List your company

One-step next-observation prediction on WebShop (test)

63Token F1Word2World
26.636.0545.554.95May 29, 2026

Evaluation results

MethodLinks
Word2WorldBackbone=Qwen3.5-4B, LLM Usage=SFT, Infer. LLM?=Yes2026.056342
PoE-WorldBackbone=Mimo-v2.5, LLM Usage=CodeGen, Infer. LLM?=No2026.056047
LLM-DirectBackbone=DeepSeek-V4-Flash, LLM Usage=ICL, Infer. LLM?=Yes2026.055836
WorldCoderBackbone=Qwen3-Coder-480B, LLM Usage=CodeGen, Infer. LLM?=No2026.055845
WorldCoderBackbone=DeepSeek-V4-Flash, LLM Usage=CodeGen, Infer. LLM?=No2026.055845
PoE-WorldBackbone=Qwen3-Coder-480B, LLM Usage=CodeGen, Infer. LLM?=No2026.055844
LLM-DirectBackbone=Qwen3-Coder-480B, LLM Usage=ICL, Infer. LLM?=Yes2026.055634
WorldCoderBackbone=Mimo-v2.5, LLM Usage=CodeGen, Infer. LLM?=No2026.055337
PatchWorld-SimpleBackbone=Qwen3-Coder-480B, LLM Usage=CodeGen, Infer. LLM?=No2026.055330
LLM-DirectBackbone=Mimo-v2.5, LLM Usage=ICL, Infer. LLM?=Yes2026.055225
PatchWorld-ResidualBackbone=Qwen3-Coder-480B, LLM Usage=CodeGen, Infer. LLM?=No2026.055026
PatchWorld-ResidualBackbone=Mimo-v2.5, LLM Usage=CodeGen, Infer. LLM?=No2026.055026
PatchWorld-ResidualBackbone=DeepSeek-V4-Flash, LLM Usage=CodeGen, Infer. LLM?=No2026.055026
PoE-WorldBackbone=DeepSeek-V4-Flash, LLM Usage=CodeGen, Infer. LLM?=No2026.054733
PatchWorld-SimpleBackbone=Mimo-v2.5, LLM Usage=CodeGen, Infer. LLM?=No2026.052812
PatchWorld-SimpleBackbone=DeepSeek-V4-Flash, LLM Usage=CodeGen, Infer. LLM?=No2026.052810