Collection by
9 days ago
9 days ago
Collections
Discover the best community collections!
Collections including paper arxiv:2501.08197
Collection by
4 days ago
4 days ago
-
2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
Paper • 2501.00958 • Published • 98 -
CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings
Paper • 2501.01257 • Published • 48 -
Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
Paper • 2501.01423 • Published • 36 -
REDUCIO! Generating 1024times1024 Video within 16 Seconds using Extremely Compressed Motion Latents
Paper • 2411.13552 • Published
Collection by
10 days ago
10 days ago
-
Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
Paper • 2411.11504 • Published • 20 -
Top-nσ: Not All Logits Are You Need
Paper • 2411.07641 • Published • 20 -
Adaptive Decoding via Latent Preference Optimization
Paper • 2411.09661 • Published • 10 -
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training
Paper • 2411.13476 • Published • 15
Collection by
6 days ago
6 days ago
-
MS MARCO Web Search: a Large-scale Information-rich Web Dataset with Millions of Real Click Labels
Paper • 2405.07526 • Published • 19 -
Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach
Paper • 2405.15613 • Published • 15 -
A Touch, Vision, and Language Dataset for Multimodal Alignment
Paper • 2402.13232 • Published • 15 -
How Do Large Language Models Acquire Factual Knowledge During Pretraining?
Paper • 2406.11813 • Published • 31
Collection by
4 days ago
4 days ago
-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 26 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 13 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 41 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 22