Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting
Jinjin Chi, Lei Feng, Lulu Zhang +6
Time series foundation models (TSFMs) have recently achieved strong zero-shot forecasting performance through large-scale pretraining and retrieval-augmented prediction. However, o…
cs.LG2026
Distillation Traps and Guards: A Calibration Knob for LLM Distillability
Weixiao Zhan, Yongcheng Jing, Leszek Rutkowski +1
Knowledge distillation (KD) transfers capabilities from large language models (LLMs) to smaller students, yet it can fail unpredictably and also underpins model leakage risks. Our…
cs.LG2025
Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning
Guozheng Ma, Lu Li, Zilin Wang +4
Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL), where larger models often degrade perfor…