01

LOCALITY-AWARE GAUSSIAN COMPRESSION FOR FAST AND HIGH-QUALITY RENDERING

02

Exploiting Deblurring Networks for Radiance Fields

03

Elevating 3D Models: High-Quality Texture and Geometry Refinement from a Low-Quality Model

04

Review-driven Personalized Preference Reasoning with Large Language Models for Recommendation

05

Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation

06

Representation Shift: Unifying Token Compression with FlashAttention

07

Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval

08

EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality

9

Super-Class Guided Transformer for Zero-Shot Attribute Classification

10

VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning