arXiv subjects

Dong Zhang

Publications and source records attributed to Dong Zhang.

At least 127 records · Page 7Linked to original sources

arXiv2024

UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model

Significant advancements has recently been achieved in the field of multi-modal large language models (MLLMs), demonstrating their remarkable capabilities in understanding and reasoning across diverse tasks. However, these models are often trained for specific tasks and rely on task-specific input-output formats, limiting their applicability to a broader range of tasks. This raises a fundamental question: Can we develop a unified approach to represent and handle different multi-modal tasks to maximize the generalizability of MLLMs? In this paper, we propose UnifiedMLLM, a comprehensive model designed to represent various tasks using a unified representation. Our model exhibits strong capabilities in comprehending the implicit intent of user instructions and preforming reasoning. In addition to generating textual responses, our model also outputs task tokens and grounding tokens, serving as indicators of task types and task granularity. These outputs are subsequently routed through the task router and directed to specific expert models for task completion. To train our model, we construct a task-specific dataset and an 100k multi-task dataset encompassing complex scenarios. Employing a three-stage training strategy, we equip our model with robust reasoning and task processing capabilities while preserving its generalization capacity and knowledge reservoir. Extensive experiments showcase the impressive performance of our unified representation approach across various tasks, surpassing existing methodologies. Furthermore, our approach exhibits exceptional scalability and generality. Our code, model, and dataset will be available at \url{https://github.com/lzw-lzw/UnifiedMLLM}.

cs.CL↗

arXiv2024

Building a Hierarchical Architecture and Communication Model for the Quantum Internet

The research of architecture has tremendous significance in realizing quantum Internet. Although there is not yet a standard quantum Internet architecture, the distributed architecture is one of the possible solutions, which utilizes quantum repeaters or dedicated entanglement sources in a flat structure for entanglement preparation & distribution. In this paper, we analyze the distributed architecture in detail and demonstrate that it has three limitations: 1) possible high maintenance overhead, 2) possible low-performance entanglement distribution, and 3) unable to support optimal entanglement routing. We design a hierarchical quantum Internet architecture and a communication model to solve the problems above. We also present a W-state Based Centralized Entanglement Preparation & Distribution (W-state Based CEPD) scheme and a Centralized Entanglement Routing (CER) algorithm within our hierarchical architecture and perform an experimental comparison with other entanglement preparation & distribution schemes and entanglement routing algorithms within the distributed architecture. The evaluation results show that the entanglement distribution efficiency of hierarchical architecture is 11.5% higher than that of distributed architecture on average (minimum 3.3%, maximum 37.3%), and the entanglement routing performance of hierarchical architecture is much better than that of a distributed architecture according to the fidelity and throughput.

quant-ph↗

arXiv2024

Operationalizing AI in Future Networks: A Bird's Eye View from the System Perspective

Modern Artificial Intelligence (AI) technologies, led by Machine Learning (ML), have gained unprecedented momentum over the past decade. Following this wave of "AI summer", the network research community has also embraced AI/ML algorithms to address many problems related to network operations and management. However, compared to their counterparts in other domains, most ML-based solutions have yet to receive large-scale deployment due to insufficient maturity for production settings. This article concentrates on the practical issues of developing and operating ML-based solutions in real networks. Specifically, we enumerate the key factors hindering the integration of AI/ML in real networks and review existing solutions to uncover the missing considerations. Further, we highlight a promising direction, i.e., Machine Learning Operations (MLOps), that can close the gap. We believe this paper spotlights the system-related considerations on implementing \& maintaining ML-based solutions and invigorate their full adoption in future networks.

cs.NI↗

arXiv2024

Deep-MPC: A DAGGER-Driven Imitation Learning Strategy for Optimal Constrained Battery Charging

In the realm of battery charging, several complex aspects demand meticulous attention, including thermal management, capacity degradation, and the need for rapid charging while maintaining safety and battery lifespan. By employing the imitation learning paradigm, this manuscript introduces an innovative solution to confront the inherent challenges often associated with conventional predictive control strategies for constrained battery charging. A significant contribution of this study lies in the adaptation of the Dataset Aggregation (DAGGER) algorithm to address scenarios where battery parameters are uncertain, and internal states are unobservable. Results drawn from a practical battery simulator that incorporates an electrochemical model highlight substantial improvements in battery charging performance, particularly in meeting all safety constraints and outperforming traditional strategies in computational processing.

eess.SY↗

arXiv2024

Safety-Driven Battery Charging: A Fisher Information-guided Adaptive MPC with Real-time Parameter Identification

Lithium-ion (Li-ion) batteries are ubiquitous in modern energy storage systems, highlighting the critical need to comprehend and optimize their performance. Yet, battery models often exhibit poor parameter identifiability which hinders the development of effective battery management strategies and impacts their overall performance, longevity, and safety. This manuscript explores the integration of Fisher Information (FI) theory with Model Predictive Control (MPC) for battery charging. The study addresses the inherent hurdles in accurately estimating battery model parameters due to nonlinear dynamics and uncertainty. Our proposed method aims to ensure safe battery charging and enhance real-time parameter estimation capabilities by leveraging adaptive control strategies guided by FI metrics. Simulation results underscore the effectiveness of our approach in mitigating parameter identifiability issues, offering promising solutions for improving the control of batteries during safe charging process.

eess.SY↗

arXiv2024

A Recover-then-Discriminate Framework for Robust Anomaly Detection

Anomaly detection (AD) has been extensively studied and applied in a wide range of scenarios in the recent past. However, there are still gaps between achieved and desirable levels of recognition accuracy for making AD for practical applications. In this paper, we start from an insightful analysis of two types of fundamental yet representative failure cases in the baseline model, and reveal reasons that hinder current AD methods from achieving a higher recognition accuracy. Specifically, by Case-1, we found that the main reasons detrimental to current AD methods is that the inputs to the recovery model contain a large number of detailed features to be recovered, which leads to the normal/abnormal area has-not/has been recovered into its original state. By Case-2, we surprisingly found that the abnormal area that cannot be recognized in image-level representations can be easily recognized in the feature-level representation. Based on the above observations, we propose a novel Recover-then-Discriminate (ReDi) framework for AD. ReDi takes a self-generated feature map and a selected prompted image as explicit input information to solve problems in case-1. Concurrently, a feature-level discriminative network is proposed to enhance abnormal differences between the recovered representation and the input representation. Extensive experimental results on two popular yet challenging AD datasets validate that ReDi achieves the new state-of-the-art accuracy.

cs.CV↗

arXiv2024

GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators

Recent advances in large language models (LLMs) have stepped forward the development of multilingual speech and machine translation by its reduced representation errors and incorporated external knowledge. However, both translation tasks typically utilize beam search decoding and top-1 hypothesis selection for inference. These techniques struggle to fully exploit the rich information in the diverse N-best hypotheses, making them less optimal for translation tasks that require a single, high-quality output sequence. In this paper, we propose a new generative paradigm for translation tasks, namely "GenTranslate", which builds upon LLMs to generate better results from the diverse translation versions in N-best list. Leveraging the rich linguistic knowledge and strong reasoning abilities of LLMs, our new paradigm can integrate the rich information in N-best candidates to generate a higher-quality translation result. Furthermore, to support LLM finetuning, we build and release a HypoTranslate dataset that contains over 592K hypotheses-translation pairs in 11 languages. Experiments on various speech and machine translation benchmarks (e.g., FLEURS, CoVoST-2, WMT) demonstrate that our GenTranslate significantly outperforms the state-of-the-art model.

cs.CL↗

arXiv2024

On the Temperature of Machine Learning Systems

We develop a thermodynamic theory for machine learning (ML) systems. Similar to physical thermodynamic systems which are characterized by energy and entropy, ML systems possess these characteristics as well. This comparison inspire us to integrate the concept of temperature into ML systems grounded in the fundamental principles of thermodynamics, and establish a basic thermodynamic framework for machine learning systems with non-Boltzmann distributions. We introduce the concept of states within a ML system, identify two typical types of state, and interpret model training and refresh as a process of state phase transition. We consider that the initial potential energy of a ML system is described by the model's loss functions, and the energy adheres to the principle of minimum potential energy. For a variety of energy forms and parameter initialization methods, we derive the temperature of systems during the phase transition both analytically and asymptotically, highlighting temperature as a vital indicator of system data distribution and ML training complexity. Moreover, we perceive deep neural networks as complex heat engines with both global temperature and local temperatures in each layer. The concept of work efficiency is introduced within neural networks, which mainly depends on the neural activation functions. We then classify neural networks based on their work efficiency, and describe neural networks as two types of heat engines.

cs.LG↗

arXiv2024

Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection

The growing importance of multi-modal humor detection within affective computing correlates with the expanding influence of short-form video sharing on social media platforms. In this paper, we propose a novel two-branch hierarchical model for short-form video humor detection (SVHD), named Comment-aided Video-Language Alignment (CVLA) via data-augmented multi-modal contrastive pre-training. Notably, our CVLA not only operates on raw signals across various modal channels but also yields an appropriate multi-modal representation by aligning the video and language components within a consistent semantic space. The experimental results on two humor detection datasets, including DY11k and UR-FUNNY, demonstrate that CVLA dramatically outperforms state-of-the-art and several competitive baseline approaches. Our dataset, code and model release at https://github.com/yliu-cs/CVLA.

cs.CV↗

arXiv2024

Location-guided Head Pose Estimation for Fisheye Image

Camera with a fisheye or ultra-wide lens covers a wide field of view that cannot be modeled by the perspective projection. Serious fisheye lens distortion in the peripheral region of the image leads to degraded performance of the existing head pose estimation models trained on undistorted images. This paper presents a new approach for head pose estimation that uses the knowledge of head location in the image to reduce the negative effect of fisheye distortion. We develop an end-to-end convolutional neural network to estimate the head pose with the multi-task learning of head pose and head location. Our proposed network estimates the head pose directly from the fisheye image without the operation of rectification or calibration. We also created a fisheye-distorted version of the three popular head pose estimation datasets, BIWI, 300W-LP, and AFLW2000 for our experiments. Experiments results show that our network remarkably improves the accuracy of head pose estimation compared with other state-of-the-art one-stage and two-stage methods.

cs.CV↗

arXiv2024

SpeechAlign: Aligning Speech Generation to Human Preferences

Speech language models have significantly advanced in generating realistic speech, with neural codec language models standing out. However, the integration of human feedback to align speech outputs to human preferences is often neglected. This paper addresses this gap by first analyzing the distribution gap in codec language models, highlighting how it leads to discrepancies between the training and inference phases, which negatively affects performance. Then we explore leveraging learning from human feedback to bridge the distribution gap. We introduce SpeechAlign, an iterative self-improvement strategy that aligns speech language models to human preferences. SpeechAlign involves constructing a preference codec dataset contrasting golden codec tokens against synthetic tokens, followed by preference optimization to improve the codec language model. This cycle of improvement is carried out iteratively to steadily convert weak models to strong ones. Through both subjective and objective evaluations, we show that SpeechAlign can bridge the distribution gap and facilitating continuous self-improvement of the speech language model. Moreover, SpeechAlign exhibits robust generalization capabilities and works for smaller models. Code and models will be available at https://github.com/0nutation/SpeechGPT.

cs.CL↗

arXiv2024

Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers

Non-linear functions are prevalent in Transformers and their lightweight variants, incurring substantial and frequently underestimated hardware costs. Previous state-of-the-art works optimize these operations by piece-wise linear approximation and store the parameters in look-up tables (LUT), but most of them require unfriendly high-precision arithmetics such as FP/INT 32 and lack consideration of integer-only INT quantization. This paper proposed a genetic LUT-Approximation algorithm namely GQA-LUT that can automatically determine the parameters with quantization awareness. The results demonstrate that GQA-LUT achieves negligible degradation on the challenging semantic segmentation task for both vanilla and linear Transformer models. Besides, proposed GQA-LUT enables the employment of INT8-based LUT-Approximation that achieves an area savings of 81.3~81.7% and a power reduction of 79.3~80.2% compared to the high-precision FP/INT 32 alternatives. Code is available at https:// github.com/PingchengDong/GQA-LUT.

cs.LG↗

arXiv2024

Unleashing Network Potentials for Semantic Scene Completion

Semantic scene completion (SSC) aims to predict complete 3D voxel occupancy and semantics from a single-view RGB-D image, and recent SSC methods commonly adopt multi-modal inputs. However, our investigation reveals two limitations: ineffective feature learning from single modalities and overfitting to limited datasets. To address these issues, this paper proposes a novel SSC framework - Adversarial Modality Modulation Network (AMMNet) - with a fresh perspective of optimizing gradient updates. The proposed AMMNet introduces two core modules: a cross-modal modulation enabling the interdependence of gradient flows between modalities, and a customized adversarial training scheme leveraging dynamic gradient competition. Specifically, the cross-modal modulation adaptively re-calibrates the features to better excite representation potentials from each single modality. The adversarial training employs a minimax game of evolving gradients, with customized guidance to strengthen the generator's perception of visual fidelity from both geometric completeness and semantic correctness. Extensive experimental results demonstrate that AMMNet outperforms state-of-the-art SSC methods by a large margin, providing a promising direction for improving the effectiveness and generalization of SSC methods.

cs.CV↗

arXiv2024

GroundingGPT:Language Enhanced Multi-modal Grounding Model

Multi-modal large language models have demonstrated impressive performance across various tasks in different modalities. However, existing multi-modal models primarily emphasize capturing global information within each modality while neglecting the importance of perceiving local information across modalities. Consequently, these models lack the ability to effectively understand the fine-grained details of input data, limiting their performance in tasks that require a more nuanced understanding. To address this limitation, there is a compelling need to develop models that enable fine-grained understanding across multiple modalities, thereby enhancing their applicability to a wide range of tasks. In this paper, we propose GroundingGPT, a language enhanced multi-modal grounding model. Beyond capturing global information like other multi-modal models, our proposed model excels at tasks demanding a detailed understanding of local information within the input. It demonstrates precise identification and localization of specific regions in images or moments in videos. To achieve this objective, we design a diversified dataset construction pipeline, resulting in a multi-modal, multi-granularity dataset for model training. The code, dataset, and demo of our model can be found at https: //github.com/lzw-lzw/GroundingGPT.

cs.CV↗

arXiv2024

Sophia-in-Audition: Virtual Production with a Robot Performer

We present Sophia-in-Audition (SiA), a new frontier in virtual production, by employing the humanoid robot Sophia within an UltraStage environment composed of a controllable lighting dome coupled with multiple cameras. We demonstrate Sophia's capability to replicate iconic film segments, follow real performers, and perform a variety of motions and expressions, showcasing her versatility as a virtual actor. Key to this process is the integration of facial motion transfer algorithms and the UltraStage's controllable lighting and multi-camera setup, enabling dynamic performances that align with the director's vision. Our comprehensive user studies indicate positive audience reception towards Sophia's performances, highlighting her potential to reduce the uncanny valley effect in virtual acting. Additionally, the immersive lighting in dynamic clips was highly rated for its naturalness and its ability to mirror professional film standards. The paper presents a first-of-its-kind multi-view robot performance video dataset with dynamic lighting, offering valuable insights for future enhancements in humanoid robotic performers and virtual production techniques. This research contributes significantly to the field by presenting a unique virtual production setup, developing tools for sophisticated performance control, and providing a comprehensive dataset and user study analysis for diverse applications.

cs.GR↗

arXiv2024

SpeechGPT-Gen: Scaling Chain-of-Information Speech Generation

Benefiting from effective speech modeling, current Speech Large Language Models (SLLMs) have demonstrated exceptional capabilities in in-context speech generation and efficient generalization to unseen speakers. However, the prevailing information modeling process is encumbered by certain redundancies, leading to inefficiencies in speech generation. We propose Chain-of-Information Generation (CoIG), a method for decoupling semantic and perceptual information in large-scale speech generation. Building on this, we develop SpeechGPT-Gen, an 8-billion-parameter SLLM efficient in semantic and perceptual information modeling. It comprises an autoregressive model based on LLM for semantic information modeling and a non-autoregressive model employing flow matching for perceptual information modeling. Additionally, we introduce the novel approach of infusing semantic information into the prior distribution to enhance the efficiency of flow matching. Extensive experimental results demonstrate that SpeechGPT-Gen markedly excels in zero-shot text-to-speech, zero-shot voice conversion, and speech-to-speech dialogue, underscoring CoIG's remarkable proficiency in capturing and modeling speech's semantic and perceptual dimensions. Code and models are available at https://github.com/0nutation/SpeechGPT.

cs.CL↗

arXiv2024

SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models

Current speech large language models build upon discrete speech representations, which can be categorized into semantic tokens and acoustic tokens. However, existing speech tokens are not specifically designed for speech language modeling. To assess the suitability of speech tokens for building speech language models, we established the first benchmark, SLMTokBench. Our results indicate that neither semantic nor acoustic tokens are ideal for this purpose. Therefore, we propose SpeechTokenizer, a unified speech tokenizer for speech large language models. SpeechTokenizer adopts the Encoder-Decoder architecture with residual vector quantization (RVQ). Unifying semantic and acoustic tokens, SpeechTokenizer disentangles different aspects of speech information hierarchically across different RVQ layers. Furthermore, We construct a Unified Speech Language Model (USLM) leveraging SpeechTokenizer. Experiments show that SpeechTokenizer performs comparably to EnCodec in speech reconstruction and demonstrates strong performance on the SLMTokBench benchmark. Also, USLM outperforms VALL-E in zero-shot Text-to-Speech tasks. Code and models are available at https://github.com/ZhangXInFD/SpeechTokenizer/.

cs.CL↗

arXiv2024

InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in the success of current LLMs is the alignment process. Current alignment methods, such as supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF), focus on training-time alignment and are often complex and cumbersome to implement. Therefore, we develop \textbf{InferAligner}, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. InferAligner utilizes safety steering vectors extracted from safety-aligned model to modify the activations of the target model when responding to harmful inputs, thereby guiding the target model to provide harmless responses. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics, as well as to multimodal large language models (MLLMs) such as LLaVA. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.

cs.CL↗