AI Paper Atlas

Research map / Video / Video-language understanding

Understanding Temporal Logic Consistency in Video-Language Models through Cross-Modal Attention Discriminability

Chengzhi Li, Heyan Huang, Ping Jian, Zhen Yang, Yaning Tian, Zhongbin Guo

CVPR 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add TCAS loss to SFTTimeChat (VTune) · Charades-CONGround: 76.2 -> 83.3Improved
add TCAS loss to SFTTimeChat (VTune) · Charades-CONH-Verify: 44.8 -> 52.9Improved
add TCAS loss to SFTTimeChat (TimeIT) · Charades-CONS-Ground: 10.5 -> 33.8Improved
add TCAS loss to SFTQwen2.5-VL-7B (VTune) · Charades-CONGround: 28.3 -> 34.0Improved
add TCAS loss to SFTTimeChat (VTune) · ActivityNet-CONGround: 37.4 -> 38.8Improved
add TCAS loss to SFTTimeChat · Charades-STAR@1,0.7: 34.7 -> 37.6Improved
add TCAS loss to SFTVideo-LLaMA-7B · Charades-STAR@1,0.7: 20.1 -> 20.1No clear effect
add TCAS loss to SFTQwen2.5-VL-7B · ActivityNet CaptionsR@1,0.5: 16.5 -> 16.5No clear effect
add TCAS loss to SFT on videos longer than 40sTimeChat (VTune) · Charades-CON, videos >40sGround: 58.8 -> 76.5Improved
intervene mildly on attention toward ground truth (alpha 0.2) at inference (ablation)TimeChat · Charades-CON rephrased groundingR0.7: 79.9 -> 80.8Improved
intervene strongly on attention (alpha 1.0) at inference (ablation)TimeChat · Charades-CON groundingmIoU: 65.8 -> 63.2Hurt
random attention intervention alpha 0.1 (ablation)TimeChat SFT · Charades-CONc_rg: 65.4 -> 2.1Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy