arXiv subjects

Wenkai Zhang

Publications and source records attributed to Wenkai Zhang.

At least 19 recordsLinked to original sources

arXiv2026

ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond

Enabling LLM agents to sustain productive, stable, and goal-aligned research over extended horizons is a central challenge for autonomous machine learning and scientific discovery, as progress hinges on continuously managing evolving state, exploration decisions, and computational resources. Pioneering autoresearch agents, despite great success, still lack mechanisms for continuity, recovery from dead ends, and value-driven compute allocation, which inherently undermines overall search efficiency, wastes computational resources, and lowers the chance of ultimate success. To bridge this gap, we introduce ScienceFlow, an end-to-end autoresearch agent framework that organizes long-horizon research work into research segments grounded in executable workspaces. It represents research progress as recoverable executable states, enabling efficient exploration, revision, and execution. Transitions between research segments are governed by Executable-State Transition through Re-Anchoring (ESTRA), which selects either the live state or an archived state as the next anchor and determines whether to continue or redirect the research trajectory. An evidence-aware execution controller allocates resources to physical jobs based on resource availability, remaining budget, and validated progress. We evaluate ScienceFlow on tasks spanning machine learning, scientific modeling, and mathematical optimization. Results on diverse long-horizon benchmarks demonstrate its ability to sustain effective research processes, highlighted by a SOTA 70.22 percent Any-Medal score on the full MLE-bench within a 24-hour budget, outperforming prior reported results by 4.92 percentage points. The efficacy of ScienceFlow further demonstrates that efficient state management, adaptive exploration, and objective-aligned execution are critical for scaling autonomous research beyond short-horizon interactions.

cs.AI↗

arXiv2026

RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search

In commercial web search, aligning content freshness with user intent remains challenging due to the highly varied lifespans of information. Traditional industrial approaches rely on static time-window filtering, resulting in "one-size-fits-all" rankings where content may be chronologically recent but semantically expired. To address the limitation, we present a novel Large Language Models (LLMs)-based Query-Aware Dynamic Content Expiration Prediction Framework deployed in Baidu search, reformulating timeliness as a dynamic validity inference task. Our framework extracts fine-grained temporal contexts from documents and leverages LLMs to deduce a query-specific "validity horizon"-a semantic boundary defining when information becomes obsolete based on user intent. Integrated with robust hallucination mitigation strategies to ensure reliability, our approach has been evaluated through offline and online A/B testing on live production traffic. Results demonstrate significant improvements in search freshness and user experience metrics, validating the effectiveness of LLM-driven reasoning for solving semantic expiration at an industrial scale.

cs.IR↗

arXiv2026

DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation

Presentation generation requires deep content research, coherent visual design, and iterative refinement based on observation. However, existing presentation agents often rely on predefined workflows and fixed templates. To address this, we present DeepPresenter, an agentic framework that adapts to diverse user intents, enables effective feedback-driven refinement, and generalizes beyond a scripted pipeline. Specifically, DeepPresenter autonomously plans, renders, and revises intermediate slide artifacts to support long-horizon refinement with environmental observations. Furthermore, rather than relying on self-reflection over internal signals (e.g., reasoning traces), our environment-grounded reflection conditions the generation process on perceptual artifact states (e.g., rendered slides), enabling the system to identify and correct presentation-specific issues during execution. Results on the evaluation set covering diverse presentation-generation scenarios show that DeepPresenter achieves state-of-the-art performance, and the fine-tuned 9B model remains highly competitive at substantially lower cost. Our project is available at: https://github.com/icip-cas/PPTAgent

cs.AI↗

arXiv2025

Cryptocurrencies and Interest Rates: Inferring Yield Curves in a Bondless Market

In traditional financial markets, yield curves are widely available for countries (and, by extension, currencies), financial institutions, and large corporates. These curves are used to calibrate stochastic interest rate models, discount future cash flows, and price financial products. Yield curves, however, can be readily computed only because of the current size and structure of bond markets. In cryptocurrency markets, where fixed-rate lending and bonds are almost nonexistent as of early 2025, the yield curve associated with each currency must be estimated by other means. In this paper, we show how mathematical tools can be used to construct yield curves for cryptocurrencies by leveraging data from the highly developed markets for cryptocurrency derivatives.

q-fin.GN↗

arXiv2025

Photonic logic tensor computing beyond TOPS per core

The soaring demand for computing resources has spurred great interest in photonic computing with higher speed and larger computing capacity. Photonic logic gates are of crucial importance due to the fundamental role of Boolean logic in modern digital computing systems. However, most photonic logic schemes struggle to exhibit the capability of massively parallel processing and flexible reconfiguration, owing to weak and fixed nonlinearity in optical elements. Here, we propose a photonic logic tensor computing architecture for the first time and fabricate the photonic universal logic tensor core (PULTC) with a parallel logic computing capacity beyond TOPS. Ten wavelength channels and four spatial channels are designed in PULTC, where the logic computing speed in each channel can reach 50 Gbit/s. After the nonlinear mapping of microring modulators, arbitrary logic operations can be achieved by configuring the Mach-Zehnder interferometer mesh. Our work offers an innovative route for photonic universal logic computing with high-parallel capability and propels the practical applications of photonic logic computing.

physics.optics↗

arXiv2025

Secret Sharing for DNA Probability Vectors

Emerging DNA storage technologies use composite DNA letters, where information is represented by a probability vector, leading to higher information density and lower synthesis costs. However, it faces the problem of information leakage in sharing the DNA vessels among untrusted vendors. This paper introduces an asymptotic ramp secret sharing scheme (ARSSS) for secret information storage using composite DNA letters. This innovative scheme, inspired by secret sharing methods over finite fields and enhanced with a modified matrix-vector multiplication operation for probability vectors, achieves asymptotic information-theoretic data security for a large alphabet size. Moreover, this scheme reduces the number of reading operations for DNA samples compared to traditional schemes, and therefore lowers the complexity and the cost of DNA-based secret sharing. We further explore the construction of the scheme, starting with a proof of the existence of a suitable generator, followed by practical examples. Finally, we demonstrate efficient constructions to support large information sizes, which utilize multiple vessels for each secret share rather than a single vessel.

cs.IT↗

arXiv2025

Codes for Limited-Magnitude Probability Error in DNA Storage

DNA, with remarkable properties of high density, durability, and replicability, is one of the most appealing storage media. Emerging DNA storage technologies use composite DNA letters, where information is represented by probability vectors, leading to higher information density and lower synthesizing costs than regular DNA letters. However, it faces the problem of inevitable noise and information corruption. This paper explores the channel of composite DNA letters in DNA-based storage systems and introduces block codes for limited-magnitude probability errors on probability vectors. First, outer and inner bounds for limited-magnitude probability error correction codes are provided. Moreover, code constructions are proposed where the number of errors is bounded by t, the error magnitudes are bounded by l, and the probability resolution is fixed as k. These constructions focus on leveraging the properties of limited-magnitude probability errors in DNA-based storage systems, leading to improved performance in terms of complexity and redundancy. In addition, the asymptotic optimality for one of the proposed constructions is established. Finally, systematic codes based on one of the proposed constructions are presented, which enable efficient information extraction for practical implementation.

cs.IT↗

arXiv2025

A Resource-Efficient Training Framework for Remote Sensing Text--Image Retrieval

Remote sensing text--image retrieval (RSTIR) aims to retrieve the matched remote sensing (RS) images from the database according to the descriptive text. Recently, the rapid development of large visual-language pre-training models provides new insights for RSTIR. Nevertheless, as the complexity of models grows in RSTIR, the previous studies suffer from suboptimal resource efficiency during transfer learning. To address this issue, we propose a computation and memory-efficient retrieval (CMER) framework for RSTIR. To reduce the training memory consumption, we propose the Focus-Adapter module, which adopts a side branch structure. Its focus layer suppresses the interference of background pixels for small targets. Simultaneously, to enhance data efficacy, we regard the RS scene category as the metadata and design a concise augmentation technique. The scene label augmentation leverages the prior knowledge from land cover categories and shrinks the search space. We propose the negative sample recycling strategy to make the negative sample pool decoupled from the mini-batch size. It improves the generalization performance without introducing additional encoders. We have conducted quantitative and qualitative experiments on public datasets and expanded the benchmark with some advanced approaches, which demonstrates the competitiveness of the proposed CMER. Compared with the recent advanced methods, the overall retrieval performance of CMER is 2%--5% higher on RSITMD. Moreover, our proposed method reduces memory consumption by 49% and has a 1.4x data throughput during training. The code of the CMER and the dataset will be released at https://github.com/ZhangWeihang99/CMER.

cs.CV↗

arXiv2023

Eight-input optical programmable logic array enabled by parallel spectrum modulation

Despite over 40 years' development of optical logic computing, the studies have been still struggling to support more than four operands, since the high parallelism of light has not been fully leveraged blocked by the optical nonlinearity and redundant input modulation in existing methods. Here, we propose a scalable multi-input optical programmable logic array (PLA) with minimal logical input, enabled by parallel spectrum modulation. By making full use of the wavelength resource, an eight-input PLA is experimentally demonstrated, and there are 2^256 possible combinations of generated logic gates. Various complex logic fuctions, such as 8-256 decoder, 4-bit comparator, adder and multiplier are experimentally demonstrated via leveraging the PLA. The scale of PLA can be further extended by fully using the dimensions of wavelength and space. As an example, a nine-input PLA is implemented to realize the two-dimensional optical cellular automaton for the first time and perform Conway's Game of Life to simulate the evolutionary process of cells. Our work significantly alleviates the challenge of extensibility of optical logic devices, opening up new avenues for future large-scale, high-speed and energy-efficient optical digital computing.

cs.ET↗

arXiv2023

Chip-to-chip optical multimode communication with universal mode processors

The increasing amount of data exchange requires higher-capacity optical communication links. Mode division multiplexing (MDM) is considered as a promising technology to support the higher data throughput. In an MDM system, the mode generator and sorter are the backbone. However, most of the current schemes lack the programmability and universality, which makes the MDM link susceptible to the mode crosstalk and environmental disturbances. In this paper, we propose an intelligent multimode optical communication link using universal mode processing (generation and sorting) chips. The mode processor consists of a programmable 4*4 Mach Zehnder interferometer (MZI) network and can be intelligently configured to generate or sort both quasi linearly polarized (LP) modes and orbital angular momentum (OAM) modes in any desired routing state. We experimentally establish a chip-to-chip MDM communication system. The mode basis can be freely switched between four LP modes and four OAM modes. We also demonstrate the multimode optical communication capability at a data rate of 25 Gbit/s. The proposed scheme shows significant advantages in terms of universality, intelligence, programmability and resistance to mode crosstalk, environmental disturbances and fabrication errors, demonstrating that the MZI-based reconfigurable mode processor chip has great potential in long-distance chip-to-chip multimode optical communication systems.

physics.optics↗

arXiv2022

Learning to Evaluate Performance of Multi-modal Semantic Localization

Semantic localization (SeLo) refers to the task of obtaining the most relevant locations in large-scale remote sensing (RS) images using semantic information such as text. As an emerging task based on cross-modal retrieval, SeLo achieves semantic-level retrieval with only caption-level annotation, which demonstrates its great potential in unifying downstream tasks. Although SeLo has been carried out successively, but there is currently no work has systematically explores and analyzes this urgent direction. In this paper, we thoroughly study this field and provide a complete benchmark in terms of metrics and testdata to advance the SeLo task. Firstly, based on the characteristics of this task, we propose multiple discriminative evaluation metrics to quantify the performance of the SeLo task. The devised significant area proportion, attention shift distance, and discrete attention distance are utilized to evaluate the generated SeLo map from pixel-level and region-level. Next, to provide standard evaluation data for the SeLo task, we contribute a diverse, multi-semantic, multi-objective Semantic Localization Testset (AIR-SLT). AIR-SLT consists of 22 large-scale RS images and 59 test cases with different semantics, which aims to provide a comprehensive evaluations for retrieval models. Finally, we analyze the SeLo performance of RS cross-modal retrieval models in detail, explore the impact of different variables on this task, and provide a complete benchmark for the SeLo task. We have also established a new paradigm for RS referring expression comprehension, and demonstrated the great advantage of SeLo in semantics through combining it with tasks such as detection and road extraction. The proposed evaluation metrics, semantic localization testsets, and corresponding scripts have been open to access at github.com/xiaoyuan1996/SemanticLocalizationMetrics .

cs.CV↗

arXiv2022

Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion

Open-domain multi-turn conversations normally face the challenges of how to enrich and expand the content of the conversation. Recently, many approaches based on external knowledge are proposed to generate rich semantic and information conversation. Two types of knowledge have been studied for knowledge-aware open-domain dialogue generation: structured triples from knowledge graphs and unstructured texts from documents. To take both advantages of abundant unstructured latent knowledge in the documents and the information expansion capabilities of the structured knowledge graph, this paper presents a new dialogue generation model, Dynamic Multi-form Knowledge Fusion based Open-domain Chatt-ing Machine (DMKCM).In particular, DMKCM applies an indexed text (a virtual Knowledge Base) to locate relevant documents as 1st hop and then expands the content of the dialogue and its 1st hop using a commonsense knowledge graph to get apposite triples as 2nd hop. To merge these two forms of knowledge into the dialogue effectively, we design a dynamic virtual knowledge selector and a controller that help to enrich and expand knowledge space. Moreover, DMKCM adopts a novel dynamic knowledge memory module that effectively uses historical reasoning knowledge to generate better responses. Experimental results indicate the effectiveness of our method in terms of dialogue coherence and informativeness.

cs.CL↗

arXiv2022

Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrieval

Remote sensing (RS) cross-modal text-image retrieval has attracted extensive attention for its advantages of flexible input and efficient query. However, traditional methods ignore the characteristics of multi-scale and redundant targets in RS image, leading to the degradation of retrieval accuracy. To cope with the problem of multi-scale scarcity and target redundancy in RS multimodal retrieval task, we come up with a novel asymmetric multimodal feature matching network (AMFMN). Our model adapts to multi-scale feature inputs, favors multi-source retrieval methods, and can dynamically filter redundant features. AMFMN employs the multi-scale visual self-attention (MVSA) module to extract the salient features of RS image and utilizes visual features to guide the text representation. Furthermore, to alleviate the positive samples ambiguity caused by the strong intraclass similarity in RS image, we propose a triplet loss function with dynamic variable margin based on prior similarity of sample pairs. Finally, unlike the traditional RS image-text dataset with coarse text and higher intraclass similarity, we construct a fine-grained and more challenging Remote sensing Image-Text Match dataset (RSITMD), which supports RS image retrieval through keywords and sentence separately and jointly. Experiments on four RS text-image datasets demonstrate that the proposed model can achieve state-of-the-art performance in cross-modal RS text-image retrieval task.

cs.CV↗

arXiv2022

Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information

Cross-modal remote sensing text-image retrieval (RSCTIR) has recently become an urgent research hotspot due to its ability of enabling fast and flexible information extraction on remote sensing (RS) images. However, current RSCTIR methods mainly focus on global features of RS images, which leads to the neglect of local features that reflect target relationships and saliency. In this article, we first propose a novel RSCTIR framework based on global and local information (GaLR), and design a multi-level information dynamic fusion (MIDF) module to efficaciously integrate features of different levels. MIDF leverages local information to correct global information, utilizes global information to supplement local information, and uses the dynamic addition of the two to generate prominent visual representation. To alleviate the pressure of the redundant targets on the graph convolution network (GCN) and to improve the model s attention on salient instances during modeling local features, the de-noised representation matrix and the enhanced adjacency matrix (DREA) are devised to assist GCN in producing superior local representations. DREA not only filters out redundant features with high similarity, but also obtains more powerful local features by enhancing the features of prominent objects. Finally, to make full use of the information in the similarity matrix during inference, we come up with a plug-and-play multivariate rerank (MR) algorithm. The algorithm utilizes the k nearest neighbors of the retrieval results to perform a reverse search, and improves the performance by combining multiple components of bidirectional retrieval. Extensive experiments on public datasets strongly demonstrate the state-of-the-art performance of GaLR methods on the RSCTIR task. The code of GaLR method, MR algorithm, and corresponding files have been made available at https://github.com/xiaoyuan1996/GaLR .

cs.CV↗

arXiv2021

Disentangling and Vectorization: A 3D Visual Perception Approach for Autonomous Driving Based on Surround-View Fisheye Cameras

The 3D visual perception for vehicles with the surround-view fisheye camera system is a critical and challenging task for low-cost urban autonomous driving. While existing monocular 3D object detection methods perform not well enough on the fisheye images for mass production, partly due to the lack of 3D datasets of such images. In this paper, we manage to overcome and avoid the difficulty of acquiring the large scale of accurate 3D labeled truth data, by breaking down the 3D object detection task into some sub-tasks, such as vehicle's contact point detection, type classification, re-identification and unit assembling, etc. Particularly, we propose the concept of Multidimensional Vector to include the utilizable information generated in different dimensions and stages, instead of the descriptive approach for the bird's eye view (BEV) or a cube of eight points. The experiments of real fisheye images demonstrate that our solution achieves state-of-the-art accuracy while being real-time in practice.

cs.CV↗

arXiv2021

De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention

Distant supervision tackles the data bottleneck in NER by automatically generating training instances via dictionary matching. Unfortunately, the learning of DS-NER is severely dictionary-biased, which suffers from spurious correlations and therefore undermines the effectiveness and the robustness of the learned models. In this paper, we fundamentally explain the dictionary bias via a Structural Causal Model (SCM), categorize the bias into intra-dictionary and inter-dictionary biases, and identify their causes. Based on the SCM, we learn de-biased DS-NER via causal interventions. For intra-dictionary bias, we conduct backdoor adjustment to remove the spurious correlations introduced by the dictionary confounder. For inter-dictionary bias, we propose a causal invariance regularizer which will make DS-NER models more robust to the perturbation of dictionaries. Experiments on four datasets and three DS-NER models show that our method can significantly improve the performance of DS-NER.

cs.CL↗

arXiv2021

Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Model

Denoising is the essential step for distant supervision based named entity recognition. Previous denoising methods are mostly based on instance-level confidence statistics, which ignore the variety of the underlying noise distribution on different datasets and entity types. This makes them difficult to be adapted to high noise rate settings. In this paper, we propose Hypergeometric Learning (HGL), a denoising algorithm for distantly supervised NER that takes both noise distribution and instance-level confidence into consideration. Specifically, during neural network training, we naturally model the noise samples in each batch following a hypergeometric distribution parameterized by the noise-rate. Then each instance in the batch is regarded as either correct or noisy one according to its label confidence derived from previous training step, as well as the noise distribution in this sampled batch. Experiments show that HGL can effectively denoise the weakly-labeled data retrieved from distant supervision, and therefore results in significant improvements on the trained models.

cs.CL↗

arXiv2021

DeepWORD: A GCN-based Approach for Owner-Member Relationship Detection in Autonomous Driving

It's worth noting that the owner-member relationship between wheels and vehicles has an significant contribution to the 3D perception of vehicles, especially in the embedded environment. However, there are currently two main challenges about the above relationship prediction: i) The traditional heuristic methods based on IoU can hardly deal with the traffic jam scenarios for the occlusion. ii) It is difficult to establish an efficient applicable solution for the vehicle-mounted system. To address these issues, we propose an innovative relationship prediction method, namely DeepWORD, by designing a graph convolution network (GCN). Specifically, we utilize the feature maps with local correlation as the input of nodes to improve the information richness. Besides, we introduce the graph attention network (GAT) to dynamically amend the prior estimation deviation. Furthermore, we establish an annotated owner-member relationship dataset called WORD as a large-scale benchmark, which will be available soon. The experiments demonstrate that our solution achieves state-of-the-art accuracy and real-time in practice.

cs.CV↗