Research map / Vision-language and multimodal / Cross-modal learning
BSAN: Behavioral State Attention Network for Modeling Mosquito Host-Seeking Behavior
Haotian Sun, Jessie Zixin Li, John M. Marshall
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 |
|---|---|---|---|
| use LSTM temporal encoder instead of GRU (ablation) | BSAN · Aedes aegypti trajectories (held-out test) | ADE (cm): 0.58 -> 0.47 | Improved |
| use LSTM temporal encoder instead of Transformer (ablation) | BSAN · Aedes aegypti trajectories (held-out test) | ADE (cm): 0.48 -> 0.47 | No clear effect |
| use LSTM temporal encoder instead of CNN (ablation) | BSAN · Aedes aegypti trajectories (held-out test) | ADE (cm): 0.53 -> 0.47 | Improved |
| use LSTM temporal encoder instead of GRU (ablation) | BSAN · Aedes aegypti trajectories (held-out test) | state entropy (%): 0.4 -> 96.5 | Improved |
| use LSTM temporal encoder instead of CNN (ablation) | BSAN · Aedes aegypti trajectories (held-out test) | state entropy (%): 38.3 -> 96.5 | Improved |
| use LSTM temporal encoder instead of Transformer (ablation) | BSAN · Aedes aegypti trajectories (held-out test) | state transitions per sequence: 1.2 -> 2.2 | Improved |
| use BSAN instead of AgentFormer | trajectory prediction · Aedes aegypti trajectories (held-out test) | ADE (cm): 12.72 -> 0.47 | Improved |
| use BSAN instead of PINN | trajectory prediction · Aedes aegypti trajectories (held-out test) | ADE (cm): 0.50 -> 0.47 | Improved |
| use BSAN instead of Markov model | trajectory prediction · Aedes aegypti trajectories (held-out test) | FDE (cm): 0.90 -> 0.72 | Improved |
| use BSAN instead of Pure Physical model | trajectory prediction · Aedes aegypti trajectories (held-out test) | ADE (cm): 0.7 -> 0.47 | Improved |
Closest papers by meaning
- BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillation (ICLR 2025 · similarity 0.83)
- Mechanistic Interpretability of RNNs emulating Hidden Markov Models (NeurIPS 2025 · similarity 0.83)
- Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments (NeurIPS 2025 · similarity 0.82)
- Characterizing control between interacting subsystems with deep Jacobian estimation (NeurIPS 2025 · similarity 0.82)
- Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks (NeurIPS 2025 · similarity 0.82)
- Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network (ICML 2024 · similarity 0.82)
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.
