Papers
-
Novel Semantic Prompting for Zero-Shot Action Recognition
-
Minor First, Major Last: A Depth-Induced Implicit Bias of Sharpness-Aware MinimizationKorea Advanced Institute of Science & Technology
-
Deconstructing Multimodal Mathematical Reasoning: Towards a Unified Perception-Alignment-Reasoning ParadigmColumbia University, New York University, The Pennsylvania State University, University of Notre Dame, Yale University
-
Graph-Instructed Neural Networks for parametric problems with varying boundary conditionsGruppo Nazionale per il Calcolo Scientifico, Politecnico di Torino
-
Retrieval-Augmented Anatomical Guidance for Text-to-CT GenerationUmeå University, Università Campus Bio-Medico di Roma
-
Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve RobustnessTel Aviv University, The Open University
-
Sign Identifiability of Causal Effects in Stationary Stochastic Dynamical SystemsLeiden University
-
Learning Multiple Utterance-Level Attribute Representations with a Unified Speech EncoderAvignon Université
-
HDR-NSFF: High Dynamic Range Neural Scene Flow FieldsKorea Advanced Institute of Science & Technology, Pohang University of Science and Technology
-
SlowBA: An efficiency backdoor attack towards VLM-based GUI agentsShanghai Jiao Tong University
-
Human-AI Divergence in Ego-centric Action Recognition under Spatial and Spatiotemporal ManipulationsNewcastle University, University of Surrey
-
CORE-Acu: Structured Reasoning Traces and Knowledge Graph Safety Verification for Acupuncture Clinical Decision Support
-
Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial DesignCornell University, Technische Universität Wien
-
EndoSERV: A Vision-based Endoluminal Robot Navigation SystemThe Institute of Electrical and Electronics Engineers
-
Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in HistopathologyAignostics / Berlin Institute for the Foundations of Learning and Data, Charité – Universitätsmedizin Berlin, German Cancer Research Center, Korea University, Ludwig Maximilian University of Munich, Max Planck Institute for Informatics, Technische Universitat Berlin, The Chinese University of Hong Kong, University of Toronto, Vector Institute for Artificial Intelligence
-
SPD-RAG: Sub-Agent Per Document Retrieval-Augmented GenerationOstim Teknik Üniversitesi, TOBB University of Economics and Technology
-
Detecting Fake Reviewer Groups in Dynamic Networks: An Adaptive Graph Learning MethodThe Institute of Electrical and Electronics Engineers
-
Electrocardiogram Classification with Transformers Using Koopman and Wavelet FeaturesCentral Institute of Mental Health, Heidelberg University
-
Rethinking Attention Output Projection: Structured Hadamard Transforms for Efficient Transformers
-
Local-Global Prompt Learning via Sparse Optimal TransportGazi University, Middle East Technical University
-
Towards plausibility in time series counterfactual explanations
-
Do Language Models Know Theo Has a Wife? Investigating the Proviso ProblemCarleton University, University of Ottawa
-
Computational modeling of early language learning from acoustic speech and audiovisual input without linguistic priorsTampere University
-
$Δ$VLA: Prior-Guided Vision-Language-Action Models via World Knowledge VariationThe Institute of Electrical and Electronics Engineers
-
Diffusion-Based Data Augmentation for Image Recognition: A Systematic Analysis and EvaluationNanjing University, The University of Hong Kong
-
M$^3$-ACE: Rectifying Visual Perception in Multimodal Math Reasoning via Multi-Agentic Context Engineering
-
Unifying On- and Off-Policy Variance Reduction Methods
-
Leaderboard Incentives: Model Rankings under Strategic Post-TrainingTübingen AI Center
-
This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse
-
Beyond the Markovian Assumption: Robust Optimization via Fractional Weyl Integrals in Imbalanced DataUniversidad Nacional del Nordeste
-
Structure from Rank: Rank-Order Coding as a Bridge from Sequence to StructureAgency for Science, Technology and Research, Singapore, Cergy-Paris Université, International Research Laboratory on Artificial Intelligence
-
InFusionLayer: a CFA-based ensemble tool to generate new classifiers for learning and modelingThe Institute of Electrical and Electronics Engineers
-
Rectified flow-based prediction of post-treatment brain MRI from pre-radiotherapy priors for patients with gliomaAmsterdam University Medical Centers, Cancer Center Amsterdam, Vrije Universiteit Amsterdam
-
Real-Time Drone Detection in Event Cameras via Per-Pixel Frequency AnalysisJohns Hopkins University
-
AULLM++: Structural Reasoning with Large Language Models for Micro-Expression RecognitionThe Institute of Electrical and Electronics Engineers
-
A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action GenerationBeihang University
-
StructBiHOI: Structured Articulation Modeling for Long--Horizon Bimanual Hand--Object Interaction GenerationHefei University of Technology, Shanghai Jiao Tong University
-
Adaptive Loops and Memory in Transformers: Think Harder or Know More?Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme, Lamarr Institute, University of Bonn
-
COACH meets QUORUM: A Framework and Pipeline for Aligning User, Expert and Developer Perspectives in LLM-generated Health Counselling
-
Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective
-
A Recipe for Stable Offline Multi-agent Reinforcement LearningSungkyunkwan University, University of Texas
-
SPIRAL: A Closed-Loop Framework for Self-Improving Action World Models via Reflective Planning AgentsTencent / Chinese Academy of Sciences, Nanyang Technological University, National University of Singapore, Shanghai AI Lab, Zhejiang University
-
Sandpiper: Orchestrated AI-Annotation for Educational Discourse at ScaleCarnegie Mellon University, Cornell University, Massachusetts Institute of Technology
-
Aligning to Illusions: Choice Blindness in Human and AI FeedbackUniversity of Cambridge
-
Geometrically Constrained Outlier SynthesisAXA AI Research, École Polytechnique Fédérale de Lausanne, Polish Academy of Science, Sorbonne University
-
Meta-RL with Shared Representations Enables Fast Adaptation in Energy SystemsInstitut National des Sciences Appliquées Rouen, Université Claude Bernard Lyon 1, Université Lumière Lyon 2, Université Sorbonne Paris Nord
-
Human-Aware Robot Behaviour in Self-Driving LabsUniversity of Liverpool
-
SYNAPSE: Framework for Neuron Analysis and Perturbation in Sequence EncodingUniversidad de Murcia
-
IronEngine: Towards General AI Assistant
-
Grow, Assess, Compress: Adaptive Backbone Scaling for Memory-Efficient Class Incremental LearningIkerlan Technology Research Center, Mondragon Unibertsitatea, University of the Basque Country
MongoDB - Build AI That Scales
