Models
Datasets
Spaces
Docs
Enterprise
Pricing
Log In
Sign Up

Collections

Discover the best community collections!

Collections including paper arxiv:2502.13063

about 17 hours ago

EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

Paper • 2402.04252 • Published Feb 6, 2024 • 29
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models

Paper • 2402.03749 • Published Feb 6, 2024 • 13
ScreenAI: A Vision-Language Model for UI and Infographics Understanding

Paper • 2402.04615 • Published Feb 7, 2024 • 44
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss

Paper • 2402.05008 • Published Feb 7, 2024 • 23

Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published Feb 18 • 73

InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU

Paper • 2502.08910 • Published Feb 13 • 149
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published Feb 18 • 73
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Paper • 2502.11089 • Published Feb 16 • 165
LLM Pretraining with Continuous Concepts

Paper • 2502.08524 • Published Feb 12 • 29

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Paper • 2409.10516 • Published Sep 16, 2024 • 44
Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse

Paper • 2409.11242 • Published Sep 17, 2024 • 7
Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models

Paper • 2409.11136 • Published Sep 17, 2024 • 25
On the Diagram of Thought

Paper • 2409.10038 • Published Sep 16, 2024 • 14

LM Capabilities and Scaling

Compression Represents Intelligence Linearly

Paper • 2404.09937 • Published Apr 15, 2024 • 29
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Paper • 2404.06395 • Published Apr 9, 2024 • 23
Long-context LLMs Struggle with Long In-context Learning

Paper • 2404.02060 • Published Apr 2, 2024 • 38
Are large language models superhuman chemists?

Paper • 2404.01475 • Published Apr 1, 2024 • 19

Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published Feb 18 • 73

Magma: A Foundation Model for Multimodal AI Agents

Paper • 2502.13130 • Published Feb 18 • 58
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published Feb 18 • 73

Large Language Models Think Too Fast To Explore Effectively

Paper • 2501.18009 • Published Jan 29 • 24
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published Jan 28 • 123
Intuitive physics understanding emerges from self-supervised pretraining on natural videos

Paper • 2502.11831 • Published Feb 17 • 20
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published Feb 18 • 73

Perception and abstraction. Each modality is tokenized and embedded into vectors for model to comprehend.

VILA^2: VILA Augmented VILA

Paper • 2407.17453 • Published Jul 24, 2024 • 42
Octopus v4: Graph of language models

Paper • 2404.19296 • Published Apr 30, 2024 • 119
Octo-planner: On-device Language Model for Planner-Action Agents

Paper • 2406.18082 • Published Jun 26, 2024 • 49
Dolphin: Long Context as a New Modality for Energy-Efficient On-Device Language Models

Paper • 2408.15518 • Published Aug 28, 2024 • 43

about 17 hours ago

EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

Paper • 2402.04252 • Published Feb 6, 2024 • 29
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models

Paper • 2402.03749 • Published Feb 6, 2024 • 13
ScreenAI: A Vision-Language Model for UI and Infographics Understanding

Paper • 2402.04615 • Published Feb 7, 2024 • 44
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss

Paper • 2402.05008 • Published Feb 7, 2024 • 23

Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published Feb 18 • 73

Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published Feb 18 • 73

Magma: A Foundation Model for Multimodal AI Agents

Paper • 2502.13130 • Published Feb 18 • 58
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published Feb 18 • 73

InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU

Paper • 2502.08910 • Published Feb 13 • 149
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published Feb 18 • 73
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Paper • 2502.11089 • Published Feb 16 • 165
LLM Pretraining with Continuous Concepts

Paper • 2502.08524 • Published Feb 12 • 29

Large Language Models Think Too Fast To Explore Effectively

Paper • 2501.18009 • Published Jan 29 • 24
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published Jan 28 • 123
Intuitive physics understanding emerges from self-supervised pretraining on natural videos

Paper • 2502.11831 • Published Feb 17 • 20
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published Feb 18 • 73

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Paper • 2409.10516 • Published Sep 16, 2024 • 44
Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse

Paper • 2409.11242 • Published Sep 17, 2024 • 7
Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models

Paper • 2409.11136 • Published Sep 17, 2024 • 25
On the Diagram of Thought

Paper • 2409.10038 • Published Sep 16, 2024 • 14

Perception and abstraction. Each modality is tokenized and embedded into vectors for model to comprehend.

VILA^2: VILA Augmented VILA

Paper • 2407.17453 • Published Jul 24, 2024 • 42
Octopus v4: Graph of language models

Paper • 2404.19296 • Published Apr 30, 2024 • 119
Octo-planner: On-device Language Model for Planner-Action Agents

Paper • 2406.18082 • Published Jun 26, 2024 • 49
Dolphin: Long Context as a New Modality for Energy-Efficient On-Device Language Models

Paper • 2408.15518 • Published Aug 28, 2024 • 43

LM Capabilities and Scaling

Compression Represents Intelligence Linearly

Paper • 2404.09937 • Published Apr 15, 2024 • 29
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Paper • 2404.06395 • Published Apr 9, 2024 • 23
Long-context LLMs Struggle with Long In-context Learning

Paper • 2404.02060 • Published Apr 2, 2024 • 38
Are large language models superhuman chemists?

Paper • 2404.01475 • Published Apr 1, 2024 • 19

Company

TOS Privacy About Jobs

Website

Models Datasets Spaces Pricing Docs