Junhui He

junhuihe-hjh's activity

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

upvoted 2 papers about 21 hours ago

CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification

Paper • 2409.01366 • Published Sep 2, 2024 • 1

POP: Prefill-Only Pruning for Efficient Large Model Inference

Paper • 2602.03295 • Published 2 days ago • 4

liked a model 27 days ago

Qwen/Qwen3-VL-Embedding-8B

Feature Extraction • 8B • Updated 17 days ago • 225k • 324

liked 2 datasets about 2 months ago

lmms-lab/MMMU

Viewer • Updated Mar 8, 2024 • 11.6k • 27.1k • 7

lmms-lab/OCRBench-v2

Viewer • Updated Feb 9, 2025 • 10k • 1.05k • 12

liked 2 models about 2 months ago

zai-org/GLM-4.6V-Flash

Image-Text-to-Text • 10B • Updated Dec 9, 2025 • 28.4k • • 572

mistralai/Ministral-3-8B-Instruct-2512

9B • Updated 21 days ago • 35.8k • 140

liked 3 datasets about 2 months ago

liuhaotian/LLaVA-Instruct-150K

Preview • Updated Jan 3, 2024 • 3.08k • 570

openbmb/UltraChat

Viewer • Updated Feb 22, 2024 • 949k • 4k • 470

WizardLMTeam/WizardLM_evol_instruct_V2_196k

Viewer • Updated Mar 10, 2024 • 143k • 1.48k • 246

liked a model about 2 months ago

Qwen/Qwen3-VL-8B-Instruct

Image-Text-to-Text • 9B • Updated Oct 15, 2025 • 2.42M • • 725

liked a dataset about 2 months ago

xai-org/RealworldQA

Viewer • Updated Apr 18, 2024 • 765 • 1.41k • 117

liked a model 2 months ago

Qwen/Qwen3-4B-Instruct-2507

Text Generation • 4B • Updated Sep 17, 2025 • 3.15M • • 694

liked a dataset 2 months ago

HuggingFaceH4/ultrachat_200k

Viewer • Updated Oct 16, 2024 • 515k • 32.4k • 648

liked 5 models 3 months ago

liufanfanlff/C3-Context-Cascade-Compression

Text Generation • 3B • Updated Nov 21, 2025 • 151 • 4

flax-community/t5-vae-wiki

Updated Jul 19, 2021 • 1 • 1

thesephist/contra-bottleneck-t5-large-wikipedia

Text Generation • Updated Oct 9, 2023 • 111 • 20

inclusionAI/LLaDA2.0-mini-preview

Text Generation • 16B • Updated Dec 19, 2025 • 2.7k • 87

Qwen/Qwen3-4B

Text Generation • 4B • Updated Jul 26, 2025 • 5.04M • 544

liked a model 4 months ago

Qwen/Qwen3-4B-Thinking-2507

Text Generation • 4B • Updated Aug 6, 2025 • 437k • • 538