Scaling up self-supervised learning has driven breakthroughs in language and vision, yet comparable progress has remained elusive in reinforcement learning (RL). In this paper, we study building blocks for self-supervised RL that unlock substantial improvements in scalability, with network depth serving as a critical factor. Whereas most RL papers in recent years have relied on shallow architectures (around 2 - 5 layers), we demonstrate that increasing the depth up to 1024 layers can significantly boost performance. Our experiments are conducted in an unsupervised goal-conditioned setting, where no demonstrations or rewards are provided, so an agent must explore (from scratch) and learn how to maximize the likelihood of reaching commanded goals. Evaluated on simulated locomotion and manipulation tasks, our approach increases performance by $2\times$ - $50\times$. Increasing the model depth not only increases success rates but also qualitatively changes the behaviors learned.

Reasoning and strategic behavior in social interactions is a hallmark of intelligence. This form of reasoning is significantly more sophisticated than isolated planning or reasoning tasks in static settings (e.g., math problem solving). In this paper, we present Strategic Planning, Interaction, and Negotiation (SPIN-Bench), a new multi-domain evaluation designed to measure the intelligence of strategic planning and social reasoning. While many existing benchmarks focus on narrow planning or single-agent reasoning, SPIN-Bench combines classical PDDL tasks, competitive board games, cooperative card games, and multi-agent negotiation scenarios in one unified framework. The framework includes both a benchmark as well as an arena to simulate and evaluate the variety of social settings to test reasoning and strategic behavior of AI agents. We formulate the benchmark SPIN-Bench by systematically varying action spaces, state complexity, and the number of interacting agents to simulate a variety of social settings where success depends on not only methodical and step-wise decision making, but also conceptual inference of other (adversarial or cooperative) participants. Our experiments reveal that while contemporary LLMs handle basic fact retrieval and short-range planning reasonably well, they encounter significant performance bottlenecks in tasks requiring deep multi-hop reasoning over large state spaces and socially adept coordination under uncertainty. We envision SPIN-Bench as a catalyst for future research on robust multi-agent planning, social reasoning, and human--AI teaming. Project Website: https://spinbench.github.io/

Combining LiDAR and Camera-view data has become a common approach for 3D Object Detection. However, previous approaches combine the two input streams at a point-level, throwing away semantic information derived from camera features. In this paper we propose Cross-View Center Point-Fusion, a state-of-the-art model to perform 3D object detection by combining camera and LiDAR-derived features in the BEV space to preserve semantic density from the camera stream while incorporating spacial data from the LiDAR stream. Our architecture utilizes aspects from previously established algorithms--Cross-View Transformers and CenterPoint--and runs their backbones in parallel, allowing efficient computation for real-time processing and application. In this paper we find that while an implicitly calculated depth-estimate may be sufficiently accurate in a 2D map-view representation, explicitly calculated geometric and spacial information is needed for precise bounding box prediction in the 3D world-view space. Code to reproduce our results is available at https: // github.

Recent advancements in Large Language Models (LLMs) have showcased their ability to perform complex reasoning tasks, but their effectiveness in planning remains underexplored. In this study, we evaluate the planning capabilities of OpenAI's o1 models across a variety of benchmark tasks, focusing on three key aspects: feasibility, optimality, and generalizability. Through empirical evaluations on constraint-heavy tasks (e.g., $\textit{Barman}$, $\textit{Tyreworld}$) and spatially complex environments (e.g., $\textit{Termes}$, $\textit{Floortile}$), we highlight o1-preview's strengths in self-evaluation and constraint-following, while also identifying bottlenecks in decision-making and memory management, particularly in tasks requiring robust spatial reasoning. Our results reveal that o1-preview outperforms GPT-4 in adhering to task constraints and managing state transitions in structured environments. However, the model often generates suboptimal solutions with redundant actions and struggles to generalize effectively in spatially complex tasks. This pilot study provides foundational insights into the planning limitations of LLMs, offering key directions for future research on improving memory management, decision-making, and generalization in LLM-based planning. Code available at https://github.com/VITA-Group/o1-planning.

This paper presents GPFC, a novel Graphics Processing Unit (GPU) Phase Folding and Convolutional Neural Network (CNN) system to detect exoplanets using the transit method. We devise a fast folding algorithm parallelized on a GPU to amplify low signal-to-noise ratio transit signals, allowing a search at high precision and speed. A CNN trained on two million synthetic light curves reports a score indicating the likelihood of a planetary signal at each period. While the GPFC method has broad applicability across period ranges, this research specifically focuses on detecting ultra-short-period planets with orbital periods less than one day. GPFC improves on speed by three orders of magnitude over the predominant Box-fitting Least Squares (BLS) method. Our simulation results show GPFC achieves $97%$ training accuracy, higher true positive rate at the same false positive rate of detection, and higher precision at the same recall rate when compared to BLS. GPFC recovers $100\%$ of known ultra-short-period planets in $\textit{Kepler}$ light curves from a blind search. These results highlight the promise of GPFC as an alternative approach to the traditional BLS algorithm for finding new transiting exoplanets in data taken with $\textit{Kepler}$ and other space transit missions such as K2, TESS and future PLATO and Earth 2.0.

With the rapid evolution of Natural Language Processing (NLP), Large Language Models (LLMs) like ChatGPT have emerged as powerful tools capable of transforming various sectors. Their vast knowledge base and dynamic interaction capabilities represent significant potential in improving education by operating as a personalized assistant. However, the possibility of generating incorrect, biased, or unhelpful answers are a key challenge to resolve when deploying LLMs in an education context. This work introduces an innovative architecture that combines the strengths of ChatGPT with a traditional information retrieval based chatbot framework to offer enhanced student support in higher education. Our empirical evaluations underscore the high promise of this approach.

Since the discovery of the first hot Jupiter orbiting a solar-type star, 51 Peg, in 1995, more than 4000 exoplanets have been identified using various observational techniques. The formation process of these sub-Earths remains elusive, and acquiring additional samples is essential for investigating this unique population. In our study, we employ a novel GPU Phase Folding algorithm combined with a Convolutional Neural Network, termed the GPFC method, on Kepler photometry data. This method enhances the transit search speed significantly over the traditional Box-fitting Least Squares method, allowing a complete search of the known KOI photometry data within hours using a commercial GPU card. To date, we have identified five promising sub-Earth short-period candidates: K00446.c, K01821.b, K01522.c, K03404.b, and K04978.b. A closer analysis reveals the following characteristics: K00446.c orbits a K dwarf on a 0.645091-day period. With a radius of $0.461R_\oplus$, it ranks as the second smallest USP discovered to date. K01821.b is a sub-Earth with a radius of $0.648R_\oplus$, orbiting a G dwarf over a 0.91978-day period. It is the second smallest USP among all confirmed USPs orbiting G dwarfs in the NASA Archive. K01522.c has a radius of $0.704 R_\oplus$ and completes an orbit around a Sun-like G dwarf in 0.64672 days; K03404.b, with a radius of $0.738 R_\oplus$, orbits a G dwarf on a 0.68074-day period; and K04978.b, with its planetary radius of $0.912 R_\oplus$, orbits a G dwarf, completing an orbit every 0.94197 days. Three of our finds, K01821.b, K01522.c and K03404.b, rank as the smallest planets among all confirmed USPs orbiting G dwarfs in the Kepler dataset. The discovery of these small exoplanets underscores the promising capability of the GPFC method for searching for small, new transiting exoplanets in photometry data from Kepler, TESS, and future space transit missions.

Ultrasound (US) imaging is a vital adjunct to mammography in breast cancer screening and diagnosis, but its reliance on hand-held transducers often lacks repeatability and heavily depends on sonographers' skills. Integrating US systems from different vendors further complicates clinical standards and workflows. This research introduces a co-robotic US platform for repeatable, accurate, and vendor-independent breast US image acquisition. The platform can autonomously perform 3D volume scans or swiftly acquire real-time 2D images of suspicious lesions. Utilizing a Universal Robot UR5 with an RGB camera, a force sensor, and an L7-4 linear array transducer, the system achieves autonomous navigation, motion control, and image acquisition. The calibrations, including camera-mammogram, robot-camera, and robot-US, were rigorously conducted and validated. Governed by a PID force control, the robot-held transducer maintains a constant contact force with the compression plate during the scan for safety and patient comfort. The framework was validated on a lesion-mimicking phantom. Our results indicate that the developed co-robotic US platform promises to enhance the precision and repeatability of breast cancer screening and diagnosis. Additionally, the platform offers straightforward integration into most mammographic devices to ensure vendor-independence.

Generative AI systems such as ChatGPT have a disruptive effect on learning and assessment. Computer science requires practice to develop skills in problem solving and programming that are traditionally developed using assignments. Generative AI has the capability of completing these assignments for students with high accuracy, which dramatically increases the potential for academic integrity issues and students not achieving desired learning outcomes. This work investigates the performance of ChatGPT by evaluating it across three courses (CS1,CS2,databases). ChatGPT completes almost all introductory assessments perfectly. Existing detection methods, such as MOSS and JPlag (based on similarity metrics) and GPTzero (AI detection), have mixed success in identifying AI solutions. Evaluating instructors and teaching assistants using heuristics to distinguish between student and AI code shows that their detection is not sufficiently accurate. These observations emphasize the need for adapting assessments and improved detection methods.

For a complicated algorithm, its implementation by a human programmer usually starts with outlining a rough control flow followed by iterative enrichments, eventually yielding carefully generated syntactic structures and variables in a hierarchy. However, state-of-the-art large language models generate codes in a single pass, without intermediate warm-ups to reflect the structured thought process of "outline-then-detail". Inspired by the recent success of chain-of-thought prompting, we propose ChainCoder, a program synthesis language model that generates Python code progressively, i.e. from coarse to fine in multiple passes. We first decompose source code into layout frame components and accessory components via abstract syntax tree parsing to construct a hierarchical representation. We then reform our prediction target into a multi-pass objective, each pass generates a subsequence, which is concatenated in the hierarchy. Finally, a tailored transformer architecture is leveraged to jointly encode the natural language descriptions and syntactically aligned I/O data samples. Extensive evaluations show that ChainCoder outperforms state-of-the-arts, demonstrating that our progressive generation eases the reasoning procedure and guides the language model to generate higher-quality solutions. Our codes are available at: https://github.com/VITA-Group/ChainCoder.