Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies that map egocentric observations and language instructions directly to navigation actions. Although semantically capable, such action-centric training does not explicitly model how the agent's visual observations evolve under its predicted motion. Generative world-action models (WAMs) jointly predict future observations and actions, yet existing WAMs for continuous VLN do not condition joint future-view and action generation on geometry-aware representations inferred from the observation history. We present WNM-3D, a generative World Navigation Model with 3D scene conditioning for continuous VLN. A frozen feed-forward geometry encoder extracts cross-view representations from monocular RGB history, and a trainable 3D Scene-to-Token Adapter converts them into a fixed-length scene prefix for the world-action Diffusion Transformer. Through block-causal attention, this prefix remains visible to every future video-action block throughout joint denoising, providing persistent geometric context. We train WNM-3D with supervised world-action learning, DAgger-style adaptation on policy-visited states, and Counterfactual DanceGRPO refinement. Across GN-Bench and VLN-CE, WNM-3D consistently outperforms the backbone-matched WNM-2D counterpart, demonstrating gains from 3D scene conditioning across distinct visual domains. WNM-3D further outperforms strong VLN baselines on GN-Bench and demonstrates closed-loop deployment on a physical robot. Component and stage-wise ablations support the Adapter design and the complementary roles of DAgger-SFT and subsequent reward-guided refinement.
Yuzhou Ji, Jiepeng Wang, Tianyu Jin, Lizhuang Ma, Haibin Huang, Chi Zhang, Xuelong Li
Visual autoencoders must balance reconstruction fidelity, compactness, and semantic structure. Existing semantic tokenizers typically inherit semantics from pretrained recognition encoders, whose invariances can discard the appearance detail required for inversion. We show that this inheritance is unnecessary: semantic structure can be learned inside an autoencoder's own reconstructive representation. We introduce WithinVAE, a compact variational visual autoencoder with a sequential bottleneck, DINO/iBOT-style self-distillation from an exponential-moving-average copy of the autoencoder itself, and position-dependent token masking to achieve a 4-fold compression ratio, which is free of pretrained representation encoder or external semantic target. On ImageNet-1K at $256\times256$, WithinVAE improves all four reported reconstruction metrics over RPiAE including PSNR by 1.36 dB, while using half its latent scalar capacity. Under frozen evaluation, the same latents improve linear probing by 6.5 points over RPiAE and 5.1 points over our reconstruction-only baseline, attributing the semantic gains to self-distillation rather than architecture or external supervision. An auxiliary latent-to-latent model reproduces the ordered-compression trend, and a pixel-to-latent model transfers the objective to a pretrained generative space. These results separate the origin of semantic supervision from its use: a compact visual autoencoder can organize semantic structure without borrowing a recognition representation.
Recent advancements in text-guided 3D editing, particularly with 3D Gaussian Splatting (3DGS), have shown promise but still lag behind the flexibility of 2D editing tools. Existing methods face a critical trade-off between preserving multi-view consistency and allowing structural modifications. Image-based editors can also struggle to apply the intended edit to objects viewed from unusual angles. To address these limitations, we introduce VidEdit3D, a framework that reformulates 3D scene editing as a trajectory-based video editing task. By drawing a parallel between camera movement in static 3D scenes and temporal dynamics in video, we leverage the robust spatiotemporal priors of pre-trained Video Diffusion Models (VDMs) to encourage semantic and structural coherence across views. Specifically, we propose Trajectory-Guided Rendering (TGR) to select informative keyframes and construct smooth video clips aligned with VDM input requirements. To propagate edits from an anchor view to these clips, we develop Flow-Aligned Video Editing (FAVE), a training-free framework incorporating an Editing Consistency Guidance (ECG) mechanism. ECG contrasts source and edited image conditions at a shared latent state, using scheduled source-image amplification to strengthen adherence to the edited reference while maintaining original scene context. Finally, we introduce Region-Selective 3DGS Refinement (RS-GS) to strictly confine geometric and appearance updates to target primitives, reducing background attribute leakage. Experiments demonstrate stronger instruction alignment and better multi-view consistency than the baselines.
Paribesh Regmi, Qingshuang Chen, Chi Zhang, Heba Aly, Yelin Kim, Hongda Mao
Vision-language models excel at image and video understanding but suffer from high inference latency due to the need to process thousands of tokens per image, limiting their deployment on resource-constrained edge devices and in real-time surveillance applications. This challenge is further amplified in video processing, where multiple frames must be analyzed simultaneously. Existing token reduction techniques generally rely on a fixed, uniform pruning ratio applied across all inputs, which is suboptimal because the degree of redundancy can vary significantly between different videos, necessitating content-dependent pruning levels to preserve critical information. To address these limitations, we propose an adaptive token pruning strategy specifically designed for video processing. Crucially, the pruning ratio is determined adaptively based on the content of each video. This is achieved by analyzing the correlation structure of token embeddings to quantify redundancy, enabling dynamic token allocation that retains more tokens for dynamic scenes while aggressively pruning repetitive or static content. Importantly, our method is entirely post-hoc and requires no additional training or fine-tuning, while achieving strong empirical gains; notably, it improves accuracy by +7\% on a video captioning benchmark at 10\% token retention, while reducing computation TFLOPs by 95\%.
Qian Chen Alibaba Group, Xianyin Zhang Fudan University, Yanzhi Liu Alibaba Group, Lifan Guo, Feng Chen Alibaba Group, Chi Zhang Alibaba Group
The emergence of Large Vision-Language Models (LVLMs) has substantially expanded model capabilities beyond text-only understanding, enabling unified inference across both visual and textual modalities and supporting a broader range of real-world applications. To comprehensively evaluate the perception, understanding, reasoning, and cognition capabilities of LVLMs throughout the entire financial business workflow in Chinese contexts, we introduce CFMME, a novel Chinese financial multimodal evaluation benchmark. CFMME comprises 6,052 instances spanning from fundamental academic knowledge to complex real-world applications, covering eight primary financial image modalities and four core multimodal tasks. On CFMME, we conduct a thorough evaluation of representative LVLMs. The results show that the state-of-the-art model attains an overall accuracy of 66.11% on the question answering task and an average score of 77.18 on the detection, recognition, and information extraction tasks, indicating substantial room for improvement in current LVLMs. In addition, we conduct detailed analyses of error causes, cross-modal capabilities, and multi-orientation settings, yielding valuable insights for future research. We hope that CFMME will spur further progress in LVLMs, especially by improving their performance on multiple multimodal tasks in the financial domain.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Jiawei Zhou, Chi Zhang Wuhan University, Xiang Feng Wuhan University, Qiming Zhang, Haibo Qiu Meituan, Lihuo He Xidian University, Dengpan Ye Guangzhou University, Xinbo Gao Xidian University 等 9 位作者
We present Omni-I2C, a comprehensive benchmark designed to evaluate the capability of Large Multimodal Models (LMMs) in converting complex, structured digital graphics into executable code. We argue that this task represents a non-trivial challenge for the current generation of LMMs: it demands an unprecedented synergy between high-fidelity visual perception—to parse intricate spatial hierarchies and symbolic details—and precise generative expression—to synthesize syntactically sound and logically consistent code. Unlike traditional descriptive tasks, Omni-I2C requires a holistic understanding where any minor perceptual hallucination or coding error leads to a complete failure in visual reconstruction. Omni-I2C features 1130 meticulously curated samples, defined by its breadth across subjects, image modalities, and programming languages. By incorporating authentic user-sourced cases, the benchmark spans a vast spectrum of digital content—from scientific visualizations to complex symbolic notations—each paired with executable reference code. To complement this diversity, our evaluation framework provides necessary depth; by decoupling performance into perceptual fidelity and symbolic precision, it transcends surface-level accuracy to expose the granular structural failures and reasoning bottlenecks of current LMMs. Our evaluation reveals a substantial performance gap among leading LMMs; even state-of-the-art models struggle to preserve structural integrity in complex scenarios, underscoring that multimodal code generation remains a formidable challenge. Data and code are available at https://github.com/MiliLab/Omni-I2C.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表