A single-layer wideband differential filtering patch antenna for 5G IoT applications is proposed. The proposed antenna features a simple configuration, comprising a pair of T-shaped structures, shorted parasitic patches, and defected ground structures (DGS) etched into the metal ground plane. Two shorted parasitic patches are loaded to achieve λ/4 resonance, and a high-frequency radiation null is introduced. A pair of T-shaped structures, composed of meandered slots, is etched into the main radiating patch, which causes strong current disturbance and excites opposite current components around the slots, thereby introducing a low-frequency radiation null. Moreover, a pair of DGS is incorporated into the ground plane, exciting an additional resonance within the passband to broaden the impedance bandwidth effectively. Finally, a prototype of the proposed antenna is fabricated and measured. The measured results are consistent with the simulated values, demonstrating an impedance bandwidth of 16.8% centered at 4.75 GHz, a peak realized gain of 6.1 dBi, and two controllable radiation nulls near the band edges. The designed antenna achieves a broad bandwidth and filtering response, while maintaining a small electrical size of 0.2 λ20and a low profile of 0.025 λ0. These performance metrics make the proposed wideband differential filtering antenna a promising candidate for 5G IoT applications.

An effective surface plasmon polariton (ESPP) filtering waveguide-fed D-band antenna is proposed for 6G Internet of Things (IoT) applications. Aiming at cross-band interference and link stability in 6G IoT, the design integrates an ESPP filtering structure with a waveguide slot antenna, achieving high selectivity and deep out-of-band suppression while maintaining stable radiation performance. Through ESPP dispersion engineering, the passband (135.9–143.2 GHz) and out-of-band suppression can be independently tuned. Benefiting from ESPPs’ steep asymptotic dispersion and extended modal bandgap, deep out-of-band suppression (>55 dB) and a stable stopband (147–170 GHz) are realized. Notably, the ESPP-based waveguide ensures robust performance against fabrication errors, maintaining frequency consistency between the filtering and radiation responses. The proposed ESPP-based design provides a high-selectivity and fabrication-tolerant solution, effectively mitigating complex interference in ultra-high-speed 6G IoT links and ensuring reliable operation for heterogeneous devices, such as Vehicle-to-Everything (V2X) sensors and smart city terminals.

Confidential Compute Architecture (CCA) is the latest Trusted Execution Environment (TEE) system on Arm. It offers a VM-level execution environment designed to host applications that manage security-sensitive tasks and safeguard them from malicious system software. Although this VM-level design simplifies TEE adoption, it introduces a large attack surface. Attackers can break isolation by exploiting vulnerabilities in any component of the VM. In this paper, we present HiveTEE, a scalable intra-TEE isolation architecture that leverages Realm Management Extension (RME) and Memory Tagging Extension (MTE). HiveTEE allows developers to partition applications into multiple isolated domains (SDoms), preventing a compromise in one part of the application from propagating across the entire TEE. To evaluate the performance overhead introduced by HiveTEE, we apply it to three real-world applications: OpenSSL, SQLite, and Memcached. The evaluation results show that HiveTEE incurs a small performance overhead (<3%).

Synthesizing novel views from sparse input images is a significant and challenging problem in neural rendering. As an innovative 3D representation, 3D Gaussian Splatting (3DGS) has demonstrated exceptional performance and real-time rendering capabilities. However, rendering novel views from few-shot inputs in 3DGS remains a formidable problem. To address this challenge, we propose PGDGS, a highly efficient method that surpasses existing methods with minimal modifications to the original 3DGS framework. We conducted a detailed analysis of the challenges encountered by 3DGS in sparse settings and identified the crucial role played by the Gaussian densification strategy during the training process. Building upon this observation, we propose two strategies: the Progressive Gaussian Densification strategy that reconstructs Gaussians from coarse to fine, and the Dynamic Frequency Regularization strategy that enhances the details of the reconstruction. We demonstrate that original 3DGS can achieve performance comparable to existing methods with only a few lines of code change. Notably, our approach achieves a 120 times improvement in training speed and a 4000 times increase in inference speed compared to previous NeRF-based methods due to its simplicity and minimal impact on training overhead. PGDGS achieves state-of-the-art performance across diverse datasets, including LLFF and Mip-NeRF360.

Asynchronous circuits become an attractive alternative to synchronous circuits owing to their potential benefits such as low power consumption, and no clock distribution problems. However, handshake control and relative timing analysis make designing asynchronous circuits a complex and error-prone task. Moreover, traditional electronic design automation (EDA) tools are tailored specifically for synchronous circuits, resulting in significant manual effort when designing asynchronous circuits. To address these issues, this paper proposes a desynchronization method based on Chisel, which converts synchronous circuits into bundled-data asynchronous ones automatically. For demonstration, an open-source synchronous RISC-V processor is desynchronized to an asynchronous one, and both are implemented on Zynq7020 FPGA. The experimental results illustrate that the power consumption of Clicks for handshaking in the desynchronized processor is only 33.3% of that of the global clocks in the synchronous one. Besides, with Clicks the power consumption of memory access is reduced by 80%. Compared with previous synchronous and asynchronous RISC-V processors, the asynchronous RISC-V processor achieves up to 8.4x and 1.5x dynamic power reductions respectively.

In this work, we present GPDiT, a Generative Pre-trained Autoregressive Diffusion Transformer that unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis, within a continuous latent space. Instead of predicting discrete tokens, GPDiT autoregressively predicts future latent frames using a diffusion loss, enabling natural modeling of motion dynamics and semantic consistency across frames. This continuous autoregressive framework not only enhances generation quality but also endows the model with representation capabilities. Additionally, we introduce a lightweight causal attention variant and a parameter-free rotation-based time-conditioning mechanism, improving both the training and inference efficiency. Extensive experiments demonstrate that GPDiT achieves strong performance in video generation quality, video representation ability, and few-shot learning tasks, highlighting its potential as an effective framework for video modeling in continuous space.

Tianyi Tang, Wenyang Luo, Haoyang Huang, Dongdong Zhang, Xiaolei Wang, Xin Zhao, Furu Wei, Ji-Rong Wen. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Large Language Models (LLMs) show strong instruction understanding ability across multiple languages.However, they are easily biased towards English in instruction tuning, and generate English responses even given non-English instructions.In this paper, we investigate the language inconsistent generation problem in monolingual instruction tuning.We find that instruction tuning in English increases the models' preference for English responses.It attaches higher probabilities to English responses than to responses in the same language as the instruction.Based on the findings, we alleviate the language inconsistent generation problem by counteracting the model preference for English responses in both the training and inference stages.Specifically, we propose Pseudo-Inconsistent Penalization (PIP) which prevents the model from generating English responses when given non-English language prompts during training, and Prior Enhanced Decoding (PED) which improves the language-consistent prior by leveraging the untuned base language model.Experimental results show that our two methods significantly improve the language consistency of the model without requiring any multilingual data 1 .

Large language models (LLMs) have shown surprisingly good performance in multilingual neural machine translation (MNMT) even if not being trained explicitly for translation.Yet, they still struggle with translating low-resource languages.As supported by our experiments, a bilingual dictionary between the source and the target language could help.Motivated by the fact that multilingual training effectively improves cross-lingual performance, we show that a chained multilingual dictionary with words expressed in more languages can provide more information to better enhance the LLM translation.To this end, we present a novel framework, COD, Chain-of-Dictionary Prompting, which augments LLMs with prior knowledge with the chains of multilingual dictionaries for a subset of input words to elicit translation abilities for LLMs.Experiments indicate that ChatGPT and InstructGPT still have room for improvement in translating many language pairs.And COD elicits large gains by up to 13x chrF++ points for MNMT (3.08 to 42.63 for English to Serbian written in Cyrillic script) on FLORES-200 full devtest set.We demonstrate the importance of chaining the multilingual dictionaries, as well as the superiority of COD to few-shot in-context learning for low-resource languages.Using COD helps ChatGPT to obviously surpass the SOTA translator NLLB 3.3B.

Tianyi Tang, Hongyuan Lu, Yuchen Jiang, Haoyang Huang, Dongdong Zhang, Xin Zhao, Tom Kocmi, Furu Wei. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Jian Yang, Shuming Ma, Li Dong, Shaohan Huang, Haoyang Huang, Yuwei Yin, Dongdong Zhang, Liqun Yang, Furu Wei, Zhoujun Li. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Transformer structure, stacked by a sequence of encoder and decoder network layers, achieves significant development in neural machine translation. However, vanilla Transformer mainly exploits the top-layer representation, assuming the lower layers provide trivial or redundant information and thus ignoring the bottom-layer feature that is potentially valuable. In this work, we propose theGroup-Transformer model (GTrans) that flexibly divides multi-layer representations of both encoder and decoder into different groups and then fuses these group features to generate target words. To corroborate the effectiveness of the proposed method, extensive experiments and analytic experiments are conducted on three bilingual translation benchmarks and three multilingual translation tasks, including the IWLST-14, IWLST-17, LDC, WMT-14, WMT-21 and OPUS-100 benchmark. Experimental and analytical results demonstrate that our model outperforms its Transformer counterparts by a consistent gain. Furthermore, it can be successfully scaled up to 60 encoder layers and 36 decoder layers.

Multimodal Machine Translation (MMT) focuses on enhancing text-only translation with visual features, which has attracted considerable attention from both natural language processing and computer vision communities.Recent advances still struggle to train a separate model for each language pair, which is costly and unaffordable when the number of languages increases in the real world.In other words, the multilingual multimodal machine translation (Multilingual MMT) task has not been investigated, which aims to handle the aforementioned issues by providing a shared semantic space for multiple languages.Besides, the image modality has no language boundaries, which is superior to bridging the semantic gap between languages.To this end, we first propose the Multilingual MMT task by establishing two new Multilingual MMT benchmark datasets covering seven languages.Then, an effective baseline LVP-M 3 using visual prompts is proposed to support translations between different languages, which includes three stages (token encoding, language-aware visual prompt generation, and language translation).Extensive experimental results on our constructed benchmark datasets demonstrate the effectiveness of LVP-M 3 method for Multilingual MMT.* First two authors contributed equally.

Yuchen Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Jian Yang, Haoyang Huang, Rico Sennrich, Ryan Cotterell, Mrinmaya Sachan, Ming Zhou. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Lei Ji, Xianglin Guo, Haoyang Huang, Xilin Chen. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training into a unified framework via multitask pre-training. Our goal is to learn universal representations that can map objects occurred in different modalities or texts expressed in different languages into a common semantic space. In addition, to explicitly encourage fine-grained alignment between images and non-English languages, we also propose Multimodal Code-switched Training (MCT) to combine monolingual pre-training and multimodal pre-training via a code-switch strategy. Experiments are performed on the multilingual image retrieval task across two benchmark datasets, including MSCOCO and Multi30K. M3P can achieve comparable results for English and new state-of-the-art results for non-English languages.

Haoyang Huang, Yaobo Liang, Nan Duan, Ming Gong, Linjun Shou, Daxin Jiang, Ming Zhou. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.