conftrace_

video-qa

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

clavi (1) quag (1) multi-resolution causal q-former (1) unpaired audio-visual mixed training (1) most-grounding (1) self-reflection training (1) localization (1) audio-visual large language model (1) diversity loss (1) multimodal llm (1)

Papers

Modularized Self-Reflected Video Reasoner for Multimodal LLM with Application to Video Question Answering ICML 2025 Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion ICML 2024 video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models ICML 2024