HarnessEval-W: Agentifying the Evaluation of Visual Worlds
Paper • 2608.16859 • Published • 123
AI & ML interests
None defined yet.
Recent Activity
MingyuLiu
authored 12
papers 1 day ago
AdvDex: Learning Dexterous Manipulation from Human Demonstrations via Joint-Aligned Actions and Adversarial Learning
Paper • 2608.14028 • Published
Perfect Demo Makes Poor Teacher: Learning Robust Alignment from Critical Motion Segments
Paper • 2606.15587 • Published
PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
Paper • 2503.06486 • Published
OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering
Paper • 2604.08209 • Published • 27
VideoAfford: Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Model
Paper • 2602.09638 • Published
World Guidance: World Modeling in Condition Space for Action Generation
Paper • 2602.22010 • Published • 16
Bridge Thinking and Acting: Unleashing Physical Potential of VLM with Generalizable Action Expert
Paper • 2510.03896 • Published
Learning Primitive Embodied World Models: Towards Scalable Robotic Learning
Paper • 2508.20840 • Published
Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model
Paper • 2508.06206 • Published • 1
Generative Video Matting
Paper • 2508.07905 • Published
VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
Paper • 2507.01016 • Published • 1
dongqianyu99
authored 2
papers 11 days ago
dongqianyu99
authored a
paper 11 months ago
MingyuLiu
authored 2
papers 11 months ago
dongqianyu99
authored a
paper 12 months ago
MingyuLiu
authored a
paper 12 months ago
MingyuLiu
authored a
paper about 1 year ago