Jialu Li

Jialu Li, Hao Tan, Mohit Bansal

In Vision-and-Language Navigation (VLN), an agent needs to navigate through the environment based on natural language instructions. Due to limited available data for agent training and finite diversity in navigation environments, it is challenging for the agent to generalize to new, unseen environments. To address this problem, we propose EnvEdit, a data augmentation method that creates new environments by editing existing environments, which are used to train a more generalizable agent. Our augmented environments can differ from the seen environments in three diverse aspects: style, object appearance, and object classes. Training on these edit-augmented environments prevents the agent from overfitting to existing environments and helps generalize better to new, unseen environments. Empirically, on both the Room-to-Room and the multi-lingual Room-Across-Room datasets, we show that our proposed EnvEdit method gets significant improvements in all metrics on both pre-trained and non-pre-trained VLN agents, and achieves the new state-of-the-art on the test leaderboard. We further ensemble the VLN agents augmented on different edited environments and show that these edit methods are complementary. Code and data are available at https://github.com/jialuli-luka/EnvEdit

Jialu Li, Hao Tan, Mohit Bansal

Vision-and-Language Navigation (VLN) tasks require an agent to navigate through the environment based on language instructions. In this paper, we aim to solve two key challenges in this task: utilizing multilingual instructions for improved instruction-path grounding and navigating through new environments that are unseen during training. To address these challenges, we propose CLEAR: Cross-Lingual and Environment-Agnostic Representations. First, our agent learns a shared and visually-aligned cross-lingual language representation for the three languages (English, Hindi and Telugu) in the Room-Across-Room dataset. Our language representation learning is guided by text pairs that are aligned by visual information. Second, our agent learns an environment-agnostic visual representation by maximizing the similarity between semantically-aligned image pairs (with constraints on object-matching) from different environments. Our environment agnostic visual representation can mitigate the environment bias induced by low-level visual information. Empirically, on the Room-Across-Room dataset, we show that our multilingual agent gets large improvements in all metrics over the strong baseline model when generalizing to unseen environments with the cross-lingual language representation and the environment-agnostic visual representation. Furthermore, we show that our learned language and visual representations can be successfully transferred to the Room-to-Room and Cooperative Vision-and-Dialogue Navigation task, and present detailed qualitative and quantitative generalization and grounding analysis. Our code is available at https://github.com/jialuli-luka/CLEAR

Zun Wang, Jialu Li, Yicong Hong et al.

Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents. To tackle the common data scarcity issue in existing vision-and-language navigation datasets, we propose an effective paradigm for generating large-scale data for learning, which applies 1200+ photo-realistic environments from HM3D and Gibson datasets and synthesizes 4.9 million instruction trajectory pairs using fully-accessible resources on the web. Importantly, we investigate the influence of each component in this paradigm on the agent's performance and study how to adequately apply the augmented data to pre-train and fine-tune an agent. Thanks to our large-scale dataset, the performance of an existing agent can be pushed up (+11% absolute with regard to previous SoTA) to a significantly new best of 80% single-run success rate on the R2R test split by simple imitation learning. The long-lasting generalization gap between navigating in seen and unseen environments is also reduced to less than 1% (versus 8% in the previous best method). Moreover, our paradigm also facilitates different models to achieve new state-of-the-art navigation results on CVDN, REVERIE, and R2R in continuous environments.

Jialu Li, Mohit Bansal

Vision-and-Language Navigation (VLN) is the task that requires an agent to navigate through the environment based on natural language instructions. At each step, the agent takes the next action by selecting from a set of navigable locations. In this paper, we aim to take one step further and explore whether the agent can benefit from generating the potential future view during navigation. Intuitively, humans will have an expectation of how the future environment will look like, based on the natural language instructions and surrounding views, which will aid correct navigation. Hence, to equip the agent with this ability to generate the semantics of future navigation views, we first propose three proxy tasks during the agent's in-domain pre-training: Masked Panorama Modeling (MPM), Masked Trajectory Modeling (MTM), and Action Prediction with Image Generation (APIG). These three objectives teach the model to predict missing views in a panorama (MPM), predict missing steps in the full trajectory (MTM), and generate the next view based on the full instruction and navigation history (APIG), respectively. We then fine-tune the agent on the VLN task with an auxiliary loss that minimizes the difference between the view semantics generated by the agent and the ground truth view semantics of the next step. Empirically, our VLN-SIG achieves the new state-of-the-art on both the Room-to-Room dataset and the CVDN dataset. We further show that our agent learns to fill in missing patches in future views qualitatively, which brings more interpretability over agents' predicted actions. Lastly, we demonstrate that learning to predict future view semantics also enables the agent to have better performance on longer paths.

Yue Zhang, Ziqiao Ma, Jialu Li et al.

Vision-and-Language Navigation (VLN) has gained increasing attention over recent years and many approaches have emerged to advance their development. The remarkable achievements of foundation models have shaped the challenges and proposed methods for VLN research. In this survey, we provide a top-down review that adopts a principled framework for embodied planning and reasoning, and emphasizes the current methods and future opportunities leveraging foundation models to address VLN challenges. We hope our in-depth discussions could provide valuable resources and insights: on one hand, to milestone the progress and explore opportunities and potential roles for foundation models in this field, and on the other, to organize different challenges and solutions in VLN to foundation model researchers.

Zuyao Xu, Yuqi Qiu, Lu Sun et al.

Citations provide the basis for trusting scientific claims; when they are invalid or fabricated, this trust collapses. With the advent of Large Language Models (LLMs), this risk has intensified: LLMs are increasingly used for academic writing, yet their tendency to fabricate citations (``ghost citations'') poses a systemic threat to citation validity. To quantify this threat and inform mitigation, we develop CiteVerifier, an open-source framework for large-scale citation verification, and conduct the first comprehensive study of citation validity in the LLM era through three experiments built on it. We benchmark 13 state-of-the-art LLMs on citation generation across 40 research domains, finding that all models hallucinate citations at rates from 14.23\% to 94.93\%, with significant variation across research domains. Moreover, we analyze 2.2 million citations from 56,381 papers published at top-tier AI/ML and Security venues (2020--2025), confirming that 1.07\% of papers contain invalid or fabricated citations (604 papers), with an 80.9\% increase in 2025 alone. Furthermore, we survey 97 researchers and analyze 94 valid responses after removing 3 conflicting samples, revealing a critical ``verification gap'': 41.5\% of researchers copy-paste BibTeX without checking and 44.4\% choose no-action responses when encountering suspicious references; meanwhile, 76.7\% of reviewers do not thoroughly check references and 80.0\% never suspect fake citations. Our findings reveal an accelerating crisis where unreliable AI tools, combined with inadequate human verification by researchers and insufficient peer review scrutiny, enable fabricated citations to contaminate the scientific record. We propose interventions for researchers, venues, and tool developers to protect citation integrity.

Jialu Li, Mark Hasegawa-Johnson, Nancy L. McElwain

In the U.S., approximately 15-17% of children 2-8 years of age are estimated to have at least one diagnosed mental, behavioral or developmental disorder. However, such disorders often go undiagnosed, and the ability to evaluate and treat disorders in the first years of life is limited. To analyze infant developmental changes, previous studies have shown advanced ML models excel at classifying infant and/or parent vocalizations collected using cell phone, video, or audio-only recording device like LENA. In this study, we pilot test the audio component of a new infant wearable multi-modal device that we have developed called LittleBeats (LB). LB audio pipeline is advanced in that it provides reliable labels for both speaker diarization and vocalization classification tasks, compared with other platforms that only record audio and/or provide speaker diarization labels. We leverage wav2vec 2.0 to obtain superior and more nuanced results with the LB family audio stream. We use a bag-of-audio-words method with wav2vec 2.0 features to create high-level visualizations to understand family-infant vocalization interactions. We demonstrate that our high-quality visualizations capture major types of family vocalization interactions, in categories indicative of mental, behavioral, and developmental health, for both labeled and unlabeled LB audio.

Youshan Zhang, Jialu Li

Audio denoising has been explored for decades using both traditional and deep learning-based methods. However, these methods are still limited to either manually added artificial noise or lower denoised audio quality. To overcome these challenges, we collect a large-scale natural noise bird sound dataset. We are the first to transfer the audio denoising problem into an image segmentation problem and propose a deep visual audio denoising (DVAD) model. With a total of 14,120 audio images, we develop an audio ImageMask tool and propose to use a few-shot generalization strategy to label these images. Extensive experimental results demonstrate that the proposed model achieves state-of-the-art performance. We also show that our method can be easily generalized to speech denoising, audio separation, audio enhancement, and noise estimation.

Yao-Hung Hubert Tsai, Vansh Dhar, Jialu Li et al.

Recent efforts to enable visual navigation using large language models have mainly focused on developing complex prompt systems. These systems incorporate instructions, observations, and history into massive text prompts, which are then combined with pre-trained large language models to facilitate visual navigation. In contrast, our approach aims to fine-tune large language models for visual navigation without extensive prompt engineering. Our design involves a simple text prompt, current observations, and a history collector model that gathers information from previous observations as input. For output, our design provides a probability distribution of possible actions that the agent can take during navigation. We train our model using human demonstrations and collision signals from the Habitat-Matterport 3D Dataset (HM3D). Experimental results demonstrate that our method outperforms state-of-the-art behavior cloning methods and effectively reduces collision rates.

Youshan Zhang, Jialu Li

Achieving high-performance audio denoising is still a challenging task in real-world applications. Existing time-frequency methods often ignore the quality of generated frequency domain images. This paper converts the audio denoising problem into an image generation task. We first develop a complex image generation SwinTransformer network to capture more information from the complex Fourier domain. We then impose structure similarity and detailed loss functions to generate high-quality images and develop an SDR loss to minimize the difference between denoised and clean audios. Extensive experiments on two benchmark datasets demonstrate that our proposed model is better than state-of-the-art methods.

Enhui Yu, Junhui Li, Ruitong Lu et al.

Fine-grained fruit classification is a critical yet challenging task in agricultural computer vision, primarily hindered by a severe shortage of high-quality datasets and the high visual similarity between classes. To address these challenges, we first constructed a comprehensive dataset comprising 306 fruit categories with 116,233 samples. Moreover, we propose FruitEnsemble, a practical two-stage dynamic inference framework designed to overcome the generalization limitations of static single-model architectures. In the first stage, FruitEnsemble employs a validation-calibrated weighted ensemble of heterogeneous backbones to generate a robust Top-3 candidate pool. To tackle difficult samples, we introduce an expert arbitration mechanism: when ensemble confidence falls below 0.6, a multimodal large language model (MLLM) is triggered to perform rigorous visual verification by integrating external botanical descriptions using Chain-of-Thought (CoT) reasoning. Furthermore, we optimized the training pipeline with a hard sample-aware joint loss. Extensive experiments demonstrate that FruitEnsemble achieves a classification accuracy of 70.49\% and outperforms existing state-of-the-art models. Our framework provides an efficient, deployment-oriented solution for real-world agricultural visual sorting and quality inspection tasks.

Qisen Wang, Yifan Zhao, Peisen Shen et al.

Although prevailing camera-controlled video generation models can produce cinematic results, lifting them directly to the generation of 3D-consistent and high-fidelity time-synchronized multi-view videos remains challenging, which is a pivotal capability for taming 4D worlds. Some works resort to data augmentation or test-time optimization, but these strategies are constrained by limited model generalization and scalability issues. To this end, we propose ChronosObserver, a training-free method including World State Hyperspace to represent the spatiotemporal constraints of a 4D world scene, and Hyperspace Guided Sampling to synchronize the diffusion sampling trajectories of multiple views using the hyperspace. Experimental results demonstrate that our method achieves high-fidelity and 3D-consistent time-synchronized multi-view videos generation without training or fine-tuning for diffusion models.

Pengfei Zhu, Qian Wang, Yu Wang et al.

Attributed graph clustering is an unsupervised task that partitions nodes into different groups. Self-supervised learning (SSL) shows great potential in handling this task, and some recent studies simultaneously learn multiple SSL tasks to further boost performance. Currently, different SSL tasks are assigned the same set of weights for all graph nodes. However, we observe that some graph nodes whose neighbors are in different groups require significantly different emphases on SSL tasks. In this paper, we propose to dynamically learn the weights of SSL tasks for different nodes and fuse the embeddings learned from different SSL tasks to boost performance. We design an innovative graph clustering approach, namely Dynamically Fusing Self-Supervised Learning (DyFSS). Specifically, DyFSS fuses features extracted from diverse SSL tasks using distinct weights derived from a gating network. To effectively learn the gating network, we design a dual-level self-supervised strategy that incorporates pseudo labels and the graph structure. Extensive experiments on five datasets show that DyFSS outperforms the state-of-the-art multi-task SSL methods by up to 8.66% on the accuracy metric. The code of DyFSS is available at: https://github.com/q086/DyFSS.

Lakshmikar R. Polamreddy, Kalyan Roy, Sheng-Han Yueh et al.

The scarcity of accessible medical image data poses a significant obstacle in effectively training deep learning models for medical diagnosis, as hospitals refrain from sharing their data due to privacy concerns. In response, we gathered a diverse dataset named MedImgs, which comprises over 250,127 images spanning 61 disease types and 159 classes of both humans and animals from open-source repositories. We propose a Leapfrog Latent Consistency Model (LLCM) that is distilled from a retrained diffusion model based on the collected MedImgs dataset, which enables our model to generate real-time high-resolution images. We formulate the reverse diffusion process as a probability flow ordinary differential equation (PF-ODE) and solve it in latent space using the Leapfrog algorithm. This formulation enables rapid sampling without necessitating additional iterations. Our model demonstrates state-of-the-art performance in generating medical images. Furthermore, our model can be fine-tuned with any custom medical image datasets, facilitating the generation of a vast array of images. Our experimental results outperform those of existing models on unseen dog cardiac X-ray images. Source code is available at https://github.com/lskdsjy/LeapfrogLCM.

Junhui Li, Pu Wang, Jialu Li et al.

Recent high-performance transformer-based speech enhancement models demonstrate that time domain methods could achieve similar performance as time-frequency domain methods. However, time-domain speech enhancement systems typically receive input audio sequences consisting of a large number of time steps, making it challenging to model extremely long sequences and train models to perform adequately. In this paper, we utilize smaller audio chunks as input to achieve efficient utilization of audio information to address the above challenges. We propose a dual-phase audio transformer for denoising (DPATD), a novel model to organize transformer layers in a deep structure to learn clean audio sequences for denoising. DPATD splits the audio input into smaller chunks, where the input length can be proportional to the square root of the original sequence length. Our memory-compressed explainable attention is efficient and converges faster compared to the frequently used self-attention module. Extensive experiments demonstrate that our model outperforms state-of-the-art methods.

Pu Wang, Zhixuan Mao, Jialu Li et al.

Automatic diagnosis of canine pneumothorax is challenged by data scarcity and the need for trustworthy models. To address this, we first introduce a public, pixel-level annotated dataset to facilitate research. We then propose a novel diagnostic paradigm that reframes the task as a synergistic process of signal localization and spectral detection. For localization, our method employs a Vision-Language Model (VLM) to guide an iterative Flow Matching process, which progressively refines segmentation masks to achieve superior boundary accuracy. For detection, the segmented mask is used to isolate features from the suspected lesion. We then apply Random Matrix Theory (RMT), a departure from traditional classifiers, to analyze these features. This approach models healthy tissue as predictable random noise and identifies pneumothorax by detecting statistically significant outlier eigenvalues that represent a non-random pathological signal. The high-fidelity localization from Flow Matching is crucial for purifying the signal, thus maximizing the sensitivity of our RMT detector. This synergy of generative segmentation and first-principles statistical analysis yields a highly accurate and interpretable diagnostic system (source code is available at: https://github.com/Pu-Wang-alt/Canine-pneumothorax).

Jialu Li, Manish Kumar Thota, Ruslan Gokhman et al.

Visual Question Answering (VQA) research seeks to create AI systems to answer natural language questions in images, yet VQA methods often yield overly simplistic and short answers. This paper aims to advance the field by introducing Visual Question Explanation (VQE), which enhances the ability of VQA to provide detailed explanations rather than brief responses and address the need for more complex interaction with visual content. We first created an MLVQE dataset from a 14-week streamed video machine learning course, including 885 slide images, 110,407 words of transcripts, and 9,416 designed question-answer (QA) pairs. Next, we proposed a novel SparrowVQE, a small 3 billion parameters multimodal model. We trained our model with a three-stage training mechanism consisting of multimodal pre-training (slide images and transcripts feature alignment), instruction tuning (tuning the pre-trained model with transcripts and QA pairs), and domain fine-tuning (fine-tuning slide image and QA pairs). Eventually, our SparrowVQE can understand and connect visual information using the SigLIP model with transcripts using the Phi-2 language model with an MLP adapter. Experimental results demonstrate that our SparrowVQE achieves better performance in our developed MLVQE dataset and outperforms state-of-the-art methods in the other five benchmark VQA datasets. The source code is available at \url{https://github.com/YoushanZhang/SparrowVQE}.

AgiBot-World-Contributors, Qingwen Bu, Jisong Cai et al.

We explore how scalable robot data can address real-world challenges for generalized robotic manipulation. Introducing AgiBot World, a large-scale platform comprising over 1 million trajectories across 217 tasks in five deployment scenarios, we achieve an order-of-magnitude increase in data scale compared to existing datasets. Accelerated by a standardized collection pipeline with human-in-the-loop verification, AgiBot World guarantees high-quality and diverse data distribution. It is extensible from grippers to dexterous hands and visuo-tactile sensors for fine-grained skill acquisition. Building on top of data, we introduce Genie Operator-1 (GO-1), a novel generalist policy that leverages latent action representations to maximize data utilization, demonstrating predictable performance scaling with increased data volume. Policies pre-trained on our dataset achieve an average performance improvement of 30% over those trained on Open X-Embodiment, both in in-domain and out-of-distribution scenarios. GO-1 exhibits exceptional capability in real-world dexterous and long-horizon tasks, achieving over 60% success rate on complex tasks and outperforming prior RDT approach by 32%. By open-sourcing the dataset, tools, and models, we aim to democratize access to large-scale, high-quality robot data, advancing the pursuit of scalable and general-purpose intelligence.

Varun Biyyala, Bharat Chanderprakash Kathuria, Jialu Li et al.

Video editing models have advanced significantly, but evaluating their performance remains challenging. Traditional metrics, such as CLIP text and image scores, often fall short: text scores are limited by inadequate training data and hierarchical dependencies, while image scores fail to assess temporal consistency. We present SST-EM (Semantic, Spatial, and Temporal Evaluation Metric), a novel evaluation framework that leverages modern Vision-Language Models (VLMs), Object Detection, and Temporal Consistency checks. SST-EM comprises four components: (1) semantic extraction from frames using a VLM, (2) primary object tracking with Object Detection, (3) focused object refinement via an LLM agent, and (4) temporal consistency assessment using a Vision Transformer (ViT). These components are integrated into a unified metric with weights derived from human evaluations and regression analysis. The name SST-EM reflects its focus on Semantic, Spatial, and Temporal aspects of video evaluation. SST-EM provides a comprehensive evaluation of semantic fidelity and temporal smoothness in video editing. The source code is available in the \textbf{\href{https://github.com/custommetrics-sst/SST_CustomEvaluationMetrics.git}{GitHub Repository}}.

Jialu Li, Hao Tan, Mohit Bansal

Vision language navigation is the task that requires an agent to navigate through a 3D environment based on natural language instructions. One key challenge in this task is to ground instructions with the current visual information that the agent perceives. Most of the existing work employs soft attention over individual words to locate the instruction required for the next action. However, different words have different functions in a sentence (e.g., modifiers convey attributes, verbs convey actions). Syntax information like dependencies and phrase structures can aid the agent to locate important parts of the instruction. Hence, in this paper, we propose a navigation agent that utilizes syntax information derived from a dependency tree to enhance alignment between the instruction and the current visual scenes. Empirically, our agent outperforms the baseline model that does not use syntax information on the Room-to-Room dataset, especially in the unseen environment. Besides, our agent achieves the new state-of-the-art on Room-Across-Room dataset, which contains instructions in 3 languages (English, Hindi, and Telugu). We also show that our agent is better at aligning instructions with the current visual information via qualitative visualizations. Code and models: https://github.com/jialuli-luka/SyntaxVLN

Jialu Li, Jaemin Cho, Yi-Lin Sung et al. · allen-ai

Recent text-to-image (T2I) generation models have demonstrated impressive capabilities in creating images from text descriptions. However, these T2I generation models often fall short of generating images that precisely match the details of the text inputs, such as incorrect spatial relationship or missing objects. In this paper, we introduce SELMA: Skill-Specific Expert Learning and Merging with Auto-Generated Data, a novel paradigm to improve the faithfulness of T2I models by fine-tuning models on automatically generated, multi-skill image-text datasets, with skill-specific expert learning and merging. First, SELMA leverages an LLM's in-context learning capability to generate multiple datasets of text prompts that can teach different skills, and then generates the images with a T2I model based on the prompts. Next, SELMA adapts the T2I model to the new skills by learning multiple single-skill LoRA (low-rank adaptation) experts followed by expert merging. Our independent expert fine-tuning specializes multiple models for different skills, and expert merging helps build a joint multi-skill T2I model that can generate faithful images given diverse text prompts, while mitigating the knowledge conflict from different datasets. We empirically demonstrate that SELMA significantly improves the semantic alignment and text faithfulness of state-of-the-art T2I diffusion models on multiple benchmarks (+2.1% on TIFA and +6.9% on DSG), human preference metrics (PickScore, ImageReward, and HPS), as well as human evaluation. Moreover, fine-tuning with image-text pairs auto-collected via SELMA shows comparable performance to fine-tuning with ground truth data. Lastly, we show that fine-tuning with images from a weaker T2I model can help improve the generation quality of a stronger T2I model, suggesting promising weak-to-strong generalization in T2I models.

Jialu Li, Yuanzhen Li, Neal Wadhwa et al.

We introduce the concept of a generative infinite game, a video game that transcends the traditional boundaries of finite, hard-coded systems by using generative models. Inspired by James P. Carse's distinction between finite and infinite games, we leverage recent advances in generative AI to create Unbounded: a game of character life simulation that is fully encapsulated in generative models. Specifically, Unbounded draws inspiration from sandbox life simulations and allows you to interact with your autonomous virtual character in a virtual world by feeding, playing with and guiding it - with open-ended mechanics generated by an LLM, some of which can be emergent. In order to develop Unbounded, we propose technical innovations in both the LLM and visual generation domains. Specifically, we present: (1) a specialized, distilled large language model (LLM) that dynamically generates game mechanics, narratives, and character interactions in real-time, and (2) a new dynamic regional image prompt Adapter (IP-Adapter) for vision models that ensures consistent yet flexible visual generation of a character across multiple environments. We evaluate our system through both qualitative and quantitative analysis, showing significant improvements in character life simulation, user instruction following, narrative coherence, and visual consistency for both characters and the environments compared to traditional related approaches.

Jialu Li, Aishwarya Padmakumar, Gaurav Sukhatme et al. · amazon-science

Outdoor Vision-and-Language Navigation (VLN) requires an agent to navigate through realistic 3D outdoor environments based on natural language instructions. The performance of existing VLN methods is limited by insufficient diversity in navigation environments and limited training data. To address these issues, we propose VLN-Video, which utilizes the diverse outdoor environments present in driving videos in multiple cities in the U.S. augmented with automatically generated navigation instructions and actions to improve outdoor VLN performance. VLN-Video combines the best of intuitive classical approaches and modern deep learning techniques, using template infilling to generate grounded navigation instructions, combined with an image rotation similarity-based navigation action predictor to obtain VLN style data from driving videos for pretraining deep learning VLN models. We pre-train the model on the Touchdown dataset and our video-augmented dataset created from driving videos with three proxy tasks: Masked Language Modeling, Instruction and Trajectory Matching, and Next Action Prediction, so as to learn temporally-aware and visually-aligned instruction representations. The learned instruction representation is adapted to the state-of-the-art navigator when fine-tuning on the Touchdown dataset. Empirical results demonstrate that VLN-Video significantly outperforms previous state-of-the-art models by 2.1% in task completion rate, achieving a new state-of-the-art on the Touchdown dataset.

Zun Wang, Jialu Li, Yicong Hong et al.

Creating high-quality data for training robust language-instructed agents is a long-lasting challenge in embodied AI. In this paper, we introduce a Self-Refining Data Flywheel (SRDF) that generates high-quality and large-scale navigational instruction-trajectory pairs by iteratively refining the data pool through the collaboration between two models, the instruction generator and the navigator, without any human-in-the-loop annotation. Specifically, SRDF starts with using a base generator to create an initial data pool for training a base navigator, followed by applying the trained navigator to filter the data pool. This leads to higher-fidelity data to train a better generator, which can, in turn, produce higher-quality data for training the next-round navigator. Such a flywheel establishes a data self-refining process, yielding a continuously improved and highly effective dataset for large-scale language-guided navigation learning. Our experiments demonstrate that after several flywheel rounds, the navigator elevates the performance boundary from 70% to 78% SPL on the classic R2R test set, surpassing human performance (76%) for the first time. Meanwhile, this process results in a superior generator, evidenced by a SPICE increase from 23.5 to 26.2, better than all previous VLN instruction generation methods. Finally, we demonstrate the scalability of our method through increasing environment and instruction diversity, and the generalization ability of our pre-trained navigator across various downstream navigation tasks, surpassing state-of-the-art methods by a large margin in all cases.

Jialu Li, Shoubin Yu, Han Lin et al. · allen-ai

Recent advancements in text-to-video (T2V) diffusion models have significantly enhanced the visual quality of the generated videos. However, even recent T2V models find it challenging to follow text descriptions accurately, especially when the prompt requires accurate control of spatial layouts or object trajectories. A recent line of research uses layout guidance for T2V models that require fine-tuning or iterative manipulation of the attention map during inference time. This significantly increases the memory requirement, making it difficult to adopt a large T2V model as a backbone. To address this, we introduce Video-MSG, a training-free Guidance method for T2V generation based on Multimodal planning and Structured noise initialization. Video-MSG consists of three steps, where in the first two steps, Video-MSG creates Video Sketch, a fine-grained spatio-temporal plan for the final video, specifying background, foreground, and object trajectories, in the form of draft video frames. In the last step, Video-MSG guides a downstream T2V diffusion model with Video Sketch through noise inversion and denoising. Notably, Video-MSG does not need fine-tuning or attention manipulation with additional memory during inference time, making it easier to adopt large T2V models. Video-MSG demonstrates its effectiveness in enhancing text alignment with multiple T2V backbones (VideoCrafter2 and CogVideoX-5B) on popular T2V generation benchmarks (T2VCompBench and VBench). We provide comprehensive ablation studies about noise inversion ratio, different background generators, background object detection, and foreground object segmentation.

Yi-Lin Sung, Prateek Yadav, Jialu Li et al.

Layer-wise quantization is a key technique for efficiently compressing large models without expensive retraining. Previous methods typically quantize the weights of each layer by "uniformly" optimizing the layer reconstruction loss across all output tokens. However, in this paper, we demonstrate that better-quantized models can be obtained by prioritizing learning from important tokens (e.g. which have large attention scores). Building on this finding, we propose RSQ (Rotate, Scale, then Quantize), which (1) applies rotations (orthogonal transformation) to the model to mitigate outliers (those with exceptionally large magnitude), (2) scales the token feature based on its importance, and (3) quantizes the model using the GPTQ framework with the second-order statistics computed by scaled tokens. To compute token importance, we explore both heuristic and dynamic strategies. Based on a thorough analysis of all approaches, we adopt attention concentration, which uses attention scores of each token as its importance, as the best approach. We demonstrate that RSQ consistently outperforms baseline methods across multiple downstream tasks and three model families: LLaMA3, Mistral, and Qwen2.5. Additionally, models quantized with RSQ achieve superior performance on long-context tasks, further highlighting its effectiveness. Lastly, RSQ demonstrates generalizability across various setups, including different model sizes, calibration datasets, bit precisions, and quantization methods.

Zun Wang, Jaemin Cho, Jialu Li et al. · allen-ai

Recent approaches on 3D camera control in video diffusion models (VDMs) often create anchor videos to guide diffusion models as a structured prior by rendering from estimated point clouds following annotated camera trajectories. However, errors inherent in point cloud estimation often lead to inaccurate anchor videos. Moreover, the requirement for extensive camera trajectory annotations further increases resource demands. To address these limitations, we introduce EPiC, an efficient and precise camera control learning framework that automatically constructs high-quality anchor videos without expensive camera trajectory annotations. Concretely, we create highly precise anchor videos for training by masking source videos based on first-frame visibility. This approach ensures high alignment, eliminates the need for camera trajectory annotations, and thus can be readily applied to any in-the-wild video to generate image-to-video (I2V) training pairs. Furthermore, we introduce Anchor-ControlNet, a lightweight conditioning module that integrates anchor video guidance in visible regions to pretrained VDMs, with less than 1% of backbone model parameters. By combining the proposed anchor video data and ControlNet module, EPiC achieves efficient training with substantially fewer parameters, training steps, and less data, without requiring modifications to the diffusion model backbone typically needed to mitigate rendering misalignments. Although being trained on masking-based anchor videos, our method generalizes robustly to anchor videos made with point clouds during inference, enabling precise 3D-informed camera control. EPiC achieves SOTA performance on RealEstate10K and MiraData for I2V camera control task, demonstrating precise and robust camera control ability both quantitatively and qualitatively. Notably, EPiC also exhibits strong zero-shot generalization to video-to-video scenarios.

Ruslan Gokhman, Jialu Li, Youshan Zhang

Automating teaching presents unique challenges, as replicating human interaction and adaptability is complex. Automated systems cannot often provide nuanced, real-time feedback that aligns with students' individual learning paces or comprehension levels, which can hinder effective support for diverse needs. This is especially challenging in fields where abstract concepts require adaptive explanations. In this paper, we propose a vision language retrieval augmented generation (named VL-RAG) system that has the potential to bridge this gap by delivering contextually relevant, visually enriched responses that can enhance comprehension. By leveraging a database of tailored answers and images, the VL-RAG system can dynamically retrieve information aligned with specific questions, creating a more interactive and engaging experience that fosters deeper understanding and active student participation. It allows students to explore concepts visually and verbally, promoting deeper understanding and reducing the need for constant human oversight while maintaining flexibility to expand across different subjects and course material.

Zun Wang, Jialu Li, Han Lin et al.

Storytelling video generation (SVG) aims to produce coherent and visually rich multi-scene videos that follow a structured narrative. Existing methods primarily employ LLM for high-level planning to decompose a story into scene-level descriptions, which are then independently generated and stitched together. However, these approaches struggle with generating high-quality videos aligned with the complex single-scene description, as visualizing such complex description involves coherent composition of multiple characters and events, complex motion synthesis and multi-character customization. To address these challenges, we propose DREAMRUNNER, a novel story-to-video generation method: First, we structure the input script using a large language model (LLM) to facilitate both coarse-grained scene planning as well as fine-grained object-level layout planning. Next, DREAMRUNNER presents retrieval-augmented test-time adaptation to capture target motion priors for objects in each scene, supporting diverse motion customization based on retrieved videos, thus facilitating the generation of new videos with complex, scripted motions. Lastly, we propose a novel spatial-temporal region-based 3D attention and prior injection module SR3AI for fine-grained object-motion binding and frame-by-frame spatial-temporal semantic control. We compare DREAMRUNNER with various SVG baselines, demonstrating state-of-the-art performance in character consistency, text alignment, and smooth transitions. Additionally, DREAMRUNNER exhibits strong fine-grained condition-following ability in compositional text-to-video generation, significantly outperforming baselines on T2V-ComBench. Finally, we validate DREAMRUNNER's robust ability to generate multi-object interactions with qualitative examples.

Jialu Li, Taiyan Zhou

Reconstructing natural visual scenes from neural activity is a key challenge in neuroscience and computer vision. We present SpikeVAEDiff, a novel two-stage framework that combines a Very Deep Variational Autoencoder (VDVAE) and the Versatile Diffusion model to generate high-resolution and semantically meaningful image reconstructions from neural spike data. In the first stage, VDVAE produces low-resolution preliminary reconstructions by mapping neural spike signals to latent representations. In the second stage, regression models map neural spike signals to CLIP-Vision and CLIP-Text features, enabling Versatile Diffusion to refine the images via image-to-image generation. We evaluate our approach on the Allen Visual Coding-Neuropixels dataset and analyze different brain regions. Our results show that the VISI region exhibits the most prominent activation and plays a key role in reconstruction quality. We present both successful and unsuccessful reconstruction examples, reflecting the challenges of decoding neural activity. Compared with fMRI-based approaches, spike data provides superior temporal and spatial resolution. We further validate the effectiveness of the VDVAE model and conduct ablation studies demonstrating that data from specific brain regions significantly enhances reconstruction performance.

Yue Zhang, Zun Wang, Han Lin et al.

Despite recent progress in 3D-LLMs, they remain limited in accurately grounding language to visual and spatial elements in 3D environments. This limitation stems in part from training data that focuses on language reasoning rather than spatial understanding due to scarce 3D resources, leaving inherent grounding biases unresolved. To address this, we propose 3D scene editing as a key mechanism to generate precise visual counterfactuals that mitigate these biases through fine-grained spatial manipulation, without requiring costly scene reconstruction or large-scale 3D data collection. Furthermore, to make these edits targeted and directly address the specific weaknesses of the model, we introduce DEER-3D, an error-driven framework following a structured "Decompose, Diagnostic Evaluation, Edit, and Re-train" workflow, rather than broadly or randomly augmenting data as in conventional approaches. Specifically, upon identifying a grounding failure of the 3D-LLM, our framework first diagnoses the exact predicate-level error (e.g., attribute or spatial relation). It then executes minimal, predicate-aligned 3D scene edits, such as recoloring or repositioning, to produce targeted counterfactual supervision for iterative model fine-tuning, significantly enhancing grounding accuracy. We evaluate our editing pipeline across multiple benchmarks for 3D grounding and scene understanding tasks, consistently demonstrating improvements across all evaluated datasets through iterative refinement. DEER-3D underscores the effectiveness of targeted, error-driven scene editing in bridging linguistic reasoning capabilities with spatial grounding in 3D LLMs.

Songze Li, Zun Wang, Gengze Zhou et al.

Goal-oriented language-guided navigation requires robust exploration capabilities for agents to navigate to specified goals in unknown environments without step-by-step instructions. Existing methods tend to exclusively utilize shortest-path trajectories, lacking effective exploration priors for training navigation agents. To address the above challenges, we present SID, a goal-oriented language-guided navigation learning approach with Self-Improving Demonstrations. Specifically, SID learns an initial agent on the shortest-path data sampled from environments and then leverages this agent to generate novel exploration trajectories. The novel rollouts provide demonstrations with stronger exploration strategies to train a better agent, which in turn produces higher-quality agent demonstrations for the next round of training. We show that this iterative self-improving pipeline readily scales to new environments, and the resulting demonstrations can be transferred across a variety of language-guided navigation tasks, elevating the performance ceiling in diverse goal-oriented navigation tasks. Extensive experiments demonstrate that SID significantly boosts the exploration capabilities and generalization of navigation agents. The resulting agent achieves new state-of-the-art performance on goal-oriented language-guided navigation tasks, including REVERIE, SOON, notably achieving a 50.9% success rate on the unseen validation splits of SOON, surpassing the prior leading approaches by a margin of 13.9%.

Jialu Li, Chen Wu, Meiqi Hu

Time series change detection is a critical task for exploring ecosystem dynamics using time series remote sensing images, because it can simultaneously indicate where and when change occur. While deep learning has shown excellent performance in this domain, it continues to approach change area detection and change moment identification as distinct tasks. Given that change area can be inferred from change moment, we propose a time series change detection network, named CAIM-Net (Change Area Inference from Moment Network), to ensure consistency between change area and change moment results. CAIM-Net infers change area from change moment based on the intrinsic relationship between time series analysis and spatial change detection. The CAIM-Net comprises three key steps: Difference Extraction and Enhancement, Coarse Change Moment Extraction, and Fine Change Moment Extraction and Change Area Inference. In the Difference Extraction and Enhancement, a lightweight encoder with batch dimension stacking is designed to rapidly extract difference features. Subsequently, boundary enhancement convolution is applied to amplify these difference features. In the Coarse Change Moment Extraction, the enhanced difference features from the first step are used to spatiotemporal correlation analysis, and then two distinct methods are employed to determine coarse change moments. In the Fine Change Moment Extraction and Change Area Inference, a multiscale temporal Class Activation Mapping (CAM) module first increases the weight of the change-occurring moment from coarse change moments. Then the weighted change moment is used to infer change area based on the fact that pixels with the change moment must have undergone a change.

Yuhong Zhang, Jialu Li, Shilai Yang et al.

Reading comprehension is a fundamental skill in human cognitive development. With the advancement of Large Language Models (LLMs), there is a growing need to compare how humans and LLMs understand language across different contexts and apply this understanding to functional tasks such as inference, emotion interpretation, and information retrieval. Our previous work used LLMs and human biomarkers to study the reading comprehension process. The results showed that the biomarkers corresponding to words with high and low relevance to the inference target, as labeled by the LLMs, exhibited distinct patterns, particularly when validated using eye-tracking data. However, focusing solely on individual words limited the depth of understanding, which made the conclusions somewhat simplistic despite their potential significance. This study used an LLM-based AI agent to group words from a reading passage into nodes and edges, forming a graph-based text representation based on semantic meaning and question-oriented prompts. We then compare the distribution of eye fixations on important nodes and edges. Our findings indicate that LLMs exhibit high consistency in language understanding at the level of graph topological structure. These results build on our previous findings and offer insights into effective human-AI co-learning strategies.

Pengyu Wang, Jialu Li, Ling Shi

With the increasing prevalence of autonomous vehicles (AVs), their vulnerability to various types of attacks has grown, presenting significant security challenges. In this paper, we propose a reinforcement learning (RL)-based approach for designing optimal stealthy integrity attacks on AV actuators. We also analyze the limitations of state-of-the-art RL-based secure controllers developed to counter such attacks. Through extensive simulation experiments, we demonstrate the effectiveness and efficiency of our proposed method.

Pengyu Wang, Zhaohua Yang, Jialu Li et al.

Safety-critical cyber-physical systems (CPS), such as quadrotor UAVs, are particularly prone to cyber attacks, which can result in significant consequences if not detected promptly and accurately. During outdoor operations, the nonlinear dynamics of UAV systems, combined with non-Gaussian noise, pose challenges to the effectiveness of conventional statistical and machine learning methods. To overcome these limitations, we present QUADFormer, an advanced attack detection framework for quadrotor UAVs leveraging a transformer-based architecture. This framework features a residue generator that produces sequences sensitive to anomalies, which are then analyzed by the transformer to capture statistical patterns for detection and classification. Furthermore, an alert mechanism ensures UAVs can operate safely even when under attack. Extensive simulations and experimental evaluations highlight that QUADFormer outperforms existing state-of-the-art techniques in detection accuracy.

Mohammad Nur Hossain Khan, Jialu Li, Nancy L. McElwain et al.

Certain environmental noises have been associated with negative developmental outcomes for infants and young children. Though classifying or tagging sound events in a domestic environment is an active research area, previous studies focused on data collected from a non-stationary microphone placed in the environment or from the perspective of adults. Further, many of these works ignore infants or young children in the environment or have data collected from only a single family where noise from the fixed sound source can be moderate at the infant's position or vice versa. Thus, despite the recent success of large pre-trained models for noise event detection, the performance of these models on infant-centric noise soundscapes in the home is yet to be explored. To bridge this gap, we have collected and labeled noises in home soundscapes from 22 families in an unobtrusive manner, where the data are collected through an infant-worn recording device. In this paper, we explore the performance of a large pre-trained model (Audio Spectrogram Transformer [AST]) on our noise-conditioned infant-centric environmental data as well as publicly available home environmental datasets. Utilizing different training strategies such as resampling, utilizing public datasets, mixing public and infant-centric training sets, and data augmentation using noise and masking, we evaluate the performance of a large pre-trained model on sparse and imbalanced infant-centric data. Our results show that fine-tuning the large pre-trained model by combining our collected dataset with public datasets increases the F1-score from 0.11 (public datasets) and 0.76 (collected datasets) to 0.84 (combined datasets) and Cohen's Kappa from 0.013 (public datasets) and 0.77 (collected datasets) to 0.83 (combined datasets) compared to only training with public or collected datasets, respectively.

Pu Wang, Junhui Li, Jialu Li et al.

Recent diffusion models have achieved promising performances in audio-denoising tasks. The unique property of the reverse process could recover clean signals. However, the distribution of real-world noises does not comply with a single Gaussian distribution and is even unknown. The sampling of Gaussian noise conditions limits its application scenarios. To overcome these challenges, we propose a DiffGMM model, a denoising model based on the diffusion and Gaussian mixture models. We employ the reverse process to estimate parameters for the Gaussian mixture model. Given a noisy audio signal, we first apply a 1D-U-Net to extract features and train linear layers to estimate parameters for the Gaussian mixture model, and we approximate the real noise distributions. The noisy signal is continuously subtracted from the estimated noise to output clean audio signals. Extensive experimental results demonstrate that the proposed DiffGMM model achieves state-of-the-art performance.

Jialu Li, Mohit Bansal

Vision-and-Language Navigation (VLN) requires the agent to follow language instructions to navigate through 3D environments. One main challenge in VLN is the limited availability of photorealistic training environments, which makes it hard to generalize to new and unseen environments. To address this problem, we propose PanoGen, a generation method that can potentially create an infinite number of diverse panoramic environments conditioned on text. Specifically, we collect room descriptions by captioning the room images in existing Matterport3D environments, and leverage a state-of-the-art text-to-image diffusion model to generate the new panoramic environments. We use recursive outpainting over the generated images to create consistent 360-degree panorama views. Our new panoramic environments share similar semantic information with the original environments by conditioning on text descriptions, which ensures the co-occurrence of objects in the panorama follows human intuition, and creates enough diversity in room appearance and layout with image outpainting. Lastly, we explore two ways of utilizing PanoGen in VLN pre-training and fine-tuning. We generate instructions for paths in our PanoGen environments with a speaker built on a pre-trained vision-and-language model for VLN pre-training, and augment the visual observation with our panoramic environments during agents' fine-tuning to avoid overfitting to seen environments. Empirically, learning with our PanoGen environments achieves the new state-of-the-art on the Room-to-Room, Room-for-Room, and CVDN datasets. Pre-training with our PanoGen speaker data is especially effective for CVDN, which has under-specified instructions and needs commonsense knowledge. Lastly, we show that the agent can benefit from training with more generated panoramic environments, suggesting promising results for scaling up the PanoGen environments.

Jiajie Zou, Yuran Zhang, Jialu Li et al.

The computational principles underlying attention allocation in complex goal-directed tasks remain elusive. Goal-directed reading, i.e., reading a passage to answer a question in mind, is a common real-world task that strongly engages attention. Here, we investigate what computational models can explain attention distribution in this complex task. We show that the reading time on each word is predicted by the attention weights in transformer-based deep neural networks (DNNs) optimized to perform the same reading task. Eye-tracking further reveals that readers separately attend to basic text features and question-relevant information during first-pass reading and rereading, respectively. Similarly, text features and question relevance separately modulate attention weights in shallow and deep DNN layers. Furthermore, when readers scan a passage without a question in mind, their reading time is predicted by DNNs optimized for a word prediction task. Therefore, attention during real-world reading can be interpreted as the consequence of task optimization.

Jialu Li, Esin Durmus, Claire Cardie

Online debate forums provide users a platform to express their opinions on controversial topics while being exposed to opinions from diverse set of viewpoints. Existing work in Natural Language Processing (NLP) has shown that linguistic features extracted from the debate text and features encoding the characteristics of the audience are both critical in persuasion studies. In this paper, we aim to further investigate the role of discourse structure of the arguments from online debates in their persuasiveness. In particular, we use the factor graph model to obtain features for the argument structure of debates from an online debating platform and incorporate these features to an LSTM-based model to predict the debater that makes the most convincing arguments. We find that incorporating argument structure features play an essential role in achieving the better predictive performance in assessing the persuasiveness of the arguments in online debates.

Jialu Li, Mark Hasegawa-Johnson

Phones, the segmental units of the International Phonetic Alphabet (IPA), are used for lexical distinctions in most human languages; Tones, the suprasegmental units of the IPA, are used in perhaps 70%. Many previous studies have explored cross-lingual adaptation of automatic speech recognition (ASR) phone models, but few have explored the multilingual and cross-lingual transfer of synchronization between phones and tones. In this paper, we test four Connectionist Temporal Classification (CTC)-based acoustic models, differing in the degree of synchrony they impose between phones and tones. Models are trained and tested multilingually in three languages, then adapted and tested cross-lingually in a fourth. Both synchronous and asynchronous models are effective in both multilingual and cross-lingual settings. Synchronous models achieve lower error rate in the joint phone+tone tier, but asynchronous training results in lower tone error rate.