跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 21:02 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-22 00:10 — 2026-11-23 00:10(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-22 21:02最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 8,809 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 21:00(北京时间)
版本更新 · v2arXiv:2611.23845

ReflectScene:MLLM-Guided Closed-Loop Diffusion for 3D Indoor Scene Generation

Jiawei Shen, Jie Feng, Junpeng Zhang, Guanbin Li, Wanyi Chen, Weisheng Dong, Guangming Shi

原文摘要

Text-conditioned 3D indoor scene generation requires layouts satisfying geometric, functional, and semantic constraints. However, existing diffusion methods rely primarily on static textual conditions, limiting their ability to assess evolving scenes and translate semantic discrepancies into executable object-level corrections. MLLM-based post-hoc refinement provides semantic feedback but remains decoupled from denoising, potentially disrupting scene coherence. We propose ReflectScene, an MLLM-guided closed-loop diffusion framework. First, we introduce Hierarchical Prior-Grounded Scene Understanding that aligns structured layouts with multi-view visual evidence, to interpret object-specific context and scene global semantics via a frozen multi-modal large language model (MLLM). Second, we propose MLLM-Guided Semantic Reward Evaluation to distill MLLM's diagnoses and assessments on possible candidate corrections into a lightweight Reward Predictor, enabling correction decision making with reduced computation burden. Finally, Decision-Conditioned Trajectory-Consistent Diffusion is proposed to integrate selected corrections through transient conditioning and persistent clean-estimate projection, correcting object layout in the generated scene while preserving non-target arrangements throughout denoising. Experiments on 3D-FRONT demonstrate improved functional consistency and semantic alignment while maintaining competitive generation quality and diversity.

cs.CV · cs.AI

新论文 · v1arXiv:2611.25553

TwoPass: Draft-Guided Few-Step Video Prediction for Robotic Manipulation

Yijun Liu, Shijia Ge, Tongtong Feng, Xin Wang, Yuan Meng, Yuwei Liu, Zhi Wang, Wenwu Zhu

原文摘要

Action-conditioned video prediction lets robots anticipate the visual consequences of their actions for planning and policy evaluation. Existing predictors denoise each future from noise without using their own estimate of it, which limits the quality of the predicted future, in particular of the manipulated objects, and requires many network calls. We present TwoPass, a self-conditioned training-and-inference framework that keeps the standard flow-matching objective. Self-Generated Draft Training supplies a detached clean-video estimate from the shared network as conditioning at the same noisy state. A Refinement-Only Late Adapter applies a dedicated residual transformation when a draft is present. At inference, Draft-Reuse Iterative Refinement obtains both a solver update and the next draft from each velocity prediction, requiring as few as 4 function evaluations (NFE) per video chunk. Training samples discrete solver-query noise levels and updates the pretrained backbone. Extensive experiments on Bridge and Language Table show that TwoPass achieves state-of-the-art results with 4 NFE, far fewer than the 50-59 calls of existing predictors. Code: https://github.com/PlantPotatoOnMoon/TwoPass.

cs.CV

新论文 · v1arXiv:2611.25551

Anchored Inertial Proposals with Objective Verification for Diffusion-Prior Inverse Problems

Minwoo Kim, Seunghyeok Shin, Dabin Kim, Hongki Lim

原文摘要

Training-free diffusion priors are powerful for inverse problems, but measurement guidance during reverse sampling is local: aggressive updates can improve immediate data fit while disrupting later denoising. We introduce an anchored inertial correction rule that separates proposal generation from acceptance. At each corrected step, the denoiser prediction anchors a frozen clean-space objective combining measurement fit with a noise-level-dependent proximal term. Heavy-ball dynamics with step size and momentum computed from the measured curvature generate a clean-state candidate; a separate verifier evaluates it with the same objective, with the denoiser prediction retained as fallback; both stages are derived from one objective for the whole trajectory, considered one step at a time. The accepted clean state is re-noised to continue sampling. The rule applies to pixel and latent diffusion with differentiable measurement operators, requires no retraining, and adds no denoiser calls inside the correction loop. We analyze how objective verification yields local nonincrease and displacement control. Across natural-image benchmarks, the method achieves competitive reconstruction quality. Code is available at https://github.com/Seunghyeok0715/PIVOT2026.

cs.CV

版本更新 · v3arXiv:2509.17955

Breaking the Discretization Barrier of Continuous Physics Simulation Learning

Fan Xu, Hao Wu, Nan Wang, Lilan Peng, Kun Wang, Wei Gong, Xibin Zhao

原文摘要

The modeling of complicated time-evolving physical dynamics from partial observations is a long-standing challenge. Particularly, observations can be sparsely distributed in a seemingly random or unstructured manner, making it difficult to capture highly nonlinear features in a variety of scientific and engineering problems. However, existing data-driven approaches are often constrained by fixed spatial and temporal discretization. While some researchers attempt to achieve spatio-temporal continuity by designing novel strategies, they either overly rely on traditional numerical methods or fail to truly overcome the limitations imposed by discretization. To address these, we propose CoPS, a purely data-driven methods, to effectively model continuous physics simulation from partial observations. Specifically, we employ multiplicative filter network to fuse and encode spatial information with the corresponding observations. Then we customize geometric grids and use message-passing mechanism to map features from original spatial domain to the customized grids. Subsequently, CoPS models continuous-time dynamics by designing multi-scale graph ODEs, while introducing a Markov-based neural auto-correction module to assist and constrain the continuous extrapolations. Comprehensive experiments demonstrate that CoPS advances the state-of-the-art methods in space-time continuous modeling across various scenarios.

cs.CV

版本更新 · v2arXiv:2611.22132

DailyBrick: Language-Guided Synthesis of Brick Assembly Instructions

Hang Zhang, Qijian Tian, Yuan Xie, Xuhong Wang, Xin Tan

原文摘要

Generating a LEGO model from a user request is more than a plausible 3D shape generation. LEGO models require physical support per brick, and each brick should be placed unblocked. Current methods address this issue by training an expert large language model. We reduce the problem of generating extremely long context on all brick connections to that of writing a program that builds LEGO models like a human, considering each intermediate step could be executed. We introduce DailyBrick , a multi-stage agentic system that produces a LEGO model together with a brick-by-brick assembly instruction for human building and robot assembly. We design a multi-stage harness with roles to help LLMs generate more effectively. A versioned construction SDK compiles multi-level decisions, from semantic subparts to individual bricks, into canonical operations. An external Meta-Reviewer agent replays and inspects the generated package, verifies the model and its construction process, identifies failures, traces them to the responsible stage, and routes them to bounded repairs or to editable candidates for later skill or tool updates. Extensive experiments demonstrate that DailyBrick generates LEGO models based on simple user requests better than recent agentic systems, and show its utility in downstream applications such as robot manipulations on model assembly from instructions and brick sets (https://spatialagentlab.github.io/DailyBrick.github.io/).

cs.RO · cs.CV

版本更新 · v3arXiv:2605.12088

UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation

Yiyan Xu, Qiulin Wang, Wenjie Wang, Yunyao Mao, Xintao Wang, Pengfei Wan, Kun Gai, Fuli Feng

原文摘要

Multi-reference image generation aims to synthesize images from textual instructions while faithfully preserving subject identities from multiple reference images. Existing VLM-enhanced diffusion models commonly rely on decoupled visual conditioning: semantic ViT features are processed by the VLM for instruction understanding, whereas appearance-rich VAE features are injected later into the diffusion backbone. Despite its intuitive design, this separation makes it difficult for the model to associate each semantically grounded subject with visual details from the correct reference image. As a result, the model may recognize which subject is being referred to, but fail to preserve its identity and fine-grained appearance, leading to attribute leakage and cross-reference confusion in complex multi-reference settings. To address this issue, we propose UniCustom, a unified visual conditioning framework that fuses ViT and VAE features before VLM encoding. This early fusion exposes the VLM to both semantic cues and appearance-rich details, enabling its hidden states to jointly encode the referred subject and corresponding visual appearance with only a lightweight linear fusion layer. To learn such unified representations, we adopt a two-stage training strategy: reconstruction-oriented pretraining that preserves reference-specific appearance details in the fused hidden states, followed by supervised finetuning on single- and multi-reference generation tasks. We further introduce a slot-wise binding regularization that encourages each image slot to preserve low-level details of its corresponding reference, thereby reducing cross-reference entanglement. Experiments on two multi-reference generation benchmarks demonstrate that UniCustom consistently improves subject consistency, instruction following, and compositional fidelity over strong baselines.

cs.CV

版本更新 · v2arXiv:2609.30981

RevisitQA: Short Videos Are Not Easy under Dense Revisits

Siru Zhong, Shenghan Tan, Rihong Yan, Xiaohui Lv, Yuzheng Zhuang, Shuai Tao, Wulong Liu, Haohuan Fu 等 9 位作者

原文摘要

Video question answering benchmarks have increasingly focused on longer recordings, yet short videos can also be challenging when scenes are revisited frequently. As a camera repeatedly leaves and returns to the same workspace, objects may change out of view, making earlier observations outdated or misleading. Understanding such videos requires models to track evolving states across repeated visits rather than simply retrieve past observations. To study this challenge, we introduce RevisitQA, a benchmark containing 2,577 questions across 622 episodes with a median duration of 44.8 seconds, drawn from five real-world egocentric domains and two simulated environments. RevisitQA covers six question types and evaluates models at specific query times, requiring them to answer from the observed history or abstain when it is insufficient. Across 15 offline and seven streaming video LLMs, the median model correctly answers only 55.5% of answerable questions and abstains on just 30.3% of unanswerable ones. Removing earlier frames further reveals that historical observations help answer questions but can also make models less likely to abstain when answers remain unresolved. These findings highlight dense episodic revisits as an important and unresolved challenge for video question answering. Code is available at https://github.com/siruzhong/RevisitQA.

cs.CV

版本更新 · v2arXiv:2611.16217

WorldDraft: If Code Builds the World, Can Video Models Just Render It?

Zhiyu Hou, Wen-Jie Shu, Harold Haodong Chen, Weilin Ruan, Chenfei Liao, Liuzhou Zhang, Disen Lan, Xiaogang Xu 等 10 位作者

原文摘要

Multimodal coding agents decouple 4D world construction from visual generation, repurposing video models from world generators toward generative renderers. This division of labor raises a fundamental question: if code builds the world, can video models just render it? A reliable generative renderer hinges on two complementary criteria: (i) world preservation, retaining prescribed 4D kinematics and camera paths; and (ii) visual realization, persistently binding text-specified target attributes over time. To evaluate this capability, we introduce WorldDraft, a benchmark of $432$ strictly paired test cases across $48$ executable 4D world families spanning six dynamic challenge categories. Under a $3 \times 3$ factorial design, WorldDraft orthogonally crosses draft granularity (abstract proxy to previs) and appearance alignment (neutral to conflicting) under identical dynamics. Extensive evaluations across $12$ representative models reveal that: (I) world preservation and visual realization remain in stark operational tension; (II) richer draft scaffolding anchors structure but paradoxically impairs appearance fidelity; and (III) conflicting source cues trigger severe source leakage (up to $64\%$), exposing fragile cross-modal disentanglement. To mitigate these bottlenecks, we propose WorldDraft-Primer, a plug-and-play visual prompting strategy that consistently improves both objectives across frozen video renderers. Together, WorldDraft and WorldDraft-Primer lay a foundation for bridging programmatic 4D simulation with video generation, advancing physically grounded generative rendering.

cs.CV

新论文 · v1arXiv:2611.25537

Query-Aware vs. Query-Agnostic Training-Free Video Token Pruning in Multimodal LLMs

Divya Kothandaraman, Timo Kumkel, Jaclyn Pytlarz

原文摘要

Video Large Language Models process large numbers of visual tokens, making token pruning important for efficient inference. Training-free pruning methods differ in whether and how they use the user query, and the value of query conditioning remains unclear. We present a controlled study of training-free, pre-LLM video token selection. Using a shared Qwen-3-VL backbone, token budgets, and decoding settings, we compare 21 pruning principles spanning query-agnostic, shallow query-conditioned, structured query-conditioned, and holistic strategies. To instantiate the last two categories, we introduce Structured Query Pruning, which decomposes the question into semantic anchors, and a Pareto variant, which combines anchor relevance with query-agnostic visual diversity. Across Video-MME, MVBench, and LongVideoBench, relevance computed from the raw question embedding is unreliable (8--16 points below the best methods), whereas anchors derived from query decomposition avoid this failure. However, query access is not inherently advantageous: strong query-agnostic coverage methods remain competitive or superior in the full-field comparison. Relative to a redundancy-only baseline, structured selection helps most on evidence-specific and long-context tasks at tight budgets; on broad tasks, the holistic selector improves over either relevance or redundancy alone. Further, pruning reduces cost and memory. These results support a practical design rule: preserve visual coverage by default, and add structured relevance when the task and token budget demand selective evidence retrieval.

cs.CV

新论文 · v1arXiv:2611.25535

Support-Guided Triadic Decoding for Hallucination Mitigation in Multimodal Dialogue with LVLMs

Yiheng Li, Wenhao Wang, Xingyi Li, Zhilin Tang, Zichang Tan, Zhen Lei, Yang Yang

原文摘要

In multimodal multi-turn dialogue, dialogue history plays a dual role: reliable responses provide useful context for subsequent turns, whereas hallucinated responses can propagate errors across turns. Existing training-free methods globally adjust the effect of dialogue history on generation, making it difficult to suppress misleading information without weakening useful context. To address this trade-off, we introduce Support-Guided Triadic Decoding (SGTD), a training-free framework that selectively controls the influence of unreliable history and fuses complementary predictions during decoding. Specifically, Historical Answer Support Estimation measures the visual support of historical responses against type-matched alternatives and identifies low-support content that may mislead later generation. Support-Targeted Attention Intervention then weakens the influence of this content while preserving the surrounding dialogue, producing a support-refined prediction. Triadic Decoding combines this prediction with the full-history prediction and answer-free visual evidence, while the Support-Adaptive Plausibility Constraint filters implausible tokens using visual agreement and historical support. Experiments on MMHalSnowball and VisDiaHalBench across representative LVLMs show that SGTD consistently achieves the highest accuracy under hallucinated histories while preserving the benefits of factual context.

cs.CV

版本更新 · v2arXiv:2611.18690

Perceptual Weight Space Programming for Diffusion Super-Resolution

Chenzhi Zheng, Zhuoran Zheng

原文摘要

Diffusion models for image super-resolution can recover scene content while producing distracting artifacts or unbalanced colors. We study whether a large language model (LLM) can improve perceptual quality by editing a small subset of existing U-Net weights without a clean reference image. The proposed framework provides the editor with architecture code, selected weights, activation summaries, and sampling previews. It permits up to 1,020 candidate trials while limiting accepted changes to three layers and fewer than 0.1\% of model parameters. The evaluation protocol uses ResShift, SinSR, and SUPIR and compares GPT-6 Astra with a specified Qwen3-VL model under matched access. Feedback metrics guide editing, while separate quality metrics and blinded human comparisons evaluate the final weights. We also report an executed color calibration experiment using real photographs and two small residual networks. This experiment demonstrates correction of a fixed color shift and reveals that an improving feedback score can accompany worse performance on unseen scenes. A separate lightweight super-resolution experiment isolates modest changes in luminance detail while preserving color. The findings motivate restricted updates and independent evaluation of perceptual weight editing.

cs.CV · cs.AI

新论文 · v1arXiv:2611.25524

Contrast Where It Matters: Visual Evidence-Guided Decoding for Mitigating Hallucinations in LVLMs

Yiheng Li, Wenhao Wang, Xingyi Li, Mingda Jia, Zichang Tan, Yinhang Tang, Zhen Lei, Yang Yang

原文摘要

Despite strong multimodal capabilities, large vision-language models (LVLMs) often hallucinate when linguistic priors outweigh visual evidence or when predictions are grounded in irrelevant or misleading image regions. Training-free contrastive decoding mitigates hallucinations by contrasting the original prediction with an auxiliary one that exposes linguistic priors. Yet existing methods focus on altering the auxiliary input or computation and do not ensure that either branch uses query-relevant visual evidence during decoding. We propose Visual Evidence-Guided Decoding (VEGD), a training-free framework that identifies query-relevant visual evidence and guides its use throughout contrastive decoding. VEGD locates this evidence by aggregating localization heads with strong visual responses and coherent spatial structure, then selectively weakens it in the auxiliary image. During generation, VEGD directs visual-carrier heads in both branches toward the same evidence location, strengthening access to intact evidence in the main branch while anchoring the auxiliary branch to its weakened counterpart. An adaptive distribution fusion strategy then combines or contrasts their predictions according to distribution divergence. Experiments across diverse LVLMs and benchmarks demonstrate that VEGD consistently reduces hallucinations.

cs.CV

新论文 · v1arXiv:2611.25523

Multi-View Relighting with Mergeable Radiance Fields

Yinan Wang, Rohan Kadkol, Hyunjin Yoo, Jean-François Lalonde, James J. Clark

原文摘要

We propose MergeableRF, a method for radiance field relighting through model parameter merging. Given multi-view images of a scene under known basis lights, our goal is to relight the scene by directly combining the parameters of radiance fields trained under these lights. This is motivated by the linearity of light transport: the image under a mixture of lights is the same weighted combination of the images under each light. However, combining the parameters of independently trained radiance fields does not produce the corresponding combination of images. To address this, we represent a scene with shared geometry and a separate appearance network for each basis light. We start these networks from the same initialization and introduce merge-aware training, which teaches their parameter combinations to reproduce the corresponding combinations of images. Given a target HDR environment map, we compute its basis-light coefficients and use them to merge the appearance networks into a single relit model. Our method supports both Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS), without material estimation, additional relighting networks, or target-specific optimization. Unlike image-space blending, it requires only one rendering pass per viewpoint. Experiments on synthetic Neural Gaffer objects and real OLATverse captures demonstrate relighting quality competitive with methods trained on the same multi-light observations.

cs.CV

版本更新 · v2arXiv:2607.14821

Blurring Modal Boundaries: A Unified Survey from Single- to Multi-Modal Person Re-ldentification

Xiao Wang, Bing Wang, Bin Yang, Cuiqun Chen, Xin Xu, Mang Ye

原文摘要

Person re-identification (ReID) serves as a critical component in intelligent surveillance systems, aiming to match identities across disjoint camera networks. While traditional methods primarily rely on single-modal RGB imagery, they are often constrained by environmental challenges such as low illumination and occlusion. To overcome these limitations, the field is rapidly evolving toward cross-modal and multi-modal paradigms. This survey presents a comprehensive overview of this transition, systematically reviewing key cross-modal tasks including visible-infrared (VI-ReID), text-image (TI-ReID), sketch-based (Sketch-ReID), and the emerging Non-Line-of-Sight (NLOS) ReID, which extends perception beyond direct visibility. Furthermore, we examine tri-spectral and multi-modal fusion ReID, discussing how complementary information from diverse sensors enhances robustness. Beyond summarizing datasets, challenges, and methodologies, we propose a Transformer-based baseline framework for visible-infrared ReID, designed to effectively capture modality-invariant features. Finally, based on the current landscape, we outline several promising directions for future research.

cs.CV

版本更新 · v3arXiv:2605.05895

Detecting AI-Generated Videos with Spiking Neural Networks

Minsuk Jang, Yujin Yang, Hee-Seon Kim, Minseok Son, Younghun Kim, Changick Kim

原文摘要

Modern AI-generated videos are photorealistic at the single-frame level, leaving inter-frame dynamics as the main remaining axis for detection. Existing detectors typically handle this temporal evidence in three ways: feeding the full frame sequence to a generic temporal backbone, reducing one dominant temporal cue to fixed video-level descriptors, or comparing temporal features to real-video statistics through a detection metric. These strategies degrade sharply under cross-generator evaluation, where artifact type and timescale vary across generators. On caption-paired benchmark, GenVidBench, we identify two signatures that prior detectors do not jointly exploit: AI-generated videos exhibit smoother frame-to-frame temporal residuals at the pixel level, and more compact trajectories in the semantic feature space, indicating a temporal smoothness gap at both levels. We further observe that, when raw video is fed into a Spiking Neural Networks (SNNs), fake clips elicit firing predominantly at object and motion boundaries, unlike real clips, suggesting that the SNN responds to temporal artifacts localized at edges. These cues are sparse, asynchronous, and concentrated at moments of change, which makes SNNs a natural choice for this task: their event-driven, sparsely-activated dynamics align with the structure of the residual signal in a way that dense ANN backbones do not. Building on this observation, we propose MAST, a detector that processes multi-channel temporal residuals with a spike-driven temporal branch alongside a frozen semantic encoder for cross-generator generalization. On the GenVideo benchmark, MAST achieves 93.14\% mean accuracy across 10 unseen generators under strict cross-generator evaluation, matching or surpassing the strongest ANN-based detectors and demonstrating the practical applicability of SNNs to AI-generated video detection.

cs.CV · cs.AI

版本更新 · v3arXiv:2607.12304

What Does a Temporal Benchmark Score Measure? Decomposing Channel Use in Video VLM Evaluation

Farrukh Rahman

原文摘要

A score on a temporal video question answering benchmark is meant to measure that a model has temporal understanding, but it conflates two questions. (1) is the question even temporal, does it need several frames and their order? And (2) when it does, does the model recover the order from the pixels, or read it off the positional encoding (RoPE)? Most of a temporal score answers neither, since a single frame and answer priors often carry it, and the field's validity checks, frame-shuffle sensitivity and multi-frame gain, speak only to (1). For (2) we score a reversal conflict, frames reversed while RoPE stays forward, two ways: label-free, as the accuracy lost against the forward labels, and against reversed labels wherever labels transform deterministically under time reversal. This separates a model that follows the reversed content from one merely disrupted. The two readings dissociate two similarly scoring models at both model scales. Qwen3-VL answers the reversed event it actually sees, reading the visual sequence. Molmo2 correctly reports a backwards video when positions agree, and flipping only the RoPE indices flips its prediction to the forward events, i.e. it reads positions. We call these regimes visual-sequence-dominant and position-dominant. Controls show reversed content is processable whenever the channels agree, and that both families share a bias toward describing events as running forward (arrow-of-time prior) that, being similar in strength, cannot by itself account for the dissociation. The distinction matters because the two channels fail on opposite inputs: two models with the same score are not interchangeable.

cs.CV · cs.LG

版本更新 · v3arXiv:2605.26104

EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding

Geo Ahn, Jiwook Han, Youngrae Kim, Joonseok Lee, Jinwoo Choi

原文摘要

Fine-tuning MLLMs for Video Temporal Grounding (VTG) often improves in-domain performance but degrades sharply under domain shift. In this work, we find that this failure is primarily driven not just by unseen query concepts, but by visual domain shift, which prevents the model from coupling its learned temporal localization knowledge with its inherent entity-attention capability. To address this, we introduce EVIDENT, a parameter-efficient adaptation framework that anchors temporal grounding in the inherent entity-attention of pre-trained MLLMs by routing VTG adaptation through explicit visual entity evidence. EVIDENT consists of three components: (i) an Entity Bottleneck Adapter that transforms dense visual tokens into compact entity-level slots, (ii) an Entity-Binding Distillation loss that instills objectness priors into the semantically unstructured MLLM visual space, guiding each slot to bind to a coherent entity, and (iii) an Entity-to-eVidence gating mechanism that leverages the captured entities as evidence, steering the model to localize moments containing query-relevant entities. Together, these components enable VTG fine-tuning to rely on entity-grounded evidence rather than brittle dataset shortcuts. Experiments on cross-domain VTG benchmarks show that EVIDENT consistently improves out-of-domain robustness while preserving competitive in-domain performance with modest parameter overhead. These results suggest that entity-level grounding is an effective inductive bias for generalizable temporal localization.

cs.CV

版本更新 · v2arXiv:2611.24171

Efficient World-Model Planning via Physics-Guided Search Distillation

Hongyu Zhang, Xiaoshuai Hao, Heye Huang, Qingwen Meng, Wenjun Shi, Jianao Xu, Xin Hu, Xuanru Jin 等 10 位作者

原文摘要

World models support autonomous driving by evaluating candidate trajectories through predicted future scene evolution. However, accurate future prediction does not ensure road-compliant execution; when all candidates violate road boundaries, re-ranking cannot select a feasible trajectory. We propose Physics-Guided Search Distillation (PGSD), a single-view planning framework that combines future representations and execution feedback for verified beyond-pool repair through three components: (1) Execution-Aware Selection checks ego-vehicle road compliance under simulated execution and selects the highest-scoring feasible trajectory; (2) a Clearance-Aware Search Teacher generates beyond-pool corrections and selects demonstrations with larger minimum road-boundary clearance during execution to buffer imitation errors; and (3) a Future-Conditioned Repair Student predicts one correction from rewarder features and execution feedback for single-rollout verification. The pretrained planner and rewarder remain frozen; no future scenes are generated online. On NAVSIM v1, single-view PGSD achieves 90.97 PDMS, exceeding all compared prior single-view planners and retaining 73.2% of the search teacher's PDMS gain over execution-aware selection. On NAVSIM v2 navhard, it reaches 38.96 EPDMS, improving on WorldDrive by 11.24 points (40.5%). The student replaces up to ten search rollouts with a single verification rollout per repair trigger. HUGSIM Hard examples provide qualitative evidence of zero-shot transfer.

cs.RO · cs.CV

版本更新 · v4arXiv:2512.05391

LoC-Path: Learning to Compress for Pathology Multimodal Large Language Models

Qingqiao Hu, Weimin Lyu, Meilong Xu, Xiaoling Hu, Kehan Qi, Saumya Gupta, Jiawei Zhou, Chao Chen

原文摘要

Whole Slide Image (WSI) multimodal large language models (MLLMs) are difficult to build and deploy because gigapixel slides induce thousands of highly redundant visual tokens that must be learned from sparse slide-level language supervision. Existing slide-level pathology MLLMs typically combine heavy slide-level encoders with long visual prefixes, making development and deployment expensive under limited computational resources. We revisit this regime and show that WSI tile features are highly redundant at both global and local scales, while task-relevant evidence is sparse and query-dependent. We therefore introduce LoC-Path, a resource-efficient slide-level MLLM that compresses before fusion. LoC-Path uses a sparse token merger and a masked-autoencoder (MAE)-pretrained resampler to replace expensive slide-level encoding with a compact latent interface. A token importance scorer selects the most relevant latents and cross-attention routing adapters fuse them into a few LLM decoder layers. This design lowers both multimodal tuning cost and inference-time latency/memory by avoiding heavy slide-level encoding and long visual prefixes. Extensive experiments show that the inference TFLOPs of LoC-Path are 97% lower and inference memory is also 39% lower. LoC-Path enables efficient end-to-end development and deployment under limited computational resources while remaining competitive with prior slide-level MLLMs. Code is available at https://github.com/WinstonHuTiger/loc_path.

cs.CV

版本更新 · v2arXiv:2611.23788

Geometry-bridge flow matching for blind rigid-motion correction in head cone-beam CT

Sungho Yun, Seungryong Cho

原文摘要

Rigid motion of a patient head during head cone-beam CT (CBCT) scan can degrade image quality and complicate recovery of accurate anatomical structures from the measured projections. We present a 3D flow-matching prior approach that learns the image changes induced by motion. Its geometry-bridge connects motion-corrupted and motion-free Feldkamp-Davis-Kress (FDK) reconstructed images of the same source volume through progressively reduced simulated motion. The forward projector's geometry derivative supplies analytic velocity targets along this path. A plug-and-play loop encompasses the learned image updates together with spline-based pose estimation, conjugate-gradient data consistency, and image total-variation regularization. Both the refined image volume and the FDK reconstructed image volume at the estimated poses are evaluated. On simulated 360-view scans from 30 held-out CQ500 patients with nominal per-component motion amplitudes within 10 mm / 10 degrees, the framework achieved state-of-the-art image reconstruction quality and motion accuracy in comparison with other methos such as learned autofocus and diffusion-based joint reconstruction. Mean peak signal-to-noise ratio (PSNR) reached 37.1 dB and mean detector-plane reprojection error (RPE) was 0.27 mm. With matched endpoints at the inference settings, the geometry bridge improved PSNR by 1.6 dB and reduced RPE by 33% relative to image-linear training. With 50 prior updates and coarse-to-fine motion estimation, total processing time averaged 9.1 minutes per patient on an RTX A6000.

physics.med-ph · cs.CL · cs.CV

新论文 · v1arXiv:2611.25513

Mesh-Free Keypoint Learning for Category-Level 6D Object Pose Estimation

Junghoon Seo, Hakjin Lee, Jaehoon Sim

原文摘要

Category-level 6D pose estimation relates partial RGB-D observations of unseen instances to a canonical frame shared across a category. Object-aware reconstruction helps adaptive keypoints retain the geometry of the visible surface. Common reconstruction targets select observed points by their distance to a registered instance surface. We present MORSEPose, which derives this support directly from standard pose and metric-size annotations. We map observed 3D points to normalized object coordinates and retain those inside a tolerancedilated pose-and-size envelope. This construction is consistent across camera frames and metric scales. When the annotated extent bounds the object surface, the envelope conservatively contains the support of a conventional surface-distance selector. We integrate this target with multi-level RGB-D features, adaptive keypoints, and learnable category context. Experiments on REAL275 and HouseCat6D show that the envelope closely matches surface-based supervision at both point and task levels, remains stable under boundary perturbations and viewpoint changes, and supports competitive category-level pose accuracy across benchmarks.

cs.CV · cs.RO

新论文 · v1arXiv:2611.25510

Life-IQA+: Boosting Blind Image Quality Assessment via GCN-enhanced Layer Interaction and Flexible Hierarchical Expert Specialization

Long Tang, Guoquan Zheng, Huiyu Duan, Jie Hao, Yucheng Zhu, Liang Yuan, Xiongkuo Min, Guangtao Zhai

原文摘要

Blind image quality assessment (BIQA) is essential for evaluating and optimizing visual experience. Existing BIQA methods typically aggregate features from multiple backbone stages without accounting for their unequal contributions to quality prediction. Furthermore, uniformly supervising all experts may constrain their flexibility and limit the diversity of the learned quality representations. To address these issues, we present Life-IQA+, a quality representation decoding framework that combines graph convolutional network (GCN) enhanced layer interaction and flexible hierarchical expert specialization. Specifically, the layer interaction module constructs quality queries from GCN-refined deepest-stage features and uses penultimate-stage features as keys and values, thereby enabling cross-layer representation interaction via the cross-attention mechanism. Building on these representations, we further introduce a flexible hierarchical mixture-of-experts (MoE) architecture comprising a densely activated shared expert layer and a sparsely activated routed expert layer. To enhance the representation diversity and ability of experts, we apply auxiliary classification supervision to a subset of shared experts using distortion-type labels for synthetic datasets and discretized quality-level labels for authentic datasets. Experiments on synthetic and authentic distortion benchmarks, together with controlled ablations of expert configurations and supervision strategies, show that Life-IQA+ achieves competitive prediction accuracy with a favorable balance between accuracy and computational cost. The code is available at: https://github.com/TANGLONG2/Life-IQA-PlusPlus.

eess.IV · cs.CV

新论文 · v1arXiv:2611.25508

Persona Lenses: What Makes a Vision-Language Model See Through Its Persona's Eyes?

Yoonho Shin

原文摘要

Vision-language models have been used to simulate where a user looks on a web page. However, a persona in the prompt reaches the simulated gaze only partly. We measure this reach as the difference in one model's gaze between two MatrAIx personas that differ in a single attribute. We introduce persona lenses, which place the persona between the model and the page: a text lens (a two-step prompt in which the model first writes what the persona would look at), a pixel lens (marks on the region matching the persona's interests) and a weight lens (a dwell reward gated to keep the scanpath natural). Using Qwen3-VL (4B and 32B) and Qwen3.5-9B on generated and live pages, we compare the lenses with one another and with scale, the 32B model with no lens. It has been confirmed that the text lens separates the personas strongly but is not robust to profile changes that should not move gaze. The pixel lens separates the personas less but is unaffected by attributes unrelated to gaze. At 4B and 9B, the weight lens separates the personas on interests held out from training, with no extra step on a new page. The 32B model separates the personas with the base prompt alone. Therefore, the choice of a lens depends on cost and model size.

cs.CV · cs.AI · cs.HC

新论文 · v1arXiv:2611.25506

Carry the Fine Print: Budget-Aware Visual Token Compression for Document OCR

Yixuan Huang, ShengFan Zhang, Jiawei Chen

原文摘要

Visual token compression often treats salience or similarity as a proxy for transcription importance. Complete document OCR breaks this assumption: small symbols and repeated entries can be indispensable to the transcript despite being visually inconspicuous. We present Select and Compensate, a two-stage framework built on a simple idea: choosing where to retain a token need not determine all the evidence it carries. Selection combines adaptive encoding resolution with global importance and local contrast to choose which tokens to retain as anchors. Compensation enriches these anchors with nearby discarded content and its relative position, without adding tokens. The OCR backbone remains frozen, and native coordinates and structural tokens are preserved. We evaluate complete page transcription across five backbones on OmniDocBench and document reconstruction on MPDocBench. With half the original visual tokens, our input-adapted configuration reaches 95.42 OmniDocBench Overall on Ovis versus 96.09 for the uncompressed model, and paired evaluations show gains over simply reducing the input resolution on both benchmarks. With the original input grid, our method stays within 0.17 points of the uncompressed model at 75% retention and exceeds a learned global selector by 4.70 points at 25%. On a fixed 200-page Ovis workload at the same 50% visual-token budget, only 3 of its outputs hit the length limit, versus 30-34 for the evaluated RTPrune, DivPrune, and HiPrune adaptations, and it finishes the batch 35-40% sooner. Code will be made publicly available.

cs.CV

新论文 · v1arXiv:2611.25500

PRIO: Pre-trained Representation for Interactive Objects in 4D Worlds

Shixun Huang, Lifu Wei, Yue Chang, Chen Geng, Heng Zhang, Jinhyung Ahn, Caoliwen Wang, Siyuan Chen 等 11 位作者

原文摘要

3D worlds can now be captured, reconstructed, and generated at scale, yet the objects in them stay still: a pressed pillow does not compress, and a pulled door does not swing. Bringing these objects into interactive 4D world models requires a representation of how they can move, deform, and respond physically to user actions in real time. We present PRIO, a pre-trained representation for interactive objects. Given static geometry, PRIO predicts an object-specific configuration space in a single forward pass. This space provides generalized coordinates for Lagrangian mechanics, allowing physical laws and user actions to govern motion. Configurations are linear in these coordinates, allowing the quantities needed by the dynamics to be precomputed. Dynamics then run at interactive rates without further network inference. Pre-trained on diverse 4D trajectories, PRIO learns priors over object configurations that generalize to unseen shapes. It supports meshes, point clouds, and 3D Gaussians, bringing objects in reconstructed and generated scenes into interaction. We demonstrate its use in real-to-sim workflows and robot manipulation. In addition, compared with existing 4D generation methods, PRIO generates dynamics faster and follows user actions more faithfully.

cs.CV

版本更新 · v4arXiv:2512.16767

Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters

Zhiyang Guo, Ori Zhang, Jax Xiang, Alan Zhao, Zhenxun Yuan, Wengang Zhou, Houqiang Li

原文摘要

Posing 3D characters is a fundamental task in computer graphics. However, existing paradigms, ranging from traditional auto-rigging to recent pose-conditioned generative models, frequently struggle with inaccurate skinning weights, fixed mesh topologies, and poor pose conformance. These challenges have become particularly pronounced with the recent explosion of AI-generated 3D assets, which often exhibit flawed structures and fused geometry. To address these issues, we introduce \textbf{Make-It-Poseable}, a novel feed-forward framework that reformulates character posing as a skinning-free latent-space transformation problem. By decoupling shape deformation from the constraints of fixed mesh connectivity, our method directly operates on compact latent representations to reconstruct characters in target poses. To achieve this, our framework integrates a latent posing transformer for shape manipulation, a dense pose representation for fine-grained control, and an adaptive completion module optimized via a bipartite-matched latent loss to robustly handle topological changes. Extensive experiments demonstrate that our method significantly outperforms existing baselines in posing quality. Furthermore, our design shows promising generalization to diverse morphologies such as quadrupeds in our qualitative tests, and supports various 3D authoring applications such as part replacement and refinement.

cs.CV

版本更新 · v2arXiv:2602.02227

Show, Don't Tell: Morphing Latent Reasoning into Image Generation

Harold Haodong Chen, Xinxiang Yin, Wen-Jie Shu, Hongfei Zhang, Zixin Zhang, Chenfei Liao, Litao Guo, Qifeng Chen 等 9 位作者

原文摘要

Text-to-image (T2I) generation has achieved remarkable progress, yet existing methods often lack the ability to dynamically reason and refine during generation--a hallmark of human creativity. Current reasoning-augmented paradigms most rely on explicit thought processes, where intermediate reasoning is decoded into discrete text at fixed steps with frequent image decoding and re-encoding, leading to inefficiencies, information loss, and cognitive mismatches. To bridge this gap, we introduce LatentMorph, a novel framework that seamlessly integrates implicit latent reasoning into the T2I generation process. At its core, LatentMorph introduces four lightweight components: (i) a condenser for summarizing intermediate generation states into compact visual memory, (ii) a translator for converting latent thoughts into actionable guidance, (iii) a shaper for dynamically steering next image token predictions, and (iv) an RL-trained invoker for adaptively determining when to invoke reasoning. By performing reasoning entirely in continuous latent spaces, LatentMorph avoids the bottlenecks of explicit reasoning and enables more adaptive self-refinement. Extensive experiments demonstrate that LatentMorph (I) enhances the base model Janus-Pro by $16\%$ on GenEval and $25\%$ on T2I-CompBench; (II) outperforms explicit paradigms (e.g., TwiG) by $15\%$ and $11\%$ on abstract reasoning tasks like WISE and IPV-Txt, (III) while reducing inference time by $44\%$ and token consumption by $51\%$; and (IV) exhibits $71\%$ cognitive alignment with human intuition on reasoning invocation.

cs.CV

版本更新 · v3arXiv:2601.17747

Bridging Supervision Gaps: A Unified Framework for Remote Sensing Change Detection

Kaixuan Jiang, Chen Wu, Zhenghui Zhao, Chengxi Han, Haonan Guo, Hongruixuan Chen

原文摘要

Change detection (CD) identifies surface changes from bi-temporal remote sensing imagery. Depending on annotation budgets and application contexts, real-world change labels take heterogeneous forms: pixel-level masks, image-level labels, unlabeled samples, or mixtures of these supervision types. However, most existing CD methods target a single supervision paradigm and cannot leverage complex annotation scenarios. To tackle this challenge, we present UniCD, a unified change detection framework that accommodates supervised, weakly supervised, unsupervised, and mixed-supervision learning within a single network. To bridge supervision granularity gaps, we design Supervision-Anchored Cross-Granularity Prototype Propagation, which constructs class-specific prototypes from pixel-level annotations and transfers reliable change semantics to image-level labeled and unlabeled samples. We further design Multi-source Consistency Rectification to filter unreliable pseudo labels and selectively recover informative pixels through multi-source evidence and cross-view consistency. Experiments on LEVIR-CD, WHU-CD, and CLCD demonstrate that UniCD consistently outperforms conventional mixed training, improving the average IoU by 3.02 percentage points across different mixed-supervision settings, while achieving state-of-the-art performance under individual supervision settings.

cs.CV

版本更新 · v2arXiv:2608.07981

Distilling Physical Priors into Streaming World Models

Liangliang Zhao, Junying Wang, Danni Yang, Yifan Chang, Bin Fu, Yu Qiao, Bowen Zhou, Yihao Liu

原文摘要

Streaming world models predict future visual states online while maintaining physically coherent dynamics over long horizons. However, their rollouts often violate basic physical constraints. A common approach distills pretrained bidirectional DiTs into few-step causal generators. However, this paradigm suffers from two fundamental limitations: generic bidirectional teachers acquire limited physical priors from visually oriented pretraining, and the limited priors suffer further loss during bidirectional-to-causal distillation. We present PhyS, a three-stage framework for distilling physical priors into streaming world models. To acquire physical priors from real-world interactions, we construct PhyS-120K, a dataset of 120K real-world physical-interaction videos spanning rigid-body dynamics, soft-body deformation, fluid phenomena, and phase transitions. Each video is annotated with structured descriptions of object properties and causal state transitions. Physics-aware supervised fine-tuning injects the physical priors into a bidirectional 14B DiT teacher, which we then distill into a lightweight 1.3B causal DiT for few-step autoregressive streaming generation. Finally, we use online reinforcement learning to incentivize the distilled model to generate physically plausible rollouts and further propose Temporal Credit Routing (TCR) to address temporal credit assignment. TCR evaluates physical consistency over overlapping temporal windows and routes the resulting group-relative advantages to temporally aligned denoising actions. On PhysicsIQ, PhyS improves the Wan2.1-14B teacher by 18.2\% and the Self Forcing, Rolling Forcing, and Causal Forcing by 23.7\%, 14.8\%, and 31.4\%, respectively. Results also improve the physics-aware video benchmarks VideoPhy, VideoPhy2, and PhyGenBench. The dataset, code, and more sample videos are available on our Project Page.

cs.CV

版本更新 · v2arXiv:2611.16413

RICapBench: A Fine-Grained Visual Understanding Benchmark Dataset for Vision-Language Models in Remote Sensing

Xue Wang, Yubin Xu, Kun Tan

原文摘要

Advances in vision-language models (VLMs) have improved remote sensing image analysis and supported geospatial decision-making. However, fine-grained understanding of remote sensing imagery remains challenging for VLMs. Large variations in object scale, complex geospatial relations among instances, and limited visual detail hinder precise instance localization, visible attribute identification, and spatial relation understanding, potentially leading to descriptions that lack visual grounding. Existing datasets and benchmarks insufficiently assess end-to-end instance localization and captioning without target-specific textual cues. To support this evaluation, we introduce RICapBench, a dataset and benchmark that unifies instance localization and fine-grained captioning in remote sensing. RICapBench contains 245,466 instance-level annotations and 498,005 spatial relation tuples spanning general remote sensing, UAV remote sensing, and dense small-object scenarios. Each annotation pairs an object's oriented bounding box with a natural language description of its visible attributes and spatial relations to surrounding instances and environmental elements. To evaluate the accuracy and completeness of spatial relation captioning, we propose a remote sensing spatial relation parser and the RelCap-F1 metric. We combine RelCap-F1 with instance localization and attribute captioning metrics into a composite metric, RICScore. Our evaluation of 15 advanced open-source and closed-source VLMs identifies instance localization as a major bottleneck for these models. LocateAnything achieves the highest RICScore of 31.68, but scores lower on spatial relation captioning than other task-fine-tuned open-source VLMs. Code and dataset are available at https://github.com/Xldln/RICapBench.

cs.CV