Unverified50% confidenceBenchmarkExact time
On the Find-the-Item task, current state-of-the-art VLA models are only at or below chance level (success rate ≤33.3%).
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/21/2026
First Seen
Valid until: 11/4/2026
Sources
Related Entities
Related Claims
UnverifiedIn the LIBERO-RIG evaluation, the aggregate success rate of VLA models dropped from a baseline of 0.932 to 0.767 at moderate severity, and further fell to 0.509 at the highest severity.69% similarUnverified即使只有5-10%的训练样本存在错位，也会导致VLM模型在下游任务上出现显著的性能退化65% similarUnverifiedAfter a vision-language model (VLM) is fine-tuned on class-imbalanced data, the recall for rare classes can even be lower than the model's own zero-shot performance.65% similarUnverifiedA 3,000-question probe experiment shows that incorrect VLM predictions attract more image attention than correct ones (Cohen's d = -0.46, p = 1.4×10⁻²⁴), contrary to the core assumption of grounding-based correction methods.63% similarUnverifiedSmall VLMs (such as LLaVA-7B and Qwen-VL-Chat) typically have parameter counts in the billions, making them far heavier than object detection models (which have tens of millions to hundreds of millions of parameters).61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1078958API
curl https://kongchang.com/api/v1/knowledge/claims/1078958MCP
get_claim(id=1078958)