Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Learning What to Share: Expert Specialization for Time-Series Forecasting
Bashar Khoury, Shadi Omari, Assaf Schuster
A central challenge in multivariate forecasting is deciding what to share across channels and where to specialize. Mixture-of-experts models offer flexible sharing, yet it remains…
cs.LG2026
Quantile-Guided Diffusion for Probabilistic Time-Series Forecasting
Shadi Omari, Bashar Khoury, Assaf Schuster
Quantile forecasts summarize uncertainty at each future time step, while diffusion forecasters represent it through sampled future trajectories. We study how predicted quantiles ca…
cs.LG2026
AnchorKV: Anchor-Residual KV Cache Compression
Malik Khalaf, Yara Shamshoum, Nitzan Hodos +2
The key-value (KV) cache is the primary memory bottleneck in long-context LLM inference. Existing approaches attack it from opposite ends: eviction methods permanently discard toke…