arxiv:2509.16198
ymh233
ymh233
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
ActionOPD: Distilling Decisions, Not Tokens upvoted a paper 9 days ago
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight liked a dataset 13 days ago
RealSR/SciLaws-BenchOrganizations
models 11
ymh233/swe_traj
Updated
ymh233/Focal_pretrain-Qwen-Qwen2.5-Coder-1.5B-NTE-d512-w0.1-zw1_1_1-20251217_step_10000
2B • Updated • 6
ymh233/Focal_pretrain-Qwen-Qwen2.5-Coder-1.5B-NTE-d512-w0.01-zw1_1_1-20251216_step_10000
2B • Updated • 5
ymh233/Focal_pretrain-Qwen-Qwen2.5-Coder-1.5B-NTE-d512-w0-zw1_1_1-20251216_step_10000
2B • Updated • 6
ymh233/Focal_pretrain-Qwen-Qwen2.5-Coder-1.5B-NTE-d512-w0.1-zw1_1_1-minspan2-20251217_step_10000
2B • Updated • 3
ymh233/Focal_pretrain-Qwen-Qwen2.5-Coder-1.5B-NTE-d512-w0.1-longest_only-20251218_step_10000
2B • Updated • 4
ymh233/Focal_pretrain-Qwen-Qwen2.5-Coder-1.5B-NTE-d512-w0.1-zw1_1_1-minspan2-20251217_step_19000
2B • Updated • 6
ymh233/Focal_pretrain-Llama-3.2-1B-NTE-d512-w0-20251218_step_8000
1B • Updated • 9
ymh233/Focal_pretrain-Llama-3.2-1B-NTE-d512-w0.1-longest_only-20251218_step_8000
1B • Updated • 6
ymh233/Focal_nvidia-OpenReasoning-Nemotron-1.5B-nemotron_code_lf_filtered-train_prompt-lr1e-04-ep3
2B • Updated • 6
datasets 0
None public yet