Self-Distillation as a Performance Recovery Mechanism for LLMs: Counteracting Compression and Catastrophic Forgetting
Paper • 2604.15794 • Published • 2
Kailune-AI
CobraMamba
AI & ML interests
None yet
Recent Activity
liked a dataset 16 days ago
SWE-bench-Live/SWE-bench-Live liked a dataset 17 days ago
r0b0tlab/qwen3.8-max-glm5.2-kimi-k3-distillationOrganizations
None yet
upvoted a paper 4 days ago
liked a
dataset 16 days ago
liked 5
datasets 17 days ago
r0b0tlab/qwen3.8-max-glm5.2-kimi-k3-distillation
Viewer • Updated • 22.9M • 6.85k • 261
nvidia/Open-SWE-Traces
Viewer • Updated • 512k • 30.3k • 129
nvidia/Nemotron-SFT-SWE-v3.5
Viewer • Updated • 5.12k • 3.14k • 32
wjn922-01/scale-swe-distill5000-deepseek-v4-flash-0731-think-rollout4-instance3393-trajectories7928
Viewer • Updated • 7.93k • 185 • 1
AweAI-Team/Scale-SWE-Distilled-DeepSeek-v4-Pro-High-41k
Preview • Updated • 662 • 16
liked a
dataset 23 days ago
liked 2
models 23 days ago
liked a
model 25 days ago
liked a
model 27 days ago
liked a
model 28 days ago
liked a
model 29 days ago
liked a
dataset about 1 month ago
liked 5
models about 1 month ago
Qwen/Qwen3.8-27B
Image-Text-to-Text • 28B • Updated • 7.36M • • 15.6k
meta-models/Muse-Glimmer-30B
Image-Text-to-Text • 30B • Updated • 303k • • 1.91k
tsinghua-sigs-robot-lab/veriloop-coder-e1
Text Generation • 28B • Updated • 453 • 26
endless-frontier/BigBang-v1
Image-Text-to-Text • 36B • Updated • 1.6k • • 228
FrontisAI/Frontis-MA1-35B
Image-Text-to-Text • 36B • Updated • 161 • 24