
  106. One-to-many Reconstruction of 3D Geometry of cultural Artifacts using a synthetically trained Generative Model
  107. Prompted Contextual Vectors for Spear-Phishing Detection
  108. ChatCell: Facilitating Single-Cell Analysis with Natural Language
  109. An Order-Complexity Aesthetic Assessment Model for Aesthetic-aware Music Recommendation
  110. Time to Stop and Think: What kind of research do we want to do?
  111. Multi-Level GNN Preconditioner for Solving Large Scale Problems
  112. Learning semantic image quality for fetal ultrasound from noisy ranking annotation
  113. A Logical Approach to Criminal Case Investigation
  114. Classification Using Global and Local Mahalanobis Distances
  115. Pix2Code: Learning to Compose Neural Visual Concepts as Programs
  116. Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering
  117. Rethinking U-net Skip Connections for Biomedical Image Segmentation
  118. Geometry-induced Regularization in Deep ReLU Neural Networks
  119. Improving Image Coding for Machines through Optimizing Encoder via Auxiliary Loss
  120. Modeling Balanced Explicit and Implicit Relations with Contrastive Learning for Knowledge Concept Recommendation in MOOCs
  121. Distal Interference: Exploring the Limits of Model-Based Continual Learning
  122. Object Detection in Thermal Images Using Deep Learning for Unmanned Aerial Vehicles
  123. A survey of recent methods for addressing AI fairness and bias in biomedicine
  124. SepRep-Net: Multi-source Free Domain Adaptation via Model Separation And Reparameterization
  125. Ant Colony Optimization for Cooperative Inspection Path Planning Using Multiple Unmanned Aerial Vehicles
  126. APALU: A Trainable, Adaptive Activation Function for Deep Learning Networks
  127. Towards Equitable Agile Research and Development of AI and Robotics
  128. BERT4FCA: A Method for Bipartite Link Prediction using Formal Concept Analysis and BERT
  129. Color Image Denoising Using The Green Channel Prior
  130. End-to-End Policy Learning of a Statistical Arbitrage Autoencoder Architecture
  131. Causal Discovery under Off-Target Interventions
  132. Investigating Out-of-Distribution Generalization of GNNs: An Architecture Perspective
  133. Privacy-Preserving Language Model Inference with Instance Obfuscation
  134. Improving Black-box Robustness with In-Context Rewriting
  135. MetaTra: Meta-Learning for Generalized Trajectory Prediction in Unseen Domain
  136. BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models
  137. Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Tasks
  138. Quantum Computing-Enhanced Algorithm Unveils Novel Inhibitors for KRAS
  139. Thresholding Data Shapley for Data Cleansing Using Multi-Armed Bandits
  140. Inherent Diverse Redundant Safety Mechanisms for AI-based Software Elements in Automotive Applications
  141. Translating Images to Road Network: A Sequence-to-Sequence Perspective
  142. Confronting Discrimination in Classification: Smote Based on Marginalized Minorities in the Kernel Space for Imbalanced Data
  143. Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap
  144. PSC-CPI: Multi-Scale Protein Sequence-Structure Contrasting for Efficient and Generalizable Compound-Protein Interaction Prediction
  145. Optimized Information Flow for Transformer Tracking
  146. Gaussian Ensemble Belief Propagation for Efficient Inference in High-Dimensional Systems
  147. THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation
  148. Learning time-dependent PDE via graph neural networks and deep operator network for robust accuracy on irregular grids
  149. Advancing Data-driven Weather Forecasting: Time-Sliding Data Augmentation of ERA5
  150. Enabling Multi-Agent Transfer Reinforcement Learning via Scenario Independent Representation
  151. Pixel Sentence Representation Learning
  152. Variational Continual Test-Time Adaptation
  153. Online Structured Prediction with Fenchel--Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss
  154. Hierarchical Position Embedding of Graphs with Landmarks and Clustering for Link Prediction
  155. LLaGA: Large Language and Graph Assistant
  156. On Limitations of the Transformer Architecture
  157. Differentially Private Distributed Inference for Multicenter Clinical Studies
  158. CMA-R:Causal Mediation Analysis for Explaining Rumour Detection
  159. Perturbative adaptive importance sampling for Bayesian LOO cross-validation
  160. Epistemic Exploration for Generalizable Planning and Learning in Non-Stationary Settings
  161. Average-Case Analysis of Iterative Voting
  162. Artificial intelligence and the transformation of higher education institutions
  163. H2O-SDF: Two-phase Learning for 3D Indoor Reconstruction using Object Surface Fields
  164. Randomized Algorithms for Symmetric Nonnegative Matrix Factorization