AI Paper Atlas

Research map / Video / Video-language understanding

Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas

Yuxuan Li, Lingxi Xie, Xinyue Huo, Jihao Qiu, Jiacheng Shao, Pengfei Chen, Jiannan Ge, Kaiwen Duan, Qi Tian

ICML 2026 · Video › Video-language understanding · approach: Video question answering · 0 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 RL (GRPO) after SFTQwen3-8B DramaSR-LRM · Speaker recognition test setaccuracy (%): 75.22% -> 86.93%Improved
add SFT and RL on top of direct Qwen3-8B useQwen3-8B · Speaker recognition test setaccuracy (%): 27.40% -> 86.93%Improved
add confidence sampling (invoke LRM only when margin < rho)DramaSR-LRM · Speaker recognition test setaccuracy (%): 86.93% -> 87.79%Improved
add confidence sampling to SFT-only modelQwen3-8B + SFT · Speaker recognition test setaccuracy (%): 75.22% -> 82.70%Improved
add the voice_sim tool (ablation)DramaSR-LRM · Speaker recognition test setaccuracy (%): 72.61% -> 87.79%Improved
add the video_cap tool (ablation)DramaSR-LRM · Speaker recognition test setaccuracy (%): 86.76% -> 87.79%Improved
add the char_relation tool (ablation)DramaSR-LRM · Speaker recognition test setaccuracy (%): 87.55% -> 87.79%Improved
add the video_cap tool (ablation)DramaSR-LRM · Very short utterances (0-0.5s)accuracy (%): 72.33% -> 76.65%Improved
replace label propagation with DramaSR-LRMLabel propagation · Very short utterances (0-0.5s)accuracy (%): 67.45% -> 76.65%Improved
replace label propagation with DramaSR-LRMLabel propagation · English subsetaccuracy (%): 82.41% -> 85.22%Improved
add a second iterative refinement pass (ablation)DramaSR-LRM · The Long Nightaccuracy (%): 90.15% -> 90.40%Improved
raise confidence threshold rho from 0.10 to 0.20 (ablation)DramaSR-LRM · Stand by Me 1accuracy (%): 93.63 -> 91.91Hurt

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