MASRA improves video temporal grounding accuracy by using MLLM-generated textual priors for event semantic alignment and local relational consistency during training only.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
SpecValidator detects lexical vagueness, under-specification, and syntax-formatting defects in LLM code-generation prompts with F1 0.804, outperforming GPT-5-mini and Claude Sonnet 4, and shows that under-specification is the most damaging defect type while richer benchmarks are more resilient.
citing papers explorer
-
MASRA: MLLM-Assisted Semantic-Relational Consistent Alignment for Video Temporal Grounding
MASRA improves video temporal grounding accuracy by using MLLM-generated textual priors for event semantic alignment and local relational consistency during training only.
-
Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis
SpecValidator detects lexical vagueness, under-specification, and syntax-formatting defects in LLM code-generation prompts with F1 0.804, outperforming GPT-5-mini and Claude Sonnet 4, and shows that under-specification is the most damaging defect type while richer benchmarks are more resilient.