Jizhou Huang

Jiankun Li, Hao Li, Jiangjiang Liu et al. · baidu

Deep learning-based models are widely deployed in autonomous driving areas, especially the increasingly noticed end-to-end solutions. However, the black-box property of these models raises concerns about their trustworthiness and safety for autonomous driving, and how to debug the causality has become a pressing concern. Despite some existing research on the explainability of autonomous driving, there is currently no systematic solution to help researchers debug and identify the key factors that lead to the final predicted action of end-to-end autonomous driving. In this work, we propose a comprehensive approach to explore and analyze the causality of end-to-end autonomous driving. First, we validate the essential information that the final planning depends on by using controlled variables and counterfactual interventions for qualitative analysis. Then, we quantitatively assess the factors influencing model decisions by visualizing and statistically analyzing the response of key model inputs. Finally, based on the comprehensive study of the multi-factorial end-to-end autonomous driving system, we have developed a strong baseline and a tool for exploring causality in the close-loop simulator CARLA. It leverages the essential input sources to obtain a well-designed model, resulting in highly competitive capabilities. As far as we know, our work is the first to unveil the mystery of end-to-end autonomous driving and turn the black box into a white one. Thorough close-loop experiments demonstrate that our method can be applied to end-to-end autonomous driving solutions for causality debugging. Code will be available at https://github.com/bdvisl/DriveInsight.

Congxi Xiao, Jingbo Zhou, Jizhou Huang et al. · baidu

Urban villages (UVs) refer to the underdeveloped informal settlement falling behind the rapid urbanization in a city. Since there are high levels of social inequality and social risks in these UVs, it is critical for city managers to discover all UVs for making appropriate renovation policies. Existing approaches to detecting UVs are labor-intensive or have not fully addressed the unique challenges in UV detection such as the scarcity of labeled UVs and the diverse urban patterns in different regions. To this end, we first build an urban region graph (URG) to model the urban area in a hierarchically structured way. Then, we design a novel contextual master-slave framework to effectively detect the urban village from the URG. The core idea of such a framework is to firstly pre-train a basis (or master) model over the URG, and then to adaptively derive specific (or slave) models from the basis model for different regions. The proposed framework can learn to balance the generality and specificity for UV detection in an urban area. Finally, we conduct extensive experiments in three cities to demonstrate the effectiveness of our approach.

Jizhou Huang, Zhengjie Huang, Xiaomin Fang et al. · baidu

Estimated time of arrival (ETA) prediction, also known as travel time estimation, is a fundamental task for a wide range of intelligent transportation applications, such as navigation, route planning, and ride-hailing services. To accurately predict the travel time of a route, it is essential to take into account both contextual and predictive factors, such as spatial-temporal interaction, driving behavior, and traffic congestion propagation inference. The ETA prediction models previously deployed at Baidu Maps have addressed the factors of spatial-temporal interaction (ConSTGAT) and driving behavior (SSML). In this work, we focus on modeling traffic congestion propagation patterns to improve ETA performance. Traffic congestion propagation pattern modeling is challenging, and it requires accounting for impact regions over time and cumulative effect of delay variations over time caused by traffic events on the road network. In this paper, we present a practical industrial-grade ETA prediction framework named DuETA. Specifically, we construct a congestion-sensitive graph based on the correlations of traffic patterns, and we develop a route-aware graph transformer to directly learn the long-distance correlations of the road segments. This design enables DuETA to capture the interactions between the road segment pairs that are spatially distant but highly correlated with traffic conditions. Extensive experiments are conducted on large-scale, real-world datasets collected from Baidu Maps. Experimental results show that ETA prediction can significantly benefit from the learned traffic congestion propagation patterns. In addition, DuETA has already been deployed in production at Baidu Maps, serving billions of requests every day. This demonstrates that DuETA is an industrial-grade and robust solution for large-scale ETA prediction services.

Deguo Xia, Zihan Li, Haochen Zhao et al.

Lane-level maps are critical infrastructure for autonomous driving and lane-level navigation, yet constructing and maintaining standardized lane networks for hundreds of cities remains highly labor-intensive. Recent end-to-end vectorized mapping methods can predict lane geometry and topology directly from sensor data, but they typically treat mapping specifications and traffic regulations as implicit, dataset-dependent supervision. Moreover, in complex scenes (e.g., worn or missing markings and occlusions), correct lane configurations are often under-determined by visual evidence alone, making specification violations a major source of human post-editing. We propose MapAgent, an industrial-grade agentic architecture that augments a vectorization backbone for specification-compliant lane-map production. Rather than merely adding an agent loop to map prediction, MapAgent couples backbone perception with explicit specification verification, constraint-aware reasoning, and deterministic map editing under a bounded, verification-driven Judge-Planner-Worker loop. A vision-language Judge diagnoses errors by jointly inspecting visual evidence and draft vectors, while a tool-calling Planner generates minimal corrective edits with post-edit re-validation. To remain scalable for city-scale production, MapAgent is selectively triggered only on tiles with low backbone confidence, adding modest overhead while preserving throughput. Experiments on real-world datasets show consistent gains over strong production baselines, especially in complex and long-tail scenarios. Additionally, MapAgent has been integrated into Baidu Maps, supporting lane-level map generation for over 360 cities nationwide and elevating the overall production automation to over 95%, demonstrating MapAgent's practicality and effectiveness for large-scale lane-level map generation.

Jizhou Huang, Haifeng Wang, Yibo Sun et al. · baidu

Pre-trained models (PTMs) have become a fundamental backbone for downstream tasks in natural language processing and computer vision. Despite initial gains that were obtained by applying generic PTMs to geo-related tasks at Baidu Maps, a clear performance plateau over time was observed. One of the main reasons for this plateau is the lack of readily available geographic knowledge in generic PTMs. To address this problem, in this paper, we present ERNIE-GeoL, which is a geography-and-language pre-trained model designed and developed for improving the geo-related tasks at Baidu Maps. ERNIE-GeoL is elaborately designed to learn a universal representation of geography-language by pre-training on large-scale data generated from a heterogeneous graph that contains abundant geographic knowledge. Extensive quantitative and qualitative experiments conducted on large-scale real-world datasets demonstrate the superiority and effectiveness of ERNIE-GeoL. ERNIE-GeoL has already been deployed in production at Baidu Maps since April 2021, which significantly benefits the performance of various downstream tasks. This demonstrates that ERNIE-GeoL can serve as a fundamental backbone for a wide range of geo-related tasks.

Congxi Xiao, Jingbo Zhou, Jizhou Huang et al. · baidu

Graph Neural Networks (GNNs) have been broadly applied in many urban applications upon formulating a city as an urban graph whose nodes are urban objects like regions or points of interest. Recently, a few enhanced GNN architectures have been developed to tackle heterophily graphs where connected nodes are dissimilar. However, urban graphs usually can be observed to possess a unique spatial heterophily property; that is, the dissimilarity of neighbors at different spatial distances can exhibit great diversity. This property has not been explored, while it often exists. To this end, in this paper, we propose a metric, named Spatial Diversity Score, to quantitatively measure the spatial heterophily and show how it can influence the performance of GNNs. Indeed, our experimental investigation clearly shows that existing heterophilic GNNs are still deficient in handling the urban graph with high spatial diversity score. This, in turn, may degrade their effectiveness in urban applications. Along this line, we propose a Spatial Heterophily Aware Graph Neural Network (SHGNN), to tackle the spatial diversity of heterophily of urban graphs. Based on the key observation that spatially close neighbors on the urban graph present a more similar mode of difference to the central node, we first design a rotation-scaling spatial aggregation module, whose core idea is to properly group the spatially close neighbors and separately process each group with less diversity inside. Then, a heterophily-sensitive spatial interaction module is designed to adaptively capture the commonality and diverse dissimilarity in different spatial groups. Extensive experiments on three real-world urban datasets demonstrate the superiority of our SHGNN over several its competitors.

Yumeng Zhang, Shi Gong, Kaixin Xiong et al. · baidu

World models have attracted increasing attention in autonomous driving for their ability to forecast potential future scenarios. In this paper, we propose BEVWorld, a novel framework that transforms multimodal sensor inputs into a unified and compact Bird's Eye View (BEV) latent space for holistic environment modeling. The proposed world model consists of two main components: a multi-modal tokenizer and a latent BEV sequence diffusion model. The multi-modal tokenizer first encodes heterogeneous sensory data, and its decoder reconstructs the latent BEV tokens into LiDAR and surround-view image observations via ray-casting rendering in a self-supervised manner. This enables joint modeling and bidirectional encoding-decoding of panoramic imagery and point cloud data within a shared spatial representation. On top of this, the latent BEV sequence diffusion model performs temporally consistent forecasting of future scenes, conditioned on high-level action tokens, enabling scene-level reasoning over time. Extensive experiments demonstrate the effectiveness of BEVWorld on autonomous driving benchmarks, showcasing its capability in realistic future scene generation and its benefits for downstream tasks such as perception and motion prediction.

Rui Zhu, Xin Shen, Shuchen Wu et al.

Spatial reasoning has emerged as a critical capability for Multimodal Large Language Models (MLLMs), drawing increasing attention and rapid advancement. However, existing benchmarks primarily focus on single-step perception-to-judgment tasks, leaving scenarios requiring complex visual-spatial logical chains significantly underexplored. To bridge this gap, we introduce Video-MSR, the first benchmark specifically designed to evaluate Multi-hop Spatial Reasoning (MSR) in dynamic video scenarios. Video-MSR systematically probes MSR capabilities through four distinct tasks: Constrained Localization, Chain-based Reference Retrieval, Route Planning, and Counterfactual Physical Deduction. Our benchmark comprises 3,052 high-quality video instances with 4,993 question-answer pairs, constructed via a scalable, visually-grounded pipeline combining advanced model generation with rigorous human verification. Through a comprehensive evaluation of 20 state-of-the-art MLLMs, we uncover significant limitations, revealing that while models demonstrate proficiency in surface-level perception, they exhibit distinct performance drops in MSR tasks, frequently suffering from spatial disorientation and hallucination during multi-step deductions. To mitigate these shortcomings and empower models with stronger MSR capabilities, we further curate MSR-9K, a specialized instruction-tuning dataset, and fine-tune Qwen-VL, achieving a +7.82% absolute improvement on Video-MSR. Our results underscore the efficacy of multi-hop spatial instruction data and establish Video-MSR as a vital foundation for future research. The code and data will be available at https://github.com/ruiz-nju/Video-MSR.

Can Xu, Lingyong Yan, Jiayi Wu et al. · baidu

Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged perspective, limiting their ability to conduct deep, self-correcting reasoning over external documents, and (2) existing training paradigms rely excessively on outcome-oriented rewards, which provide insufficient signal for shaping the complex, multi-step reasoning process. To address these issues, we propose an Reasoner-Verifier framework named Adversarial Reasoning RAG (ARR). The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage that requires no external scoring model. This reward combines explicit observational signals with internal model uncertainty to jointly optimize reasoning fidelity and verification rigor. Experiments on multiple benchmarks demonstrate the effectiveness of our method.

Wang Chen, Guanqiang Qi, Weikang Li et al.

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, but existing approaches indiscriminately trigger retrieval and rely on single-path evidence construction, often introducing noise and limiting performance gains. In this work, we propose Decide Then Retrieve (DTR), a training-free framework that adaptively determines when retrieval is necessary and how external information should be selected. DTR leverages generation uncertainty to guide retrieval triggering and introduces a dual-path retrieval mechanism with adaptive information selection to better handle sparse and ambiguous queries. Extensive experiments across five open-domain QA benchmarks, multiple model scales, and different retrievers demonstrate that DTR consistently improves EM and F1 over standard RAG and strong retrieval-enhanced baselines, while reducing unnecessary retrievals. The code and data used in this paper are available at https://github.com/ChenWangHKU/DTR.

Zhaoxi Zhang, Yitong Duan, Yanzhi Zhang et al. · baidu, tsinghua

Locating files and functions requiring modification in large software repositories is challenging due to their scale and structural complexity. Existing LLM-based methods typically treat this as a repository-level retrieval task and rely on multiple auxiliary tools, which often overlook code execution logic and complicate model control. We propose RepoNavigator, an LLM agent equipped with a single execution-aware tool: jumping to the definition of an invoked symbol. This unified design reflects the actual flow of code execution while simplifying tool manipulation. RepoNavigator is trained end-to-end via Reinforcement Learning (RL) directly from a base pretrained model, without relying on closed-source distillation. Experiments demonstrate that RL-trained RepoNavigator achieves state-of-the-art performance, with the 7B model outperforming 14B baselines, the 14B model surpassing 32B competitors, and the 32B model exceeding closed-source models such as GPT-5 on most metrics. These results confirm that integrating a single, structurally grounded tool with RL training provides an efficient and scalable solution for repository-level issue localization.

Mingyang Liao, Yichen Wan, shuchen wu et al. · baidu, tsinghua

LLM-based role-playing has rapidly improved in fidelity, yet stronger adherence to persona constraints commonly increases vulnerability to jailbreak attacks, especially for risky or negative personas. Most prior work mitigates this issue with training-time solutions (e.g., data curation or alignment-oriented regularization). However, these approaches are costly to maintain as personas and attack strategies evolve, can degrade in-character behavior, and are typically infeasible for frontier closed-weight LLMs. We propose a training-free Dual-Cycle Adversarial Self-Evolution framework with two coupled cycles. A Persona-Targeted Attacker Cycle synthesizes progressively stronger jailbreak prompts, while a Role-Playing Defender Cycle distills observed failures into a hierarchical knowledge base of (i) global safety rules, (ii) persona-grounded constraints, and (iii) safe in-character exemplars. At inference time, the Defender retrieves and composes structured knowledge from this hierarchy to guide generation, producing responses that remain faithful to the target persona while satisfying safety constraints. Extensive experiments across multiple proprietary LLMs show consistent gains over strong baselines on both role fidelity and jailbreak resistance, and robust generalization to unseen personas and attack prompts.

Xin Shen, Zhishu Jiang, Jiaye Yang et al. · baidu, tsinghua

Immersive conversational systems in production face a persistent trade-off between responsiveness and long-horizon task capability. Real-time interaction is achievable for lightweight turns, but requests involving planning and tool invocation (e.g., search and media generation) produce heavy-tail execution latency that degrades turn-taking, persona consistency, and user trust. To address this challenge, we propose DuCCAE (Conversation while Collaboration with Augmentation and Evolution), a hybrid engine for immersive conversation deployed within Baidu Search, serving millions of users. DuCCAE decouples real-time response generation from asynchronous agentic execution and synchronizes them via a shared state that maintains session context and execution traces, enabling asynchronous results to be integrated back into the ongoing dialogue. The system orchestrates five subsystems-Info, Conversation, Collaboration, Augmentation, and Evolution-to support multi-agent collaboration and continuous improvement. We evaluate DuCCAE through a comprehensive framework that combines offline benchmarking on the Du-Interact dataset and large-scale production evaluation within Baidu Search. Experimental results demonstrate that DuCCAE outperforms strong baselines in agentic execution reliability and dialogue quality while reducing latency to fit strict real-time budgets. Crucially, deployment metrics since June 2025 confirm substantial real-world effectiveness, evidenced by a tripling of Day-7 user retention to 34.2% and a surge in the complex task completion rate to 65.2%. Our hybrid architecture successfully preserves conversational continuity while enabling reliable agentic execution, offering practical guidelines for deploying scalable agentic systems in industrial settings.

Jiulong Wu, Yucheng Shen, Lingyong Yan et al.

Facial Emotion Analysis (FEA) extends traditional facial emotion recognition by incorporating explainable, fine-grained reasoning. The task integrates three subtasks: emotion recognition, facial Action Unit (AU) recognition, and AU-based emotion reasoning to model affective states jointly. While recent approaches leverage Vision-Language Models (VLMs) and achieve promising results, they face two critical limitations: (1) hallucinated reasoning, where VLMs generate plausible but inaccurate explanations due to insufficient emotion-specific knowledge; and (2) misalignment between emotion reasoning and recognition, caused by fragmented connections between observed facial features and final labels. We propose Facial-R1, a three-stage alignment framework that effectively addresses both challenges with minimal supervision. First, we employ instruction fine-tuning to establish basic emotional reasoning capability. Second, we introduce reinforcement training guided by emotion and AU labels as reward signals, which explicitly aligns the generated reasoning process with the predicted emotion. Third, we design a data synthesis pipeline that iteratively leverages the prior stages to expand the training dataset, enabling scalable self-improvement of the model. Built upon this framework, we introduce FEA-20K, a benchmark dataset comprising 17,737 training and 1,688 test samples with fine-grained emotion analysis annotations. Extensive experiments across eight standard benchmarks demonstrate that Facial-R1 achieves state-of-the-art performance in FEA, with strong generalization and robust interpretability.

Le Zhang, Shengming Zhang, Rui Zha et al.

Accurate Point of Interest (POI) attribute acquisition is essential for location-based services, yet traditional modular Interactive Voice Response (IVR) systems suffer from error accumulation and high maintenance overhead. We present DuIVRS-2, a large language model (LLM)-based end-to-end framework designed for large-scale POI attribute acquisition at Baidu Maps. To address the long-tail distribution of real-world interactions, our methodology first employs a finite state machine (FSM)-guided data augmentation strategy to synthesize a balanced and diverse training dataset. We then streamline dialogue management via a selective generation scheme combined with a Chain-of-Thought (CoT) mechanism, which ensures output stability and effectively eliminates hallucinations in industrial settings. To facilitate continuous policy refinement with minimal manual effort, we design a cooperative iterative learning framework that leverages a dual-evaluator voting system. Deployed in production for two months, DuIVRS-2 processed 0.4 million calls daily and achieved a 83.9\% Task Success Rate (TSR), outperforming its predecessor by 4 percentage points while maintaining a low reaction time of 130ms. This work provides a production-proven reference for developing robust, cost-effective LLM agents for large-scale industrial dialogue applications.

Dayu Wang, Jiaye Yang, Weikang Li et al.

Large Language Models (LLMs) often suffer from ''Reasoning Collapse'' on challenging mathematical reasoning tasks, where stochastic sampling produces lexical variations of the same erroneous logic rather than genuine semantic exploration. We observe that failed reasoning traces are often associated with a low-rank bias manifold in the model's hidden-state geometry, which reduces exploration toward corrective solution directions. To address this, we propose Spectral Orthogonal Exploration (SOE), a geometric inference framework under a ''Student Guides Teacher'' paradigm. Instead of using a weak auxiliary agent for imitation, SOE uses it as an orthogonal probe to introduce semantically heterogeneous reasoning signals into the teacher's orthogonal complement of its dominant subspace. This intervention steers the teacher toward more diverse reasoning trajectories and improves exploration beyond standard sampling. Experiments on mathematical benchmarks show that SOE improves average accuracy by 62.4\% and average sampling efficiency by 113.7\% over baseline methods, suggesting that geometric interventions can be effective for mitigating reasoning collapse in mathematical reasoning. We further provide preliminary evidence that SOE is also effective on logic and code generation benchmarks.

Lingyong Yan, Jiulong Wu, Dong Xie et al.

Although recent end-to-end video generation models demonstrate impressive performance in visually oriented content creation, they remain limited in scenarios that require strict logical rigor and precise knowledge representation, such as instructional and educational media. To address this problem, we propose LAVES, a hierarchical LLM-based multi-agent system for generating high-quality instructional videos from educational problems. The LAVES formulates educational video generation as a multi-objective task that simultaneously demands correct step-by-step reasoning, pedagogically coherent narration, semantically faithful visual demonstrations, and precise audio--visual alignment. To address the limitations of prior approaches--including low procedural fidelity, high production cost, and limited controllability--LAVES decomposes the generation workflow into specialized agents coordinated by a central Orchestrating Agent with explicit quality gates and iterative critique mechanisms. Specifically, the Orchestrating Agent supervises a Solution Agent for rigorous problem solving, an Illustration Agent that produces executable visualization codes, and a Narration Agent for learner-oriented instructional scripts. In addition, all outputs from the working agents are subject to semantic critique, rule-based constraints, and tool-based compilation checks. Rather than directly synthesizing pixels, the system constructs a structured executable video script that is deterministically compiled into synchronized visuals and narration using template-driven assembly rules, enabling fully automated end-to-end production without manual editing. In large-scale deployments, LAVES achieves a throughput exceeding one million videos per day, delivering over a 95% reduction in cost compared to current industry-standard approaches while maintaining a high acceptance rate.

Yiqun Chen, Erhan Zhang, Lingyong Yan et al. · baidu

In question-answering (QA) systems, Retrieval-Augmented Generation (RAG) has become pivotal in enhancing response accuracy and reducing hallucination issues. The architecture of RAG systems varies significantly, encompassing single-round RAG, iterative RAG, and reasoning RAG, each tailored to address different types of queries. Due to the varying complexity of real-world queries, a fixed RAG pipeline often struggles to balance performance and cost efficiency across different queries. To address this challenge, we propose an adaptive RAG framework called MAO-ARAG, which leverages multi-agent orchestration. Our adaptive RAG is conceived as a multi-turn framework. Specifically, we define multiple executor agents, representing typical RAG modules such as query reformulation agents, document selection agent, and generation agents. A planner agent intelligently selects and integrates the appropriate agents from these executors into a suitable workflow tailored for each query, striving for high-quality answers while maintaining reasonable costs. During each turn, the planner agent is trained using reinforcement learning, guided by an outcome-based reward (F1 score) and a cost-based penalty, continuously improving answer quality while keeping costs within a reasonable range. Experiments conducted on multiple QA datasets demonstrate that our approach, which dynamically plans workflows for each query, not only achieves high answer quality but also maintains both cost and latency within acceptable limits.The code of MAO-ARAG is on https://github.com/chenyiqun/Agentic-RAG.

Hua Tang, Lingyong Yan, Yukun Zhao et al. · baidu

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks. Nevertheless, they still pose notable safety risks due to potential misuse for malicious purposes. Jailbreaking, which seeks to induce models to generate harmful content through single-turn or multi-turn attacks, plays a crucial role in uncovering underlying security vulnerabilities. However, prior methods, including sophisticated multi-turn approaches, often struggle to adapt to the evolving dynamics of dialogue as interactions progress. To address this challenge, we propose \ours (JailBreaking via \textbf{G}lobally \textbf{R}efining and \textbf{A}daptively \textbf{F}abricating), a novel multi-turn jailbreaking method that globally refines the attack trajectory at each interaction. In addition, we actively fabricate model responses to suppress safety-related warnings, thereby increasing the likelihood of eliciting harmful outputs in subsequent queries. Extensive experiments across six state-of-the-art LLMs demonstrate the superior effectiveness of our approach compared to existing single-turn and multi-turn jailbreaking methods. Our code will be released at https://github.com/Ytang520/Multi-Turn_jailbreaking_Global-Refinment_and_Active-Fabrication.

Jiulong Wu, Zhengliang Shi, Shuaiqiang Wang et al. · baidu

Large Visual Language Models (LVLMs) have demonstrated impressive capabilities across multiple tasks. However, their trustworthiness is often challenged by hallucinations, which can be attributed to the modality misalignment and the inherent hallucinations of their underlying Large Language Models (LLMs) backbone. Existing preference alignment methods focus on aligning model responses with human preferences while neglecting image-text modality alignment, resulting in over-reliance on LLMs and hallucinations. In this paper, we propose Entity-centric Multimodal Preference Optimization (EMPO), which achieves enhanced modality alignment compared to existing human preference alignment methods. Besides, to overcome the scarcity of high-quality multimodal preference data, we utilize open-source instruction datasets to automatically construct high-quality preference data across three aspects: image, instruction, and response. Experiments on two human preference datasets and five multimodal hallucination benchmarks demonstrate the effectiveness of EMPO, e.g., reducing hallucination rates by 85.9\% on Object-HalBench and 49.8\% on MM-HalBench.

Jizhou Huang, Brendan Juba

We study three problems that involve identifying homogeneous halfspaces under Gaussian distributions: agnostic learning, one-sided reliable learning, and fairness auditing. In each of these problems, we are given labeled examples $(\mathbf{x}, \mathrm{y})$ drawn from an unknown distribution on $\mathbb{R}^d\times\{-1, +1\}$, whose marginal distribution on $\mathbf{x}$ is standard Gaussian and on $\mathrm{y}$ is arbitrary. The goal of each problem is to output a homogeneous halfspace that approaches the best-fitting homogeneous halfspace in terms of its corresponding loss measure. We prove near-optimal computational hardness results for these problems under the widely believed hardness assumption of the Learning With Errors (LWE) problem. Prior hardness results for these problems were mostly established for general halfspaces; our findings extend some of these hardness results to homogeneous halfspaces. Remarkably, our lower bound strictly generalizes over prior works and narrows the gap between the upper and lower bounds for agnostically learning homogeneous halfspaces under Gaussian marginals.

Miao Fan, Jizhou Huang, Haifeng Wang · baidu

With the increased popularity of mobile devices, Web mapping services have become an indispensable tool in our daily lives. To provide user-satisfied services, such as location searches, the point of interest (POI) database is the fundamental infrastructure, as it archives multimodal information on billions of geographic locations closely related to people's lives, such as a shop or a bank. Therefore, verifying the correctness of a large-scale POI database is vital. To achieve this goal, many industrial companies adopt volunteered geographic information (VGI) platforms that enable thousands of crowdworkers and expert mappers to verify POIs seamlessly; but to do so, they have to spend millions of dollars every year. To save the tremendous labor costs, we devised DuMapper, an automatic system for large-scale POI verification with the multimodal street-view data at Baidu Maps. DuMapper takes the signboard image and the coordinates of a real-world place as input to generate a low-dimensional vector, which can be leveraged by ANN algorithms to conduct a more accurate search through billions of archived POIs in the database for verification within milliseconds. It can significantly increase the throughput of POI verification by $50$ times. DuMapper has already been deployed in production since \DuMPOnline, which dramatically improves the productivity and efficiency of POI verification at Baidu Maps. As of December 31, 2021, it has enacted over $405$ million iterations of POI verification within a 3.5-year period, representing an approximate workload of $800$ high-performance expert mappers.

Deguo Xia, Weiming Zhang, Xiyan Liu et al. · baidu, tsinghua

An up-to-date city-scale lane-level map is an indispensable infrastructure and a key enabling technology for ensuring the safety and user experience of autonomous driving systems. In industrial scenarios, reliance on manual annotation for map updates creates a critical bottleneck. Lane-level updates require precise change information and must ensure consistency with adjacent data while adhering to strict standards. Traditional methods utilize a three-stage approach-construction, change detection, and updating-which often necessitates manual verification due to accuracy limitations. This results in labor-intensive processes and hampers timely updates. To address these challenges, we propose LDMapNet-U, which implements a new end-to-end paradigm for city-scale lane-level map updating. By reconceptualizing the update task as an end-to-end map generation process grounded in historical map data, we introduce a paradigm shift in map updating that simultaneously generates vectorized maps and change information. To achieve this, a Prior-Map Encoding (PME) module is introduced to effectively encode historical maps, serving as a critical reference for detecting changes. Additionally, we incorporate a novel Instance Change Prediction (ICP) module that learns to predict associations with historical maps. Consequently, LDMapNet-U simultaneously achieves vectorized map element generation and change detection. To demonstrate the superiority and effectiveness of LDMapNet-U, extensive experiments are conducted using large-scale real-world datasets. In addition, LDMapNet-U has been successfully deployed in production at Baidu Maps since April 2024, supporting map updating for over 360 cities and significantly shortening the update cycle from quarterly to weekly. The updated maps serve hundreds of millions of users and are integrated into the autonomous driving systems of several leading vehicle companies.

Feifan Xia, Mingyang Liao, Yuyang Fang et al. · baidu, tsinghua

Traditional parameter-efficient fine-tuning (PEFT) methods such as LoRA are tightly coupled with the base model architecture, which constrains their applicability across heterogeneous pretrained large language models (LLMs). To address this limitation, we introduce Cross-LoRA, a data-free framework for transferring LoRA modules between diverse base models without requiring additional training data. Cross-LoRA consists of two key components: (a) LoRA-Align, which performs subspace alignment between source and target base models through rank-truncated singular value decomposition (SVD) and Frobenius-optimal linear transformation, ensuring compatibility under dimension mismatch; and (b) LoRA-Shift, which applies the aligned subspaces to project source LoRA weight updates into the target model parameter space. Both components are data-free, training-free, and enable lightweight adaptation on a commodity GPU in 20 minutes. Experiments on ARCs, OBOA and HellaSwag show that Cross-LoRA achieves relative gains of up to 5.26% over base models. Across other commonsense reasoning benchmarks, Cross-LoRA maintains performance comparable to that of directly trained LoRA adapters.

Miao Fan, Jizhou Huang, An Zhuo et al. · baidu

The value assessment of private properties is an attractive but challenging task which is widely concerned by a majority of people around the world. A prolonged topic among us is ``\textit{how much is my house worth?}''. To answer this question, most experienced agencies would like to price a property given the factors of its attributes as well as the demographics and the public facilities around it. However, no one knows the exact prices of these factors, especially the values of public facilities which may help assess private properties. In this paper, we introduce our newly launched project ``Monopoly'' (named after a classic board game) in which we propose a distributed approach for revaluing private properties by learning to price public facilities (such as hospitals etc.) with the large-scale urban data we have accumulated via Baidu Maps. To be specific, our method organizes many points of interest (POIs) into an undirected weighted graph and formulates multiple factors including the virtual prices of surrounding public facilities as adaptive variables to parallelly estimate the housing prices we know. Then the prices of both public facilities and private properties can be iteratively updated according to the loss of prediction until convergence. We have conducted extensive experiments with the large-scale urban data of several metropolises in China. Results show that our approach outperforms several mainstream methods with significant margins. Further insights from more in-depth discussions demonstrate that the ``Monopoly'' is an innovative application in the interdisciplinary field of business intelligence and urban computing, and it will be beneficial to tens of millions of our users for investments and to the governments for urban planning as well as taxation.

Wang Chen, Guanqiang Qi, Weikang Li et al. · baidu, tsinghua

Retrieval-Augmented Generation (RAG) has become a cornerstone technique for enhancing large language models (LLMs) with external knowledge. However, current RAG systems face two critical limitations: (1) they inefficiently retrieve information for every query, including simple questions that could be resolved using the LLM's parametric knowledge alone, and (2) they risk retrieving irrelevant documents when queries contain sparse information signals. To address these gaps, we introduce Parametric-verified Adaptive Information Retrieval and Selection (PAIRS), a training-free framework that integrates parametric and retrieved knowledge to adaptively determine whether to retrieve and how to select external information. Specifically, PAIRS employs a dual-path generation mechanism: First, the LLM produces both a direct answer and a context-augmented answer using self-generated pseudo-context. When these outputs converge, PAIRS bypasses external retrieval entirely, dramatically improving the RAG system's efficiency. For divergent cases, PAIRS activates a dual-path retrieval (DPR) process guided by both the original query and self-generated contextual signals, followed by an Adaptive Information Selection (AIS) module that filters documents through weighted similarity to both sources. This simple yet effective approach can not only enhance efficiency by eliminating unnecessary retrievals but also improve accuracy through contextually guided retrieval and adaptive information selection. Experimental results on six question-answering (QA) benchmarks show that PAIRS reduces retrieval costs by around 25% (triggering for only 75% of queries) while still improving accuracy-achieving +1.1% EM and +1.0% F1 over prior baselines on average.

Yucheng Shen, Jiulong Wu, Jizhou Huang et al.

Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents. To tackle complex queries requiring multi-step reasoning, agentic VRAG systems interleave reasoning with iterative retrieval.. However, existing agentic VRAG faces two critical bottlenecks. (1) Visual Evidence Sparsity: key evidence is scattered across pages yet processed in isolation, hindering cross-page reasoning; moreover, fine-grained intra-image evidence often requires precise visual actions, whose misuse degrades retrieval quality; (2) Search Drift in Long Horizons: the accumulation of visual tokens across retrieved pages dilutes context and causes cognitive overload, leading agents to deviate from their search objective. To address these challenges, we propose VISOR (Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning), a unified single-agent framework. VISOR features a structured Evidence Space for progressive cross-page reasoning, coupled with a Visual Action Evaluation and Correction mechanism to manage visual actions. Additionally, we introduce a Dynamic Trajectory with Sliding Window and Intent Injection to mitigate search drift. They anchor the evidence space while discarding earlier raw interactions, preventing context from being overwhelmed by visual tokens. We train VISOR using a Group Relative Policy Optimization-based Reinforcement Learning (GRPO-based RL) pipeline with state masking and credit assignment tailored for dynamic context reconstruction. Extensive experiments on ViDoSeek, SlideVQA, and MMLongBench demonstrate that VISOR achieves state-of-the-art performance with superior efficiency for long-horizon visual reasoning tasks.

Wang Chen, Wenhan Yu, Guanqiang Qi et al. · baidu, tsinghua

Retrieval-Augmented Generation (RAG) has become a core paradigm in document question answering tasks. However, existing methods have limitations when dealing with multimodal documents: one category of methods relies on layout analysis and text extraction, which can only utilize explicit text information and struggle to capture images or unstructured content; the other category treats document segmentation as visual input and directly passes it to visual language models (VLMs) for processing, yet it ignores the semantic advantages of text, leading to suboptimal retrieval and generation results. To address these research gaps, we propose the Co-Modality-based RAG (CMRAG) framework, which can simultaneously leverage texts and images for more accurate retrieval and generation. Our framework includes two key components: (1) a Unified Encoding Model (UEM) that projects queries, parsed text, and images into a shared embedding space via triplet-based training, and (2) a Unified Co-Modality-informed Retrieval (UCMR) method that statistically normalizes similarity scores to effectively fuse cross-modal signals. To support research in this direction, we further construct and release a large-scale triplet dataset of (query, text, image) examples. Experiments demonstrate that our proposed framework consistently outperforms single-modality--based RAG in multiple visual document question-answering (VDQA) benchmarks. The findings of this paper show that integrating co-modality information into the RAG framework in a unified manner is an effective approach to improving the performance of complex VDQA systems.

Jizhou Huang, Brendan Juba

We study ``selective'' or ``conditional'' classification problems under an agnostic setting. Classification tasks commonly focus on modeling the relationship between features and categories that captures the vast majority of data. In contrast to common machine learning frameworks, conditional classification intends to model such relationships only on a subset of the data defined by some selection rule. Most work on conditional classification either solves the problem in a realizable setting or does not guarantee the error is bounded compared to an optimal solution. In this work, we consider selective/conditional classification by sparse linear classifiers for subsets defined by halfspaces, and give both positive as well as negative results for Gaussian feature distributions. On the positive side, we present the first PAC-learning algorithm for homogeneous halfspace selectors with error guarantee $\bigO*{\sqrt{\mathrm{opt}}}$, where $\mathrm{opt}$ is the smallest conditional classification error over the given class of classifiers and homogeneous halfspaces. On the negative side, we find that, under cryptographic assumptions, approximating the conditional classification loss within a small additive error is computationally hard even under Gaussian distribution. We prove that approximating conditional classification is at least as hard as approximating agnostic classification in both additive and multiplicative form.

Daniel Hsu, Jizhou Huang, Brendan Juba

We study the problem of auditing classifiers with the notion of statistical subgroup fairness. Kearns et al. (2018) has shown that the problem of auditing combinatorial subgroups fairness is as hard as agnostic learning. Essentially all work on remedying statistical measures of discrimination against subgroups assumes access to an oracle for this problem, despite the fact that no efficient algorithms are known for it. If we assume the data distribution is Gaussian, or even merely log-concave, then a recent line of work has discovered efficient agnostic learning algorithms for halfspaces. Unfortunately, the reduction of Kearns et al. was formulated in terms of weak, "distribution-free" learning, and thus did not establish a connection for families such as log-concave distributions. In this work, we give positive and negative results on auditing for Gaussian distributions: On the positive side, we present an alternative approach to leverage these advances in agnostic learning and thereby obtain the first polynomial-time approximation scheme (PTAS) for auditing nontrivial combinatorial subgroup fairness: we show how to audit statistical notions of fairness over homogeneous halfspace subgroups when the features are Gaussian. On the negative side, we find that under cryptographic assumptions, no polynomial-time algorithm can guarantee any nontrivial auditing, even under Gaussian feature distributions, for general halfspace subgroups.

Wenhan Yu, Wang Chen, Guanqiang Qi et al.

Document Visual Question Answering (DocVQA) is a fundamental task for multimodal document understanding and a key testbed for vision language reasoning. However, most existing DocVQA datasets are limited to the page level and lack fine grained spatial grounding, constraining the interpretability and reasoning capability of Vision Language Models (VLMs). To address this gap, we introduce BBox DocVQA a large scale, bounding box grounded dataset designed to enhance spatial reasoning and evidence localization in visual documents. We further present an automated construction pipeline, Segment Judge and Generate, which integrates a segment model for region segmentation, a VLM for semantic judgment, and another advanced VLM for question answer generation, followed by human verification for quality assurance. The resulting dataset contains 3.6 K diverse documents and 32 K QA pairs, encompassing single and multi region as well as single and multi page scenarios. Each QA instance is grounded on explicit bounding boxes, enabling fine grained evaluation of spatial semantic alignment. Benchmarking multiple state of the art VLMs (e.g., GPT 5, Qwen2.5 VL, and InternVL) on BBox DocVQA reveals persistent challenges in spatial grounding and reasoning accuracy. Furthermore, fine tuning on BBox DocVQA substantially improves both bounding box localization and answer generation, validating its effectiveness for enhancing the reasoning ability of VLMs. Our dataset and code will be publicly released to advance research on interpretable and spatially grounded vision language reasoning.

Xin Shen, Rui Zhu, Lei Shen et al.

Understanding fine-grained human hand motion is fundamental to visual perception, embodied intelligence, and multimodal communication. In this work, we propose Fine-grained Finger-level Hand Motion Captioning (FingerCap), which aims to generate textual descriptions that capture detailed finger-level semantics of hand actions. To support this task, we curate FingerCap-40K, a large-scale corpus of 40K paired hand-motion videos and captions spanning two complementary sources: concise instruction-style finger motions and diverse, naturalistic hand-object interactions. To enable effective evaluation, we employ HandJudge, a LLM-based rubric that measures finger-level correctness and motion completeness. Temporal sparsity remains a fundamental bottleneck for current Video-MLLMs, since sparse RGB sampling is insufficient to capture the subtle, high-frequency dynamics underlying fine finger motions. As a simple and compute-friendly remedy, we introduce FiGOP (Finger Group-of-Pictures), which pairs each RGB keyframe with subsequent hand keypoints until the next keyframe. A lightweight temporal encoder converts the keypoints into motion embeddings and integrates them with RGB features. FiGOP adapts the classic GOP concept to finger motion, recovering fine temporal cues without increasing RGB density. Experiments on FingerCap-40K show that strong open- and closed-source Video-MLLMs still struggle with finger-level reasoning, while our FiGOP-augmented model yield consistent gains under HandJudge and human studies.

Feifan Xia, Yuyang Fang, Defang Li et al. · baidu, tsinghua

We present a probabilistic intent modeling framework for large language model (LLM) agents in multi-turn social dialogue. The framework maintains a belief distribution over a partner's latent intentions, initialized from contextual priors and dynamically updated through likelihood estimation after each utterance. The evolving distribution provides additional contextual grounding for the policy, enabling adaptive dialogue strategies under uncertainty. Preliminary experiments in the SOTOPIA environment show consistent improvements: the proposed framework increases the Overall score by 9.0% on SOTOPIA-All and 4.1% on SOTOPIA-Hard compared with the Qwen2.5-7B baseline, and slightly surpasses an oracle agent that directly observes partner intentions. These early results suggest that probabilistic intent modeling can contribute to the development of socially intelligent LLM agents.

Jizhou Huang, Brendan Juba

In machine learning applications, predictive models are trained to serve future queries across the entire data distribution. Real-world data often demands excessively complex models to achieve competitive performance, however, sacrificing interpretability. Hence, the growing deployment of machine learning models in high-stakes applications, such as healthcare, motivates the search for methods for accurate and explainable predictions. This work proposes a Personalized Prediction scheme, where an easy-to-interpret predictor is learned per query. In particular, we wish to produce a "sparse linear" classifier with competitive performance specifically on some sub-population that includes the query point. The goal of this work is to study the PAC-learnability of this prediction model for sub-populations represented by "halfspaces" in a label-agnostic setting. We first give a distribution-specific PAC-learning algorithm for learning reference classes for personalized prediction. By leveraging both the reference-class learning algorithm and a list learner of sparse linear representations, we prove the first upper bound, $O(\mathrm{opt}^{1/4} )$, for personalized prediction with sparse linear classifiers and homogeneous halfspace subsets. We also evaluate our algorithms on a variety of standard benchmark data sets.

Deguo Xia, Weiming Zhang, Xiyan Liu et al.

Generating city-scale lane-level maps faces significant challenges due to the intricate urban environments, such as blurred or absent lane markings. Additionally, a standard lane-level map requires a comprehensive organization of lane groupings, encompassing lane direction, style, boundary, and topology, yet has not been thoroughly examined in prior research. These obstacles result in labor-intensive human annotation and high maintenance costs. This paper overcomes these limitations and presents an industrial-grade solution named DuMapNet that outputs standardized, vectorized map elements and their topology in an end-to-end paradigm. To this end, we propose a group-wise lane prediction (GLP) system that outputs vectorized results of lane groups by meticulously tailoring a transformer-based network. Meanwhile, to enhance generalization in challenging scenarios, such as road wear and occlusions, as well as to improve global consistency, a contextual prompts encoder (CPE) module is proposed, which leverages the predicted results of spatial neighborhoods as contextual information. Extensive experiments conducted on large-scale real-world datasets demonstrate the superiority and effectiveness of DuMapNet. Additionally, DuMap-Net has already been deployed in production at Baidu Maps since June 2023, supporting lane-level map generation tasks for over 360 cities while bringing a 95% reduction in costs. This demonstrates that DuMapNet serves as a practical and cost-effective industrial solution for city-scale lane-level map generation.

Linlang Jiang, Jingbo Zhou, Tong Xu et al.

Trip recommender system, which targets at recommending a trip consisting of several ordered Points of Interest (POIs), has long been treated as an important application for many location-based services. Currently, most prior arts generate trips following pre-defined objectives based on constraint programming, which may fail to reflect the complex latent patterns hidden in the human mobility data. And most of these methods are usually difficult to respond in real time when the number of POIs is large. To that end, we propose an Adversarial Neural Trip Recommendation (ANT) framework to tackle the above challenges. First of all, we devise a novel attention-based encoder-decoder trip generator that can learn the correlations among POIs and generate well-designed trips under given constraints. Another novelty of ANT relies on an adversarial learning strategy integrating with reinforcement learning to guide the trip generator to produce high-quality trips. For this purpose, we introduce a discriminator, which distinguishes the generated trips from real-life trips taken by users, to provide reward signals to optimize the generator. Moreover, we devise a novel pre-train schema based on learning from demonstration, which speeds up the convergence to achieve a sufficient-and-efficient training process. Extensive experiments on four real-world datasets validate the effectiveness and efficiency of our proposed ANT framework, which demonstrates that ANT could remarkably outperform the state-of-the-art baselines with short response time.

Yibo Sun, Jizhou Huang, Chunyuan Yuan et al.

Providing timely accessibility reminders of a point-of-interest (POI) plays a vital role in improving user satisfaction of finding places and making visiting decisions. However, it is difficult to keep the POI database in sync with the real-world counterparts due to the dynamic nature of business changes. To alleviate this problem, we formulate and present a practical solution that jointly extracts POI mentions and identifies their coupled accessibility labels from unstructured text. We approach this task as a sequence tagging problem, where the goal is to produce <POI name, accessibility label> pairs from unstructured text. This task is challenging because of two main issues: (1) POI names are often newly-coined words so as to successfully register new entities or brands and (2) there may exist multiple pairs in the text, which necessitates dealing with one-to-many or many-to-one mapping to make each POI coupled with its accessibility label. To this end, we propose a Geographic-Enhanced and Dependency-guIded sequence Tagging (GEDIT) model to concurrently address the two challenges. First, to alleviate challenge #1, we develop a geographic-enhanced pre-trained model to learn the text representations. Second, to mitigate challenge #2, we apply a relational graph convolutional network to learn the tree node representations from the parsed dependency tree. Finally, we construct a neural sequence tagging model by integrating and feeding the previously pre-learned representations into a CRF layer. Extensive experiments conducted on a real-world dataset demonstrate the superiority and effectiveness of GEDIT. In addition, it has already been deployed in production at Baidu Maps. Statistics show that the proposed solution can save significant human effort and labor costs to deal with the same amount of documents, which confirms that it is a practical way for POI accessibility maintenance.

Min Yang, Dongliang He, Miao Fan et al.

Image Retrieval is a fundamental task of obtaining images similar to the query one from a database. A common image retrieval practice is to firstly retrieve candidate images via similarity search using global image features and then re-rank the candidates by leveraging their local features. Previous learning-based studies mainly focus on either global or local image representation learning to tackle the retrieval task. In this paper, we abandon the two-stage paradigm and seek to design an effective single-stage solution by integrating local and global information inside images into compact image representations. Specifically, we propose a Deep Orthogonal Local and Global (DOLG) information fusion framework for end-to-end image retrieval. It attentively extracts representative local information with multi-atrous convolutions and self-attention at first. Components orthogonal to the global image representation are then extracted from the local information. At last, the orthogonal components are concatenated with the global representation as a complementary, and then aggregation is performed to generate the final representation. The whole framework is end-to-end differentiable and can be trained with image-level labels. Extensive experimental results validate the effectiveness of our solution and show that our model achieves state-of-the-art image retrieval performances on Revisited Oxford and Paris datasets.

Ji Liu, Jizhou Huang, Yang Zhou et al.

In recent years, data and computing resources are typically distributed in the devices of end users, various regions or organizations. Because of laws or regulations, the distributed data and computing resources cannot be directly shared among different regions or organizations for machine learning tasks. Federated learning emerges as an efficient approach to exploit distributed data and computing resources, so as to collaboratively train machine learning models, while obeying the laws and regulations and ensuring data security and data privacy. In this paper, we provide a comprehensive survey of existing works for federated learning. We propose a functional architecture of federated learning systems and a taxonomy of related techniques. Furthermore, we present the distributed training, data communication, and security of FL systems. Finally, we analyze their limitations and propose future research directions.

Cheng Cui, Ruoyu Guo, Yuning Du et al.

Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the community and are proven to be of great potential in obtaining a powerful pre-trained model. However, these models require huge training costs (i.e., hundreds of millions of images or training iterations). In this paper, we propose to improve existing baseline networks via knowledge distillation from off-the-shelf pre-trained big powerful models. Different from existing knowledge distillation frameworks which require student model to be consistent with both soft-label generated by teacher model and hard-label annotated by humans, our solution performs distillation by only driving prediction of the student model consistent with that of the teacher model. Therefore, our distillation setting can get rid of manually labeled data and can be trained with extra unlabeled data to fully exploit capability of teacher model for better learning. We empirically find that such simple distillation settings perform extremely effective, for example, the top-1 accuracy on ImageNet-1k validation set of MobileNetV3-large and ResNet50-D can be significantly improved from 75.2% to 79% and 79.1% to 83%, respectively. We have also thoroughly analyzed what are dominant factors that affect the distillation performance and how they make a difference. Extensive downstream computer vision tasks, including transfer learning, object detection and semantic segmentation, can significantly benefit from the distilled pretrained models. All our experiments are implemented based on PaddlePaddle, codes and a series of improved pretrained models with ssld suffix are available in PaddleClas.

Congxi Xiao, Jingbo Zhou, Jizhou Huang et al.

The novel coronavirus disease (COVID-19) has crushed daily routines and is still rampaging through the world. Existing solution for nonpharmaceutical interventions usually needs to timely and precisely select a subset of residential urban areas for containment or even quarantine, where the spatial distribution of confirmed cases has been considered as a key criterion for the subset selection. While such containment measure has successfully stopped or slowed down the spread of COVID-19 in some countries, it is criticized for being inefficient or ineffective, as the statistics of confirmed cases are usually time-delayed and coarse-grained. To tackle the issues, we propose C-Watcher, a novel data-driven framework that aims at screening every neighborhood in a target city and predicting infection risks, prior to the spread of COVID-19 from epicenters to the city. In terms of design, C-Watcher collects large-scale long-term human mobility data from Baidu Maps, then characterizes every residential neighborhood in the city using a set of features based on urban mobility patterns. Furthermore, to transfer the firsthand knowledge (witted in epicenters) to the target city before local outbreaks, we adopt a novel adversarial encoder framework to learn "city-invariant" representations from the mobility-related features for precise early detection of high-risk neighborhoods, even before any confirmed cases known, in the target city. We carried out extensive experiments on C-Watcher using the real-data records in the early stage of COVID-19 outbreaks, where the results demonstrate the efficiency and effectiveness of C-Watcher for early detection of high-risk neighborhoods from a large number of cities.

Dongliang He, Xiang Zhao, Jizhou Huang et al.

The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or exhaustively ranking all possible clip-sentence pairs in a pre-segmented video, which inevitably suffer from exhaustively enumerated candidates. To alleviate this problem, we formulate this task as a problem of sequential decision making by learning an agent which regulates the temporal grounding boundaries progressively based on its policy. Specifically, we propose a reinforcement learning based framework improved by multi-task learning and it shows steady performance gains by considering additional supervised boundary information during training. Our proposed framework achieves state-of-the-art performance on ActivityNet'18 DenseCaption dataset and Charades-STA dataset while observing only 10 or less clips per video.