iclr2026
Differentiable Tversky similarity layers for PyTorch. Official implementation from the ICLR 2026 paper "Tversky Neural Networks."
Framework-agnostic ReasoningBank (Ouyang et al., ICLR 2026): agents that learn from successful AND failed trajectories, with MaTTS.
CommitMind: Semantic search for Git commit history powered by TurboQuant vector compression (ICLR 2026). Search commits by meaning, not just keywords.