mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 16 Jun 2024

184 papers

  1. People will agree what I think: Investigating LLM's False Consensus EffectLLM reasoning → Reasoning benchmarks and evaluation
  2. Current state of LLM Risks and AI GuardrailsLLM safety and security → Safety alignment, refusal and guardrails
  3. A Notion of Complexity for Theory of Mind via Discrete World ModelsWorld models → World models for language agents
  4. Mixture-of-Subspaces in Low-Rank AdaptationDiffusion models → Image generation, text-to-image and editing
  5. Exploiting Diffusion Prior for Out-of-Distribution DetectionDiffusion models → Medical imaging and segmentation
  6. An Analysis on Quantizing Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  7. RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional InformationRetrieval-augmented generation → Privacy and security of RAG
  8. WildVision: Evaluating Vision-Language Models in the Wild with Human PreferencesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  9. A Unified View of Abstract Visual Reasoning ProblemsLLM reasoning → Multimodal reasoning
  10. A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual ReasoningLLM reasoning → Multimodal reasoning
  11. Interacting Particle Systems for Fast Linear Quadratic RLDeep reinforcement learning methods → RL theory and sample complexity
  12. A Peek into Token Bias: Large Language Models Are Not Yet Genuine ReasonersLLM reasoning → Reasoning benchmarks and evaluation
  13. Dynamic Normativity: Necessary and Sufficient Conditions for Value AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  14. garak: A Framework for Security Probing Large Language ModelsLLM safety and security → Prompt injection and agent security
  15. Scaling Synthetic Logical Reasoning Datasets with Context-Sensitive Declarative GrammarsLLM reasoning → Reasoning benchmarks and evaluation
  16. Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation ModelsKnowledge distillation → Speech and audio distillation
  17. RUPBench: Benchmarking Reasoning Under Perturbations for Robustness Evaluation in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  18. Optimized Speculative Sampling for GPU Hardware AcceleratorsEfficient LLM inference and serving → Speculative decoding
  19. Connecting the Dots: Evaluating Abstract Reasoning Capabilities of LLMs Using the New York Times Connections Word GameLLM reasoning → Reasoning for agents, planning and code
  20. Threat Modelling and Risk Analysis for Large Language Model (LLM)-Powered ApplicationsLLM safety and security → Prompt injection and agent security
  21. Towards Lifelong Dialogue Agents via Timeline-based Memory ManagementLLM agents and tool use → Agent memory systems
  22. Concept-skill Transferability-based Data Selection for Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  23. Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational AnswersLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  24. ViD-GPT: Introducing GPT-style Autoregressive Generation in Video Diffusion ModelsDiffusion models → Video generation
  25. Toward Optimal LLM Alignments Using Two-Player GamesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  26. Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL DivergenceLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  27. Towards Efficient Target-Level Machine Unlearning Based on Essential GraphLLM safety and security → Machine unlearning
  28. Really Unlearned? Verifying Machine Unlearning via Influential Sample PairsLLM safety and security → Machine unlearning
  29. Avoiding Copyright Infringement via Large Language Model UnlearningLLM safety and security → Machine unlearning
  30. Don't Forget Too Much: Towards Machine Unlearning on Feature LevelLLM safety and security → Machine unlearning
  31. Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech RecognitionLLM safety and security → Audio jailbreaks and speech backdoors
  32. Investigating Video Reasoning Capability of Large Language Models with Tropes in MoviesLLM reasoning → Multimodal reasoning
  33. Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  34. AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  35. DIPPER: Direct Preference Optimization to Accelerate Primitive-Enabled Hierarchical Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  36. RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language ModelsLLM safety and security → Machine unlearning
  37. VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict EntailmentLLM reasoning → Multimodal reasoning
  38. Exploring the Potential of Multimodal LLM with Knowledge-Intensive Multimodal ASRMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  39. Graph Neural Reaction Diffusion ModelsDiffusion models → Flow matching, time series and science
  40. Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New SolutionsKnowledge distillation → Federated, robust and private distillation
  41. Step-level Value Preference Optimization for Mathematical ReasoningLLM reasoning → Mathematical reasoning +1
  42. TorchOpera: A Compound AI System for LLM SafetyLLM safety and security → Safety alignment, refusal and guardrails
  43. Reminding Multimodal Large Language Models of Object-aware Knowledge with Retrieved TagsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  44. Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical ReasoningLLM reasoning → Mathematical reasoning
  45. PyramidMamba: Rethinking Pyramid Feature Fusion with Selective Space State Model for Semantic Segmentation of Remote Sensing ImageryState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  46. GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  47. Self-Evolution Fine-Tuning for Policy OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  48. Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance MatchingDiffusion models → Diffusion foundations and sampling
  49. Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight FunctionsDeep reinforcement learning methods → RL theory and sample complexity
  50. Towards Understanding Jailbreak Attacks in LLMs: A Representation Space AnalysisLLM safety and security → Jailbreaking
  51. Physically Embodied Gaussian Splatting: A Realtime Correctable World Model for RoboticsWorld models → Latent predictive world models
  52. Quest: Query-Aware Sparsity for Efficient Long-Context LLM InferenceEfficient LLM inference and serving → KV cache optimization
  53. A MgNO Method for Multiphase Flow in Porous Media
  54. Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex
  55. Multi-UAV Multi-RIS QoS-Aware Aerial Communication Systems using DRL and PSO
  56. CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics
  57. Self-Regulated Data-Free Knowledge Amalgamation for Text Classification
  58. WundtGPT: Shaping Large Language Models To Be An Empathetic, Proactive Psychologist
  59. Automatic Speech Recognition for Biomedical Data in Bengali Language
  60. Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization
  61. Enhanced Elephant Herding Optimization for Large Scale Information Access on Social Media
  62. miniCodeProps: a Minimal Benchmark for Proving Code Properties
  63. Initial Investigation of Kolmogorov-Arnold Networks (KANs) as Feature Extractors for IMU Based Human Activity Recognition
  64. AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology
  65. NovoBench: Benchmarking Deep Learning-based De Novo Peptide Sequencing Methods in Proteomics
  66. Grading Massive Open Online Courses Using Large Language Models
  67. InstructCMP: Length Control in Sentence Compression through Instruction-based Large Language Models
  68. The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models
  69. Guaranteed Sampling Flexibility for Low-tubal-rank Tensor Completion
  70. DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models
  71. Multiple Sources are Better Than One: Incorporating External Knowledge in Low-Resource Glossing
  72. GANmut: Generating and Modifying Facial Expressions
  73. Learning Relighting and Intrinsic Decomposition in Neural Radiance Fields
  74. Exploring the Limitations of Detecting Machine-Generated Text
  75. Fine-grained Classes and How to Find Them
  76. Parameter Blending for Multi-Camera Harmonization for Automotive Surround View Systems
  77. Can LLMs Understand the Implication of Emphasized Sentences in Dialogue?
  78. FastPoseCNN: Real-Time Monocular Category-Level Pose and Size Estimation Framework
  79. Advancing Solar Flare Prediction using Deep Learning with Active Region Patches
  80. Reconsidering Sentence-Level Sign Language Translation
  81. Leveraging Foundation Models for Multi-modal Federated Learning with Incomplete Modality
  82. Enhancing Supermarket Robot Interaction: A Multi-Level LLM Conversational Interface for Handling Diverse Customer Intents
  83. Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks
  84. Evaluating the Performance of Large Language Models via Debates
  85. HAIChart: Human and AI Paired Visualization System
  86. FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture
  87. Curating Stopwords in Marathi: A TF-IDF Approach for Improved Text Analysis and Information Retrieval
  88. Universal Cross-Lingual Text Classification
  89. Boosting Medical Image Classification with Segmentation Foundation Model
  90. Large Language Models for Dysfluency Detection in Stuttered Speech
  91. Physics-Informed Deep Learning and Partial Transfer Learning for Bearing Fault Diagnosis in the Presence of Highly Missing Data
  92. α-OCC: Uncertainty-Aware Camera-based 3D Semantic Occupancy Prediction
  93. Self-supervised Pretraining and Finetuning for Monocular Depth and Visual Odometry
  94. Latent Communication in Artificial Neural Networks
  95. Data Shapley in One Training Run
  96. WeShap: Weak Supervision Source Evaluation with Shapley Values
  97. SPEAR: Receiver-to-Receiver Acoustic Neural Warping Field
  98. 3D Gaze Tracking for Studying Collaborative Interactions in Mixed-Reality Environments
  99. Balancing Rigor and Utility: Mitigating Cognitive Biases in Large Language Models for Multiple-Choice Questions
  100. Two-level overlapping additive Schwarz preconditioner for training scientific machine learning applications
All 184
  1. CoSTA: Code-Switched Speech Translation using Aligned Speech-Text Interleaving
  2. Predicting the Understandability of Computational Notebooks through Code Metrics Analysis
  3. Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens
  4. Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings
  5. Promoting Data and Model Privacy in Federated Learning through Quantized LoRA
  6. Towards Supporting Legal Argumentation with NLP: Is More Data Really All You Need?
  7. ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts
  8. DocNet: Semantic Structure in Inductive Bias Detection Models
  9. Ontology Embedding: A Survey of Methods, Applications and Resources
  10. SynthTree: Co-supervised Local Model Synthesis for Explainable Prediction
  11. Open-Vocabulary X-ray Prohibited Item Detection via Fine-tuning CLIP
  12. ESCoT: Towards Interpretable Emotional Support Dialogue Systems
  13. Convergence Analysis for Entropy-Regularized Control Problems: A Probabilistic Approach
  14. City-LEO: Toward Transparent City Management Using LLM with End-to-End Optimization
  15. Robust Channel Learning for Large-Scale Radio Speaker Verification
  16. E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models
  17. Incorporating uncertainty quantification into travel mode choice modeling: a Bayesian neural network (BNN) approach and an uncertainty-guided active survey framework
  18. Rectified Iterative Disparity for Stereo Matching
  19. Effective Generative AI: The Human-Algorithm Centaur
  20. From Data Quality for AI to AI for Data Quality: A Systematic Review of Tools for AI-Augmented Data Quality Management in Data Warehouses
  21. Understanding Understanding: A Pragmatic Framework Motivated by Large Language Models
  22. Pick-or-Mix: Dynamic Channel Sampling for ConvNets
  23. Improving Adversarial Robustness via Decoupled Visual Representation Masking
  24. Make Your Home Safe: Time-aware Unsupervised User Behavior Anomaly Detection in Smart Homes via Loss-guided Mask
  25. Generating Tables from the Parametric Knowledge of Language Models
  26. Hamilton-Jacobi Based Policy-Iteration via Deep Operator Learning
  27. Multi-LLM QA with Embodied Exploration
  28. Bayesian Intervention Optimization for Causal Discovery
  29. First-Order Manifold Data Augmentation for Regression Learning
  30. Logit Separability-Driven Samples and Multiple Class-Related Words Selection for Advancing In-Context Learning
  31. SparseDet: A Simple and Effective Framework for Fully Sparse LiDAR-based 3D Object Detection
  32. Breaking the Attention Bottleneck
  33. New Solutions on LLM Acceleration, Optimization, and Application
  34. TrafficBots V1.5: Traffic Simulation via Conditional VAEs and Transformers with Relative Pose Encoding
  35. Development and Validation of Fully Automatic Deep Learning-Based Algorithms for Immunohistochemistry Reporting of Invasive Breast Ductal Carcinoma
  36. Noisy Annotations in Semantic Segmentation
  37. Imperceptible Face Forgery Attack via Adversarial Semantic Mask
  38. Distilling Opinions at Scale: Incremental Opinion Summarization using XL-OPSUMM
  39. On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions
  40. Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectives
  41. SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models
  42. Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals
  43. Demonstration Notebook: Finding the Most Suited In-Context Learning Example from Interactions
  44. Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for space-time solutions of semilinear partial differential equations
  45. Optimizing Automatic Speech Assessment: W-RankSim Regularization and Hybrid Feature Fusion Strategies
  46. COOL: Comprehensive Knowledge Enhanced Prompt Learning for Domain Adaptive Few-shot Fake News Detection
  47. Geometric Distortion Guided Transformer for Omnidirectional Image Super-Resolution
  48. Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts
  49. Geometric-informed GFlowNets for Structure-Based Drug Design
  50. Global-Local Graph Neural Networks for Node-Classification
  51. ALPS: An Auto-Labeling and Pre-training Scheme for Remote Sensing Segmentation With Segment Anything Model
  52. MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Images
  53. IG2: Integrated Gradient on Iterative Gradient Path for Feature Attribution
  54. Leading Whitespaces of Language Models' Subword Vocabulary Pose a Confound for Calculating Word Probabilities
  55. LAIP: Learning Local Alignment from Image-Phrase Modeling for Text-based Person Search
  56. Enriching the Machine Learning Workloads in BigBench
  57. Large Language Models for Automatic Milestone Detection in Group Discussions
  58. CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph
  59. A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery
  60. Design and Optimization of Hierarchical Gradient Coding for Distributed Learning at Edge Devices
  61. Algorithm Selection for Optimal Multi-Agent Path Finding via Graph Embedding
  62. Citation-Based Summarization of Landmark Judgments
  63. Iterated Schr"odinger bridge approximation to Wasserstein Gradient Flows
  64. Optimization of Armv9 architecture general large language model inference performance based on Llama.cpp
  65. On the Effectiveness of Supervision in Asymmetric Non-Contrastive Learning
  66. LLMFactor: Extracting Profitable Factors through Prompts for Explainable Stock Movement Prediction
  67. Post-hoc Utterance Refining Method by Entity Mining for Faithful Knowledge Grounded Conversations
  68. Bayesian Networks and Machine Learning for COVID-19 Severity Explanation and Demographic Symptom Classification
  69. ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language
  70. HiddenTables & PyQTax: A Cooperative Game and Dataset For TableQA to Ensure Scale and Data Privacy Across a Myriad of Taxonomies
  71. KGPA: Robustness Evaluation for Large Language Models via Cross-Domain Knowledge Graphs
  72. Saliency-guided and Patch-based Mixup for Long-tailed Skin Cancer Image Classification
  73. Federated Learning Optimization: A Comparative Study of Data and Model Exchange Strategies in Dynamic Networks
  74. STAR: Scale-wise Text-conditioned AutoRegressive image generation
  75. Ab Initio Structure Solutions from Nanocrystalline Powder Diffraction Data
  76. Learning Traffic Crashes as Language: Datasets, Benchmarks, and What-if Causal Analyses
  77. Evidential Uncertainty Sets in Deep Classifiers Using Conformal Prediction
  78. Evaluating LLMs with Multiple Problems at once
  79. ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation
  80. RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning
  81. A Rate-Distortion View of Uncertainty Quantification
  82. Quantifying Generative Media Bias with a Corpus of Real-world and Generated News Articles
  83. Predicting Exoplanetary Features with a Residual Model for Uniform and Gaussian Distributions
  84. GNOME: Generating Negotiations through Open-Domain Mapping of Exchanges