qinqi

Dakerqi's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 4 days ago

SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning

Paper • 2506.01713 • Published 5 days ago • 30

upvoted 2 papers 22 days ago

EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models

Paper • 2505.09694 • Published 24 days ago • 18

EnerVerse-AC: Envisioning Embodied Environments with Action Condition

Paper • 2505.09723 • Published 24 days ago • 22

upvoted a paper 30 days ago

Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities

Paper • 2505.02567 • Published May 5 • 74

upvoted 2 papers about 2 months ago

OmniCaptioner: One Captioner to Rule Them All

Paper • 2504.07089 • Published Apr 9 • 20

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published Apr 7 • 105

upvoted 2 papers 2 months ago

Lumina-Image 2.0: A Unified and Efficient Image Generative Framework

Paper • 2503.21758 • Published Mar 27 • 22

LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis

Paper • 2503.21749 • Published Mar 27 • 26

upvoted a paper 3 months ago

Adversarial Data Collection: Human-Collaborative Perturbations for Efficient and Robust Robotic Imitation Learning

Paper • 2503.11646 • Published Mar 14 • 36

upvoted 2 papers 5 months ago

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Paper • 2501.09732 • Published Jan 16 • 72

EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation

Paper • 2501.01895 • Published Jan 3 • 56