GASP: Guided Asymmetric Self-Play For Coding LLMs

Asymmetric self-play has emerged as a promising paradigm for post-training large language models, where a teacher continually generates questions for a student to solve at the edge of the student's learnability. Although these methods promise open-ended data generation bootstrapped from no human data, they suffer from one major problem: not all problems that are hard to solve are interesting or informative to improve the overall capabilities of the model. Current asymmetric self-play methods are goal-agnostic with no real grounding. We propose Guided Asymmetric Self-Play (GASP), where grounding is provided by real-data goalpost questions that are identified to pose a hard exploration challenge to the model. During self-play, the teacher first generates an easier variant of a hard question, and then a harder variant of that easier question, with the goal of gradually closing the gap to the goalpost throughout training. Doing so, we improve pass@20 on LiveCodeBench (LCB) by 2.5% over unguided asymmetric self-play, and through the curriculum constructed by the teacher, we manage to solve hard goalpost questions that remain out of reach for all baselines.

SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients

Automatic differentiation (AD) frameworks such as JAX and PyTorch have enabled gradient-based optimization for a wide range of scientific fields. Yet, many "hard" primitives in these libraries such as thresholding, Boolean logic, discrete indexing, and sorting operations yield zero or undefined gradients that are not useful for optimization. While numerous "soft" relaxations have been proposed that provide informative gradients, the respective implementations are fragmented across projects, making them difficult to combine and compare. This work introduces SoftJAX and SoftTorch, open-source, feature-complete libraries for soft differentiable programming. These libraries provide a variety of soft functions as drop-in replacements for their hard JAX and PyTorch counterparts. This includes (i) elementwise operators such as clip or abs, (ii) utility methods for manipulating Booleans and indices via fuzzy logic, (iii) axiswise operators such as sort or rank -- based on optimal transport or permutahedron projections, and (iv) offer full support for straight-through gradient estimation. Overall, SoftJAX and SoftTorch make the toolbox of soft relaxations easily accessible to differentiable programming, as demonstrated through benchmarking and a practical case study. Code is available at github.com/a-paulus/softjax and github.com/a-paulus/softtorch.

Smoothly Differentiable and Efficiently Vectorizable Contact Manifold Generation

Simulating rigid-body dynamics with contact in a fast, massively vectorizable, and smoothly differentiable manner is highly desirable in robotics. An important bottleneck faced by existing differentiable simulation frameworks is contact manifold generation: representing the volume of intersection between two colliding geometries via a discrete set of properly distributed contact points. A major factor contributing to this bottleneck is that the related routines of commonly used robotics simulators were not designed with vectorization and differentiability as a primary concern, and thus rely on logic and control flow that hinder these goals. We instead propose a framework designed from the ground up with these goals in mind, by trying to strike a middle ground between: i) convex primitive based approaches used by common robotics simulators (efficient but not differentiable), and ii) mollified vertex-face and edge-edge unsigned distance-based approaches used by barrier methods (differentiable but inefficient). Concretely, we propose: i) a representative set of smooth analytical signed distance primitives to implement vertex-face collisions, and ii) a novel differentiable edge-edge collision routine that can provide signed distances and signed contact normals. The proposed framework is evaluated via a set of didactic experiments and benchmarked against the collision detection routine of the well-established Mujoco XLA framework, where we observe a significant speedup. Supplementary videos can be found at https://github.com/bekeronur/contax, where a reference implementation in JAX will also be made available at the conclusion of the review process.

Adding internal audio sensing to internal vision enables human-like in-hand fabric recognition with soft robotic fingertips

Distinguishing the feel of smooth silk from coarse cotton is a trivial everyday task for humans. When exploring such fabrics, fingertip skin senses both spatio-temporal force patterns and texture-induced vibrations that are integrated to form a haptic representation of the explored material. It is challenging to reproduce this rich, dynamic perceptual capability in robots because tactile sensors typically cannot achieve both high spatial resolution and high temporal sampling rate. In this work, we present a system that can sense both types of haptic information, and we investigate how each type influences robotic tactile perception of fabrics. Our robotic hand's middle finger and thumb each feature a soft tactile sensor: one is the open-source Minsight sensor that uses an internal camera to measure fingertip deformation and force at 50 Hz, and the other is our new sensor Minsound that captures vibrations through an internal MEMS microphone with a bandwidth from 50 Hz to 15 kHz. Inspired by the movements humans make to evaluate fabrics, our robot actively encloses and rubs folded fabric samples between its two sensitive fingers. Our results test the influence of each sensing modality on overall classification performance, showing high utility for the audio-based sensor. Our transformer-based method achieves a maximum fabric classification accuracy of 97 % on a dataset of 20 common fabrics. Incorporating an external microphone away from Minsound increases our method's robustness in loud ambient noise conditions. To show that this audio-visual tactile sensing approach generalizes beyond the training data, we learn general representations of fabric stretchiness, thickness, and roughness.

Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities

Recent advancements in zero-shot reinforcement learning (RL) have facilitated the extraction of diverse behaviors from unlabeled, offline data sources. In particular, forward-backward algorithms (FB) can retrieve a family of policies that can approximately solve any standard RL problem (with additive rewards, linear in the occupancy measure), given sufficient capacity. While retaining zero-shot properties, we tackle the greater problem class of RL with general utilities, in which the objective is an arbitrary differentiable function of the occupancy measure. This setting is strictly more expressive, capturing tasks such as distribution matching or pure exploration, which may not be reduced to additive rewards. We show that this additional complexity can be captured by a novel, maximum entropy (soft) variant of the forward-backward algorithm, which recovers a family of stochastic policies from offline data. When coupled with zero-order search over compact policy embeddings, this algorithm can sidestep iterative optimization schemes, and optimizes general utilities directly at test-time. Across both didactic and high-dimensional experiments, we demonstrate that our method retains favorable properties of FB algorithms, while also extending their range to more general RL problems.

Stochastic Decision Horizons for Constrained Reinforcement Learning

Constrained Markov decision processes (CMDPs) provide a principled model for handling constraints, such as safety and other auxiliary objectives, in reinforcement learning. The common approach of using additive-cost constraints and dual variables often hinders off-policy scalability. We propose a Control as Inference formulation based on stochastic decision horizons, where constraint violations attenuate reward contributions and shorten the effective planning horizon via state-action-dependent continuation. This yields survival-weighted objectives that remain replay-compatible for off-policy actor-critic learning. We propose two violation semantics, absorbing and virtual termination, that share the same survival-weighted return but result in distinct optimization structures that lead to SAC/MPO-style policy improvement. Experiments demonstrate improved sample efficiency and favorable return-violation trade-offs on standard benchmarks. Moreover, MPO with virtual termination (VT-MPO) scales effectively to our high-dimensional musculoskeletal Hyfydy setup.

Fault Detection in Solar Thermal Systems using Probabilistic Reconstructions

Solar thermal systems (STS) present a promising avenue for low-carbon heat generation, with a well-running system providing heat at minimal cost and carbon emissions. However, STS can exhibit faults due to improper installation, maintenance, or operation, often resulting in a substantial reduction in efficiency or even damage to the system. As monitoring at the individual level is economically prohibitive for small-scale systems, automated monitoring and fault detection should be used to address such issues. Recent advances in data-driven anomaly detection, particularly in time series analysis, offer a cost-effective solution by leveraging existing sensors to identify abnormal system states. Here, we propose a probabilistic reconstruction-based framework for anomaly detection. We evaluate our method on the publicly available PaSTS dataset of operational domestic STS, which features real-world complexities and diverse fault types. Our experiments show that reconstruction-based methods can detect faults in domestic STS both qualitatively and quantitatively, while generalizing to previously unseen systems. We also demonstrate that our model outperforms both simple and more complex deep learning baselines. Additionally, we show that heteroscedastic uncertainty estimation is essential to fault detection performance. Finally, we discuss the engineering overhead required to unlock these improvements and make a case for simple deep learning models.

Hard Contacts with Soft Gradients: Refining Differentiable Simulators for Learning and Control

Contact forces pose a major challenge for gradient-based optimization of robot dynamics as they introduce jumps in the system's velocities. Penalty-based simulators, such as MuJoCo, simplify gradient computation by softening the contact forces. However, realistically simulating hard contacts requires very stiff contact settings, which leads to incorrect gradients when using automatic differentiation. On the other hand, using non-stiff settings strongly increases the sim-to-real gap. We analyze the contact computation of penalty-based simulators to identify the causes of gradient errors. Then, we propose DiffMJX, which combines adaptive integration with MuJoCo XLA, to notably improve gradient quality in the presence of hard contacts. Finally, we address a key limitation of contact gradients: they vanish when objects do not touch. To overcome this, we introduce Contacts From Distance (CFD), a mechanism that enables the simulator to generate informative contact gradients even before objects are in contact. To preserve physical realism, we apply CFD only in the backward pass using a straight-through trick, allowing us to compute useful gradients without modifying the forward simulation.

Learning 3D-Gaussian Simulators from RGB Videos

Learning physics simulations from video data requires maintaining spatial and temporal consistency, a challenge often addressed with strong inductive biases or ground-truth 3D information -- limiting scalability and generalization. We introduce 3DGSim, a 3D physics simulator that learns object dynamics end-to-end from multi-view RGB videos. It encodes images into a 3D Gaussian particle representation, propagates dynamics via a transformer, and renders frames using 3D Gaussian splatting. By jointly training inverse rendering with a dynamics transformer using a temporal encoding and merging layer, 3DGSimembeds physical properties into point-wise latent vectors without enforcing explicit connectivity constraints. This enables the model to capture diverse physical behaviors, from rigid to elastic and cloth-like interactions, along with realistic lighting effects that also generalize to unseen multi-body interactions and novel scene edits.

A Smooth Analytical Formulation of Collision Detection and Rigid Body Dynamics With Contact

Generating intelligent robot behavior in contact-rich settings is a research problem where zeroth-order methods currently prevail. A major contributor to the success of such methods is their robustness in the face of non-smooth and discontinuous optimization landscapes that are characteristic of contact interactions, yet zeroth-order methods remain computationally inefficient. It is therefore desirable to develop methods for perception, planning and control in contact-rich settings that can achieve further efficiency by making use of first and second order information (i.e., gradients and Hessians). To facilitate this, we present a joint formulation of collision detection and contact modelling which, compared to existing differentiable simulation approaches, provides the following benefits: i) it results in forward and inverse dynamics that are entirely analytical (i.e. do not require solving optimization or root-finding problems with iterative methods) and smooth (i.e. twice differentiable), ii) it supports arbitrary collision geometries without needing a convex decomposition, and iii) its runtime is independent of the number of contacts. Through simulation experiments, we demonstrate the validity of the proposed formulation as a "physics for inference" that can facilitate future development of efficient methods to generate intelligent contact-rich behavior.