Leveraging pre-trained 2D image representations in behavior cloning policies has achieved great success and has become a standard approach for robotic manipulation. However, such representations fail to capture the 3D spatial information about objects and scenes that is essential for precise manipulation. In this work, we introduce Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining (CLAMP), a novel 3D pre-training framework that utilizes point clouds and robot actions. From the merged point cloud computed from RGB-D images […]

Ver mais

I’ve been working on developing foundation models for massively multimodal datasets (around 30-40 different modalities on 1 dataset, you can kind of think of it like robot with a lot of different sensors). I think most scientific papers I see from the last couple years use Perceiver, which I feel is a really intuitive and elegant solution (like you literally just slap on name of modality + the data and let it handle the rest). However, it is […]

Ver mais

arXiv:2601.17003v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for mental health support, yet existing safety evaluations rely primarily on small, simulation-based test sets that have an unknown relationship to the linguistic distribution of real usage. In this study, we present replications of four published safety test sets targeting suicide risk assessment, harmful content generation, refusal robustness, and adversarial jailbreaks for a leading frontier generic AI model alongside an AI purpose built for mental health […]

Ver mais

The global crypto market has faced a very difficult season recently. Over the last five months, the total market value has dropped by a staggering $2 trillion. Many famous coins have lost half of their value, leaving investors looking for safety. However, even in a down market, there are always outliers that defy the trend. While the giants are falling, a new project has managed to climb 300% during its development stage. This performance is catching the eye […]

Ver mais

arXiv:2601.12203v1 Announce Type: new Abstract: In young animals like poultry chicks (Gallus gallus), vocalisations convey information about affective and behavioural states. Traditional approaches to vocalisation analysis, relying on manual annotation and predefined categories, introduce biases, limit scalability, and fail to capture the full complexity of vocal repertoires. We introduce a computational framework for the automated detection, acoustic feature extraction, and unsupervised learning of chick vocalisations. Applying this framework to a dataset of newly hatched chicks, we identified two […]

Ver mais

As has been said by many commentators, rare earths are not particularly rare.  Via source, here is an estimate of their abundance in the Earth’s surface: Note by the way the Y-axis is logarithmic so small changes in vertical position can mean a factor of 10 or more difference in concentration.  But the rare earths are not unreasonably far off fairly common industrial metals like lead, nickel, copper, and molybdenum and well more common than gold, silver, and […]

Ver mais

arXiv:2601.20900v1 Announce Type: new Abstract: Adapting automatic speech recognition (ASR) systems based on large language models (LLMs) to new domains using text-only data is a significant yet underexplored challenge. Standard fine-tuning of the LLM on target-domain text often disrupts the critical alignment between speech and text modalities learned by the projector, degrading performance. We introduce a novel text-only adaptation method that emulates the audio projection task by treating it as a text denoising task. Our approach thus trains […]

Ver mais

arXiv:2601.21860v1 Announce Type: cross Abstract: The reconstruction and inference of stochastic dynamical systems from data is a fundamental task in inverse problems and statistical learning. While surrogate modeling advances computational methods to approximate these dynamics, standard approaches typically require high-fidelity training data. In many practical settings, the data are indirectly observed through noisy and nonlinear measurement. The challenge lies not only in approximating the coefficients of the SDEs, but in simultaneously inferring the posterior updates given the observations. […]

Ver mais