FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference

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.

CoT-VLM4Tar: Chain-of-Thought Guided Vision-Language Models for Traffic Anomaly Resolution

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.

When Compression Meets Model Compression: Memory-Efficient Double Compression for Large Language Models

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.

EvoP: Robust LLM Inference via Evolutionary Pruning

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 structured 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 structured 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.

A$^2$ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization

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 $2.7 \times$.

RALAD: Bridging the Real-to-Sim Domain Gap in Autonomous Driving with Retrieval-Augmented Learning

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.

Autoware.Flex: Human-Instructed Dynamically Reconfigurable Autonomous Driving Systems

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.

GeneQuery: A General QA-based Framework for Spatial Gene Expression Predictions from Histology Images

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.

SHAP-CAT: A interpretable multi-modal framework enhancing WSI classification via virtual staining and shapley-value-based multimodal fusion

The multimodal model has demonstrated promise in histopathology. However, most multimodal models are based on H\&E and genomics, adopting increasingly complex yet black-box designs. In our paper, we propose a novel interpretable multimodal framework named SHAP-CAT, which uses a Shapley-value-based dimension reduction technique for effective multimodal fusion. Starting with two paired modalities -- H\&E and IHC images, we employ virtual staining techniques to enhance limited input data by generating a new clinical-related modality. Lightweight bag-level representations are extracted from image modalities and a Shapley-value-based mechanism is used for dimension reduction. For each dimension of the bag-level representation, attribution values are calculated to indicate how changes in the specific dimensions of the input affect the model output. In this way, we select a few top important dimensions of bag-level representation for each image modality to late fusion. Our experimental results demonstrate that the proposed SHAP-CAT framework incorporating synthetic modalities significantly enhances model performance, yielding a 5\% increase in accuracy for the BCI, an 8\% increase for IHC4BC-ER, and an 11\% increase for the IHC4BC-PR dataset.

CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification

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 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, these methods do not explicitly model the impact of activation sparsification on performance, leading to suboptimal performance degradation. To address this issue, this paper reformulates the activation sparsification problem by introducing a new objective that optimizes the sparsification decisions. Building on this reformulation, we propose 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 8 downstream tasks while activating fewer parameters compared to existing methods, thus speeding up the LLM inference by up to 1.27x.