Latent-Space Scoring Cuts Video Generation to 1-4 Steps

Also Worth Noting

• Phase-Preserving Trimodal Transformer for Tropical Forest Biomass Estimation Using Optical and PolInSAR Data score 4
  机构: Amazon; 关键词(1): fine-tuning
• Sparse-View Surface Reconstruction using Gaussian Splatting through High-Confidence Depth Propagation with Normal Priors score 4
  关键词(1): edge; 顶会接收: ECCV
• G$^2$TAM: Geometry Grounded Track Anything Model score 4
  关键词(1): reasoning; 顶会接收: ICML
• Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection score 4
  关键词(2): deployment, fine-tuning; 顶会接收: ECCV
• Q-TriM: Question-Guided Tri-Modal Attention for Audio-Visual Question Answering score 4
  关键词(1): reasoning; 顶会接收: ECCV
• MPSelectTune: Prompt-type Selection for Fine-tuning improves Concept Unlearning in LLMs score 4
  关键词(1): fine-tuning; 顶会接收: NeurIPS
• Reward Lightning: Fast Video Generation via Homologous Preference Distillation score 4
  关键词(1): distillation; 顶会接收: ECCV
• City-Level 3D Surface Reconstruction with Viewpoint Orientation Partitioning and Scene Completion score 3
  顶会接收: ECCV
• Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks score 3
  顶会接收: ICML
• BAT3R: Bootstrapping Articulated 3D Reconstruction from 2D Image Collections score 3
  顶会接收: ECCV
• DICT: Data Injection and Contrastive Trajectory Refinement for Conditional Image Generation with Diffusion Models score 3
  顶会接收: ECCV
• SAGE: Synchronized Action-Gaze Recognition and Anticipation for Human Behavior Understanding score 3
  顶会接收: ECCV