Papers
-
Improving Visual Reasoning with Iterative Evidence Refinement
-
Low-Field Magnetic Resonance Image Quality Enhancement using Undersampled k-Space and Out-of-Distribution Generalisation
-
Towards Agentic Honeynet Configuration
-
Low-Field Magnetic Resonance Image Enhancement using Undersampled k-Space
-
The Institutional Scaling Law: Non-Monotonic Fitness, Capability-Trust Divergence, and Symbiogenetic Scaling in Generative AI
-
Implementation and discussion of the Pith Estimation on Rough Log End Images using Local Fourier Spectrum Analysis method
-
Diffusion Reinforcement Learning via Centered Reward Distillation
-
The GELATO Dataset for Legislative NER
-
Is the reconstruction loss culprit? An attempt to outperform JEPA
-
DualSwinFusionSeg: Multimodal Martian Landslide Segmentation via Dual Swin Transformer with Multi-Scale Fusion and UNet++
-
Solving physics-constrained inverse problems with conditional flow matching
-
Multifidelity Surrogate Modeling of Depressurized Loss of Forced Cooling in High-temperature Gas Reactors
-
MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos
-
An Alternative Trajectory for Generative AI
-
CIPHER: Culvert Inspection through Pairwise Frame Selection and High-Efficiency Reconstruction
-
Seeing Through the PRISM: Compound & Controllable Restoration of Scientific Images
-
SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation
-
Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories
-
Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate Networks
-
Clinician input steers frontier AI models toward both accurate and harmful decisions
-
MRGeo: Robust Cross-View Geo-Localization of Corrupted Images via Spatial and Channel Feature Enhancement
-
SDF-Net: Structure-Aware Disentangled Feature Learning for Opticall-SAR Ship Re-identification
-
CA-HFP: Curvature-Aware Heterogeneous Federated Pruning with Model Reconstruction
-
Early Pruning for Public Transport Routing
-
Maximizing Incremental Information Entropy for Contrastive Learning
-
Swap-guided Preference Learning for Personalized Reinforcement Learning from Human Feedback
-
Optimize Wider, Not Deeper: Consensus Aggregation for Policy Optimization
-
MIBench: Evaluating LMMs on Multimodal Interaction
-
Feynman: Knowledge-Infused Diagramming Agent for Scalable Visual Designs
-
Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating
-
A Prediction-as-Perception Framework for 3D Object Detection
-
A2Z-10M+: Geometric Deep Learning with A-to-Z BRep Annotations for AI-Assisted CAD Modeling and Reverse Engineering
-
EvoClaw: Evaluating AI Agents on Continuous Software Evolution
-
Mastering Negation: Boosting Grounding Models via Grouped Opposition-Based Learning
-
CarPLAN: Context-Adaptive and Robust Planning with Dynamic Scene Awareness for Autonomous Driving
-
FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control
-
A Deformable Attention-Based Detection Transformer with Cross-Scale Feature Fusion for Industrial Coil Spring Inspection
-
Dynamic Sparse Attention: Access Patterns and Architecture
-
Literary Narrative as Moral Probe : A Cross-System Framework for Evaluating AI Ethical Reasoning and Refusal Behavior
-
When Drafts Evolve: Speculative Decoding Meets Online Learning
-
Human-AI Collaborative Autonomous Experimentation With Proxy Modeling for Comparative Observation
-
Prompt-Driven Lightweight Foundation Model for Instance Segmentation-Based Fault Detection in Freight Trains
-
VLM4Rec: Multimodal Semantic Representation for Recommendation with Large Vision-Language Models
-
Batched Kernelized Bandits: Refinements and Extensions
-
Towards unified brain-to-text decoding across speech production and perception
-
The Economics of AI Supply Chain Regulation
-
Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents
-
Adaptive Diffusion Posterior Sampling for Data and Model Fusion of Complex Nonlinear Dynamical Systems
-
Weakly Time-Coupled Approximation of Markov Decision Processes
-
Using a Human-AI Teaming Approach to Create and Curate Scientific Datasets with the SCILIRE System
