Pinned Loading

1. OmniVTG OmniVTG Public

   [CVPR 2026] OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding

   Python 64 1

2. QuatRoPE QuatRoPE Public

   [CVPR 2026] Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models

   Python 21 2

3. CPL CPL Public

   [TPAMI 2026] Confidence-aware Pseudo-label Self-Correction for Weakly Supervised Visual Grounding

   Python 35

4. TaRO TaRO Public

   [ICML 2026] Temporal-Aware Reasoning Optimization for Video Temporal Grounding

   Python 19

5. APEIRIA APEIRIA Public

   [ICML 2026] Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs

   Python 17

6. HOI-Edit HOI-Edit Public

   [ICML 2026] Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework

   Python 4