Mircea Teodorescu

John R. Minnick, Jesus Gonzalez-Ferrer, Kamran Hussain et al.

Closed-loop brain-computer interfaces often require both a forecast of upcoming neural population activity and a readout of the animal's behavioral state. A single Mamba forecaster, trained only on next-step spike counts at Neuropixels scale, can deliver both in one forward pass. A lightweight per-session linear head reading the model's predicted rates decodes behavior better than the same linear classifier reading the raw spike counts, under matched temporal context. We test on the Steinmetz visual-discrimination benchmark, which spans 39 sessions, roughly 27,000 neurons, and 1,994 held-out trials. Across three training seeds, Mamba's predicted rates decode mouse choice at 75.7$\pm$0.2% trial vote, roughly 2.3 times chance level, and stimulus side at 66.1$\pm$0.6%, about twice chance. Compared to a matched 500 ms-context linear decoder on the raw spike counts, Mamba wins at trial vote by 4-6 pp on response and 4-6 pp on stimulus side. A session-start calibration block of about 100-150 trials brings the readout within 1-2 pp of asymptote, and the full pipeline fits inside the 50 ms bin budget on workstation-class GPUs typical of tethered chronic Neuropixels recordings.

John R. Minnick, Jinghui Geng, Kamran Hussain et al.

Neural population models, which predict the joint firing of many simultaneously recorded neurons forward in time, are typically evaluated by a single aggregate Pearson correlation $r$ between predicted and actual spike counts, a number that masks critical structure. We argue that how we evaluate spike forecasting matters as much as what we build, and introduce SpikeProphecy, the first large-scale benchmark for causal, autoregressive spike-count forecasting on real electrophysiology recordings. Our core contribution is a population metric decomposition that separates aggregate performance into temporal fidelity, spatial pattern accuracy, and magnitude-invariant alignment. The decomposition surfaces aspects of the underlying data that an aggregate scalar collapses together. We apply the protocol to 105 Neuropixels sessions (Steinmetz 2019 + IBL Repeated Site; ~89,800 neurons) with seven architecture baselines spanning four structural families: four SSMs (three diagonal and one non-diagonal), a Transformer, an LSTM, and a spiking network. The decomposition surfaces a brain-region predictability ranking that reproduces across all seven baselines and survives ANCOVA correction for firing-statistics constraints (region $ΔR^2 = 0.018$ above the firing-statistics covariates). It also exposes a sub-Poisson evaluation floor where rigorous metrics combine with genuine biophysical constraints on regular spike trains, and yields a negative result on KL-on-output-rates distillation for ANN-to-SNN transfer in this Poisson count domain.

Maryam Tebyani, Alex Spaeth, Nicholas Cramer et al.

Voxel-based structures provide a modular, mechanically flexible periodic lattice which can be used as a soft robot through internal deformations. To engage these structures for robotic tasks, we use a finite element method to characterize the motion caused by deforming single degrees of freedom and develop a reduced kinematic model. We find that node translations propagate periodically along geometric planes within the lattice, and briefly show that translational modes dominate the energy usage of the actuators. The resulting kinematic model frames the structural deformations in terms of user-defined control and end effector nodes, which further reduces the model size. The derived Planes of Motion (POM) model can be equivalently used for forward and inverse kinematics, as demonstrated by the design of a tripod stable gait for a locomotive voxel robot and validation of the quasi-static model through physical experiments.

Alex Spaeth, Maryam Tebyani, David Haussler et al.

We propose a modular architecture for neuromorphic closed-loop control based on bistable relaxation oscillator modules consisting of three spiking neurons each. Like its biological prototypes, this basic component is robust to parameter variation but can be modulated by external inputs. By combining these modules, we can construct a neural state machine capable of generating the cyclic or repetitive behaviors necessary for legged locomotion. A concrete case study for the approach is provided by a modular robot constructed from flexible plastic volumetric pixels, in which we produce a forward crawling gait entrained to the natural frequency of the robot by a minimal system of twelve neurons organized into four modules.

Steven Lessard, Dennis Castro, William Asper et al.

Most traditional robotic mechanisms feature inelastic joints that are unable to robustly handle large deformations and off-axis moments. As a result, the applied loads are transferred rigidly throughout the entire structure. The disadvantage of this approach is that the exerted leverage is magnified at each subsequent joint possibly damaging the mechanism. In this paper, we present two lightweight, elastic, bio-inspired tensegrity robotics arms which mitigate this danger while improving their mechanism's functionality. Our solutions feature modular tensegrity structures that function similarly to the human elbow and the human shoulder when connected. Like their biological counterparts, the proposed robotic joints are flexible and comply with unanticipated forces. Both proposed structures have multiple passive degrees of freedom and four active degrees of freedom (two from the shoulder and two from the elbow). The structural advantages demonstrated by the joints in these manipulators illustrate a solution to the fundamental issue of elegantly handling off-axis compliance.

Steven Lessard, Jonathan Bruce, Erik Jung et al.

In this paper, we present a light-weight, multi- axis compliant tenegrity joint that is biologically inspired by the human elbow. This tensegrity elbow actuates by shortening and lengthening cable in a method inspired by muscular actuation in a person. Unlike many series elastic actuators, this joint is structurally compliant not just along each axis of rotation, but along other axes as well. Compliant robotic joints are indispensable in unpredictable environments, including ones where the robot must interface with a person. The joint also addresses the need for functional redundancy and flexibility, traits which are required for many applications that investigate the use of biologically accurate robotic models.