Analytical information needs, such as trend analysis and causal impact assessment, are prevalent across various domains including law, finance, science, and much more. However, existing information retrieval paradigms, whether based on relevance-oriented document ranking or retrieval-augmented generation (RAG) with large language models (LLMs), often struggle to meet the end-to-end requirements of such tasks at the corpus scale. They either emphasize information finding rather than end-to-end problem solving, or simply treat everything as question answering, offering limited control over reasoning, evidence usage, and verifiability. As a result, they struggle to support analytical queries that have diverse utility concepts and high accountability requirements.

FPGA-based accelerators have emerged as an effective solution for GPT inference, given their inherent flexibility and capacity for domain-specific customization. However, the effective utilization of GPT has been hindered by two main obstacles: the unequal ratios between compute and memory access during the prefilling and generation stages, and the growing hardware resource requirements for nonlinear operations caused by longer text lengths and larger embedding dimensions. To address these challenges, we introduce DTrans, an FPGA accelerator specifically designed for GPT, which leverages nonlinear-operator fusion and a customized pipeline to efficiently handle long-input and long-generation tasks. We introduce a sequence-length-decoupled nonlinear operator design that enables in-place execution while preserving computational accuracy. Additionally, we employ a customized pipeline design that utilizes a two-level alternating input pipeline mapping for long-input tasks to alleviate the overhead associated with residual computation and on-chip buffers. Furthermore, for long-token generation tasks, our pipeline overlaps computational delays in operations such as Softmax and layer normalization with matrix operations. We also propose a novel two-stage dataflow transformation strategy that adopts different reuse strategies for the prefilling and generating stages with different computational/memory access characteristics. Our comparative analyses reveal that DTrans outperforms the GPU(V100) in terms of throughput and energy efficiency, achieving improvements of $11.99 \times$ and $11.7 \times$, respectively. When compared with state-of-the-art GPT inference accelerators, DTrans demonstrates more than $5.64 \times$ and $5.22 \times$ enhancements in these metrics.

Functional near-infrared spectroscopy (fNIRS) as an emerging optical neuroimaging technique has attracted the interest and attention of many investigators. With the growth of fNIRS data volume, effective data compression methods are urgent. Compressive sensing (CS) has been demonstrated a promising tool to deal with biomedical data. However, whether the compressibility of fNIRS data can discriminate different brain states is unclear. In this study, the fNIRS signals from fifteen attention-deficit/hyperactivity disorder (ADHD) children and fifteen typically developing (TD) children were recorded during an N-back task and a Go/NoGo task respectively. A block sparse Bayesian learning-based CS method was used to reconstruct the compressed fNIRS data. To assess the performance of the CS method, we adopted two metrics, structural similarity index (SSIM) and mean squared error (MSE), both of them effective in evaluating the compressibility of fNIRS data. Then, the two metrics were analyzed to discriminate the brain states of ADHD children and TD children during the two tasks using the multivariate pattern analysis (MVPA) method. As indicated by the results, the CS method could reconstruct the compressed fNIRS data with a high reconstruction quality at different compression ratio ([Formula: see text] and [Formula: see text]). Furthermore, the MVPA method could distinguish different brain states with high accuracy, and identify that the prefrontal cortex is a key brain region for distinguishing ADHD vs. TD or N-back vs. Go/NoGo. These findings indicated that CS is very promising for the storage and transmission of massive fNIRS data, and the compressibility of fNIRS data is a potential biomarker for the diagnosis of ADHD.

Baidu runs the largest commercial web search engine in China, serving hundreds of millions of online users every day in response to a great variety of queries. In order to build a high-efficiency sponsored search engine, we used to adopt a three-layer funnel-shaped structure to screen and sort hundreds of ads from billions of ad candidates subject to the requirement of low response latency and the restraints of computing resources. Given a user query, the top matching layer is responsible for providing semantically relevant ad candidates to the next layer, while the ranking layer at the bottom concerns more about business indicators (e.g., CPM, ROI, etc.) of those ads. The clear separation between the matching and ranking objectives results in a lower commercial return. The Mobius project has been established to address this serious issue. It is our first attempt to train the matching layer to consider CPM as an additional optimization objective besides the query-ad relevance, via directly predicting CTR (click-through rate) from billions of query-ad pairs. Specifically, this paper will elaborate on how we adopt active learning to overcome the insufficiency of click history at the matching layer when training our neural click networks offline, and how we use the SOTA ANN search technique for retrieving ads more efficiently (Here "ANN'' stands for approximate nearest neighbor search). We contribute the solutions to Mobius-V1 as the first version of our next generation query-ad matching system.

Recently, L1-norm-based discriminant subspace learning has attracted much more attention in dimensionality reduction and machine learning. However, most existing approaches solve the column vectors of the optimal projection matrix one by one with greedy strategy. Thus, the obtained optimal projection matrix does not necessarily best optimize the corresponding trace ratio objective function, which is the essential criterion function for general supervised dimensionality reduction. In this paper, we propose a non-greedy iterative algorithm to solve the trace ratio form of L1-norm-based linear discriminant analysis. We analyze the convergence of our proposed algorithm in detail. Extensive experiments on five popular image databases illustrate that our proposed algorithm can maximize the objective function value and is superior to most existing L1-LDA algorithms.