Heng Wang

AAAI Conference 2026 Conference Paper

Gotta Hear Them All: Towards Sound Source Aware Audio Generation

• Wei Guo
• Heng Wang
• Jianbo Ma
• Weidong Cai

Audio synthesis has broad applications in multimedia. Recent advancements have made it possible to generate relevant audios from inputs describing an audio scene, such as images or texts. However, the immersiveness and expressiveness of the generation are limited. One possible problem is that existing methods solely rely on the global scene and overlook details of local sounding objects (i.e., sound sources). To address this issue, we propose a Sound Source-Aware Audio (SS2A) generator. SS2A is able to locally perceive multimodal sound sources from a scene with visual detection and cross-modality translation. It then contrastively learns a Cross-Modal Sound Source (CMSS) Manifold to semantically disambiguate each source. Finally, we attentively mix their CMSS semantics into a rich audio representation, from which a pretrained audio generator outputs the sound. To model the CMSS manifold, we curate a novel single-sound-source visual-audio dataset VGGS3 from VGGSound. We also design a Sound Source Matching Score to clearly measure localized audio relevance. With the effectiveness of explicit sound source modeling, SS2A achieves state-of-the-art performance in extensive image-to-audio tasks. We also qualitatively demonstrate SS2A's ability to achieve intuitive synthesis control by compositing vision, text, and audio conditions. Furthermore, we show that our sound source modeling can achieve competitive video-to-audio performance with a straightforward temporal aggregation mechanism.

AAAI Conference 2026 Conference Paper

Improving Implicit Discourse Relation Recognition with Natural Language Explanations from LLMs

• Heng Wang
• Changxing Wu

Implicit Discourse Relation Recognition (IDRR) remains a challenging task due to the requirement for deep semantic understanding in the absence of explicit discourse markers. A further limitation is that existing methods only predict relations without providing any supporting explanations. Recent advances in large language models (LLMs) have shown strong reasoning capabilities in both deep language understanding and natural language explanation generation. In this work, we propose a simple yet effective approach to distill the reasoning capabilities of LLMs into lightweight IDRR models to improve both performance and interpretability. Specifically, we first prompt an LLM to generate explanations for each training instance conditioned on its gold label. Then, we introduce a novel classification-generation framework that jointly performs relation prediction and explanation generation, and train it with the additional supervision of LLM-generated explanations. Our framework is plug-and-play, enabling easy integration with most existing IDRR models. Experimental results on PDTB demonstrate that our approach significantly improves IDRR performance, while human evaluation further confirms that the generated explanations enhance model interpretability. Furthermore, we validate the generality of our approach on sentiment classification and natural language inference.

EAAI Journal 2025 Journal Article

Adaptive multimodal control of trans-media vehicle based on deep reinforcement learning

• Jingkang Wang
• Shuang Liang
• Mingming Guo
• Heng Wang
• Hua Zhang

ICLR Conference 2025 Conference Paper

Autoregressive Pretraining with Mamba in Vision

• Sucheng Ren
• Xianhang Li
• Haoqin Tu
• Feng Wang
• Fangxun Shu
• Lei Zhang
• Jieru Mei
• Linjie Yang

The vision community has started to build with the recently developed state space model, Mamba, as the new backbone for a range of tasks. This paper shows that Mamba's visual capability can be significantly enhanced through autoregressive pretraining, a direction not previously explored. Efficiency-wise, the autoregressive nature can well capitalize on the Mamba's unidirectional recurrent structure, enabling faster overall training speed compared to other training strategies like mask modeling. Performance-wise, autoregressive pretraining equips the Mamba architecture with markedly higher accuracy over its supervised-trained counterparts and, more importantly, successfully unlocks its scaling potential to large and even huge model sizes. For example, with autoregressive pretraining, a base-size Mamba attains 83.2\% ImageNet accuracy, outperforming its supervised counterpart by 2.0\%; our huge-size Mamba, the largest Vision Mamba to date, attains 85.0\% ImageNet accuracy (85.5\% when finetuned with $384\times384$ inputs), notably surpassing all other Mamba variants in vision. The code is available at \url{https://github.com/OliverRensu/ARM}.

ICML Conference 2025 Conference Paper

CoSER: Coordinating LLM-Based Persona Simulation of Established Roles

• Xintao Wang 0001
• Heng Wang
• Yifei Zhang
• Xinfeng Yuan
• Rui Xu 0026
• Jen-tse Huang 0001
• Siyu Yuan
• Haoran Guo

Role-playing language agents (RPLAs) have emerged as promising applications of large language models (LLMs). However, simulating established characters presents a challenging task for RPLAs, due to the lack of authentic character datasets and nuanced evaluation methods using such data. In this paper, we present CoSER, a collection of a high-quality dataset, open models, and an evaluation protocol towards effective RPLAs of established characters. The CoSER dataset covers 17, 966 characters from 771 renowned books. It provides authentic dialogues with real-world intricacies, as well as diverse data types such as character experiences and internal thoughts. Drawing from acting methodology, we introduce given-circumstance acting for training and evaluating role-playing LLMs, where LLMs sequentially portray multiple characters in book scenes. Using our dataset, we develop CoSER 8B and CoSER 70B, i. e. , advanced open role-playing LLMs built on LLaMA-3. 1 models. Extensive experiments demonstrate the value of the CoSER dataset for RPLA training, evaluation and retrieval. Moreover, CoSER 70B exhibits state-of-the-art performance surpassing or matching GPT-4o on our evaluation and three existing benchmarks, i. e. , achieving 75. 80% and 93. 47% accuracy on the InCharacter and LifeChoice benchmarks respectively. Our code, dataset and models are available at: https: //github. com/Neph0s/CoSER.

ICLR Conference 2025 Conference Paper

HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing

• Mude Hui
• Siwei Yang
• Bingchen Zhao
• Yichun Shi
• Heng Wang
• Peng Wang 0001
• Cihang Xie
• Yuyin Zhou

This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with around 200,000 edits. Unlike prior approaches relying on attribute guidance or human feedback on building datasets, we devise a scalable data collection pipeline leveraging advanced foundation models, namely GPT-4V and DALL-E 3. To ensure its high quality, diverse examples are first collected online, expanded, and then used to create high-quality diptychs featuring input and output images with detailed text prompts, followed by precise alignment ensured through post-processing. In addition, we propose two evaluation metrics, Alignment and Coherence, to quantitatively assess the quality of image edit pairs using GPT-4V. HQ-Edits high-resolution images, rich in detail and accompanied by comprehensive editing prompts, substantially enhance the capabilities of existing image editing models. For example, an HQ-Edit finetuned InstructPix2Pix can attain state-of-the-art image editing performance, even surpassing those models fine-tuned with human-annotated data.

NeurIPS Conference 2025 Conference Paper

OpenCUA: Open Foundations for Computer-Use Agents

• Xinyuan Wang
• Bowen Wang
• Dunjie Lu
• Junlin Yang
• Tianbao Xie
• Junli Wang
• Jiaqi Deng
• Xiaole Guo

Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs) capable of automating diverse computer tasks. As their commercial potential grows, critical details of the most capable CUA systems remain closed. As these agents will increasingly mediate digital interactions and execute consequential decisions on our behalf, the research community needs access to open CUA frameworks to study their capabilities, limitations, and risks. To bridge this gap, we propose OpenCUA, a comprehensive open-source framework for scaling CUA data and foundation models. Our framework consists of: (1) an annotation infrastructure that seamlessly captures human computer-use demonstrations; (2) AgentNet, the first large-scale computer-use task dataset spanning 3 operating systems and 200+ applications and websites; (3) a scalable pipeline that transforms demonstrations into state–action pairs with reflective long Chain-of-Thought reasoning that sustain robust performance gains as data scales. Our end-to-end agent models demonstrate strong performance across CUA benchmarks. In particular, OpenCUA-72B achieves an average success rate of 45. 0% on OSWorld‑Verified, establishing a new state-of-the-art (SOTA) among open-source models. Further analysis confirms that our approach generalizes well across domains and benefits significantly from increased test-time computation. We release our annotation tool, datasets, code, and models to build open foundations for further CUA research.

EAAI Journal 2025 Journal Article

Prediction of high-performance concrete compressive strength using Decision Tree-Guided Artificial Neural Network Pretraining approach

• Yang Zhang
• Xinghai Yuan
• Xuanpeng Zhang
• Heng Wang
• Pan He
• Ling Luo
• Chuanyun Xu

ICLR Conference 2025 Conference Paper

Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos

• Mingfei Han 0002
• Linjie Yang
• Xiaojun Chang
• Lina Yao 0001
• Heng Wang

A short clip of video may contain progression of multiple events and an interesting story line. A human need to capture both the event in every shot and associate them together to understand the story behind it. In this work, we present a new multi-shot video understanding benchmark \dataset with detailed shot-level captions, comprehensive video summaries and question-answering pairs. To facilitate better semantic understanding of videos, we provide captions for both visual signals and human narrations. We design several distinct tasks including single-shot video captioning, multi-shot video summarization, and multi-shot video question answering. Preliminary experiments show some challenges to generate a long and comprehensive video summary for multi-shot videos. Nevertheless, the generated imperfect summaries can already achieve competitive performance on existing video understanding tasks such as video question-answering, promoting an under-explored setting of video understanding with detailed summaries.

NeurIPS Conference 2024 Conference Paper

Explaining Datasets in Words: Statistical Models with Natural Language Parameters

• Ruiqi Zhong
• Heng Wang
• Dan Klein
• Jacob Steinhardt

To make sense of massive data, we often first fit simplified models and then interpret the parameters; for example, we cluster the text embeddings and then interpret the mean parameters of each cluster. However, these parameters are often high-dimensional and hard to interpret. To make model parameters directly interpretable, we introduce a family of statistical models---including clustering, time series, and classification models---parameterized by natural language predicates. For example, a cluster of text about COVID could be parameterized by the predicate `` discusses COVID ''. To learn these statistical models effectively, we develop a model-agnostic algorithm that optimizes continuous relaxations of predicate parameters with gradient descent and discretizes them by prompting language models (LMs). Finally, we apply our framework to a wide range of problems: taxonomizing user chat dialogues, characterizing how they evolve across time, finding categories where one language model is better than the other, clustering math problems based on subareas, and explaining visual features in memorable images. Our framework is highly versatile, applicable to both textual and visual domains, can be easily steered to focus on specific properties (e. g. subareas), and explains sophisticated concepts that classical methods (e. g. n-gram analysis) struggle to produce.

AAAI Conference 2024 Conference Paper

Stitching Segments and Sentences towards Generalization in Video-Text Pre-training

• Fan Ma
• Xiaojie Jin
• Heng Wang
• Jingjia Huang
• Linchao Zhu
• Yi Yang

Video-language pre-training models have recently achieved remarkable results on various multi-modal downstream tasks. However, most of these models rely on contrastive learning or masking modeling to align global features across modalities, neglecting the local associations between video frames and text tokens. This limits the model’s ability to perform fine-grained matching and generalization, especially for tasks that selecting segments in long videos based on query texts. To address this issue, we propose a novel stitching and matching pre-text task for video-language pre-training that encourages fine-grained interactions between modalities. Our task involves stitching video frames or sentences into longer sequences and predicting the positions of cross-model queries in the stitched sequences. The individual frame and sentence representations are thus aligned via the stitching and matching strategy, encouraging the fine-grained interactions between videos and texts. in the stitched sequences for the cross-modal query. We conduct extensive experiments on various benchmarks covering text-to-video retrieval, video question answering, video captioning, and moment retrieval. Our results demonstrate that the proposed method significantly improves the generalization capacity of the video-text pre-training models.

AAAI Conference 2024 Conference Paper

V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models

• Heng Wang
• Jianbo Ma
• Santiago Pascual
• Richard Cartwright
• Weidong Cai

Building artificial intelligence (AI) systems on top of a set of foundation models (FMs) is becoming a new paradigm in AI research. Their representative and generative abilities learnt from vast amounts of data can be easily adapted and transferred to a wide range of downstream tasks without extra training from scratch. However, leveraging FMs in cross-modal generation remains under-researched when audio modality is involved. On the other hand, automatically generating semantically-relevant sound from visual input is an important problem in cross-modal generation studies. To solve this vision-to-audio (V2A) generation problem, existing methods tend to design and build complex systems from scratch using modestly sized datasets. In this paper, we propose a lightweight solution to this problem by leveraging foundation models, specifically CLIP, CLAP, and AudioLDM. We first investigate the domain gap between the latent space of the visual CLIP and the auditory CLAP models. Then we propose a simple yet effective mapper mechanism (V2A-Mapper) to bridge the domain gap by translating the visual input between CLIP and CLAP spaces. Conditioned on the translated CLAP embedding, pretrained audio generative FM AudioLDM is adopted to produce high-fidelity and visually-aligned sound. Compared to previous approaches, our method only requires a quick training of the V2A-Mapper. We further analyze and conduct extensive experiments on the choice of the V2A-Mapper and show that a generative mapper is better at fidelity and variability (FD) while a regression mapper is slightly better at relevance (CS). Both objective and subjective evaluation on two V2A datasets demonstrate the superiority of our proposed method compared to current state-of-the-art approaches - trained with 86% fewer parameters but achieving 53% and 19% improvement in FD and CS, respectively. Supplementary materials such as audio samples are provided at our demo website: https://v2a-mapper.github.io/.

NeurIPS Conference 2023 Conference Paper

Can Language Models Solve Graph Problems in Natural Language?

• Heng Wang
• Shangbin Feng
• Tianxing He
• Zhaoxuan Tan
• Xiaochuang Han
• Yulia Tsvetkov

Large language models (LLMs) are increasingly adopted for a variety of tasks with implicit graphical structures, such as planning in robotics, multi-hop question answering or knowledge probing, structured commonsense reasoning, and more. While LLMs have advanced the state-of-the-art on these tasks with structure implications, whether LLMs could explicitly process textual descriptions of graphs and structures, map them to grounded conceptual spaces, and perform structured operations remains underexplored. To this end, we propose NLGraph (Natural Language Graph), a comprehensive benchmark of graph-based problem solving designed in natural language. NLGraph contains 29, 370 problems, covering eight graph reasoning tasks with varying complexity from simple tasks such as connectivity and shortest path up to complex problems such as maximum flow and simulating graph neural networks. We evaluate LLMs (GPT-3/4) with various prompting approaches on the NLGraph benchmark and find that 1) language models do demonstrate preliminary graph reasoning abilities, 2) the benefit of advanced prompting and in-context learning diminishes on more complex graph problems, while 3) LLMs are also (un)surprisingly brittle in the face of spurious correlations in graph and problem settings. We then propose Build-a-Graph Prompting and Algorithmic Prompting, two instruction-based approaches to enhance LLMs in solving natural language graph problems. Build-a-Graph and Algorithmic prompting improve the performance of LLMs on NLGraph by 3. 07% to 16. 85% across multiple tasks and settings, while how to solve the most complicated graph reasoning tasks in our setup with language models remains an open research question.

AAAI Conference 2023 Conference Paper

One Is All: Bridging the Gap between Neural Radiance Fields Architectures with Progressive Volume Distillation

• Shuangkang Fang
• Weixin Xu
• Heng Wang
• Yi Yang
• Yufeng Wang
• Shuchang Zhou

Neural Radiance Fields (NeRF) methods have proved effective as compact, high-quality and versatile representations for 3D scenes, and enable downstream tasks such as editing, retrieval, navigation, etc. Various neural architectures are vying for the core structure of NeRF, including the plain Multi-Layer Perceptron (MLP), sparse tensors, low-rank tensors, hashtables and their compositions. Each of these representations has its particular set of trade-offs. For example, the hashtable-based representations admit faster training and rendering but their lack of clear geometric meaning hampers downstream tasks like spatial-relation-aware editing. In this paper, we propose Progressive Volume Distillation (PVD), a systematic distillation method that allows any-to-any conversions between different architectures, including MLP, sparse or low-rank tensors, hashtables and their compositions. PVD consequently empowers downstream applications to optimally adapt the neural representations for the task at hand in a post hoc fashion. The conversions are fast, as distillation is progressively performed on different levels of volume representations, from shallower to deeper. We also employ special treatment of density to deal with its specific numerical instability problem. Empirical evidence is presented to validate our method on the NeRF-Synthetic, LLFF and TanksAndTemples datasets. For example, with PVD, an MLP-based NeRF model can be distilled from a hashtable-based Instant-NGP model at a 10~20X faster speed than being trained the original NeRF from scratch, while achieving a superior level of synthesis quality. Code is available at https://github.com/megvii-research/AAAI2023-PVD.

ICLR Conference 2023 Conference Paper

Revisit Finetuning strategy for Few-Shot Learning to Transfer the Emdeddings

• Heng Wang
• Tan Yue
• Xiang Ye
• Zihang He
• Bohan Li 0013
• Yong Li 0025

Few-Shot Learning (FSL) aims to learn a simple and effective bias on limited novel samples. Recently, many methods have been focused on re-training a randomly initialized linear classifier to adapt it to the novel features extracted by the pre-trained feature extractor (called Linear-Probing-based methods). These methods typically assumed the pre-trained feature extractor was robust enough, i.e., finetuning was not needed, and hence the pre-trained feature extractor does not change on the novel samples. However, the unchanged pre-trained feature extractor will distort the features of novel samples because the robustness assumption may not hold, especially on the out-of-distribution samples. To extract the undistorted features, we designed Linear-Probing-Finetuning with Firth-Bias (LP-FT-FB) to yield an accurate bias on the limited samples for better finetuning the pre-trained feature extractor, providing stronger transferring ability. In LP-FT-FB, we further proposed inverse Firth Bias Reduction (i-FBR) to regularize the over-parameterized feature extractor on which FBR does not work well. The proposed i-FBR effectively alleviates the over-fitting problem of the feature extractor in the process of finetuning and helps extract undistorted novel features. To show the effectiveness of the designed LP-FT-FB, we conducted a lot of experiments on the commonly used FSL datasets under different backbones, including in-domain and cross-domain FSL tasks. The experimental results show that the proposed FT-LP-FB outperforms the SOTA FSL methods. The code is available at https://github.com/whzyf951620/LinearProbingFinetuningFirthBias.

EAAI Journal 2023 Journal Article

Time-energy-jerk optimal trajectory planning for high-speed parallel manipulator based on quantum-behaved particle swarm optimization algorithm and quintic B-spline

• Weihua Chen
• Heng Wang
• Zhanhao Liu
• Kejian Jiang

IROS Conference 2022 Conference Paper

A Deep-Learning-based System for Indoor Active Cleaning

• Yike Yun
• Linjie Hou
• Zijian Feng
• Wei Jin
• Yang Liu
• Heng Wang
• Ruonan He
• Weitao Guo

Cleaning public areas like commercial complexes is challenging due to their sophisticated surroundings and the vast kinds of real-life dirt. Robots are required to distinguish dirts and apply corresponding cleaning strategies. In this work, we proposed an active-cleaning framework by utilizing deep-learning methods for both solid wastes detection and liquid stains segmentation. Our system consists of 4 components: a Perception module integrated with deep-learning models, a Post-processing module for projection, a Tracking module for map localization, and a Planning and Control module for cleaning strategies. Compared with classic approaches, our vision-based system significantly improves cleaning efficiency. Besides, we released the largest real-world indoor hybrid dirt cleaning dataset (HD10K) containing 10K labeled images, together with a track-level evaluation metric for better cleaning performance measurement. The proposed deep-learning based system is verified with extensive experiments on our dataset, and deployed to Gaussian Robotics's robots operating globally. Dataset is available at: https://gaussianopensource.github.io/projects/active_cleaning.

IJCAI Conference 2022 Conference Paper

Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds

• Heng Wang
• Chaoyi Zhang
• Jianhui Yu
• Weidong Cai

Dense captioning in 3D point clouds is an emerging vision-and-language task involving object-level 3D scene understanding. Apart from coarse semantic class prediction and bounding box regression as in traditional 3D object detection, 3D dense captioning aims at producing a further and finer instance-level label of natural language description on visual appearance and spatial relations for each scene object of interest. To detect and describe objects in a scene, following the spirit of neural machine translation, we propose a transformer-based encoder-decoder architecture, namely SpaCap3D, to transform objects into descriptions, where we especially investigate the relative spatiality of objects in 3D scenes and design a spatiality-guided encoder via a token-to-token spatial relation learning objective and an object-centric decoder for precise and spatiality-enhanced object caption generation. Evaluated on two benchmark datasets, ScanRefer and ReferIt3D, our proposed SpaCap3D outperforms the baseline method Scan2Cap by 4. 94% and 9. 61% in CIDEr@0. 5IoU, respectively. Our project page with source code and supplementary files is available at https: //SpaCap3D. github. io/.

NeurIPS Conference 2022 Conference Paper

TwiBot-22: Towards Graph-Based Twitter Bot Detection

• Shangbin Feng
• Zhaoxuan Tan
• Herun Wan
• Ningnan Wang
• Zilong Chen
• Binchi Zhang
• Qinghua Zheng
• Wenqian Zhang

Twitter bot detection has become an increasingly important task to combat misinformation, facilitate social media moderation, and preserve the integrity of the online discourse. State-of-the-art bot detection methods generally leverage the graph structure of the Twitter network, and they exhibit promising performance when confronting novel Twitter bots that traditional methods fail to detect. However, very few of the existing Twitter bot detection datasets are graph-based, and even these few graph-based datasets suffer from limited dataset scale, incomplete graph structure, as well as low annotation quality. In fact, the lack of a large-scale graph-based Twitter bot detection benchmark that addresses these issues has seriously hindered the development and evaluation of novel graph-based bot detection approaches. In this paper, we propose TwiBot-22, a comprehensive graph-based Twitter bot detection benchmark that presents the largest dataset to date, provides diversified entities and relations on the Twitter network, and has considerably better annotation quality than existing datasets. In addition, we re-implement 35 representative Twitter bot detection baselines and evaluate them on 9 datasets, including TwiBot-22, to promote a fair comparison of model performance and a holistic understanding of research progress. To facilitate further research, we consolidate all implemented codes and datasets into the TwiBot-22 evaluation framework, where researchers could consistently evaluate new models and datasets. The TwiBot-22 Twitter bot detection benchmark and evaluation framework are publicly available at \url{https: //twibot22. github. io/}.

ICML Conference 2021 Conference Paper

Is Space-Time Attention All You Need for Video Understanding?

• Gedas Bertasius
• Heng Wang
• Lorenzo Torresani

We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named “TimeSformer, ” adapts the standard Transformer architecture to video by enabling spatiotemporal feature learning directly from a sequence of frame-level patches. Our experimental study compares different self-attention schemes and suggests that “divided attention, ” where temporal attention and spatial attention are separately applied within each block, leads to the best video classification accuracy among the design choices considered. Despite the radically new design, TimeSformer achieves state-of-the-art results on several action recognition benchmarks, including the best reported accuracy on Kinetics-400 and Kinetics-600. Finally, compared to 3D convolutional networks, our model is faster to train, it can achieve dramatically higher test efficiency (at a small drop in accuracy), and it can also be applied to much longer video clips (over one minute long). Code and models are available at: https: //github. com/facebookresearch/TimeSformer.

AAAI Conference 2020 Conference Paper

FASTER Recurrent Networks for Efficient Video Classification

• Linchao Zhu
• Du Tran
• Laura Sevilla-Lara
• Yi Yang
• Matt Feiszli
• Heng Wang

Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips independently ignores the temporal structure of the video sequence, and increases the computational cost at inference time. In this paper, we propose a novel framework named FASTER, i. e. , Feature Aggregation for Spatio-TEmporal Redundancy. FASTER aims to leverage the redundancy between neighboring clips and reduce the computational cost by learning to aggregate the predictions from models of different complexities. The FASTER framework can integrate high quality representations from expensive models to capture subtle motion information and lightweight representations from cheap models to cover scene changes in the video. A new recurrent network (i. e. , FAST-GRU) is designed to aggregate the mixture of different representations. Compared with existing approaches, FASTER can reduce the FLOPs by over 10× while maintaining the state-of-the-art accuracy across popular datasets, such as Kinetics, UCF-101 and HMDB-51.