Transformers and State-Space Models Unite, Multi-modal LLM Benchmark, Perplexity in Data Pruning, Advancing 4D Content Generation

AI Papers Podcast

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling 4Diffusion: Multi-view Video Diffusion Model for 4D Generation