Ao Wang

jameslahm's activity

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

upvoted a paper 13 days ago

OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data

Paper • 2606.13432 • Published 14 days ago • 109

upvoted a paper about 1 month ago

Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context

Paper • 2605.13831 • Published May 13 • 88

upvoted a paper 6 months ago

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

Paper • 2601.02151 • Published Jan 5 • 115

updated 6 models about 1 year ago

jameslahm/lsnet_b_distill

Image Classification • Updated Apr 4, 2025 • 4

jameslahm/lsnet_s_distill

Image Classification • Updated Apr 4, 2025 • 8

jameslahm/lsnet_b

Image Classification • Updated Apr 4, 2025 • 25 • 4

jameslahm/lsnet_s

Image Classification • Updated Apr 4, 2025 • 12 • 1

jameslahm/lsnet_t

Image Classification • Updated Apr 4, 2025 • 110

jameslahm/lsnet_t_distill

Image Classification • Updated Apr 4, 2025 • 6

New activity in jameslahm/lsnet_t about 1 year ago

Add image-classification pipeline tag

❤️ 1

1

#1 opened about 1 year ago by

nielsr

New activity in jameslahm/lsnet_s about 1 year ago

Add pipeline tag, remove redundant tag

❤️ 1

1

#1 opened about 1 year ago by

nielsr

New activity in jameslahm/lsnet_t_distill about 1 year ago

Update code link and add Github README content

❤️ 1

1

#1 opened about 1 year ago by

nielsr

New activity in jameslahm/lsnet_s_distill about 1 year ago

No changes needed

❤️ 1

1

#1 opened about 1 year ago by

nielsr

New activity in jameslahm/lsnet_b_distill about 1 year ago

Add image-classification pipeline tag and fix github URL

❤️ 1

1

#1 opened about 1 year ago by

nielsr

New activity in jameslahm/lsnet_b about 1 year ago

Add pipeline tag and usage example, remove library_tag

❤️ 1

1

#1 opened about 1 year ago by

nielsr

upvoted a paper about 1 year ago

LSNet: See Large, Focus Small

Paper • 2503.23135 • Published Mar 29, 2025 • 11

commented a paper about 1 year ago

LSNet: See Large, Focus Small

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

3

authored 3 papers about 1 year 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