🤝 Open to Collab
Siyuan Wang
OldKingMeister
AI & ML interests
ML system
Recent Activity
reacted to tardellirs's post with 👍 about 6 hours ago
Crivo-150M is now on the Pareto frontier of the Decision Index 🎯
Scored by the maintainers on the private tests: Full 22.21, the best of all submissions at or below 150M and higher than every model below 0.75B, including models up to 4× its size. Median latency on the board's GPU: 13 ms.
It is a 149M typed-decision encoder (Ettin / ModernBERT): a state plus choice, noul or score questions in, a probability for every option out, in one forward pass. Trained on open data only.
Next: tasks from new domains, the weak spot of every small encoder on the board.
https://huggingface.co/tardellirs/crivo-150m
https://huggingface.co/spaces/multimodalart/jev-decision-index
Thanks to @multimodalart for the Decision Index and its open kit, @orionweller and the Ettin team, @tomaarsen for the Ettin rerankers, @hotchpotch for the Bekko System One data and @sileod for tasksource. reacted to tardellirs's post with 😎 about 6 hours ago
Crivo-150M is now on the Pareto frontier of the Decision Index 🎯
Scored by the maintainers on the private tests: Full 22.21, the best of all submissions at or below 150M and higher than every model below 0.75B, including models up to 4× its size. Median latency on the board's GPU: 13 ms.
It is a 149M typed-decision encoder (Ettin / ModernBERT): a state plus choice, noul or score questions in, a probability for every option out, in one forward pass. Trained on open data only.
Next: tasks from new domains, the weak spot of every small encoder on the board.
https://huggingface.co/tardellirs/crivo-150m
https://huggingface.co/spaces/multimodalart/jev-decision-index
Thanks to @multimodalart for the Decision Index and its open kit, @orionweller and the Ettin team, @tomaarsen for the Ettin rerankers, @hotchpotch for the Bekko System One data and @sileod for tasksource. reacted to tardellirs's post with 🔥 about 6 hours ago
Crivo-150M is now on the Pareto frontier of the Decision Index 🎯
Scored by the maintainers on the private tests: Full 22.21, the best of all submissions at or below 150M and higher than every model below 0.75B, including models up to 4× its size. Median latency on the board's GPU: 13 ms.
It is a 149M typed-decision encoder (Ettin / ModernBERT): a state plus choice, noul or score questions in, a probability for every option out, in one forward pass. Trained on open data only.
Next: tasks from new domains, the weak spot of every small encoder on the board.
https://huggingface.co/tardellirs/crivo-150m
https://huggingface.co/spaces/multimodalart/jev-decision-index
Thanks to @multimodalart for the Decision Index and its open kit, @orionweller and the Ettin team, @tomaarsen for the Ettin rerankers, @hotchpotch for the Bekko System One data and @sileod for tasksource.Organizations
-
Self-Distillation Enables Continual Learning
Paper • 2601.19897 • Published • 41 -
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
Paper • 2601.21468 • Published • 25 -
Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents
Paper • 2509.23040 • Published • 12
-
Self-Distillation Enables Continual Learning
Paper • 2601.19897 • Published • 41 -
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
Paper • 2601.21468 • Published • 25 -
Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents
Paper • 2509.23040 • Published • 12
models 6
OldKingMeister/kaggriculture-research-archive-20261013
Reinforcement Learning • Updated
OldKingMeister/llama-3-8b-instruct-lmsys-arena-final
Updated • 10
OldKingMeister/llama-3-8b-lmsys-arena-final
Updated • 17
OldKingMeister/gemma-2b-lmsys-arena-final
Updated • 13
OldKingMeister/SPMM-Pretrained
Updated • 1
OldKingMeister/Qwen2.5-1.5B-Instruct-YaRN
Text Generation • 2B • Updated • 34 • 2