Daily Papers of 2025-07-03

1. Kwai Keye-VL Technical Report 118 upvotes, #1 of 2025-07-03
2. LongAnimation: Long Animation Generation with Dynamic Global-Local Memory 72 upvotes, #2 of 2025-07-03
3. Depth Anything at Any Condition 46 upvotes, #3 of 2025-07-03
4. A Survey on Vision-Language-Action Models: An Action Tokenization Perspective 30 upvotes, #4 of 2025-07-03
5. FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model 19 upvotes, #5 of 2025-07-03
6. Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation 18 upvotes, #6 of 2025-07-03
7. μ^2Tokenizer: Differentiable Multi-Scale Multi-Modal Tokenizer for Radiology Report Generation 15 upvotes, #7 of 2025-07-03
8. MARVIS: Modality Adaptive Reasoning over VISualizations 11 upvotes, #8 of 2025-07-03
9. ARIG: Autoregressive Interactive Head Generation for Real-time Conversations 10 upvotes, #9 of 2025-07-03
10. JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching 9 upvotes, #10 of 2025-07-03
11. Answer Matching Outperforms Multiple Choice for Language Model Evaluation 8 upvotes, #11 of 2025-07-03
12. STR-Match: Matching SpatioTemporal Relevance Score for Training-Free Video Editing 5 upvotes, #12 of 2025-07-03

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.