LSG checkpoints — When Sinks Help or Hurt (ECCV 2026 Oral, Spotlight)
0
11 commits
1 linked in READMEs
updated Aug 5, 2026
Layer-wise Sink Gating (LSG) gate checkpoints for
"When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models"
(arXiv:2604.03316). All checkpoints are
gate-only (non_lora_trainables.bin, well under 3 MB each); backbones are
loaded separately and remain unchanged.
| folder | backbone | configuration |
|---|---|---|
llava15_L10_PEFT/ | liuhaotian/llava-v1.5-7b | single layer L10 (paper main) |
llava15_stack_L3_6_7_10_19_PEFT/ | liuhaotian/llava-v1.5-7b | 5-layer stack {3,6,7,10,19} (paper main) |
crossarch_phi3_L20/ | xtuner/llava-phi-3-mini-hf | Appendix F Track A, L20 |
crossarch_qwen25_L4/ | Zhang199/TinyLLaVA-Qwen2.5-3B-SigLIP | Appendix F Track B, L4 (prior 1.25) |
Each folder ships the matching sink_cfg.json. The two LLaVA-1.5 folders keep the _PEFT suffix because the loader activates gate-only loading when the model_base directory name contains PEFT. Usage instructions:
github.com/JH-GEECS/lsg_public.
LSG checkpoints — When Sinks Help or Hurt (ECCV 2026 Oral, Spotlight)
0
11 commits
1 linked in READMEs
updated Aug 5, 2026
Layer-wise Sink Gating (LSG) gate checkpoints for
"When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models"
(arXiv:2604.03316). All checkpoints are
gate-only (non_lora_trainables.bin, well under 3 MB each); backbones are
loaded separately and remain unchanged.
| folder | backbone | configuration |
|---|---|---|
llava15_L10_PEFT/ | liuhaotian/llava-v1.5-7b | single layer L10 (paper main) |
llava15_stack_L3_6_7_10_19_PEFT/ | liuhaotian/llava-v1.5-7b | 5-layer stack {3,6,7,10,19} (paper main) |
crossarch_phi3_L20/ | xtuner/llava-phi-3-mini-hf | Appendix F Track A, L20 |
crossarch_qwen25_L4/ | Zhang199/TinyLLaVA-Qwen2.5-3B-SigLIP | Appendix F Track B, L4 (prior 1.25) |
Each folder ships the matching sink_cfg.json. The two LLaVA-1.5 folders keep the _PEFT suffix because the loader activates gate-only loading when the model_base directory name contains PEFT. Usage instructions:
github.com/JH-GEECS/lsg_public.
