Daily Papers of 2024-08-20

1. LongVILA: Scaling Long-Context Visual Language Models for Long Videos 50 upvotes, #1 of 2024-08-20
2. MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model 30 upvotes, #2 of 2024-08-20
3. Segment Anything with Multiple Modalities 19 upvotes, #3 of 2024-08-20
4. ShortCircuit: AlphaZero-Driven Circuit Design 14 upvotes, #4 of 2024-08-20
5. Factorized-Dreamer: Training A High-Quality Video Generator with Limited and Low-Quality Data 14 upvotes, #4 of 2024-08-20
6. NeuFlow v2: High-Efficiency Optical Flow Estimation on Edge Devices 11 upvotes, #6 of 2024-08-20
7. Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering 9 upvotes, #7 of 2024-08-20
8. SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views 9 upvotes, #7 of 2024-08-20
9. Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges 8 upvotes, #9 of 2024-08-20
10. TraDiffusion: Trajectory-Based Training-Free Image Generation 6 upvotes, #10 of 2024-08-20
11. Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risk of Language Models 4 upvotes, #11 of 2024-08-20

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.