Mini toolsPapers
Filter by company
-
Efficient RGB-D Scene Understanding via Multi-task Adaptive Learning and Cross-dimensional Feature GuidanceChinese Academy of Sciences, Hubei University of Technology, Nanjing University, Xihua University
-
A Systematic Comparison of Training Objectives for Out-of-Distribution Detection in Image ClassificationBilkent University, Middle East Technical University
-
TS-MLLM: A Multi-Modal Large Language Model-based Framework for Industrial Time-Series Big Data AnalysisBeihang University, St. Francis Xavier University, State Key Laboratory of Intelligent Manufacturing System Technology, Zhengzhou University
-
Integration of deep generative Anomaly Detection algorithm in high-speed industrial line
-
KCoEvo: A Knowledge Graph Augmented Framework for Evolutionary Code Generation
-
Generalized Reduction to the Isotropy for Flexible Equivariant Neural FieldsEindhoven University of Technology, Universiteit Leiden, University of Amsterdam
-
Analysis-Driven Procedural Generation of an Engine Sound Dataset with Embedded Control Annotations
-
3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise ClassificationCardiff University, Centre for Perceptual and Interactive Intelligence, Sun Yat-sen University, Texas A&M University
-
Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints
-
Fast Attention-Based Simplification of LiDAR Point Clouds for Object Detection and ClassificationDe Montfort University, Institute for Computer Science and Control, Nanchang University, Shandong University, Jinan
-
Shorter Thoughts, Same Answers: Difficulty-Scaled Segment-Wise RL for CoT Compression
-
StyleBench: Evaluating Speech Language Models on Conversational Speaking Style ControlNortheastern University
-
MetaSort: An Accelerated Approach for Non-uniform Compression and Few-shot Classification of Neural Spike WaveformsUniversity of Southampton
-
EmbedTalk: Triplane-Free Talking Head Synthesis using Embedding-Driven Gaussian DeformationUniversity of Leeds
-
TT-Sparse: Learning Sparse Rule Models with Differentiable Truth TablesNanyang Technological University
-
MAS-H2: A Hierarchical Multi-Agent System for Holistic Cloud-Native AutoscalingUniversity of Westminster, University of York
-
KohakuRAG: A simple RAG framework with hierarchical document indexingNational Tsing Hua University
-
Looking Into the Water by Unsupervised Learning of the Surface ShapeUniversity of Haifa
-
Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation ModelsUniversity of Cambridge
-
SMAT: Staged Multi-Agent Training for Co-Adaptive Exoskeleton ControlNew Jersey Institute of Technology
-
Overthinking Causes Hallucination: Tracing Confounder Propagation in Vision Language ModelsHanoi University, University of Adelaide
-
Duala: Dual-Level Alignment of Subjects and Stimuli for Cross-Subject fMRI DecodingNanjing University
-
Accelerating Diffusion Models for Generative AI Applications with Silicon PhotonicsColorado State University
-
Exoskeleton Control through Learning to Reduce Biological Joint Moments in SimulationsNew Jersey Institute of Technology
-
Real-Time Glottis Detection Framework via Spatial-decoupled Feature Learning for Nasal Transnasal IntubationHuazhong University of Science and Technology, Hubei University of Technology
-
Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem SolvingTsinghua University
-
Evaluating Synthetic Data for Baggage Trolley Detection in Airport LogisticsThe National School of Artificial Intelligence
-
AtomicVLA: Unlocking the Potential of Atomic Skill Learning in RobotsPeng Cheng Laboratory, Sun Yat-sen University
-
GLASS: Graph and Vision-Language Assisted Semantic Shape CorrespondenceFondazione Bruno Kessler, Laboratory for Artificial Intelligence, The Hong Kong Polytechnic University, University of Technology Sydney
-
Compressed Proximal Federated Learning for Non-Convex Composite Optimization on Heterogeneous DataSun Yat-sen University, Tsinghua University, University of Victoria
-
Partial Differential Equations in the Age of Machine Learning: A Critical Synthesis of Classical, Machine Learning, and Hybrid MethodsFriedrich-Schiller-Universität Jena, University of Bergen, University of Oslo
-
Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference FrameworkChinese Academy of Sciences, Tongji University, University of Chinese Academy of Sciences
-
Ref-DGS: Reflective Dual Gaussian SplattingChinese Academy of Sciences, Chongqing University, King Abdullah University of Science and Technology (KAUST)
-
AI-Driven Phase Identification from X-ray Hyperspectral Imaging of cycled Na-ion Cathode MaterialsCentre national de la recherche scientifique, Université de Bordeaux
-
FusionRegister: Every Infrared and Visible Image Fusion Deserves RegistrationJiangnan University, Suzhou University of Science and Technology
-
Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
-
Beyond Surrogates: A Quantitative Analysis for Inter-Metric RelationshipsState Key Laboratory of Cognitive Intelligence, University of Science and Technology of China
-
A Primer on Evolutionary Frameworks for Near-Field Multi-Source LocalizationKTH Royal Institute of Technology, Mid Sweden University
-
Mitigating the Memory Bottleneck with Machine Learning-Driven and Data-Aware Microarchitectural TechniquesETH Zurich
-
UniUncer: Unified Dynamic Static Uncertainty for End to End DrivingRensselaer Polytechnic Institute, Tsinghua University
-
FrameVGGT: Frame Evidence Rolling Memory for streaming VGGTThe University of Tokyo
-
RoboPCA: Pose-centered Affordance Learning from Human Demonstrations for Robot ManipulationChinese Academy of Sciences, University of Chinese Academy of Sciences
-
Compressed-Domain-Aware Online Video Super-ResolutionBeijing Institute of Technology
-
Learning Context-Adaptive Motion Priors for Masked Motion Diffusion Models with Efficient Kinematic Attention AggregationHong Kong Baptist University
-
Global Convergence of Average Reward Constrained MDPs with Neural Critic and General Policy ParameterizationPurdue University, University of Maryland
-
EDMFormer: Genre-Specific Self-Supervised Learning for Music Structure SegmentationUniversity of Waterloo
-
TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable RewardHong Kong University of Science and Technology, The Chinese University of Hong Kong
-
Step-Size Decay and Structural Stagnation in Greedy Sparse LearningColegio Universitario de Estudios Financieros
-
PARSE: Part-Aware Relational Spatial ModelingShanghaiTech University
-
Deep Incentive Design with Differentiable Equilibrium BlocksETH Zurich
