Hamiltonian Dynamics Model Captures User Preference Inertia
_reachsumit · x · 2026-08-27
This paper introduces HSR, a sequential recommender that models preference evolution as a dissipative Hamiltonian system. By decomposing preferences into position (stable) and momentum (short-term), it captures inertia, periodicity, and shifts that first-order models miss. Experiments show HSR outperforms Transformer and SSM-based models on benchmarks.
More from Research
- MoME: Context-Aware Mixture-of-Memory Embeddings Outperform Value Embedding Baselines at Iso-FLOPs — vector-institute · 2026-09-21
- FRAUDSkill Boosts Audio Anti-Fraud Macro-F1 to 73.5% With Frozen Weights — PPSUCTeleantifraudCommunity · 2026-09-21
- TeleAntiFraud 2.0: Chinese Audio Fraud Benchmark Shows F1 Drops to 0.65 on Near-Domain Negatives — PPSUCTeleantifraudCommunity · 2026-09-21
- Fitting a performance cone with bootstrapped models to test if AI leaderboard rankings actually hold — PTenigma · 2026-09-21
- Researchers pitch peer review fixes: dedicated screeners, sanctions for bad submissions, review ratios — m2saxon · 2026-09-21
- AI writing detectors flagged her lab vision post; she asks what we should actually measure — furongh · 2026-09-21