THUIR

AI & ML interests

Information retrieval

Recent Activity

LittleDinoC  new activity about 16 hours ago

THUIR/MemoryBench-Results:Add EvoSkill llm-as-judge evaluations: Qwen3-8B + Mistral-Small-3.2-24B (7 sets each, domain+task)

LittleDinoC  new activity 1 day ago

THUIR/MemoryBench-Results:Backfill llm-as-judge evaluations: Mistral autoskill_with_library (domain/Academic&Knowledge, task/Long-Short)

LittleDinoC  new activity 29 days ago

THUIR/MemoryBench-Results:add llm-as-a-judge evaluation results

View all activity

Team members 9