-
Video Creation by Demonstration
Paper • 2412.09551 • Published • 8 -
DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation
Paper • 2412.07589 • Published • 45 -
Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation
Paper • 2412.06531 • Published • 71 -
APOLLO: SGD-like Memory, AdamW-level Performance
Paper • 2412.05270 • Published • 38
Collections
Discover the best community collections!
Collections including paper arxiv:2412.05270
-
VILA^2: VILA Augmented VILA
Paper • 2407.17453 • Published • 39 -
Octopus v4: Graph of language models
Paper • 2404.19296 • Published • 116 -
Octo-planner: On-device Language Model for Planner-Action Agents
Paper • 2406.18082 • Published • 47 -
Dolphin: Long Context as a New Modality for Energy-Efficient On-Device Language Models
Paper • 2408.15518 • Published • 42
-
Depth Anything V2
Paper • 2406.09414 • Published • 95 -
An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
Paper • 2406.09415 • Published • 50 -
Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
Paper • 2406.04338 • Published • 34 -
SAM 2: Segment Anything in Images and Videos
Paper • 2408.00714 • Published • 109
-
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
Paper • 2311.17049 • Published • 1 -
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Paper • 2405.04434 • Published • 14 -
A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision
Paper • 2303.17376 • Published -
Sigmoid Loss for Language Image Pre-Training
Paper • 2303.15343 • Published • 5
-
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 26 -
MoDE: CLIP Data Experts via Clustering
Paper • 2404.16030 • Published • 12 -
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Paper • 2405.12130 • Published • 46 -
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 28