arXiv subjects

Yiheng Li

Publications and source records attributed to Yiheng Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

Fine-Grained Representation for Lane Topology Reasoning

Precise modeling of lane topology is essential for autonomous driving, as it directly impacts navigation and control decisions. Existing methods typically represent each lane with a single query and infer topological connectivity based on the similarity between lane queries. However, this kind of design struggles to accurately model complex lane structures, leading to unreliable topology prediction. In this view, we propose a Fine-Grained lane topology reasoning framework (TopoFG). It divides the procedure from bird's-eye-view (BEV) features to topology prediction via fine-grained queries into three phases, i.e., Hierarchical Prior Extractor (HPE), Region-Focused Decoder (RFD), and Robust Boundary-Point Topology Reasoning (RBTR). Specifically, HPE extracts global spatial priors from the BEV mask and local sequential priors from in-lane keypoint sequences to guide subsequent fine-grained query modeling. RFD constructs fine-grained queries by integrating the spatial and sequential priors. It then samples reference points in RoI regions of the mask and applies cross-attention with BEV features to refine the query representations of each lane. RBTR models lane connectivity based on boundary-point query features and further employs a topological denoising strategy to reduce matching ambiguity. By integrating spatial and sequential priors into fine-grained queries and applying a denoising strategy to boundary-point topology reasoning, our method precisely models complex lane structures and delivers trustworthy topology predictions. Extensive experiments on the OpenLane-V2 benchmark demonstrate that TopoFG achieves new state-of-the-art performance, with an OLS of 48.0 on subsetA and 45.4 on subsetB.

cs.CV↗

arXiv2025

Explicit Temporal-Semantic Modeling for Dense Video Captioning via Context-Aware Cross-Modal Interaction

Dense video captioning jointly localizes and captions salient events in untrimmed videos. Recent methods primarily focus on leveraging additional prior knowledge and advanced multi-task architectures to achieve competitive performance. However, these pipelines rely on implicit modeling that uses frame-level or fragmented video features, failing to capture the temporal coherence across event sequences and comprehensive semantics within visual contexts. To address this, we propose an explicit temporal-semantic modeling framework called Context-Aware Cross-Modal Interaction (CACMI), which leverages both latent temporal characteristics within videos and linguistic semantics from text corpus. Specifically, our model consists of two core components: Cross-modal Frame Aggregation aggregates relevant frames to extract temporally coherent, event-aligned textual features through cross-modal retrieval; and Context-aware Feature Enhancement utilizes query-guided attention to integrate visual dynamics with pseudo-event semantics. Extensive experiments on the ActivityNet Captions and YouCook2 datasets demonstrate that CACMI achieves the state-of-the-art performance on dense video captioning task.

cs.CV↗

arXiv2025

Grounding Foundational Vision Models with 3D Human Poses for Robust Action Recognition

For embodied agents to effectively understand and interact within the world around them, they require a nuanced comprehension of human actions grounded in physical space. Current action recognition models, often relying on RGB video, learn superficial correlations between patterns and action labels, so they struggle to capture underlying physical interaction dynamics and human poses in complex scenes. We propose a model architecture that grounds action recognition in physical space by fusing two powerful, complementary representations: V-JEPA 2's contextual, predictive world dynamics and CoMotion's explicit, occlusion-tolerant human pose data. Our model is validated on both the InHARD and UCF-19-Y-OCC benchmarks for general action recognition and high-occlusion action recognition, respectively. Our model outperforms three other baselines, especially within complex, occlusive scenes. Our findings emphasize a need for action recognition to be supported by spatial understanding instead of statistical pattern recognition.

cs.CV↗

arXiv2025

Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction

In click-through rate prediction, click-through rate prediction is used to model users' interests. However, most of the existing CTR prediction methods are mainly based on the ID modality. As a result, they are unable to comprehensively model users' multi-modal preferences. Therefore, it is necessary to introduce multi-modal CTR prediction. Although it seems appealing to directly apply the existing multi-modal fusion methods to click-through rate prediction models, these methods (1) fail to effectively disentangle commonalities and specificities across different modalities; (2) fail to consider the synergistic effects between modalities and model the complex interactions between modalities. To address the above issues, this paper proposes the Diffusion-based Multi-modal Synergy Interest Network (Diff-MSIN) framework for click-through prediction. This framework introduces three innovative modules: the Multi-modal Feature Enhancement (MFE) Module Synergistic Relationship Capture (SRC) Module, and the Feature Dynamic Adaptive Fusion (FDAF) Module. The MFE Module and SRC Module extract synergistic, common, and special information among different modalities. They effectively enhances the representation of the modalities, improving the overall quality of the fusion. To encourage distinctiveness among different features, we design a Knowledge Decoupling method. Additionally, the FDAF Module focuses on capturing user preferences and reducing fusion noise. To validate the effectiveness of the Diff-MSIN framework, we conducted extensive experiments using the Rec-Tmall and three Amazon datasets. The results demonstrate that our approach yields a significant improvement of at least 1.67% compared to the baseline, highlighting its potential for enhancing multi-modal recommendation systems. Our code is available at the following link: https://github.com/Cxx-0/Diff-MSIN.

cs.IR↗

arXiv2025

Multi-Modal Multi-Behavior Sequential Recommendation with Conditional Diffusion-Based Feature Denoising

The sequential recommendation system utilizes historical user interactions to predict preferences. Effectively integrating diverse user behavior patterns with rich multimodal information of items to enhance the accuracy of sequential recommendations is an emerging and challenging research direction. This paper focuses on the problem of multi-modal multi-behavior sequential recommendation, aiming to address the following challenges: (1) the lack of effective characterization of modal preferences across different behaviors, as user attention to different item modalities varies depending on the behavior; (2) the difficulty of effectively mitigating implicit noise in user behavior, such as unintended actions like accidental clicks; (3) the inability to handle modality noise in multi-modal representations, which further impacts the accurate modeling of user preferences. To tackle these issues, we propose a novel Multi-Modal Multi-Behavior Sequential Recommendation model (M$^3$BSR). This model first removes noise in multi-modal representations using a Conditional Diffusion Modality Denoising Layer. Subsequently, it utilizes deep behavioral information to guide the denoising of shallow behavioral data, thereby alleviating the impact of noise in implicit feedback through Conditional Diffusion Behavior Denoising. Finally, by introducing a Multi-Expert Interest Extraction Layer, M$^3$BSR explicitly models the common and specific interests across behaviors and modalities to enhance recommendation performance. Experimental results indicate that M$^3$BSR significantly outperforms existing state-of-the-art methods on benchmark datasets.

cs.IR↗

arXiv2025

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models

Hallucinations pose a significant challenge in Large Vision Language Models (LVLMs), with misalignment between multimodal features identified as a key contributing factor. This paper reveals the negative impact of the long-term decay in Rotary Position Encoding (RoPE), used for positional modeling in LVLMs, on multimodal alignment. Concretely, under long-term decay, instruction tokens exhibit uneven perception of image tokens located at different positions within the two-dimensional space: prioritizing image tokens from the bottom-right region since in the one-dimensional sequence, these tokens are positionally closer to the instruction tokens. This biased perception leads to insufficient image-instruction interaction and suboptimal multimodal alignment. We refer to this phenomenon as image alignment bias. To enhance instruction's perception of image tokens at different spatial locations, we propose MCA-LLaVA, based on Manhattan distance, which extends the long-term decay to a two-dimensional, multi-directional spatial decay. MCA-LLaVA integrates the one-dimensional sequence order and two-dimensional spatial position of image tokens for positional modeling, mitigating hallucinations by alleviating image alignment bias. Experimental results of MCA-LLaVA across various hallucination and general benchmarks demonstrate its effectiveness and generality. The code can be accessed in https://github.com/ErikZ719/MCA-LLaVA.

cs.CV↗

arXiv2025

Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation

To tackle the threat of fake news, the task of detecting and grounding multi-modal media manipulation DGM4 has received increasing attention. However, most state-of-the-art methods fail to explore the fine-grained consistency within local content, usually resulting in an inadequate perception of detailed forgery and unreliable results. In this paper, we propose a novel approach named Contextual-Semantic Consistency Learning (CSCL) to enhance the fine-grained perception ability of forgery for DGM4. Two branches for image and text modalities are established, each of which contains two cascaded decoders, i.e., Contextual Consistency Decoder (CCD) and Semantic Consistency Decoder (SCD), to capture within-modality contextual consistency and across-modality semantic consistency, respectively. Both CCD and SCD adhere to the same criteria for capturing fine-grained forgery details. To be specific, each module first constructs consistency features by leveraging additional supervision from the heterogeneous information of each token pair. Then, the forgery-aware reasoning or aggregating is adopted to deeply seek forgery cues based on the consistency features. Extensive experiments on DGM4 datasets prove that CSCL achieves new state-of-the-art performance, especially for the results of grounding manipulated content. Codes and weights are avaliable at https://github.com/liyih/CSCL.

cs.CV↗

arXiv2025

Comparative Analysis of Machine Learning Models for Lung Cancer Mutation Detection and Staging Using 3D CT Scans

Lung cancer is the leading cause of cancer mortality worldwide, and non-invasive methods for detecting key mutations and staging are essential for improving patient outcomes. Here, we compare the performance of two machine learning models - FMCIB+XGBoost, a supervised model with domain-specific pretraining, and Dinov2+ABMIL, a self-supervised model with attention-based multiple-instance learning - on 3D lung nodule data from the Stanford Radiogenomics and Lung-CT-PT-Dx cohorts. In the task of KRAS and EGFR mutation detection, FMCIB+XGBoost consistently outperformed Dinov2+ABMIL, achieving accuracies of 0.846 and 0.883 for KRAS and EGFR mutations, respectively. In cancer staging, Dinov2+ABMIL demonstrated competitive generalization, achieving an accuracy of 0.797 for T-stage prediction in the Lung-CT-PT-Dx cohort, suggesting SSL's adaptability across diverse datasets. Our results emphasize the clinical utility of supervised models in mutation detection and highlight the potential of SSL to improve staging generalization, while identifying areas for enhancement in mutation sensitivity.

eess.IV↗

arXiv2025

WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving

Language models uncover unprecedented abilities in analyzing driving scenarios, owing to their limitless knowledge accumulated from text-based pre-training. Naturally, they should particularly excel in analyzing rule-based interactions, such as those triggered by traffic laws, which are well documented in texts. However, such interaction analysis remains underexplored due to the lack of dedicated language datasets that address it. Therefore, we propose Waymo Open Motion Dataset-Reasoning (WOMD-Reasoning), a comprehensive large-scale Q&As dataset built on WOMD focusing on describing and reasoning traffic rule-induced interactions in driving scenarios. WOMD-Reasoning also presents by far the largest multi-modal Q&A dataset, with 3 million Q&As on real-world driving scenarios, covering a wide range of driving topics from map descriptions and motion status descriptions to narratives and analyses of agents' interactions, behaviors, and intentions. To showcase the applications of WOMD-Reasoning, we design Motion-LLaVA, a motion-language model fine-tuned on WOMD-Reasoning. Quantitative and qualitative evaluations are performed on WOMD-Reasoning dataset as well as the outputs of Motion-LLaVA, supporting the data quality and wide applications of WOMD-Reasoning, in interaction predictions, traffic rule compliance plannings, etc. The dataset and its vision modal extension are available on https://waymo.com/open/download/. The codes & prompts to build it are available on https://github.com/yhli123/WOMD-Reasoning.

cs.RO↗

arXiv2025

Benchmarking Chest X-ray Diagnosis Models Across Multinational Datasets

Foundation models leveraging vision-language pretraining have shown promise in chest X-ray (CXR) interpretation, yet their real-world performance across diverse populations and diagnostic tasks remains insufficiently evaluated. This study benchmarks the diagnostic performance and generalizability of foundation models versus traditional convolutional neural networks (CNNs) on multinational CXR datasets. We evaluated eight CXR diagnostic models - five vision-language foundation models and three CNN-based architectures - across 37 standardized classification tasks using six public datasets from the USA, Spain, India, and Vietnam, and three private datasets from hospitals in China. Performance was assessed using AUROC, AUPRC, and other metrics across both shared and dataset-specific tasks. Foundation models outperformed CNNs in both accuracy and task coverage. MAVL, a model incorporating knowledge-enhanced prompts and structured supervision, achieved the highest performance on public (mean AUROC: 0.82; AUPRC: 0.32) and private (mean AUROC: 0.95; AUPRC: 0.89) datasets, ranking first in 14 of 37 public and 3 of 4 private tasks. All models showed reduced performance on pediatric cases, with average AUROC dropping from 0.88 +/- 0.18 in adults to 0.57 +/- 0.29 in children (p = 0.0202). These findings highlight the value of structured supervision and prompt design in radiologic AI and suggest future directions including geographic expansion and ensemble modeling for clinical deployment. Code for all evaluated models is available at https://drive.google.com/drive/folders/1B99yMQm7bB4h1sVMIBja0RfUu8gLktCE

eess.IV↗

arXiv2025

Tailoring hBN's Phonon Polaritons with the Plasmonic Phase-Change Material In3SbTe2

Polaritons in van-der-Waals materials (vdWM) promise high confinement and multiple tailoring options by optical structures, e.g., resonators, launching structures and lenses. These optical structures are conventionally fabricated using cumbersome multi-process lithography techniques. In contrast, phase-change materials (PCMs) offer fast and reconfigurable programming of optical structures. PCMs can reversibly be switched between two stable phases with distinct permittivities by local heating, e.g., by optical laser pulses. While the well-known dielectric PCM GeSbTe-alloys feature only a permittivity change, the PCM In3SbTe2 can be switched between a dielectric and metallic phase. This makes In3SbTe2 promising for programming metallic launching structures. Here, we demonstrate direct optical programming and thereby rapid prototyping of optical launching structures in In3SbTe2 to tailor and confine polaritons in vdWM. We combine the vdWM hexagonal boron nitride (hBN) with In3SbTe2 and optically program circular resonators for hBN's phonon polaritons through hBN into In3SbTe2. We investigate the polariton resonators with near-field optical microscopy. Demonstrating the reconfigurability, we decrease the resonator diameter to increase the polariton confinement. Finally, we fabricate focusing structures for hBN's phonon polaritons whose focal point is changed in a second post-processing step. We promote In3SbTe2 as a versatile platform for rapid prototyping of polariton optics in vdWM.

physics.optics↗

arXiv2025

UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing

Human pose plays a crucial role in the digital age. While recent works have achieved impressive progress in understanding and generating human poses, they often support only a single modality of control signals and operate in isolation, limiting their application in real-world scenarios. This paper presents UniPose, a framework employing Large Language Models (LLMs) to comprehend, generate, and edit human poses across various modalities, including images, text, and 3D SMPL poses. Specifically, we apply a pose tokenizer to convert 3D poses into discrete pose tokens, enabling seamless integration into the LLM within a unified vocabulary. To further enhance the fine-grained pose perception capabilities, we facilitate UniPose with a mixture of visual encoders, among them a pose-specific visual encoder. Benefiting from a unified learning strategy, UniPose effectively transfers knowledge across different pose-relevant tasks, adapts to unseen tasks, and exhibits extended capabilities. This work serves as the first attempt at building a general-purpose framework for pose comprehension, generation, and editing. Extensive experiments highlight UniPose's competitive and even superior performance across various pose-relevant tasks.

cs.CV↗

arXiv2025

Fast square-oscillations in semiconductor VCSELs with delayed orthogonal polarization feedback

We present an experimental investigation into the generation of self-sustained and fast square oscillations from the TE mode of semiconductor VCSELs with delayed orthogonal polarization feedback. We find that the low frequency switching originates from the rotation of the TE and TM modes facilitated by a long time delay, but the fast oscillations are anchored to the frequency beating between the TE and TM modes and are modified by a half-wavelength ($λ/2$) plate. A comprehensive analysis of the evolution of the nonlinear dynamics is conducted and the related mechanism is discussed. Our study not only deepens our comprehension of laser nonlinear dynamics but also offers an all-optical approach for producing specialized signals, which could be instrumental in applications such as optical communications and photonic computing leveraging the complexity of long-delay systems.

physics.optics↗

arXiv2025

CoreNet: Conflict Resolution Network for Point-Pixel Misalignment and Sub-Task Suppression of 3D LiDAR-Camera Object Detection

Fusing multi-modality inputs from different sensors is an effective way to improve the performance of 3D object detection. However, current methods overlook two important conflicts: point-pixel misalignment and sub-task suppression. The former means a pixel feature from the opaque object is projected to multiple point features of the same ray in the world space, and the latter means the classification prediction and bounding box regression may cause mutual suppression. In this paper, we propose a novel method named Conflict Resolution Network (CoreNet) to address the aforementioned issues. Specifically, we first propose a dual-stream transformation module to tackle point-pixel misalignment. It consists of ray-based and point-based 2D-to-BEV transformations. Both of them achieve approximately unique mapping from the image space to the world space. Moreover, we introduce a task-specific predictor to tackle sub-task suppression. It uses the dual-branch structure which adopts class-specific query and Bbox-specific query to corresponding sub-tasks. Each task-specific query is constructed of task-specific feature and general feature, which allows the heads to adaptively select information of interest based on different sub-tasks. Experiments on the large-scale nuScenes dataset demonstrate the superiority of our proposed CoreNet, by achieving 75.6\% NDS and 73.3\% mAP on the nuScenes test set without test-time augmentation and model ensemble techniques. The ample ablation study also demonstrates the effectiveness of each component. The code is released on https://github.com/liyih/CoreNet.

cs.CV↗

arXiv2024

RCTrans: Radar-Camera Transformer via Radar Densifier and Sequential Decoder for 3D Object Detection

In radar-camera 3D object detection, the radar point clouds are sparse and noisy, which causes difficulties in fusing camera and radar modalities. To solve this, we introduce a novel query-based detection method named Radar-Camera Transformer (RCTrans). Specifically, we first design a Radar Dense Encoder to enrich the sparse valid radar tokens, and then concatenate them with the image tokens. By doing this, we can fully explore the 3D information of each interest region and reduce the interference of empty tokens during the fusing stage. We then design a Pruning Sequential Decoder to predict 3D boxes based on the obtained tokens and random initialized queries. To alleviate the effect of elevation ambiguity in radar point clouds, we gradually locate the position of the object via a sequential fusion structure. It helps to get more precise and flexible correspondences between tokens and queries. A pruning training strategy is adopted in the decoder, which can save much time during inference and inhibit queries from losing their distinctiveness. Extensive experiments on the large-scale nuScenes dataset prove the superiority of our method, and we also achieve new state-of-the-art radar-camera 3D detection results. Our implementation is available at https://github.com/liyih/RCTrans.

cs.CV↗

arXiv2024

360° Stereo Image Composition with Depth Adaption

360° images and videos have become an economic and popular way to provide VR experiences using real-world content. However, the manipulation of the stereo panoramic content remains less explored. In this paper, we focus on the 360° image composition problem, and develop a solution that can take an object from a stereo image pair and insert it at a given 3D position in a target stereo panorama, with well-preserved geometry information. Our method uses recovered 3D point clouds to guide the composited image generation. More specifically, we observe that using only a one-off operation to insert objects into equirectangular images will never produce satisfactory depth perception and generate ghost artifacts when users are watching the result from different view directions. Therefore, we propose a novel per-view projection method that segments the object in 3D spherical space with the stereo camera pair facing in that direction. A deep depth densification network is proposed to generate depth guidance for the stereo image generation of each view segment according to the desired position and pose of the inserted object. We finally combine the synthesized view segments and blend the objects into the target stereo 360° scene. A user study demonstrates that our method can provide good depth perception and removes ghost artifacts. The per-view solution is a potential paradigm for other content manipulation methods for 360° images and videos.

cs.GR↗

arXiv2024

Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment

In this paper, we point out that suboptimal noise-data mapping leads to slow training of diffusion models. During diffusion training, current methods diffuse each image across the entire noise space, resulting in a mixture of all images at every point in the noise layer. We emphasize that this random mixture of noise-data mapping complicates the optimization of the denoising function in diffusion models. Drawing inspiration from the immiscibility phenomenon in physics, we propose Immiscible Diffusion, a simple and effective method to improve the random mixture of noise-data mapping. In physics, miscibility can vary according to various intermolecular forces. Thus, immiscibility means that the mixing of molecular sources is distinguishable. Inspired by this concept, we propose an assignment-then-diffusion training strategy to achieve Immiscible Diffusion. As one example, prior to diffusing the image data into noise, we assign diffusion target noise for the image data by minimizing the total image-noise pair distance in a mini-batch. The assignment functions analogously to external forces to expel the diffuse-able areas of images, thus mitigating the inherent difficulties in diffusion training. Our approach is remarkably simple, requiring only one line of code to restrict the diffuse-able area for each image while preserving the Gaussian distribution of noise. In this way, each image is preferably projected to nearby noise. Experiments demonstrate that our method can achieve up to 3x faster training for unconditional Consistency Models on the CIFAR dataset, as well as for DDIM and Stable Diffusion on CelebA and ImageNet dataset, and in class-conditional training and fine-tuning. In addition, we conducted a thorough analysis that sheds light on how it improves diffusion training speed while improving fidelity. The code is available at https://yhli123.github.io/immiscible-diffusion

cs.CV↗

arXiv2024

Mitigating Object Hallucination via Concentric Causal Attention

Recent Large Vision Language Models (LVLMs) present remarkable zero-shot conversational and reasoning capabilities given multimodal queries. Nevertheless, they suffer from object hallucination, a phenomenon where LVLMs are prone to generate textual responses not factually aligned with image inputs. Our pilot study reveals that object hallucination is closely tied with Rotary Position Encoding (RoPE), a widely adopted positional dependency modeling design in existing LVLMs. Due to the long-term decay in RoPE, LVLMs tend to hallucinate more when relevant visual cues are distant from instruction tokens in the multimodal input sequence. Additionally, we observe a similar effect when reversing the sequential order of visual tokens during multimodal alignment. Our tests indicate that long-term decay in RoPE poses challenges to LVLMs while capturing visual-instruction interactions across long distances. We propose Concentric Causal Attention (CCA), a simple yet effective positional alignment strategy that mitigates the impact of RoPE long-term decay in LVLMs by naturally reducing relative distance between visual and instruction tokens. With CCA, visual tokens can better interact with instruction tokens, thereby enhancing model's perception capability and alleviating object hallucination. Without bells and whistles, our positional alignment method surpasses existing hallucination mitigation strategies by large margins on multiple object hallucination benchmarks.

cs.CV↗