Doubt cast on SWA effective receptive field math
giffmana · x · 2026-09-01
Challenging the formula that SWA's effective receptive field equals layers times sliding window size, noting it likely doesn't transfer and asking for verification.
More from Research
- AI Research Preference Models: Using Compute to Decide What Experiments to Run — anirudhg9119 · 2026-09-01
- RPM-guided search sets new SOTA on benchmarks, proving selection scales with compute — anirudhg9119 · 2026-09-01
- Inference-only RPM: Frozen LLM Ranks Candidates to Save Compute — anirudhg9119 · 2026-09-01
- From score forecasting to preference ranking: picking which of 15 ideas to run — anirudhg9119 · 2026-09-01
- AI Research Agents Face Bottleneck: Ideas Outpace GPU Budget — anirudhg9119 · 2026-09-01
- Paper: AI Research Preference Models Solve Compute Bottleneck — anirudhg9119 · 2026-09-01