Is LLaVA-o1 superseded?

LLaVA-o1 (LLM reasoning / chain-of-thought): cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here. 1 paper(s) critique it, 0 beat it on benchmarks — #401 of 772 most-superseded. Sub-problem: cluster led by VL-Rethinker-7B. Newer alternatives in the same sub-problem include TVI-CoT.

LLM reasoning / chain-of-thought

LLaVA-o1

Superseded baseline#401 of 772 most-superseded

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

1 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites LLaVA-o1 as a baseline.

However, these approaches, even advanced models like GPT-5 or Gemini, perform CoT in pure text space. Once visual features are initially encoded, they cannot be re-accessed during reasoning.

— TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.

TVI-CoTTVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding
Jun 7, 2026