Papers
-
Mapping Dark-Matter Clusters via Physics-Guided Diffusion Models
-
Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models
-
Unlocking the Latent Canvas: Eliciting and Benchmarking Symbolic Visual Expression in LLMs
-
Expanding mmWave Datasets for Human Pose Estimation with Unlabeled Data and LiDAR Datasets
-
High-Probability Bounds for SGD under the Polyak-Lojasiewicz Condition with Markovian Noise
-
Excited Pfaffians: Generalized Neural Wave Functions Across Structure and State
-
Learning to Forget: Sleep-Inspired Memory Consolidation for Resolving Proactive Interference in Large Language Models
-
VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning
-
MALicious INTent Dataset and Inoculating LLMs for Enhanced Disinformation Detection
-
LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion
-
Interp3R: Continuous-time 3D Geometry Estimation with Frames and Events
-
Emotional Cost Functions for AI Safety: Teaching Agents to Feel the Weight of Irreversible Consequences
-
Visualizing Critic Match Loss Landscapes for Interpretation of Online Reinforcement Learning Control Algorithms
-
Distilling Latent Manifolds: Resolution Extrapolation by Variational Autoencoders
-
Expert Mind: A Retrieval-Augmented Architecture for Expert Knowledge Preservation in the Energy Sector
-
ASAP: Attention-Shift-Aware Pruning for Efficient LVLM Inference
-
Learning to Order: Task Sequencing as In-Context Optimization
-
Evidential Domain Adaptation for Remaining Useful Life Prediction with Incomplete Degradation
-
An End-to-end Architecture for Collider Physics and Beyond
-
JobMatchAI An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search and Explainable AI
-
A comprehensive multimodal dataset and benchmark for ulcerative colitis scoring in endoscopy
-
Multilingual TinyStories: A Synthetic Combinatorial Corpus of Indic Children's Stories for Training Small Language Models
-
Top-b: Entropic Regulation of Relative Probability Bands in Autoregressive Language Processes
-
Rigorous Asymptotics for First-Order Algorithms Through the Dynamical Cavity Method
-
CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad
-
IQP Born Machines under Data-dependent and Agnostic Initialization Strategies
-
Covariance-Guided Resource Adaptive Learning for Efficient Edge Inference
-
Power-Law Spectrum of the Random Feature Model
-
Medical Image Spatial Grounding with Semantic Sampling
-
Machine Learning-Driven Intelligent Memory System Design: From On-Chip Caches to Storage
-
The Scenic Route to Deception: Dark Patterns and Explainability Pitfalls in Conversational Navigation
-
Texel Splatting: Perspective-Stable 3D Pixel Art
-
SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory
-
Adapting Critic Match Loss Landscape Visualization to Off-policy Reinforcement Learning
-
FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference
-
A Multi-Scale Graph Learning Framework with Temporal Consistency Constraints for Financial Fraud Detection in Transaction Networks under Non-Stationary Conditions
-
Parameter-Efficient Quality Estimation via Frozen Recursive Models
-
Scaling the Explanation of Multi-Class Bayesian Network Classifiers
-
D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing
-
A Loss Landscape Visualization Framework for Interpreting Reinforcement Learning: An ADHDP Case Study
-
$K-$means with learned metrics
-
$PA^3$: $\textbf{P}$olicy-$\textbf{A}$ware $\textbf{A}$gent $\textbf{A}$lignment through Chain-of-Thought
-
Tactile Modality Fusion for Vision-Language-Action Models
-
Delightful Policy Gradient
-
GroundSet: A Cadastral-Grounded Dataset for Spatial Understanding with Vector Data
-
Make it SING: Analyzing Semantic Invariants in Classifiers
-
PulmoVec: A Two-Stage Stacking Meta-Learning Architecture Built on the HeAR Foundation Model for Multi-Task Classification of Pediatric Respiratory Sounds
-
LLM-Augmented Release Intelligence: Automated Change Summarization and Impact Analysis in Cloud-Native CI/CD Pipelines
-
A Heterogeneous Ensemble for Multi-Center COVID-19 Classification from Chest CT Scans
-
Proactive Routing to Interpretable Surrogates with Distribution-Free Safety Guarantees
