-
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 • 43 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 22
Collections
Discover the best community collections!
Collections including paper arxiv:2410.00907
-
Addition is All You Need for Energy-efficient Language Models
Paper • 2410.00907 • Published • 146 -
Emu3: Next-Token Prediction is All You Need
Paper • 2409.18869 • Published • 94 -
An accurate detection is not all you need to combat label noise in web-noisy datasets
Paper • 2407.05528 • Published • 4 -
Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP
Paper • 2407.00402 • Published • 23
-
Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models
Paper • 2410.02740 • Published • 52 -
From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
Paper • 2410.01215 • Published • 32 -
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Paper • 2409.17146 • Published • 108 -
EuroLLM: Multilingual Language Models for Europe
Paper • 2409.16235 • Published • 26
-
Attention Heads of Large Language Models: A Survey
Paper • 2409.03752 • Published • 89 -
Transformer Explainer: Interactive Learning of Text-Generative Models
Paper • 2408.04619 • Published • 159 -
Addition is All You Need for Energy-efficient Language Models
Paper • 2410.00907 • Published • 146 -
DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining
Paper • 2305.10429 • Published • 3
-
RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
Paper • 2409.10516 • Published • 41 -
Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
Paper • 2409.11242 • Published • 7 -
Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models
Paper • 2409.11136 • Published • 23 -
On the Diagram of Thought
Paper • 2409.10038 • Published • 14
-
LinFusion: 1 GPU, 1 Minute, 16K Image
Paper • 2409.02097 • Published • 33 -
Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
Paper • 2409.11406 • Published • 26 -
Diffusion Models Are Real-Time Game Engines
Paper • 2408.14837 • Published • 123 -
Segment Anything with Multiple Modalities
Paper • 2408.09085 • Published • 22
-
Controllable Text Generation for Large Language Models: A Survey
Paper • 2408.12599 • Published • 65 -
xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations
Paper • 2408.12590 • Published • 36 -
Real-Time Video Generation with Pyramid Attention Broadcast
Paper • 2408.12588 • Published • 16 -
Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
Paper • 2408.11039 • Published • 59