# SyncRA: Learning Temporal Correspondence in Omni-Modal Models

arXiv: https://arxiv.org/abs/2609.34363 · HTML: https://mlsanity.com/paper/2609.34363/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 25 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Look, Listen and Learn](https://mlsanity.com/paper/1705.08168/) (2017)
- [Audio-Visual Scene Analysis with Self-Supervised Multisensory Features](https://mlsanity.com/paper/1804.03641/) (2018)
- [Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization](https://mlsanity.com/paper/1807.00230/) (2018)
- [WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs](https://mlsanity.com/paper/2502.04326/) (2025)
- [Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities](https://mlsanity.com/paper/2505.17862/) (2025)
- [What matters for Representation Alignment: Global Information or Spatial Structure?](https://mlsanity.com/paper/2512.10794/) (2025)
- [MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction](https://mlsanity.com/paper/2604.27393/) (2026)
- [OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs](https://mlsanity.com/paper/2510.10689/) (2025)
- [TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs](https://mlsanity.com/paper/2512.14698/) (2025)
- [Audio-centric Video Understanding Benchmark without Text Shortcut](https://mlsanity.com/paper/2503.19951/) (2025)
- [LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs](https://mlsanity.com/paper/2603.19217/) (2026)
- [CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment](https://mlsanity.com/paper/2505.01237/) (2025)
- [OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains](https://mlsanity.com/paper/2606.14702/) (2026)
- [LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning](https://mlsanity.com/paper/2605.22012/) (2026)
- [AVID: A Benchmark for Omni-Modal Audio-Visual Inconsistency Understanding via Agent-Driven Construction](https://mlsanity.com/paper/2604.13593/) (2026)
- [AVTrace: Diagnosing Audio-Visual Temporal Reasoning in Omni Models](https://mlsanity.com/paper/2609.19991/) (2026)

## Abstract (arXiv)

Recent omni-modal models demonstrate strong perception of audio and visual inputs, yet often struggle to connect what they hear with what they see at the same moment. This weakness in temporal correspondence can cause models to associate spoken cues with the wrong visual scenes, producing plausible answers grounded in incorrect audio-visual pairings. We diagnose this problem through controlled temporal swaps, revealing that model answers do not reliably follow changes in these pairings. To address it, we propose Synchrony-Guided Representation Alignment (SyncRA), a lightweight method for strengthening temporal correspondence between audio and vision. Specifically, SyncRA contrasts intermediate audio-visual representations within each video, aligning matching moments while separating mismatched ones to capture local temporal correspondence within a shared global context. The objective derives supervision directly from existing input timing, requiring no additional annotations and leaving inference unchanged. We evaluate SyncRA across four open omni-modal models spanning different sizes and architectures on five public video benchmarks. SyncRA consistently outperforms answer-only fine-tuning across all model-benchmark combinations, while substantially improving the ability to track changing audio-visual pairings in controlled evaluations. These results demonstrate that lightweight, targeted supervision can effectively strengthen temporal correspondence and translate into broad improvements in audio-visual question answering.