Daily Papers of 2024-07-30
- SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain 59 upvotes, #1 of 2024-07-30
- Integrating Large Language Models into a Tri-Modal Architecture for Automated Depression Classification 55 upvotes, #2 of 2024-07-30
- SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages 52 upvotes, #3 of 2024-07-30
- FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention 47 upvotes, #4 of 2024-07-30
- Theia: Distilling Diverse Vision Foundation Models for Robot Learning 45 upvotes, #5 of 2024-07-30
- MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains 37 upvotes, #6 of 2024-07-30
- MindSearch: Mimicking Human Minds Elicits Deep AI Searcher 37 upvotes, #6 of 2024-07-30
- Mixture of Nested Experts: Adaptive Processing of Visual Tokens 33 upvotes, #8 of 2024-07-30
- Diffusion Feedback Helps CLIP See Better 33 upvotes, #8 of 2024-07-30
- Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning 30 upvotes, #10 of 2024-07-30
- Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models 22 upvotes, #11 of 2024-07-30
- 3D Question Answering for City Scene Understanding 21 upvotes, #12 of 2024-07-30
- Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle 20 upvotes, #13 of 2024-07-30
- Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge 19 upvotes, #14 of 2024-07-30
- ATHAR: A High-Quality and Diverse Dataset for Classical Arabic to English Translation 19 upvotes, #14 of 2024-07-30
- ImagiNet: A Multi-Content Dataset for Generalizable Synthetic Image Detection via Contrastive Learning 19 upvotes, #14 of 2024-07-30
- WalkTheDog: Cross-Morphology Motion Alignment via Phase Manifolds 12 upvotes, #17 of 2024-07-30
- Bridging the Gap: Studio-like Avatar Creation from a Monocular Phone Capture 12 upvotes, #17 of 2024-07-30
- Sentiment Analysis of Lithuanian Online Reviews Using Large Language Models 12 upvotes, #17 of 2024-07-30
- TAPTRv2: Attention-based Position Update Improves Tracking Any Point 10 upvotes, #20 of 2024-07-30
- VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks 10 upvotes, #20 of 2024-07-30
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.