How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining
Paper • 2609.35457 • Published • 55
xinming wang
ein66666
AI & ML interests
None yet
Recent Activity
upvoted a paper about 19 hours ago
How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining upvoted a paper about 1 month ago
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs upvoted a paper about 1 month ago
Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMsOrganizations
None yet
upvoted a paper about 19 hours ago