Chun Jason Xue

Shangyu Wu, Yufei Cui, Jinghuan Yu et al.

Recent works on learned index open a new direction for the indexing field. The key insight of the learned index is to approximate the mapping between keys and positions with piece-wise linear functions. Such methods require partitioning key space for a better approximation. Although lots of heuristics are proposed to improve the approximation quality, the bottleneck is that the segmentation overheads could hinder the overall performance. This paper tackles the approximation problem by applying a \textit{distribution transformation} to the keys before constructing the learned index. A two-stage Normalizing-Flow-based Learned index framework (NFL) is proposed, which first transforms the original complex key distribution into a near-uniform distribution, then builds a learned index leveraging the transformed keys. For effective distribution transformation, we propose a Numerical Normalizing Flow (Numerical NF). Based on the characteristics of the transformed keys, we propose a robust After-Flow Learned Index (AFLI). To validate the performance, comprehensive evaluations are conducted on both synthetic and real-world workloads, which shows that the proposed NFL produces the highest throughput and the lowest tail latency compared to the state-of-the-art learned indexes.

Hongchao Du, Shangyu Wu, Qiao Li et al.

Smartphones represent a uniquely challenging environment for agentic systems. Unlike cloud or desktop settings, mobile devices combine constrained execution contexts, fragmented control interfaces, and rapidly changing application states. As large language models (LLMs) evolve from conversational assistants to action-oriented agents, achieving reliable smartphone-native autonomy requires rethinking how reasoning and control are composed. We introduce ClawMobile as a concrete exploration of this design space. ClawMobile adopts a hierarchical architecture that separates high-level language reasoning from structured, deterministic control pathways, improving execution stability and reproducibility on real devices. Using ClawMobile as a case study, we distill the design principles for mobile LLM runtimes and identify key challenges in efficiency, adaptability, and stability. We argue that building robust smartphone-native agentic systems demands principled coordination between probabilistic planning and deterministic system interfaces. The implementation is open-sourced~\footnote{https://github.com/ClawMobile/ClawMobile} to facilitate future exploration.

Shangyu Wu, Ying Xiong, Yufei Cui et al.

Large language models (LLMs) have demonstrated great success in various fields, benefiting from their huge amount of parameters that store knowledge. However, LLMs still suffer from several key issues, such as hallucination problems, knowledge update issues, and lacking domain-specific expertise. The appearance of retrieval-augmented generation (RAG), which leverages an external knowledge database to augment LLMs, makes up those drawbacks of LLMs. This paper reviews all significant techniques of RAG, especially in the retriever and the retrieval fusions. Besides, tutorial codes are provided for implementing the representative techniques in RAG. This paper further discusses the RAG update, including RAG with/without knowledge update. Then, we introduce RAG evaluation and benchmarking, as well as the application of RAG in representative NLP tasks and industrial scenarios. Finally, this paper discusses RAG's future directions and challenges for promoting this field's development.

Zikang Zhou, Haibo Hu, Xinhong Chen et al.

Multimodal motion forecasting is inherently under-supervised: each training scene provides only one realized future, yet multiple plausible futures exist. This sparse supervision often leads to mode collapse (redundant hypotheses and insufficient mode coverage) and unreliable confidence ranking when predicting a small set of trajectories. We propose Mode-as-Sequence, a unified decoding framework that translates an unordered mode set into an ordered mode sequence and explicitly models mode-to-mode dependency. Under this framework, we develop two complementary instantiations. ModeSeq performs recurrent mode decoding, where each mode is generated conditioned on the previously generated modes, encouraging diverse, non-redundant hypotheses with calibrated confidence ordering. To remove the mode-by-mode autoregressive bottleneck, we further propose Parallel ModeSeq, which preserves the same causal dependency using masked mode-to-mode self-attention while decoding all modes in a single forward pass, enabling efficient large-$K$ inference and scalable joint-scene prediction. To learn representative modes and calibrated confidence under sparse labels, we introduce Early-Match-Take-All (EMTA) and its joint-scene extension MA-EMTA, together with a lightweight ranking regularizer that reduces confidence inversions. Extensive experiments on large-scale benchmarks demonstrate consistent improvements in both ranking-oriented metrics and best-of-K accuracy across datasets, horizons, and object types. In the Waymo Open Dataset challenges, ModeSeq achieves 1st place in the 2024 LiDAR-free motion prediction track, and Parallel ModeSeq achieves 1st place in the 2025 Interaction Prediction Challenge, validating the effectiveness of Mode-as-Sequence for both accuracy and efficiency.

Jingzong Li, Yik Hong Cai, Libin Liu et al.

3D object detection plays a pivotal role in many applications, most notably autonomous driving and robotics. These applications are commonly deployed on edge devices to promptly interact with the environment, and often require near real-time response. With limited computation power, it is challenging to execute 3D detection on the edge using highly complex neural networks. Common approaches such as offloading to the cloud induce significant latency overheads due to the large amount of point cloud data during transmission. To resolve the tension between wimpy edge devices and compute-intensive inference workloads, we explore the possibility of empowering fast 2D detection to extrapolate 3D bounding boxes. To this end, we present Moby, a novel system that demonstrates the feasibility and potential of our approach. We design a transformation pipeline for Moby that generates 3D bounding boxes efficiently and accurately based on 2D detection results without running 3D detectors. Further, we devise a frame offloading scheduler that decides when to launch the 3D detector judiciously in the cloud to avoid the errors from accumulating. Extensive evaluations on NVIDIA Jetson TX2 with real-world autonomous driving datasets demonstrate that Moby offers up to 91.9% latency improvement with modest accuracy loss over state of the art.

Jun Wang, Yu Mao, Nan Guan et al.

Whole slide images (WSIs) are gigapixel-scale digital images of H\&E-stained tissue samples widely used in pathology. The substantial size and complexity of WSIs pose unique analytical challenges. Multiple Instance Learning (MIL) has emerged as a powerful approach for addressing these challenges, particularly in cancer classification and detection. This survey provides a comprehensive overview of the challenges and methodologies associated with applying MIL to WSI analysis, including attention mechanisms, pseudo-labeling, transformers, pooling functions, and graph neural networks. Additionally, it explores the potential of MIL in discovering cancer cell morphology, constructing interpretable machine learning models, and quantifying cancer grading. By summarizing the current challenges, methodologies, and potential applications of MIL in WSI analysis, this survey aims to inform researchers about the state of the field and inspire future research directions.

Wenjing Xie, Tao Hu, Neiwen Ling et al.

Fusing Radar and Lidar sensor data can fully utilize their complementary advantages and provide more accurate reconstruction of the surrounding for autonomous driving systems. Surround Radar/Lidar can provide 360-degree view sampling with the minimal cost, which are promising sensing hardware solutions for autonomous driving systems. However, due to the intrinsic physical constraints, the rotating speed of surround Radar, and thus the frequency to generate Radar data frames, is much lower than surround Lidar. Existing Radar/Lidar fusion methods have to work at the low frequency of surround Radar, which cannot meet the high responsiveness requirement of autonomous driving systems.This paper develops techniques to fuse surround Radar/Lidar with working frequency only limited by the faster surround Lidar instead of the slower surround Radar, based on the state-of-the-art object detection model MVDNet. The basic idea of our approach is simple: we let MVDNet work with temporally unaligned data from Radar/Lidar, so that fusion can take place at any time when a new Lidar data frame arrives, instead of waiting for the slow Radar data frame. However, directly applying MVDNet to temporally unaligned Radar/Lidar data greatly degrades its object detection accuracy. The key information revealed in this paper is that we can achieve high output frequency with little accuracy loss by enhancing the training procedure to explore the temporal redundancy in MVDNet so that it can tolerate the temporal unalignment of input data. We explore several different ways of training enhancement and compare them quantitatively with experiments.

Junhui He, Shangyu Wu, Weidong Wen et al.

Deploying large language models (LLMs) on edge devices presents significant challenges due to the substantial computational overhead and memory requirements. Activation sparsification can mitigate these resource challenges by reducing the number of activated neurons during inference. Existing methods typically employ thresholding-based sparsification based on the statistics of activation tensors. However, they do not model the impact of activation sparsification on performance, resulting in suboptimal performance degradation. To address the limitations, this paper reformulates the activation sparsification problem to explicitly capture the relationship between activation sparsity and model performance. Then, this paper proposes CHESS, a general activation sparsification approach via CHannel-wise thrEsholding and Selective Sparsification. First, channel-wise thresholding assigns a unique threshold to each activation channel in the feed-forward network (FFN) layers. Then, selective sparsification involves applying thresholding-based activation sparsification to specific layers within the attention modules. Finally, we detail the implementation of sparse kernels to accelerate LLM inference. Experimental results demonstrate that the proposed CHESS achieves lower performance degradation over eight downstream tasks while activating fewer parameters than existing methods, thus speeding up the LLM inference by up to 1.27x.

Jiacheng Zuo, Haibo Hu, Zikang Zhou et al.

In the pursuit of robust autonomous driving systems, models trained on real-world datasets often struggle to adapt to new environments, particularly when confronted with corner cases such as extreme weather conditions. Collecting these corner cases in the real world is non-trivial, which necessitates the use of simulators for validation. However,the high computational cost and the domain gap in data distribution have hindered the seamless transition between real and simulated driving scenarios. To tackle this challenge, we propose Retrieval-Augmented Learning for Autonomous Driving (RALAD), a novel framework designed to bridge the real-to-sim gap at a low cost. RALAD features three primary designs, including (1) domain adaptation via an enhanced Optimal Transport (OT) method that accounts for both individual and grouped image distances, (2) a simple and unified framework that can be applied to various models, and (3) efficient fine-tuning techniques that freeze the computationally expensive layers while maintaining robustness. Experimental results demonstrate that RALAD compensates for the performance degradation in simulated environments while maintaining accuracy in real-world scenarios across three different models. Taking Cross View as an example, the mIOU and mAP metrics in real-world scenarios remain stable before and after RALAD fine-tuning, while in simulated environments,the mIOU and mAP metrics are improved by 10.30% and 12.29%, respectively. Moreover, the re-training cost of our approach is reduced by approximately 88.1%. Our code is available at https://github.com/JiachengZuo/RALAD.git.

Yixin Chen, Ying Xiong, Shangyu Wu et al.

Retrieval-augmented generation (RAG) has become a dominant paradigm for grounding large language models (LLMs) with external evidence in knowledge-intensive question answering. A core design choice is how to fuse retrieved samples into the LLMs, where existing internal fusion approaches broadly fall into query-based fusion, parametric fusion, and latent-based fusion. Despite their effectiveness at modest retrieval scales, these methods often fail to scale gracefully as the number of retrieved candidates k increases: Larger k improves evidence coverage, yet realistic top-k retrieval inevitably contains irrelevant or redundant content and increases the inference cost. To address these limitations, we propose ReFilter, a novel latent-based fusion framework that performs token-level filtering and fusion. ReFilter consists of three key components: a context encoder for encoding context features, a gated filter for weighting each token, and a token fusion module for integrating the weighted token feature into the LLM's hidden states. Our experiments across four general-domain QA benchmarks show that ReFilter consistently achieves the best average performance under both in-domain adaptation and out-of-domain transfer. ReFilter further generalizes to five biomedical QA benchmarks in zero-shot transfer without domain fine-tuning, reaching 70.01% average accuracy with Qwen2.5-14B-Instruct.

Yu Mao, Yufei Cui, Tei-Wei Kuo et al.

Deep-learning-based compressor has received interests recently due to much improved compression ratio. However, modern approaches suffer from long execution time. To ease this problem, this paper targets on cutting down the execution time of deep-learning-based compressors. Building history-dependencies sequentially (e.g., recurrent neural networks) is responsible for long inference latency. Instead, we introduce transformer into deep learning compressors to build history-dependencies in parallel. However, existing transformer is too heavy in computation and incompatible to compression tasks. This paper proposes a fast general-purpose lossless compressor, TRACE, by designing a compression-friendly structure based on a single-layer transformer. We first design a new metric to advise the selection part of compression model structures. Byte-grouping and Shared-ffn schemes are further proposed to fully utilize the capacity of the single-layer transformer. These features allow TRACE to achieve competitive compression ratio and a much faster speed. In addition, we further accelerate the compression procedure by designing a controller to reduce the parameter updating overhead. Experiments show that TRACE achieves an overall $\sim$3x speedup while keeps a comparable compression ratio to the state-of-the-art compressors. The source code for TRACE and links to the datasets are available at https://github.com/mynotwo/A-Fast-Transformer-based-General-Purpose-LosslessCompressor.

Yu Mao, Weilan Wang, Hongchao Du et al.

Deploying Large Language Models (LLMs) on edge or mobile devices offers significant benefits, such as enhanced data privacy and real-time processing capabilities. However, it also faces critical challenges due to the substantial memory requirement of LLMs. Quantization is an effective way of reducing the model size while maintaining good performance. However, even after quantization, LLMs may still be too big to fit entirely into the limited memory of edge or mobile devices and have to be partially loaded from the storage to complete the inference. In this case, the I/O latency of model loading becomes the bottleneck of the LLM inference latency. In this work, we take a preliminary step of studying applying data compression techniques to reduce data movement and thus speed up the inference of quantized LLM on memory-constrained devices. In particular, we discussed the compressibility of quantized LLMs, the trade-off between the compressibility and performance of quantized LLMs, and opportunities to optimize both of them jointly.

Junhui He, Junna Xing, Nan Wang et al.

Long context large language models (LLMs) pose significant challenges for efficient serving due to the large memory footprint and high access overhead of KV cache. Retrieval-based KV cache reduction methods can mitigate these challenges, typically by offloading the complete KV cache to CPU and retrieving necessary tokens on demand during inference. However, these methods still suffer from unsatisfactory accuracy degradation and extra retrieval overhead. To address these limitations, this paper proposes A$^2$ATS, a novel retrieval-based KV cache reduction method. A$^2$ATS aims to obtain an accurate approximation of attention scores by applying the vector quantization technique to key states, thereby enabling efficient and precise retrieval of the top-K tokens. First, we propose Windowed Rotary Position Embedding, which decouples the positional dependency from query and key states after position embedding. Then, we propose query-aware vector quantization that optimizes the objective of attention score approximation directly. Finally, we design the heterogeneous inference architecture for KV cache offloading, enabling long context serving with larger batch sizes. Experimental results demonstrate that A$^2$ATS can achieve a lower performance degradation with similar or lower overhead compared to existing methods, thereby increasing long context serving throughput by up to $2.7 \times$.

Hongchao Du, Shangyu Wu, Arina Kharlamova et al.

Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading framework for on-device inference, addressing these issues with techniques like asynchronous prefetching, balanced memory locking, and flexible tensor preservation. These strategies enhance memory efficiency and mitigate I/O bottlenecks, ensuring high performance within user-specified resource constraints. Experiments demonstrate that FlexInfer significantly improves throughput under limited resources, achieving up to 12.5 times better performance than existing methods and facilitating the deployment of large models on resource-constrained devices.

Shangyu Wu, Ying Xiong, Yufei Cui et al.

Retrieval-based augmentations (RA) incorporating knowledge from an external database into language models have greatly succeeded in various knowledge-intensive (KI) tasks. However, integrating retrievals in non-knowledge-intensive (NKI) tasks is still challenging. Existing works focus on concatenating retrievals with inputs to improve model performance. Unfortunately, the use of retrieval concatenation-based augmentations causes an increase in the input length, substantially raising the computational demands of attention mechanisms. This paper proposes a new paradigm of RA named \textbf{ReFusion}, a computation-efficient Retrieval representation Fusion with bi-level optimization. Unlike previous works, ReFusion directly fuses the retrieval representations into the hidden states of models. Specifically, ReFusion leverages an adaptive retrieval integrator to seek the optimal combination of the proposed ranking schemes across different model layers. Experimental results demonstrate that the proposed ReFusion can achieve superior and robust performance in various NKI tasks.

Weilan Wang, Yu Mao, Dongdong Tang et al.

Large language models (LLMs) exhibit excellent performance in various tasks. However, the memory requirements of LLMs present a great challenge when deploying on memory-limited devices, even for quantized LLMs. This paper introduces a framework to compress LLM after quantization further, achieving about 2.2x compression ratio. A compression-aware quantization is first proposed to enhance model weight compressibility by re-scaling the model parameters before quantization, followed by a pruning method to improve further. Upon this, we notice that decompression can be a bottleneck during practical scenarios. We then give a detailed analysis of the trade-off between memory usage and latency brought by the proposed method. A speed-adaptive method is proposed to overcome it. The experimental results show inference with the compressed model can achieve a 40% reduction in memory size with negligible loss in accuracy and inference speed.

Shangyu Wu, Hongchao Du, Ying Xiong et al.

Large Language Models (LLMs) have achieved remarkable success in natural language processing tasks, but their massive size and computational demands hinder their deployment in resource-constrained environments. Existing model pruning methods address this issue by removing redundant structures (e.g., elements, channels, layers) from the model. However, these methods employ a heuristic pruning strategy, which leads to suboptimal performance. Besides, they also ignore the data characteristics when pruning the model. To overcome these limitations, we propose EvoP, an evolutionary pruning framework for robust LLM inference. EvoP first presents a cluster-based calibration dataset sampling (CCDS) strategy for creating a more diverse calibration dataset. EvoP then introduces an evolutionary pruning pattern searching (EPPS) method to find the optimal pruning pattern. Compared to existing model pruning techniques, EvoP achieves the best performance while maintaining the best efficiency. Experiments across different LLMs and different downstream tasks validate the effectiveness of the proposed EvoP, making it a practical and scalable solution for deploying LLMs in real-world applications.

Yu Mao, Jun Wang, Nan Guan et al.

Whole-Slide Images (WSIs) have revolutionized medical analysis by presenting high-resolution images of the whole tissue slide. Despite avoiding the physical storage of the slides, WSIs require considerable data volume, which makes the storage and maintenance of WSI records costly and unsustainable. To this end, this work presents the first investigation of lossless compression of WSI images. Interestingly, we find that most existing compression methods fail to compress the WSI images effectively. Furthermore, our analysis reveals that the failure of existing compressors is mainly due to information irregularity in WSI images. To resolve this issue, we developed a simple yet effective lossless compressor called WISE, specifically designed for WSI images. WISE employs a hierarchical encoding strategy to extract effective bits, reducing the entropy of the image and then adopting a dictionary-based method to handle the irregular frequency patterns. Through extensive experiments, we show that WISE can effectively compress the gigapixel WSI images to 36 times on average and up to 136 times.

Yu Mao, Holger Pirk, Chun Jason Xue

As large language models (LLMs) continue to be deployed and utilized across domains, the volume of LLM-generated data is growing rapidly. This trend highlights the increasing importance of effective and lossless compression for such data in modern text management systems. However, compressing LLM-generated data presents unique challenges compared to traditional human- or machine-generated content. Traditional machine-generated data is typically derived from computational processes or device outputs, often highly structured and limited to low-level elements like labels or numerical values. This structure enables conventional lossless compressors to perform efficiently. In contrast, LLM-generated data is more complex and diverse, requiring new approaches for effective compression. In this work, we conduct the first systematic investigation of lossless compression techniques tailored specifically to LLM-generated data. Notably, because LLMs are trained via next-token prediction, we find that LLM-generated data is highly predictable for the models themselves. This predictability enables LLMs to serve as efficient compressors of their own outputs. Through extensive experiments with 14 representative LLMs and 8 LLM-generated datasets from diverse domains, we show that LLM-based prediction methods achieve remarkable compression rates, exceeding 20x, far surpassing the 3x rate achieved by Gzip, a widely used general-purpose compressor. Furthermore, this advantage holds across different LLM sizes and dataset types, demonstrating the robustness and practicality of LLM-based methods in lossless text compression under generative AI workloads.

Tianchi Ren, Haibo Hu, Jiacheng Zuo et al.

With the acceleration of urbanization, modern urban traffic systems are becoming increasingly complex, leading to frequent traffic anomalies. These anomalies encompass not only common traffic jams but also more challenging issues such as phantom traffic jams, intersection deadlocks, and accident liability analysis, which severely impact traffic flow, vehicular safety, and overall transportation efficiency. Currently, existing solutions primarily rely on manual intervention by traffic police or artificial intelligence-based detection systems. However, these methods often suffer from response delays and inconsistent management due to inadequate resources, while AI detection systems, despite enhancing efficiency to some extent, still struggle to handle complex traffic anomalies in a real-time and precise manner. To address these issues, we propose CoT-VLM4Tar: (Chain of Thought Visual-Language Model for Traffic Anomaly Resolution), this innovative approach introduces a new chain-of-thought to guide the VLM in analyzing, reasoning, and generating solutions for traffic anomalies with greater reasonable and effective solution, and to evaluate the performance and effectiveness of our method, we developed a closed-loop testing framework based on the CARLA simulator. Furthermore, to ensure seamless integration of the solutions generated by the VLM with the CARLA simulator, we implement an itegration module that converts these solutions into executable commands. Our results demonstrate the effectiveness of VLM in the resolution of real-time traffic anomalies, providing a proof-of-concept for its integration into autonomous traffic management systems.

Haibo Hu, Jiacheng Zuo, Yang Lou et al.

With the widespread adoption and deployment of autonomous driving, handling complex environments has become an unavoidable challenge. Due to the scarcity and diversity of extreme scenario datasets, current autonomous driving models struggle to effectively manage corner cases. This limitation poses a significant safety risk, according to the National Highway Traffic Safety Administration (NHTSA), autonomous vehicle systems have been involved in hundreds of reported crashes annually in the United States, occurred in corner cases like sun glare and fog, which caused a few fatal accident. Furthermore, in order to consistently maintain a robust and reliable autonomous driving system, it is essential for models not only to perform well on routine scenarios but also to adapt to newly emerging scenarios, especially those corner cases that deviate from the norm. This requires a learning mechanism that incrementally integrates new knowledge without degrading previously acquired capabilities. However, to the best of our knowledge, no existing continual learning methods have been proposed to ensure consistent and scalable corner case learning in autonomous driving. To address these limitations, we propose VLM-C4L, a continual learning framework that introduces Vision-Language Models (VLMs) to dynamically optimize and enhance corner case datasets, and VLM-C4L combines VLM-guided high-quality data extraction with a core data replay strategy, enabling the model to incrementally learn from diverse corner cases while preserving performance on previously routine scenarios, thus ensuring long-term stability and adaptability in real-world autonomous driving. We evaluate VLM-C4L on large-scale real-world autonomous driving datasets, including Waymo and the corner case dataset CODA.

Jun Wang, Yu Mao, Yufei Cui et al.

Immunohistochemistry (IHC) plays a crucial role in pathology as it detects the over-expression of protein in tissue samples. However, there are still fewer machine learning model studies on IHC's impact on accurate cancer grading. We discovered that IHC and H\&E possess distinct advantages and disadvantages while possessing certain complementary qualities. Building on this observation, we developed a two-stage multi-modal bilinear model with a feature pooling module. This model aims to maximize the potential of both IHC and HE's feature representation, resulting in improved performance compared to their individual use. Our experiments demonstrate that incorporating IHC data into machine learning models, alongside H\&E stained images, leads to superior predictive results for cancer grading. The proposed framework achieves an impressive ACC higher of 0.953 on the public dataset BCI.

Haochen Liu, Weien Li, Rui Song et al.

Large language model (LLM) systems are increasingly used to support high-stakes decision-making, but they typically perform worse when the available evidence is internally inconsistent. Such a scenario exists in real-world healthcare settings, with patient-reported symptoms contradicting medical signs. To study this problem, we introduce MIMIC-DOS, a dataset for short-horizon organ dysfunction worsening prediction in the intensive care unit (ICU) setting. We derive this dataset from the widely recognized MIMIC-IV, a publicly available electronic health record dataset, and construct it exclusively from cases in which discordance between signs and symptoms exists. This setting poses a substantial challenge for existing LLM-based approaches, with single-pass LLMs and agentic pipelines often struggling to reconcile such conflicting signals. To address this problem, we propose CARE: a multi-stage privacy-compliant agentic reasoning framework in which a remote LLM provides guidance by generating structured categories and transitions without accessing sensitive patient data, while a local LLM uses these categories and transitions to support evidence acquisition and final decision-making. Empirically, CARE achieves stronger performance across all key metrics compared to multiple baseline settings, showing that CARE can more robustly handle conflicting clinical evidence while preserving privacy.

Haibo HU, Lianming Huang, Nan Guan et al.

Vision-Language Action (VLA) models unify perception, reasoning, and trajectory generation for autonomous driving, but suffer from significant inference latency due to deep transformer stacks. We present DeeAD, a training-free, action-guided early-exit framework that accelerates VLA planning by evaluating the physical feasibility of intermediate trajectories. Instead of relying on confidence scores, DeeAD terminates inference when predicted trajectories align with lightweight planning priors (e.g., Navigation or Low-precision Planning) within a tolerable deviation (<2m). To improve efficiency, we introduce a multi-hop controller that adaptively skips redundant layers based on the change rate of scores. DeeAD integrates into existing VLA models, such as ORION, without requiring retraining. Experiments on the Bench2Drive benchmark demonstrate up to 28% transformer-layer sparsity and 29% latency reduction, while preserving planning quality and safety.

Lianming Huang, Haibo Hu, Qiao Li et al.

Sparsity is essential for deploying large models on resource constrained edge platforms. However, optimizing sparsity patterns for individual tasks in isolation ignores the significant I/O overhead incurred during frequent task switching. We introduce an on-demand multi-task sparsity framework specifically designed to minimize switching costs by maximizing parameter reuse. Unlike monolithic approaches, we decompose weights into reusable block-granular units and align sparse structures across tasks to maximize overlap. By dynamically loading only the small differential set of blocks required for the next task, our method effectively mitigates the cold-start latency inherent in traditional monolithic approaches.Experiments on a real-world autonomous driving platform demonstrate that our framework achieves superior switching efficiency, accelerating task switching by over 6.6X on average compared to existing sparsity methods.

Arina Kharlamova, Jiawen Liu, Tianyi Zhang et al.

Linux kernel evolution breaks drivers through API/ABI changes, semantic shifts, and security-hardening updates. We introduce DRIVEBENCH, an executable corpus of kernel$\rightarrow$driver co-evolution cases, and AUTODRIVER, a closed-loop, LLM-driven system for automating driver maintenance. The system integrates prompt engineering, multi-agent collaboration, static analysis, and iterative validation to ensure that generated patches are not only syntactically correct but also functionally and semantically consistent with kernel conventions. The corpus spans v5.10-v6.10 with 235 validated cases drawn from 612 candidates. In evaluation across 55 cases, AUTODRIVER achieves 56.4% compilation success; QEMU-based boot verification indicates that compiled patches preserve driver initialization in most instances. By releasing DRIVEBENCH and tooling, we enable reproducible research and a practical route to continuous, safe co-evolution of drivers with the Linux kernel.

Haibo Hu, Lianming Huang, Xinyu Wang et al.

Vision-Language Models (VLMs) are increasingly applied in autonomous driving for unified perception and reasoning, but high inference latency hinders real-time deployment. Early-exit reduces latency by terminating inference at intermediate layers, yet its task-dependent nature limits generalization across diverse scenarios. We observe that this limitation aligns with autonomous driving: navigation systems can anticipate upcoming contexts (e.g., intersections, traffic lights), indicating which tasks will be required. We propose Nav-EE, a navigation-guided early-exit framework that precomputes task-specific exit layers offline and dynamically applies them online based on navigation priors. Experiments on CODA, Waymo, and BOSCH show that Nav-EE achieves accuracy comparable to full inference while reducing latency by up to 63.9%. Real-vehicle integration with Autoware Universe further demonstrates reduced inference latency (600ms to 300ms), supporting faster decision-making in complex scenarios. These results suggest that coupling navigation foresight with early-exit offers a viable path toward efficient deployment of large models in autonomous systems. Code and data are available at our anonymous repository: https://anonymous.4open.science/r/Nav-EE-BBC4

Lianming Huang, Haibo Hu, Qiao Li et al.

Transformer-based Vision-Language Models (VLMs) have achieved impressive performance on tasks such as image captioning, object recognition, and visual reasoning, but their high computational cost hinders deployment in latency-sensitive applications like autonomous driving. We introduce GM-Skip, a flexible and metric-adaptive framework for Transformer block skipping that accelerates VLM inference while preserving output quality. GM-Skip features a greedy, metric-guided block selection strategy that uses metric feedback (e.g., accuracy, CIDEr) to identify redundant layers, along with a reverse-order deletion mechanism that preserves early foundational blocks to avoid performance collapse. To support diverse deployment needs, it incorporates a tunable trade-off between sparsity and performance via a score-sparsity balance objective. Experiments across multiple tasks and datasets, including COCO and CODA, show that GM-Skip consistently improves inference speed while maintaining task performance. On the COCO dataset, GM-Skip improves single-object classification accuracy on the Person category from 19.1 percent to 87.3 percent while skipping more than 40 percent of Transformer blocks. In real-world deployment, it achieves up to 45.4 percent latency reduction on single-object detection when integrated into an autonomous vehicle running Autoware.Universe, validating the effectiveness of its skip configurations and confirming its practical value in accelerating real-world inference.

Yixin Chen, Ying Xiong, Shangyu Wu et al.

Tool-augmented large language models (LLMs) leverage external functions to extend their capabilities, but inaccurate function calls can lead to inefficiencies and increased costs.Existing methods address this challenge by fine-tuning LLMs or using demonstration-based prompting, yet they often suffer from high training overhead and fail to account for inconsistent demonstration samples, which misguide the model's invocation behavior. In this paper, we trained a behavior-aligned retriever (BAR), which provides behaviorally consistent demonstrations to help LLMs make more accurate tool-using decisions. To train the BAR, we construct a corpus including different function-calling behaviors, i.e., calling or non-calling.We use the contrastive learning framework to train the BAR with customized positive/negative pairs and a dual-negative contrastive loss, ensuring robust retrieval of behaviorally consistent examples.Experiments demonstrate that our approach significantly reduces erroneous function calls while maintaining high task performance, offering a cost-effective and efficient solution for tool-augmented LLMs.

Mu-Chi Chen, Po-Hsuan Huang, Xiangrui Ke et al.

Large Language Models (LLMs) have revolutionized Artificial Intelligence (AI) with significant advancements such as OpenAI's ChatGPT, Meta's Llama, and Databricks' DBRX. This paper addresses the cost and scalability challenges encountered when constructing private LLM systems for personal or small group services, as aimed by Apple Intelligence. A Mac Studio cluster with Apple's M2 Ultra chips is established as a cost-efficient solution to host and accelerate the pretrained DBRX model with the Mixture-of-Experts (MoE) architecture. Our performance analysis reveal that parallel execution of the model's experts across two to four machine nodes significantly reduces inference time. We find that computation time for the experts is comparable to the communication time for exchanging their outputs, emphasizing the importance of network latency over bandwidth. We also observe significant management overhead due to Apple software stack's memory management logic. Based on these findings, we develop optimization schemes to eliminate the memory management overhead. As a result, the Mac Studio cluster is 1.15 times more cost-efficient than the state-of-the-art AI supercomputer with NVIDIA H100 GPUs. In addition, we construct a performance model to estimate system performance under varying configurations, and the model provides valuable insights for designing private LLM systems.

Lianming Huang, Haibo Hu, Yufei Cui et al.

With the rapid advancement of autonomous driving, deploying Vision-Language Models (VLMs) to enhance perception and decision-making has become increasingly common. However, the real-time application of VLMs is hindered by high latency and computational overhead, limiting their effectiveness in time-critical driving scenarios. This challenge is particularly evident when VLMs exhibit over-inference, continuing to process unnecessary layers even after confident predictions have been reached. To address this inefficiency, we propose AD-EE, an Early Exit framework that incorporates domain characteristics of autonomous driving and leverages causal inference to identify optimal exit layers. We evaluate our method on large-scale real-world autonomous driving datasets, including Waymo and the corner-case-focused CODA, as well as on a real vehicle running the Autoware Universe platform. Extensive experiments across multiple VLMs show that our method significantly reduces latency, with maximum improvements reaching up to 57.58%, and enhances object detection accuracy, with maximum gains of up to 44%.

Yu Mao, Jingzong Li, Jun Wang et al.

Neural image compression, necessary in various machine-to-machine communication scenarios, suffers from its heavy encode-decode structures and inflexibility in switching between different compression levels. Consequently, it raises significant challenges in applying the neural image compression to edge devices that are developed for powerful servers with high computational and storage capacities. We take a step to solve the challenges by proposing a new transformer-based edge-compute-free image coding framework called Easz. Easz shifts the computational overhead to the server, and hence avoids the heavy encoding and model switching overhead on the edge. Easz utilizes a patch-erase algorithm to selectively remove image contents using a conditional uniform-based sampler. The erased pixels are reconstructed on the receiver side through a transformer-based framework. To further reduce the computational overhead on the receiver, we then introduce a lightweight transformer-based reconstruction structure to reduce the reconstruction load on the receiver side. Extensive evaluations conducted on a real-world testbed demonstrate multiple advantages of Easz over existing compression approaches, in terms of adaptability to different compression levels, computational efficiency, and image reconstruction quality.

Ziwei Song, Mingsong Lv, Tianchi Ren et al.

Existing Autonomous Driving Systems (ADS) independently make driving decisions, but they face two significant limitations. First, in complex scenarios, ADS may misinterpret the environment and make inappropriate driving decisions. Second, these systems are unable to incorporate human driving preferences in their decision-making processes. This paper proposes Autoware$.$Flex, a novel ADS system that incorporates human input into the driving process, allowing users to guide the ADS in making more appropriate decisions and ensuring their preferences are satisfied. Achieving this needs to address two key challenges: (1) translating human instructions, expressed in natural language, into a format the ADS can understand, and (2) ensuring these instructions are executed safely and consistently within the ADS' s decision-making framework. For the first challenge, we employ a Large Language Model (LLM) assisted by an ADS-specialized knowledge base to enhance domain-specific translation. For the second challenge, we design a validation mechanism to ensure that human instructions result in safe and consistent driving behavior. Experiments conducted on both simulators and a real-world autonomous vehicle demonstrate that Autoware$.$Flex effectively interprets human instructions and executes them safely.

Ying Xiong, Linjing Liu, Yufei Cui et al.

Gene expression profiling provides profound insights into molecular mechanisms, but its time-consuming and costly nature often presents significant challenges. In contrast, whole-slide hematoxylin and eosin (H&E) stained histological images are readily accessible and allow for detailed examinations of tissue structure and composition at the microscopic level. Recent advancements have utilized these histological images to predict spatially resolved gene expression profiles. However, state-of-the-art works treat gene expression prediction as a multi-output regression problem, where each gene is learned independently with its own weights, failing to capture the shared dependencies and co-expression patterns between genes. Besides, existing works can only predict gene expression values for genes seen during training, limiting their ability to generalize to new, unseen genes. To address the above limitations, this paper presents GeneQuery, which aims to solve this gene expression prediction task in a question-answering (QA) manner for better generality and flexibility. Specifically, GeneQuery takes gene-related texts as queries and whole-slide images as contexts and then predicts the queried gene expression values. With such a transformation, GeneQuery can implicitly estimate the gene distribution by introducing the gene random variable. Besides, the proposed GeneQuery consists of two architecture implementations, i.e., spot-aware GeneQuery for capturing patterns between images and gene-aware GeneQuery for capturing patterns between genes. Comprehensive experiments on spatial transcriptomics datasets show that the proposed GeneQuery outperforms existing state-of-the-art methods on known and unseen genes. More results also demonstrate that GeneQuery can potentially analyze the tissue structure.

Jun Wang, Yu Mao, Yufei Cui et al.

Pre-processing whole slide images (WSIs) can impact classification performance. Our study shows that using fixed hyper-parameters for pre-processing out-of-domain WSIs can significantly degrade performance. Therefore, it is critical to search domain-specific hyper-parameters during inference. However, searching for an optimal parameter set is time-consuming. To overcome this, we propose BAHOP, a novel Similarity-based Basin Hopping optimization for fast parameter tuning to enhance inference performance on out-of-domain data. The proposed BAHOP achieves 5\% to 30\% improvement in accuracy with $\times5$ times faster on average.

Yufei Cui, Yu Mao, Ziquan Liu et al.

Nested dropout is a variant of dropout operation that is able to order network parameters or features based on the pre-defined importance during training. It has been explored for: I. Constructing nested nets: the nested nets are neural networks whose architectures can be adjusted instantly during testing time, e.g., based on computational constraints. The nested dropout implicitly ranks the network parameters, generating a set of sub-networks such that any smaller sub-network forms the basis of a larger one. II. Learning ordered representation: the nested dropout applied to the latent representation of a generative model (e.g., auto-encoder) ranks the features, enforcing explicit order of the dense representation over dimensions. However, the dropout rate is fixed as a hyper-parameter during the whole training process. For nested nets, when network parameters are removed, the performance decays in a human-specified trajectory rather than in a trajectory learned from data. For generative models, the importance of features is specified as a constant vector, restraining the flexibility of representation learning. To address the problem, we focus on the probabilistic counterpart of the nested dropout. We propose a variational nested dropout (VND) operation that draws samples of multi-dimensional ordered masks at a low cost, providing useful gradients to the parameters of nested dropout. Based on this approach, we design a Bayesian nested neural network that learns the order knowledge of the parameter distributions. We further exploit the VND under different generative models for learning ordered latent distributions. In experiments, we show that the proposed approach outperforms the nested network in terms of accuracy, calibration, and out-of-domain detection in classification tasks. It also outperforms the related generative models on data generation tasks.

Yufei Cui, Wuguannan Yao, Qiao Li et al.

Estimating the predictive uncertainty of a Bayesian learning model is critical in various decision-making problems, e.g., reinforcement learning, detecting adversarial attack, self-driving car. As the model posterior is almost always intractable, most efforts were made on finding an accurate approximation the true posterior. Even though a decent estimation of the model posterior is obtained, another approximation is required to compute the predictive distribution over the desired output. A common accurate solution is to use Monte Carlo (MC) integration. However, it needs to maintain a large number of samples, evaluate the model repeatedly and average multiple model outputs. In many real-world cases, this is computationally prohibitive. In this work, assuming that the exact posterior or a decent approximation is obtained, we propose a generic framework to approximate the output probability distribution induced by model posterior with a parameterized model and in an amortized fashion. The aim is to approximate the true uncertainty of a specific Bayesian model, meanwhile alleviating the heavy workload of MC integration at testing time. The proposed method is universally applicable to Bayesian classification models that allow for posterior sampling. Theoretically, we show that the idea of amortization incurs no additional costs on approximation performance. Empirical results validate the strong practical performance of our approach.

Jianzhong Sheng, Chuanbo Chen, Chenchen Fu et al.

Convolution operations dominate the overall execution time of Convolutional Neural Networks (CNNs). This paper proposes an easy yet efficient technique for both Convolutional Neural Network training and testing. The conventional convolution and pooling operations are replaced by Easy Convolution and Random Pooling (ECP). In ECP, we randomly select one pixel out of four and only conduct convolution operations of the selected pixel. As a result, only a quarter of the conventional convolution computations are needed. Experiments demonstrate that the proposed EasyConvPooling can achieve 1.45x speedup on training time and 1.64x on testing time. What's more, a speedup of 5.09x on pure Easy Convolution operations is obtained compared to conventional convolution operations.