# CircuitProbe: Tracing Visual Temporal Evidence Flow in Video Language Models

arXiv: https://arxiv.org/abs/2507.19420 · HTML: https://mlsanity.com/paper/2507.19420/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 41 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning](https://mlsanity.com/paper/2310.09478/) (2023)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [TempCompass: Do Video LLMs Really Understand Videos?](https://mlsanity.com/paper/2403.00476/) (2024)
- [Transfer between Modalities with MetaQueries](https://mlsanity.com/paper/2504.06256/) (2025)
- [STAR: A Benchmark for Situated Reasoning in Real-World Videos](https://mlsanity.com/paper/2405.09711/) (2024)
- [How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model](https://mlsanity.com/paper/2305.00586/) (2023)
- [Linearly Mapping from Image to Text Space](https://mlsanity.com/paper/2209.15162/) (2022)
- [Towards Interpreting Visual Information Processing in Vision-Language Models](https://mlsanity.com/paper/2410.07149/) (2024)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Rethinking Interpretability in the Era of Large Language Models](https://mlsanity.com/paper/2402.01761/) (2024)
- [Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations](https://mlsanity.com/paper/2410.02762/) (2024)
- [AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model](https://mlsanity.com/paper/2309.16058/) (2023)
- [What's in the Image? A Deep-Dive into the Vision of Vision Language Models](https://mlsanity.com/paper/2411.17491/) (2024)
- [Knowledge Circuits in Pretrained Transformers](https://mlsanity.com/paper/2405.17969/) (2024)
- [Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models](https://mlsanity.com/paper/2405.17820/) (2024)
- [Frozen Transformers in Language Models Are Effective Visual Encoder Layers](https://mlsanity.com/paper/2310.12973/) (2023)
- [Temporal Reasoning Transfer from Text to Video](https://mlsanity.com/paper/2410.06166/) (2024)
- [Locating and Editing Factual Associations in Mamba](https://mlsanity.com/paper/2404.03646/) (2024)
- [Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis](https://mlsanity.com/paper/2409.14144/) (2024)
- [CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning](https://mlsanity.com/paper/2503.19900/) (2025)
- [Analyzing Vision Transformers for Image Classification in Class Embedding Space](https://mlsanity.com/paper/2310.18969/) (2023)

## Abstract (arXiv)

Autoregressive large vision--language models (LVLMs) interface video and language by projecting video features into the LLM's embedding space as continuous visual token embeddings. However, it remains unclear where temporal evidence is represented and how it causally influences decoding. To address this gap, we present CircuitProbe, a circuit-level analysis framework that dissects the end-to-end video-language pathway through two stages: (i) Visual Auditing, which localizes object semantics within the projected video-token sequence and reveals their causal necessity via targeted ablations and controlled substitutions; and (ii) Semantic Tracing, which uses logit-lens probing to track the layer-wise emergence of object and temporal concepts, augmented with temporal frame interventions to assess sensitivity to temporal structure. Based on the resulting analysis, we design a targeted surgical intervention that strictly follows our observations: identifying temporally specialized attention heads and selectively amplifying them within the critical layer interval revealed by Semantic Tracing. This analysis-driven intervention yields consistent improvements (up to 2.4% absolute) on the temporal-heavy TempCompass benchmark, validating the correctness, effectiveness, and practical value of the proposed circuit-level analysis for temporal understanding in LVLMs.