conftrace_

audio-visual large language model

3 papers

Explore in graph

Also known as

AVLLM

Co-occurring keywords · papers mentioning both

temporal alignment (2) moment captioning (1) speech-vision hallucination (1) cross-modality understanding (1) video-qa (1) multi-resolution causal q-former (1) unpaired audio-visual mixed training (1) shot boundary detection (1) diversity loss (1) hallucination benchmark (1)

Papers

FAVE: A Structured Benchmark for Fine-Grained Audio-Visual Temporal Evaluation in Multimodal LLMs CVPR 2026 SVHalluc: Benchmarking Speech-Vision Hallucination in Audio-Visual Large Language Models CVPR 2026 video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models ICML 2024