Ao Wang

jameslahm's activity

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

upvoted a paper 4 days ago

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting

Paper • 2601.02151 • Published 8 days ago • 92

updated 6 models 9 months ago

jameslahm/lsnet_b_distill

Image Classification • Updated Apr 4, 2025 • 14

jameslahm/lsnet_s_distill

Image Classification • Updated Apr 4, 2025 • 15

jameslahm/lsnet_b

Image Classification • Updated Apr 4, 2025 • 59 • 4

jameslahm/lsnet_s

Image Classification • Updated Apr 4, 2025 • 43 • 1

jameslahm/lsnet_t

Image Classification • Updated Apr 4, 2025 • 57

jameslahm/lsnet_t_distill

Image Classification • Updated Apr 4, 2025 • 9

New activity in jameslahm/lsnet_t 9 months ago

Add image-classification pipeline tag

❤️ 1

1

#1 opened 9 months ago by

nielsr

New activity in jameslahm/lsnet_s 9 months ago

Add pipeline tag, remove redundant tag

❤️ 1

1

#1 opened 9 months ago by

nielsr

New activity in jameslahm/lsnet_t_distill 9 months ago

Update code link and add Github README content

❤️ 1

1

#1 opened 9 months ago by

nielsr

New activity in jameslahm/lsnet_s_distill 9 months ago

No changes needed

❤️ 1

1

#1 opened 9 months ago by

nielsr

New activity in jameslahm/lsnet_b_distill 9 months ago

Add image-classification pipeline tag and fix github URL

❤️ 1

1

#1 opened 9 months ago by

nielsr

New activity in jameslahm/lsnet_b 9 months ago

Add pipeline tag and usage example, remove library_tag

❤️ 1

1

#1 opened 9 months ago by

nielsr

upvoted a paper 10 months ago

LSNet: See Large, Focus Small

Paper • 2503.23135 • Published Mar 29, 2025 • 11

commented a paper 10 months ago

LSNet: See Large, Focus Small

Paper • 2503.23135 • Published Mar 29, 2025 • 11 •

3

authored 5 papers 10 months ago

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

Paper • 2412.05819 • Published Dec 8, 2024

LSNet: See Large, Focus Small

Paper • 2503.23135 • Published Mar 29, 2025 • 11

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation

Paper • 2412.03409 • Published Dec 4, 2024

YOLOE: Real-Time Seeing Anything

Paper • 2503.07465 • Published Mar 10, 2025 • 16

RepViT: Revisiting Mobile CNN From ViT Perspective

Paper • 2307.09283 • Published Jul 18, 2023 • 2