real-time system developers

Abstract: Natural intelligence learns from a continuous stream of sensorimotor experience: data can arrive at high bandwidth, and behavior adapts to feedback as soon as it arrives, even when it is delayed. In contrast, most modern deep learning systems rely on stored datasets, replay buffers, and retained contexts through which credit is later assigned. At high data rates, storing and revisiting past experience can be impractical under tight memory and computational constraints. This paper studies recurrent memory under a streaming learning constraint: the learner learns from experience as soon as it arrives without storing raw experience. We ask whether a streaming learner can maintain a state that remains useful for future prediction and control from delayed feedback. We introduce Streaming Recurrent Memory (SRM), a recurrent memory designed for the streaming setting which preserves information that may matter later while remaining trainable with one-step backpropagation through time (BPTT). SRM provides a streaming-compatible recurrence that is designed to recall past information by content or time, track elapsed steps, and compose transformations whose outcome depends on the order in which inputs are observed. Across controlled memory tasks and streaming applications, SRM learns effectively with one-step BPTT, outperforming recurrent baselines in associative recall and online language modeling while achieving near-perfect success in associative T-Maze with delayed rewards. These results suggest that fixing how inputs are stored in the recurrent state, while learning how that state is read out, enables effective streaming learning without long-range backpropagation.

Abstract: Value-based Task Selection (VTS) asks whether a real-time system can select tasks whose total value reaches a required target while preserving every deadline. We study its threshold decision form for finite collections of independent sporadic tasks scheduled preemptively on one processor. We prove that this problem is $Σ_2^P$-complete for both constrained and arbitrary deadlines, even when all numerical parameters are encoded in unary. The existential choice is the selected task set, while the universal condition requires every processor-demand window to remain feasible. Our hardness reduction already uses constrained-deadline tasks. It represents universal assignments by Chinese Remainder Theorem timestamps and uses polynomial-weight local selector locks to enforce a valid existential assignment. The reduction produces polynomially many tasks, and every generated execution time, deadline, period, task value, and target is polynomially bounded in the source-instance size.

Abstract: On million-node graphs, the memory wall arrives before the compute wall: a GNN that never fits in VRAM cannot deliver the all-node inference its accuracy promises. The standard remedy, pruning, has always been an accuracy tax - paid once and never refunded. DPR refuses this framing. Its central insight is that the mask that shrinks training can also scaffold recovery: one compact node set bounds both computations of graph learning, serving as the encoder's training graph and, at inference, as the anchor from which a sparse structure-aware decoder rebuilds every pruned node (double-layer sparsification). The order is inverted - prune for efficiency, then reconstruct for accuracy - and the tax is repaid: the deployed 30%-budget model trains in 1,450 MiB of peak memory on one 6 GB GPU and recovers 96.9% of its dense-reconstruction reference, beating a same-GPU rerun of the edge-sparsification baseline DSpar by +1.36 pp at 50.1% lower peak training memory; against the same-protocol full-batch no-prune encoder the deployed point pays a measured 2.64 pp accuracy tax for a 2.8x smaller training footprint. Pruning without reconstruction leaves the encoder at 0.378 within the same 40-epoch window (Fig. 4), and all-node serving runs 46x faster than sampling-based GraphSAGE, giving up approx. 5.4 pp of test accuracy. The framework scales to a 2.45M-node production graph at 6,285 MiB of peak training memory; extended variants (long-range context, external text features, a CAN-bus application) are reported as extensions and do not compete with the deployed method, and the 41.8%-budget M4 point, scored on a coarsened super-node graph with its own split, is reported separately rather than compared with the original-node baselines. DPR thus turns aggressive node pruning from an accuracy tax into a safe training accelerator for VRAM-limited all-node inference.

Abstract: Large Language Models excel at reasoning and generation but their autoregressive, token-by-token inference makes them unnecessarily slow, expensive, and poorly calibrated for the many routine decisions (routing, gating, scoring, classification) that modern AI systems require at sub-second latency. A growing class of models addresses this gap: System 1 decision models, architectures that map an input directly to a typed, structured decision in a single forward pass. This guide provides a comprehensive, practitioner-oriented treatment of the field. We propose a five-family taxonomy covering encoder-based classifiers, reward models, non-autoregressive decision engines, contrastive decision models, and extraction models, and we provide in-depth coverage of each family's architecture, training methodology, and deployment trade-offs. A central theme is calibration: we develop the theory of proper scoring rules, analyze Reinforcement Learning for Calibrated Decisions (RLCD), and examine recently discovered phenomena including IIA violations, ordinal-scale bias, and few-shot recalibration under distribution shift. On the integration side, we describe how System 1 models serve as decision infrastructure within agentic workflows and System 1 + System 2 cascades that route between fast and slow models based on calibrated confidence. The guide covers 18 application domains, maps the rapidly growing open-source ecosystem (over 70 model reproductions in weeks), provides runnable code throughout, and includes a practitioner's checklist, an open-source model zoo, and 22 self-assessment questions with detailed answers. Spanning 190 references, it is intended as a unified entry point for researchers and engineers working at the intersection of fast decision-making, calibration, and production AI systems.

Abstract: Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Long-WAM, a model-system framework for scaling the context of causal world-action models under real-time control constraints. Our central finding is that access to history is not the same as using it: longer histories pay off far more when the video foundation is pretrained autoregressively (AR). We first learn causal prediction from robot and egocentric videos without action labels, then preserve this history-to-future structure during world-action adaptation. On RoboCasa GR-1, increasing context from 0.0 to 19.2 seconds raises success from 63.3% to 78.7%, whereas a bidirectionally pretrained initialization shows no net gain; robot-domain AR pretraining further raises peak success on GR-1 and LIBERO-Long. Long-WAM also achieves the best results among compared methods on LIBERO-Long, RoboTwin 2.0, and DOMINO. Streaming observation encoding, asynchronous execution, and hardware-specific acceleration enable deployment on RTX 5090, DGX Spark, and Jetson AGX Thor without dropping future prediction; on RTX 5090, each action chunk, including future-video latent prediction, takes 107.4 ms. Real-time deployment on Unitree G1 and YAM supports dynamic and long-horizon manipulation, including 95% success on dynamic cup stacking, where Pi0.5 and Fast-WAM succeed in none of 20 trials. As a memory-informed executor, Long-WAM also complements higher-level planning in composite tasks.

Abstract: Machine learning models are increasingly used in feedback control loops for nuclear fusion, where inference speed and predictable timing are critical. We summarize lessons from models deployed for control on the DIII-D tokamak and develop a benchmark to compare inference backends across ten neural networks and model components from fusion control and diagnostic pipelines. For models greater than five million parameters, the CPU backends take tens to thousands of milliseconds, while GPU inference is substantially faster, suggesting an upper limit on CPU-oriented development for control. These results show why the deployment backend must be selected together with the model and its control-cycle budget.

Abstract: World-Action Models (WAMs) improve robotic manipulation by conditioning action generation on predicted future observations, but future prediction adds further inference overhead to already expensive iterative action generation. Action chunking can amortize this cost over multiple actions, yet performance degrades over long execution horizons because later actions remain conditioned on stale observations. We introduce STAIRCASE POLICY, a streaming inference and training framework that turns a flow-matching VLA into a JEPA-style WAM and partitions a large action chunk into sub-chunks at staggered denoising stages. Near-term actions are executed as soon as they become available, while later actions continue to be refined. At each sub-chunk boundary, the future latent is re-predicted from the latest observation and used to update all unexecuted actions, enabling long-horizon execution without repeated full policy inference. The resulting future-prediction error can further serve as a signal for adaptive chunking. S-WAM achieves 97.7% on LIBERO and 87.9% on LIBERO-Plus, and improves performance across multiple policy backbones and real-robot tasks. It reaches 292.7 executed actions per second, $3.62\times$ the throughput of conventional execution at comparable accuracy, while reducing time-to-first-action from 123.6 to 73.3 ms. With additional inference optimizations, throughput further increases to 642.9 actions per second.

Abstract: One-step action generation can substantially reduce the inference cost of vision-language-action (VLA) policies, but its effect on closed-loop task success remains an open question. This technical report studies a GR00T N1.7 variant in which the iterative diffusion-transformer action head is replaced by a one-step drifting action head, together with an overlap-conditioned extension for asynchronous chunk replacement. All multi-seed drifting runs were trained on two NVIDIA A800 GPUs. On LIBERO, the action head reduces the mean model-forward time of the action head from approximately $45.3\,\mathrm{ms}$ to $5.0\,\mathrm{ms}$, while the measured backbone-plus-head time falls from approximately $70.0\,\mathrm{ms}$ to $30.6\,\mathrm{ms}$. However, this speedup is accompanied by a systematic reduction in task success. Across three drifting seeds, success is $64.0\pm4.0\%$ on LIBERO-Spatial, $52.0\pm1.0\%$ on LIBERO-Goal, and $26.0\pm2.6\%$ on LIBERO-Long. The low seed variance indicates that the degradation is not explained by random initialization alone. We report the result as a speed--success trade-off rather than an overall improvement, and discuss likely contributing factors including deterministic one-step mode averaging, batch-dependent geometry estimation, long open-loop chunk execution, and the fact that synchronous LIBERO evaluation does not exercise the asynchronous overlap path.