Jiale Zhang, Yang Liu, Chengyang Li, Jin Yuan, Qianxi Jia, Taicheng Huang
High-fidelity 3D geometry generation requires maintaining global structural coherence alongside fine-grained surface details. While recent coarse-to-fine frameworks leverage Rotary Position Embeddings (RoPE) to condition local queries, we reveal a critical training-inference resolution discrepancy: coordinate guidance and geometric supervision are aligned during training, whereas inference decodes high-resolution geometry from coarse spatial coordinates. This mismatch introduces a severe distribution shift that degrades fine details. To overcome this, we propose Resolution-Decoupled Training (RDT), which anchors RoPE guidance at 512 resolution while supervising geometry at 1536, enabling robust detail extrapolation. Additionally, to eliminate high-resolution data bottlenecks, we present Dual3D-300K, a large-scale paired dataset comprising 300K watertight 3D point clouds explicitly aligned across 512 and 1536 resolutions. Extensive experiments demonstrate that RDT substantially improves sharp geometric regions, while Dual3D-300K offers a scalable benchmark for high-resolution 3D generation.
While single-image 3D texture generation has advanced significantly, conditioning texture synthesis on multi-view reference images remains largely under-explored, despite its necessity for resolving surface ambiguity in unobserved regions. In this paper, we propose RouTex, a novel multi-reference 3D texture generation framework based on in-context Diffusion Transformers (DiT). Our key insight is that native 3D Rotary Position Encoding (RoPE) inherently possesses spatial addressing capabilities. We introduce Positional Routing (PR) to reprogram 3D RoPE along spatial and semantic dimensions, establishing explicit reference-to-view correspondence without introducing additional parameters. To execute this routing efficiently, Dual-Granularity Attention (DGA) combines per-view local attention for fine texture fidelity with global joint attention over deduplicated references for cross-view consistency. Extensive experiments demonstrate that RouTex achieves new state-of-the-art performance in multi-reference 3D texture generation.
Henrique Schechter Vera, Sahil Dua, Jovan Andonov, Sara Smoot, Sebastian Russo, Ivan Llanos, Max Matveev, Jae Hyeon Yoo 等 73 位作者
We present EmbeddingGemma 2, an open multimodal embedding model which natively represents text, images, audio, video, and combinations thereof in a unified space. Our approach introduces improvements such as simplified per-layer embeddings and a multi-stage curriculum with modality and objective progression which ensure strong quality across unimodal, cross-modal, and mixed-modal evaluations. Notably, in comprehensive embedding benchmarks across all modalities, EmbeddingGemma 2 establishes a new Pareto frontier, outperforming both specialist models and models two to twelve times larger. Furthermore, our design offers flexibility for resource-constrained environments, supporting selective modality encoder loading, adjustable vision token budgets, truncatable embedding dimensions, and quantized weights. We present ablations analyzing key decisions and release EmbeddingGemma 2 to promote further research.
External skills provide language-model agents with reusable procedural knowledge, yet how models use such knowledge after it is supplied remains poorly understood. We identify Procedural Exposure Bias (PEB), the tendency of language models to increasingly favor an action as its associated procedural pattern is repeatedly exposed in a skill, even when the interaction state and action relevance remain unchanged. We find that PEB strongly depends on how procedural knowledge is represented: presenting the same content visually substantially attenuates exposure-induced shifts in action preference relative to textual presentation. Further analysis shows that this attenuation primarily arises from visual encoding rather than structured layout. Although repeated procedural signals remain recoverable from Visual representations, they exert a weaker influence on downstream action prediction, distinguishing signal accessibility from its use as action evidence. This effect also extends to executable action selection, where increasing exposure more strongly favors the corresponding action under Text than Visual. Layer-wise analyses show that exposure-dependent action evidence becomes more pronounced toward the model output, with stronger evidence under Text, while activation interventions reveal architecture-specific roles of internal components in transmitting or counteracting the preference shift. Complete-agent evaluations across ALFWorld, ScienceWorld, and WebShop further show that Visual skills achieve higher macro-average task success than Text skills for all four evaluated models. These findings establish skill representation as an important factor governing how procedural knowledge is translated into agent decisions. All code is available at https://github.com/NEUIR/Vis-Skill.
When adapting self-supervised Vision Transformers (ViTs) to dense prediction, existing methods often treat the ViT as a passive feature extractor and may underuse the rich priors encoded in its representations, including saliency, global context, and high-frequency details. We propose SAGE (Saliency-Annealed Gated Encoder), an enhanced ViT-Adapter backbone that explicitly exploits these priors through three complementary innovations: (1) a saliency-guided architecture that extracts DINO-style class-token (CLS) saliency to guide feature gating and high-frequency enhancement, together with dynamic multi-layer aggregation and a local-detail branch; (2) an annealing-based training paradigm designed to improve convergence and feature quality during early training while reducing feature drift later in training; and (3) a two-stage, quality-aware training mechanism that smoothly transitions from focal loss to Varifocal Loss (VFL) within a single training run. Across the evaluated tasks (Fig.~\ref{fig:fig_com}), SAGE achieves state-of-the-art (SOTA) or competitive results on COCO (62.8 box AP and 55.3 mask AP), COCO keypoint estimation (78.5 AP), ADE20K (60.3 mIoU for semantic segmentation and 44.9 mask AP for instance segmentation), TinyImageNet classification (94.76\% Top-1 accuracy), and DIOR-R oriented object detection (78.8 AP$_{50}$). The same backbone is used across tasks, with task-specific decoders. To the best of our knowledge, SAGE is the first framework to achieve multi-task state-of-the-art results on Huawei Ascend NPUs. Code and pretrained models will be released after internal review.
Diandian Guo Institute of Information Engineering, Chinese Academy of Sciences, Cong Cao Institute of Information Engineering，Chinese Academy of Sciences, Fangfang Yuan Institute of Information Engineering, Chinese Academy of Sciences, Pin Xu University of the Chinese Academy of Sciences and Institute of Information Engineering, Chinese Academy of Sciences, Cheng Hu, Zhicheng Zhang University of the Chinese Academy of Sciences and Institute of Information Engineering, Chinese Academy Of Sciences, Yu Liu Institute of Information Engineering, Chinese Academy of Sciences, Yanbing Liu Institute of Information Engineering，Chinese Academy of Sciences
Multimodal Sarcasm Understanding (MSU) comprises multiple subtasks, demanding both incongruity perception and intent reasoning. However, this progress is impeded by two bottlenecks. First, the lack of a unified benchmark for holistic satirical cognition hinders comprehensive evaluation of MSU. Second, jointly modeling these heterogeneous subtasks often leads to feature entanglement. Specifically, while subtasks share a dependence on incongruity, they diverge in granular focus, causing specific execution patterns to erode the fundamental perception capability. To address these challenges, we make two contributions. First, we introduce DocMSU-PLUS, a comprehensive benchmark covering five cognitive dimensions of MSU. All tasks are reformulated into multiple-choice questions (MCQs), enabling a unified accuracy-based evaluation. Second, we propose the Dual Orthogonal Stream Experts (DOSE) framework. DOSE structurally decouples experts into orthogonal shared perception and private execution streams to physically block gradient interference between tasks. Experiments demonstrate that DOSE achieves superior performance on DocMSU-PLUS, effectively balancing general perception with task-specific adaptation.
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
Jiacheng Hua Tencent and Tsinghua University, Yishu Yin Tsinghua University, Yuhang Wu Tsinghua University, Tsinghua University, Tai Wang, Yifei Huang The University of Tokyo, Miao Liu Tsinghua University
Existing Multimodal Large Language Models (MLLMs) struggle with 3D spatial reasoning, as they fail to construct structured abstractions of the 3D environment depicted in video inputs. To bridge this gap, drawing inspiration from cognitive theories of allocentric spatial reasoning, we investigate how to enable MLLMs to model and reason over text-based spatial representations of video. Specifically, we introduce Textual Representation of Allocentric Context from Egocentric Video (TRACE), a prompting method that induces MLLMs to generate text-based representations of 3D environments as intermediate reasoning traces for more accurate spatial question answering. TRACE encodes meta-context, camera trajectories, and detailed object entities to support structured spatial reasoning over egocentric videos. Extensive experiments on VSI-Bench and OST-Bench demonstrate that TRACE yields notable and consistent improvements over prior prompting strategies across a diverse range of MLLM backbones, spanning different parameter scales and training schemas. We further present ablation studies to validate our design choices, along with detailed analyses that probe the bottlenecks of 3D spatial reasoning in MLLMs.
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