Junxian Li

Duke-de-Artois's activity

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

authored 3 papers 1 day ago

Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models

Paper • 2609.34972 • Published 10 days ago • 30

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction

Paper • 2609.32353 • Published 12 days ago • 8

TurboClear: One-Step Object-Effect Removal via Region-Calibrated Distribution Matching and Fusion

Paper • 2608.01288 • Published Aug 2

upvoted 2 papers 9 days ago

Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models

Paper • 2609.34972 • Published 10 days ago • 30

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction

Paper • 2609.32353 • Published 12 days ago • 8

submitted a paper to Daily Papers 9 days ago

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction

Paper • 2609.32353 • Published 12 days ago • 8

updated a model 10 days ago

Duke-de-Artois/LlaVA_refcoco_pure

Updated 10 days ago • 7

published a model 10 days ago

Duke-de-Artois/LlaVA_refcoco_pure

Updated 10 days ago • 7

commented a paper 16 days ago

SlowBA: An efficiency backdoor attack towards VLM-based GUI agents

Paper • 2603.08316 • Published Mar 9 • 1 •

3

updated a model 21 days ago

Duke-de-Artois/LlaVA_lora_refcoco_iag

Updated 21 days ago • 20

published a model 21 days ago

Duke-de-Artois/LlaVA_lora_refcoco_iag

Updated 21 days ago • 20

updated a model 21 days ago

Duke-de-Artois/Refcoco_internvl_iag

8B • Updated 21 days ago • 4

published a model 21 days ago

Duke-de-Artois/Refcoco_internvl_iag

8B • Updated 21 days ago • 4

upvoted a paper 28 days ago

What Did I Just Say? Self-Listening for Full-Duplex Speech Models

Paper • 2609.05592 • Published Sep 4 • 25

upvoted a paper 3 months ago

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Paper • 2607.14952 • Published Jul 16 • 92

published a model 3 months ago

Duke-de-Artois/SlowBA_ckpt

4B • Updated Jun 29 • 1

updated a model 3 months ago

Duke-de-Artois/SlowBA_ckpt

4B • Updated Jun 29 • 1

authored a paper 5 months ago

$δ$-mem: Efficient Online Memory for Large Language Models

Paper • 2605.12357 • Published May 12 • 133

upvoted a paper 5 months ago

δ-mem: Efficient Online Memory for Large Language Models

Paper • 2605.12357 • Published May 12 • 133

authored a paper 7 months ago

SlowBA: An efficiency backdoor attack towards VLM-based GUI agents

Paper • 2603.08316 • Published Mar 9 • 1