Beyond Prompt Count: How Data Shapes Transfer in On-Policy Distillation
Paper • 2609.37377 • Published
jiaxuan Wang
wyy1112
AI & ML interests
None yet
Recent Activity
authored a paper about 18 hours ago
Beyond Prompt Count: How Data Shapes Transfer in On-Policy Distillation submitted a paper 1 day ago
Beyond Prompt Count: How Data Shapes Transfer in On-Policy DistillationOrganizations
authored a
paper about 18 hours ago
submitted a
paper to Daily Papers 1 day ago
authored 4
papers 1 day ago
Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors
Paper • 2609.34344 • Published • 5
Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms
Paper • 2608.27409 • Published
Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling
Paper • 2604.08178 • Published
TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment
Paper • 2605.10194 • Published • 1
liked a
model 16 days ago
updated a
model 21 days ago
published a
model 21 days ago
upvoted a paper 3 months ago
liked a
dataset 6 months ago
updated a
dataset 6 months ago
published a
dataset 6 months ago