AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Twins: Learn to Predict Unified Representations with Focal Loss

Kaixiong Gong, Xin Cai, Bin Lin, Hao Wang, Yunlong Lin, Mingzhe Zheng, Bohao Li, Jian-Wei Zhang, Miles Yang, Zhao Zhong, Liefeng Bo, Xiangyu Yue

ICML 2026 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 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
replace MSE with focal-weighted flow matching loss on VAE channels (ablation)Twins DiT, VAE-decoded · ImageNet 256 gFID w/o guidance (80 epochs)gFID: 14.41 -> 3.84Improved
replace MSE with focal loss (ablation)Twins DiT, VAE-decoded · ImageNet 256 gFID w/o guidance (20 epochs)gFID: 23.69 -> 7.38Improved
replace MSE with focal loss (ablation)Twins DiT, SigLIP2-decoded · ImageNet 256 gFID w/o guidance (80 epochs)gFID: 2.86 -> 2.50Improved
replace MSE with focal loss (ablation)Twins DiT · ImageNet 512 gFID w/o guidance (80 epochs)gFID: 6.80 -> 3.78Improved
jointly model ViT and VAE channels with plain MSE instead of VAE only (ablation)DiT on Twins · ImageNet 256 gFID w/o guidance (80 epochs)gFID: 3.99 -> 14.41Hurt
concatenate Flux.2 VAE latents to SigLIP2 features for the VLM encoder (ablation)Qwen2.5-7B VLM · GQA, TQA, MME-Saccuracy / score: GQA 64.54 -> 64.93; TQA 56.92 -> 58.89; MME-S 1826.8 -> 1971.0Improved
concatenate Flux.2 VAE latents to SigLIP2 features for the VLM encoder (ablation)Qwen2.5-7B VLM · MMBenchaccuracy: 77.00 -> 77.00No clear effect
concatenate SigLIP2 semantic features with Flux.2 VAE latents instead of semantic features aloneunified tokenizer · ImageNet-1K val reconstructionPSNR: 18.83 -> 31.46Improved
use features with higher intrinsic dimension (Flux.2 vs DINOv2-B) as the diffusion target (ablation)DiT latent diffusion · ImageNet 256 FID vs intrinsic dimensionFIDHurt

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