AI & ML interests
Natural Language Processing
Recent Activity
View all activity
Papers
GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards
Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics
-
declare-lab/Trust-Data
Viewer • Updated • 32.3k • 157 • 1 -
declare-lab/trustalign_qwen2.5_0.5b
Text Generation • 0.5B • Updated • 9 -
declare-lab/trustalign_qwen2.5_1.5b
Text Generation • 2B • Updated • 7 • 1 -
declare-lab/trustalign_qwen2.5_3b
Text Generation • 3B • Updated • 2
TangoFlux models and data
-
declare-lab/Trust-Data
Viewer • Updated • 32.3k • 157 • 1 -
declare-lab/trustalign_qwen2.5_0.5b
Text Generation • 0.5B • Updated • 9 -
declare-lab/trustalign_qwen2.5_1.5b
Text Generation • 2B • Updated • 7 • 1 -
declare-lab/trustalign_qwen2.5_3b
Text Generation • 3B • Updated • 2