arXiv subjects

Bowen Yang

Publications and source records attributed to Bowen Yang.

At least 91 records · Page 5Linked to original sources

arXiv2024

Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking

Learning generic skills for humanoid robots interacting with 3D scenes by mimicking human data is a key research challenge with significant implications for robotics and real-world applications. However, existing methodologies and benchmarks are constrained by the use of small-scale, manually collected demonstrations, lacking the general dataset and benchmark support necessary to explore scene geometry generalization effectively. To address this gap, we introduce Mimicking-Bench, the first comprehensive benchmark designed for generalizable humanoid-scene interaction learning through mimicking large-scale human animation references. Mimicking-Bench includes six household full-body humanoid-scene interaction tasks, covering 11K diverse object shapes, along with 20K synthetic and 3K real-world human interaction skill references. We construct a complete humanoid skill learning pipeline and benchmark approaches for motion retargeting, motion tracking, imitation learning, and their various combinations. Extensive experiments highlight the value of human mimicking for skill learning, revealing key challenges and research directions.

cs.RO↗

arXiv2024

Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier

We introduce the Aya Expanse model family, a new generation of 8B and 32B parameter multilingual language models, aiming to address the critical challenge of developing highly performant multilingual models that match or surpass the capabilities of monolingual models. By leveraging several years of research at Cohere For AI and Cohere, including advancements in data arbitrage, multilingual preference training, and model merging, Aya Expanse sets a new state-of-the-art in multilingual performance. Our evaluations on the Arena-Hard-Auto dataset, translated into 23 languages, demonstrate that Aya Expanse 8B and 32B outperform leading open-weight models in their respective parameter classes, including Gemma 2, Qwen 2.5, and Llama 3.1, achieving up to a 76.6% win-rate. Notably, Aya Expanse 32B outperforms Llama 3.1 70B, a model with twice as many parameters, achieving a 54.0% win-rate. In this short technical report, we present extended evaluation results for the Aya Expanse model family and release their open-weights, together with a new multilingual evaluation dataset m-ArenaHard.

cs.CL↗

arXiv2024

Real-Time Metric-Semantic Mapping for Autonomous Navigation in Outdoor Environments

The creation of a metric-semantic map, which encodes human-prior knowledge, represents a high-level abstraction of environments. However, constructing such a map poses challenges related to the fusion of multi-modal sensor data, the attainment of real-time mapping performance, and the preservation of structural and semantic information consistency. In this paper, we introduce an online metric-semantic mapping system that utilizes LiDAR-Visual-Inertial sensing to generate a global metric-semantic mesh map of large-scale outdoor environments. Leveraging GPU acceleration, our mapping process achieves exceptional speed, with frame processing taking less than 7ms, regardless of scenario scale. Furthermore, we seamlessly integrate the resultant map into a real-world navigation system, enabling metric-semantic-based terrain assessment and autonomous point-to-point navigation within a campus environment. Through extensive experiments conducted on both publicly available and self-collected datasets comprising 24 sequences, we demonstrate the effectiveness of our mapping and navigation methodologies. Code has been publicly released: https://github.com/gogojjh/cobra

cs.RO↗

arXiv2024

ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering

The context window of large language models (LLMs) has been extended significantly in recent years. However, while the context length that the LLM can process has grown, the capability of the model to accurately reason over that context degrades noticeably. This occurs because modern LLMs often become overwhelmed by the vast amount of information in the context; when answering questions, the model must identify and reason over relevant evidence sparsely distributed throughout the text. To alleviate the challenge of long-context reasoning, we develop a retrieve-then-reason framework, enabling LLMs to reason over relevant evidence collected during an intermediate retrieval step. We find that modern LLMs struggle to accurately retrieve relevant facts and instead, often hallucinate "retrieved facts", resulting in flawed reasoning and the production of incorrect answers. To address these issues, we introduce ALR$^2$, a method that augments the long-context reasoning capability of LLMs via an explicit two-stage procedure, i.e., aligning LLMs with the objectives of both retrieval and reasoning. We demonstrate the efficacy of ALR$^2$ for mitigating performance degradation in long-context reasoning tasks. Through extensive experiments on long-context QA benchmarks, we find our method to outperform competitive baselines by large margins, achieving at least 8.4 and 7.9 EM gains on the long-context versions of HotpotQA and SQuAD datasets, respectively.

cs.CL↗

arXiv2024

A spiral sampling method for calculating the complex orbital angular momentum spectrum

OAM spectrum reflects the OAM component included in measured light field which is crucial in OAM -based application. However, traditional definition-based OAM spectrum algorithm is extraordinary time-consuming and limited to prior knowledge severely. To overcome it, in this paper, we propose a novel method to calculate the complex spectrum. After spiral sampling and Fourier transform, one can retrieve the radial coefficient of arbitrary OAM component by proper filtering and inverse Fourier transform. The simulation results reveal that the Mean Absolute Error (MAE) between retrieved one and target could reach at 0.0221 and 0.0199 on average for amplitude and phase respectively after normalized. This method could provide a powerful tool for future OAM-based and application.

physics.optics↗

arXiv2024

SnapKV: LLM Knows What You are Looking for Before Generation

Large Language Models (LLMs) have made remarkable progress in processing extensive contexts, with the Key-Value (KV) cache playing a vital role in enhancing their performance. However, the growth of the KV cache in response to increasing input length poses challenges to memory and time efficiency. To address this problem, this paper introduces SnapKV, an innovative and fine-tuning-free approach that efficiently minimizes KV cache size while still delivering comparable performance in real-world applications. We discover that each attention head in the model consistently focuses on specific prompt attention features during generation. Meanwhile, this robust pattern can be obtained from an 'observation' window located at the end of the prompts. Drawing on this insight, SnapKV automatically compresses KV caches by selecting clustered important KV positions for each attention head. Our approach significantly reduces the growing computational overhead and memory footprint when processing long input sequences. Specifically, SnapKV achieves a consistent decoding speed with a 3.6x increase in generation speed and an 8.2x enhancement in memory efficiency compared to the baseline when processing inputs of 16K tokens. At the same time, it maintains comparable performance to the baseline models across 16 long sequence datasets. Moreover, SnapKV can process up to 380K context tokens on a single A100-80GB GPU using HuggingFace implementation with minor changes, exhibiting only a negligible accuracy drop in the Needle-in-a-Haystack test. Further comprehensive studies suggest SnapKV's potential for practical applications.

cs.CL↗

arXiv2024

Macroscopic Tunneling Probe of Moiré Spin Textures in Twisted CrI$_3$

Various noncollinear spin textures and magnetic phases have been predicted in twisted two-dimensional CrI$_3$ due to competing ferromagnetic (FM) and antiferromagnetic (AFM) interlayer exchange from moiré stacking - with potential spintronic applications even when the underlying material possesses a negligible Dzyaloshinskii-Moriya or dipole-dipole interaction. Recent measurements have shown evidence of coexisting FM and AFM layer order in small-twist-angle CrI$_3$ bilayers and double bilayers. Yet, the nature of the magnetic textures remains unresolved and possibilities for their manipulation and electrical readout are unexplored. Here, we use tunneling magnetoresistance to investigate the collective spin states of twisted double-bilayer CrI$_3$ under both out-of-plane and in-plane magnetic fields together with detailed micromagnetic simulations of domain dynamics based on magnetic circular dichroism. Our results capture hysteretic and anisotropic field evolutions of the magnetic states and we further uncover two distinct non-volatile spin textures (out-of-plane and in-plane domains) at $\approx$ 1° twist angle, with a different global tunneling resistance that can be switched by magnetic field.

cond-mat.mtrl-sci↗

arXiv2024

BeautyMap: Binary-Encoded Adaptable Ground Matrix for Dynamic Points Removal in Global Maps

Global point clouds that correctly represent the static environment features can facilitate accurate localization and robust path planning. However, dynamic objects introduce undesired ghost tracks that are mixed up with the static environment. Existing dynamic removal methods normally fail to balance the performance in computational efficiency and accuracy. In response, we present BeautyMap to efficiently remove the dynamic points while retaining static features for high-fidelity global maps. Our approach utilizes a binary-encoded matrix to efficiently extract the environment features. With a bit-wise comparison between matrices of each frame and the corresponding map region, we can extract potential dynamic regions. Then we use coarse to fine hierarchical segmentation of the $z$-axis to handle terrain variations. The final static restoration module accounts for the range-visibility of each single scan and protects static points out of sight. Comparative experiments underscore BeautyMap's superior performance in both accuracy and efficiency against other dynamic points removal methods. The code is open-sourced at https://github.com/MKJia/BeautyMap.

cs.RO↗

arXiv2024

Homological invariants of Pauli stabilizer codes

We study translationally invariant Pauli stabilizer codes with qudits of arbitrary, not necessarily uniform, dimensions. Using homological methods, we define a series of invariants called charge modules. We describe their properties and physical meaning. The most complete results are obtained for codes whose charge modules have Krull dimension zero. This condition is interpreted as mobility of excitations. We show that it is always satisfied for translation invariant 2D codes with unique ground state in infinite volume, which was previously known only in the case of uniform, prime qudit dimension. For codes all of whose excitations are mobile we construct a $p$-dimensional excitation and a $(D-p-1)$-form symmetry for every element of the $p$-th charge module. Moreover, we define a braiding pairing between charge modules in complementary degrees. We discuss examples which illustrate how charge modules and braiding can be computed in practice.

math-ph↗

arXiv2024

Efficient Global Navigational Planning in 3D Structures based on Point Cloud Tomography

Navigation in complex 3D scenarios requires appropriate environment representation for efficient scene understanding and trajectory generation. We propose a highly efficient and extensible global navigation framework based on a tomographic understanding of the environment to navigate ground robots in multi-layer structures. Our approach generates tomogram slices using the point cloud map to encode the geometric structure as ground and ceiling elevations. Then it evaluates the scene traversability considering the robot's motion capabilities. Both the tomogram construction and the scene evaluation are accelerated through parallel computation. Our approach further alleviates the trajectory generation complexity compared with planning in 3D spaces directly. It generates 3D trajectories by searching through multiple tomogram slices and separately adjusts the robot height to avoid overhangs. We evaluate our framework in various simulation scenarios and further test it in the real world on a quadrupedal robot. Our approach reduces the scene evaluation time by 3 orders of magnitude and improves the path planning speed by 3 times compared with existing approaches, demonstrating highly efficient global navigation in various complex 3D environments. The code is available at: https://github.com/byangw/PCT_planner.

cs.RO↗

arXiv2024

Real-time Neural Dense Elevation Mapping for Urban Terrain with Uncertainty Estimations

Having good knowledge of terrain information is essential for improving the performance of various downstream tasks on complex terrains, especially for the locomotion and navigation of legged robots. We present a novel framework for neural urban terrain reconstruction with uncertainty estimations. It generates dense robot-centric elevation maps online from sparse LiDAR observations. We design a novel pre-processing and point features representation approach that ensures high robustness and computational efficiency when integrating multiple point cloud frames. A Bayesian-GAN model then recovers the detailed terrain structures while simultaneously providing the pixel-wise reconstruction uncertainty. We evaluate the proposed pipeline through extensive simulation and real-world experiments. It demonstrates efficient terrain reconstruction with high quality and real-time performance on a mobile platform, which further benefits the downstream tasks of legged robots. (See https://kin-zhang.github.io/ndem/ for more details.)

cs.RO↗

arXiv2023

High-Sensitive Microwave Electrometry with Enhanced Instantaneous Bandwidth

Rydberg microwave (MW) sensors are superior to conventional antenna-based techniques because of their wide operating frequency range and outstanding potential sensitivity. Here, we demonstrate a Rydberg microwave receiver with a high sensitivity of $62\,\mathrm{nV} \mathrm{cm}^{-1} \mathrm{Hz}^{-1/2}$ and broad instantaneous bandwidth of up to $10.2\,\mathrm{MHz}$. Such excellent performance was achieved by the amplification of one generated sideband wave induced by the strong coupling field in the six-wave mixing process of the Rydberg superheterodyne receiver, which was well predicted by our theory. Our system, which possesses a uniquely enhanced instantaneous bandwidth and high-sensitivity features that can be improved further, will promote the application of Rydberg microwave electrometry in radar and communication.

quant-ph↗

arXiv2023

BTLM-3B-8K: 7B Parameter Performance in a 3B Parameter Model

We introduce the Bittensor Language Model, called "BTLM-3B-8K", a new state-of-the-art 3 billion parameter open-source language model. BTLM-3B-8K was trained on 627B tokens from the SlimPajama dataset with a mixture of 2,048 and 8,192 context lengths. BTLM-3B-8K outperforms all existing 3B parameter models by 2-5.5% across downstream tasks. BTLM-3B-8K is even competitive with some 7B parameter models. Additionally, BTLM-3B-8K provides excellent long context performance, outperforming MPT-7B-8K and XGen-7B-8K on tasks up to 8,192 context length. We trained the model on a cleaned and deduplicated SlimPajama dataset; aggressively tuned the \textmu P hyperparameters and schedule; used ALiBi position embeddings; and adopted the SwiGLU nonlinearity. On Hugging Face, the most popular models have 7B parameters, indicating that users prefer the quality-size ratio of 7B models. Compacting the 7B parameter model to one with 3B parameters, with little performance impact, is an important milestone. BTLM-3B-8K needs only 3GB of memory with 4-bit precision and takes 2.5x less inference compute than 7B models, helping to open up access to a powerful language model on mobile and edge devices. BTLM-3B-8K is available under an Apache 2.0 license on Hugging Face: https://huggingface.co/cerebras/btlm-3b-8k-base.

cs.AI↗

arXiv2023

Rethinking Imitation-based Planner for Autonomous Driving

In recent years, imitation-based driving planners have reported considerable success. However, due to the absence of a standardized benchmark, the effectiveness of various designs remains unclear. The newly released nuPlan addresses this issue by offering a large-scale real-world dataset and a standardized closed-loop benchmark for equitable comparisons. Utilizing this platform, we conduct a comprehensive study on two fundamental yet underexplored aspects of imitation-based planners: the essential features for ego planning and the effective data augmentation techniques to reduce compounding errors. Furthermore, we highlight an imitation gap that has been overlooked by current learning systems. Finally, integrating our findings, we propose a strong baseline model-PlanTF. Our results demonstrate that a well-designed, purely imitation-based planner can achieve highly competitive performance compared to state-of-the-art methods involving hand-crafted rules and exhibit superior generalization capabilities in long-tail cases. Our models and benchmarks are publicly available. Project website https://jchengai.github.io/planTF.

cs.RO↗

arXiv2023

ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles

Automatically generating textual content with desired attributes is an ambitious task that people have pursued long. Existing works have made a series of progress in incorporating unimodal controls into language models (LMs), whereas how to generate controllable sentences with multimodal signals and high efficiency remains an open question. To tackle the puzzle, we propose a new paradigm of zero-shot controllable text generation with multimodal signals (\textsc{ZeroGen}). Specifically, \textsc{ZeroGen} leverages controls of text and image successively from token-level to sentence-level and maps them into a unified probability space at decoding, which customizes the LM outputs by weighted addition without extra training. To achieve better inter-modal trade-offs, we further introduce an effective dynamic weighting mechanism to regulate all control weights. Moreover, we conduct substantial experiments to probe the relationship of being in-depth or in-width between signals from distinct modalities. Encouraging empirical results on three downstream tasks show that \textsc{ZeroGen} not only outperforms its counterparts on captioning tasks by a large margin but also shows great potential in multimodal news generation with a higher degree of control. Our code will be released at https://github.com/ImKeTT/ZeroGen.

cs.CL↗

arXiv2023

The Resource Demand of Terawatt-Scale Perovskite Tandem Photovoltaics

Photovoltaics (PV) is the most important energy conversion technology for cost-efficient climate change mitigation. To reach the international climate goals, the annual PV module production capacity must be expanded to multi-terawatt scale. Economic and resource constraints demand the implementation cost-efficient multi-junction technologies, for which perovskite-based tandem technologies are highly promising. In this work, the resource demand of the emerging perovskite PV technology is investigated, considering two factors of supply criticality, namely mining capacity for minerals, as well as production capacity for synthetic materials. Overall, the expansion of perovskite PV to a multi-terawatt scale may not be limited by material supply if certain materials, especially cesium and indium, can be replaced. Moreover, organic charge transport materials face unresolved scalability challenges. This study demonstrates that, besides the improvement of efficiency and stability, perovskite PV research needs also to be guided by sustainable materials choices and design-for-recycling considerations.

physics.app-ph↗

arXiv2022

Development of a Self-Calibrated Motion Capture System by Nonlinear Trilateration of Multiple Kinects v2

In this paper, a Kinect-based distributed and real-time motion capture system is developed. A trigonometric method is applied to calculate the relative position of Kinect v2 sensors with a calibration wand and register the sensors' positions automatically. By combining results from multiple sensors with a nonlinear least square method, the accuracy of the motion capture is optimized. Moreover, to exclude inaccurate results from sensors, a computational geometry is applied in the occlusion approach, which discovers occluded joint data. The synchronization approach is based on an NTP protocol that synchronizes the time between the clocks of a server and clients dynamically, ensuring that the proposed system is a real-time system. Experiments for validating the proposed system are conducted from the perspective of calibration, occlusion, accuracy, and efficiency. Furthermore, to demonstrate the practical performance of our system, a comparison of previously developed motion capture systems (the linear trilateration approach and the geometric trilateration approach) with the benchmark OptiTrack system is conducted, therein showing that the accuracy of our proposed system is $38.3\%$ and 24.1% better than the two aforementioned trilateration systems, respectively.

cs.RO↗

arXiv2022

3-D Markerless Tracking of Human Gait by Geometric Trilateration of Multiple Kinects

In this paper, we develop an integrated markerless gait tracking system with three Kinect v2 sensors. A geometric principle-based trilateration method is proposed for optimizing the accuracy of the measured gait data. To tackle the data synchronization problem among the Kinect clients and the server, a synchronization mechanism based on NTP (Network Time Protocol) is designed for synchronizing the server and Kinect clients' clocks. Furthermore, a time schedule is designed for timing each Kinect client's data transmission. In the experiment, participants are asked to perform a 60 s walk while the proposed tracking system obtains the participant's gait data. Six joints (including left hip, right hip, left knee, right knee, left ankle and right ankle) of the participants are tracked where the obtained gait data are described as 6000 {movements} of joint positions (1000 {movements} for each joint). The results show that the trilateration tracking result by the three Kinect sensors has a much higher accuracy compared with the accuracy measured by a single Kinect sensor. Within a randomly sampled time period (67.726 s in the experiment), 98.37% of the frames generated by the gait tracking system have timing errors less than 1 ms, which is much better than the default NTP service embedded in the Windows 8.1 operating system. The accuracy of the proposed system is quantitatively evaluated and verified by a comparison with a commercial medical system (Delsys Trigno Smart Sensor System).

cs.MM↗