When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
Paper • 2609.20511 • Published • 99
Taylor Killian
tkillian-byu
AI & ML interests
None yet
Recent Activity
authored a paper 3 days ago
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation authored a paper 3 days ago
LARK: Learnability-Grounded Trajectory Selection for Efficient Reasoning DistillationOrganizations
None yet
authored 8
papers 3 days ago
LARK: Learnability-Grounded Trajectory Selection for Efficient Reasoning Distillation
Paper • 2605.30651 • Published
From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning
Paper • 2606.18089 • Published
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
Paper • 2605.22138 • Published • 10
Concise Reasoning in the Lens of Lagrangian Optimization
Paper • 2510.10168 • Published
IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL
Paper • 2603.12151 • Published • 2
K2-V2: A 360-Open, Reasoning-Enhanced LLM
Paper • 2512.06201 • Published • 2
K2-Think: A Parameter-Efficient Reasoning System
Paper • 2509.07604 • Published • 14