Papers
-
OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise OptimalityShenzhen University of Advanced Technology
-
On the Structural Failure of Chamfer Distance in 3D Shape OptimizationVanderbilt University
-
Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late InteractionAalto University, Fudan University, Georgia Institute of Technology
-
Adaptive Clinical-Aware Latent Diffusion for Multimodal Brain Image Generation and Missing Modality ImputationLehigh University, Stanford University, Worcester Polytechnic Institute
-
Unsupervised Domain Adaptation with Target-Only Margin Disparity DiscrepancyInstitut Polytechnique de Paris
-
Generative Drifting is Secretly Score Matching: a Spectral and Variational PerspectiveInstitut Polytechnique de Paris
-
Model Merging in the Era of Large Language Models: Methods, Applications, and Future Directions
-
SignalMC-MED: A Multimodal Benchmark for Evaluating Biosignal Foundation Models on Single-Lead ECG and PPGNational Institute for Health and Care Research, Oxford Biomedical Research Centre, University of Oxford
-
Towards Flexible Spectrum Access: Data-Driven Insights into Spectrum DemandCarleton University, Communications Research Centre
-
PathMem: Toward Cognition-Aligned Memory Transformation for Pathology MLLMsHuazhong University of Science and Technology, Imperial College London, Nanyang Technological University, Shenzhen University, University of Science and Technology of China
-
Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models
-
No Image, No Problem: End-to-End Multi-Task Cardiac Analysis from Undersampled k-SpaceImperial College London, Technical University of Munich
-
Denoising the US Census: Succinct Block Hierarchical Regression
-
The Confidence Gate Theorem: When Should Ranked Decision Systems Abstain?Haske Labs
-
When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic
-
Leveraging whole slide difficulty in Multiple Instance Learning to improve prostate cancer gradingInstitut Polytechnique de Paris
-
From Semantics to Pixels: Coarse-to-Fine Masked Autoencoders for Hierarchical Visual UnderstandingPeking University, Peng Cheng Laboratory, University of Chinese Academy of Sciences
-
Think Before You Lie: How Reasoning Improves Honesty
-
TinyNav: End-to-End TinyML for Real-Time Autonomous Navigation on MicrocontrollersQueen’s University
-
BEACON: Language-Conditioned Navigation Affordance Prediction under OcclusionDelft University of Technology
-
Emotional Modulation in Swarm Decision DynamicsUniversity of Las Palmas de Gran Canaria
-
Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision PeopleCornell University
-
CREATE: Testing LLMs for Associative CreativityNew York University, University of Texas
-
From Data Statistics to Feature Geometry: How Correlations Shape SuperpositionImperial College London
-
Hardware Efficient Approximate Convolution with Tunable Error Tolerance for CNNsIndian Institute of Technology Guwahati
-
Task Aware Modulation Using Representation Learning for Upsaling of Terrestrial Carbon FluxesUniversity of Minnesota
-
CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR
-
Lost in the Middle at Birth: An Exact Theory of Transformer Position Bias
-
4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular VideoSouthern University of Science and Technology, The University of Hong Kong, Tsinghua University
-
AR-VLA: True Autoregressive Action Expert for Vision-Language-Action ModelsKU Leuven, Sofia University
-
HG-Lane: High-Fidelity Generation of Lane Scenes under Adverse Weather and Lighting Conditions without Re-annotationChinese Academy of Sciences, Henan University, Nanyang Technological University, University of Science and Technology of China
-
The Prediction-Measurement Gap: Toward Meaning Representations as Scientific InstrumentsIDEAS Research Institute
-
Unbalanced Optimal Transport Dictionary Learning for Unsupervised Hyperspectral Image ClusteringTufts University, University of California
-
Agentic Control Center for Data Product Optimization
-
The Generation-Recognition Asymmetry: Six Dimensions of a Fundamental Divide in Formal Language Theory
-
Reason and Verify: A Framework for Faithful Retrieval-Augmented GenerationCentre de recherche informatique de Montréal, Concordia University
-
Lost in Backpropagation: The LM Head is a Gradient BottleneckCornell University
-
Social Knowledge for Cross-Domain User Preference ModelingBen-Gurion University of the Negev, University of Haifa
-
A neural operator for predicting vibration frequency response curves from limited dataFlorida International University, New Mexico State University
-
OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile RobotsJohns Hopkins University, University of South Florida
-
Mashup Learning: Faster Finetuning by Remixing Past Checkpoints
-
ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
-
Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance VulnerabilitiesUniversity of Minnesota
-
Calibration-Reasoning Framework for Descriptive Speech Quality Assessment
-
Video-Based Reward Modeling for Computer-Use AgentsAmazon / Mohamed bin Zayed University of Artificial Intelligence, University of Southern California, University of Washington
-
DT-BEHRT: Disease Trajectory-aware Transformer for Interpretable Patient Representation LearningUniversity of Florida, University of Kansas, University of South Florida
-
Stability and Robustness via Regularization: Bandit Inference via Regularized Stochastic Mirror DescentIndian Statistical Institute, Rutgers University
-
ARCHE: Autoregressive Residual Compression with Hyperprior and ExcitationIonian University, University of Patras
-
MCP-in-SoS: Risk assessment framework for open-source MCP serversNew Mexico State University, University of Hartford
-
Adaptive Activation Cancellation for Hallucination Mitigation in Large Language ModelsCalifornia Polytechnic State University, Dakota State University, North Carolina Agricultural and Technical State University, South Carolina State University, University of Idaho
MongoDB - Build AI That Scales
