CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-centric 3D Scene Generation Paper • 2607.03819 • Published Jul 4 • 11
EarlyTom: Early Token Compression Completes Fast Video Understanding Paper • 2605.30010 • Published May 28 • 30
PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks Paper • 2605.10977 • Published May 9 • 10
Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View Paper • 2503.12553 • Published Mar 16, 2025 • 8
Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models Paper • 2503.16257 • Published Mar 20, 2025 • 28
