Daily Papers of 2024-08-02
- SAM 2: Segment Anything in Images and Videos 89 upvotes, #1 of 2024-08-02
- Gemma 2: Improving Open Language Models at a Practical Size 67 upvotes, #2 of 2024-08-02
- SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement 24 upvotes, #3 of 2024-08-02
- Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning 20 upvotes, #4 of 2024-08-02
- Coarse Correspondence Elicit 3D Spacetime Understanding in Multimodal Language Model 20 upvotes, #4 of 2024-08-02
- OmniParser for Pure Vision Based GUI Agent 16 upvotes, #6 of 2024-08-02
- TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models 10 upvotes, #7 of 2024-08-02
- MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities 10 upvotes, #7 of 2024-08-02
- Finch: Prompt-guided Key-Value Cache Compression 9 upvotes, #9 of 2024-08-02
- Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion 8 upvotes, #10 of 2024-08-02
- UniTalker: Scaling up Audio-Driven 3D Facial Animation through A Unified Model 8 upvotes, #10 of 2024-08-02
- Tails Tell Tales: Chapter-Wide Manga Transcriptions with Character Names 6 upvotes, #12 of 2024-08-02
- Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention 4 upvotes, #13 of 2024-08-02
- Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey 3 upvotes, #14 of 2024-08-02
- Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation 3 upvotes, #14 of 2024-08-02
- Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses 3 upvotes, #14 of 2024-08-02
- Enhancing Semantic Similarity Understanding in Arabic NLP with Nested Embedding Learning 2 upvotes, #17 of 2024-08-02
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.