arXiv subjects

Mingxin Zhou

Publications and source records attributed to Mingxin Zhou.

9 recordsLinked to original sources

arXiv2026

iFLYTEK-Embodied-Omni Technical Report

General-purpose embodied agents must understand multimodal instructions, anticipate how their environment will evolve, and produce precise control actions over extended horizons. Existing approaches typically specialize in visual-language reasoning, video-based world modeling, or action generation, while cascaded pipelines that first synthesize future observations and then infer actions can introduce interface bottlenecks and compound prediction errors. We present iFLYTEK-Embodied-Omni, a unified multimodal foundation model that jointly models vision(videos and images), language, and action within a single Omni framework. Its modality-specific visual-language, video-generation, and action-generation components communicate through shared multimodal self-attention. This design establishes brain-cerebellum collaboration: the vision-language modeland video generation model form a high-level brain for instruction understanding, task planning, progress tracking, and future visual-state prediction, whereas the action generation modelserves as a low-level cerebellum that directly converts planned subgoals and shared multimodal context into executable action chunks. To develop these capabilities, we combine action-annotated and action-free embodied videos from human demonstrations and robot interactions with embodied reasoning, embodied perception, and general-purpose image-text data to construct a comprehensive dataset. We further adopt a four-stage strategy that progressively trains the VLM, VGM, and AGM before jointly fine-tuning the complete model.

cs.AI↗

arXiv2020

SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection

While the self-attention mechanism has been widely used in a wide variety of tasks, it has the unfortunate property of a quadratic cost with respect to the input length, which makes it difficult to deal with long inputs. In this paper, we present a method for accelerating and structuring self-attentions: Sparse Adaptive Connection (SAC). In SAC, we regard the input sequence as a graph and attention operations are performed between linked nodes. In contrast with previous self-attention models with pre-defined structures (edges), the model learns to construct attention edges to improve task-specific performances. In this way, the model is able to select the most salient nodes and reduce the quadratic complexity regardless of the sequence length. Based on SAC, we show that previous variants of self-attention models are its special cases. Through extensive experiments on neural machine translation, language modeling, graph representation learning and image classification, we demonstrate SAC is competitive with state-of-the-art models while significantly reducing memory cost.

cs.CL↗

arXiv2020

Analyzing COVID-19 on Online Social Media: Trends, Sentiments and Emotions

At the time of writing, the ongoing pandemic of coronavirus disease (COVID-19) has caused severe impacts on society, economy and people's daily lives. People constantly express their opinions on various aspects of the pandemic on social media, making user-generated content an important source for understanding public emotions and concerns. In this paper, we perform a comprehensive analysis on the affective trajectories of the American people and the Chinese people based on Twitter and Weibo posts between January 20th, 2020 and May 11th 2020. Specifically, by identifying people's sentiments, emotions (i.e., anger, disgust, fear, happiness, sadness, surprise) and the emotional triggers (e.g., what a user is angry/sad about) we are able to depict the dynamics of public affect in the time of COVID-19. By contrasting two very different countries, China and the Unites States, we reveal sharp differences in people's views on COVID-19 in different cultures. Our study provides a computational approach to unveiling public emotions and concerns on the pandemic in real-time, which would potentially help policy-makers better understand people's need and thus make optimal policy.

cs.SI↗

arXiv2019

Entity-Relation Extraction as Multi-Turn Question Answering

In this paper, we propose a new paradigm for the task of entity-relation extraction. We cast the task as a multi-turn question answering problem, i.e., the extraction of entities and relations is transformed to the task of identifying answer spans from the context. This multi-turn QA formalization comes with several key advantages: firstly, the question query encodes important information for the entity/relation class we want to identify; secondly, QA provides a natural way of jointly modeling entity and relation; and thirdly, it allows us to exploit the well developed machine reading comprehension (MRC) models. Experiments on the ACE and the CoNLL04 corpora demonstrate that the proposed paradigm significantly outperforms previous best models. We are able to obtain the state-of-the-art results on all of the ACE04, ACE05 and CoNLL04 datasets, increasing the SOTA results on the three datasets to 49.4 (+1.0), 60.2 (+0.6) and 68.9 (+2.1), respectively. Additionally, we construct a newly developed dataset RESUME in Chinese, which requires multi-step reasoning to construct entity dependencies, as opposed to the single-step dependency extraction in the triplet exaction in previous datasets. The proposed multi-turn QA model also achieves the best performance on the RESUME dataset.

cs.CL↗

arXiv2017

Full-duplex Amplify-and-Forward Relaying: Power and Location Optimization

In this paper, we consider a full-duplex (FD) amplify-and-forward (AF) relay system and optimize its power allocation and relay location to minimize the system symbol error rate (SER). We first derive the asymptotic expressions of the outage probability and SER performance by taking into account the residual self interference (RSI) in FD systems. We then formulate the optimization problem based on the minimal SER criterion. Analytical and numerical results show that optimized relay location and power allocation can greatly improve system SER performance, and the performance floor caused by the RSI can be significantly reduced via optimizing relay location or power allocation.

cs.IT↗

arXiv2017

X-duplex Relaying: Adaptive Antenna Configuration

In this letter, we propose a joint transmission mode and transmit/receive (Tx/Rx) antenna configuration scheme referred to as X-duplex in the relay network with one source, one amplify-and-forward (AF) relay and one destination. The relay is equipped with two antennas, each of which is capable of reception and transmission. In the proposed scheme, the relay adaptively selects its Tx and Rx antenna, operating in either full-duplex (FD) or half-duplex (HD) mode. The proposed scheme is based on minimizing the symbol error rate (SER) of the relay system. The asymptotic expressions of the cumulative distribution function (CDF) for the end-to-end signal to interference plus noise ratio (SINR), average SER and diversity order are derived and validated by simulations. Results show that the X-duplex scheme achieves additional spatial diversity, significantly reduces the performance floor at high SNR and improves the system performance.

cs.IT↗

arXiv2017

On the Performance of X-Duplex Relaying

In this paper, we study a X-duplex relay system with one source, one amplify-and-forward (AF) relay and one destination, where the relay is equipped with a shared antenna and two radio frequency (RF) chains used for transmission or reception. X-duplex relay can adaptively configure the connection between its RF chains and antenna to operate in either HD or FD mode, according to the instantaneous channel conditions. We first derive the distribution of the signal to interference plus noise ratio (SINR), based on which we then analyze the outage probability, average symbol error rate (SER), and average sum rate. We also investigate the X-duplex relay with power allocation and derive the lower bound and upper bound of the corresponding outage probability. Both analytical and simulated results show that the X-duplex relay achieves a better performance over pure FD and HD schemes in terms of SER, outage probability and average sum rate, and the performance floor caused by the residual self interference can be eliminated using flexible RF chain configurations.

cs.NI↗

arXiv2015

Simultaneous Bidirectional Link Selection in Full Duplex MIMO Systems

In this paper, we consider a point to point full duplex (FD) MIMO communication system. We assume that each node is equipped with an arbitrary number of antennas which can be used for transmission or reception. With FD radios, bidirectional information exchange between two nodes can be achieved at the same time. In this paper we design bidirectional link selection schemes by selecting a pair of transmit and receive antenna at both ends for communications in each direction to maximize the weighted sum rate or minimize the weighted sum symbol error rate (SER). The optimal selection schemes require exhaustive search, so they are highly complex. To tackle this problem, we propose a Serial-Max selection algorithm, which approaches the exhaustive search methods with much lower complexity. In the Serial-Max method, the antenna pairs with maximum "obtainable SINR" at both ends are selected in a two-step serial way. The performance of the proposed Serial-Max method is analyzed, and the closed-form expressions of the average weighted sum rate and the weighted sum SER are derived. The analysis is validated by simulations. Both analytical and simulation results show that as the number of antennas increases, the Serial-Max method approaches the performance of the exhaustive-search schemes in terms of sum rate and sum SER.

cs.IT↗

arXiv2013

A Differential Feedback Scheme Exploiting the Temporal and Spectral Correlation

Channel state information (CSI) provided by limited feedback channel can be utilized to increase the system throughput. However, in multiple input multiple output (MIMO) systems, the signaling overhead realizing this CSI feedback can be quite large, while the capacity of the uplink feedback channel is typically limited. Hence, it is crucial to reduce the amount of feedback bits. Prior work on limited feedback compression commonly adopted the block fading channel model where only temporal or spectral correlation in wireless channel is considered. In this paper, we propose a differential feedback scheme with full use of the temporal and spectral correlations to reduce the feedback load. Then, the minimal differential feedback rate over MIMO doubly selective fading channel is investigated. Finally, the analysis is verified by simulations.

cs.IT↗