Papers
-
Silicon Bureaucracy and AI Test-Oriented Education: Contamination Sensitivity and Score Confidence in LLM Benchmarks
-
No Dense Tensors Needed: Fully Sparse Object Detection on Event-Camera Voxel Grids
-
Engineering Distributed Governance for Regional Prosperity: A Socio-Technical Framework for Mitigating Under-Vibrancy via Human Data Engines
-
FedCVU: Federated Learning for Cross-View Video Understanding
-
MISApp: Multi-Hop Intent-Aware Session Graph Learning for Next App Prediction
-
Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks
-
TrustFed: Enabling Trustworthy Medical AI under Data Privacy Constraints
-
A Comparative Analysis of LLM Memorization at Statistical and Internal Levels: Cross-Model Commonalities and Model-Specific Signatures
-
OmniFM: Toward Modality-Robust and Task-Agnostic Federated Learning for Heterogeneous Medical Imaging
-
Cross-Scenario Deraining Adaptation with Unpaired Data: Superpixel Structural Priors and Multi-Stage Pseudo-Rain Synthesis
-
TAMTRL: Teacher-Aligned Reward Reshaping for Multi-Turn Reinforcement Learning in Long-Context Compression
-
HumanOmni-Speaker: Identifying Who said What and When
-
Optimal Memory Encoding Through Fluctuation-Response Structure
-
Rethinking Multimodal Fusion for Time Series: Auxiliary Modalities Need Constrained Fusion
-
PRM-as-a-Judge: A Dense Evaluation Paradigm for Fine-Grained Robotic Auditing
-
Optimizing Multi-Agent Weather Captioning via Text Gradient Descent: A Training-Free Approach with Consensus-Aware Gradient Fusion
-
SPINONet: Scalable Spiking Physics-informed Neural Operator for Computational Mechanics Applications
-
Thinking Deeper, Not Longer: Depth-Recurrent Transformers for Compositional Generalization
-
CoNBONet: Conformalized Neuroscience-inspired Bayesian Operator Network for Reliability Analysis
-
LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Signal Processing and its Application to Plug-and-Play Dereverberation
-
MIRAGE: The Illusion of Visual Understanding
-
AI Token Futures Market: Commoditization of Compute and Derivatives Contract Design
-
Reasoning Provenance for Autonomous AI Agents: Structured Behavioral Analytics Beyond State Checkpoints and Execution Traces
-
Deterministic Hallucination Detection in Medical VQA via Confidence-Evidence Bayesian Gain
-
RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing
-
MIND: Multi-agent inference for negotiation dialogue in travel planning
-
Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
-
A Blueprint for Self-Evolving Coding Agents in Vehicle Aerodynamic Drag Prediction
-
PPGL-Swarm: Integrated Multimodal Risk Stratification and Hereditary Syndrome Detection in Pheochromocytoma and Paraganglioma
-
Rethinking Token Reduction for Large Vision-Language Models
-
Data-Free Layer-Adaptive Merging via Fisher Information for Long-to-Short Reasoning LLMs
-
Compensating Visual Insufficiency with Stratified Language Guidance for Long-Tail Class Incremental Learning
-
When Exploration Comes for Free with Mixture-Greedy: Do we need UCB in Diversity-Aware Multi-Armed Bandits?
-
Uncertainty Quantification for Distribution-to-Distribution Flow Matching in Scientific Imaging
-
Probing How Scalable Table Data Enhances General Long-Context Reasoning
-
SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Models
-
FISformer: Replacing Self-Attention with a Fuzzy Inference System in Transformer Models for Time Series Forecasting
-
CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning
-
Three Creates All: You Only Sample 3 Steps
-
EvoIdeator: Evolving Scientific Ideas through Checklist-Grounded Reinforcement Learning
-
Cognitive Agency Surrender: Defending Epistemic Sovereignty via Scaffolded AI Friction
-
The Reasoning Error About Reasoning: Why Different Types of Reasoning Require Different Representational Structures
-
AI Co-Scientist for Ranking: Discovering Novel Search Ranking Models alongside LLM-based AI Agents with Cloud Computing Access
-
CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning
-
The Presupposition Problem in Representation Genesis
-
Getting to the Point: Why Pointing Improves LVLMs
-
Model selection in hybrid quantum neural networks with applications to quantum transformer architectures
-
Identifiability and amortized inference limitations in Kuramoto models
-
Let's Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework with Dynamic and Precise Visual Thoughts
-
Cycle Inverse-Consistent TransMorph: A Balanced Deep Learning Framework for Brain MRI Registration
MongoDB - Build AI That Scales
