AbstractionLayer

SatoHaruto's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 1 month ago

SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models

Paper • 2503.07605 • Published Mar 10 • 68

upvoted 19 papers about 2 months ago

SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension

Paper • 2404.16790 • Published Apr 25, 2024 • 9

NeRF-XL: Scaling NeRFs with Multiple GPUs

Paper • 2404.16221 • Published Apr 24, 2024 • 15

Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings

Paper • 2404.16820 • Published Apr 25, 2024 • 17

ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving

Paper • 2404.16771 • Published Apr 25, 2024 • 20

Interactive3D: Create What You Want by Interactive 3D Generation

Paper • 2404.16510 • Published Apr 25, 2024 • 21

List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs

Paper • 2404.16375 • Published Apr 25, 2024 • 18

Make Your LLM Fully Utilize the Context

Paper • 2404.16811 • Published Apr 25, 2024 • 55

How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Paper • 2404.16821 • Published Apr 25, 2024 • 60

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Paper • 2404.16710 • Published Apr 25, 2024 • 80

BASS: Batched Attention-optimized Speculative Sampling

Paper • 2404.15778 • Published Apr 24, 2024 • 10

XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference

Paper • 2404.15420 • Published Apr 23, 2024 • 10

MaGGIe: Masked Guided Gradual Human Instance Matting

Paper • 2404.16035 • Published Apr 24, 2024 • 10

ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning

Paper • 2404.15449 • Published Apr 23, 2024 • 13

MotionMaster: Training-free Camera Motion Transfer For Video Generation

Paper • 2404.15789 • Published Apr 24, 2024 • 12

MoDE: CLIP Data Experts via Clustering

Paper • 2404.16030 • Published Apr 24, 2024 • 14

PuLID: Pure and Lightning ID Customization via Contrastive Alignment

Paper • 2404.16022 • Published Apr 24, 2024 • 25

CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data

Paper • 2404.15653 • Published Apr 24, 2024 • 29

Transformers Can Represent n-gram Language Models

Paper • 2404.14994 • Published Apr 23, 2024 • 21

Pegasus-v1 Technical Report

Paper • 2404.14687 • Published Apr 23, 2024 • 33