Research map / Vision-language and multimodal / Visual question answering
E-Logic Prompt: Unified Energy-Logic Framework for Continual Visual Question Answering
Jiayao Tan, Tianle Liu, Fuyuan Hu, Wei Feng, Liang Wan
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Lq-p (query-prompt energy alignment) loss (ablation) | prompt-based CVQA baseline · VQA v2 (DI) | accuracy A: 33.17 -> 34.42 (+1.25) | Improved |
| add Lq-p (query-prompt energy alignment) loss (ablation) | prompt-based CVQA baseline · VQA v2 (DI) | inter-task forgetting: reduces forgetting by 0.53 | Improved |
| add Llayer and Ltask on top of Lq-p (all three losses) (ablation) | E-Logic Prompt · VQA v2 (DI) | accuracy A: 34.420 -> 36.223 | Improved |
| all three losses vs none (ablation) | E-Logic Prompt · VQA v2 (DI) | inter-task forgetting: 2.503 -> 0.447 | Improved |
| E-Logic Prompt vs best baseline MaPLe | E-Logic Prompt · VQA v2 (DI) | accuracy A: 35.187 -> 36.963 | Improved |
| add Cross-Task Prompt Logical Consistency to Dual Prompt | Dual Prompt · NExT-QA (DI), task order | accuracy stability across task orders | Improved |
| use E-Logic Prompt instead of Dual Prompt | Dual Prompt · Inference time per 100 samples | seconds: 0.151 -> 0.179 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MaPLe — MaPLe: Multi-Modal Prompt Learning (CVPR 2023) · better on 3 of 3 shared results
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
- Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning (NeurIPS 2026 · similarity 0.88)
- Convolutional Prompting meets Language Models for Continual Learning (CVPR 2024 · similarity 0.88)
- Mixture of Experts Meets Prompt-Based Continual Learning (NeurIPS 2024 · similarity 0.87)
- One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning (ICML 2024 · similarity 0.87)
- SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs (ICML 2026 · similarity 0.86)
- Adaptive Prompting for Continual Relation Extraction: A Within-Task Variance Perspective (AAAI 2025 · 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.
