Shared autonomy combines human user and AI copilot actions to control complex systems such as robotic arms. When a task is challenging, requires high dimensional control, or is subject to corruption, shared autonomy can significantly increase task performance by using a trained copilot to effectively correct user actions in a manner consistent with the user’s goals. To significantly improve the performance of shared autonomy, we introduce Diffusion Sequence Copilots (DiSCo): a method of shared autonomy with diffusion policy that plans action sequences consistent with past user actions. DiSCo seeds and inpaints the diffusion process with user-provided actions with hyperparameters to balance conformity to expert actions, alignment with user intent, and perceived responsiveness. We demonstrate that DiSCo substantially improves task performance in simulated driving and robotic arm tasks. Project website: https://sites.google.com/view/disco-shared-autonomy/

Speech neuroprostheses aim to restore communication for people with severe paralysis by decoding speech directly from neural activity. To accelerate algorithmic progress, a recent benchmark released intracranial recordings from a paralyzed participant attempting to speak, along with a baseline decoding algorithm. Prior work on the benchmark showed impressive accuracy gains. However, these gains increased computational costs and were not demonstrated in a real-time decoding setting. Here, we make three contributions that pave the way towards accurate, efficient, and real-time neural speech decoding. First, we incorporate large amounts of time-masking during training. On average, over $50\%$ of each trial is masked. Second, we replace the gated recurrent unit (GRU) architecture used in the baseline algorithm with a compact Transformer. The Transformer architecture uses $83\%$ fewer parameters, cuts peak GPU memory usage by $52\%$, and is significantly faster to calibrate relative to the GRU. Third, we design a lightweight variant of an existing test-time adaptation method developed for decoding handwriting from neural activity. Our variant adapts the model using multiple time-masked augmentations of a single trial and requires only one gradient step per trial. Together, these contributions reduce word error rate by over $20\%$ and effectively mitigate performance degradations across held-out days in a real-time decoding setting while substantially lowering computational costs.

Surface electromyography (sEMG) at the wrists could enable natural, keyboard‑free text entry, yet the state‑of‑the‑art emg2qwerty baseline still misrecognizes 51.8\% of characters zero‑shot on unseen users and 7.0\% after user‑specific fine‑tuning. We trace much of these errors to mismatched cross‑user signal statistics, fragile reliance on high‑order feature dependencies, and the absence of architectural inductive biases aligned with the bilateral nature of typing. To address these issues, we introduce three simple modifications: (i) Rolling Time Normalization which adaptively aligns input distributions across users; (ii) Aggressive Channel Masking, which encourages reliance on low‑order feature combinations more likely to generalize across users; and (iii) a Split‑and‑Share encoder that processes each hand independently with weight‑shared streams to reflect the bilateral symmetry of the neuromuscular system. Combined with a five‑fold reduction in spectral resolution (33$\rightarrow$6 frequency bands), these components yield a compact Split-and-Share model, SplashNet‑mini, which uses only ¼ the parameters and 0.6× the FLOPs of the baseline while reducing character error rate (CER) to 36.4\% zero‑shot and 5.9\% after fine‑tuning. An upscaled variant, SplashNet (½ parameters, 1.15× FLOPs of the baseline), further lowers error to 35.7\% and 5.5\%, representing 31\% and 21\% relative improvements in the zero-shot and finetuned settings, respectively. SplashNet therefore establishes a new state-of-the-art without requiring additional data.

Offline goal-conditioned reinforcement learning (GCRL) is a promising approach for pretraining generalist policies on large datasets of reward-free trajectories, akin to the self-supervised objectives used to train foundation models for computer vision and natural language processing. However, scaling GCRL to longer horizons remains challenging due to the combination of sparse rewards and discounting, which obscures the comparative advantages of primitive actions with respect to distant goals. Hierarchical RL methods achieve strong empirical results on long-horizon goal-reaching tasks, but their reliance on modular, timescale-specific policies and subgoal generation introduces significant additional complexity and hinders scaling to high-dimensional goal spaces. In this work, we introduce an algorithm to train a flat (non-hierarchical) goal-conditioned policy by bootstrapping on subgoal-conditioned policies with advantage-weighted importance sampling. Our approach eliminates the need for a generative model over the (sub)goal space, which we find is key for scaling to high-dimensional control in large state spaces. We further show that existing hierarchical and bootstrapping-based approaches correspond to specific design choices within our derivation. Across a comprehensive suite of state- and pixel-based locomotion and manipulation benchmarks, our method matches or surpasses state-of-the-art offline GCRL algorithms and scales to complex, long-horizon tasks where prior approaches fail. Project page: https://johnlyzhou.github.io/saw/

The rapid development of artificial intelligence (AI) has unearthed the potential to assist humans in controlling advanced technologies. Shared autonomy (SA) facilitates control by combining inputs from a human pilot and an AI copilot. In prior SA studies, the copilot is constantly active in determining the action played at each time step. This limits human autonomy that may have deleterious effects on performance. In general, the amount of helpful copilot assistance varies greatly depending on the task dynamics. We therefore hypothesized that human autonomy and SA performance improves through dynamic and selective copilot intervention. To address this, we develop a goal-agnostic intervention assistance (IA) that dynamically shares control by having the copilot intervene only when the expected value of the copilot’s action exceeds that of the human’s action. We implement IA with a diffusion copilot (termed IDA) trained on expert demonstrations with goal masking. We prove that IDA performance is lower bounded by human performance, so that IDA does not negatively impact human control. In experiments with simulated human pilots, we show that IDA achieves higher performance than both pilot-only and traditional SA control in variants of the Reacher environment and Lunar Lander. We then demonstrate with human-in the-loop experiments that IDA achieves better control in Lunar Lander and that human participants experience greater autonomy and prefer IDA over pilot-only and traditional SA control. We attribute the success of IDA to preserving human autonomy while simultaneously offering assistance to prevent the human from entering universally bad states.

Cooperation between self-interested individuals is a widespread phenomenon in the natural world, but remains elusive in interactions between artificially intelligent agents. Instead, naïve reinforcement learning algorithms typically converge to Pareto-dominated outcomes in even the simplest of social dilemmas. An emerging literature on opponent shaping has demonstrated the ability to reach prosocial outcomes by influencing the learning of other agents. However, such methods differentiate through the learning step of other agents or optimize for meta-game dynamics, which rely on privileged access to opponents' learning algorithms or exponential sample complexity, respectively. To provide a learning rule-agnostic and sample-efficient alternative, we introduce Reciprocators, reinforcement learning agents which are intrinsically motivated to reciprocate the influence of opponents' actions on their returns. This approach seeks to modify other agents' $Q$-values by increasing their return following beneficial actions (with respect to the Reciprocator) and decreasing it after detrimental actions, guiding them towards mutually beneficial actions without directly differentiating through a model of their policy. We show that Reciprocators can be used to promote cooperation in temporally extended social dilemmas during simultaneous learning. Our code is available at https://github.com/johnlyzhou/reciprocator/.

We propose a notion of common information that allows one to quantify and separate the information that is shared between two random variables from the information that is unique to each. Our notion of common information is defined by an optimization problem over a family of functions and recovers the G\'acs-K\"orner common information as a special case. Importantly, our notion can be approximated empirically using samples from the underlying data distribution. We then provide a method to partition and quantify the common and unique information using a simple modification of a traditional variational auto-encoder. Empirically, we demonstrate that our formulation allows us to learn semantically meaningful common and unique factors of variation even on high-dimensional data such as images and videos. Moreover, on datasets where ground-truth latent factors are known, we show that we can accurately quantify the common information between the random variables.

Recurrent neural networks (RNNs) trained on neuroscience-based tasks have been widely used as models for cortical areas performing analogous tasks. However, very few tasks involve a single cortical area, and instead require the coordination of multiple brain areas. Despite the importance of multi-area computation, there is a limited understanding of the principles underlying such computation. We propose to use multi-area RNNs with neuroscience-inspired architecture constraints to derive key features of multi-area computation. In particular, we show that incorporating multiple areas and Dale's Law is critical for biasing the networks to learn biologically plausible solutions. Additionally, we leverage the full observability of the RNNs to show that output-relevant information is preferentially propagated between areas. These results suggest that cortex uses modular computation to generate minimal sufficient representations of task information. More broadly, our results suggest that constrained multi-area RNNs can produce experimentally testable hypotheses for computations that occur within and across multiple brain areas, enabling new insights into distributed computation in neural systems.

Recurrent neural networks (RNNs) are popular tools for studying computational dynamics in neurobiological circuits. However, due to the dizzying array of design choices, it is unclear if computational dynamics unearthed from RNNs provide reliable neurobiological inferences. Understanding the effects of design choices on RNN computation is valuable in two ways. First, invariant properties that persist in RNNs across a wide range of design choices are more likely to be candidate neurobiological mechanisms. Second, understanding what design choices lead to similar dynamical solutions reduces the burden of imposing that all design choices be totally faithful replications of biology. We focus our investigation on how RNN learning rule and task design affect RNN computation. We trained large populations of RNNs with different, but commonly used, learning rules on decision-making tasks inspired by neuroscience literature. For relatively complex tasks, we find that attractor topology is invariant to the choice of learning rule, but representational geometry is not. For simple tasks, we find that attractor topology depends on task input noise. However, when a task becomes increasingly complex, RNN attractor topology becomes invariant to input noise. Together, our results suggest that RNN dynamics are robust across learning rules but can be sensitive to the training task design, especially for simpler tasks.

Brain-computer interfaces (BCIs) record brain activity and translate the information into useful control signals. They can be used to restore function to people with paralysis by controlling end effectors such as computer cursors and robotic limbs. Communication neural prostheses are BCIs that control user interfaces on computers or mobile devices. Here we demonstrate a communication prosthesis by simulating a typing task with two rhesus macaques implanted with electrode arrays. The monkeys used two of the highest known performing BCI decoders to type out words and sentences when prompted one symbol/letter at a time. On average, Monkeys J and L achieved typing rates of 10.0 and 7.2 words per minute (wpm), respectively, copying text from a newspaper article using a velocity-only two dimensional BCI decoder with dwell-based symbol selection. With a BCI decoder that also featured a discrete click for key selection, typing rates increased to 12.0 and 7.8 wpm. These represent the highest known achieved communication rates using a BCI. We then quantified the relationship between bitrate and typing rate and found it approximately linear: typing rate in wpm is nearly three times bitrate in bits per second. We also compared the metrics of achieved bitrate and information transfer rate and discuss their applicability to real-world typing scenarios. Although this study cannot model the impact of cognitive load of word and sentence planning, the findings here demonstrate the feasibility of BCIs to serve as communication interfaces and represent an upper bound on the expected achieved typing rate for a given BCI throughput.

Brain-machine interface (BMI) systems convert neural signals from motor regions of the brain into control signals to guide prosthetic devices. The ultimate goal of BMIs is to improve the quality of life for people with paralysis by providing direct neural control of prosthetic arms or computer cursors. While considerable research over the past 15 years has led to compelling BMI demonstrations, there remain several challenges to achieving clinically viable BMI systems. In this review, we focus on the challenge of increasing BMI performance and robustness. We review and highlight key aspects of intracortical BMI decoder design, which is central to the conversion of neural signals into prosthetic control signals, and discuss emerging opportunities to improve intracortical BMI decoders. This is one of the primary research opportunities where information systems engineering can directly impact the future success of BMIs.