Semantic parsing, which converts natural language questions into logic forms, plays a crucial role in reasoning within structured environments.However, existing methods encounter two significant challenges: reliance on extensive manually annotated datasets and limited generalization capability to unseen examples.To tackle these issues, we propose Targeted Synthetic Data Generation (TARGA), a practical framework that dynamically generates high-relevance synthetic data without manual annotation.Starting from the pertinent entities and relations of a given question, we probe for the potential relevant queries through layer-wise expansion and cross-layer combination.Then we generate corresponding natural language questions for these constructed queries to jointly serve as the synthetic demonstrations for in-context learning.Experiments on multiple knowledge base question answering (KBQA) datasets demonstrate that TARGA, using only a 7B-parameter model, substantially outperforms existing non-finetuned methods that utilize close-sourced model, achieving notable improvements in F1 scores on GrailQA (+7.7) and KBQA-Agent (+12.2).Furthermore, TARGA also exhibits superior sample efficiency, robustness, and generalization capabilities under non-I.I.D. settings.

The rapid development of multimodal large language models (MLLMs) has brought significant breakthroughs to this field. However, current MLLMs typically rely on vision instruction tuning based on large language models (LLMs) to endow them with multimodal capabilities, which may lead to low video utilization and catastrophic forgetting due to the task-specific nature of vision instruction tuning. Take case of multiple-choice Video Question Answering (VideoQA) as an example, requiring only selecting correct answers makes it easier for LLMs to shortcut rather than fully comprehend video content. Moreover, the fixed task format of ’’predicting the correct option" risks catastrophic forgetting, which can cause LLMs to lose their origin cognitive abilities. To address this, we propose ViCo, a training framework that enables LLMs to perform a specific auxiliary tasks during vision instruction tuning, which helps the model leverage video information more thoroughly while mitigating catastrophic forgetting, thereby improving modality alignment and enhancing performance. We evaluate our method on several strong VideoQA benchmarks, where it outperforms all state-of-the-art methods, demonstrating its effectiveness and generality. Additionally, we also provide extensive analysis on the video information utilization and catastrophic forgetting resulting. The code will be made available at https://github.com/dunknsabsw/ViCo.

Xiang Huang, Sitao Cheng, Shanshan Huang, Jiayu Shen, Yong Xu, Chaoyun Zhang, Yuzhong Qu. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Abstract Near-field technology is increasingly recognized due to its transformative potential in communication systems, establishing it as a critical enabler for sixth-generation (6G) telecommunication development. This paper presents a comprehensive survey of recent advancements in near-field technology research. First, we explore the near-field propagation fundamentals by detailing definitions, transmission characteristics, and performance analysis. Next, we investigate various near-field channel models—deterministic, stochastic, and electromagnetic information theory based models, and review the latest progress in near-field channel testing, highlighting practical performance and limitations. With evolving channel models, traditional mechanisms such as channel estimation, beamtraining, and codebook design require redesign and optimization to align with near-field propagation characteristics. We then introduce innovative beam designs enabled by near-field technologies, focusing on non-diffractive beams (such as Bessel and Airy) and orbital angular momentum (OAM) beams, addressing both hardware architectures and signal processing frameworks, showcasing their revolutionary potential in near-field communication systems. Additionally, we highlight progress in both engineering and standardization, covering the primary 6G spectrum allocation, enabling technologies for near-field propagation, and network deployment strategies. Finally, we conclude by identifying promising future research directions for near-field technology development that could significantly impact system design. This comprehensive review provides a detailed understanding of the current state and potential of near-field technologies.

Quantum optimization, a key application of quantum computing, has traditionally been stymied by the linearly increasing complexity of gradient calculations with an increasing number of parameters. This work bridges the gap between Koopman operator theory, which has found utility in applications because it allows for a linear representation of nonlinear dynamical systems, and natural gradient methods in quantum optimization, leading to a significant acceleration of gradient-based quantum optimization. We present Quantum-circuit Alternating Controlled Koopman learning (QuACK), a novel framework that leverages an alternating algorithm for efficient prediction of gradient dynamics on quantum computers. We demonstrate QuACK's remarkable ability to accelerate gradient-based optimization across a range of applications in quantum optimization and machine learning. In fact, our empirical studies, spanning quantum chemistry, quantum condensed matter, quantum machine learning, and noisy environments, have shown accelerations of more than 200x speedup in the overparameterized regime, 10x speedup in the smooth regime, and 3x speedup in the non-smooth regime. With QuACK, we offer a robust advancement that harnesses the advantage of gradient-based quantum optimization for practical benefits.