Further fine-tuning CLIP with contrastive losses often fails on out-of-distribution data
wightmanr · x · 2026-11-13
The author notes that fine-tuning CLIP models further with contrastive losses usually fails due to lack of data or poor data quality, especially when distribution differs significantly from training data. He argues decent coding agents can orchestrate the needed experiments on OpenCLIP, particularly the cleaned-up 4.x main branch.
Related event: OpenCLIP Adds Layer-Wise LR Decay to Ease CLIP Fine-Tuning(2 posts)→
More from coding & agent
- Google's Antigravity Orchestrator pairs two models, cuts quota 24% and runs 19% faster — shangbinfeng · 2026-11-13
- Mapin: A Laravel Code Graph Exposed via MCP So AI Agents Know What Depends on What — Brandon-Vergara · 2026-11-13
- airbench: Testing Local Models on Visual Desktop Challenges via Keyboard and Mouse Agents — dh7net · 2026-11-13
- Agent names itself 'Doodlebug' and posts comments on a user's behalf — max__drake · 2026-11-13
- Luke Wroblewski: it's a golden age for multi-taskers spinning up and steering parallel agents — LukeW · 2026-11-13
- Day 13 of an OpenClaw agent teaching itself music production in REAPER — it rebuilt its own workflow — heyneighbor · 2026-11-13