Search

Modern robots vary significantly in shape, size, and sensor configurations used to perceive and interact with their environments. However, most navigation policies are embodiment-specific; a policy learned using one robot's configuration does not typically gracefully generalize to another. Even small changes in the body size or camera viewpoint may cause failures. With the recent surge in custom hardware developments, it is necessary to learn a single policy that can be transferred to other embodiments, eliminating the need to (re)train for each specific robot. In this paper, we introduce RING (Robotic Indoor Navigation Generalist), an embodiment-agnostic policy, trained solely in simulation with diverse randomly initialized embodiments at scale. Specifically, we augment the AI2-THOR simulator with the ability to instantiate robot embodiments with controllable configurations, varying across body size, rotation pivot point, and camera configurations. In the visual object-goal navigation task, RING achieves robust performance on real unseen robot platforms (Stretch RE-1, LoCoBot, Unitree's Go1), achieving an average of 72.1% and 78.9% success rate across 5 embodiments in simulation and 4 robot platforms in the real world. (project website: https://one-ring-policy.allen.ai/)

Spatial perception is a fundamental component of intelligence. While many studies highlight that large multimodal language models (MLMs) struggle to reason about space, they only test for static spatial reasoning, such as categorizing the relative positions of objects. Meanwhile, real-world deployment requires dynamic capabilities like perspective-taking and egocentric action recognition. As a roadmap to improving spatial intelligence, we introduce SAT, Spatial Aptitude Training, which goes beyond static relative object position questions to the more dynamic tasks. SAT contains 218K question-answer pairs for 22K synthetic scenes across a training and testing set. Generated using a photo-realistic physics engine, our dataset can be arbitrarily scaled and easily extended to new actions, scenes, and 3D assets. We find that even MLMs that perform relatively well on static questions struggle to accurately answer dynamic spatial questions. Further, we show that SAT instruction-tuning data improves not only dynamic spatial reasoning on SAT, but also zero-shot performance on existing real-image spatial benchmarks: $23\%$ on CVBench, $8\%$ on the harder BLINK benchmark, and $18\%$ on VSR. When instruction-tuned on SAT, our 13B model matches larger proprietary MLMs like GPT4-V and Gemini-3-1.0 in spatial reasoning. Our data/code is available at http://arijitray1993.github.io/SAT/ ., Comment: Project webpage: http://arijitray1993.github.io/SAT/

We introduce FedEvPrompt, a federated learning approach that integrates principles of evidential deep learning, prompt tuning, and knowledge distillation for distributed skin lesion classification. FedEvPrompt leverages two sets of prompts: b-prompts (for low-level basic visual knowledge) and t-prompts (for task-specific knowledge) prepended to frozen pre-trained Vision Transformer (ViT) models trained in an evidential learning framework to maximize class evidences. Crucially, knowledge sharing across federation clients is achieved only through knowledge distillation on attention maps generated by the local ViT models, ensuring enhanced privacy preservation compared to traditional parameter or synthetic image sharing methodologies. FedEvPrompt is optimized within a round-based learning paradigm, where each round involves training local models followed by attention maps sharing with all federation clients. Experimental validation conducted in a real distributed setting, on the ISIC2019 dataset, demonstrates the superior performance of FedEvPrompt against baseline federated learning algorithms and knowledge distillation methods, without sharing model parameters. In conclusion, FedEvPrompt offers a promising approach for federated learning, effectively addressing challenges such as data heterogeneity, imbalance, privacy preservation, and knowledge sharing., Comment: Published as a conference paper at ICPR 2024

Richardson-Lucy deconvolution is widely used to restore images from degradation caused by the broadening effects of a point spread function and corruption by photon shot noise, in order to recover an underlying object. In practice, this is achieved by iteratively maximizing a Poisson emission likelihood. However, the RL algorithm is known to prefer sparse solutions and overfit noise, leading to high-frequency artifacts. The structure of these artifacts is sensitive to the number of RL iterations, and this parameter is typically hand-tuned to achieve reasonable perceptual quality of the inferred object. Overfitting can be mitigated by introducing tunable regularizers or other ad hoc iteration cutoffs in the optimization as otherwise incorporating fully realistic models can introduce computational bottlenecks. To resolve these problems, we present Bayesian deconvolution, a rigorous deconvolution framework that combines a physically accurate image formation model avoiding the challenges inherent to the RL approach. Our approach achieves deconvolution while satisfying the following desiderata: I deconvolution is performed in the spatial domain (as opposed to the frequency domain) where all known noise sources are accurately modeled and integrated in the spirit of providing full probability distributions over the density of the putative object recovered; II the probability distribution is estimated without making assumptions on the sparsity or continuity of the underlying object; III unsupervised inference is performed and converges to a stable solution with no user-dependent parameter tuning or iteration cutoff; IV deconvolution produces strictly positive solutions; and V implementation is amenable to fast, parallelizable computation., Comment: 5 figures

We present Crux, a cross-language verification tool for Rust and C/LLVM. Crux targets bounded, intricate pieces of code that are difficult for humans to get right: for example, cryptographic modules and serializer / deserializer pairs. Crux builds on the same framework as the mature SAW-Cryptol toolchain, but Crux provides an interface where proofs are phrased as symbolic unit tests. Crux is designed for use in production environments, and has already seen use in industry. In this paper, we focus on Crux-MIR, our verification tool for Rust. Crux-MIR provides a bit-precise model of safe and unsafe Rust which can be used to check both inline properties about Rust code, and extensional equality to executable specifications written in Cryptol or in the hacspec dialect of Rust. Notably, Crux-MIR supports compositional reasoning, which is necessary to scale to even moderately complex proofs. We demonstrate Crux-MIR by verifying the Ring library implementations of SHA1 and SHA2 against pre-existing functional specifications. Crux is available at https://crux.galois.com.

Today's most advanced vision-language models (VLMs) remain proprietary. The strongest open-weight models rely heavily on synthetic data from proprietary VLMs to achieve good performance, effectively distilling these closed VLMs into open ones. As a result, the community has been missing foundational knowledge about how to build performant VLMs from scratch. We present Molmo, a new family of VLMs that are state-of-the-art in their class of openness. Our key contribution is a collection of new datasets called PixMo, including a dataset of highly detailed image captions for pre-training, a free-form image Q&A dataset for fine-tuning, and an innovative 2D pointing dataset, all collected without the use of external VLMs. The success of our approach relies on careful modeling choices, a well-tuned training pipeline, and, most critically, the quality of our newly collected datasets. Our best-in-class 72B model not only outperforms others in the class of open weight and data models, but also outperforms larger proprietary models including Claude 3.5 Sonnet, and Gemini 1.5 Pro and Flash, second only to GPT-4o based on both academic benchmarks and on a large human evaluation. Our model weights, new datasets, and source code are available at https://molmo.allenai.org/blog., Comment: Updated with ablations and more technical details

In recent years, the Robotics field has initiated several efforts toward building generalist robot policies through large-scale multi-task Behavior Cloning. However, direct deployments of these policies have led to unsatisfactory performance, where the policy struggles with unseen states and tasks. How can we break through the performance plateau of these models and elevate their capabilities to new heights? In this paper, we propose FLaRe, a large-scale Reinforcement Learning fine-tuning framework that integrates robust pre-trained representations, large-scale training, and gradient stabilization techniques. Our method aligns pre-trained policies towards task completion, achieving state-of-the-art (SoTA) performance both on previously demonstrated and on entirely novel tasks and embodiments. Specifically, on a set of long-horizon mobile manipulation tasks, FLaRe achieves an average success rate of 79.5% in unseen environments, with absolute improvements of +23.6% in simulation and +30.7% on real robots over prior SoTA methods. By utilizing only sparse rewards, our approach can enable generalizing to new capabilities beyond the pretraining data with minimal human effort. Moreover, we demonstrate rapid adaptation to new embodiments and behaviors with less than a day of fine-tuning. Videos can be found on the project website at https://robot-flare.github.io/

Deep learning models have achieved promising results in breast cancer classification, yet their 'black-box' nature raises interpretability concerns. This research addresses the crucial need to gain insights into the decision-making process of convolutional neural networks (CNNs) for mammogram classification, specifically focusing on the underlying reasons for the CNN's predictions of breast cancer. For CNNs trained on the Mammographic Image Analysis Society (MIAS) dataset, we compared the post-hoc interpretability techniques LIME, Grad-CAM, and Kernel SHAP in terms of explanatory depth and computational efficiency. The results of this analysis indicate that Grad-CAM, in particular, provides comprehensive insights into the behavior of the CNN, revealing distinctive patterns in normal, benign, and malignant breast tissue. We discuss the implications of the current findings for the use of machine learning models and interpretation techniques in clinical practice., Comment: 16 pages, 13 figures (9 in the main text, 3 in the appendix). Accepted at PMLR 2024

When attempting to understand the behavior of an executable, a binary analyst can make use of many different techniques. These include program slicing, dynamic instrumentation, binary-level rewriting, symbolic execution, and formal verification, all of which can uncover insights into how a piece of machine code behaves. As a result, there is no one-size-fits-all binary analysis tool, so a binary analysis researcher will often combine several different tools. Sometimes, a researcher will even need to design new tools to study problems that existing frameworks are not well equipped to handle. Designing such tools from complete scratch is rarely time- or cost-effective, however, given the scale and complexity of modern instruction set architectures. We present Macaw, a modular framework that makes it possible to rapidly build reliable binary analysis tools across a range of use cases. Over a decade of development, we have used Macaw to support an industrial research team in building tools for machine code-related tasks. As such, the name "Macaw" refers not just to the framework itself, but also a suite of tools that are built on top of the framework. We describe Macaw in depth and describe the different static and dynamic analyses that it performs, many of which are powered by an SMT-based symbolic execution engine. We put a particular focus on interoperability between machine code and higher-level languages, including binary lifting from x86 to LLVM, as well verifying the correctness of mixed C and assembly code.

We present PoliFormer (Policy Transformer), an RGB-only indoor navigation agent trained end-to-end with reinforcement learning at scale that generalizes to the real-world without adaptation despite being trained purely in simulation. PoliFormer uses a foundational vision transformer encoder with a causal transformer decoder enabling long-term memory and reasoning. It is trained for hundreds of millions of interactions across diverse environments, leveraging parallelized, multi-machine rollouts for efficient training with high throughput. PoliFormer is a masterful navigator, producing state-of-the-art results across two distinct embodiments, the LoCoBot and Stretch RE-1 robots, and four navigation benchmarks. It breaks through the plateaus of previous work, achieving an unprecedented 85.5% success rate in object goal navigation on the CHORES-S benchmark, a 28.5% absolute improvement. PoliFormer can also be trivially extended to a variety of downstream applications such as object tracking, multi-object navigation, and open-vocabulary navigation with no finetuning.

The use of e-learning systems has a long tradition, where students can study online helped by a system. In this context, the use of recommender systems is relatively new. In our research project, we investigated various ways to create a recommender system. They all aim at facilitating the learning and understanding of a student. We present a common concept of the learning path and its learning indicators and embed 5 different recommenders in this context.

We present an optimization strategy for atom-specific spin-polarization constants within the spin-polarized GFN2-xTB framework, aiming to enhance the accuracy of molecular simulations. We compare a sequential and global optimization of spin parameters for hydrogen, carbon, nitrogen, oxygen, and fluorine. Sensitivity analysis using Sobol indices guides the identification of the most influential parameters for a given reference dataset, allowing for a nuanced understanding of their impact on diverse molecular properties. In the case of the W4-11 dataset, substantial error reduction was achieved, demonstrating the potential of the optimization. Transferability of the optimized spin-polarization constants over different properties, however, is limited, as we demonstrate by applying the optimized parameters on a set of singlet-triplet gaps in carbenes. Further studies on ionization potentials and electron affinities highlight some inherent limitations of current extended tight-binding methods that can not be resolved by simple parameter optimization. We conclude that the significantly improved accuracy strongly encourages the present re-optimization of the spin-polarization constants, whereas the limited transferability motivates a property-specific optimization strategy.

Pulmonary nodules may be an early manifestation of lung cancer, the leading cause of cancer-related deaths among both men and women. Numerous studies have established that deep learning methods can yield high-performance levels in the detection of lung nodules in chest X-rays. However, the lack of gold-standard public datasets slows down the progression of the research and prevents benchmarking of methods for this task. To address this, we organized a public research challenge, NODE21, aimed at the detection and generation of lung nodules in chest X-rays. While the detection track assesses state-of-the-art nodule detection systems, the generation track determines the utility of nodule generation algorithms to augment training data and hence improve the performance of the detection systems. This paper summarizes the results of the NODE21 challenge and performs extensive additional experiments to examine the impact of the synthetically generated nodule training images on the detection algorithm performance., Comment: 15 pages, 5 figures

Recent advancements in robotics have enabled robots to navigate complex scenes or manipulate diverse objects independently. However, robots are still impotent in many household tasks requiring coordinated behaviors such as opening doors. The factorization of navigation and manipulation, while effective for some tasks, fails in scenarios requiring coordinated actions. To address this challenge, we introduce, HarmonicMM, an end-to-end learning method that optimizes both navigation and manipulation, showing notable improvement over existing techniques in everyday tasks. This approach is validated in simulated and real-world environments and adapts to novel unseen settings without additional tuning. Our contributions include a new benchmark for mobile manipulation and the successful deployment with only RGB visual observation in a real unseen apartment, demonstrating the potential for practical indoor robot deployment in daily life. More results are on our project site: https://rchalyang.github.io/HarmonicMM/, Comment: More results are on our project site: https://rchalyang.github.io/HarmonicMM/

In testing industry, precise item categorization is pivotal to align exam questions with the designated content domains outlined in the assessment blueprint. Traditional methods either entail manual classification, which is laborious and error-prone, or utilize machine learning requiring extensive training data, often leading to model underfit or overfit issues. This study unveils a novel approach employing the zero-shot and few-shot Generative Pretrained Transformer (GPT) classifier for hierarchical item categorization, minimizing the necessity for training data, and instead, leveraging human-like language descriptions to define categories. Through a structured python dictionary, the hierarchical nature of examination blueprints is navigated seamlessly, allowing for a tiered classification of items across multiple levels. An initial simulation with artificial data demonstrates the efficacy of this method, achieving an average accuracy of 92.91% measured by the F1 score. This method was further applied to real exam items from the 2022 In-Training Examination (ITE) conducted by the American Board of Family Medicine (ABFM), reclassifying 200 items according to a newly formulated blueprint swiftly in 15 minutes, a task that traditionally could span several days among editors and physicians. This innovative approach not only drastically cuts down classification time but also ensures a consistent, principle-driven categorization, minimizing human biases and discrepancies. The ability to refine classifications by adjusting definitions adds to its robustness and sustainability.

Reinforcement learning (RL) with dense rewards and imitation learning (IL) with human-generated trajectories are the most widely used approaches for training modern embodied agents. RL requires extensive reward shaping and auxiliary losses and is often too slow and ineffective for long-horizon tasks. While IL with human supervision is effective, collecting human trajectories at scale is extremely expensive. In this work, we show that imitating shortest-path planners in simulation produces agents that, given a language instruction, can proficiently navigate, explore, and manipulate objects in both simulation and in the real world using only RGB sensors (no depth map or GPS coordinates). This surprising result is enabled by our end-to-end, transformer-based, SPOC architecture, powerful visual encoders paired with extensive image augmentation, and the dramatic scale and diversity of our training data: millions of frames of shortest-path-expert trajectories collected inside approximately 200,000 procedurally generated houses containing 40,000 unique 3D assets. Our models, data, training code, and newly proposed 10-task benchmarking suite CHORES are available in https://spoc-robot.github.io., Comment: First six authors contributed equally. Project page: https://spoc-robot.github.io/