Search papers, labs, and topics across Lattice.
13
0
12
NGS-Marker effectively thwarts partial infringement in 3D Gaussian Splatting, ensuring robust copyright protection for 3D assets.
Confidence miscalibration in medical AI can be mitigated, leading to both higher diagnostic accuracy and improved trust in clinical applications.
CLEAR achieves superior 3D Gaussian super-resolution by resolving gradient conflicts and optimizing low-resolution and high-resolution data in a single unified framework.
Living-Harness enables agents to learn from past failures dynamically, leading to substantial performance improvements in interactive tasks.
LAPO reveals that removing a single turn can significantly clarify its contribution to the overall reasoning process, leading to better performance in multi-turn search tasks.
LLMs can now be trained to prioritize task constraints intrinsically, resulting in a dramatic improvement in planning reliability.
Trajectory neglect in LLM agents can be significantly reduced using a novel reward mechanism that enhances focus on task goals without sacrificing training stability.
MLLMs can mislead medical professionals by misaligning confidence with accuracy, but a new calibration method cuts Expected Calibration Error by 40%.
Unreliable Gaussians are the root cause of artifacts in sparse-view 3D Gaussian Splatting, and modeling their reliability in both the optimization and observation domains dramatically improves reconstruction quality.
Forget balanced multimodal learning – letting the best modality lead the way actually unlocks better performance.
Reconstructing 3D scenes from images obscured by smoke and extreme darkness is now significantly more achievable, thanks to insights gleaned from the NTIRE 2026 challenge.
Compressing 3D Gaussian Splatting just got a whole lot better: GeoHCC maintains geometric integrity and rendering fidelity by explicitly modeling inter-anchor geometric correlations, outperforming existing anchor-based approaches.
MLLMs are often overconfident, but a new confidence-driven training and test-time scaling approach can boost accuracy by 8.8% across benchmarks.
