Hugging Face Models on Foundry Managed Compute
• 21
AI & ML interests
None defined yet.
Recent Activity
Papers
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models
Articles
akolobov
published 2
models 16 minutes ago
akolobov
published 2
models 17 minutes ago
akolobov
published a
model 18 minutes ago
akolobov
updated a
dataset about 14 hours ago
ykim362
authored 5
papers 4 days ago
When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models
Paper • 2609.19671 • Published • 42
ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks
Paper • 2609.18805 • Published • 61
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation
Paper • 2609.08798 • Published • 81
Temporal Preference Optimization for Unsupervised Retrieval
Paper • 2606.17664 • Published • 1
Scaling Reasoning Efficiently via Relaxed On-Policy Distillation
Paper • 2603.11137 • Published • 1
junshim
submitted a
paper to Daily Papers 5 days ago
akolobov
updated 4
models 5 days ago
Reproducing CT-RATE retrieval numbers
6
#6 opened 4 months ago
by 
gings
Classification Probes
1
#8 opened 6 days ago
by 
KennySty
sharadagarwal
published a
dataset 11 days ago
sharadagarwal
updated a
dataset 11 days ago