Unverified50% confidenceOpinionExact time
Multimodal large language models (MLLMs) applied to the PSG task act as static observers, are limited to fixed-resolution views, often ignore key relations involving small or peripheral objects, and struggle to distinguish ambiguous predicates.
1
Sources
50%
Confidence
Long-term
Relevance
11/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCurrent MLLMs tend to rely on semantic patterns in training data rather than flexibly adapting to visual uncertainty.69% similarUnverifiedVision-language models (VLMs) suffer from prompt bias: when the prompt explicitly specifies a target category, the model tends to 'find' objects matching the description in the image even when they do not actually exist.67% similarUnverified多模态大模型(VLM)不是OCR,它在视觉向量上进行注意力计算并结合语言先验推断内容,对无规律哈希值会产生幻觉而非报识别失败66% similarUnverifiedTemporal multimodal large language models (TS-MLLMs) leverage the reasoning capabilities of large language models to handle question-answering tasks, but struggle to genuinely capture dynamic temporal patterns, typically providing implicit reasoning that lacks explicit explanation of the logic behind conclusions.65% similarUnverifiedThe vast majority of multimodal large language models (MLLMs) are still optimized around single-image input, and with multi-image input the visual token encoding overhead grows linearly or even superlinearly with the number of images.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1141778API
curl https://kongchang.com/api/v1/knowledge/claims/1141778MCP
get_claim(id=1141778)