state-tracking

Expanding linear RNN state-transition matrix eigenvalues to include negatives improves state-tracking tasks and language modeling without added training or inference costs.

DeltaProduct is a new linear recurrent neural network architecture that uses products of generalized Householder matrices as state-transition matrices enabling better expressivity, state-tracking, and language modeling performance than DeltaNet.

Seamlessly track the visibility state of your document across different browsers. Know when your users switch to another window or tab.

Precise object change detection library - Automatically tracks property changes with zero intrusion.

Official implementation of "DZ-TiDPO: Non-Destructive Temporal Alignment for Mutable State Tracking". SOTA on Multi-Session Chat with negligible alignment tax.

Saryu: a recurrent language model whose state is moved by input-dependent Householder reflections. Open architecture research from India — constant memory per token, an exact parallel kernel, and two technical reports: the architecture, and what the same transport does when it fails (it collapses onto exact group quotients).

Brainfuck-based generator and exact Rust harness for controlled machine-state tasks; v0.4.0-alpha engineering candidate.

A per-project state layer for long Claude Code sessions: keeps a .claude/state.json (objective / current focus / deliverables), prints a WHERE YOU ARE orientation block at session start, re-injects the goal as you work, and nudges when state goes stale. /plugin marketplace add goldenwo/claude-state-drift

Task-oriented multi-turn dialogue system for flight booking with state tracking and error recovery

Algoverse: deterministic generator for the 5,000-example stale-state evaluation set used to probe LLM state tracking

Reproduction code for the paper 'Structure, Not Size: The Sample and Parameter Complexity of State Tracking in Selective State-Space Models' (selective PD-SSM / diagonal SSM / GRU state-tracking, MLX).

Redis-backed orchestration for NVIDIA NeMo Agent Toolkit — task lifecycle, abort control, crash recovery, session persistence.

Chess-based benchmark measuring whether LLMs can maintain coherent state and apply rules across many reasoning turns. PlayStrength + MoveQuality metrics across Anthropic, OpenAI, Google, DeepSeek, and OpenAI-compatible endpoints.

Code and experiments for studying length generalization in recurrent Transformers on permutation state-tracking tasks.

This is a short term task oriented conversation system designed to gather user feedback about a lecture the students had in a user centered manner. Sentiments are converted to polarities and engagement are utilized to make informed decision on the interaction mode switching.

Controlled generation and transition-preserving state tracking for multi-turn structured interfaces.

minGRU (Feng et al.) in PyTorch, plus a measured ladder of state-tracking recoveries — signed, rotation, Givens, and delta (DeltaNet-style Householder products) mixers with time decay, all under one parallel scan — with fused Triton GPU kernels as an optional backend

Spanfold is a composable multi-language library for stateful event windows and hierarchical rollups.

NOVA: Neural Organic Vivid Architecture — a sub-quadratic sequence architecture with recurrent multi-timescale memory (FLUX), antisymmetric attention (IRIS), and role-separated representations (RSLA)