Author name cluster

Haonan Lu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

1 author row

AAAI Conference 2026 Conference Paper

Aligning Cross-View Visual Geometries in LVLMs Through Human-Like Reasoning Learning

Yuming Qiao
Liang Luo
Dan Meng
Yifan Yang
Qingyuan Wang
Juntuo Wang
Yuwei Zhang
Ru Zhen

Spatial understanding is a critical capability for LVLMs (Large Vision-Language Models) to advance embodied AI applications. Existing works primarily focus on enhancing spatial understanding within a single frame, i.e., injecting 3D spatial concepts into LVLMs under single coordinate system. However, such improvements struggle in real-world tasks that require consistent cross-view spatial reasoning. In this paper, we propose CVVG-Reasoner(Cross-View Visual Geometries) that lifts single-frame spatial comprehension to unified cross-view spatial understanding by mimicking human-like cross-view reasoning mechanisms. First, we introduce MV3DSR(Multi-View 3D Spatial Reasoning), a scalable pipeline for cross-view spatial reasoning data generation, and construct MV3DSR-Dataset, a large-scale dataset with diverse 3D cross-view reasoning tasks. Based on MV3DSR, we propose MV3DSR-Bench, a comprehensive benchmark for evaluating cross-view spatial reasoning capabilities. Second, we design a three-stage training strategy: the first two stages progressively equip the model with (1) fundamental spatial knowledge and (2) human-like cross-view reasoning patterns, while the final stage employs reinforcement learning to further boost its performance. Extensive experiments demonstrate that our CVVG-Reasoner significantly outperforms existing 3D LLMs(Large Language Models) and advanced LVLMs in cross-view tasks while maintaining robust performance on out-of-domain data. Ablations further reveal that injecting human-like reasoning patterns yields 44% performance gain, validating the effectiveness of our design.

PDF Details DOI

AAAI Conference 2026 Conference Paper

DRIFT: Difference-Aware Reinforcement Through Iterative Fine-Tuning for Language Model

Wenjie Liao
Xiaohui Song
Haonan Lu

Self-play fine-tuning has emerged as a promising approach to improve Large Language Models (LLMs) without additional human annotations. However, existing methods struggle with complex generation tasks requiring long context understanding, where models produce partially correct outputs interleaved with errors. Traditional approaches train on entire sequences uniformly, failing to distinguish between well-predicted and erroneous regions, leading to diluted learning signals and slow convergence. We propose DRIFT (Difference-aware Reinforcement through Iterative Fine-Tuning), a novel self-play framework that selectively trains on prediction differences. DRIFT introduces two key innovations: (1) Difference-Aware Masking (DAM) that identifies and masks common subsequences between model outputs and ground truth, focusing training exclusively on error regions; (2) Occurrence-Aware Loss (OAL) that provides position-invariant vocabulary supervision, complementing the position-sensitive adversarial loss. This dual mechanism enables models to correct both positional and lexical errors effectively. Theoretically, we prove that DRIFT converges when masked distributions align. Empirically, we evaluate DRIFT on diverse summarization benchmarks using Qwen2.5-3B and LLaMA-3.1-8B models. Results show that DRIFT significantly outperforms both supervised fine-tuning (SFT) and self-play fine-tuning (SPIN), achieving up to 16\% improvement on SAMSum dialogue summarization tasks while maintaining general capabilities. Notably, DRIFT breaks the performance ceiling of continued SFT and demonstrates superior efficiency compared to holistic self-play methods, validating that targeted optimization on prediction differences is crucial for structured text generation tasks.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile Automation

Yuxiang Zhou
Jichang Li
Yanhao Zhang
Haonan Lu
Guanbin Li

Mobile agents show immense potential, yet current state-of-the-art (SoTA) agents exhibit inadequate success rates on real-world, long-horizon, cross-application tasks. We attribute this bottleneck to the agents' excessive reliance on static, internal knowledge within MLLMs, which leads to two critical failure points: 1) strategic hallucinations in high-level planning and 2) operational errors during low-level execution on user interfaces (UI). The core insight of this paper is that high-level planning and low-level UI operations require fundamentally distinct types of knowledge. Planning demands high-level, strategy-oriented experiences, whereas operations necessitate low-level, precise instructions closely tied to specific app UIs. Motivated by these insights, we propose Mobile-Agent-RAG, a novel hierarchical multi-agent framework that innovatively integrates dual-level retrieval augmentation. At the planning stage, we introduce Manager-RAG to reduce strategic hallucinations by retrieving human-validated comprehensive task plans that provide high-level guidance. At the execution stage, we develop Operator-RAG to improve execution accuracy by retrieving the most precise low-level guidance for accurate atomic actions, aligned with the current app and subtask. To accurately deliver these knowledge types, we construct two specialized retrieval-oriented knowledge bases. Furthermore, we introduce Mobile-Eval-RAG, a challenging benchmark for evaluating such agents on realistic multi-app, long-horizon tasks. Extensive experiments demonstrate that Mobile-Agent-RAG significantly outperforms SoTA baselines, improving task completion rate by 11.0% and step efficiency by 10.2%, establishing a robust paradigm for context-aware, reliable multi-agent mobile automation.

PDF Details DOI

AAAI Conference 2026 Conference Paper

OwlCap: Harmonizing Motion-Detail for Video Captioning via HMD-270K and Caption Set Equivalence Reward

Chunlin Zhong
Qiuxia Hou
Zhangjun Zhou
Yanhao Zhang
Shuang Hao
Haonan Lu
He Tang
Xiang Bai

Video captioning aims to generate comprehensive and coherent descriptions of the video content, contributing to the advancement of both video understanding and generation. However, existing methods often suffer from motion-detail imbalance, as models tend to overemphasize one aspect while neglecting the other. This imbalance results in incomplete captions, which in turn leads to a lack of consistency in video understanding and generation. To address this issue, we propose solutions from two aspects: 1) Data aspect: We constructed the Harmonizing Motion-Detail 270K (HMD-270K) dataset through a two-stage pipeline: Motion-Detail Fusion (MDF) and Fine-Grained Examination (FGE). 2) Optimization aspect: We introduce the Caption Set Equivalence Reward (CSER) based on Group Relative Policy Optimization (GRPO). CSER enhances completeness and accuracy in capturing both motion and details through unit-to-set matching and bidirectional validation. Based on the HMD-270K supervised fine-tuning and GRPO post-training with CSER, we developed OwlCap, a powerful video captioning Multi-modal Large Language Model (MLLM) with motion-detail balance. Experimental results demonstrate that OwlCap achieves significant improvements compared to baseline models on two benchmarks: the detail-focused VDC (+4.2 Acc) and the motion-focused DREAM-1K (+4.6 F1).

PDF Details DOI

AAAI Conference 2026 Conference Paper

X2Edit: Revisiting Arbitrary-Instruction Image Editing Through Self-Constructed Data and Task-Aware Representation Learning

Jian Ma
Xujie Zhu
Zihao Pan
Qirong Peng
Xu Guo
Chen Chen
Haonan Lu

Existing open-source datasets for arbitrary-instruction image editing remain suboptimal, while a plug-and-play editing module compatible with community-prevalent generative models is notably absent. In this paper, we first introduce the X2Edit Dataset, a comprehensive dataset covering 14 diverse editing tasks, including subject-driven generation. We utilize the industry-leading unified image generation models and expert models to construct the data. Meanwhile, we design reasonable editing instructions with the VLM and implement various scoring mechanisms to filter the data. As a result, we construct 3.7 million high-quality data with balanced categories. Second, to better integrate seamlessly with community image generation models, we design task-aware MoE-LoRA training based on FLUX.1, with only 8% of the parameters of the full model. To further improve the final performance, we utilize the internal representations of the diffusion model and define positive/negative samples based on image editing types to introduce contrastive learning. Extensive experiments demonstrate that the model's editing performance is competitive among many excellent models. Additionally, the constructed dataset exhibits substantial advantages over existing open-source datasets.

PDF Details DOI

AAAI Conference 2025 Conference Paper

GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models

Jian Ma
Yonglin Deng
Chen Chen
Nanyang Du
Haonan Lu
Zhenyu Yang

Posters serve an essential function in marketing and advertising by improving visual communication and brand visibility, thus significantly contributing to industrial design. With the latest developments in controllable T2I diffusion models, research interest has surged in text rendering within synthesized images. Although text rendering accuracy has seen advancements, automatic poster generation remains a relatively untapped area. This paper presents an automatic poster generation framework featuring text rendering capabilities through the use of LLMs. Our framework employs a triple-cross attention mechanism based on alignment learning to achieve precise text placement within detailed contextual backgrounds. Moreover, it supports adjustable fonts, varying image resolutions, and poster rendering with textual prompts in both English and Chinese. Additionally, we present a comprehensive bilingual image-text dataset, GlyphDraw-3M, comprising 3 million image-text pairs, each with OCR annotations and resolutions exceeding 1024. Our method utilizes the SDXL architecture, and extensive experiments confirm its ability to generate posters with intricate and context-rich backgrounds.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

InstructHOI: Context-Aware Instruction for Multi-Modal Reasoning in Human-Object Interaction Detection

Jinguo Luo
Weihong Ren
Quanlong Zheng
Yanhao Zhang
Zhenlong Yuan
Zhiyong Wang
Haonan Lu
Honghai Liu

Recently, Large Foundation Models (LFMs), e. g. , CLIP and GPT, have significantly advanced the Human-Object Interaction (HOI) detection, due to their superior generalization and transferability. Prior HOI detectors typically employ single- or multi-modal prompts to generate discriminative representations for HOIs from pretrained LFMs. However, such prompt-based approaches focus on transferring HOI-specific knowledge, but unexplore the potential reasoning capabilities of LFMs, which can provide informative context for ambiguous and open-world interaction recognition. In this paper, we propose InstructHOI, a novel method that leverages context-aware instructions to guide multi-modal reasoning for HOI detection. Specifically, to bridge knowledge gap and enhance reasoning abilities, we first perform HOI-domain fine-tuning on a pretrained multi-modal LFM, using a generated dataset with 140K interaction-reasoning image-text pairs. Then, we develop a Context-aware Instruction Generator (CIG) to guide interaction reasoning. Unlike traditional language-only instructions, CIG first mines visual interactive context at the human-object level, which is then fused with linguistic instructions, forming multi-modal reasoning guidance. Furthermore, an Interest Token Selector (ITS) is adopted to adaptively filter image tokens based on context-aware instructions, thereby aligning reasoning process with interaction regions. Extensive experiments on two public benchmarks demonstrate that our proposed method outperforms the state-of-the-art ones, under both supervised and zero-shot settings.

PDF Details

IJCAI Conference 2025 Conference Paper

MsRAG: Knowledge Augumented Image Captioning with Object-level Multi-source RAG

Yuming Qiao
Yuechen Wang
Dan Meng
Haonan Lu
Zhenyu Yang
Xudong Zhang

Language-Visual Large Models (LVLMs) have made significant strides in enhancing visual understanding capabilities. However, these models often struggle with knowledge-based visual tasks due to constrains in their pre-training data scope and timeliness. Existing Retrieval-Augmented Generation (RAG) methods can effectively solve the problem but primarily rely on user queries, limiting their applicability in scenarios without explicit language input. To overcome these challenges, we introduce MsRAG, a knowledge-augmented captioning framework designed to effectively retrieve and utilize external real-world knowledge, particularly in the absence of user queries, and perform dense captioning for subjects. MsRAG comprises three key components: (1) Parallel Visual Search Module. It retrieves fine-grained object-level knowledge using both online visual search engines and offline domain-knowledge databases, enhancing the robustness and richness of retrieved information. (2) Prompt Templates Pool. The prompt pool dynamically assigns appropriate prompts based on retrieved information, optimizing LVLMs' ability to leverage relevant data under complex RAG conditions. (3) Visual-RAG Alignment Module, which employs a novel visual prompting method to bridge the modality gap between textual RAG content and corresponding visual objects, enabling precise alignment of visual elements with their text-format RAG content. To validate the effectiveness of MsRAG, we conducted a series of qualitative and quantitative experiments. The evaluation results demonstrate the superiority of MsRAG over other methods.

PDF Details DOI

AAAI Conference 2025 Conference Paper

SCott: Accelerating Diffusion Models with Stochastic Consistency Distillation

Hongjian Liu
Qingsong Xie
Tianxiang Ye
Zhijie Deng
Chen Chen
Shixiang Tang
Xueyang Fu
Haonan Lu

The iterative sampling procedure employed by diffusion models (DMs) often leads to significant latency. To address this, we propose Stochastic Consistency Distillation (SCott) to enable accelerated text-to-image generation, where high-quality generations can be achieved with just 2-4 sampling steps or even1 step, and further improvements can be obtained by additional cost, e.g., 4 steps. In contrast to vanilla consistency distillation (CD) which distills the ordinary differential equation solvers-based sampling process of a pre-trained teacher model into a student, SCott explores the possibility and validates the efficacy of integrating stochastic differential equation (SDE) solvers into CD to fully unleash the potential of the teacher. SCott is augmented with elaborate strategies to control the noise strength and sampling process of the SDE solver. An adversarial loss is further incorporated to strengthen the sample quality with rare sampling steps. Empirically, on the MSCOCO-2017 5K dataset with a Stable Diffusion-V1.5 teacher, SCott achieves an FID of 21.9, surpassing that of the 1-step InstaFlow (23.4) and the 4-step UFOGen (22.1). Moreover, SCott can yield more diverse samples than other consistency models for high-resolution image generation, with up to 16% improvement in a qualified metric.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models

Ruichen Wang
Zekang Chen
Chen Chen
Jian Ma
Haonan Lu
Xiaodong Lin

Recent text-to-image (T2I) diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, they fail to semantically align the generated images with the prompts due to their limited compositional capabilities, leading to attribute leakage, entity leakage, and missing entities. In this paper, we propose a novel attention mask control strategy based on predicted object boxes to address these issues. In particular, we first train a BoxNet to predict a box for each entity that possesses the attribute specified in the prompt. Then, depending on the predicted boxes, a unique mask control is applied to the cross- and self-attention maps. Our approach produces a more semantically accurate synthesis by constraining the attention regions of each token in the prompt to the image. In addition, the proposed method is straightforward and effective and can be readily integrated into existing cross-attention-based T2I generators. We compare our approach to competing methods and demonstrate that it can faithfully convey the semantics of the original text to the generated content and achieve high availability as a ready-to-use plugin. Please refer to https://github.com/OPPO-Mente-Lab/attention-mask-control.

PDF Details DOI