Papers
-
Causal Interpretation of Neural Network Computations with Contribution DecompositionStanford University
-
EgoReasoner: Learning Egocentric 4D Reasoning via Task-Adaptive Structured ThinkingNortheastern University
-
Physics-Informed Diffusion Model for Generating Synthetic Extreme Rare Weather Events DataUniversity of London
-
Boosting deep Reinforcement Learning using pretraining with Logical OptionsGerman Research Center for Artificial Intelligence, Technical University of Darmstadt
-
A recipe for scalable attention-based MLIPs: unlocking long-range accuracy with all-to-all node attentionLawrence Berkeley National Laboratory, University of California
-
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
-
SUREON: A Benchmark and Vision-Language-Model for Surgical Reasoning
-
SCOPE: Scene-Contextualized Incremental Few-Shot 3D SegmentationSingapore University of Technology and Design, University of Copenhagen, University of Exeter, University of Surrey, University of Wollongong
-
Fly360: Omnidirectional Obstacle Avoidance within Drone ViewInstitute of Automation Chinese Academy of Sciences, Wuhan University
-
BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View RepresentationsUniversity of California
-
Multimodal Large Language Models as Image ClassifiersCzech Technical University
-
Optimistic Policy RegularizationDartmouth College
-
Best-of-Tails: Bridging Optimism and Pessimism in Inference-Time Alignment
-
NEST: Network- and Memory-Aware Device Placement For Distributed Deep LearningGeorgia Institute of Technology, University of Washington
-
Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential EnergyHarvard University, Mohamed bin Zayed University of Artificial Intelligence, Renmin University of China
-
A Hybrid Machine Learning Model for Cerebral Palsy DetectionSharda University
-
Multi-Agent Reinforcement Learning with Submodular RewardTexas A&M University
-
Making AI Evaluation Deployment Relevant Through Context Specification
-
Reinforcing the World's Edge: A Continual Learning Problem in the Multi-Agent-World BoundaryMcGill University
-
AI-Assisted Curation of Conference Scholarship: Compiling, Structuring, and Analyzing Two Decades of Presentations at the Society for Social Work and ResearchUniversity of Michigan, Wayne State University
-
"Dark Triad" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial BehaviorUniversity of Southern California, University of Stuttgart
-
CREDO: Epistemic-Aware Conformalized Credal Envelopes for RegressionFederal University of São Carlos, The University of Manchester, Université Grenoble Alpes, University of São Paulo
-
Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language ModelsAmerican International University, University of Dhaka
-
Joint 3D Gravity and Magnetic Inversion via Rectified Flow and Ginzburg-Landau GuidanceAshoka University
-
Validation of a Small Language Model for DSM-5 Substance Category Classification in Child Welfare RecordsUlm University, University of Michigan, Zurich University of Applied Sciences
-
MotionBits: Video Segmentation through Motion-Level Analysis of Rigid BodiesUniversity of Texas
-
Twitch: Learning Abstractions for Equational Theorem ProvingChalmers University of Technology, University of Gothenburg
-
Bilateral Trade Under Heavy-Tailed Valuations: Minimax Regret with Infinite Variance
-
Active View Selection with Perturbed Gaussian Ensemble for Tomographic ReconstructionAustralian National University, Johns Hopkins University, University of Illinois Urbana-Champaign
-
An Extended Topological Model For High-Contrast Optical Flow
-
Are Audio-Language Models Listening? Audio-Specialist Heads for Adaptive Audio SteeringBar-Ilan University, Columbia University
-
Contextual Counterfactual Credit Assignment for Multi-Agent Reinforcement Learning in LLM CollaborationThe Eastern Institute of Technology, The Hong Kong Polytechnic University
-
ColonSplat: Reconstruction of Peristaltic Motion in Colonoscopy with Dynamic Gaussian SplattingJagiellonian University, Sano Centre for Computational Medicine, University of Verona, Warsaw University of Technology
-
IGLU: The Integrated Gaussian Linear Unit Activation FunctionBowdoin College
-
Supporting Artifact Evaluation with LLMs: A Study with Published Security Research PapersRWTH Aachen University
-
A prior information informed learning architecture for flying trajectory predictionSouthern University of Science and Technology, The Chinese University of Hong Kong
-
Counting on Consensus: Selecting the Right Inter-annotator Agreement Metric for NLP Annotation and EvaluationThe University of Sheffield
-
Symmetry-Constrained Language-Guided Program Synthesis for Discovering Governing Equations from Noisy and Partial ObservationsHamdard University
-
LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon ReasoningÉcole Polytechnique Fédérale de Lausanne
-
PICS: Pairwise Image Compositing with Spatial InteractionsConcordia University, University of Alberta
-
LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models
-
Stochastic Attention via Langevin Dynamics on the Modern Hopfield Energy
-
Not Too Short, Not Too Long: How LLM Response Length Shapes People's Critical Thinking in Error Detection
-
Physics-informed AI Accelerated Retention Analysis of Ferroelectric Vertical NAND: From Day-Scale TCAD to Second-Scale Surrogate ModelGeorgia Institute of Technology
-
Distributed Legal Infrastructure for a Trustworthy Agentic WebBerkeley Center for Law & Technology, McGill University, New York University Shanghai, Norwegian University of Science and Technology, Shanghai Innovation Institute, Sun Yat-sen University, Technical University of Munich, Università degli Studi dell'Aquila, University of California, University of Oxford, York University
-
OPTED: Open Preprocessed Trachoma Eye Dataset Using Zero-Shot SAM 3 SegmentationMaharishi International University, Mekelle University
-
Enhancing the Detection of Coronary Artery Disease Using Machine LearningSharda University
-
Single-pass Possibilistic Clustering with Damped Window FootprintsUniversity of Missouri
-
Learning From Design Procedure To Generate CAD Programs for Data AugmentationToyota Research Institute
-
Fairness May Backfire: When Leveling-Down Occurs in Fair Machine LearningArizona State University, Xi'an Jiaotong University
MongoDB - Build AI That Scales
