AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs

Chao Gong, Depeng Wang, Zhipeng Wei, Ya Guo, Huijia Zhu, Jingjing Chen

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual speech separation · 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
use bidirectional attention in the CS2 encoder instead of causal (ablation)CS2 encoder · Daily-Omni (20% budget ablation)overall accuracy: 56.06 -> 60.65Improved
use joint cross-modal attention instead of intra-modal attention (ablation)CS2 encoder · Daily-Omni (20% budget ablation)overall accuracy: 57.73 -> 60.65Improved
add text instruction pre-fusion (ablation)CS2 encoder · Daily-Omni (20% budget ablation)overall accuracy: 57.39 -> 60.65Improved
replace random selection with learned scorer trained by STE (ablation)token selection · Daily-Omni (20% budget ablation)overall accuracy: 57.81 -> 60.65Improved
replace similarity-to-text heuristic with learned scorer (ablation)token selection · Daily-Omni (20% budget ablation)overall accuracy: 41.85 -> 60.65Improved
use STE instead of Gumbel-Softmax (ablation)token selection · Daily-Omni (20% budget ablation)overall accuracy: 59.06 -> 60.65Improved
use joint pool with dynamic budget instead of per-modality fixed ratio (ablation)token selection · Daily-Omni (20% budget ablation)overall accuracy: 58.23 -> 60.65Improved
replace TMRoPE with Sync-RoPE [18,18,18,10] (ablation)positional encoding · Daily-Omni (20% budget ablation)overall accuracy: 57.98 -> 60.65Improved
reallocate even 4 low-frequency channels to time ([20,20,20,4]) (ablation)Sync-RoPE · Daily-Omni (20% budget ablation)overall accuracy: 57.98 -> 59.65Improved
use [18,18,18,10] rather than [16,16,16,16] split (ablation)Sync-RoPE · Daily-Omni (20% budget ablation)overall accuracy: 59.31 -> 60.65Improved
use Sync-RoPE instead of interleaved TMRoPE-I (ablation)positional encoding · Daily-Omni (20% budget ablation)overall accuracy: 57.89 -> 60.65Improved
increase CS2 encoder depth from 3 to 4 layers (ablation)CS2 encoder · Daily-Omniaccuracy: 51.04 -> 60.65Improved

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