mlsanityData to 7 Oct 2026

Papers

New on arXiv

Mon 21 Apr 2025

270 papers

  1. Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive ModelsLLM safety and security → Jailbreaking
  2. RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target OptimizationLLM safety and security → Jailbreaking
  4. Backdoor Defense in Diffusion Models via Spatial Attention UnlearningDiffusion models → Robustness, privacy and adversarial aspects +1
  5. Multimodal Large Language Models for Enhanced Traffic Safety: A Comprehensive Review and Future TrendsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  6. MARFT: Multi-Agent Reinforcement Fine-TuningLLM agents and tool use → Reinforcement learning for LLM agents
  7. CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object CountingLLM reasoning → Spatial and embodied reasoning +1
  8. In-context Ranking Preference OptimizationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  9. Speculative Sampling via Exponential RacesEfficient LLM inference and serving → Speculative decoding
  10. Agent for User: Testing Multi-User Interactive Features in TikTokLLM agents and tool use → GUI and mobile agents
  11. Emergence and Evolution of Interpretable Concepts in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  12. LAPP: Large Language Model Feedback for Preference-Driven Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  13. Learning Adaptive Parallel Reasoning with Language ModelsLLM reasoning → Test-time compute and efficient thinking
  14. IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMsLLM reasoning → Multimodal reasoning +1
  15. MirrorVerse: Pushing Diffusion Models to Realistically Reflect the WorldDiffusion models → 3D, point cloud and scene generation
  16. KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained EnvironmentsEfficient LLM inference and serving → KV cache optimization
  17. LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 PerceptionLLM reasoning → Multimodal reasoning
  18. Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  19. VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  20. Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  21. Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  22. An LMM for Efficient Video Understanding via Reinforced Compression of Video CubesMultimodal LLMs / vision-language models → Video understanding with MLLMs
  23. Interpretable Locomotion Prediction in Construction Using a Memory-Driven LLM Agent With Chain-of-Thought ReasoningLLM reasoning → Spatial and embodied reasoning +1
  24. Bringing Diversity from Diffusion Models to Semantic-Guided Face Asset GenerationDiffusion models → Image generation, text-to-image and editing
  25. Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling EvaluatorsLLM reasoning → Reasoning benchmarks and evaluation +1
  26. MrGuard: A Multilingual Reasoning Guardrail for Universal LLM SafetyLLM reasoning → Reasoning for agents, planning and code +1
  27. A Self-Improving Coding AgentLLM agents and tool use → Software engineering coding agents +1
  28. DRAGON: Distributional Rewards Optimize Diffusion Generative ModelsDiffusion models → Diffusion and flow policies for robotics +1
  29. Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLMsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  30. Support Evaluation for the TREC 2024 RAG Track: Comparing Human versus LLM JudgesRetrieval-augmented generation → RAG pipeline design and evaluation
  31. Synergistic Weak-Strong Collaboration by Aligning PreferencesLLM reasoning → Test-time compute and efficient thinking +1
  32. DSPO: Direct Semantic Preference Optimization for Real-World Image Super-ResolutionDiffusion models → Diffusion and flow policies for robotics +1
  33. Automatic Generation of Aerobatic Flight in Complex Environments via Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  34. Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose EstimationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  35. Rethinking the Potential of Multimodality in Collaborative Problem Solving Diagnosis with Large Language ModelsLLM reasoning → Multimodal reasoning
  36. Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQLLLM reasoning → Knowledge- and tool-augmented reasoning
  37. The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
  38. Structure-guided Diffusion Transformer for Low-Light Image EnhancementDiffusion models → Inverse problems and image restoration
  39. RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity SearchLLM safety and security → Prompt injection and agent security
  40. Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language SupervisionOffline RL and imitation learning from data → Decision transformers and sequence modeling
  41. Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New RecipesLLM reasoning → Spatial and embodied reasoning +1
  42. SOLIDO: A Robust Watermarking Method for Speech Synthesis via Low-Rank AdaptationDiffusion models → Robustness, privacy and adversarial aspects
  43. Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  44. Efficient Pretraining Length ScalingEfficient LLM inference and serving → Early exit and edge inference
  45. Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive EvaluationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  46. aiXamine: Simplified LLM Safety and SecurityLLM safety and security → Safety alignment, refusal and guardrails
  47. MoE Parallel Folding: Heterogeneous Parallelism Mappings for Efficient Large-Scale MoE Model Training with Megatron CoreMixture-of-experts → Efficient MoE training and inference systems
  48. PIV-FlowDiffuser:Transfer-learning-based denoising diffusion models for PIVDiffusion models → Flow matching, time series and science
  49. Learning to Reason under Off-Policy GuidanceLLM reasoning → Reinforcement learning for reasoning
  50. WindVE: Collaborative CPU-NPU Vector EmbeddingRetrieval-augmented generation → RAG pipeline design and evaluation
  51. TWIG: Two-Step Image Generation using Segmentation Masks in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  52. EducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue FrameworkLLM agents and tool use → Educational agents and math problem solving
  53. POLYRAG: Integrating Polyviews into Retrieval-Augmented Generation for Medical ApplicationsLLM reasoning → Clinical and biomedical applications +1
  54. CRAVE: A Conflicting Reasoning Approach for Explainable Claim Verification Using LLMsLLM reasoning → Reasoning benchmarks and evaluation
  55. Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive SurveyRetrieval-augmented generation → RAG pipeline design and evaluation
  56. Efficient Function Orchestration for Large Language ModelsLLM agents and tool use → Tool learning and function calling
  57. Acting Less is Reasoning More! Teaching Model to Act EfficientlyLLM reasoning → Reasoning for agents, planning and code +1
  58. Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and OptimizationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  59. Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy CitationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  60. Object-Level Verbalized Confidence Calibration in Vision-Language Models via Semantic PerturbationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  61. Establishing Reliability Metrics for Reward Models in Large Language ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  62. Completing A Systematic Review in Hours instead of Months with Interactive AI AgentsLLM agents and tool use → Web, search, and research agents
  63. What Lurks Within? Concept Auditing for Shared Diffusion Models at ScaleDiffusion models → Robustness, privacy and adversarial aspects
  64. On Self-improving Token EmbeddingsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  65. RUB: Evaluating Residual Knowledge in Unlearned ModelsLLM safety and security → Machine unlearning
  66. Novel Concept-Oriented Synthetic Data approach for Training Generative AI-Driven Crystal Grain Analysis Using Diffusion ModelDiffusion models → Flow matching, time series and science
  67. gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token ThrottlingEfficient LLM inference and serving → Serving systems and request scheduling
  68. PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning CapabilitiesLLM agents and tool use → General LLM agent frameworks and benchmarks
  69. Developing a Dyslexia Indicator Using Eye Tracking
  70. Advancing AI-assisted Hardware Design with Hierarchical Decentralized Training and Personalized Inference-Time Optimization
  71. A comprehensive survey of cybercrimes in India over the last decade
  72. From Dialect Gaps to Identity Maps: Tackling Variability in Speaker Verification
  73. Ultra-Low-Power Spiking Neurons in 7 nm FinFET Technology: A Comparative Analysis of Leaky Integrate-and-Fire, Morris-Lecar, and Axon-Hillock Architectures
  74. Splitwiser: Efficient LM inference with constrained resources
  75. The AI Co-Ethnographer: How Far Can Automation Take Qualitative Research?
  76. HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization
  77. ViQA-COVID: COVID-19 Machine Reading Comprehension Dataset for Vietnamese
  78. Nested Named-Entity Recognition on Vietnamese COVID-19: Dataset and Experiments
  79. Feature Selection via GANs (GANFS): Enhancing Machine Learning Models for DDoS Mitigation
  80. Fuzzy Logic -- Based Scheduling System for Part-Time Workforce
  81. Spectral Dictionary Learning for Generative Image Modeling
  82. Intrinsic Barriers to Explaining Deep Foundation Models
  83. Trends in Frontier AI Model Count: A Forecast to 2028
  84. Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark
  85. Active Learning Methods for Efficient Data Utilization and Model Performance Enhancement
  86. A Conceptual Framework for AI-based Decision Systems in Critical Infrastructures
  87. Efficacy of a Computer Tutor that Models Expert Human Tutors
  88. Introduction to Quantum Machine Learning and Quantum Architecture Search
  89. A Self-supervised Learning Method for Raman Spectroscopy based on Masked Autoencoders
  90. Hybrid Knowledge Transfer through Attention and Logit Distillation for On-Device Vision Systems in Agricultural IoT
  91. MonoTher-Depth: Enhancing Thermal Depth Estimation via Confidence-Aware Distillation
  92. Application of Deep Generative Models for Anomaly Detection in Complex Financial Transactions
  93. Fourier analysis of the physics of transfer learning for data-driven subgrid-scale models of ocean turbulence
  94. Split-quaternions for perceptual white balance
  95. Unifying Image Counterfactuals and Feature Attributions with Latent-Space Adversarial Attacks
  96. Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models
  97. Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images
  98. LithOS: An Operating System for Efficient Machine Learning on GPUs
  99. Compton Form Factor Extraction using Quantum Deep Neural Networks
  100. Improving Human-AI Coordination through Online Adversarial Training and Generative Models
All 270
  1. Visualizing Public Opinion on X: A Real-Time Sentiment Dashboard Using VADER and DistilBERT
  2. Demand for LLMs: Descriptive Evidence on Substitution, Market Expansion, and Multihoming
  3. Combating Toxic Language: A Review of LLM-Based Strategies for Software Engineering
  4. AGI Is Coming... Right After AI Learns to Play Wordle
  5. Feeding LLM Annotations to BERT Classifiers at Your Own Risk
  6. Trillion 7B Technical Report
  7. Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL
  8. LLM-Assisted Translation of Legacy FORTRAN Codes to C++: A Cross-Platform Study
  9. On the Boolean Network Theory of Datalog^neg
  10. Post-Convergence Sim-to-Real Policy Transfer: A Principled Alternative to Cherry-Picking
  11. Context Aware Grounded Teacher for Source Free Object Detection
  12. Improving Learning to Optimize Using Parameter Symmetries
  13. Tell Me What You Know About Sexism: Expert-LLM Interaction Strategies and Co-Created Definitions for Zero-Shot Sexism Detection
  14. Deep learning with missing data
  15. Assessing Surrogate Heterogeneity in Real World Data Using Meta-Learners
  16. ICGM-FRAX: Iterative Cross Graph Matching for Hip Fracture Risk Assessment using Dual-energy X-ray Absorptiometry Images
  17. Plug-and-Play Versatile Compressed Video Enhancement
  18. Physics Driven Image Simulation from Commercial Satellite Imagery
  19. Towards Understanding Camera Motions in Any Video
  20. FLARE: Feature-based Lightweight Aggregation for Robust Evaluation of IoT Intrusion Detection
  21. Event2Vec: Processing Neuromorphic Events Directly by Representations in Vector Space
  22. Transferable Learning of Reaction Pathways from Geometric Priors
  23. Solving New Tasks by Adapting Internet Video Knowledge
  24. FedFetch: Faster Federated Learning with Adaptive Downstream Prefetching
  25. Reliable Classification with Conformal Learning and Interval-Type 2 Fuzzy Sets
  26. Exploring Compositional Generalization (in COGS/ReCOGS_pos) by Transformers using Restricted Access Sequence Processing (RASP)
  27. Med-CoDE: Medical Critique based Disagreement Evaluation Framework
  28. Vision6D: 3D-to-2D Interactive Visualization and Annotation Tool for 6D Pose Estimation
  29. Bayesian Federated Learning for Continual Training
  30. Advancing Embodied Intelligence in Robotic-Assisted Endovascular Procedures: A Systematic Review of AI Solutions
  31. Significativity Indices for Agreement Values
  32. A Graph Based Raman Spectral Processing Technique for Exosome Classification
  33. HyperFlow: Gradient-Free Emulation of Few-Shot Fine-Tuning
  34. How to systematically develop an effective AI-based bias correction model?
  35. StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussians
  36. DRAWER: Digital Reconstruction and Articulation With Environment Realism
  37. Diffusion Bridge Models for 3D Medical Image Translation
  38. Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction
  39. Revealing the 3D Cosmic Web through Gravitationally Constrained Neural Fields
  40. Leveraging Language Models for Automated Patient Record Linkage
  41. FlowReasoner: Reinforcing Query-Level Meta-Agents
  42. CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilation
  43. SuoiAI: Building a Dataset for Aquatic Invertebrates in Vietnam
  44. On Learning Parallel Pancakes with Mostly Uniform Weights
  45. Faster Algorithms for Agnostically Learning Disjunctions and their Implications
  46. Single-loop Algorithms for Stochastic Non-convex Optimization with Weakly-Convex Constraints
  47. Conformalized-KANs: Uncertainty Quantification with Coverage Guarantees for Kolmogorov-Arnold Networks (KANs) in Scientific Machine Learning
  48. Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions
  49. Shape-Guided Clothing Warping for Virtual Try-On
  50. A Genetic Fuzzy-Enabled Framework on Robotic Manipulation for In-Space Servicing
  51. M2AD: Multi-Sensor Multi-System Anomaly Detection through Global Scoring and Calibrated Thresholding
  52. A Deep Learning Framework for Sequence Mining with Bidirectional LSTM and Multi-Scale Attention
  53. Fully Bayesian Approaches to Topics over Time
  54. EvalAgent: Discovering Implicit Evaluation Criteria from the Web
  55. Histogram-based Parameter-efficient Tuning for Passive and Active Sonar Classification
  56. Embracing Ambiguity: Bayesian Nonparametrics and Stakeholder Participation for Ambiguity-Aware Safety Evaluation
  57. A Causal Convolutional Low-rank Representation Model for Imputation of Water Quality Data
  58. Compute-Optimal LLMs Provably Generalize Better With Scale
  59. How Global Calibration Strengthens Multiaccuracy
  60. Zero-Shot, But at What Cost? Unveiling the Hidden Overhead of MILS's LLM-CLIP Framework for Image Captioning
  61. Automated Measurement of Eczema Severity with Self-Supervised Learning
  62. Breast density in MRI: an AI-based quantification and relationship to assessment in mammography
  63. Tiger200K: Manually Curated High Visual Quality Video Dataset from UGC Platform
  64. Mapping Industry Practices to the EU AI Act's GPAI Code of Practice Safety and Security Measures
  65. FaceCraft4D: Animated 3D Facial Avatar Generation from a Single Image
  66. Audio-Visual Class-Incremental Learning for Fish Feeding intensity Assessment in Aquaculture
  67. HSANET: A Hybrid Self-Cross Attention Network For Remote Sensing Change Detection
  68. On true empty category
  69. An Efficient Aerial Image Detection with Variable Receptive Fields
  70. Survey of Loss Augmented Knowledge Tracing
  71. The Synthetic Imputation Approach: Generating Optimal Synthetic Texts For Underrepresented Categories In Supervised Classification Tasks
  72. Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration
  73. Advanced posterior analyses of hidden Markov models: finite Markov chain imbedding and hybrid decoding
  74. Dynamic 3D KAN Convolution with Adaptive Grid Optimization for Hyperspectral Image Classification
  75. Landmark-Free Preoperative-to-Intraoperative Registration in Laparoscopic Liver Resection
  76. Behavioral Universe Network (BUN): A Behavioral Information-Based Framework for Complex Systems
  77. "I Know It When I See It": Mood Spaces for Connecting and Expressing Visual Concepts
  78. C2RUST-BENCH: A Minimized, Representative Dataset for C-to-Rust Transpilation Evaluation
  79. KGMEL: Knowledge Graph-Enhanced Multimodal Entity Linking
  80. EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models
  81. Neural ATTF: A Scalable Solution to Lifelong Multi-Agent Path Planning
  82. Towards Task-Oriented Flying: Framework, Infrastructure, and Principles
  83. Contemplative Artificial Intelligence
  84. MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video
  85. Robust and Real-time Surface Normal Estimation from Stereo Disparities using Affine Transformations
  86. Kuwain 1.5B: An Arabic SLM via Language Injection
  87. Improving Sound Source Localization with Joint Slot Attention on Image and Audio
  88. Approximation Rates in Besov Norms and Sample-Complexity of Kolmogorov-Arnold Networks with Residual Connections
  89. Unwarping Screen Content Images via Structure-texture Enhancement Network and Transformation Self-estimation
  90. A triple-branch network for latent fingerprint enhancement guided by orientation fields and minutiae
  91. NeuGaze: Reshaping the future BCI
  92. Application of Sensitivity Analysis Methods for Studying Neural Network Models
  93. Fast-Slow Co-advancing Optimizer: Toward Harmonious Adversarial Training of GAN
  94. VistaDepth: Improving far-range Depth Estimation with Spectral Modulation and Adaptive Reweighting
  95. Federated Latent Factor Model for Bias-Aware Recommendation with Privacy-Preserving
  96. Cognitive-Inspired Hierarchical Attention Fusion With Visual and Textual for Cross-Domain Sequential Recommendation
  97. Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLMs
  98. Mitigating Degree Bias in Graph Representation Learning with Learnable Structural Augmentation and Structural Self-Attention
  99. Rhythm of Opinion: A Hawkes-Graph Framework for Dynamic Propagation Analysis
  100. Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music Modeling
  101. Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides
  102. Mining Characteristics of Vulnerable Smart Contracts Across Lifecycle Stages
  103. OPO: Making Decision-Focused Data Acquisition Decisions
  104. Testing LLMs' Capabilities in Annotating Translations Based on an Error Typology Designed for LSP Translation: First Experiments with ChatGPT
  105. VeLU: Variance-enhanced Learning Unit for Deep Neural Networks
  106. ScanEdit: Hierarchically-Guided Functional 3D Scan Editing
  107. Beyond Terabit/s Integrated Neuromorphic Photonic Processor for DSP-Free Optical Interconnects
  108. Distribution-aware Forgetting Compensation for Exemplar-Free Lifelong Person Re-identification
  109. DyST-XL: Dynamic Layout Planning and Content Control for Compositional Text-to-Video Generation
  110. A Controllable Appearance Representation for Flexible Transfer and Editing
  111. DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models
  112. LLMs as Data Annotators: How Close Are We to Human Performance
  113. Is Intelligence the Right Direction in New OS Scheduling for Multiple Resources in Cloud Environments?
  114. Stay Hungry, Stay Foolish: On the Extended Reading Articles Generation with LLMs
  115. Insert Anything: Image Insertion via In-Context Editing in DiT
  116. Shifts in Doctors' Eye Movements Between Real and AI-Generated Medical Images
  117. NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: KwaiSR Dataset and Study
  118. Trainable Quantum Neural Network for Multiclass Image Classification with the Power of Pre-trained Tree Tensor Networks
  119. Learning Compositional Transferability of Time Series for Source-Free Domain Adaptation
  120. RealisDance-DiT: Simple yet Strong Baseline towards Controllable Character Animation in the Wild
  121. Cyc3D: Fine-grained Controllable 3D Generation via Cycle Consistency Regularization
  122. Evaluating LLMs on Chinese Topic Constructions: A Research Proposal Inspired by Tian et al. (2024)
  123. 3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations
  124. Evaluating Code Generation of LLMs in Advanced Computer Science Problems
  125. Speaker Fuzzy Fingerprints: Benchmarking Text-Based Identification in Multiparty Dialogues
  126. Efficient Document Retrieval with G-Retriever
  127. AGI-Driven Generative Semantic Communications: Principles and Practices
  128. Symmetry-Preserving Architecture for Multi-NUMA Environments (SPANE): A Deep Reinforcement Learning Approach for Dynamic VM Scheduling
  129. Integrating Response Time and Attention Duration in Bayesian Preference Learning for Multiple Criteria Decision Aiding
  130. Causal DAG Summarization (Full Version)
  131. Giving AI a voice: how does AI think it should be treated?
  132. Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos
  133. DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding
  134. GenCLIP: Generalizing CLIP Prompts for Zero-shot Anomaly Detection
  135. StableQuant: Layer Adaptive Post-Training Quantization for Speech Foundation Models
  136. Guidelines for External Disturbance Factors in the Use of OCR in Real-World Environments
  137. Dynamic Graph-Like Learning with Contrastive Clustering on Temporally-Factored Ship Motion Data for Imbalanced Sea State Estimation in Autonomous Vessel
  138. OmniAudio: Generating Spatial Audio from 360-Degree Video
  139. VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform
  140. Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation
  141. Expected Free Energy-based Planning as Variational Inference
  142. Latent Bayesian Optimization via Autoregressive Normalizing Flows
  143. WMKA-Net: A Weighted Multi-Kernel Attention Network for Retinal Vessel Segmentation
  144. Memory-Augmented Dual-Decoder Networks for Multi-Class Unsupervised Anomaly Detection
  145. Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness
  146. Impact of Latent Space Dimension on IoT Botnet Detection Performance: VAE-Encoder Versus ViT-Encoder
  147. Collaborative Enhancement Network for Low-quality Multi-spectral Vehicle Re-identification
  148. ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams
  149. Natural Fingerprints of Large Language Models
  150. Twin Co-Adaptive Dialogue for Progressive Image Generation
  151. Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer
  152. Uncertainty quantification of neural network models of evolving processes via Langevin sampling
  153. Reliable Multi-Modal Object Re-Identification via Modality-Aware Graph Reasoning
  154. Exploring ℓ0 Sparsification for Inference-free Sparse Retrievers
  155. Protecting Your Voice: Temporal-aware Robust Watermarking
  156. Distribution-aware Dataset Distillation for Efficient Image Restoration
  157. ECViT: Efficient Convolutional Vision Transformer with Local-Attention and Multi-scale Stages
  158. A Diagnostic Evaluation of Neural Networks Trained with the Error Diffusion Learning Algorithm
  159. DONOD: Efficient and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Dataset Pruning
  160. Real-Time Sleepiness Detection for Driver State Monitoring System
  161. Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment
  162. Automatic Evaluation Metrics for Document-level Translation: Overview, Challenges and Trends
  163. A Survey on Small Sample Imbalance Problem: Metrics, Feature Analysis, and Solutions
  164. Automated Duplicate Bug Report Detection in Large Open Bug Repositories
  165. Edge-boosted graph learning for functional brain connectivity analysis
  166. A Bayesian Approach to Segmentation with Noisy Labels via Spatially Correlated Distributions
  167. Enhanced Data-driven Topology Design Methodology with Multi-level Mesh and Correlation-based Mutation for Stress-related Multi-objective Optimization
  168. DC4CR: When Cloud Removal Meets Diffusion Control in Remote Sensing
  169. How Effective Can Dropout Be in Multiple Instance Learning ?
  170. Exploring Collaborative GenAI Agents in Synchronous Group Settings: Eliciting Team Perceptions and Design Considerations for the Future of Work