Daily Papers of 2024-05-15
- Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory 24 upvotes, #1 of 2024-05-15
- Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning 18 upvotes, #2 of 2024-05-15
- Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding 17 upvotes, #3 of 2024-05-15
- Compositional Text-to-Image Generation with Dense Blob Representations 11 upvotes, #4 of 2024-05-15
- Understanding the performance gap between online and offline alignment algorithms 11 upvotes, #4 of 2024-05-15
- No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding 10 upvotes, #6 of 2024-05-15
- SpeechVerse: A Large-scale Generalizable Audio Language Model 9 upvotes, #7 of 2024-05-15
- SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models 8 upvotes, #8 of 2024-05-15
Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.