Papers with learnable module
HOPE: Hybrid Optimized Parallel Encoding with Supervised and Unsupervised Semantic Fusion for Depression Symptom Detection (2026.acl-long)
Copied to clipboard
| Challenge: | HOPE is a framework for detecting depression symptoms from social media data . it combines supervised symptom relevance signals with unsupervised intrinsic semantic clustering . |
| Approach: | They propose a Hybrid Optimized Parallel Encoding framework that combines supervised symptom relevance signals with unsupervised intrinsic semantic clustering. |
| Outcome: | The proposed framework outperforms existing methods on multiple benchmark datasets and shows that it can detect fine-grained symptoms and early warning of mental health risk. |
Octopus: Gated Selective Attention for Memory-Bounded Long-Context Inference in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Subquadratic architectures rely on aggressive state compression that degrades performance on complex reasoning tasks. |
| Approach: | They propose a framework that confers fixed-memory inference onto pretrained Transformers . they use a learnable module that enforces an adaptive sparsity policy over the context history . |
| Outcome: | The proposed framework outperforms state-of-the-art linearized baselines on the GSM8K benchmark by over 36 points under identical memory constraints. |