hongbin

L-Hongbin's activity

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

New activity in nvidia/Qwen3-30B-A3B-NVFP4 3 months ago

Is this model a MoE model from Qwen3-30B-A3B?

1

#2 opened 3 months ago by

L-Hongbin

commented 2 papers 4 months ago

Optimizing Large Language Models through Quantization: A Comparative Analysis of PTQ and QAT Techniques

Paper • 2411.06084 • Published Nov 9, 2024 •

1

DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models

Paper • 2504.09223 • Published Apr 12 •

1

commented 2 papers 8 months ago

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float

Paper • 2504.11651 • Published Apr 15 • 31 •

5

Agent models: Internalizing Chain-of-Action Generation into Reasoning models

Paper • 2503.06580 • Published Mar 9 • 20 •

3

commented 5 papers about 1 year ago

VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks

Paper • 2406.08394 • Published Jun 12, 2024 •

2

Instruction-guided Multi-Granularity Segmentation and Captioning with Large Multimodal Model

Paper • 2409.13407 • Published Sep 20, 2024 •

2

OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding

Paper • 2406.19389 • Published Jun 27, 2024 • 54 •

10

OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding

Paper • 2406.19389 • Published Jun 27, 2024 • 54 •

10

GLaMM: Pixel Grounding Large Multimodal Model

Paper • 2311.03356 • Published Nov 6, 2023 • 37 •

3