Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness Paper • 2604.12373 • Published 18 days ago • 9
SpectralSplats: Robust Differentiable Tracking via Spectral Moment Supervision Paper • 2603.24036 • Published Mar 25 • 13
SpectralSplats: Robust Differentiable Tracking via Spectral Moment Supervision Paper • 2603.24036 • Published Mar 25 • 13
Alignment Makes Language Models Normative, Not Descriptive Paper • 2603.17218 • Published Mar 17 • 46
SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis Paper • 2603.13884 • Published Mar 14 • 3
Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods Paper • 2603.15026 • Published Mar 16 • 8
Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models Paper • 2602.02600 • Published Feb 1 • 13
LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals Paper • 2601.10700 • Published Jan 15 • 18
The Poisoned Apple Effect: Strategic Manipulation of Mediated Markets via Technology Expansion of AI Agents Paper • 2601.11496 • Published Jan 16 • 47
CaricatureGS: Exaggerating 3D Gaussian Splatting Faces With Gaussian Curvature Paper • 2601.03319 • Published Jan 6 • 54
RadarGen: Automotive Radar Point Cloud Generation from Cameras Paper • 2512.17897 • Published Dec 19, 2025 • 18
Learning Eigenstructures of Unstructured Data Manifolds Paper • 2512.01103 • Published Nov 30, 2025 • 6
InstructMix2Mix: Consistent Sparse-View Editing Through Multi-View Model Personalization Paper • 2511.14899 • Published Nov 18, 2025 • 12
High-Perceptual Quality JPEG Decoding via Posterior Sampling Paper • 2211.11827 • Published Nov 21, 2022