Jizhou Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jizhou Huang has a total of 140 co-authors. Here are the top co-authors by number of shared publications:
Haifeng Wang
Baidu, Inc., Beijing, Beijing, China
11 shared publications- Jingbo Zhou
Frontier Research Department, Baidu Inc., Beijing, China
8 shared publications Miao Fan
Baidu Inc., Beijing, China
7 shared publications- Dejing Dou
Baidu Inc., Beijing, China
6 shared publications - Haifeng Wang
Baidu Inc., Beijing, China
6 shared publications Ying Li
Baidu Inc., Beijing, China
6 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8722-8730
VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8722-8730
Open AccessVISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8369-8378
Beyond End-to-End Video Models: An LLM-Based Multi-Agent System for Educational Video Generation
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8369-8378
Open AccessBeyond End-to-End Video Models: An LLM-Based Multi-Agent System for Educational Video Generation
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8289-8300
MapAgent: An Industrial-Grade Agentic Framework for City-scale Lane-level Map Generation
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8289-8300
Open AccessMapAgent: An Industrial-Grade Agentic Framework for City-scale Lane-level Map Generation
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7935-7946
DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolution
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7935-7946
Open AccessDuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolution
- Open Access
Probabilistic Modeling of Intentions in Socially Intelligent LLM Agents
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.
Open AccessProbabilistic Modeling of Intentions in Socially Intelligent LLM Agents
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.
- Open Access
Cross-LoRA: A Data-Free LoRA Transfer Framework across Heterogeneous LLMs
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.
Open AccessCross-LoRA: A Data-Free LoRA Transfer Framework across Heterogeneous LLMs
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.
- Open Access
PAIRS: Parametric-Verified Adaptive Information Retrieval and Selection for Efficient RAG
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.
Open AccessPAIRS: Parametric-Verified Adaptive Information Retrieval and Selection for Efficient RAG
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.
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2693-2702
LDMapNet-U: An End-to-End System for City-Scale Lane-Level Map Updating
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2693-2702
Open AccessLDMapNet-U: An End-to-End System for City-Scale Lane-Level Map Updating
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 3527-3538
ReFound: Crafting a Foundation Model for Urban Region Understanding upon Language and Visual Foundations
Understanding urban regional characteristics is pivotal in driving critical insights for urban planning and management. We have witnessed the successful application of pre-trained Foundation Models (FMs) in generating universal representations for various downstream tasks. However, applying this principle to the geospatial domain remains challenging, primarily due to the difficulty of gathering extensive data for developing a dedicated urban foundation model. Though there have been some attempts to empower the existing FMs with urban data, most of them focus on single-modality FMs without considering the multi-modality nature of urban region understanding tasks. To address this gap, we introduce ReFound - a novel framework for Re-training a Foundation model for urban region understanding, harnessing the strengths of both language and visual FMs. In this framework, we first invent a Mixture-of-Geospatial-Expert (MoGE) Transformer, to effectively integrate the embedding of multi-source geospatial data. Building on this, ReFound is enhanced by jointly distilling knowledge from language, visual, and visual-language FMs respectively, thus augmenting its generalization capabilities. Meanwhile, we design a masked geospatial data modeling approach alongside a cross-modal spatial alignment mechanism, to enhance the spatial knowledge of ReFound derived from geospatial data. Extensive experiments conducted on six real-world datasets over three urban region understanding tasks demonstrate the superior performance of our framework.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 3527-3538
Open AccessReFound: Crafting a Foundation Model for Urban Region Understanding upon Language and Visual Foundations
Understanding urban regional characteristics is pivotal in driving critical insights for urban planning and management. We have witnessed the successful application of pre-trained Foundation Models (FMs) in generating universal representations for various downstream tasks. However, applying this principle to the geospatial domain remains challenging, primarily due to the difficulty of gathering extensive data for developing a dedicated urban foundation model. Though there have been some attempts to empower the existing FMs with urban data, most of them focus on single-modality FMs without considering the multi-modality nature of urban region understanding tasks. To address this gap, we introduce ReFound - a novel framework for Re-training a Foundation model for urban region understanding, harnessing the strengths of both language and visual FMs. In this framework, we first invent a Mixture-of-Geospatial-Expert (MoGE) Transformer, to effectively integrate the embedding of multi-source geospatial data. Building on this, ReFound is enhanced by jointly distilling knowledge from language, visual, and visual-language FMs respectively, thus augmenting its generalization capabilities. Meanwhile, we design a masked geospatial data modeling approach alongside a cross-modal spatial alignment mechanism, to enhance the spatial knowledge of ReFound derived from geospatial data. Extensive experiments conducted on six real-world datasets over three urban region understanding tasks demonstrate the superior performance of our framework.
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 6015-6024
DuMapNet: An End-to-End Vectorization System for City-Scale Lane-Level Map Generation
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, DuMapNet 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.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 6015-6024
Open AccessDuMapNet: An End-to-End Vectorization System for City-Scale Lane-Level Map Generation
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, DuMapNet 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.