搜索结果：Apollo

Leveraging machine learning (ML) to predict an initial solution for mixed-integer linear programming (MILP) has gained considerable popularity in recent years. These methods predict a solution and fix a subset of variables to reduce the problem dimension. Then, they solve the reduced problem to obtain the final solutions. However, directly fixing variable values can lead to low-quality solutions or even infeasible reduced problems if the predicted solution is not accurate enough. To address this challenge, we propose an Alternating prediction-correction neural solving framework (Apollo-MILP) that can identify and select accurate and reliable predicted values to fix. In each iteration, Apollo-MILP conducts a prediction step for the unfixed variables, followed by a correction step to obtain an improved solution (called reference solution) through a trust-region search. By incorporating the predicted and reference solutions, we introduce a novel Uncertainty-based Error upper BOund (UEBO) to evaluate the uncertainty of the predicted values and fix those with high confidence. A notable feature of Apollo-MILP is the superior ability for problem reduction while preserving optimality, lead

The Apollo Advanced Telecommunications Computing Architecture (ATCA) platform is an open-source design consisting of a generic "Service Module" (SM) and a customizable "Command Module" (CM), allowing for cost-effective use in applications such as the readout of the inner tracker and the Level-1 track trigger for the CMS Phase-II upgrade at the HL-LHC. The SM integrates an intelligent IPMC, robust power entry and conditioning systems, a powerful system-on-module computer, and flexible clock and communication infrastructure. The CM is designed around two Xilinx Ultrascale+ FPGAs and high-density, high-bandwidth optical transceivers capable of 25 Gb/s. Crates of Apollo blades are currently being tested at Boston University, Cornell University, and CERN.

Urban mobility and transportation systems have been profoundly transformed by the advancement of autonomous vehicle technologies. Baidu Apollo Go, a pioneer robotaxi service from the Chinese tech giant Baidu, has recently been widely deployed in major cities like Beijing and Wuhan, sparking increased conversation and offering a glimpse into the future of urban mobility. This study investigates public attitudes towards Apollo Go across China using Sentiment Analysis with a hybrid BERT model on 36,096 Weibo posts from January to July 2024. The analysis shows that 89.56\% of posts related to Apollo Go are clustered in July. From January to July, public sentiment was mostly positive, but negative comments began to rise after it became a hot topic on July 21. Spatial analysis indicates a strong correlation between provinces with high discussion intensity and those where Apollo Go operates. Initially, Hubei and Guangdong dominated online posting volume, but by July, Guangdong, Beijing, and international regions had overtaken Hubei. Attitudes varied significantly among provinces, with Xinjiang and Qinghai showing optimism and Tibet and Gansu expressing concerns about the impact on traditi

Audio-video joint generation has progressed rapidly, yet substantial challenges still remain. Non-commercial approaches still suffer audio-visual asynchrony, poor lip-speech alignment, and unimodal degradation, which can be stemmed from weak audio-visual correspondence modeling, limited generalization, and scarce high-quality dense-caption data. To address these issues, we introduce Apollo and delve into three axes--model architecture, training strategy, and data curation. Architecturally, we adopt a single-tower design with unified DiT blocks and an Omni-Full Attention mechanism, achieving tight audio-visual alignment and strong scalability. Training-wise, we adopt a progressive multitask regime--random modality masking to joint optimization across tasks, and a multistage curriculum, yielding robust representations, strengthening A-V aligned world knowledge, and preventing unimodal collapse. For datasets, we present the first large-scale audio-video dataset with dense captions, and introduce a novel automated data-construction pipeline which annotates and filters millions of diverse, high-quality, strictly aligned audio-video-caption triplets. Building on this, Apollo scales to la

Formal reasoning and automated theorem proving constitute a challenging subfield of machine learning, in which machines are tasked with proving mathematical theorems using formal languages like Lean. A formal verification system can check whether a formal proof is correct or not almost instantaneously, but generating a completely correct formal proof with large language models (LLMs) remains a formidable task. The usual approach in the literature is to prompt the LLM many times (up to several thousands) until one of the generated proofs passes the verification system. In this work, we present APOLLO (Automated PrOof repair viaLLM and Lean cOllaboration), a modular, model-agnostic agentic framework that combines the strengths of the Lean compiler with an LLM's reasoning abilities to achieve better proof-generation results at a low token and sampling budgets. Apollo directs a fully automated process in which the LLM generates proofs for theorems, a set of agents analyze the proofs, fix the syntax errors, identify the mistakes in the proofs using Lean, isolate failing sub-lemmas, utilize automated solvers, and invoke an LLM on each remaining goal with a low top-K budget. The repaired

Full-stack autonomous driving system spans diverse technological domains-including perception, planning, and control-that each require in-depth research. Moreover, validating such technologies of the system necessitates extensive supporting infrastructure, from simulators and sensors to high-definition maps. These complexities with barrier to entry pose substantial limitations for individual developers and research groups. Recently, open-source autonomous driving software platforms have emerged to address this challenge by providing autonomous driving technologies and practical supporting infrastructure for implementing and evaluating autonomous driving functionalities. Among the prominent open-source platforms, Autoware and Apollo are frequently adopted in both academia and industry. While previous studies have assessed each platform independently, few have offered a quantitative and detailed head-to-head comparison of their capabilities. In this paper, we systematically examine the core modules of Autoware and Apollo and evaluate their middleware performance to highlight key differences. These insights serve as a practical reference for researchers and engineers, guiding them in

Audio restoration has become increasingly significant in modern society, not only due to the demand for high-quality auditory experiences enabled by advanced playback devices, but also because the growing capabilities of generative audio models necessitate high-fidelity audio. Typically, audio restoration is defined as a task of predicting undistorted audio from damaged input, often trained using a GAN framework to balance perception and distortion. Since audio degradation is primarily concentrated in mid- and high-frequency ranges, especially due to codecs, a key challenge lies in designing a generator capable of preserving low-frequency information while accurately reconstructing high-quality mid- and high-frequency content. Inspired by recent advancements in high-sample-rate music separation, speech enhancement, and audio codec models, we propose Apollo, a generative model designed for high-sample-rate audio restoration. Apollo employs an explicit frequency band split module to model the relationships between different frequency bands, allowing for more coherent and higher-quality restored audio. Evaluated on the MUSDB18-HQ and MoisesDB datasets, Apollo consistently outperforms

Despite the vast repository of global medical knowledge predominantly being in English, local languages are crucial for delivering tailored healthcare services, particularly in areas with limited medical resources. To extend the reach of medical AI advancements to a broader population, we aim to develop medical LLMs across the six most widely spoken languages, encompassing a global population of 6.1 billion. This effort culminates in the creation of the ApolloCorpora multilingual medical dataset and the XMedBench benchmark. In the multilingual medical benchmark, the released Apollo models, at various relatively-small sizes (i.e., 0.5B, 1.8B, 2B, 6B, and 7B), achieve the best performance among models of equivalent size. Especially, Apollo-7B is the state-of-the-art multilingual medical LLMs up to 70B. Additionally, these lite models could be used to improve the multi-lingual medical capabilities of larger models without fine-tuning in a proxy-tuning fashion. We will open-source training corpora, code, model weights and evaluation benchmark.

Large language models (LLMs) are notoriously memory-intensive during training, particularly with the popular AdamW optimizer. This memory burden necessitates using more or higher-end GPUs or reducing batch sizes, limiting training scalability and throughput. To address this, various memory-efficient optimizers have been proposed to reduce optimizer memory usage. However, they face critical challenges: (i) reliance on costly SVD operations; (ii) significant performance trade-offs compared to AdamW; and (iii) still substantial optimizer memory overhead to maintain competitive performance. In this work, we identify that AdamW's learning rate adaptation rule can be effectively coarsened as a structured learning rate update. Based on this insight, we propose Approximated Gradient Scaling for Memory-Efficient LLM Optimization (APOLLO), which approximates learning rate scaling using an auxiliary low-rank optimizer state based on pure random projection. This structured learning rate update rule makes APOLLO highly tolerant to further memory reductions while delivering comparable pre-training performance. Even its rank-1 variant, APOLLO-Mini, achieves superior pre-training performance compa

This brief note presents a novel method for encoding historic Apollo 11 Lunar Module guidance computer code into a single, compact Quick Response Code (QR code) format, creating an accessible digital artifact for transmission and archival purposes. By applying tokenization, selective content preservation, and minimal HTML/JavaScript techniques, we successfully compressed key components of the original Assembly Language Code (AGC) into a shareable, preservable, and scannable 3 kilobyte (KB) image. We evaluate multiple compression strategies and their tradeoffs in terms of size, readability, and historical significance. This method addresses the challenge of making historically significant software artifacts available through modern mobile devices without requiring specialized hardware or internet connectivity. While numerous digital preservation methods exist for historic software, this approach balances accessibility with historical significance, offering a complementary method to traditional archival techniques. This work contributes to the broader field of computing heritage preservation by demonstrating how landmark software can be made accessible instantly through contemporary

With the recent developments in machine intelligence and web technologies, new generative music systems are being explored for assisted composition using machine learning techniques on the web. Such systems are built for various tasks such as melodic, harmonic or rhythm generation, music interpolation, continuation and style imitation. In this paper, we introduce Apollo, an interactive music application for generating symbolic phrases of conventional western music using corpus-based style imitation techniques. In addition to enabling the construction and management of symbolic musical corpora, the system makes it possible for music artists and researchers to generate new musical phrases in the style of the proposed corpus. The system is available as a desktop application. The generated symbolic music materials, encoded in the MIDI format, can be exported or streamed for various purposes including using them as seed material for musical projects. We present the system design, implementation details, discuss and conclude with future work for the system.

Machine Unlearning (MU) aims to update Machine Learning (ML) models following requests to remove training samples and their influences on a trained model efficiently without retraining the original ML model from scratch. While MU itself has been employed to provide privacy protection and regulatory compliance, it can also increase the attack surface of the model. Existing privacy inference attacks towards MU that aim to infer properties of the unlearned set rely on the weaker threat model that assumes the attacker has access to both the unlearned model and the original model, limiting their feasibility toward real-life scenarios. We propose a novel privacy attack, A Posteriori Label-Only Membership Inference Attack towards MU, Apollo, that infers whether a data sample has been unlearned, following a strict threat model where an adversary has access to the label-output of the unlearned model only. We demonstrate that our proposed attack, while requiring less access to the target model compared to previous attacks, can achieve relatively high precision on the membership status of the unlearned samples.

Human exploration of the moon is expected to resume in the next decade, following the last such activities in the Apollo programme time. One of the major objectives of returning to the Moon is to continue retrieving geological samples, with a focus on collecting high-quality specimens to maximize scientific return. Tools that assist astronauts in making informed decisions about sample collection activities can maximize the scientific value of future lunar missions. A lunar rock classifier is a tool that can potentially provide the necessary information for astronauts to analyze lunar rock samples, allowing them to augment in-situ value identification of samples. Towards demonstrating the value of such a tool, in this paper, we introduce a framework for classifying rock types in thin sections of lunar rocks. We leverage the vast collection of petrographic thin-section images from the Apollo missions, captured under plane-polarized light (PPL), cross-polarised light (XPL), and reflected light at varying magnifications. Advanced machine learning methods, including contrastive learning, are applied to analyze these images and extract meaningful features. The contrastive learning approa

$\textit{Aims.}$ We study the possible dynamical background of three Apollo asteroids: 3200 Phaethon, 2005 UD, and 1999 YC. The source regions under consideration are the asteroid families (2) Pallas, in the outer belt, and two inner-belt families (329) Svea and (142) Polana. We also aim to explain some of the contradictions in the literature in regards to the origin of Phaethon. $\textit{Methods.}$ Our methodology relies on the precise dynamical mapping of several mean motion resonances (MMRs), which are considered the main transport channels. This approach allows the clear detection of chaotic structures in an MMR and efficient selection of test asteroids for diffusion. We tracked the orbital evolution of the selected particles over 5 million years and registered all their eventual entries into the orbital neighborhood of the asteroids 3200 Phaethon, 2005 UD and 1999 YC. We performed massive calculations for different orbital and integration parameters using Orbit9 and Rebound software packages. $\textit{Results.}$ We observed possible connections between three targeted Apollo asteroids and asteroid families we considered as their sources. The (2) Pallas family has the highest ch

Phishing is one of the most prolific cybercriminal activities, with attacks becoming increasingly sophisticated. It is, therefore, imperative to explore novel technologies to improve user protection across both technical and human dimensions. Large Language Models (LLMs) offer significant promise for text processing in various domains, but their use for defense against phishing attacks still remains scarcely explored. In this paper, we present APOLLO, a tool based on OpenAI's GPT-4o to detect phishing emails and generate explanation messages to users about why a specific email is dangerous, thus improving their decision-making capabilities. We have evaluated the performance of APOLLO in classifying phishing emails; the results show that the LLM models have exemplary capabilities in classifying phishing emails (97 percent accuracy in the case of GPT-4o) and that this performance can be further improved by integrating data from third-party services, resulting in a near-perfect classification rate (99 percent accuracy). To assess the perception of the explanations generated by this tool, we also conducted a study with 20 participants, comparing four different explanations presented as

We present data from the Apache Point Observatory Lunar Laser-ranging Operation (APOLLO) covering the 15-year span from April 2006 through the end of 2020. APOLLO measures the earth-moon separation by recording the round-trip travel time of photons from the Apache Point Observatory to five retro-reflector arrays on the moon. The APOLLO data set, combined with the 50-year archive of measurements from other lunar laser ranging (LLR) stations, can be used to probe fundamental physics such as gravity and Lorentz symmetry, as well as properties of the moon itself. We show that range measurements performed by APOLLO since 2006 have a median nightly accuracy of 1.7 mm, which is significantly better than other LLR stations.

The choice of input text prompt plays a critical role in the performance of Vision-Language Pretrained (VLP) models such as CLIP. We present APoLLo, a unified multi-modal approach that combines Adapter and Prompt learning for Vision-Language models. Our method is designed to substantially improve the generalization capabilities of VLP models when they are fine-tuned in a few-shot setting. We introduce trainable cross-attention-based adapter layers in conjunction with vision and language encoders to strengthen the alignment between the two modalities. We enforce consistency between the respective encoder branches (receiving augmented inputs) to prevent overfitting in downstream tasks. Our method is evaluated on three representative tasks: generalization to novel classes, cross-dataset evaluation, and unseen domain shifts. In practice, APoLLo achieves a relative gain up to 6.03% over MaPLe (SOTA) on novel classes for 10 diverse image recognition datasets.

Constraints on the interior of the Moon have been derived from its inductive response, principally as measured by the magnetic transfer function (TF) between the distantly orbiting Explorer 35 satellite and the Apollo 12 surface station. The most successful prior studies used a dataset spanning 0.01-1 mHz, so the lunar response could be modeled as a simple dipole. However, earlier efforts also produced transfer functions up to 40 mHz. The smaller electromagnetic skin depth at higher frequency would better resolve the uppermost mantle-where key information about primitive lunar evolution may still be preserved-but requires a multipole treatment. I compute new profiles of electrical conductivity vs depth using both low- and high-frequency ranges of published Apollo-Explorer TFs. Using the low-frequency data, I derive temperature profiles at depths >400 km (<1 mHz) consistent with conductive heat loss and expectations of the iron (and possibly water) content of the mantle. The near-constant iron fraction (Mg# 81 +/- 10) could imply efficient mixing due to now-defunct convection. Alternatively, incomplete overturn of gravitationally unstable magma-ocean cumulates could have left

Despite the rapid integration of video perception capabilities into Large Multimodal Models (LMMs), the underlying mechanisms driving their video understanding remain poorly understood. Consequently, many design decisions in this domain are made without proper justification or analysis. The high computational cost of training and evaluating such models, coupled with limited open research, hinders the development of video-LMMs. To address this, we present a comprehensive study that helps uncover what effectively drives video understanding in LMMs. We begin by critically examining the primary contributors to the high computational requirements associated with video-LMM research and discover Scaling Consistency, wherein design and training decisions made on smaller models and datasets (up to a critical size) effectively transfer to larger models. Leveraging these insights, we explored many video-specific aspects of video-LMMs, including video sampling, architectures, data composition, training schedules, and more. For example, we demonstrated that fps sampling during training is vastly preferable to uniform frame sampling and which vision encoders are the best for video representation