Research map / Reinforcement learning / Visual and representation RL
MTDiag: An Effective Multi-Task Framework for Automatic Diagnosis
Zhenyu Hou, Yukuo Cen, Ziding Liu, Dongxue Wu, Baoyan Wang, Xuanhe Li, Lei Hong, Jie Tang
This paper tried a common change: Add a contrastive loss
Add supervised contrastive learning · MDD dev · accuracy: 88.1 -> 89.1 Improved
What 1,317 accepted papers report for this change
- 1,253 improved
- 22 no clear effect
- 16 mixed
- 26 hurt
- Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering ICML 2026 · add contrastive learning · SearchSnippets · ACC: 56.65 -> 80.12Improved
- SleepLM: Natural-Language Intelligence for Human Sleep ICML 2026 · add contrastive objective to captioning (CoCa vs Cap) · sleep event IoU · IoU: 29.2 -> 27.4Hurt
- LIMSSR: LLM-Driven Sequence-to-Score Reasoning under Training-Time Incomplete Multimodal Observations ICML 2026 · add contrastive loss L_con · FS1000 average · Spearman correlation: 0.759 -> 0.789Improved
See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use MTDiag instead of Diaformer | automatic diagnosis · MDD dev | accuracy: 86.0 -> 89.1 | Improved |
| Use MTDiag instead of Diaformer | automatic diagnosis · MZ | accuracy: 74.2 -> 75.9 | Improved |
| Use MTDiag instead of Diaformer | automatic diagnosis · DXY | accuracy: 82.9 -> 85.4 | Improved |
| Use MTDiag instead of Diaformer | automatic diagnosis · Synthetic | accuracy: 73.3 -> 75.4 | Improved |
| Add supervised contrastive learning (ablation) | MTDiag · MDD dev | accuracy: 88.1 -> 89.1 | Improved |
| Add supervised contrastive learning (ablation) | MTDiag · MZ | accuracy: 74.2 -> 75.9 | Improved |
| Add supervised contrastive learning (ablation) | MTDiag · DXY | accuracy: 84.0 -> 85.4 | Improved |
| Add supervised contrastive learning (ablation) | MTDiag · Synthetic | accuracy: 75.6 -> 75.4 | No clear effect |
| Use concurrent softmax rather than BCE while retaining multi-task disease information (ablation) | MTDiag · MDD dev | accuracy: 88.7 -> 89.1 | Improved |
| Use concurrent softmax rather than BCE while retaining multi-task disease information (ablation) | MTDiag · MZ | accuracy: 74.2 -> 75.9 | Improved |
| Use concurrent softmax rather than BCE while retaining multi-task disease information (ablation) | MTDiag · DXY | accuracy: 84.8 -> 85.4 | Improved |
| Use concurrent softmax rather than BCE while retaining multi-task disease information (ablation) | MTDiag · Synthetic | accuracy: 74.1 -> 75.4 | Improved |
Closest papers by meaning
- MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments (NeurIPS 2026 · similarity 0.85)
- Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records (NeurIPS 2024 · similarity 0.85)
- MedTVT-R1: A Multimodal LLM Empowering Medical Reasoning and Diagnosis (CVPR 2026 · similarity 0.84)
- Large Language Models Are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales (AAAI 2024 · similarity 0.84)
- PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation (AAAI 2024 · similarity 0.84)
- Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding (NeurIPS 2025 · similarity 0.83)
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.
