VeRVE uses a shared MLLM backbone with contrastive alignment and LoRA training to surpass other MLLM methods on zero-shot video retrieval while enabling competitive moment retrieval and state-of-the-art composed retrieval without further training.
The surprising effectiveness of multimodal large language models for video moment retrieval.ArXiv, abs/2406.18113
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
SpotSound adds a hallucination-suppressing objective and a needle-in-haystack benchmark to audio-language models, reaching state-of-the-art temporal grounding while keeping general task performance.
UniversalVTG is a lightweight foundation model for video temporal grounding that achieves state-of-the-art results across five benchmarks while being over 100 times smaller than recent MLLM-based methods.
A controlled study on compact video LLMs finds that continuous temporal decoding delivers the strongest accuracy-efficiency trade-off for video temporal grounding across three benchmarks.
citing papers explorer
-
SpotSound: Enhancing Large Audio-Language Models with Fine-Grained Temporal Grounding
SpotSound adds a hallucination-suppressing objective and a needle-in-haystack benchmark to audio-language models, reaching state-of-the-art temporal grounding while keeping general task performance.