论文检索

Computer Vision · Vision Models & Multimodal

Yepeng Tang, Weining Wang, Longteng Guo, Tongtian Yue, Wenxuan Wang, Chunjie Zhang, Jing Liu

Recent advances in Video LLMs have improved video understanding performance, but temporally grounded understanding in long-form videos remains challenging. Most models encode video frames into a flat sequence of visual tokens, which are then processed together with textual input by the LLM. While effective for short videos, this approach becomes inefficient for long-form videos due to lengthy token sequences that exceed context limits and incur high computational costs. Slow-Fast architectures partially address this by separating temporal and spatial features during encoding, but these features are still processed jointly within the LLM, lacking true spatio-temporal disentanglement. Moreover, spatial features are typically sampled in a query-agnostic manner, risking the loss of task-relevant content. To address these limitations, we propose Divid, a novel dual-branch framework that explicitly disentangles spatial and temporal modeling within the LLM decoder. Specifically, the temporal branch processes densely sampled, low-resolution frames to effectively capture long-range motion dynamics, while the spatial branch selects a sparse set of high-resolution keyframes guided by temporal attention. To unify the two branches, we design a lightweight spatio-temporal soft-router that adaptively fuses temporal and spatial cues at the token level, conditioned on the input query. This disentangled architecture not only improves temporal alignment accuracy but also leads to computational savings by minimizing redundant visual processing. Furthermore, we introduce TempGCap, a large-scale dataset consisting of 559K timestamp-grounded video-text pairs, providing rich temporal supervision. Extensive experiments on temporal grounding and grounded videoQA benchmarks demonstrate the superior performance and efficiency of our proposed Divid.

Computer Vision · Image and Video Generation

Kang Liao, Size Wu, Zhonghua Wu, Linyi Jin, Chao Wang, Yikai Wang, Fei Wang, Wei Li, Chen Change Loy

Camera-centric understanding and generation are two cornerstones of spatial intelligence, yet they are typically studied in isolation. We present Puffin, a unified camera-centric multimodal model that extends spatial awareness along the camera dimension. Puffin integrates language regression and diffusion-based generation to interpret and create scenes from arbitrary viewpoints. To bridge the modality gap between cameras and vision-language, we introduce a novel paradigm that treats camera as language, enabling thinking with camera. This guides the model to align spatially grounded visual cues with photographic terminology while reasoning across geometric context. Puffin is trained on Puffin-4M, a large-scale dataset of 4 million vision-language-camera triplets. We incorporate both global camera parameters and pixel-wise camera maps, yielding flexible and reliable spatial generation. Experiments demonstrate Puffin’s superior performance over specialized models for camera-centric generation and understanding. With instruction tuning, Puffin generalizes to diverse cross-view tasks such as spatial imagination, world exploration, and photography guidance. We will release the code, models, dataset pipeline, and benchmark to advance multimodal spatial intelligence research.

Computer Vision · Image and Video Generation

Haoran Bai, Xiaoxu Chen, Canqian Yang, Zongyao He, Sibin Deng, Ying Chen

We present Vivid-VR, a DiT-based generative video restoration method built upon an advanced T2V foundation model, where ControlNet is leveraged to control the generation process, ensuring content consistency. However, conventional fine-tuning of such controllable pipelines frequently suffers from distribution drift due to limitations in imperfect multimodal alignment, resulting in compromised texture realism and temporal coherence. To tackle this challenge, we propose a concept distillation training strategy that utilizes the pretrained T2V model to synthesize training samples with embedded textual concepts, thereby distilling its conceptual understanding to preserve texture and temporal quality. To enhance generation controllability, we redesign the control architecture with two key components: 1) a control feature projector that filters degradation artifacts from input video latents to minimize their propagation through the generation pipeline, and 2) a new ControlNet connector employing a dual-branch design. This connector synergistically combines MLP-based feature mapping with cross-attention mechanism for dynamic control feature retrieval, enabling both content preservation and adaptive control signal modulation. Extensive experiments show that Vivid-VR performs favorably against existing approaches on both synthetic and real-world benchmarks, as well as AIGC videos, achieving impressive texture realism, visual vividness, and temporal consistency. The codes and checkpoints are publicly available at https://github.com/csbhr/Vivid-VR.

Applications · Language, Speech and Dialog

Zihan Zhang, Xize Cheng, Zhennan Jiang, Dongjie Fu, Jingyuan Chen, Zhou Zhao, Tao Jin

Universal sound separation faces a fundamental misalignment: models optimized for low-level signal metrics often produce semantically contaminated outputs, failing to suppress perceptually salient interference from acoustically similar sources. We introduce a preference alignment perspective, analogous to aligning LLMs with human intent. To address this, we introduce MARS-Sep, a reinforcement learning framework that reformulates separation as decision making. Instead of simply regressing ground-truth masks, MARS-Sep learns a factorized Beta mask policy that is steered by a preference reward model and optimized by a stable, clipped trust-region surrogate. The reward, derived from a progressively-aligned audio-text-vision encoder, directly incentivizes semantic consistency with query prompts. Extensive experiments on multiple benchmarks demonstrate consistent gains in Text-, Audio-, and Image-Queried separation, with notable improvements in signal metrics and semantic quality. Our code is available at https://github.com/mars-sep/MARS-Sep. Sound separation samples are available at https://mars-sep.github.io/.

Applications · Robotics

Shuang Zeng, Dekang Qi, Xinyuan Chang, Feng Xiong, Shichao Xie, Xiaolong Wu, Shiyi Liang, Mu Xu, Xing Wei

Vision-and-Language Navigation (VLN) requires an embodied agent to navigate through unseen environments, guided by natural language instructions and a continuous video stream. Recent advances in VLN have been driven by the powerful semantic understanding of Multimodal Large Language Models (MLLMs). However, these methods typically rely on explicit semantic memory, such as building textual cognitive maps or storing historical visual frames. This type of method suffers from spatial information loss, computational redundancy, and memory bloat, which impede efficient navigation. Inspired by the implicit scene representation in human navigation, analogous to the left brain's semantic understanding and the right brain's spatial cognition, we propose JanusVLN, a novel VLN framework featuring a dual implicit neural memory that models spatial-geometric and visual-semantic memory as separate, compact, and fixed-size neural representations. This framework first extends the MLLM to incorporate 3D prior knowledge from the spatial-geometric encoder, thereby enhancing the spatial reasoning capabilities of models based solely on RGB input. Then, the historical key-value (KV) caches from the spatial-geometric and visual-semantic encoders are constructed into a dual implicit memory. By retaining only the KVs of tokens in the initial and sliding window, redundant computation is avoided, enabling efficient incremental updates. Extensive experiments demonstrate that JanusVLN outperforms over 20 recent methods to achieve SOTA performance. For example, the success rate improves by 10.5-35.5 compared to methods using multiple data types as input and by 3.6-10.8 compared to methods using more RGB training data. This indicates that the proposed dual implicit neural memory, as a novel paradigm, explores promising new directions for future VLN research.

Computer Vision · Vision Models & Multimodal

Wenzhe Yin, Zehao Xiao, Pan Zhou, Shujian Yu, Jiayi Shen, Jan-jakob Sonke, Efstratios Gavves

Vision-language alignment is crucial for various downstream tasks such as cross-modal generation and retrieval. Previous multimodal approaches like CLIP utilize InfoNCE to maximize mutual information, primarily aligning pairwise samples across modalities while overlooking distributional differences. In addition, InfoNCE has inherent conflict in terms of alignment and uniformity in multimodality, leading to suboptimal alignment with modality gaps. To overcome the limitations, we propose CS-Aligner, a novel framework that performs distributional vision-language alignment by integrating Cauchy-Schwarz (CS) divergence with mutual information. CS-Aligner captures both the global distribution information of each modality and the pairwise semantic relationships. We find that the CS divergence seamlessly addresses the InfoNCE's alignment-uniformity conflict and serves complementary roles with InfoNCE, yielding tighter and more precise alignment. Moreover, by introducing distributional alignment, CS-Aligner enables incorporating additional information from unpaired data and token-level representations, enhancing flexible and fine-grained alignment in practice. Experiments on text-to-image generation and cross-modality retrieval tasks demonstrate the effectiveness of our method on vision-language alignment.

Computer Vision · Vision Models & Multimodal

Xinmiao Huang, Qisong He, Zhenglin Huang, Boxuan Wang, Zhuoyun Li, Guangliang Cheng, Yi Dong, Xiaowei Huang

Spatial reasoning ability is crucial for Vision Language Models (VLMs) to support real-world applications in diverse domains including robotics, augmented reality, and autonomous navigation. Unfortunately, existing benchmarks are inadequate in assessing spatial reasoning ability, especially the \emph{intrinsic-dynamic} spatial reasoning which is a fundamental aspect of human spatial cognition. In this paper, we propose a unified benchmark, \textbf{Spatial-DISE}, based on a cognitively grounded taxonomy that categorizes tasks into four fundamental quadrants: \textbf{I}ntrinsic-\textbf{S}tatic, Intrinsic-\textbf{D}ynamic, \textbf{E}xtrinsic-Static, and Extrinsic-Dynamic spatial reasoning. Moreover, to address the issue of data scarcity, we develop a scalable and automated pipeline to generate diverse and verifiable spatial reasoning questions, resulting in a new \textbf{Spatial-DISE} dataset that includes Spatial-DISE Bench (559 evaluation VQA pairs) and Spatial-DISE-12K (12K+ training VQA pairs). Our comprehensive evaluation across 32 state-of-the-art VLMs reveals that, current VLMs have a large and consistent gap to human competence, especially on multi-step multi-view spatial reasoning. Spatial-DISE offers a robust framework, valuable dataset, and clear direction for future research toward human-like spatial intelligence. Benchmark, dataset, and code are available at https://shinmohuang.github.io/spatialdise_page/Spatial-DISE .

Haijier Chen, Bo Xu, Shoujian zhang, Haoze Liu, Jiaxuan Lin, Jingrong Wang

Recent developments in Multimodal Large Language Models (MLLMs) have significantly improved Vision–Language (VL) reasoning in 2D domains. However, extending these capabilities to 3D scene understanding remains a major challenge. Existing 3D Multimodal Large Language Models (3D-MLLMs) often depend on 3D data inputs, which limits scalability and generalization. To address this limitation, we propose Vid-LLM, a video-based 3D-MLLM that directly processes video inputs without requiring external 3D data, making it practical for real-world deployment. In our method, the geometric prior are directly used to improve the performance of the sceen perception. To integrate the geometric cues into the MLLM compactly, we design a Cross-Task Adapter (CTA) module to align the 3D geometric priors with the vision-language representations. To ensure geometric consistency and integrity, we introduce a Metric Depth Model that recovers real-scale geometry from the reconstruction outputs. Finally, the model is fine-tuned with a two-stage distillation optimization strategy, realizing fast convergence and stabilizes training. Extensive experiments across diverse benchmarks verified the effectiveness of our method on 3D Question Answering, 3D Dense Captioning and 3D Visual Grounding tasks, demonstrating the superior multi-task capabilities.

Computer Vision · Vision Models & Multimodal

Haijier Chen, Bo Xu, Shoujian zhang, Haoze Liu, Jiaxuan Lin, Jingrong Wang

Recent developments in Multimodal Large Language Models (MLLMs) have significantly improved Vision–Language (VL) reasoning in 2D domains. However, extending these capabilities to 3D scene understanding remains a major challenge. Existing 3D Multimodal Large Language Models (3D-MLLMs) often depend on 3D data inputs, which limits scalability and generalization. To address this limitation, we propose Vid-LLM, a video-based 3D-MLLM that directly processes video inputs without requiring external 3D data, making it practical for real-world deployment. In our method, the geometric prior are directly used to improve the performance of the sceen perception. To integrate the geometric cues into the MLLM compactly, we design a Cross-Task Adapter (CTA) module to align the 3D geometric priors with the vision-language representations. To ensure geometric consistency and integrity, we introduce a Metric Depth Model that recovers real-scale geometry from the reconstruction outputs. Finally, the model is fine-tuned with a two-stage distillation optimization strategy, realizing fast convergence and stabilizes training. Extensive experiments across diverse benchmarks verified the effectiveness of our method on 3D Question Answering, 3D Dense Captioning and 3D Visual Grounding tasks, demonstrating the superior multi-task capabilities.

Social Aspects · Fairness, Equity, Justice and Safety

Shruti Palaskar, Leon Gatys, Mona Abdelrahman, Mar Jacobo, Laurence Lindsey, Rutika Moharir, Gunnar Lund, Yang Xu, Navid Shiee, Jeffrey Bigham 等

Safety evaluation of multimodal foundation models often treats vision and language inputs separately, missing risks from joint interpretation where benign content becomes harmful in combination. Existing approaches also fail to distinguish clearly unsafe content from borderline cases, leading to problematic over-blocking or under-refusal of genuinely harmful content. We present Vision Language Safety Understanding (VLSU), a comprehensive framework to systematically evaluate multimodal safety through fine-grained severity classification and combinatorial analysis across 17 distinct safety patterns. Using a multi-stage pipeline with real-world images and human annotation, we construct a large-scale benchmark of 8,187 samples spanning 15 harm categories. Our evaluation of eleven state-of-the-art models reveals systematic joint understanding failures: while models achieve 90\%+ accuracy on clear unimodal safety signals, performance degrades substantially to 20-55\% when joint image-text reasoning is required to determine the safety label. Most critically, 34\% of errors in joint image-text safety classification occur despite correct classification of the individual modalities, further demonstrating absent compositional reasoning capabilities. Additionally, we find that models struggle to balance refusing unsafe content while still responding to borderline cases that deserve engagement. For example, we find that instruction framing can reduce the over-blocking rate on borderline content from 62.4\% to 10.4\% in Gemini-1.5, but only at the cost of under-refusing on unsafe content with refusal rate dropping from 90.8\% to 53.9\%. Overall, our framework exposes weaknesses in joint image-text understanding and alignment gaps in current models, and provides a critical test bed to enable the next milestones in research on robust vision–language safety.

xinyan cai, Qiang Guan, Shiguang Wu, DaFeng Chi, Yuzheng Zhuang, Xingyue Quan, Jianye Hao

In complex embodied long-horizon manipulation tasks, effective task decomposition and execution require synergistic integration of textual logical reasoning and visual-spatial imagination to ensure efficient and accurate operation. Current methods fail to adopt a unified generation framework for multimodal planning, leading to inconsistencies in multimodal planning. To address this challenge, we present EVLP (Embodied Vision-Language Planner), an innovative multimodal unified generation framework that jointly models linguistic reasoning and visual generation. Our approach achieves multimodal planning for long-horizon tasks through a novel training pipeline incorporating dynamic pretraining and reinforced alignment. Our core innovations consist of three key components: 1. Unified Multimodal Generation Framework: For understanding, we integrate semantic information with spatial features to provide comprehensive visual perception. For generation, we directly learn the joint distribution of discrete images for one-step visual synthesis, enabling coordinated language-visual modeling through learnable cross-modal attention mechanisms. 2. Dynamic Perception Pretraining: We propose a bidirectional dynamic alignment strategy employing inverse dynamics tasks and forward dynamics tasks, effectively strengthening multimodal correlations within a unified feature space. 3. Reinforced Supervised Fine-Tuning: While conducting instruction-based fine-tuning in the unified generation space, we construct a reinforce loss to align the spatial logic between textual actions and generated images, enabling the model to acquire spatio-aware multimodal planning capabilities.Comprehensive evaluations on multiple complex tasks demonstrate that EVLP significantly outperforms competitive baselines in both instruction execution accuracy and task success rate, benefiting from its unified multimodal architecture and well-designed training pipeline. Extensive ablation studies further validate the rationality of our framework design.

Computer Vision · Vision Models & Multimodal

Hari Krishna Gadi, Daniel Matos, Hongyi Luo, Lu Liu, Yongliang Wang, Yanfeng Zhang, Liqiu Meng

Visual geolocalization, the task of predicting where an image was taken, remains challenging due to global scale, visual ambiguity, and the inherently hierarchical structure of geography. Existing paradigms rely on either large-scale retrieval, which requires storing a large number of image embeddings, grid-based classifiers that ignore geographic continuity, or generative models that diffuse over space but struggle with fine detail. We introduce an entity-centric formulation of geolocation that replaces image-to-image retrieval with a compact hierarchy of geographic entities embedded in Hyperbolic space. Images are aligned directly to country, region, subregion, and city entities through Geo-Weighted Hyperbolic contrastive learning by directly incorporating haversine distance into the contrastive objective. This hierarchical design enables interpretable predictions and efficient inference with 240k entity embeddings instead of over 5 million image embeddings on the OSV5M benchmark, on which our method establishes a new state-of-the-art performance. Compared to the current methods in the literature, it reduces mean geodesic error by 19.5\%, while improving the fine-grained subregion accuracy by 43\%. These results demonstrate that geometry-aware hierarchical embeddings provide a scalable and conceptually new alternative for global image geolocation.

Xinchen Zhang, Xiaoying Zhang, Youbin Wu, Yanbin Cao, Renrui Zhang, Ruihang Chu, Ling Yang, Yujiu Yang, Guang Shi

We introduce *Generative Universal Verifier*, a novel concept and plugin designed for next-generation multimodal reasoning in vision-language models and unified multimodal models, providing the fundamental capability of reflection and refinement on visual outcomes during the reasoning and generation process. This work makes three main contributions: (1) We build **ViVerBench**, a comprehensive benchmark spanning $16$ categories of critical tasks for evaluating visual outcomes in multimodal reasoning. Results show that existing VLMs consistently underperform across these tasks, underscoring a substantial gap from human-level capability in reliable visual verification. (2) We design two automated pipelines to construct large-scale visual verification data and train **OmniVerifier-7B**, the first omni-capable generative verifier trained for universal visual verification and achieves notable gains on ViVerBench(+$8.3$). Through training, we identify three atomic capabilities in visual verification and demonstrate how they generalize and interact synergistically. (3) We propose **OmniVerifier-TTS**, a sequential test-time scaling paradigm that leverages the universal verifier to bridge image generation and editing within unified models, enhancing the upper bound of generative ability through iterative fine-grained optimization. Beyond generation, we extend universal verifier to broader world-modeling interleaved reasoning scenarios. Empirically, OmniVerifier-TTS achieves improvements on T2I-ReasonBench(+$3.7$), and GenEval++(+$4.3$), outperforming existing parallel test-time scaling methods, such as Best-of-N. By endowing multimodal reasoning with reliable visual verification, OmniVerifier advances both reliable reflection during generation and scalable test-time refinement, marking a step toward more trustworthy and controllable next-generation reasoning systems.

Computer Vision · Vision Models & Multimodal

Bozhou Li, Xinda Xue, Sihan Yang, Yang Shi, Xinlong Chen, Yushuo Guan, Yuanxing Zhang, Wentao Zhang

Multimodal Large Language Models (MLLMs), which couple pre-trained vision encoders and language models, have shown remarkable capabilities. However, their reliance on the ubiquitous Pre-Norm architecture introduces a subtle yet critical flaw: a severe norm disparity between the high-norm visual tokens and the low-norm text tokens. In this work, we present a formal theoretical analysis demonstrating that this imbalance is not a static issue. Instead, it induces an "asymmetric update dynamic", where high-norm visual tokens exhibit a ''representational inertia,'' causing them to transform semantically much slower than their textual counterparts. This fundamentally impairs effective cross-modal feature fusion. Our empirical validation across a range of mainstream MLLMs confirms that this theoretical dynamic---the persistence of norm disparity and the resulting asymmetric update rates---is a prevalent phenomenon. Based on this insight, we propose a remarkably simple yet effective solution: inserting a single, carefully initialized LayerNorm layer after the visual projector to enforce norm alignment. Experiments conducted on the LLaVA-1.5 architecture show that this intervention yields significant performance gains not only on a wide suite of multimodal benchmarks but also, notably, on text-only evaluations such as MMLU, suggesting that resolving the architectural imbalance leads to a more holistically capable model.

Computer Vision · 3D Rendering & Reconstruction

Binzhu Xie, Shi Qiu, Sicheng Zhang, Yinqiao Wang, Hao Xu, Muzammal Naseer, Chi-Wing Fu, Pheng-Ann Heng

Robust 3D hand reconstruction is challenging in egocentric vision due to depth ambiguity, self-occlusion, and complex hand-object interactions. Prior works attempt to mitigate the challenges by scaling up training data or incorporating auxiliary cues, often falling short of effectively handling unseen contexts. In this paper, we introduce EgoHandICL, the first in-context learning (ICL) framework for 3D hand reconstruction that achieves strong semantic alignment, visual consistency, and robustness under challenging egocentric conditions. Specifically, we develop (i) complementary exemplar retrieval strategies guided by vision–language models (VLMs), (ii) an ICL-tailored tokenizer that integrates multimodal context, and (iii) a Masked Autoencoders (MAE)-based architecture trained with 3D hand–guided geometric and perceptual objectives. By conducting comprehensive experiments on the ARCTIC and EgoExo4D benchmarks, our EgoHandICL consistently demonstrates significant improvements over state-of-the-art 3D hand reconstruction methods. We further show EgoHandICL’s applicability by testing it on real-world egocentric cases and integrating it with EgoVLMs to enhance their hand–object interaction reasoning. Our code and data will be publicly available.

Computer Vision · Vision Models & Multimodal

Haochen Zhou, Guofeng Ding, Mouxing Yang, Peng Hu, Yijie Lin, Xi Peng

Multi-view clustering (MVC) aims to group unlabeled data into semantically meaningful clusters by leveraging cross-view consistency. However, real-world datasets collected from the web often suffer from noisy correspondence (NC), which breaks the consistency prior and results in unreliable alignments. In this paper, we identify two critical forms of NC that particularly harm clustering: i) category-level mismatch, where semantically consistent samples from the same class are mistakenly treated as negatives; and ii) sample-level mismatch, where collected cross-view pairs are misaligned and some samples may even lack any valid counterpart. To address these challenges, we propose \textbf{CorreGen}, a generative framework that formulates noisy correspondence learning in MVC as maximum likelihood estimation over underlying cross-view correspondences. The objective is elegantly solved via an Expectation–Maximization algorithm: in the E-step, soft correspondence distributions are inferred across views, capturing class-level relations while adaptively down-weighting noisy or unalignable samples through GMM-guided marginals; in the M-step, the embedding network is updated to maximize the expected log-likelihood. Extensive experiments on both synthetic and real-world noisy datasets demonstrate that our method significantly improves clustering robustness. The code is available at [https://github.com/XLearning-SCU/2026-ICLR-CorreGen](https://github.com/XLearning-SCU/2026-ICLR-CorreGen).

Ang Li, Charles L. Wang, Deqing Fu, Kaiyu Yue, Zikui Cai, Wang Zhu, Ollie Liu, Peng Guo, Willie Neiswanger, Furong Huang 等

Humans often rely on visual aids, such as diagrams or sketches, when tackling complex problems. Teaching multimodal models to adopt similar strategies, a process known as Visual Chain of Thought (visual CoT), is much more difficult. The main challenges are: (1) weak performance of off-the-shelf visual CoT, which hinders reinforcement learning, and (2) the lack of high-quality visual CoT training data. We introduce **Zebra-CoT** a diverse large-scale interleaved text-image reasoning dataset with 182,384 reasoning traces across 18 domains with over 50 distinct tasks. This dataset is specifically designed to train models to natively perform visual CoT. We emphasize four categories of tasks where sketching or visual reasoning is especially natural, spanning (a) *scientific questions* such as geometry, physics, and algorithms; (b) *2D visual reasoning tasks* like visual search and jigsaw puzzles; (c) *3D reasoning tasks* including 3D multi-hop inference, embodied and robot planning; and (d) *visual logic problems and strategic games* like chess. Fine-tuning Anole‑7B model on Zebra-CoT yields a +12\% improvement in our test‑set accuracy and up to +13\% performance gains on standard VLM benchmarks. Similarly, fine-tuning Bagel‑7B produces models capable of generating high-quality interleaved visual reasoning chains, underscoring Zebra-CoT's effectiveness in advancing multimodal reasoning.

Computer Vision · Vision Models & Multimodal

Grégoire DHIMOÏLA, Thomas Fel, Victor Boutin, Agustin Picard

Vision–language models (VLMs) align images and text with remarkable success, yet the geometry of their shared embedding space remains poorly understood. To probe this geometry, we begin from the Iso-Energy Assumption, which exploits cross-modal redundancy: a concept that is truly shared should exhibit the same average energy across modalities. We operationalize this assumption with an Aligned Sparse Autoencoder (SAE) that encourages energy consistency during training while preserving reconstruction. We find that this inductive bias changes the SAE solution without harming reconstruction, giving us a representation that serves as a tool for geometric analysis. Sanity checks on controlled data with known ground truth confirm that alignment improves when Iso-Energy holds and remains neutral when it does not. Applied to foundational VLMs, our framework reveals a clear structure with practical consequences: **(*i*)** sparse *bimodal* atoms carry the entire *cross-modal* alignment signal; **(*ii*)** *unimodal* atoms act as *modality-specific* biases and fully explain the modality gap; **(*iii*)** removing unimodal atoms collapses the gap without harming performance; **(*iv*)** restricting vector arithmetic to the bimodal subspace yields in-distribution edits and improved retrieval. These findings suggest that the right inductive bias can both preserve model fidelity and render the latent geometry interpretable and actionable.

Applications · Robotics

Jiazhao Zhang, Anqi Li, Yunpeng Qi, Minghan Li, Jiahang Liu, Shaoan Wang, Haoran Liu, Gengze Zhou, Yuze Wu, Xingxing Li 等

Navigation is a fundamental capability in embodied AI, representing the intelligence required to perceive and interact within physical environments. To achieve such intelligence, recent advanced works leverage Vision-Language Models (VLMs), which demonstrate strong generalizability and possess a well-suited formulation for navigation. However, these approaches remain largely confined to narrow task settings and embodiment-specific architectures. In this work, we introduce a cross-embodiment and cross-task Navigation Foundation Model (NavFoM), trained on eight million navigation samples that encompass quadrupeds, drones, wheeled robots, and vehicles, and spanning diverse tasks such as vision-and-language navigation, object searching, target tracking, and autonomous driving. NavFoM employs a unified architecture that processes multimodal navigation inputs from varying camera configurations and navigation horizons. To accommodate diverse camera setups and temporal horizons, NavFoM incorporates identifier tokens that embed camera view information of embodiments and the temporal context of tasks. Furthermore, to meet the demands of real-world deployment, NavFoM controls all observation tokens using a dynamically adjusted sampling strategy under a limited token length budget. Extensive evaluations on seven public benchmarks demonstrate that our model achieves state-of-the-art or highly competitive performance across different navigation tasks and embodiments without requiring task-specific fine-tuning. Additional real-world experiments further confirm the strong generalizability and practical applicability of our approach.

Computer Vision · Vision Models & Multimodal

Hao Wu, Yingqi Fan, Dai Jinyang, Junlong Tong, Yunpu Ma, Xiaoyu Shen

The quadratic computational cost of processing vision tokens in Multimodal Large Language Models (MLLMs) hinders their widespread adoption. While progressive vision token pruning offers a promising solution, current methods misinterpret shallow layer functions and use rigid schedules, which fail to unlock the full efficiency potential. To address these issues, we propose HiDrop, a framework that aligns token pruning with the true hierarchical function of MLLM layers. HiDrop features two key innovations: (1) Late Injection, which bypasses passive shallow layers to introduce visual tokens exactly where active fusion begins; and (2) Concave Pyramid Pruning with an Early Exit mechanism to dynamically adjust pruning rates across middle and deep layers. This process is optimized via an inter-layer similarity measure and a differentiable top-$k$ operator. To ensure practical efficiency, HiDrop further incorporates persistent positional encoding, FlashAttention-compatible token selection, and parallel decoupling of vision computation to eliminate hidden overhead associated with dynamic token reduction. Extensive experiments show that HiDrop compresses $\sim$90\% visual tokens while matching the original performance and accelerating training by 1.72$\times$. Our work not only sets a new state-of-the-art for efficient MLLM training and inference but also provides valuable insights into the hierarchical nature of multimodal fusion. The code is released at https://github.com/EIT-NLP/HiDrop.