Daily Papers of 2024-11-13

1. Stronger Models are NOT Stronger Teachers for Instruction Tuning 27 upvotes, #1 of 2024-11-13
2. SAMPart3D: Segment Any Part in 3D Objects 25 upvotes, #2 of 2024-11-13
3. JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation 23 upvotes, #3 of 2024-11-13
4. BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions 21 upvotes, #4 of 2024-11-13
5. Scaling Properties of Diffusion Models for Perceptual Tasks 13 upvotes, #5 of 2024-11-13
6. Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodings 11 upvotes, #6 of 2024-11-13
7. Acoustic Volume Rendering for Neural Impulse Response Fields 5 upvotes, #7 of 2024-11-13
8. Hardware and Software Platform Inference 3 upvotes, #8 of 2024-11-13

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.