Research map / Vision-language and multimodal / Multimodal LLMs
UniF$^2$ace: A $\underline{Uni}$fied $\underline{F}$ine-grained $\underline{Face}$ Understanding and Generation Model
Junzhe Li, Sifan Zhou, Liya Guo, Xuerui Qiu, Linrui Xu, TingTing Long, Chun Fan, Ming Li, Hehe Fan, Jun Liu, Shuicheng YAN
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes UniF^2ace, a unified model for fine-grained face understanding and generation, addressing fragmented face-domain methods that handle understanding and generation separately.
Problem
Existing face-domain research is fragmented: methods fail to unify face understanding and generation within a single model, hindering progress toward unified face intelligence.
Approach
A unified multimodal model specialized for fine-grained face understanding and generation in one architecture, targeting the fragmentation of prior face-specific methods. Details beyond the abstract are not available.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add score-matching loss to masked generative loss (D3Diff, alpha 0.01) (ablation) | UniF2ace · UniF2aceD-1M test (generation) | FID: 77.463 -> 66.005 | Improved |
| use score loss only instead of masked loss only (ablation) | UniF2ace · UniF2aceD-1M test (generation) | FID: 77.463 -> 69.694 | Improved |
| vary D3Diff weight alpha from 0.01 to 0.001 (ablation) | UniF2ace · UniF2aceD-1M test (generation) | FID: 66.005 -> 72.736 | Hurt |
| add CLIP and Face experts in sequence-level MoE for understanding (ablation) | UniF2ace · UniF2aceD-1M test (understanding) | Desc-GPT: 5.21 -> 6.02 | Improved |
| add token-level MoE (ablation) | UniF2ace · UniF2aceD-1M test (generation) | FID: 72.877 -> 67.415 | Improved |
| add sequence-level MoE (ablation) | UniF2ace · UniF2aceD-1M test (generation) | FID: 72.877 -> 69.312 | Improved |
| combine token-level and sequence-level MoE (ablation) | UniF2ace · UniF2aceD-1M test (generation) | FID: 72.877 -> 66.005 | Improved |
| raise sequence-MoE Top-K from 1 to 2 (ablation) | UniF2ace · UniF2aceD-1M test (generation) | FID: 74.914 -> 66.005 | Improved |
| raise sequence-MoE Top-K from 2 to 4 (ablation) | UniF2ace · UniF2aceD-1M test (generation) | FID: 66.005 -> 63.632 | Mixed |
| add D3Diff loss to 1.3B baseline (cost) (ablation) | baseline · UniF2aceD-1M test (generation) | VLM-score: 79.698 -> 84.432 | Improved |
| add MoE architecture (1.3B to 1.8B params) (ablation) | baseline · UniF2aceD-1M test (understanding) | Desc: 4.958 -> 5.885 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- JanusFlow — JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation (CVPR 2025) · better on 1 of 1 shared result
- Show-o — Show-o: One Single Transformer to Unify Multimodal Understanding and Generation (ICLR 2025) · better on 1 of 1 shared result
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
- GroundingFace: Fine-grained Face Understanding via Pixel Grounding Multimodal Large Language Model (CVPR 2025 · similarity 0.88)
- UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation (NeurIPS 2025 · similarity 0.87)
- FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs (CVPR 2025 · similarity 0.87)
- UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture (ICML 2026 · similarity 0.86)
- Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language Models (AAAI 2025 · similarity 0.86)
- G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models (NeurIPS 2026 · similarity 0.86)
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.
