On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics
Paper • 2609.35259 • Published • 205
song bashan
songbashan
·
AI & ML interests
AI for cybersecurity, Natural Language Processing.
Recent Activity
upvoted a paper 13 days ago
On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics upvoted a paper 13 days ago
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video GenerationOrganizations
None yet
upvoted 4
papers 13 days ago
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
Paper • 2610.00686 • Published • 12
Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation
Paper • 2610.00348 • Published • 14
VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation
Paper • 2610.01499 • Published • 13