Xiangzhong Luo

Zhenyu Cui, Xiangzhong Luo

Recent mechanistic studies suggest that large language models (LLMs) may utilize their depth inefficiently in standard single-turn tasks. Whether this still holds in autonomous agent settings, where models must perform multi-turn planning, tool use, and iterative state updates, remains unclear. We study this question through a systematic layer-wise analysis of complete user-agent trajectories spanning three domains: Deep Research, Code Generation, and Tabular Processing. Using residual stream probes, causal layer-skipping interventions, and effective-depth measurements, we show that agentic reasoning exhibits a distinct depth profile from static tasks. As trajectories unfold, models progressively recruit more and deeper layers, with stronger long-range inter-layer dependencies emerging in later turns. At the same time, residual updates become increasingly correction-dominant, indicating a shift from stable feature accumulation toward repeated recalibration. Effective-depth analysis further reveals a substantial construction-refinement gap: semantic direction often forms relatively early, while deep layers remain necessary for stabilizing final outputs. Across model families, this gap is pronounced in Qwen and Minimax, whereas GLM shows a more domain-dependent depth allocation pattern. These results provide mechanistic evidence that autonomous LLM agents allocate depth adaptively as reasoning complexity grows.

Yuchu Jiang, Yue Cai, Xiangzhong Luo et al.

Diffusion-based large language models (dLLMs), despite their promising performance, still suffer from inferior inference efficiency. This is because dLLMs rely on bidirectional attention and cannot directly benefit from the standard key-value (KV) cache as autoregressive models (ARMs) do. To tackle this issue, we introduce \textit{Dual aDaptive Cache} (d$^2$Cache), which is a training-free approximate KV cache framework for accelerating dLLM inference. d$^2$Cache features a two-stage fine-grained selection strategy to identify tokens and adaptively update their KV states at each decoding step, while caching the KV states of the remaining tokens for reuse. Furthermore, d$^2$Cache naturally offers a more reliable decoding alternative, which can enable quasi left-to-right generation and mitigate premature overconfidence in tokens at the end of the sequence. Extensive experimental results on two representative dLLMs (\ie, LLaDA and Dream) demonstrate that d$^2$Cache not only achieves substantial inference speedups, but also yields consistent improvements in generation quality. The code is available at https://github.com/Kamichanw/d2Cache.

Jiaming Fan, Daming Cao, Xiangzhong Luo et al.

Speculative Decoding (SD) is a key technique for accelerating Large Language Model (LLM) inference, but it typically requires training a draft model on a large dataset. We approach this problem from a data-centric perspective, finding that not all training samples contribute equally to the SD acceptance rate. Specifically, our theoretical analysis and empirical validation reveals that tokens inducing flatter predictive distributions from the target model are more valuable than those yielding sharply peaked distributions. Based on this insight, we propose flatness, a new metric to quantify this property, and develop the Sample-level-flatness-based Dataset Distillation (SFDD) approach, which filters the training data to retain only the most valuable samples. Experiments on the EAGLE framework demonstrate that SFDD can achieve over 2$\times$ training speedup using only 50% of the data, while keeping the final model's inference speedup within 4% of the full-dataset baseline. This work introduces an effective, data-centric approach that substantially improves the training efficiency for Speculative Decoding. Our code is available at https://anonymous.4open.science/r/Flatness.

Xiangzhong Luo, Di Liu, Hao Kong et al.

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.

Xiangzhong Luo, Yilin An, Zhicheng Yu et al.

Diffusion-based large language models (dLLMs) have shown promising performance across various reasoning tasks, establishing themselves as an alternative to autoregressive large language models (LLMs). Unlike autoregressive LLMs that generate one token per step based on all previous tokens, dLLMs theoretically enable parallel generation of multiple tokens at each decoding step. However, recent dLLMs still favor one-token-per-step generation in practice, as directly decoding multiple masked tokens often leads to degraded generation quality and stability. This reveals a substantial gap between the theoretical parallelism and practical performance of dLLMs. To bridge this gap, we introduce an adaptive parallel decoding approach, namely DiCo, which features a three-phase divide-and-conquer paradigm to unleash the inherent parallelism of dLLMs. During the Divide phase, DiCo first explores the input masked sequence and identifies masked tokens as seed tokens, which are then expanded to construct a set of local clusters. During the Conquer phase, DiCo performs parallel decoding across different local clusters constructed in the Divide phase. The divide-and-conquer process repeatedly alternates between the Divide and Conquer phases until convergence. During the Finalize phase, DiCo decodes the remaining few masked tokens using an effective fine-grained compound decoding scheme to finalize the generation. Extensive experiments demonstrate that DiCo can achieve significant inference speedups while maintaining competitive generation quality.

Xiangzhong Luo, Di Liu, Shuo Huai et al.

In this paper, we present a novel multi-objective hardware-aware neural architecture search (NAS) framework, namely HSCoNAS, to automate the design of deep neural networks (DNNs) with high accuracy but low latency upon target hardware. To accomplish this goal, we first propose an effective hardware performance modeling method to approximate the runtime latency of DNNs on target hardware, which will be integrated into HSCoNAS to avoid the tedious on-device measurements. Besides, we propose two novel techniques, i.e., dynamic channel scaling to maximize the accuracy under the specified latency and progressive space shrinking to refine the search space towards target hardware as well as alleviate the search overheads. These two techniques jointly work to allow HSCoNAS to perform fine-grained and efficient explorations. Finally, an evolutionary algorithm (EA) is incorporated to conduct the architecture search. Extensive experiments on ImageNet are conducted upon diverse target hardware, i.e., GPU, CPU, and edge device to demonstrate the superiority of HSCoNAS over recent state-of-the-art approaches.

Di Liu, Hao Kong, Xiangzhong Luo et al.

Edge computing and artificial intelligence (AI), especially deep learning for nowadays, are gradually intersecting to build a novel system, called edge intelligence. However, the development of edge intelligence systems encounters some challenges, and one of these challenges is the \textit{computational gap} between computation-intensive deep learning algorithms and less-capable edge systems. Due to the computational gap, many edge intelligence systems cannot meet the expected performance requirements. To bridge the gap, a plethora of deep learning techniques and optimization methods are proposed in the past years: light-weight deep learning models, network compression, and efficient neural architecture search. Although some reviews or surveys have partially covered this large body of literature, we lack a systematic and comprehensive review to discuss all aspects of these deep learning techniques which are critical for edge intelligence implementation. As various and diverse methods which are applicable to edge systems are proposed intensively, a holistic review would enable edge computing engineers and community to know the state-of-the-art deep learning techniques which are instrumental for edge intelligence and to facilitate the development of edge intelligence systems. This paper surveys the representative and latest deep learning techniques that are useful for edge intelligence systems, including hand-crafted models, model compression, hardware-aware neural architecture search and adaptive deep learning models. Finally, based on observations and simple experiments we conducted, we discuss some future directions.