Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models
Paper • 2609.34972 • Published • 30
🤝 Open to Collab
Wu Linquan
Svard
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models authored a paper 9 days ago
Draft-KV: Learning Useful Latent Communication Between Language Models submitted a paper 10 days ago
Draft-KV: Learning Useful Latent Communication Between Language ModelsOrganizations
None yet
upvoted a paper 8 days ago
upvoted a paper 10 days ago
upvoted 4
papers 9 months ago
ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
Paper • 2510.11606 • Published • 6
VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs
Paper • 2511.20272 • Published • 2
HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks
Paper • 2410.12381 • Published • 43
LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning
Paper • 2601.10129 • Published • 13