Papers
-
A Causal Framework for Mitigating Data Shifts in Healthcare
-
The Equivalence Theorem: First-Class Relationships for Structurally Complete Database Systems
-
Orla: A Library for Serving LLM-Based Multi-Agent Systems
-
NCCL EP: Towards a Unified Expert Parallel Communication API for NCCL
-
A Grid-Based Framework for E-Scooter Demand Representation and Temporal Input Design for Deep Learning: Evidence from Austin, Texas
-
LLM Routing as Reasoning: A MaxSAT View
-
Robust Sequential Tracking via Bounded Information Geometry and Non-Parametric Field Actions
-
Egocentric World Model for Photorealistic Hand-Object Interaction Synthesis
-
Privacy-Preserving Federated Fraud Detection in Payment Transactions with NVIDIA FLARE
-
Design and evaluation of an agentic workflow for crisis-related synthetic tweet datasets
-
BERTology of Molecular Property Prediction
-
Locatability-Guided Adaptive Reasoning for Image Geo-Localization with Vision-Language Models
-
MedArena: Comparing LLMs for Medicine-in-the-Wild Clinician Preferences
-
Widespread Gender and Pronoun Bias in Moral Judgments Across LLMs
-
SemRep: Generative Code Representation Learning with Code Transformations
-
StatePlane: A Cognitive State Plane for Long-Horizon AI Systems Under Bounded Context
-
PLUME: Building a Network-Native Foundation Model for Wireless Traces via Protocol-Aware Tokenization
-
Benchmarking Large Language Models on Reference Extraction and Parsing in the Social Sciences and Humanities
-
Causal Attribution via Activation Patching
-
Privacy Preserving Topic-wise Sentiment Analysis of the Iran Israel USA Conflict Using Federated Transformer Models
-
Representation Learning for Spatiotemporal Physical SystemsFlatiron Institute, New York University, Princeton University, Université Paris Cité, University Paris-Saclay
-
XSkill: Continual Learning from Experience and Skills in Multimodal Agents
-
Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing
-
Flowcean - Model Learning for Cyber-Physical Systems
-
Neural Thickets: Diverse Task Experts Are Dense Around Pretrained WeightsMassachusetts Institute of Technology
-
Temporal Straightening for Latent PlanningBrown University, New York University, University of Toronto
-
Copula-ResLogit: A Deep-Copula Framework for Unobserved Confounding EffectsToronto Metropolitan University
-
Conversational AI-Enhanced Exploration System to Query Large-Scale Digitised Collections of Natural History MuseumsUniversity of Technology Sydney
-
MultiwayPAM: Multiway Partitioning Around Medoids for LLM-as-a-Judge Score Analysis
-
Quantum entanglement provides a competitive advantage in adversarial gamesCSIRO Clayton
-
Hybrid Self-evolving Structured Memory for GUI Agents
-
Simulation-in-the-Reasoning (SiR): A Conceptual Framework for Empirically Grounded AI in Autonomous Transportation
-
GaLoRA: Parameter-Efficient Graph-Aware LLMs for Node ClassificationSan Jose State University
-
Regime-aware financial volatility forecasting via in-context learningStanford University, University of Toronto
-
From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification
-
What do near-optimal learning rate schedules look like?
-
How to make the most of your masked language model for protein engineering
-
Is this Idea Novel? An Automated Benchmark for Judgment of Research IdeasNational Institute of Informatics, Technische Universität Dresden
-
Data-Driven Integration Kernels for Interpretable Nonlocal Operator LearningNVIDIA / Boston University, Lamont-Doherty Earth Observatory, New York University, University of California, University of Lausanne
-
Large language models can disambiguate opioid slang on social mediaStanford University
-
The Orthogonal Vulnerabilities of Generative AI Watermarks: A Comparative Empirical Benchmark of Spatial and Latent ProvenanceMillburn High School, Williamsville East High School
-
NasoVoce: A Nose-Mounted Low-Audibility Speech Interface for Always-Available Speech Interaction
-
PC-Diffuser: Path-Consistent Capsule CBF Safety Filtering for Diffusion-Based Trajectory PlannerTexas A&M University
-
Does Reasoning Make Search More Fair? Comparing Fairness in Reasoning and Non-Reasoning RerankersHuman Language Technology Center of Excellence, Johns Hopkins University
-
Fuel Gauge: Estimating Chain-of-Thought Length Ahead of Time in Large Multimodal ModelsUniversity of Texas
-
Overcoming Visual Clutter in Vision Language Action Models via Concept-Gated Visual DistillationUniversity of Technology Sydney, Western Sydney University
-
Federated Active Learning Under Extreme Non-IID and Global Class ImbalanceNanjing University of Aeronautics and Astronautics
-
On The Complexity of Best-Arm Identification in Non-Stationary Linear BanditsUniversity of Washington
-
EmoStory: Emotion-Aware Story GenerationShenzhen University
-
Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
MongoDB - Build AI That Scales
