mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 15 Jun 2025

165 papers

  1. Implicit Reward as the Bridge: A Unified View of SFT and DPO ConnectionsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  2. STRuCT-LLM: Unifying Tabular and Graph Reasoning with Reinforcement Learning for Semantic ParsingLLM reasoning → Knowledge- and tool-augmented reasoning
  3. From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-Thought AlignmentLLM reasoning → Reasoning benchmarks and evaluation +1
  4. SlimRAG: Retrieval without Graphs via Entity-Aware Context SelectionRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  5. GTA: Grouped-head latenT AttentionEfficient LLM inference and serving → KV cache optimization
  6. The Safety Reminder: A Soft Prompt to Reactivate Delayed Safety Awareness in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  7. textttSPECS: Faster Test-Time Scaling through Speculative DraftsLLM reasoning → Test-time compute and efficient thinking
  8. Can LLMs Reconcile Knowledge Conflicts in Counterfactual ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  9. Improved Iterative Refinement for Chart-to-Code Generation via Structured InstructionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  10. The Synthetic Mirror -- Synthetic Data at the Age of Agentic AILLM agents and tool use → Agent threats, guardrails and governance
  11. SymRAG: Efficient Neuro-Symbolic Retrieval Through Adaptive Query RoutingRetrieval-augmented generation → RAG robustness and adaptive retrieval
  12. Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning SkillsLLM reasoning → Reasoning for agents, planning and code +1
  13. Domain Specific Benchmarks for Evaluating Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  14. HypER: Literature-grounded Hypothesis Generation and Distillation with ProvenanceLLM reasoning → Knowledge- and tool-augmented reasoning
  15. SoundMind: RL-Incentivized Logic Reasoning for Audio-Language ModelsLLM reasoning → Audio-language model reasoning
  16. Scaling Test-time Compute for LLM AgentsLLM reasoning → Test-time compute and efficient thinking +1
  17. Jailbreak Transferability Emerges from Shared RepresentationsLLM safety and security → Jailbreaking
  18. Logit Dynamics in Softmax Policy Gradient MethodsDeep reinforcement learning methods → RL theory and sample complexity
  19. SciDA: Scientific Dynamic Assessor of LLMsLLM reasoning → Reasoning benchmarks and evaluation
  20. Universal Jailbreak Suffixes Are Strong Attention HijackersLLM safety and security → Jailbreaking
  21. QFFT, Question-Free Fine-Tuning for Adaptive ReasoningLLM reasoning → Test-time compute and efficient thinking
  22. EraserDiT: Fast Video Inpainting with Diffusion Transformer ModelDiffusion models → 3D, point cloud and scene generation
  23. CAPO: Reinforcing Consistent Reasoning in Medical Decision-MakingLLM reasoning → Clinical and biomedical applications
  24. iDiT-HOI: Inpainting-based Hand Object Interaction Reenactment via Video Diffusion TransformerDiffusion models → Diffusion and flow policies for robotics
  25. WereWolf-Plus: An Update of Werewolf Game setting Based on DSGBenchLLM reasoning → Reasoning for agents, planning and code +1
  26. DiffS-NOCS: 3D Point Cloud Reconstruction through Coloring Sketches to NOCS Maps Using Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  27. LOP: Learning Optimal Pruning for Efficient On-Demand MLLMs ScalingMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  28. Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  29. TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization ModelsOffline RL and imitation learning from data → Offline RL algorithms +1
  30. Federated Neuroevolution O-RAN: Enhancing the Robustness of Deep Reinforcement Learning xAppsDeep reinforcement learning methods → RL for energy, networks and operations
  31. Flow-Based Policy for Online Reinforcement LearningDeep reinforcement learning methods → RL with diffusion and flow models
  32. Mastering Da Vinci Code: A Comparative Study of Transformer, LLM, and PPO-based AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  33. Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  34. Rethinking Hate Speech Detection on Social Media: Can LLMs Replace Traditional Models?LLM reasoning → Reasoning benchmarks and evaluation
  35. Revealing the Challenges of Sim-to-Real Transfer in Model-Based Reinforcement Learning via Latent Space ModelingDeep reinforcement learning methods → RL for robot locomotion and manipulation
  36. MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue ResolutionLLM reasoning → Reasoning for agents, planning and code
  37. Rethinking DPO: The Role of Rejected Responses in Preference MisalignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  38. SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model AccelerationVision-language-action models → Efficient VLA inference and adaptation +1
  39. Strategic Scaling of Test-Time Compute: A Bandit Learning ApproachLLM reasoning → Test-time compute and efficient thinking
  40. GM-LDM: Latent Diffusion Model for Brain Biomarker Identification through Functional Data-Driven Gray Matter SynthesisDiffusion models → Medical imaging and segmentation
  41. Multimodal Large Language Models-Enabled UAV Swarm: Towards Efficient and Intelligent Autonomous Aerial SystemsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  42. Serving Large Language Models on Huawei CloudMatrix384Mixture-of-experts → Efficient MoE training and inference systems
  43. SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt CompressionEfficient LLM inference and serving → Diffusion LLM and MoE inference +1
  44. NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  45. Flexible Realignment of Language ModelsLLM reasoning → Reasoning benchmarks and evaluation +1
  46. SciSage: A Multi-Agent Framework for High-Quality Scientific Survey GenerationLLM agents and tool use → Web, search, and research agents
  47. Alphabet Index Mapping: Jailbreaking LLMs through Semantic DissimilarityLLM safety and security → Jailbreaking
  48. Evaluating Cell Type Inference in Vision Language Models Under Varying Visual ContextMultimodal LLMs / vision-language models → Medical vision-language models
  49. Conditional Diffusion Model-Driven Generative Channels for Double RIS-Aided Wireless SystemsDiffusion models → Diffusion for compression and wireless
  50. 3D Hand Mesh-Guided AI-Generated Malformed Hand Refinement with Hand Pose Transformation via Diffusion ModelDiffusion models → Diffusion and flow policies for robotics
  51. Goal-based Self-Adaptive Generative Adversarial Imitation Learning (Goal-SAGAIL) for Multi-goal Robotic Manipulation TasksOffline RL and imitation learning from data → Imitation learning methods +1
  52. Building Trustworthy AI by Addressing its 16+2 Desiderata with Goal-Directed Commonsense ReasoningLLM reasoning → Reasoning for agents, planning and code
  53. Quantum Inspired Encoding Strategies for Machine Learning Models: Proposing and Evaluating Instance Level, Global Discrete, and Class Conditional Representations
  54. Data Normalization Strategies for EEG Deep Learning
  55. Digital Gatekeepers: Exploring Large Language Model's Role in Immigration Decisions
  56. Recommendation systems in e-commerce applications with machine learning methods
  57. ContextBench: Modifying Contexts for Targeted Latent Activation
  58. Hybrid Meta-Learning Framework for Anomaly Forecasting in Nonlinear Dynamical Systems via Physics-Inspired Simulation and Deep Ensembles
  59. Balancing Preservation and Modification: A Region and Semantic Aware Metric for Instruction-Based Image Editing
  60. The Reflexive Integrated Information Unit: A Differentiable Primitive for Artificial Consciousness
  61. MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios
  62. Structured Program Synthesis using LLMs: Results and Insights from the IPARC Challenge
  63. Reliable Noninvasive Glucose Sensing via CNN-Based Spectroscopy
  64. Latent Representation Learning of Multi-scale Thermophysics: Application to Dynamics in Shocked Porous Energetic Material
  65. Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates
  66. SmartHome-Bench: A Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Models
  67. Large Language Models Enhanced by Plug and Play Syntactic Knowledge for Aspect-based Sentiment Analysis
  68. Humans, Machine Learning, and Language Models in Union: A Cognitive Study on Table Unionability
  69. DuoFormer: Leveraging Hierarchical Representations by Local and Global Attention Vision Transformer
  70. Boundary-Aware Vision Transformer for Angiography Vascular Network Segmentation
  71. Multi-document Summarization through Multi-document Event Relation Graph Reasoning in LLMs: a case study in Framing Bias Mitigation
  72. Assessing the Role of Data Quality in Training Bilingual Language Models
  73. Distributional Training Data Attribution: What do Influence Functions Sample?
  74. Forecasting Time Series with LLMs via Patch-Based Prompting and Decomposition
  75. Constitutive Components for Human-Like Autonomous Artificial Intelligence
  76. eLog analysis for accelerators: status and future outlook
  77. Metropolis-Hastings Sampling for 3D Gaussian Reconstruction
  78. Unsupervised risk factor identification across cancer types and data modalities via explainable artificial intelligence
  79. CliniDial: A Naturally Occurring Multimodal Dialogue Dataset for Team Reflection in Action During Clinical Operation
  80. Complexity Scaling Laws for Neural Models using Combinatorial Optimization
  81. Sectoral Coupling in Linguistic State Space
  82. Identifying and Investigating Global News Coverage of Critical Events Such as Disasters and Terrorist Attacks
  83. PINNs Algorithmic Framework for Simulation of Nonlinear Burgers' Type Models
  84. PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization
  85. Constraint-Guided Prediction Refinement via Deterministic Diffusion Trajectories
  86. Variational Learning Finds Flatter Solutions at the Edge of Stability
  87. KCLNet: Physics-Informed Power Flow Prediction via Constraints Projections
  88. JEBS: A Fine-grained Biomedical Lexical Simplification Task
  89. Structure-Preserving Patch Decoding for Efficient Neural Video Representation
  90. Assessing the Performance Gap Between Lexical and Semantic Models for Information Retrieval With Formulaic Legal Language
  91. Homeostatic Coupling for Prosocial Behavior
  92. Evolutionary Developmental Biology Can Serve as the Conceptual Foundation for a New Design Paradigm in Artificial Intelligence
  93. ArgHiTZ at ArchEHR-QA 2025: A Two-Step Divide and Conquer Approach to Patient Question Answering for Top Factuality
  94. T3S: Think in Thermal Time for Generalizable Crop Mapping from Satellite Image Time Series
  95. Exploring the Potential of Metacognitive Support Agents for Human-AI Co-Creation
  96. Silhouette-Driven Instance-Weighted k-means
  97. MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs
  98. Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs
  99. Active Adversarial Noise Suppression for Image Forgery Localization
  100. Private List Learnability vs. Online List Learnability
All 165
  1. KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills
  2. Towards Fine-Grained Emotion Understanding via Skeleton-Based Micro-Gesture Recognition
  3. VFEFL: Privacy-Preserving Federated Learning against Malicious Clients via Verifiable Functional Encryption
  4. Transforming Chatbot Text: A Sequence-to-Sequence Approach
  5. Uncovering Social Network Activity Using Joint User and Topic Interaction
  6. Fair Bayesian Model-Based Clustering
  7. HyRet-Change: A hybrid retentive network for remote sensing change detection
  8. Synesthesia of Machines (SoM)-Enhanced Sub-THz ISAC Transmission for Air-Ground Network
  9. ComplexBench-Edit: Benchmarking Complex Instruction-Driven Image Editing via Compositional Dependencies
  10. General and Estimable Learning Bound Unifying Covariate and Concept Shifts
  11. Rethinking Optimization: A Systems-Based Approach to Social Externalities
  12. Learning Unpaired Image Dehazing with Physics-based Rehazy Generation
  13. Medical Argument Mining: Exploitation of Scarce Data Using NLI Systems
  14. PDCNet: a benchmark and general deep learning framework for activity prediction of peptide-drug conjugates
  15. Nonlinear Model Order Reduction of Dynamical Systems in Process Engineering: Review and Comparison
  16. Taking the GP Out of the Loop
  17. Lyapunov Learning at the Onset of Chaos
  18. A Review of the Long Horizon Forecasting Problem in Time Series Analysis
  19. Leveraging MIMIC Datasets for Better Digital Health: A Review on Open Problems, Progress Highlights, and Future Promises
  20. Fuzzy Propositional Formulas under the Stable Model Semantics
  21. MetaEformer: Unveiling and Leveraging Meta-patterns for Complex and Dynamic Systems Load Forecasting
  22. Predicting Genetic Mutations from Single-Cell Bone Marrow Images in Acute Myeloid Leukemia Using Noise-Robust Deep Learning Models
  23. Surprise Calibration for Better In-Context Learning
  24. Resilient-native and Intelligent NextG Systems
  25. SMPL Normal Map Is All You Need for Single-view Textured Human Reconstruction
  26. PDEfuncta: Spectrally-Aware Neural Representation for PDE Solution Modeling
  27. Rasterizing Wireless Radiance Field via Deformable 2D Gaussian Splatting
  28. Semantic-Aware Visual Information Transmission With Key Information Extraction Over Wireless Networks
  29. LPMLN, Weak Constraints, and P-log
  30. A large-scale, physically-based synthetic dataset for satellite pose estimation
  31. Unconstrained Robust Online Convex Optimization
  32. From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots
  33. Scene-aware SAR ship detection guided by unsupervised sea-land segmentation
  34. Solving tricky quantum optics problems with assistance from (artificial) intelligence
  35. RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control
  36. Probing Deep into Temporal Profile Makes the Infrared Small Target Detector Much Better
  37. Base3: a simple interpolation-based ensemble method for robust dynamic link prediction
  38. On-board Sonar Data Classification for Path Following in Underwater Vehicles using Fast Interval Type-2 Fuzzy Extreme Learning Machine
  39. Democratic or Authoritarian? Probing a New Dimension of Political Biases in Large Language Models
  40. Hierarchical Group-wise Ranking Framework for Recommendation Models
  41. AFBS:Buffer Gradient Selection in Semi-asynchronous Federated Learning
  42. Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functions
  43. Free Privacy Protection for Wireless Federated Learning: Enjoy It or Suffer from It?
  44. Unleashing Diffusion and State Space Models for Medical Image Segmentation
  45. Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution
  46. Cross-architecture universal feature coding via distribution alignment
  47. Learning to Fuse: Modality-Aware Adaptive Scheduling for Robust Multimodal Foundation Models
  48. On the attainment of the Wasserstein--Cramer--Rao lower bound
  49. Decentralized Decision Making in Two Sided Manufacturing-as-a-Service Marketplaces
  50. Efficient multi-view training for 3D Gaussian Splatting
  51. Dynamic Modality Scheduling for Multimodal Large Models via Confidence, Uncertainty, and Semantic Consistency
  52. Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors
  53. Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?
  54. Combining Self-attention and Dilation Convolutional for Semantic Segmentation of Coal Maceral Groups
  55. Effect Decomposition of Functional-Output Computer Experiments via Orthogonal Additive Gaussian Processes
  56. Large Scalable Cross-Domain Graph Neural Networks for Personalized Notification at LinkedIn
  57. Unsupervised Contrastive Learning Using Out-Of-Distribution Data for Long-Tailed Dataset
  58. MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detection
  59. TFKAN: Time-Frequency KAN for Long-Term Time Series Forecasting
  60. Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework
  61. Get on the Train or be Left on the Station: Using LLMs for Software Engineering Research
  62. Adapting by Analogy: OOD Generalization of Visuomotor Policies via Functional Correspondence
  63. Dependent Randomized Rounding for Budget Constrained Experimental Design
  64. Enhancing Clinical Models with Pseudo Data for De-identification
  65. SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition