Daily Papers of 2024-08-22

1. TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models 52 upvotes, #1 of 2024-08-22
2. LLM Pruning and Distillation in Practice: The Minitron Approach 48 upvotes, #2 of 2024-08-22
3. FocusLLM: Scaling LLM's Context by Parallel Decoding 21 upvotes, #3 of 2024-08-22
4. TrackGo: A Flexible and Efficient Method for Controllable Video Generation 15 upvotes, #4 of 2024-08-22
5. GRAB: A Challenging GRaph Analysis Benchmark for Large Multimodal Models 6 upvotes, #5 of 2024-08-22
6. FRAP: Faithful and Realistic Text-to-Image Generation with Adaptive Prompt Weighting 4 upvotes, #6 of 2024-08-22
7. Iterative Object Count Optimization for Text-to-image Diffusion Models 4 upvotes, #6 of 2024-08-22
8. Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation 4 upvotes, #6 of 2024-08-22
9. Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification 3 upvotes, #9 of 2024-08-22
10. Unboxing Occupational Bias: Grounded Debiasing LLMs with U.S. Labor Data 3 upvotes, #9 of 2024-08-22
11. Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer 2 upvotes, #11 of 2024-08-22
12. Expanding FLORES+ Benchmark for more Low-Resource Settings: Portuguese-Emakhuwa Machine Translation Evaluation 2 upvotes, #11 of 2024-08-22

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.