Efficient Deep Learning Infrastructures for Embedded Computing Systems: A Comprehensive Survey and Future Envision

Deep neural networks (DNNs) have recently achieved impressive success across a wide range of real-world vision and language processing tasks, spanning from image classification to many other downstream vision tasks, such as object detection, tracking, and segmentation. However, previous well-established DNNs, despite being able to maintain superior accuracy, have also been evolving to be deeper and wider and thus inevitably necessitate prohibitive computational resources for both training and inference. This trend further enlarges the computational gap between computation-intensive DNNs and resource-constrained embedded computing systems, making it challenging to deploy powerful DNNs upon real-world embedded computing systems towards ubiquitous embedded intelligence. To alleviate the above computational gap and enable ubiquitous embedded intelligence, we, in this survey, focus on discussing recent efficient deep learning infrastructures for embedded computing systems, spanning from training to inference, from manual to automated, from convolutional neural networks to transformers, from transformers to vision transformers, from vision models to large language models, from software to hardware, and from algorithms to applications. Specifically, we discuss recent efficient deep learning infrastructures for embedded computing systems from the lens of (1) efficient manual network design for embedded computing systems, (2) efficient automated network design for embedded computing systems, (3) efficient network compression for embedded computing systems, (4) efficient on-device learning for embedded computing systems, (5) efficient large language models for embedded computing systems, (6) efficient deep learning software and hardware for embedded computing systems, and (7) efficient intelligent applications for embedded computing systems.

DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models

Discrete diffusion models have achieved success in tasks like image generation and masked language modeling but face limitations in controlled content editing. We introduce DICE (Discrete Inversion for Controllable Editing), the first approach to enable precise inversion for discrete diffusion models, including multinomial diffusion and masked generative models. By recording noise sequences and masking patterns during the reverse diffusion process, DICE enables accurate reconstruction and flexible editing of discrete data without the need for predefined masks or attention manipulation. We demonstrate the effectiveness of DICE across both image and text domains, evaluating it on models such as VQ-Diffusion, Paella, and RoBERTa. Our results show that DICE preserves high data fidelity while enhancing editing capabilities, offering new opportunities for fine-grained content manipulation in discrete spaces. For project webpage, see https://hexiaoxiao-cs.github.io/DICE/.

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Transformer-based large Language Models (LLMs) become increasingly important in various domains. However, the quadratic time complexity of attention operation poses a significant challenge for scaling to longer contexts due to the extremely high inference latency and GPU memory consumption for caching key-value (KV) vectors. This paper proposes RetrievalAttention, a training-free approach to accelerate attention computation. To leverage the dynamic sparse property of attention, RetrievalAttention builds approximate nearest neighbor search (ANNS) indexes upon KV vectors in CPU memory and retrieves the most relevant ones via vector search during generation. Due to the out-of-distribution (OOD) between query vectors and key vectors, off-the-shelf ANNS indexes still need to scan O(N) (usually 30% of all keys) data for accurate retrieval, which fails to exploit the high sparsity. RetrievalAttention first identifies the OOD challenge of ANNS-based attention, and addresses it via an attention-aware vector search algorithm that can adapt to queries and only access 1--3% of data, thus achieving a sub-linear time complexity. RetrievalAttention greatly reduces the inference cost of long-context LLM with much lower GPU memory requirements while maintaining the model accuracy. Especially, RetrievalAttention only needs 16GB GPU memory for serving 128K tokens in LLMs with 8B parameters, which is capable of generating one token in 0.188 seconds on a single NVIDIA RTX4090 (24GB).

Resolving Inconsistent Semantics in Multi-Dataset Image Segmentation

Leveraging multiple training datasets to scale up image segmentation models is beneficial for increasing robustness and semantic understanding. Individual datasets have well-defined ground truth with non-overlapping mask layouts and mutually exclusive semantics. However, merging them for multi-dataset training disrupts this harmony and leads to semantic inconsistencies; for example, the class "person" in one dataset and class "face" in another will require multilabel handling for certain pixels. Existing methods struggle with this setting, particularly when evaluated on label spaces mixed from the individual training sets. To overcome these issues, we introduce a simple yet effective multi-dataset training approach by integrating language-based embeddings of class names and label space-specific query embeddings. Our method maintains high performance regardless of the underlying inconsistencies between training datasets. Notably, on four benchmark datasets with label space inconsistencies during inference, we outperform previous methods by 1.6% mIoU for semantic segmentation, 9.1% PQ for panoptic segmentation, 12.1% AP for instance segmentation, and 3.0% in the newly proposed PIQ metric.

SceneTextGen: Layout-Agnostic Scene Text Image Synthesis with Diffusion Models

While diffusion models have significantly advanced the quality of image generation, their capability to accurately and coherently render text within these images remains a substantial challenge. Conventional diffusion-based methods for scene text generation are typically limited by their reliance on an intermediate layout output. This dependency often results in a constrained diversity of text styles and fonts, an inherent limitation stemming from the deterministic nature of the layout generation phase. To address these challenges, this paper introduces SceneTextGen, a novel diffusion-based model specifically designed to circumvent the need for a predefined layout stage. By doing so, SceneTextGen facilitates a more natural and varied representation of text. The novelty of SceneTextGen lies in its integration of three key components: a character-level encoder for capturing detailed typographic properties, coupled with a character-level instance segmentation model and a word-level spotting model to address the issues of unwanted text generation and minor character inaccuracies. We validate the performance of our method by demonstrating improved character recognition rates on generated images across different public visual text datasets in comparison to both standard diffusion based methods and text specific methods.

Implicit In-context Learning

In-context Learning (ICL) empowers large language models (LLMs) to adapt to unseen tasks during inference by prefixing a few demonstration examples prior to test queries. Despite its versatility, ICL incurs substantial computational and memory overheads compared to zero-shot learning and is susceptible to the selection and order of demonstration examples. In this work, we introduce Implicit In-context Learning (I2CL), an innovative paradigm that addresses the challenges associated with traditional ICL by absorbing demonstration examples within the activation space. I2CL first generates a condensed vector representation, namely a context vector, from the demonstration examples. It then integrates the context vector during inference by injecting a linear combination of the context vector and query activations into the model's residual streams. Empirical evaluation on nine real-world tasks across three model architectures demonstrates that I2CL achieves few-shot performance with zero-shot cost and exhibits robustness against the variation of demonstration examples. Furthermore, I2CL facilitates a novel representation of "task-ids", enhancing task similarity detection and enabling effective transfer learning. We provide a comprehensive analysis of I2CL, offering deeper insights into its mechanisms and broader implications for ICL. The source code is available at: https://github.com/LzVv123456/I2CL.

Instantaneous Perception of Moving Objects in 3D

The perception of 3D motion of surrounding traffic participants is crucial for driving safety. While existing works primarily focus on general large motions, we contend that the instantaneous detection and quantification of subtle motions is equally important as they indicate the nuances in driving behavior that may be safety critical, such as behaviors near a stop sign of parking positions. We delve into this under-explored task, examining its unique challenges and developing our solution, accompanied by a carefully designed benchmark. Specifically, due to the lack of correspondences between consecutive frames of sparse Lidar point clouds, static objects might appear to be moving - the so-called swimming effect. This intertwines with the true object motion, thereby posing ambiguity in accurate estimation, especially for subtle motions. To address this, we propose to leverage local occupancy completion of object point clouds to densify the shape cue, and mitigate the impact of swimming artifacts. The occupancy completion is learned in an end-to-end fashion together with the detection of moving objects and the estimation of their motion, instantaneously as soon as objects start to move. Extensive experiments demonstrate superior performance compared to standard 3D motion estimation approaches, particularly highlighting our method's specialized treatment of subtle motions.

Evaluating the Application of ChatGPT in Outpatient Triage Guidance: A Comparative Study

The integration of Artificial Intelligence (AI) in healthcare presents a transformative potential for enhancing operational efficiency and health outcomes. Large Language Models (LLMs), such as ChatGPT, have shown their capabilities in supporting medical decision-making. Embedding LLMs in medical systems is becoming a promising trend in healthcare development. The potential of ChatGPT to address the triage problem in emergency departments has been examined, while few studies have explored its application in outpatient departments. With a focus on streamlining workflows and enhancing efficiency for outpatient triage, this study specifically aims to evaluate the consistency of responses provided by ChatGPT in outpatient guidance, including both within-version response analysis and between-version comparisons. For within-version, the results indicate that the internal response consistency for ChatGPT-4.0 is significantly higher than ChatGPT-3.5 (p=0.03) and both have a moderate consistency (71.2% for 4.0 and 59.6% for 3.5) in their top recommendation. However, the between-version consistency is relatively low (mean consistency score=1.43/3, median=1), indicating few recommendations match between the two versions. Also, only 50% top recommendations match perfectly in the comparisons. Interestingly, ChatGPT-3.5 responses are more likely to be complete than those from ChatGPT-4.0 (p=0.02), suggesting possible differences in information processing and response generation between the two versions. The findings offer insights into AI-assisted outpatient operations, while also facilitating the exploration of potentials and limitations of LLMs in healthcare utilization. Future research may focus on carefully optimizing LLMs and AI integration in healthcare systems based on ergonomic and human factors principles, precisely aligning with the specific needs of effective outpatient triage.

AC-EVAL: Evaluating Ancient Chinese Language Understanding in Large Language Models

Given the importance of ancient Chinese in capturing the essence of rich historical and cultural heritage, the rapid advancements in Large Language Models (LLMs) necessitate benchmarks that can effectively evaluate their understanding of ancient contexts. To meet this need, we present AC-EVAL, an innovative benchmark designed to assess the advanced knowledge and reasoning capabilities of LLMs within the context of ancient Chinese. AC-EVAL is structured across three levels of difficulty reflecting different facets of language comprehension: general historical knowledge, short text understanding, and long text comprehension. The benchmark comprises 13 tasks, spanning historical facts, geography, social customs, art, philosophy, classical poetry and prose, providing a comprehensive assessment framework. Our extensive evaluation of top-performing LLMs, tailored for both English and Chinese, reveals a substantial potential for enhancing ancient text comprehension. By highlighting the strengths and weaknesses of LLMs, AC-EVAL aims to promote their development and application forward in the realms of ancient Chinese language education and scholarly research. The AC-EVAL data and evaluation code are available at https://github.com/yuting-wei/AC-EVAL.

"When He Feels Cold, He Goes to the Seahorse"-Blending Generative AI into Multimaterial Storymaking for Family Expressive Arts Therapy

Storymaking, as an integrative form of expressive arts therapy, is an effective means to foster family communication. Yet, the integration of generative AI as expressive materials in therapeutic storymaking remains underexplored. And there is a lack of HCI implications on how to support families and therapists in this context. Addressing this, our study involved five weeks of storymaking sessions with seven families guided by a professional therapist. In these sessions, the families used both traditional art-making materials and image-based generative AI to create and evolve their family stories. Via the rich empirical data and commentaries from four expert therapists, we contextualize how families creatively melded AI and traditional expressive materials to externalize their ideas and feelings. Through the lens of Expressive Therapies Continuum (ETC), we characterize the therapeutic implications of AI as expressive materials. Desirable interaction qualities to support children, parents, and therapists are distilled for future HCI research.