LatentOmni proposes a latent-space cross-modal reasoning framework that uses feature-level supervision and Omni-Sync Position Embedding to align and synchronize audio-visual latents, supported by a new 35K interleaved reasoning dataset and showing gains over text CoT baselines.
Towards universal video mllms with attribute-structured and quality-verified instructions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CapRiCorn-1K benchmark shows current video captioning models produce inaccurate and inconsistent captions that worsen with longer videos, with proposed metrics correlating to downstream task performance.
citing papers explorer
-
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
LatentOmni proposes a latent-space cross-modal reasoning framework that uses feature-level supervision and Omni-Sync Position Embedding to align and synchronize audio-visual latents, supported by a new 35K interleaved reasoning dataset and showing gains over text CoT baselines.
-
CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales
CapRiCorn-1K benchmark shows current video captioning models produce inaccurate and inconsistent captions that worsen with longer videos, with proposed metrics correlating to downstream task performance.