Viral TDV paper criticized: only beats nerfed iBOT/DINO baselines, doesn't scale
gabriberton · x · 2026-11-07
A critique of the viral TDV paper ("You Don't Need Strong Assumptions"): it only compares against its own nerfed versions of iBOT and DINO rather than the real DINO — and still loses to them. The author also notes TDV doesn't scale to larger datasets, while crediting the paper's authors for being honest about this limitation.
Related event: Viral TDV Paper Questioned Over Weakened Baselines and Scalability(3 posts)→
More from Research
- GLASS preprint teaser: graph-led LLM-assisted scoring of open-ended responses without human coding — GolinoHudson · 2026-11-07
- ICLR 2027 reviews mocked as worse than the papers, as LLMs improve mid-cycle — miniapeur · 2026-11-07
- LLMs can read and patch weights, but 20 fine-tuning steps erase the edits — kevinpl07 · 2026-11-07
- FlexiTac-Gen launches: AI-agent-assisted tool to design custom tactile sensors, accepted to CoRL 2026 — Haoyu_Xiong_ · 2026-11-07
- PolicyIK: NYU trains RL for inverse kinematics on a real arm, hitting 0.5mm median error — Lianhuiq · 2026-11-07
- Weight-space programming vs LoRA on 4 bugs: precise one-neuron patches that don't persist — kevinpl07 · 2026-11-07