TorchCurves: Differentiable Learnable Parametric Curves for PyTorch
Alex Shtoff · hf · 2026-11-11
Alex Shtoff released TorchCurves, a PyTorch library providing differentiable, learnable vector-valued parametric curves that integrate with neural models.
Use cases include continuous embeddings, Kolmogorov-Arnold networks (KANs), functional regression, and mapping scalar features (e.g., bid, visit counts) into learned embeddings for ads auctions and recommender systems.
More from Research
- Mobile AI Factory: agentic pipeline builds on-device SLMs that beat 5-shot frontier models — kalyan_kpl · 2026-11-11
- Amazon paper: multi-agent setups burn 1.4-4.7x tokens for small gains; single agent is the default — rohanpaul_ai · 2026-11-11
- MIT's Buehler builds "recursive meta-intelligence": hundreds of AI agents inhabit self-created worlds to study material failure — ProfBuehlerMIT · 2026-11-11
- Explosion launches Ellf directory: 52 NLP templates plus multi-agent annotation workflow — _inesmontani · 2026-11-11
- STABLE Optimizer Accepted at NeurIPS 2026: Taming Continual Learning Forgetting at the Optimizer Level — v_lomonaco · 2026-11-11
- From Bahdanau to FlashAttention: a timeline of attention's 8-year evolution — cneuralnetwork · 2026-11-11