Salient
-
TRINITY: A Multi-Perspective Benchmark for Personal-Style Video Highlight Detection
2026-08-30 05:46:13Qianqian Chen, Hyun Bin Kim, Denzel Elden Wijaya, Yang Yi, Bo Liu, Yangkai DingAbstract
Traditional video highlight detection relies on a narrow, event-centric definition of saliency, which often fails to generalize to unconstrained personal videos where highlights are heterogeneous and perspective-dependent. To address this, we introduce TRINITY, a multi-perspective benchmark that decomposes highlight saliency into three complementary dimensions, Event, Emotion, and Nature, within a unified temporal framework. Leveraging this multi-faceted view, we propose a shared-backbone multi-branch architecture designed for parallel multi-perspective prediction via view-specific experts. Comprehensive experiments demonstrate that our method significantly outperforms state-of-the-art baselines, achieving gains of +7.15/+3.62 mAP (rho=15%/50%) on Mr. HiSum and +10.82 mAP on YouTube Highlights. These results validate that multi-perspective modeling provides a more robust and comprehensive formulation of video saliency, especially for complex real-world scenarios. The benchmark and relevant codes will be released upon acceptance. The benchmark is available at this https URL and the code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29577
PDF
-
SGPDFuse: Semantically-Guided Physics-Disentanglement General Multi-Modal Image Fusion
2026-08-29 12:08:27Haozhen Wei, Chengjun Jiang, Yutong Guo, Xinrui Ju, Xingyuan Li, Xiang Chen, Jinyuan LiuAbstract
Multimodal image fusion (MMIF) aims to integrate complementary sensor data into a single representation that preserves intrinsic scene reality while eliminating environmental interferences. Most existing approaches rely on blind feature aggregation, which excels at signal accumulation but fails to distinguish essential content from physical degradations. We propose SGPDFuse, which bridges this gap by mapping inputs into a physics-disentangled structural representation via a Semantic-Physical Parametric Bridge (SPPB) built on pretrained vision foundation models, utilizing the Intrinsic-Variation principle to decouple invariant scene attributes from transient environmental factors. To guide this decomposition, we introduce a Semantic Alignment mechanism: we explicitly anchor the fused representation to salient semantic features in the same foundation model feature space via cosine similarity to preserve critical targets, while enforcing physical texture fidelity through Gram-matrix regularization to strictly eliminate unnatural artifacts. Extensive experiments demonstrate that SGPDFuse achieves state-of-the-art performance across infrared-visible, multi-focus, and multi-exposure benchmarks using a single architecture.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29220
PDF
-
SGRNet: Spatially Guided Radiology Network for Structured Radiological Reporting of Head and Neck Cancer
2026-08-29 09:01:52Ayush Gupta, Vinkle Srivastav, Prateek Upadhya, Amit Gupta, Krithika Rangarajan, Nicolas PadoyAbstract
Automated radiological report generation can alleviate clinical workloads and eliminate observer variability. However, standard free-text generation models pose hallucination risks in dense regions and fail under data scarcity. We address these challenges in Head and Neck Cancer (HNC) from contrast-enhanced CT (CECT) imaging. To enforce factual safety, we reformulate report generation as an anatomically grounded, multi-label, structured reporting task, predicting localized tumor involvement across a hierarchical clinical schema. To bridge the visual gap from missing metabolic imaging (e.g., PET), we introduce SGRNet (Spatially Guided Radiology Network), incorporating two low-cost spatial priors: automated organ segmentations and weakly supervised tumor localization maps modeled via 3D Gaussian heatmaps. These priors are dynamically integrated via spatial feature modulation to guide the network toward subtle tumor-induced structural alterations. Evaluated on a multi-centric dataset of 184 paired HNC CECT volumes and reports, on five clinically salient, densely packed anatomical subsites, SGRNet achieves a mean Average Precision (mAP) of 0.60, an 8.8 percentage-point absolute improvement over strong volume-only 3D baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29153
PDF
-
Diagnose, Then Refine: A Closed-Loop TTS System with AudioLLM-Guided Correction
2026-08-29 00:47:53Zeyang Song, Tianchi Liu, Tianrui Wang, Chenglin Xu, Steven Y. Guo, Haizhou LiAbstract
Current TTS systems typically rely on open-loop, single-pass generation and can produce sporadic local prosodic defects, such as misplaced stress, unnatural pauses, or flattened intonation, that utterance-level metrics often fail to expose. We present LoopTTS, a judge-guided Filter-Judge-Refiner framework for recovering low-quality TTS outputs diagnosed by an AudioLLM. Given an initial utterance from a base TTS model, an AudioLLM Judge identifies salient prosodic issues and generates structured refine instructions; a Refiner, our fine-grained instruction-following TTS model, then performs guided expressive re-synthesis conditioned on the initial utterance, target text, and instruction. To train the Refiner, we construct Refiner-DB, a 42K-example AudioLLM-annotated dataset with word-level prosodic weak supervision. Human evaluation on diagnosed low-quality utterances shows that LoopTTS can detect perceptually salient errors and correct them with the Refiner, outperforming raw generated audio and practical open-loop re-generation baselines in recovery quality. The Refiner also demonstrates stronger instruction-following ability for stress and pause control in targeted prosody modification.
Abstract (translated)
URL
https://arxiv.org/abs/2608.28970
PDF
-
Blind Stereoscopic Omnidirectional Image Quality Assessment Using Predictive Coding Hierarchy
Abstract
Stereoscopic omnidirectional images (SOIs) have provided users with newly immersive quality of experience in virtual reality environments. However, developing efficient and accurate perceptual quality assessment metrics for SOIs remains challenging due to many factors such as freely changeable field of views and binocular vision. In this paper, based on the characteristics of the human visual system (HVS), we propose a Predictive Coding Hierarchy-inspired metric (PCH) for blind/no-reference stereoscopic omnidirectional image quality assessment. Motivated by the viewing process of SOIs, the proposed PCH includes a local cyclopean perception module, a global predictive perception module, and a visual quality regressor. First, observers browse different spherical sceneries from viewports, and aggregate the local visual information to infer the perceptual quality of SOIs. Therefore, we extract various viewports, followed by cyclopean conversion and saliency detection to approach the perception and attention of the human brain. After the local aggregation, viewers then infer the global scene in their minds. Based on the binocular mechanism, we fuse left and right views to perform predictive coding hierarchy modelling. Finally, the visual quality regressor is exploited to obtain the ultimate quality score related to both local and global perceptual cues. Extensive experiments demonstrate that the proposed PCH achieves competitive and consistently improved performance compared with state-of-the-art quality assessment methods.
Abstract (translated)
URL
https://arxiv.org/abs/2608.28798
PDF
-
Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG
2026-08-27 14:25:32Dong-Hee Kim, Seonwoo Choi, Changbeen Kim, Jungmyung Wi, Juyeon Ko, Youngju Choi, Il Hyeon Mun, Hyunwoo J. Kim, Donghyun KimAbstract
Understanding long-form video remains a fundamental challenge for multimodal large language models (MLLMs). Sparse frame sampling fails to capture fine-grained visual details, while dense sampling quickly exceeds context length limits. Retrieval-augmented generation (RAG) offers a promising middle ground by selectively retrieving relevant video segments for grounded generation, yet its effectiveness critically depends on the quality of the video segments used as retrieval units. In this paper, we investigate RAG for movie understanding, which demands story-level reasoning over characters, events, and narrative arcs spanning hours of content. Scene segmentation, a long-studied problem that partitions movies into semantically coherent units, is a natural candidate for defining such retrieval units. We reexamine whether existing methods actually serve this role through comprehensive evaluation on downstream movie understanding tasks, and find that they consistently fail to outperform naive uniform temporal chunking. Our audit of the most standard scene segmentation benchmarks reveals why: current annotations prioritize visually salient transitions over narrative event structure. Motivated by this mismatch, we introduce NarraScene, a narrative-centric scene segmentation dataset annotated with a three-level cognitive taxonomy spanning physical, character, and narrative change, where every valid boundary requires a narrative-level shift. When used as retrieval units, these narrative-grounded segments outperform uniform chunking on downstream movie understanding tasks, suggesting that the central challenge for scene segmentation in movie RAG is not detecting boundaries, but identifying the narrative event units that matter for movie understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2608.28699
PDF
-
Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverable
2026-08-27 10:59:03Zhichen Dong, Zhixuan Liu, Yuyu Fan, Xiangtian Li, Shuyang Zhang, Chao YangAbstract
Scaling model-generated data is usually viewed as improving distillation: more examples should increase coverage, reduce noise, and produce stronger students. We show a second effect: larger datasets can make subtle teacher-specific signals easier to detect in the trained student, even when examples are off-task and never mention the trait. In a controlled setup inspired by subliminal learning, a teacher induced to express a target trait generates restricted off-task data, such as number-only completions. Students trained on different amounts of independent off-task data are evaluated in a separate domain, with matched no-trait controls isolating target-specific transfer. Our main finding is that larger independent datasets make the teacher's induced trait stand out more clearly in the student's later behavior. Other plausible traits may also strengthen with scale, but the target usually grows more. When the small-scale student already favors the target, scaling mainly amplifies that behavior; when it favors a related or salient alternative, more data can shift behavior toward the intended trait. Analyses of learned LoRA updates show a parallel trend. These effects appear across model families, trait types, multi-trait settings, and cross-model transfer. Our results suggest that scaling generated distillation data should be paired with trait-aware curation and evaluation, even when the data appears off-task or benign.
Abstract (translated)
URL
https://arxiv.org/abs/2608.26958
PDF
-
Real-time Unsupervised Object Discovery from Asynchronous Event Streams
2026-08-27 05:53:04Pratham G. Shenwai, Hemant Kumar Singh, Sridhar RaviAbstract
Event cameras capture pixel-level intensity changes with microsecond resolution to produce highly sparse asynchronous data streams. For visual perception in latency-critical environments, we propose a lightweight, training-free framework for discovery of moving objects based on spatio-temporal clustering. This framework is driven by two core contributions. First, a linear-time Spatio-temporal Probabilistic Event Filter (SPEF) that introduces an adaptive event acceptance threshold to distinguish salient motion structures from background noise. Second, an Event Morton Code Clustering (EMCC) module that bypasses expensive distance matrix computation to efficiently group events for unsupervised discovery of moving objects. On the E-MLB dataset benchmark, SPEF achieves the best denoising performance among classical filtering methods and remains competitive with learning-based approaches without requiring any offline training. On object discovery, EMCC achieves the highest overall accuracy and lowest execution time across the FRED and eTraM datasets, outperforming established density-based clustering baselines by a substantial margin. Overall, this work establishes a new performance benchmark for classical object discovery in event data, providing a highly scalable, training-free solution for resource-constrained visual perception. The code is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.26644
PDF
-
Diff Mining: Logit Differences Reveal Finetuning Objectives
2026-08-26 23:33:18Greg Kocher, Robert West, Cl\'ement Dumas, Julian MinderAbstract
Finetuning has become the gold standard for refining existing behaviors and inducing new ones in language models, yet it often remains unclear exactly which behaviors emerge during this process. As models grow ever more capable, understanding finetuning better becomes increasingly important, particularly since unwanted behaviors may arise during finetuning. In this paper, we introduce Diff Mining, a simple yet effective framework for identifying what a finetuned model has learned by comparing its logits to those of its base model. Diff Mining effectively surfaces salient tokens that are amplified in the finetuned model, serving as a fingerprint of its training -- even on text unrelated to the finetuning domain. Unlike many existing model diffing methods which require model internals, Diff Mining only needs access to output logits and scales to large models. The framework consists of two modular stages: (i) extracting per-context logit differences between the finetuned and base models on a reference corpus, and (ii) aggregating the resulting signals to construct an interpretable token set representing the finetune. For aggregation, we explore both a simple Top-K frequency method and a Non-negative Matrix Factorization (NMF)-based approach for disentangling multiple finetuning objectives into distinct token clusters. Empirically, Diff Mining succeeds across diverse settings: on finetune domain detection, it significantly outperforms state-of-the-art model diffing methods both in identifying relevant tokens and in downstream performance when an interpretability agent is given access to the extracted token set; on models with injected biases, it identifies more than one third of the biases without targeted probing. Overall, our framework shows promise in developing auditing tools to detect finetuning objectives.
Abstract (translated)
URL
https://arxiv.org/abs/2608.26462
PDF
-
TDFNet: Tri-projection Deformable Fusion Network for Panoramic Salient Object Detection
2026-08-26 13:54:44Qiangqiang Zhou, Jiacong Yu, Jiawei Xu, Yong Chen, Xin Huang, Ping LiAbstract
Recent years have witnessed the growing potential of panoramic salient object detection in robotic vision, virtual reality, and related applications. However, projecting spherical scenes onto 2D planes inevitably introduces geometric distortions, which fundamentally limit the effectiveness of existing projection-based methods. Specifically, Equirectangular Projection (ERP) suffers from severe polar stretching distortions, while cube map projection introduces discontinuities across cube-face boundaries, resulting in degraded feature discriminability and compromised geometric consistency. To address these limitations, we propose TDFNet, the first Tri-projection Deformable Fusion Network for panoramic salient object detection, exploiting complementary projection representations to alleviate geometric distortions and improve detection this http URL, we design a cross-projection deformable attention (CDA) module that leverages spatial correspondences between different projections to construct geometry-aware sampling locations, guiding deformable attention for cross-projection contextual aggregation and enhancing robustness against projection-induced deformations. Furthermore, we introduce a latitude-guided fusion module, which utilizes spherical latitude priors to construct geometric confidence weights for adaptively balancing ERP and CMP features. Meanwhile, LGF incorporates distortion-reduced semantic references from Tangent Projection to achieve cross-projection feature refinement and spatial this http URL constructing a three-branch encoding architecture based on ERP, CMP, and Tangent Projection, TDFNet simultaneously preserves global spatial continuity, local geometric details, and fine-grained boundary information.
Abstract (translated)
URL
https://arxiv.org/abs/2608.25808
PDF
-
MIMONet: Multi-scale Input and Multi-scale Output Network for Salient Object Detection
2026-08-26 12:46:22Zhaojian Yao, Wei Gao, Tiesong Zhao, Hui Yuan, Sam KwongAbstract
The existing methods for saliency detection task focus on the application of multi-level features, aiming to take advantage of the respective strengths of high- and low-level features. However, because the inputs of these models are single-size images, their multi-level features have difficulty in learning the knowledge of size variations of salient objects. Object-scale variation learning has great potential for detecting multi-scale objects, which has not been fully explored by existing methods. To improve the recognition ability of a model for objects with different sizes, we are inspired by the image pyramid to propose a Multi-scale Input and Multi-scale Output Network (MIMONet). In MIMONet, we extract multi-level features for three images with different resolutions to form three encoder branches, and information will be exchanged between the branches. The advantage of this approach is that the features of one branch can learn the knowledge of target size variation from the features of the other two branches. In addition, we design a Multi-scale Perception (MSP) module, in which the input feature layer is divided into several sub-layers with different resolutions. Capturing the multi-level structure information of the objects in these sub-layers can make the objects more fully perceived. For network training, we propose a Joint Saliency Loss (JSL), which can constrain multiple saliency maps output by the network to identify the same foreground objects, and induce their boundaries to be preserved clearly. Experimental results show that MIMONet has stronger detection capabilities and harvests better evaluation scores on multiple datasets compared to existing models. The code of our model will be released.
Abstract (translated)
URL
https://arxiv.org/abs/2608.25733
PDF
-
Saliency-Depth Conditioning for Zero-Shot Segmentation of Communication-Tower Components in Cluttered UAV Imagery
2026-08-26 06:47:36Ali Lesani, Chul Min Yeum, Su-Min KangAbstract
Fine-grained segmentation of communication-tower components in UAV imagery is essential for automated inspection, yet task-specific models are hard to develop due to limited instance-level annotations. Zero-shot segmentation models offer a promising alternative, but in cluttered scenes, visually similar background structures interfere with component localization, causing missed instances and false positives. We propose a model-agnostic saliency-depth foreground-conditioning strategy combining appearance-based saliency with monocular relative depth to construct a coarse tower prior and suppress irrelevant content. We integrate this module with Grounded-SAM and SAM 3, yielding SD-Grounded-SAM and SD-SAM 3. SD-Grounded-SAM further applies geometric and depth-aware box refinement before mask generation, while SD-SAM 3 relies on SAM 3's internal setup. On TOW-300, a dataset of 340 communication-tower UAV images, our strategy improves both baselines: SD-SAM 3 achieves the strongest instance-segmentation performance, while SD-Grounded-SAM produces fewer false positives. Ablations confirm complementary gains from saliency, depth, and box refinement, improving robustness in cluttered scenes.
Abstract (translated)
URL
https://arxiv.org/abs/2608.25435
PDF
-
DoublesEval: Diagnosing Multi-Agent Tactical Reasoning in Vision-Language Models via Professional Doubles Badminton
2026-08-25 11:51:01Jintao Cheng, Weibin LiAbstract
Visual Language Models (VLMs) excel at describing visible scene content but struggle to reason about dynamic multi-agent interactions, where action semantics depend on coordinated roles and spatial-temporal dependencies. We formalize this capability as \textbf{multi-agent tactical reasoning} and introduce \textbf{DoublesEval}, a diagnostic evaluation framework that leverages professional doubles badminton as a structurally tractable testbed. DoublesEval employs a key-moment-based protocol that decomposes rallies into tactically salient instants and probes models across four interpretable dimensions: atomic recognition, intra-segment composite understanding, cross-segment causal reasoning, and high-level tactical abstraction. This design isolates \emph{where} reasoning fails, rather than merely measuring answer correctness. To address observed failure modes, we propose \textbf{TacticCheck}, a lightweight constraint-guided test-time consistency checker that reranks candidate answers using the model's own lower-level tactical predictions, requiring no parameter updates or ground-truth labels at inference time. Evaluating four representative open-source VLMs on 60 curated rallies (yielding $\sim$9.6K structured instances) via a zero-shot protocol, we find that models remain weak across all diagnostic levels, with especially clear bottlenecks in spatial state, interaction binding, and terminal evidence. TacticCheck delivers consistent gains across all evaluated models, while still leaving a substantial gap to robust tactical reasoning. These results highlight the need for structured, interaction-aware evaluation paradigms for next-generation VLMs. The source code is available in \href{this https URL}{\textcolor{blue}{our GitHub repository}}.
Abstract (translated)
URL
https://arxiv.org/abs/2608.24439
PDF
-
GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Model
2026-08-25 06:28:28Md Selim Sarowar, Md Tanvir Islam, Sungho Kim, Sangtae AhnAbstract
Vision-Language-Action (VLA) models encode visual observations as flat 2D patch tokens that carry no intrinsic geometric structure, and augmenting them with dense monocular depth injects per-pixel scalar values that encode neither surface orientation nor geometric confidence. This leaves the policy with limited structured spatial reasoning for action prediction. We propose GaussVLA, a Mamba-based VLA that incorporates two custom modules: Gaussian Spatial Tokenizer (GST) to lift frozen semantic and depth features into compact 3D Gaussian tokens, pools geometrically salient regions with learned queries, and \emph{Depth-Aware Chain-of-Thought (DA-CoT)} that performs structured, non-autoregressive geometric reasoning under language and flow-time conditioning. Across both simulation and real-world evaluations, GaussVLA demonstrates strong spatial-manipulation performance while remaining parameter-efficient. On LIBERO, it achieves 93.5% average success and 100.0% success on the Spatial suite with only 200M parameters, improving over SpatialVLA by 19.7% relative average success while remaining significantly more parameter-efficient.
Abstract (translated)
URL
https://arxiv.org/abs/2608.24959
PDF
-
E2S-Pruner: Progressive Two-Stage Evidence Fusion for Visual Token Pruning in Vision-Language Models
2026-08-24 13:44:41Taoyu Qian, Qi Wang, Daqian Shi, Yuanhao Jiang, Shang Gao, Hualong YuAbstract
Vision-language models typically encode an image into hundreds of visual tokens, incurring substantial inference latency and GPU memory overhead. Existing pruning methods largely rely on attention scores and directly aggregate outputs across attention heads and network layers, making it difficult to characterize evidential uncertainty and conflict. We propose E2S-Pruner, a progressive two-stage evidence-fusion framework for visual token pruning that requires no auxiliary model, trainable parameters, or fine-tuning. In the first stage, E2S-Pruner treats each attention head as an independent evidence source, estimates its reliability from evidence clarity and inter-head consistency, and represents each visual token using three states: important, unimportant, and uncertain. In the second stage, Dempster--Shafer evidence theory is used to quantify inter-layer conflict and fuse complementary evidence from multiple network layers. We further introduce a spatial novelty constraint that promotes coverage of distinct image regions and prevents the retained tokens from concentrating in a few locally salient areas. On LLaVA-1.5-7B, E2S-Pruner retains 98.0%, 96.8%, and 90.6% of the aggregate performance when the average numbers of retained visual tokens are 192, 128, and 64, respectively, while improving throughput by 1.96x and 2.09x under the 128-token and 64-token settings. Experiments on Qwen2-VL-7B further demonstrate cross-model generalization. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.23253
PDF
-
InstructMove: A Text-Indispensable Benchmark for Instruction-Following Manipulation
2026-08-24 08:53:41Mengao Zhao, Ziang Li, Chaodong Huang, Mengchen Ma, Haoyi Jiang, Yiwei Jin, Xinjie Wang, Yun Du, Xuewu Lin, Taojun Ding, Hongyu Xie, Jackson Jiang, Chunlei Yu, Kaihua Zhang, Lichao Huang, Liu Liu, Tianwei Lin, Zhizhong SuAbstract
Vision-language-action (VLA) models have made general-purpose robot manipulation increasingly plausible by conditioning robot actions on natural-language instructions. A key test of such generality is whether policies actually follow language instructions. Yet many manipulation benchmarks leave this ability underdetermined: the intended object or destination is often visually salient or uniquely feasible, allowing policies to succeed without grounding the instruction. We argue that instruction-following evaluation should be text-indispensable: multiple actions should be visually and physically plausible, while only one should be consistent with the language instruction. We introduce InstructMove, a text-indispensable benchmark for instruction-following manipulation. InstructMove instantiates this principle in pick-and-place scenes with semantic distractors, decomposing instruction following into category identification, attribute discrimination, spatial reasoning, and compositional pick-and-place. InstructMove supports a train-eval protocol with InstructMove training data and held-out evaluation tasks, with additional diagnostics for language dependence. Experiments with representative VLA policies show that InstructMove provides a controlled testbed for diagnosing visual shortcuts and that InstructMove simulation data can improve real-world instruction-following manipulation performance. Code: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.22990
PDF
-
DECO: Depth-Guided Co-Visibility Reasoning for Low-Altitude UAV Visual Localization
2026-08-23 08:28:14Yibin Ye, Xichao Teng, Shuo Chen, Xiaokai Song, Dongdong Guan, Qifeng Yu, Zhang LiAbstract
Unmanned aerial vehicles (UAVs) increasingly require robust visual localization in GNSS-denied environments. A common solution estimates UAV poses by matching keypoints between UAV images and geo-tagged orthographic reference maps derived from satellite or aerial imagery, followed by Perspective-\(n\)-Point (PnP) pose solving. However, such reference maps mainly record top-down surfaces such as roofs and ground planes, while vertical structures such as facades and walls are often compressed or missing. Consequently, many visually distinctive keypoints in low-altitude UAV images have no valid counterparts in the reference map, leading to redundant matches and inaccurate pose estimation. To address this issue, we propose DECO, a DEpth-guided CO-visibility reasoning framework for low-altitude UAV visual localization. DECO uses monocular depth priors to infer local surface geometry and estimate co-visible regions between UAV images and the reference map. Based on this prior, a Geometry-Saliency Coupled Co-visibility Score is introduced to jointly consider geometric co-visibility and detector saliency for keypoint ranking. In this way, DECO retains keypoints that are both visually distinctive and geometrically co-visible, improving feature matching and PnP-based pose estimation. Extensive experiments demonstrate that DECO achieves superior localization performance and can be integrated with different depth models, feature detectors, and matchers. The source code will be available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.22289
PDF
-
MEMORY Wins All: Indirect Bias Injection Attacks via Social Media Feeds
2026-08-22 18:03:20Minjae Seo, Wonwoo Choi, Geonwoo Han, Taekyoung Kwon, Yongsu Kim, Sang Seo, Jaewon Noh, Hankyul Baek, Seongyun Seo, Myoungsung YouAbstract
Personal AI agents routinely consume external content while performing tasks such as web browsing, email processing, and SNS feed summarization, and they retain selected information or execution results in persistent memory for later use. We show that this ordinary ingestion of external content opens an indirect path for manipulating subsequent agent behavior. Based on this observation, we present IBIA, an Indirect Bias Injection Attack that plants an adversary-aligned stance on a specific topic into a victim agent's memory through external content, without direct access to the agent, its memory, or future user queries. For this, IBIA combines three mechanisms: comment cloaking, which keeps the crafted content consistent with the surrounding discussion, comment watermarking, which enables lightweight identification during curation, and category anchoring, which makes the retained stance salient under later related requests. We evaluate IBIA on BiasBench, a benchmark of 6,000 adversary-crafted social comments and 120 email instances. The watermark-based curation identifies 95.9% of the injected comments. Under the OpenClaw setting, IBIA achieves adversary-aligned response rates (AARs) of 91.2% on average across four downstream tasks, including 86.6% on the frontier GPT-5.5. We further propose a memory boundary defense that detects the injected bias and reduces AARs to 80.6%.
Abstract (translated)
URL
https://arxiv.org/abs/2608.22061
PDF
-
StereoDiffuer: Diffusion-based Progressive Geometry Modeling with Saliency Attention Perception for Stereo Matching
2026-08-22 01:04:27Bohan LiAbstract
With the advance of deep neural networks, the quality of disparity maps obtained through stereo matching has steadily improved. However, existing stereo matching methods still struggle to preserve fine-grained geometric details, resulting in blurred edges and over-smoothed predictions in challenging regions. To address these limitations, we propose StereoDiffuer, an iterative diffusion-based stereo matching framework that explicitly models geometric details and progressively refines disparity estimates. The framework incorporates a Saliency Attention Perception (SAP) module to extract salient geometric cues, including object boundaries, thin structures, and sharp edges. Confidence-guided SAP features are combined with the initial disparity estimate to condition an iterative denoising diffusion process, which corrects residual disparity errors and restores geometric details suppressed during cost-volume regularization and upsampling. Experimental results on the Scene Flow and KITTI benchmarks demonstrate the effectiveness of the proposed framework and its competitive performance relative to the compared stereo matching methods.
Abstract (translated)
URL
https://arxiv.org/abs/2608.21710
PDF
-
Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models
2026-08-21 15:59:37Zhuoyuan Li, Rui Zhao, Jin Wang, Hanwei Zhu, Cong Zhang, Giuseppe Valenzise, Weisi Lin, Kin-Man LamAbstract
Token compression has become a key technique for reducing the inference cost of large foundation models, with approaches such as token pruning and KV-cache reuse widely adopted in vision-language models and recently explored for embodied agents. In embodied agents, tokens not only support perception and semantic understanding but also directly affect latency-sensitive closed-loop robot action prediction. Existing schemes typically guide compression using redundancy or importance cues, such as visual similarity, attention scores, and saliency. However, these cues only indirectly measure the key factor for safe compression: how much a token can change before causing an unacceptable deviation in downstream actions. This receiver-dependent tolerance is closely related to the principle of just noticeable difference (JND). Classical JND characterizes signal tolerance in the human visual system, while machine-oriented JND extends this concept to downstream machine responses. Building on this progression, we introduce Action-JND, which extends JND modeling to embodied perception by defining noticeability through the language-conditioned action response of a vision-language-action (VLA) policy in closed-loop control. A token change is considered admissible only when the induced action deviation remains within a tolerated margin. To realize this concept, we develop a lightweight token-wise JND estimator in deep visual-feature space to predict the maximum tolerable perturbation while preserving policy responses. The resulting action-tolerance score serves as a plug-and-play criterion for VLA compression paradigms, including stale-KV reuse and token pruning, prioritizing action-tolerant tokens for compression. Experiments on the LIBERO benchmark with OpenVLA and OpenVLA-OFT demonstrate that Action-JND consistently improves compression reliability, especially under aggressive compression ratios.
Abstract (translated)
URL
https://arxiv.org/abs/2608.21247
PDF
