Papers
-
DeepXplain: XAI-Guided Autonomous Defense Against Multi-Stage APT Campaigns
-
More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection
-
Identity-Consistent Video Generation under Large Facial-Angle Variations
-
The Average Relative Entropy and Transpilation Depth determines the noise robustness in Variational Quantum Classifiers
-
Enhancing reasoning accuracy in large language models during inference time
-
F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting
-
Privacy-Preserving Federated Action Recognition via Differentially Private Selective Tuning and Efficient Communication
-
Direct Interval Propagation Methods using Neural-Network Surrogates for Uncertainty Quantification in Physical Systems Surrogate Model
-
Test-Time Adaptation via Cache Personalization for Facial Expression Recognition in Videos
-
FluidWorld: Reaction-Diffusion Dynamics as a Predictive Substrate for World Models
-
HELIX: Scaling Raw Audio Understanding with Hybrid Mamba-Attention Beyond the Quadratic Limit
-
Bridging neuroscience and AI: adaptive, culturally sensitive technologies transforming aphasia rehabilitation
-
Stream separation improves Bregman conditioning in transformers
-
Active Inference Agency Formalization, Metrics, and Convergence Assessments
-
Improving Coherence and Persistence in Agentic AI for System Optimization
-
Which Alert Removals are Beneficial?
-
B-jet Tagging Using a Hybrid Edge Convolution and Transformer Architecture
-
KHMP: Frequency-Domain Kalman Refinement for High-Fidelity Human Motion Prediction
-
COINBench: Moving Beyond Individual Perspectives to Collective Intent Understanding
-
FinRL-X: An AI-Native Modular Infrastructure for Quantitative Trading
-
AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search
-
EmoTaG: Emotion-Aware Talking Head Synthesis on Gaussian Splatting with Few-Shot Personalization
-
TimeTox: An LLM-Based Pipeline for Automated Extraction of Time Toxicity from Clinical Trial Protocols
-
ARYA: A Physics-Constrained Composable & Deterministic World Model Architecture
-
RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models
-
Generalized Discrete Diffusion from Snapshots
-
The AI Scientific Community: Agentic Virtual Lab Swarms
-
Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution
-
Respiratory Status Detection with Video Transformers
-
Beyond Memorization: Distinguishing between Reductive and Epistemic Reasoning in LLMs using Classic Logic Puzzles
-
The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
-
FluidGaussian: Propagating Simulation-Based Uncertainty Toward Functionally-Intelligent 3D Reconstruction
-
AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling
-
Benchmarking Bengali Dialectal Bias: A Multi-Stage Framework Integrating RAG-Based Translation and Human-Augmented RLAIF
-
AdaRubric: Task-Adaptive Rubrics for LLM Agent Evaluation
-
TIDE: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference
-
Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation
-
Conspiracy Frame: a Semiotically-Driven Approach for Conspiracy Theories Detection
-
PLR: Plackett-Luce for Reordering In-Context Learning Examples
-
Constrained Online Convex Optimization with Memory and Predictions
-
A transformer architecture alteration to incentivise externalised reasoning
-
HamVision: Hamiltonian Dynamics as Inductive Bias for Medical Image Analysis
-
An InSAR Phase Unwrapping Framework for Large-scale and Complex Events
-
PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost
-
Mitigating Objectness Bias and Region-to-Text Misalignment for Open-Vocabulary Panoptic Segmentation
-
Knowledge Priors for Identity-Disentangled Open-Set Privacy-Preserving Video FER
-
Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models
-
A Generalised Exponentiated Gradient Approach to Enhance Fairness in Binary and Multi-class Classification Tasks
-
Mechanisms of Introspective Awareness
-
STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems
MongoDB - Build AI That Scales
