PhyRubric: Rubric-Grounded Diagnostic Evaluation of Physical Commonsense in Text-to-Video Generation
1 version
WK
Weitai Kang
cs.CVcs.AIcs.CLcs.LG
On Valency
published · living versionsPreprints & journals
15 papers in the corpus · 2024–2026HeroFrame-Bench: Reference-Anchored Evaluation via Rubric--Ranking Co-Evolution for Movie Hero Frame Selection
0 citations
CueKFS: Agentic Cue-Driven Keyframe Selection for Long Video Understanding
0 citations
Inline Critic Steers Image Editing
0 citations
ExpVG: Investigating the Design Space of Visual Grounding in Multimodal Large Language Model
0 citations
GuirlVG: Incentivize GUI Visual Grounding via Empirical Exploration on Reinforcement Learning
0 citations
InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction
0 citations
3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation
0 citations
Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning
6 citations
Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner
0 citations
SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding
13 citations
Visual Grounding with Attention-Driven Constraint Balancing
2 citations
ACTRESS: Active Retraining for Semi-supervised Visual Grounding
1 citation
Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention
1 citation
On the Faithfulness of Vision Transformer Explanations
15 citations
Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer
14 citations
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.