Counting the Bandages: On measuring the time that AI saves
arXiv:2610.35942v1 Announce Type: new Abstract: I consider what it means for AI assistance to save time. I contrast a stopwatch…
I-HITL: Inalienable Human-in-the-Loop
arXiv:2610.35835v2 Announce Type: replace-cross Abstract: Human oversight is a pillar of AI safety. It is often exercised by a human…
Learning to Look Beyond Screens: Transferable Visual Observation from GUI Grounding
arXiv:2610.37093v1 Announce Type: cross Abstract: Visual perception is evolving from passive recognition toward active, task-oriented observation. We investigate GUI grounding…
EnergyCal: Taming Loss Spikes in Muon-Family Optimizers for Sparse MoE Training
arXiv:2610.37062v1 Announce Type: cross Abstract: Sparse mixture-of-experts (MoE) language-model training can exhibit large loss spikes with Muon-family optimizers. We introduce…
Quantitative Generalization Bounds for Multi-Layer Transformers: A Few Long Strings can Beat Many Short Ones
arXiv:2610.35715v2 Announce Type: replace-cross Abstract: Transformer-based language models exhibit an astonishing capacity to generalize to longer and more difficult problem…