paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

MOSAIK: Multi-Patch Content-Aware Spatial Allocation of Image Tokens for Efficient Generation

Mohammadreza Hami, Mohammadreza Samadi, Chao Gao, Negar Hassanpour

Pixel-space diffusion models avoid the reconstruction ceiling of latent diffusion models by generating directly in image space. However, their substantially higher token count makes generation expensive due to the quadratic complexity of self-attention. Several existing efficiency methods reduce this cost by using larger patches at selected denoising steps, thereby representing the image with fewer tokens. Yet, each step still uses a single patch size uniformly across the entire image, overlooking that different regions suffer different fidelity losses when coarsened. We introduce MOSAIK, a damage-guided framework that varies patch size across regions and denoising steps. MOSAIK adapts the PixelDiT backbone to generate arbitrary heterogeneous patch layouts, and a lightweight predictor uses intermediate denoising features to estimate the fidelity loss caused by coarsening each region. Given a token budget, our damage-guided layout predictor assigns fine patches to sensitive regions and coarse patches elsewhere. Remarkably, while reducing FLOPs by 70% and token count by 83%, MOSAIK matches the full-compute PixelDiT on GenEval and its DPG-Bench score drops by only 1.0 point. Compared to diverse efficiency paradigms, including temporal patch scheduling and feature caching, our approach delivers highly competitive performance at moderate budgets and consistently outperforms these baselines in highly constrained compute regimes.

arXiv

Invisible Shortcuts: Why Vision Encoders Know Your Camera

Vladan Stojnić, Ryan Ramos, Giorgos Kordopatis-Zilos, Noa Garcia, Giorgos Tolias

Deep vision models exploit shortcuts, relying on cues that correlate with supervision signals. Prior work has focused on visible biases, such as object-background or texture correlations. We identify a different source of shortcut learning: invisible metadata traces embedded at the pixel level, for metadata such as image processing and photo acquisition. We hypothesize that large-scale semantic supervision, whether through categorical labels (ImageNet) or billion-scale captions (LAION), naturally induces metadata-semantics correlations during pretraining, leading models to convert low-level signals into predictive features. By introducing controlled metadata-semantics correlations, we show that stronger ones produce systematically higher sensitivity to metadata traces and larger performance degradation under metadata distribution shifts. We further explore mitigation strategies applied during and after pretraining that reduce sensitivity not only to targeted metadata but also to unseen ones, without sacrificing performance on downstream tasks. Metadata sensitivity also has a positive side: it partly explains the strong generated-image detection ability of some encoders, while its mitigation can improve out-of-distribution generalization. Code: https://github.com/ryan-caesar-ramos/visual-encoder-traces

arXiv

Adapting Vision Foundation Models with Cascaded Semantics

Xi Xiao, Xingjian Li, Cheng Han, Tianyang Wang, Lin Zhao, Yunbei Zhang, Guosheng Hu, Runmin Jiang, Xi Li, Xiao Wang, Min Xu

Prompt tuning, a leading parameter-efficient adaptation paradigm in NLP, has recently been extended to computer vision. Visual prompt tuning (VPT) adapts pre-trained vision transformers (ViTs) by updating a small set of additional prompt parameters. However, existing visual prompts are randomly initialized and do not exploit prior knowledge, such as instructions in NLP. We address this gap by injecting two complementary semantic priors into VPT. Fundamental image priors, including color, texture, and shape, are extracted with classical hand-crafted operators and injected into the input space, while self-attention maps provide instance-aware semantics in the feature space. We further propose a cascaded scheme that integrates both priors throughout ViT adaptation. Experiments on 34 challenging image classification datasets demonstrate superior downstream adaptation while tuning only 0.74% of ViT parameters. Project page: https://xixiaouab.github.io/Cascaded-Semantics/.

arXiv

Text-Guided Refinement of Multi-sequence Glioma Subregion Segmentation with a Vision-Language Foundation Model

Zach Eidex, Yu-nong Lin, Mojtaba Safari, Sean Pitroda, Ralph Weichselbaum, Zhen Tian, Xiaofeng Yang

Background: Accurate glioma subregion delineation is important for radiotherapy planning and longitudinal monitoring, but manual contour correction is time-consuming. Models such as nnU-Net may generalize imperfectly and lack clinician-directed text correction. Purpose: We investigated adapting a three-dimensional (3D) vision-language foundation model for text-guided brain tumor segmentation refinement. Methods: We developed a lightweight VoxTell-based framework. Pretrained VoxTell generated initial masks. Oracle prompts derived from segmentation errors encoded target, action, location, imaging evidence, edit size, and preservation constraints. Frozen Qwen/VoxTell prompt embeddings were injected through trainable projections into its multiscale decoder conditioning; other weights remained frozen. Training, validation, and testing used 901, 100, and 250 BraTS-GLI cases. Cross-dataset transfer was evaluated on 100 meningioma, metastasis, pediatric tumor, and UPENN-GBM cases. Results: On the internal test set using post-contrast T1-weighted input, correct instructions improved subregion Dice similarity coefficient (DSC; enhancing tumor, edema, and necrotic/non-enhancing core) from $0.774\pm0.158$ to $0.796\pm0.137$. They outperformed blank prompts ($0.762\pm0.155$; Holm-adjusted $p<0.001$, $d_z=0.71$) and contradictory prompts ($0.770\pm0.163$; $p<0.001$, $d_z=0.48$). In cross-dataset testing, correct instructions improved DSC from $0.527\pm0.287$ to $0.550\pm0.278$ and outperformed contradictory instructions ($0.504\pm0.275$; $p<0.001$, $d_z=0.43$). Conclusion: A 3D vision-language foundation model can perform instruction-guided refinement of glioma subregion segmentations. Sensitivity to correct, blank, and contradictory prompts suggests text-dependent contour editing rather than nonspecific post-processing, supporting further evaluation as a clinician-in-the-loop tool.

arXiv

World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation

Yuhao Pan, Haosong Peng, Zhengshen Zhang, Zhengyang Yan, Yalun Dai, Fushuo Huo, Chujie Wang, Tianyu Qi, Xiucheng Wang, Nan Cheng, Wenchao Xu

Vision-language-action (VLA) models often treat main-view and wrist-view observations as parallel visual inputs, overlooking their distinct roles in robot manipulation. Fine-grained manipulation, however, benefits from anticipating how wrist-local interactions may evolve under the global task context. To address this limitation, we present World-to-Wrist VLA (W2-VLA), a VLA model for fine-grained robot manipulation with task-conditioned future wrist modeling. Given current multi-view observations and a task instruction, W2-VLA contextualizes a set of latent modeling tokens as a compact interface between the vision-language model and the wrist predictor. Conditioned on this interface and the observed wrist history, the predictor forecasts future wrist latents, which are transformed into future-aware context for action prediction. In addition, we introduce W2-CoT, a synthesis pipeline that produces structured annotations describing manipulation progress, physical transition cues, and wrist-local evidence. These annotations provide auxiliary supervision that shapes the task-conditioned latent interface. Experiments on LIBERO, RoboTwin 2.0, and real-world manipulation tasks demonstrate improved fine-grained and contact-sensitive manipulation across both single-arm and bimanual settings, while maintaining action-generation rates above 80 Hz.

arXiv

Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation

Yuta Kobayashi, Pradyun Ramesh, Muhammad Ahmed Chaudhry, Vincent Jeanselme, Judy Wawira Gichoya, Sanmi Koyejo, Kathleen Capaccione, Shalmali Joshi

Vision-Language Models (VLMs) for radiology report generation are typically trained on retrospective clinical reports, which suffer from omission noise: clinically present findings are left unreported due to the omission of subtle findings. For example, prior studies show that cardiomegaly may be omitted from ICU chest X-ray reports when the imaging request is focused on monitoring support device placement. As a result, models trained with standard approaches inherit these omissions, learning to under-report findings themselves. We propose PU-DPO, a preference optimization framework to prevent omission noise from corrupting the preference signal. We reformulate the objective under a positive-unlabeled (PU) learning framework, treating absent mentions as unlabeled rather than truly negative. Our framework provides preference supervision using constructed contrastive pairs, generated using edits to model responses, producing variants that explicitly mention or omit a specific finding. Generated responses that mention the finding are naturally preferred in the context of visual evidence. Across semi-synthetic experiments and analyses on real-world chest radiograph benchmarks where adjudicated labels are available, PU-DPO yields consistent gains in detection rates and recovery of hidden positives across multiple pathologies, and is more robust to omission noise than prior approaches.

arXiv

Context Matters: Support Set Selection and Failure Detection for In-Context Medical Image Segmentation

Youssef Gehad, Emmanuel Zerefa, Krish Kabra, Guha Balakrishnan

In-context learning (ICL) adapts medical image segmentation models to unseen structures and modalities without retraining by conditioning on a task-specific support set of image-mask exemplars. Because this support set is the model's only task-specific signal, its composition directly influences segmentation performance. In this work, we investigate the support set as a controllable determinant of ICL reliability. First, we compare random sampling against similarity-based selection, where exemplars are retrieved based on their visual similarity to the query image. Second, we train a transformer-based classifier to predict, from the query and support images alone, whether a segmentation will fall below a specified Intersection-over-Union (IoU) threshold. Using MultiverSeg with DINOv3 embeddings across four benchmarks and three imaging modalities, we show that similarity-based selection consistently matches or outperforms random sampling, with the largest gains at the smallest support set sizes. Furthermore, our classifier predicts segmentation failure above chance on all four benchmarks. Ultimately, these results demonstrate that the reliability of in-context segmentation can be both improved via informed support selection and anticipated before use, providing practical mechanisms for safer clinical deployment.

arXiv

Evaluating Machine Learning Models for Post-Wildfire Debris-Flow Prediction

Quinn Ledingham, Zhengsen Xu, Yimin Zhu, Zack Dewis, Mabel Heffring, Saeid Taleghanidoozdoozan, Motasem Alkayid, Megan Greenwood, Lincoln Linlin Xu

Prediction of post-wildfire debris flows is critical for mitigating hazards to communities, infrastructure, and resources during intense rainfall in recently burned areas. However, identifying reliable machine learning models is complicated by overlapping debris-flow and non-debris-flow events in feature space, the need for model interpretability, and limited training data. This paper addresses these challenges through a systematic evaluation of machine learning models in terms of predictive performance, feature importance, and synthetic data augmentation. Using basin-scale observations of post-wildfire debris-flow events across the western United States, we compare 15 models, including the Tabular Prior-Data Fitted Network (TabPFN). Repeated stratified cross-validation shows that TabPFN achieves the highest unaugmented performance with a threat score of 0.637, closely followed by the best tree-based models. SHapley Additive exPlanations (SHAP) are used to identify the features driving predictions, revealing that short-duration rainfall intensity and storm accumulation consistently rank highest, while burn severity and terrain features contribute less. We further evaluate synthetic data augmentation using TabPFN-generated samples to address the scarcity of debris-flow observations. Synthetic augmentation improves the performance of all models except CNN, with the largest mean threat score increase of +0.041 among the deep learning models. By combining rigorous model benchmarking, interpretable feature analysis, and synthetic data augmentation, this work provides a comprehensive framework for improving post-wildfire debris-flow prediction.

arXiv

A Paragraph is Worth a Thousand Captions: Rethinking Text Supervision for Vision-Language Retrieval

Mahyar Ghazanfari, Amin Tabrizian, Arsyi Aziz, Binshuai Wang, Peng Wei

Contrastive vision-language models such as CLIP and BLIP are typically trained on short image captions, limiting their ability to retrieve images from detailed textual descriptions. While methods such as Long-CLIP extend the token limit through positional embedding interpolation, we ask a simpler question: does training text granularity alone determine long-text retrieval performance? We present a systematic study of supervision ranging from single captions to multi-sentence paragraphs for contrastive image-text retrieval. Using a synthetic pipeline based on Qwen2-VL and Llama 3.2 Vision, we generate diverse captions, hard negatives, and quality-scored paragraphs for 500K CC3M images. To isolate the effect of text granularity, we fine-tune only the BLIP text encoder while keeping the vision encoder frozen across 10 training configurations. Our paragraph-supervised models match Long-CLIP-L on ShareGPT4V and outperform it by more than 14 points on DOCCI for image-to-text retrieval, without architectural changes. We further show that paragraph supervision enables effective use of long token sequences, whereas caption-only training degrades beyond 60 tokens. Increasing caption diversity improves short-caption retrieval with diminishing returns, while paragraph supervision consistently benefits long-description benchmarks and hard negatives prove detrimental in text-only fine-tuning. Evaluations on Flickr30k, COCO, ShareGPT4V, and DOCCI provide a comprehensive analysis of the trade-offs between text granularity, retrieval direction, and description length.

arXiv

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI

Casey Wall, Longwei Wang, Rodrigue Rizk, KC Santosh

Gradient-weighted Class Activation Mapping (Grad-CAM) is widely used to visualize model decisions, but it was originally formulated for convolutional neural networks, where spatial feature maps and channel dimensions have clear architectural meanings. Vision Transformers (ViTs) do not provide the same structure, instead representing images through tokens, attention, residual streams, and multimodal interactions. This paper presents a systematic taxonomy and literature audit of how Grad-CAM and related methods are adapted, justified, and reported for ViT-based architectures. From an initial search of more than 550 papers, we identify 175 papers that apply Grad-CAM or Grad-CAM-adjacent methods to ViTs. We find that most papers do not provide a full mathematical or implementation-level account of how Grad-CAM is adapted to transformer representations. To characterize this gap, we introduce a descriptive taxonomy of ViT Grad-CAM adaptations that makes explicit the feature locations, gradient targets, spatial reconstruction steps, and aggregation choices that are often left implicit. This taxonomy is not intended to prescribe a single correct adaptation, but to clarify the range of methodological choices being made. The study shows that Grad-CAM on ViTs is often treated as a trivial extension of CNN-based Grad-CAM, despite requiring nontrivial choices that affect rigor, reproducibility, and interpretation.

arXiv

WorldClaw: Agentic 3D Open-World Generation at Scale

Chunchao Guo, Jinpeng Li, Yang Li, Zilong Huang

Generating large-scale, freely explorable 3D worlds from open-ended text remains challenging because a system must jointly maintain global spatial coherence, rich local content, and explicit assets suitable for downstream editing and reuse. We present WorldClaw, a fully agentic, coarse-to-fine framework for open-world 3D scene generation. Planning agents translate a text prompt into a structured specification of regions, terrain, assets, materials, and spatial relations. WorldClaw then builds a globally coherent terrain foundation from semantic layouts, reusable assets, generative or procedural materials, and a region-aware height field. For detail-demanding regions, it generates terrain-conditioned compositions, reconstructs editable textured meshes, and recovers their placement on the terrain; render-based agents further refine terrain, objects, appearance, and contacts. Across diverse open-world prompts, WorldClaw produces large-scale scenes with coherent spatial organization, visually compelling local content, and editable instance-level assets while preserving a consistent global terrain structure.

arXiv

In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion

Lingxiao Yang, Liu Liu, Moran Li, Han Feng, Wenjian Cao, Jiangning Zhang, Ye Shi

Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the current frame. However, these clean frames leak excessive local details, which causes the model to take shortcuts, resulting in compromised temporal semantics and dynamics. Inspired by the perspective of diffusion as masking, we explore the impact of noisy contexts on few-step autoregressive generation. Yet, simply applying contexts with the same noise levels provides insufficient guidance, leading to poor temporal consistency. To resolve this dilemma, we introduce In-Context Forcing, a progressive autoregressive paradigm that utilizes contexts with decreasing noise levels. By applying less masking to distant frames and more masking to adjacent ones, this approach provides adaptive guidance, effectively ensuring both robust temporal consistency and high inter-frame dynamics. Furthermore, by decoupling the strict dependence on previous clean frames, our paradigm enables cross-frame parallel denoising, achieving substantial inference acceleration without sacrificing performance. Extensive experiments on VBench demonstrate that our method significantly outperforms state-of-the-art approaches in both visual fidelity and inference speed.

arXiv

Coherence-Oriented Dream Scene Visualisation

Azra Açıl, Simon Colton

Dreams can be emotionally intense but difficult to communicate. We describe the Dream Scene Visualiser (DSV) system which turns written dream descriptions into a temporal sequence of four panel images visualising the dream. This starts with a large language model prompted to split a dream description into four chronological parts. Then a text-to-image model produces images for each part with visual coherence maintained across the sequence, and DSV regenerates any image not suitably matching the text. We evaluate DSV over 50 visualisations from dream descriptions in DreamBank, and report quality, fidelity and coherence results via objective measures employing the CLIP, DINOv2 and Qwen2-VL vision-language models.

arXiv

NeuroAdaptTrainer: A Fiji/ImageJ Plugin for YOLO-Based Neuron Segmentation, InteractiveCorrection and Transfer Learning

Daniela Eraso-Casas, Gerard Villarroya-Pique, Esther Serrano-Pertierra, M. Teresa Fernández-Sánchez, Antonello Novellie, Angel Rio-Alvarez, Víctor M. González

Neuron counting and segmentation in microscopy images of neuronal cultures is a routine and time-consuming task in neuroscience research, traditionally performed through manual inspection or semi-automatic tools. We present NeuroAdaptTrainer, an open-source Fiji/ImageJ plugin that integrates a YOLO instance-segmentation model directly into the microscopist's workflow. The plugin allows a user to run automatic neuron detection on a single image or a batch of images, manually correct the resulting detections from within Fiji, and use those corrections to adapt the model to new imaging conditions via transfer learning. A built-in external validation module allows the base and adapted models to be compared quantitatively on a held-out annotated set. NeuroAdaptTrainer lowers the barrier for non-specialist users to benefit from deep-learning-based segmentation while keeping expert supervision at the center of the workflow.

arXiv

A Survey of Adversarial Efficiency Degradation for Vision Transformer by Exploiting Input-adaptive Optimization

Anadi Goyal, Nandish Chattopadhyay, Anupam Chattopadhyay, Chandan Karfa

Vision Transformers (ViTs) increasingly rely on input-adaptive inference, such as token pruning and early halting, to meet energy and latency budgets. This survey examines a recent class of adversarial efficiency degradation attacks that target these mechanisms to increase computation without necessarily degrading accuracy. We unify and compare two representative attacks, SlowFormer (a universal adversarial patch) and DeSparsify (per-image perturbations), across three popular token-pruning frameworks: A-ViT, ATS, and AdaViT. We standardize reporting using GFLOPs, accuracy loss, and an Attack Success (AS) metric that measures how much of the model's compute savings the attack takes away. Understanding these attacks is crucial for designing countermeasures that not only mitigate risk but also remain lightweight, since deployment often occurs in low-power settings such as mobile or embedded devices. To organize our analysis, we focus on three questions: how input-adaptive optimizations (e.g., token pruning and early halting) create attack surfaces for efficiency degradation; how such attacks operate in practice and which optimizations are most vulnerable; and which defenses exist today and whether they meaningfully restore efficiency under attack.

arXiv

VLAff: Vision-Language-Affordance Model for Unified Actionable Affordances

Jihoon Oh, Kento Kawaharazuka, Kei Okada

Learning manipulation skills from human videos is promising for scalable robot learning. However, the embodiment mismatch between humans and robots makes this challenging. One promising solution is to learn object-centric actionable affordances that are embodiment-agnostic. In this work, we propose a framework that leverages egocentric human videos with state-of-the-art 3D Structure-from-Motion and hand mesh reconstruction to extract actionable affordances such as visual, grasp, and trajectory affordances that explicitly encode where to interact, how to grasp, and how to move. We construct EgoAffordance, a large-scale dataset comprising 204K episodes with 5.6M visual affordances and 11.6M grasp and trajectory affordances. Building on this, we introduce VLAff, a large vision-language model-based unified foundation model that learns cross-modal correlations across all actionable affordances. Given a visual observation and instruction, VLAff generates visual affordance heatmaps, grasp poses, and trajectories, which are then converted into directly executable actions by utilizing 3D scene information. Through extensive experiments, we demonstrate that VLAff not only achieves state-of-the-art performance on visual affordance prediction, but can also be effectively applied to real robot applications such as zero-shot manipulation and affordance-guided robot learning.

arXiv

StyleComposer: Training-Free Multi-Reference Style Composition

Sanghyeok Lee, Jihye Kang, Namhyuk Ahn

The style of a painting is not monolithic: color, texture, and structure may come from different sources. Existing reference-guided methods transfer them as one style signal, leaving each attribute's source and strength outside the user's control. We ask where in a diffusion model one attribute can change while the others hold, and find that no single representation isolates all three. The proposed StyleComposer therefore routes each style attribute through the representation where it separates best and coordinates the routes over denoising time. Without training or inversion, it satisfies three references and the prompt jointly more closely than prior methods, and exposes one strength slider per attribute. Project page: https://lexxsh.github.io/StyleComposer

arXiv

Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation

Ye Leng, Junjie Chu, Yiting Qu, Mingjie Li, Yun Shen, Yang Zhang

Picture books and comics have long been used to disseminate hateful narratives because they are easily understood even by children, as exemplified by the notorious Nazi propaganda picture book \emph{Der Giftpilz}. Recently, frontier text-to-image (T2I) systems such as Gemini and GPT-Image have enabled conversational generation with consistent characters and scenes across turns, making hateful visual stories, namely ordered image groups that collectively convey hateful narratives, cheap and scalable to produce. Although prior work has studied hateful content generation by T2I systems, it focuses on individual images, leaving group-level hateful meaning largely unexplored. We aim to address the gap. Concretely, we introduce \texttt{HatefulStoryPrompts}, comprising 330 multi-turn configurations from 55 hateful stories across two languages and three visual styles, and evaluate five frontier models over 4,950 attempts. Every model completes over 80\% of the stories, with the strongest reaching 99.0\%. We further evaluate existing moderation systems on \texttt{HatefulVisualStory}, a human-labeled dataset of 969 hateful image sets and 990 benign controls, and find that they frequently miss group-level hateful meaning: dedicated safety models achieve at most 34.9\% recall, while a strong vision-language model reaches 67.5\%. Finally, we propose complementary proactive and post-generation defenses. An interaction-aware monitor achieves 97.3\% recall for prompt-only sessions and 92.6\% when the user supplies the first image, while post-generation methods jointly analyzing completed image groups reach 80.2\%. Our work shows that, as image generation evolves from isolated outputs to coherent visual narratives, safety must evolve accordingly, from per-image moderation to stateful reasoning over interactions and image relationships.

arXiv

MapTCL: Temporal Consistency Learning via Bidirectional Alignment for Vectorized HD Map Construction

Hyeonseo Kim, Juyeb Shin, Hyeonjun Jeong, Hiwon Shin, Dongsuk Kum

Constructing reliable online HD maps remains challenging in dynamic urban environments due to moving objects and occlusions. While recent works employ feature-level temporal fusion to address this, they rely solely on per-frame ground truth supervision. Consequently, they lack an explicit objective to directly penalize the geometric noise and temporal jitter between consecutive online HD maps. To address this, we propose MapTCL, an auxiliary training strategy that formulates temporal consistency loss between current and past frames via bidirectional alignment. Specifically, Bidirectional Vector Consistency Learning (BVCL) models the geometric and semantic discrepancies between associated past and current vector instances as an auxiliary loss. We also employ Raster map Consistency Learning (RCL) as an additional loss to stabilize dense BEV features. By jointly training with these dual losses, MapTCL improves the temporal stability of generated HD maps. Extensive experiments on two standard benchmarks demonstrate the effectiveness of our approach. As a versatile plug-and-play module, MapTCL consistently enhances existing baseline models, achieving gains of +3.7 mAP & +2.8 C-mAP on nuScenes and +3.1 mAP & +2.5 C-mAP on Argoverse 2 without additional inference overhead.

arXiv

EA-Nav: Learning Safe Visual Navigation Policies with Embodiment Awareness

JIALU ZHANG, Yong Du, Xianda Guo, Shunwang Sun, Xinqi Liu, Yue Sun, Guodong Lu, Wei Sui, Jituo Li

Cross-embodiment navigation is a key challenge in embodied intelligence. Due to differences in embodiment, the same visual observation may imply different actions for different agents, making prediction ambiguous when relying solely on vision. Existing studies mainly rely on reinforcement learning, which requires large-scale interaction and careful reward design, making it difficult to support scalable pretraining and real-world adaptation. In contrast, imitation-learning-based approaches remain limited. To address these challenges, we propose an imitation-learning-based embodiment-aware navigation framework with a modular multi-stage design. In pretraining, we construct a cross-embodiment navigation dataset from Internet videos and introduce embodiment geometry as conditional tokens to reduce action ambiguity under the same observation. In fine-tuning, we design a multimodal information injection mechanism based on a decoupled architecture. Specifically, we design a trajectory augmentation strategy to generate high-risk samples, which are used to train spatial perception and risk-aware correction separately, thereby explicitly incorporating embodiment geometry for safe navigation. Experimental results show that the proposed method effectively improves navigation performance across different embodiment settings, demonstrating the effectiveness of incorporating embodiment geometry into embodied navigation.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.