Forecast Collapse in Time-Series Foundation Models
abel-lab · hf · 2026-08-17
Research from SMU identifies a 'Forecast Collapse' issue in time-series foundation models when predicting hourly equity returns, caused by low predictability and per-series objectives. The proposed CalibRank objective balances calibration and ranking to restore cross-sectional structure.
More from Research
- COLM 2026 Paper: Literature vs. STEM Data Influence Shifts Across LLM Pretraining Stages — SinclairWang1 · 2026-08-17
- First full 11-point humanoid robot ping-pong match powered by SMASH 2.0 — 量子位 · 2026-08-17
- 7 Free YouTube Channels to Learn LLMs, From Transformer Fundamentals to Real Apps — goyalshaliniuk · 2026-08-17
- Resource: Statistical Methods in Generative AI — RexDouglass · 2026-08-17
- Second Thought: training-free parallel reasoning during agent wait times — SingaporeManagementUniversity · 2026-08-17
- Black-box attacks steal agent skills with 48% exact recovery, study finds — rohanpaul_ai · 2026-08-17