-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 27 -
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:2503.14456
-
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 28 -
MoDE: CLIP Data Experts via Clustering
Paper • 2404.16030 • Published • 14 -
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Paper • 2405.12130 • Published • 50 -
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 32
-
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders
Paper • 2503.03601 • Published • 221 -
Transformers without Normalization
Paper • 2503.10622 • Published • 143 -
RWKV-7 "Goose" with Expressive Dynamic State Evolution
Paper • 2503.14456 • Published • 131 -
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
Paper • 2503.11647 • Published • 126
-
RuCCoD: Towards Automated ICD Coding in Russian
Paper • 2502.21263 • Published • 126 -
Unified Reward Model for Multimodal Understanding and Generation
Paper • 2503.05236 • Published • 111 -
Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching
Paper • 2503.05179 • Published • 43 -
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Paper • 2503.05592 • Published • 25
-
Steel-LLM:From Scratch to Open Source -- A Personal Journey in Building a Chinese-Centric LLM
Paper • 2502.06635 • Published • 4 -
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
Paper • 2502.02737 • Published • 215 -
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models
Paper • 2501.03262 • Published • 98 -
MiniMax-01: Scaling Foundation Models with Lightning Attention
Paper • 2501.08313 • Published • 282
-
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Paper • 2502.05171 • Published • 130 -
Agency Is Frame-Dependent
Paper • 2502.04403 • Published • 22 -
Distillation Scaling Laws
Paper • 2502.08606 • Published • 46 -
LLM Pretraining with Continuous Concepts
Paper • 2502.08524 • Published • 28
-
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Paper • 2501.18585 • Published • 59 -
RWKV-7 "Goose" with Expressive Dynamic State Evolution
Paper • 2503.14456 • Published • 131 -
DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
Paper • 2503.15265 • Published • 44 -
Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
Paper • 2503.15558 • Published • 43