mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 23 Sep 2024

322 papers

  1. From Commands to Prompts: LLM-based Semantic File System for AIOSLLM agents and tool use → General LLM agent frameworks and benchmarks
  2. Lost in the Logic: An Evaluation of Large Language Models' Reasoning Capabilities on LSAT Logic GamesLLM reasoning → Reasoning benchmarks and evaluation
  3. Fine Tuning Text-to-Image Diffusion Models for Correcting Anomalous ImagesDiffusion models → Image generation, text-to-image and editing
  4. Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  5. Clinical-grade Multi-Organ Pathology Report Generation for Multi-scale Whole Slide Images via a Semantically Guided Medical Text Foundation ModelMultimodal LLMs / vision-language models → Medical vision-language models
  6. GEM-RAG: Graphical Eigen Memories For Retrieval Augmented GenerationRetrieval-augmented generation → Conversational and speech RAG
  7. Mixture of Efficient Diffusion Experts Through Automatic Interval and Sub-Network SelectionDiffusion models → Diffusion foundations and sampling
  8. Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error CorrectionLLM reasoning → Audio-language model reasoning
  9. Learning Diverse Robot Striking Motions with Diffusion Models and Kinematically Constrained Gradient GuidanceDiffusion models → Diffusion and flow policies for robotics +1
  10. Speech2rtMRI: Speech-Guided Diffusion Model for Real-time MRI Video of the Vocal Tract during SpeechDiffusion models → Audio, speech and music
  11. CANDERE-COACH: Reinforcement Learning from Noisy FeedbackOffline RL and imitation learning from data → Imitation learning methods +1
  12. Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QARetrieval-augmented generation → Conversational and speech RAG
  13. Bayesian computation with generative diffusion models by Multilevel Monte CarloDiffusion models → Inverse problems and image restoration
  14. VLMine: Long-Tail Data Mining with Vision Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  15. MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation modelsMultimodal LLMs / vision-language models → Medical vision-language models
  16. RAM2C: A Liberal Arts Educational Chatbot based on Retrieval-augmented Multi-role Multi-expert CollaborationRetrieval-augmented generation → Agentic RAG, agents and memory
  17. In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  18. Tag Map: A Text-Based Map for Spatial Reasoning and Navigation with Large Language ModelsLLM reasoning → Spatial and embodied reasoning
  19. Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAILLM safety and security → Prompt injection and agent security
  20. Parse Trees Guided LLM Prompt CompressionEfficient LLM inference and serving → Prompt and context compression
  21. MaterialFusion: Enhancing Inverse Rendering with Material Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
  22. OmniBench: Towards The Future of Universal Omni-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  23. Style Outweighs Substance: Failure Modes of LLM Judges in Alignment BenchmarkingLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  24. Generative AI Is Not Ready for Clinical Use in Patient Education for Lower Back Pain Patients, Even With Retrieval-Augmented GenerationRetrieval-augmented generation → Medical and biomedical RAG
  25. StarVid: Enhancing Semantic Alignment in Video Diffusion Models via Spatial and SynTactic Guided Attention RefocusingDiffusion models → Video generation
  26. Behavioral Bias of Vision-Language Models: A Behavioral Finance ViewMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  27. Intelligent Routing Algorithm over SDN: Reusable Reinforcement Learning ApproachDeep reinforcement learning methods → RL for energy, networks and operations
  28. A Gated Residual Kolmogorov-Arnold Networks for Mixtures of ExpertsMixture-of-experts → MoE theory and gating functions
  29. LoVA: Long-form Video-to-Audio GenerationDiffusion models → Audio, speech and music
  30. Rethinking Conventional Wisdom in Machine Learning: From Generalization to ScalingLLM reasoning → Reasoning benchmarks and evaluation
  31. RMCBench: Benchmarking Large Language Models' Resistance to Malicious CodeLLM safety and security → Jailbreaking
  32. COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language ModelsLLM reasoning → Spatial and embodied reasoning
  33. Controllable Traffic Simulation through LLM-Guided Hierarchical Reasoning and RefinementLLM reasoning → Chain-of-thought reasoning for driving
  34. Detect, Describe, Discriminate: Moving Beyond VQA for MLLM EvaluationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  35. Inferring Scientific Cross-Document Coreference and Hierarchy with Definition-Augmented Relational ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  36. SPformer: A Transformer Based DRL Decision Making Method for Connected Automated VehiclesDeep reinforcement learning methods → RL for autonomous driving and traffic
  37. Enhancing Scientific Reproducibility Through Automated BioCompute Object Creation Using Retrieval-Augmented Generation from PublicationsRetrieval-augmented generation → Medical and biomedical RAG
  38. SHFL: Secure Hierarchical Federated Learning Framework for Edge NetworksLLM safety and security → Federated unlearning and poisoning
  39. A Diagonal Structured State Space Model on Loihi 2 for Efficient Streaming Sequence ProcessingState-space sequence models (S4, Mamba) → Core SSM architectures for language
  40. Evaluating Synthetic Activations composed of SAE Latents in GPT-2Mechanistic interpretability → Sparse autoencoder training and evaluation
  41. Inference-Friendly Models With MixAttentionEfficient LLM inference and serving → KV cache optimization
  42. DepthART: Monocular Depth Estimation as Autoregressive Refinement TaskDiffusion models → 3D, point cloud and scene generation
  43. Multi-modal Generative AI: Multi-modal LLMs, Diffusions, and the UnificationMultimodal LLMs / vision-language models → Image editing and quality assessment +2
  44. Deep Reinforcement Learning-based Obstacle Avoidance for Robot Movement in Warehouse EnvironmentsDeep reinforcement learning methods → RL for robot navigation and UAV control
  45. Exploring Fine-grained Retail Product Discrimination with Zero-shot Object Classification Using Vision-Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  46. Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More WiselyRetrieval-augmented generation → RAG pipeline design and evaluation
  47. With Ears to See and Eyes to Hear: Sound Symbolism Experiments with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  48. Towards a Realistic Long-Term Benchmark for Open-Web Research AgentsLLM agents and tool use → Web, search, and research agents
  49. KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory SystemsLLM agents and tool use → Multimodal and embodied agents
  50. DSG-KD: Knowledge Distillation from Domain-Specific to General Language ModelsKnowledge distillation → Knowledge distillation for LLMs
  51. CON: Continual Object Navigation via Data-Free Inter-Agent Knowledge Transfer in Unseen and Unfamiliar PlacesLLM agents and tool use → Multimodal and embodied agents
  52. FedSlate:A Federated Deep Reinforcement Learning Recommender SystemDeep reinforcement learning methods → RL training of language and agent models
  53. A novel agent with formal goal-reaching guarantees: an experimental study with a mobile robotDeep reinforcement learning methods → Safe and constrained RL
  54. PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMsLLM safety and security → Jailbreaking
  55. A-VL: Adaptive Attention for Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  56. Orthogonal Finetuning for Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  57. ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and FeedbackLLM agents and tool use → Tool learning and function calling
  58. MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  59. Pre-trained Language Model and Knowledge Distillation for Lightweight Sequential RecommendationKnowledge distillation → Distillation for recommender systems
  60. Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  61. VLM's Eye Examination: Instruct and Inspect Visual Competency of Vision Language ModelsLLM reasoning → Multimodal reasoning +1
  62. Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and ForgettingLLM safety and security → Machine unlearning
  63. ToxiCraft: A Novel Framework for Synthetic Generation of Harmful InformationLLM safety and security → Safety alignment, refusal and guardrails
  64. PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMsLLM safety and security → Prompt injection and agent security
  65. DiSPo: Diffusion-SSM based Policy Learning for Coarse-to-Fine Action DiscretizationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models +1
  66. ERABAL: Enhancing Role-Playing Agents through Boundary-Aware LearningLLM agents and tool use → Social simulation and multi-agent debate
  67. Adaptive and Robust Watermark for Generative Tabular DataLLM safety and security → Watermarking generated content and models
  68. Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror ReflectionsDiffusion models → 3D, point cloud and scene generation
  69. RACER: Rich Language-Guided Failure Recovery Policies for Imitation LearningOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  70. Direct Judgement Preference OptimizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  71. The Impact of Generative Artificial Intelligence on Ideation and the performance of Innovation Teams (Preprint)
  72. PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training
  73. Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Driving
  74. Designing Pre-training Datasets from Unlabeled Data for EEG Classification with Transformers
  75. Dual Stream Graph Transformer Fusion Networks for Enhanced Brain Decoding
  76. TextToon: Real-Time Text Toonify Head Avatar from Single Video
  77. DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation
  78. Graph Network Models To Detect Illicit Transactions In Block Chain
  79. Lateral Ventricle Shape Modeling using Peripheral Area Projection for Longitudinal Analysis
  80. Natural Language Query Engine for Relational Databases using Generative AI
  81. Neural Differential Appearance Equations
  82. Micrometer: Micromechanics Transformer for Predicting Mechanical Responses of Heterogeneous Materials
  83. Dumpling GNN: Hybrid GNN Enables Better ADC Payload Activity Prediction Based on Chemical Structure
  84. Combining Open-box Simulation and Importance Sampling for Tuning Large-Scale Recommenders
  85. Improving Emotion Recognition Accuracy with Personalized Clustering
  86. Improving the Accessibility of Dating Websites for Individuals with Visual Impairments
  87. Temporal Graph Memory Networks For Knowledge Tracing
  88. InsightPulse: An IoT-based System for User Experience Interview Analysis
  89. FeruzaSpeech: A 60 Hour Uzbek Read Speech Corpus with Punctuation, Casing, and Context
  90. Improving Academic Skills Assessment with NLP and Ensemble Learning
  91. Identification and Mitigating Bias in Quantum Machine Learning
  92. A comprehensive study of on-device NLP applications -- VQA, automated Form filling, Smart Replies for Linguistic Codeswitching
  93. Unveiling the Potential of Graph Neural Networks in SME Credit Risk Assessment
  94. Fully automatic extraction of morphological traits from the Web: utopia or reality?
  95. MODEL&CO: Exoplanet detection in angular differential imaging by learning across multiple observations
  96. MRI Radiomics for IDH Genotype Prediction in Glioblastoma Diagnosis
  97. GATher: Graph Attention Based Predictions of Gene-Disease Links
  98. Automated Spatio-Temporal Weather Modeling for Load Forecasting
  99. MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving
  100. Gaussian Deja-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilities
All 322
  1. Safe Guard: an LLM-agent for Real-time Voice-based Hate Speech Detection in Social Virtual Reality
  2. Reinforcement Feature Transformation for Polymer Property Performance Prediction
  3. KISS-Matcher: Fast and Robust Point Cloud Registration Revisited
  4. Revolutionizing Biomarker Discovery: Leveraging Generative AI for Bio-Knowledge-Embedded Continuous Space Exploration
  5. Deep Learning Approach for Knee Point Detection on Noisy Data
  6. Assessment of Submillimeter Precision via Structure from Motion Technique in Close-Range Capture Environments
  7. Polyatomic Complexes: A topologically-informed learning representation for atomistic systems
  8. Physics Enhanced Residual Policy Learning (PERPL) for safety cruising in mixed traffic platooning under actuator and communication delay
  9. MapEx: Indoor Structure Exploration with Probabilistic Information Gain from Global Map Predictions
  10. TFT-multi: simultaneous forecasting of vital sign trajectories in the ICU
  11. FACET: Fast and Accurate Event-Based Eye Tracking Using Ellipse Modeling for Extended Reality
  12. Generalization vs. Specialization under Concept Shift
  13. Mixing Data-driven and Geometric Models for Satellite Docking Port State Estimation using an RGB or Event Camera
  14. Optimizing News Text Classification with Bi-LSTM and Attention Mechanism for Efficient Data Processing
  15. Cross-Domain Latent Factors Sharing via Implicit Matrix Factorization
  16. Asking an AI for salary negotiation advice is a matter of concern: Controlled experimental perturbation of ChatGPT for protected and non-protected group discrimination on a contextual task with no clear ground truth answers
  17. Critic Loss for Image Classification
  18. CauSkelNet: Causal Representation Learning for Human Behaviour Analysis
  19. QUB-PHEO: A Visual-Based Dyadic Multi-View Dataset for Intention Inference in Collaborative Assembly
  20. Stalactite: Toolbox for Fast Prototyping of Vertical Federated Learning Systems
  21. SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries
  22. Beyond Conformal Predictors: Adaptive Conformal Inference with Confidence Predictors
  23. A Novel Framework for the Automated Characterization of Gram-Stained Blood Culture Slides Using a Large-Scale Vision Transformer
  24. Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance
  25. Identifying Elasticities in Autocorrelated Time Series Using Causal Graphs
  26. VaLID: Verification as Late Integration of Detections for LiDAR-Camera Fusion
  27. SEAL: Suite for Evaluating API-use of LLMs
  28. MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines
  29. Eagle: Efficient Training-Free Router for Multi-LLM Inference
  30. MATCH POLICY: A Simple Pipeline from Point Cloud Registration to Manipulation Policies
  31. SpaGBOL: Spatial-Graph-Based Orientated Localisation
  32. From Text to Treatment Effects: A Meta-Learning Approach to Handling Text-Based Confounding
  33. Adenocarcinoma Segmentation Using Pre-trained Swin-UNet with Parallel Cross-Attention for Multi-Domain Imaging
  34. Analysis of Human Perception in Distinguishing Real and AI-Generated Faces: An Eye-Tracking Based Study
  35. Build Once, Monitor Continuously: Persistent Semantic Mapping via Autonomous Exploration and Open-Vocabulary Object Updates
  36. Computational Pathology for Accurate Prediction of Breast Cancer Recurrence: Development and Validation of a Deep Learning-based Tool
  37. Adapting Segment Anything Model for Unseen Object Instance Segmentation
  38. Mat'ern Kernels for Tunable Implicit Surface Reconstruction
  39. CUTE: Measuring LLMs' Understanding of Their Tokens
  40. Revealing an Unattractivity Bias in Mental Reconstruction of Occluded Faces using Generative Image Models
  41. Steward: Natural Language Web Automation
  42. Ads that Talk Back: Implications and Perceptions of Injecting Personalized Advertising into LLM Chatbots
  43. The ParlaSpeech Collection of Automatically Generated Speech and Text Datasets from Parliamentary Proceedings
  44. Neural Control Variates with Automatic Integration
  45. Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient
  46. PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions
  47. A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?
  48. ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild
  49. Peer-to-Peer Learning Dynamics of Wide Neural Networks
  50. UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework
  51. The Palomar twilight survey of 'Ayl'o'chaxnim, Atiras, and comets
  52. Identification and Localization of Cometary Activity in Solar System Objects with Machine Learning
  53. ZeroSCD: Zero-Shot Street Scene Change Detection
  54. Archon: An Architecture Search Framework for Inference-Time Techniques
  55. Investigating Robot Dogs for Construction Monitoring: A Comparative Analysis of Specifications and On-site Requirements
  56. Precise Asymptotics of Bagging Regularized M-estimators
  57. Machine Learning Toric Duality in Brane Tilings
  58. ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models
  59. On-Air Deep Learning Integrated Semantic Inference Models for Enhanced Earth Observation Satellite Networks
  60. MACeIP: A Multimodal Ambient Context-enriched Intelligence Platform in Smart Cities
  61. Domino: Eliminating Communication in LLM Training via Generic Tensor Slicing and Overlapping
  62. MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation
  63. A Comprehensive Framework for Evaluating API-oriented Code Generation in Large Language Models
  64. Enhancing Pedestrian Trajectory Prediction with Crowd Trip Information
  65. MotifDisco: Motif Causal Discovery For Time Series Motifs
  66. FLeNS: Federated Learning with Enhanced Nesterov-Newton Sketch
  67. HydroVision: LiDAR-Guided Hydrometric Prediction with Vision Transformers and Hybrid Graph Learning
  68. Fast and Accurate Triangle Counting in Graph Streams Using Predictions
  69. RAMBO: Enhancing RAG-based Repository-Level Method Body Completion
  70. ASTE Transformer Modelling Dependencies in Aspect-Sentiment Triplet Extraction
  71. Enabling Tensor Decomposition for Time-Series Classification via A Simple Pseudo-Laplacian Contrast
  72. Learning from Contrastive Prompts: Automated Optimization and Adaptation
  73. HOTVCOM: Generating Buzzworthy Comments for Videos
  74. Interpretability-Guided Test-Time Adversarial Defense
  75. PALLM: Evaluating and Enhancing PALLiative Care Conversations with Large Language Models
  76. Location is Key: Leveraging Large Language Model for Functional Bug Localization in Verilog
  77. Chattronics: using GPTs to assist in the design of data acquisition systems
  78. Goal-based Neural Physics Vehicle Trajectory Prediction Model
  79. MIMAFace: Face Animation via Motion-Identity Modulated Appearance Feature Learning
  80. SpikeGS: Learning 3D Gaussian Fields from Continuous Spike Stream
  81. Skills Made to Order: Efficient Acquisition of Robot Cooking Skills Guided by Multiple Forms of Internet Data
  82. Data-driven model discovery with Kolmogorov-Arnold networks
  83. Harmonic Path Integral Diffusion
  84. Lessons Learned on Information Retrieval in Electronic Health Records: A Comparison of Embedding Models and Pooling Strategies
  85. DRAPER: Towards a Robust Robot Deployment and Reliable Evaluation for Quasi-Static Pick-and-Place Cloth-Shaping Neural Controllers
  86. Automatic Feature Learning for Essence: a Case Study on Car Sequencing
  87. MAR-DTN: Metal Artifact Reduction using Domain Transformation Network for Radiotherapy Planning
  88. Designing an Interpretable Interface for Contextual Bandits
  89. FusionRF: High-Fidelity Satellite Neural Radiance Fields from Multispectral and Panchromatic Acquisitions
  90. CAMAL: Optimizing LSM-trees via Active Learning
  91. The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes
  92. Pareto-Optimized Open-Source LLMs for Healthcare via Context Retrieval
  93. UTrace: Poisoning Forensics for Private Collaborative Learning
  94. Log-normal Mutations and their Use in Detecting Surreptitious Fake Images
  95. Diffusion-based RGB-D Semantic Segmentation with Deformable Attention Transformer
  96. Evaluating ML Robustness in GNSS Interference Classification, Characterization & Localization
  97. ChatGPT as a Solver and Grader of Programming Exams written in Spanish
  98. The BRAVO Semantic Segmentation Challenge Results in UNCV2024
  99. PecSched: Preemptive and Efficient Cluster Scheduling for LLM Inference
  100. Robust Federated Learning Over the Air: Combating Heavy-Tailed Noise with Median Anchored Clipping
  101. Efficiently Dispatching Flash Attention For Partially Filled Attention Masks
  102. Whole-Body Teleoperation for Mobile Manipulation at Zero Added Cost
  103. M2OST: Many-to-one Regression for Predicting Spatial Transcriptomics from Digital Pathology Images
  104. Using Similarity to Evaluate Factual Consistency in Summaries
  105. AdapFair: Ensuring Adaptive Fairness for Machine Learning Operations
  106. AI Workflow, External Validation, and Development in Eye Disease Diagnosis
  107. TSCLIP: Robust CLIP Fine-Tuning for Worldwide Cross-Regional Traffic Sign Recognition
  108. Evaluating the Usability of LLMs in Threat Intelligence Enrichment
  109. FisheyeDepth: A Real Scale Self-Supervised Depth Estimation Model for Fisheye Camera
  110. Brotherhood at WMT 2024: Leveraging LLM-Generated Contextual Conversations for Cross-Lingual Image Captioning
  111. Scaling Laws of Decoder-Only Models on the Multilingual Machine Translation Task
  112. AlphaZip: Neural Network-Enhanced Lossless Text Compression
  113. AIM 2024 Sparse Neural Rendering Challenge: Methods and Results
  114. AIM 2024 Sparse Neural Rendering Challenge: Dataset and Benchmark
  115. Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP
  116. Anomaly Detection from a Tensor Train Perspective
  117. Region Mixup
  118. Generative LLM Powered Conversational AI Application for Personalized Risk Assessment: A Case Study in COVID-19
  119. Cross Branch Feature Fusion Decoder for Consistency Regularization-based Semi-Supervised Change Detection
  120. Acting for the Right Reasons: Creating Reason-Sensitive Artificial Moral Agents
  121. Analogous Alignments: Digital "Formally" meets Analog
  122. Generalizing monocular colonoscopy image depth estimation by uncertainty-based global and local fusion network
  123. Method of Equal Shares with Bounded Overspending
  124. ViBERTgrid BiLSTM-CRF: Multimodal Key Information Extraction from Unstructured Financial Documents
  125. Enhancing Aspect-based Sentiment Analysis in Tourism Using Large Language Models and Positional Information
  126. Methods for Convex (L0,L1)-Smooth Optimization: Clipping, Acceleration, and Adaptivity
  127. Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs
  128. Evaluating Theory of (an uncertain) Mind: Predicting the Uncertain Beliefs of Others in Conversation Forecasting
  129. Image-Guided Semantic Pseudo-LiDAR Point Generation for 3D Object Detection
  130. SocialCircle+: Learning the Angle-based Conditioned Interaction Representation for Pedestrian Trajectory Prediction
  131. Dynamic Integration of Task-Specific Adapters for Class Incremental Learning
  132. On The Specialization of Neural Modules
  133. (De)-regularized Maximum Mean Discrepancy Gradient Flow
  134. TS-HTFA: Advancing Time Series Forecasting via Hierarchical Text-Free Alignment with Large Language Models
  135. A new baseline for edge detection: Make Encoder-Decoder great again
  136. Blind Spatial Impulse Response Generation from Separate Room- and Scene-Specific Information
  137. Bilingual Rhetorical Structure Parsing with Large Parallel Annotations
  138. Adaptive Learning on User Segmentation: Universal to Specific Representation via Bipartite Neural Interaction
  139. Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training
  140. FastGL: A GPU-Efficient Framework for Accelerating Sampling-Based GNN Training at Large Scale
  141. Deep Cost Ray Fusion for Sparse Depth Video Completion
  142. DanceCamAnimator: Keyframe-Based Controllable 3D Dance Camera Synthesis
  143. A Realistic Simulation Framework for Analog/Digital Neuromorphic Architectures
  144. Efficient Tabular Data Preprocessing of ML Pipelines
  145. Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization
  146. Kriformer: A Novel Spatiotemporal Kriging Approach Based on Graph Transformers
  147. Built Different: Tactile Perception to Overcome Cross-Embodiment Capability Differences in Collaborative Manipulation
  148. Novel Gradient Sparsification Algorithm via Bayesian Inference
  149. Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation
  150. Advancing Video Quality Assessment for AIGC
  151. Deploying Open-Source Large Language Models: A performance Analysis
  152. Probabilistically Aligned View-unaligned Clustering with Adaptive Template Selection
  153. End-to-End Graph Flattening Method for Large Language Models
  154. Privacy Policy Analysis through Prompt Engineering for LLMs
  155. Mammo-Clustering: A Multi-views Tri-level Information Fusion Context Clustering Framework for Localization and Classification in Mammography
  156. Towards Ground-truth-free Evaluation of Any Segmentation in Medical Images
  157. Testing Dependency of Weighted Random Graphs
  158. Embedding Knowledge Graph in Function Spaces
  159. FUSED-Net: Detecting Traffic Signs with Limited Data
  160. Disentanglement with Factor Quantized Variational Autoencoders
  161. GroCo: Ground Constraint for Metric Self-Supervised Monocular Depth
  162. Revisiting Video Quality Assessment from the Perspective of Generalization
  163. HW-TSC's Submission to the CCMT 2024 Machine Translation Tasks
  164. Explainable and Human-Grounded AI for Decision Support Systems: The Theory of Epistemic Quasi-Partnerships
  165. MICSim: A Modular Simulator for Mixed-signal Compute-in-Memory based AI Accelerator
  166. Energy-Aware Federated Learning in Satellite Constellations
  167. Identify As A Human Does: A Pathfinder of Next-Generation Anti-Cheat Framework for First-Person Shooter Games
  168. RoWSFormer: A Robust Watermarking Framework with Swin Transformer for Enhanced Geometric Attack Resilience
  169. Two Deep Learning Solutions for Automatic Blurring of Faces in Videos
  170. AIM 2024 Challenge on Video Saliency Prediction: Methods and Results
  171. Towards Real-world Deployment of NILM Systems: Challenges and Practices
  172. Past Meets Present: Creating Historical Analogy with Large Language Models
  173. VARADE: a Variational-based AutoRegressive model for Anomaly Detection on the Edge
  174. SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning
  175. Benchmarking Edge AI Platforms for High-Performance ML Inference
  176. MTP: A Dataset for Multi-Modal Turning Points in Casual Conversations
  177. Choose the Final Translation from NMT and LLM hypotheses Using MBR Decoding: HW-TSC's Submission to the WMT24 General MT Shared Task
  178. Research on Dynamic Data Flow Anomaly Detection based on Machine Learning
  179. Advancing Depression Detection on Social Media Platforms Through Fine-Tuned Large Language Models
  180. Adaptive Conformal Inference for Multi-Step Ahead Time-Series Forecasting Online
  181. Multiscale scattered data analysis in samplet coordinates
  182. SAMEdge: An Edge-cloud Video Analytics Architecture for the Segment Anything Model
  183. Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method
  184. Human Hair Reconstruction with Strand-Aligned 3D Gaussians
  185. CFVNet: An End-to-End Cancelable Finger Vein Network for Recognition
  186. OMPar: Automatic Parallelization with AI-Driven Source-to-Source Compilation
  187. Language-Agnostic Analysis of Speech Depression Detection
  188. Robust and Flexible Omnidirectional Depth Estimation with Multiple 360-degree Cameras
  189. Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios?
  190. Isometric Immersion Learning with Riemannian Geometry
  191. BranchPoseNet: Characterizing tree branching with a deep learning-based pose estimation approach
  192. UniBEVFusion: Unified Radar-Vision BEVFusion for 3D Object Detection
  193. FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension
  194. LINKAGE: Listwise Ranking among Varied-Quality References for Non-Factoid QA Evaluation via LLMs
  195. Less yet robust: crucial region selection for scene recognition
  196. EDSNet: Efficient-DSNet for Video Summarization
  197. Neural refractive index field: Unlocking the Potential of Background-oriented Schlieren Tomography in Volumetric Flow Visualization
  198. ControlEdit: A MultiModal Local Clothing Image Editing Method
  199. Phantom of Latent for Large Language and Vision Models
  200. Target-Aware Language Modeling via Granular Data Sampling
  201. VLEU: a Method for Automatic Evaluation for Generalizability of Text-to-Image Models
  202. MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classification
  203. Dynamic Realms: 4D Content Analysis, Recovery and Generation with Geometric, Topological and Physical Priors
  204. EDGE-Rec: Efficient and Data-Guided Edge Diffusion For Recommender Systems Graphs
  205. Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling
  206. Robust Training Objectives Improve Embedding-based Retrieval in Industrial Recommendation Systems
  207. Quantifying Context Bias in Domain Adaptation for Object Detection
  208. TransUKAN:Computing-Efficient Hybrid KAN-Transformer for Enhanced Medical Image Segmentation
  209. Instruction Tuning Vs. In-Context Learning: Revisiting Large Language Models in Few-Shot Computational Social Science
  210. Speechworthy Instruction-tuned Language Models
  211. FedGCA: Global Consistent Augmentation Based Single-Source Federated Domain Generalization
  212. Semi-supervised Learning For Robust Speech Evaluation
  213. Fourier neural operators for spatiotemporal dynamics in two-dimensional turbulence
  214. Building Tamil Treebanks
  215. Federated Graph Learning with Adaptive Importance-based Sampling
  216. AEANet: Affinity Enhanced Attentional Networks for Arbitrary Style Transfer
  217. Demystifying Trajectory Recovery From Ash: An Open-Source Evaluation and Enhancement
  218. LSem2Vec: A Simple yet Effective Two-Stage Approach for Source Code Embedding
  219. Harmonising the Clinical Melody: Tuning Large Language Models for Hospital Course Summarisation in Clinical Coding
  220. Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting
  221. Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation
  222. Hierarchical end-to-end autonomous navigation through few-shot waypoint detection