Salient
-
Why Do You Say It Like That? A Phoneme-Level Framework for Explainable Speech Deepfake Detection
2026-07-09 15:23:45Anna Taylor, Michele Panariello, Massimiliano Todisco, Chiara Galdi, Nicholas Evans, Driss MatroufAbstract
As the accuracy of speech deepfake detection improves with the use of self-supervised representations such as wav2vec 2.0 and HuBERT, understanding why the speech is classified as bona fide or deepfake remains an open challenge. In pursuit of more trustworthy and interpretable artificial intelligence, we introduce a phoneme-level analysis framework that connects model predictions to measurable phonetic units. Our post-hoc explainability method is generally applicable to a variety of speech deepfake detection systems based on convolutional neural networks since it leverages Gradient-weighted Class Activation Mapping in conjunction with speech recognition to generate saliency maps aligned with phonemes and pauses. This pipeline reveals statistically significant attack- and speaker-dependent phonetic cues associated with spoofed speech in terms that humans can understand. Experiments using ASVspoof 5 show comparable detection performance to similar architectures while providing linguistic interpretations across speakers and spoofing conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2607.08586
PDF
-
LEEVLA: Seeing What Matters in Latent Environment Evolution for Vision-Language-Action
2026-07-09 07:28:21Qi Lyu, Baicheng Liu, Xudong Wang, Jiahua Dong, Lianqing Liu, Zhi HanAbstract
Vision-language-action (VLA) models aim to map multimodal inputs to robot actions. However, most existing approaches struggle to cover complex dynamic scenarios due to treating all visual tokens uniformly and reasoning with human-selected factors, which lack mechanisms to emphasize task-critical evidence and ignore underlying factors. To address this issue, we propose LEEVLA, a VLA architecture for seeing what matters in Latent Environment Evolution that explicitly guides the model toward informative regions while preserving the structured evolution of latent world representations. To identify salient and instruction-relevant regions, we introduce drift-guided dynamic prioritization (DGDP), which combines dynamic position prioritization (DPP) with semantic drift guidance (SDG) to guide the VLA agent where to attend during training. On top of this, we introduce structured feature flow generation (SFFG), which models how these prioritized features should evolve in latent space via prototype-to-periphery (P2P) prediction, and a mutual-neighborhood contrastive (MC) loss to maintain topological consistency among neighborhoods. Together, DGDP and SFFG form a task-aware "where-how" training framework. Extensive experiments on VLA benchmarks show that LEEVLA consistently outperforms prior methods, confirming that explicit task-evidence guidance and structured latent reasoning are both crucial for scalable VLA. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.08182
PDF
-
`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation
2026-07-08 10:13:20Waqas Arshid, Mohammad Awrangjeb, Alan Wee-Chung Liew, Yongsheng GaoAbstract
Video object segmentation (VOS) is a fundamental task in video understanding, requiring accurate delineation and consistent tracking of objects across frames. While supervised methods achieve strong performance, they rely on densely annotated datasets that are costly to obtain and have limited domain coverage. Self-supervised learning offers a promising alternative by removing the need for manual labels; however, existing approaches often struggle to jointly maintain spatial accuracy and temporal coherence, particularly in unconstrained multi-object scenarios. Many rely on optical flow, synthetic motion cues, or task-specific pretraining, limiting scalability and generalisation. We propose a self-supervised framework, Cross-Temporal Consistency and Clustering, that learns mid-level, part-aware representations by combining attention-guided token selection with lightweight temporal clustering. Instead of operating at the pixel or whole-object level, the method aligns soft part assignments across time using a saliency-weighted symmetric consistency objective. The framework leverages a frozen transformer backbone with lightweight modules for adaptive token selection and multi-offset temporal alignment, enabling efficient scaling across resolutions and motion patterns.
Abstract (translated)
URL
https://arxiv.org/abs/2607.07230
PDF
-
Geometric Collapse: When Vision Models Fail to Verify Physical Causality
2026-07-08 00:04:02Wentao Zhang, Jinhu Qi, Weiqiang Jin, Yifei Zhang, Chan-Tong Lam, Irwin KingAbstract
Recent progress in large-scale self-supervised learning has improved dense geometric prediction, but it remains unclear whether such scaling yields inference-time physical plausibility checks. We propose Scrambled Edges, a controlled counterfactual that injects salient edge-like cues while violating surface continuity, illumination coherence, and occlusion ordering. With energy-matched and structure-matched controls, we isolate the effect of unsupported edge evidence from high-frequency energy and edge sparsity. Across CNN/ViT/SSL depth predictors on NYU Depth v2 and KITTI, Scrambled Edges induce up to 3.2x larger deviation from clean predictions than energy-matched noise; additional diffusion and flow-matching depth estimators show attenuated but still significant collapse. The resulting Geometric Collapse propagates globally: even with oracle knowledge of the corrupted region, output-level repair recovers only 47%, with substantial error outside the mask. These findings provide controlled behavioral evidence that current dense predictors lack reliable mechanisms to quarantine physically unsupported edge cues, motivating explicit plausibility scoring and selective cue integration.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06871
PDF
-
Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs
2026-07-07 21:57:54Albert Zeyer, Ralf Schl\"uter, Hermann NeyAbstract
Speech-to-text alignment means finding the temporal boundaries of each word in the audio. Some models provide such an alignment directly and others do not. Connectionist temporal classification (CTC) and transducer models have an alignment by construction, whereas attention-based encoder-decoders (AED) and speech large language models (LLMs) do not, and their word timings are usually read off the attention weights instead. All of these signals live on the encoder frame grid, which bounds their temporal precision. We study a generic gradient-based alignment that applies to any differentiable ASR model. We take the gradient of each teacher-forced token log probability with respect to the input, reduce it to a per-frame saliency, and decode the resulting matrix into word boundaries with a single dynamic-programming pass. The method needs no training, no model modification and no alignment heads, works across all model families including the speech LLMs, and aligns on the input grid rather than on the coarser encoder grid. We evaluate it on sixteen models from four families, on read (TIMIT) and spontaneous (Buckeye) speech, each against the model's own native or attention-based alignment. We find that the gradient yields a usable alignment for every model, that it is usually somewhat behind a strong native aligner but better where the native alignment is weak, as for the streaming models, and that its main disadvantage is the cost of one backward pass per token.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06831
PDF
-
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
2026-07-07 17:54:28Zanyi Wang, Xin Lin, Haodong Li, Dengyang Jiang, Yijiang Li, Pengtao XieAbstract
Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining learns rich semantic, structural, and geometric priors. Existing generative and editing approaches reuse these priors by casting dense prediction as target generation: annotations such as depth, normals, alpha mattes, masks, and heatmaps are encoded into an RGB-trained VAE latent space and decoded back as image-like targets. We argue this inherits more of the generative output interface than dense prediction requires: unlike RGB synthesis, dense prediction asks for pixel-correct, task-native fields on the same image plane, not new RGB content to be rendered. Our key observation is that a pretrained DiT already organizes RGB inputs through a patch-to-token-to-patch lattice on the image plane, so each token indexes a fixed output patch whose channels can carry task-native quantities instead of RGB appearance. We instantiate this as ReChannel: we keep the VAE encoder for the DiT's input distribution but drop the target-side decoder, adapt the frozen DiT with task LoRA, and map each token to its p x p x K_t pixel-space patch through a shared token-local linear head--about 33K parameters, no spatial mixing. Using FLUX-Klein, we evaluate on six dense prediction tasks and over a dozen benchmarks. This minimal interface sets new state-of-the-art on trimap-free matting, KITTI depth, and referring segmentation, and stays competitive on normals, saliency, and pose. In a matched 4B setting it is more accurate and 2.48x faster than an edit-plus-latent-decode counterpart--dense perception can benefit from generative pretraining without inheriting its output interface.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06553
PDF
-
MSA-DCNN: A Data-Efficient Multi-Scale Deformable CNN for Medical Image Classification
2026-07-07 09:52:46Hamza Hussaini, Shahana Bano, Eyad Elyan, Carlos Francisco Moreno-Garc\'iaAbstract
Existing deep learning methods perform well in medical image classification but struggle with multi-scale morphology and limited annotations due to fixed sampling and data-hungry training. Existing approaches address these challenges in isolation: DCN-based models provide adaptive sampling but lack explicit multi-scale attention fusion and label-efficient regularisation; multi-scale architectures typically rely on static fusion; and semi-supervised methods target label scarcity without jointly modelling adaptive cross-scale representations. We propose MSA-DCNN, a scale-consistent deformable attention learning framework that introduces adaptive multi-scale sampling, within-scale saliency refinement, learned cross-scale fusion, and auxiliary self-distillation within a unified optimisation scheme, with potential to generalise to structurally heterogeneous anatomy. We evaluate on three public benchmarks and an external hold-out set for leukaemia. MSA-DCNN demonstrates competitive and often better performance against ViT baselines, CNN baselines, and a MICCAI semi-supervised baseline under distribution shift and label scarcity in accuracy, F1, and AUC (binary), while using fewer parameters. Ablations confirm complementary component contributions, supporting MSA-DCNN as a practical foundation for data-efficient medical image classification.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06083
PDF
-
Beyond Accuracy: How Humans Evaluate Legally Correct but Socially Controversial Legal Advice from Machines
Abstract
AI systems are increasingly used to provide legal advice, raising questions about whether laypeople accept guidance from algorithms--especially when that advice is legally correct but socially controversial. We report a preregistered survey experiment with 3,348 adults in mainland China examining how people evaluate identical legal advice when it is attributed either to an AI system or to a human lawyer, and when it is accompanied by reasoning or not. Contrary to expectations of algorithm aversion, attribution to an AI system has no net effect on perceived reasonableness. However, mediation analyses reveal opposing psychological pathways underlying this null result. AI-attributed advice is perceived as more objective, which increases perceived reasonableness, but also as less comprehensive and less attentive to special circumstances, which decreases perceived reasonableness. By contrast, providing legal reasoning substantially increases perceived reasonableness regardless of source, largely by enhancing perceptions of objectivity. Qualitative responses corroborate this tension between objectivity and contextual sensitivity in evaluations of legal advice. Together, these findings suggest that public responses to AI legal advisors are shaped not by rigid attitudes toward automation, but by the balancing of competing normative expectations. The results have implications for theories of algorithm aversion and the design of AI recommendation systems in normatively salient domains.
Abstract (translated)
URL
https://arxiv.org/abs/2607.05680
PDF
-
An event-driven framework for fly-inspired visual motion detection
2026-07-06 15:22:44Qinbing Fu, Jingyu Huang, Yan Xie, Jigen Peng, Yuchao TangAbstract
Fast and reliable motion detection is essential for machine vision and autonomous systems operating in dynamic environments. This work integrates emerging event-based sensing with biologically structured neural computation to establish an efficient computational paradigm for visual motion detection. The proposed framework is built upon a recently developed fly-inspired neural network that emulates motion-processing circuits in the optic lobe. Owing to its feed-forward and training-free architecture, the neural model requires only a small number of interpretable parameters and is well suited for real-time embedded implementation. Event cameras provide low-latency, low-power, and high-dynamic-range visual sensing by asynchronously transmitting brightness-change events. However, their performance can be degraded by event noise, including temporal noise and junction-leakage-induced activity, particularly under low-light conditions. Moreover, effective integration between event-based visual representations and biologically inspired neural processing remains under-explored. To address these challenges, we propose an event-driven computational framework that combines time-surface encoding for front-end event representation with a fly optic-lobe-inspired neural network for foreground motion-direction estimation. A bottom-up attention mechanism is further incorporated to suppress background motion and enhance the saliency of foreground targets. The proposed method is evaluated on real-world ground-vehicle datasets and compared with a baseline frame-based model and an optimization-based approach. Experimental results demonstrate that the framework effectively combines the temporal advantages of event-driven vision with the efficiency and interpretability of bio-inspired neural processing.
Abstract (translated)
URL
https://arxiv.org/abs/2607.05205
PDF
-
Privilege and confidentiality in generative AI workflows
Abstract
Generative AI (GenAI) systems store and process client data in three distinct ways: in the model's parameters through training and memorisation, in the context window during a live session, and in knowledge databases for retrieval-augmented generation (RAG). Each mode creates different and often counter-intuitive risks to confidentiality and legal professional privilege, and each calls for specific governance responses. Drawing on the first English and American decisions to address privilege and generative AI, UK and Munir v Secretary of State for the Home Department and United States v Heppner, on the orthodox privilege authorities against which those decisions must be read, and on recent computer science research, we explain the three modes of data storage and processing in terms accessible to practitioners and analyse the legal consequences of each. We then situate the analysis within the regulatory framework governing solicitors in England and Wales and within the ordinary principles of professional negligence, arguing that the standard of effective information governance (and with it the benchmark against which negligence and misconduct will be measured) is changing. Although we write primarily for SRA-regulated practitioners, our data-governance analysis is framed to extend to any jurisdiction in which the protection of privilege or professional secrecy depends on demonstrable confidentiality. The ultimate aim of this article is to help legal services professionals understand salient data leakage risks in GenAI systems and thereby facilitate a more responsible deployment of GenAI on client data and other sensitive material.
Abstract (translated)
URL
https://arxiv.org/abs/2607.05479
PDF
-
Ranking the Impact of Contextual Specialization in Neural Speech Enhancement
2026-07-06 08:59:07Peter Leer, Svend Feldt, Zheng-Hua Tan, Jan {\O}stergaard, Jesper JensenAbstract
We systematically investigate neural speech enhancement systems, ranging from very small ($\sim$10\,k parameters) to medium-large ($\sim$2-5\,M parameters), which specialize to acoustic conditions using contextual information such as speaker identity, noise type, speaker gender, spoken language, and SNR. By fine-tuning generalist models on specific data subsets, we find that specializing to a speaker's identity consistently yields the largest gains in estimated speech intelligibility and quality. In contrast, specializing to SNR, noise type, or gender offers only marginal benefits. Crucially, we show that a small model specialized to both a specific speaker and a specific noise type can match or exceed the performance of a generalist model ten times its size. Further, cross-lingual tests reveal that models specialized to a target language outperform multilingual generalists, suggesting that language is a salient feature for specialization. These findings highlight the potential of small, adaptive models for resource-constrained applications like hearing aids, which specialize on-the-fly to contextual information.
Abstract (translated)
URL
https://arxiv.org/abs/2607.04826
PDF
-
Agentic SABRE: An Uncertainty-Aware Neuro-Symbolic Multi-Agent Framework for Adaptive Ransomware Detection
2026-07-05 13:08:41Henry Kabuye, Biju Issac, Jeyamohan NeeraAbstract
Ransomware has evolved into a complex, adaptive, and fast-moving adversary category in which static signatures and monolithic classifiers fail to generalise under concept drift, evasion, and behavioural polymorphism. In this paper, we present Agentic SABRE (Semantic-Behavioural Arbitration for Ransomware Evaluation), an uncertainty-aware, neuro-symbolic, multi-agent framework for adaptive ransomware detection. SABRE fuses semantic, representation-based evidence with behavioural, time-window forensic telemetry and employs Monte Carlo Dropout inference to quantify epistemic uncertainty for each agent. We introduce a decision-layer orchestrator that performs risk- and uncertainty-aware triage using two interpretable thresholds: a risk score and an uncertainty budget. High-confidence, high-risk samples are automatically contained, while uncertain or borderline cases are escalated to human analysts, establishing a flexible computational contract between autonomous response and analyst oversight. To support auditability and trust, SABRE integrates post-hoc explainability mechanisms, including gradient saliency, permutation importance, and counterfactual analysis, enabling both local and global interpretation of agent decisions. Extensive evaluation on RDset and RanSMAP demonstrates that Agentic SABRE preserves perfect discrimination on saturated semantic datasets, with AUC equal to 1.0, while improving robustness under weak behavioural signals. It achieves up to a 4.9 percent relative reduction in false escalations at equal recall while maintaining calibrated predictive uncertainty. Counterfactual analysis further shows that semantic and behavioural decisions can be reversed with bounded perturbation cost, indicating stable and interpretable decision boundaries.
Abstract (translated)
URL
https://arxiv.org/abs/2607.04292
PDF
-
DICT: Data Injection and Contrastive Trajectory Refinement for Conditional Image Generation with Diffusion Models
2026-07-04 14:44:06Chunnan Shang, Xin Zhang, Zhizhong Wang, Hongwei WangAbstract
Diffusion models have become a dominant paradigm for conditional image generation, yet existing approaches generally follow two directions: task-specific designs that can improve performance but limit generalization, and training-free loss guidance that compresses rich conditions into scalar objectives and applies stepwise guidance, leading to information bottlenecks and error accumulation along the sampling trajectory. Given the urgent need for an effective unified framework across diverse conditional image generation tasks, we propose Data Injection and Contrastive Trajectory Refinement (DICT), a training-free inference method that enhances conditional image generation without introducing task-dependent architectures. DICT introduces Data Injection, where noise-perturbed conditional signals are integrated into early denoising stages; by performing guided denoising on these injected signals, DICT adaptively selects and distills task-salient information from the raw condition, effectively preserving spatial richness and ensuring precise condition-to-generation alignment. Furthermore, DICT applies Contrastive Trajectory Refinement across adjacent denoising states, enabling pairwise comparisons that progressively improve sample quality. These designs keep inference simple while improving cross-task transfer under a unified diffusion formulation. Extensive experiments on conditional image generation tasks (e.g., style transfer, image super-resolution, and image deblurring) show consistent gains in fidelity and perceptual quality over representative task-specific and loss-guided baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2607.03899
PDF
-
IPDiff: Diffusion-driven ORSI Salient Object Detection with Information Reconstruction and Multi-Prior Guidance
2026-07-04 04:03:33Gongyang Li, Zhen Bai, Runmin Cong, Dan Zeng, Weisi Lin, Xiao-Ping ZhangAbstract
Existing Salient Object Detection in Optical Remote Sensing Image (ORSI-SOD) methods mainly adopt the static inference strategy, which uses fixed trained model parameters for saliency inference in the testing phase. This means that even if the generated saliency map has errors, it cannot be further optimized. In this paper, we propose the novel IPDiff, a Diffusion-driven ORSI-SOD method with Information Reconstruction and Multi-Prior Guidance. We build IPDiff based on a unique dynamic optimization strategy, which endows IPDiff with the ability to iteratively optimize saliency maps with a dynamic parameter. Specifically, we formulate ORSI-SOD as a conditional diffusion problem in IPDiff. IPDiff first extracts informative conditional priors from ORSIs, including the saliency prior and the hierarchical priors, in the prior network with the assistance of the information reconstruction-driven attention module. The saliency prior can provide positional information of salient objects, while the hierarchical priors can provide specific detail and semantic information of salient objects. Under the guidance of these priors, IPDiff then iteratively denoises random noise as the timestep dynamically changes in the denoising network, generating saliency maps that are close to ground truths. Notably, we simultaneously supervise IPDiff in both spatial and spectral domains through a hybrid loss function to achieve efficient network training. Comprehensive experiments on public ORSSD, EORSSD, and ORSI-4199 datasets demonstrate that our proposed IPDiff achieves the best performance compared to 46 state-of-the-art methods. The code and results of our method are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.03696
PDF
-
OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models
2026-07-03 07:41:00Shijie Cao, Qingyu Zhang, Boxi Yu, Yuzhong Zhang, Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le SunAbstract
Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate large token sequences under audio-visual inputs, leading to substantial inference cost. Existing audio-visual token compression methods often rely on unimodal guidance, overlooking the temporal locality of query-relevant evidence in audio-visual inputs and implicitly assuming that the two modalities share a temporally aligned information density distribution. We propose \textbf{OmniFocus}, a training-free query-guided token compression method for OmniLLMs that performs independent importance estimation for video and audio, enabling a modality-symmetric compression design that preserves modality-specific salient evidence while maintaining audio-visual alignment, thereby mitigating the modality bias issue that can arise from unimodal-guided compression. Experiments on the Qwen2.5-Omni model family across four audio-visual benchmarks show that OmniFocus maintains strong compressed performance at low token retention ratios and outperforms existing baselines on several major benchmark scores at 25\% token retention. On DailyOmni with Qwen2.5-Omni-7B at 25\% token retention, OmniFocus maintains 59.40 accuracy while delivering up to 1.38$\times$ prefill speedup relative to the full-token baseline, highlighting a favorable practical accuracy-efficiency trade-off.
Abstract (translated)
URL
https://arxiv.org/abs/2607.03050
PDF
-
When Does Resolution Help a Frozen Backbone? Global Attention at Resolution Predicts Scalable Adaptation for Camouflaged and Marine Animal Segmentation
2026-07-02 18:51:54Tyler Rust, Chandra KambhamettuAbstract
Adapting frozen vision foundation models to fine-grained segmentation now largely depends on backbone selection. Whether the backbone applies global attention to a high-resolution token set predicts whether a low-rank adapter turns resolution into accuracy. Isotropic ViTs attend globally over the full grid and keep improving with resolution; hierarchical backbones confine early attention to local windows and pool the grid before their global stages, plateauing at lower resolutions. A controlled six-backbone study establishes the pattern, and editing the backbone points to the cause: pooling keeps the benefit, removing global attention does not. The effect is specific to low-rank adaptation. Under one fixed pipeline, SALT (Side-stem, Attention-gated U-Net, Low-rank Tuning), one RGB-only pass on a strong isotropic backbone wins the best S-measure on the four data-matched camouflaged sets, and leads every marine and salient set. It reaches a new state of the art on both marine-animal benchmarks (MAS3K mIoU 0.878).
Abstract (translated)
URL
https://arxiv.org/abs/2607.02708
PDF
-
Rethinking Conditional Generation for Underwater Salient Object Detection
2026-07-02 07:48:06Hua Li, Yongjie Weng, Yutong Li, Zhiyuan Li, Runmin Cong, Sam KwongAbstract
Salient Object Detection in underwater images remains challenging due to low contrast, uneven illumination, and color distortion caused by scattering and absorption effects, which limit the effectiveness of conventional SOD methods in underwater environments. To address these challenges, we propose a Degradation-aware Conditional Generation Network (DCGNet), specifically designed to construct reliable conditional features for underwater saliency generation. First, we design a Dynamic Multi-Granularity module (DMG) grounded in the human visual system to robustly detect salient objects of varying scales with blurred boundaries. Then, we develop an Underwater Physics-Prior module (UPP), which utilizes pseudo-depth guidance to estimate underwater light attenuation and backscatter, thereby restoring degradation-aware RGB features and mitigating color distortion and boundary ambiguity. Based on the physics-guided representation, we introduce an Underwater Spatial Gaussian module (USG), which constructs a spatial Gaussian saliency prior from the strongest guided response to enhance object-centered salient regions and suppress cluttered underwater backgrounds. In addition, a lightweight timestep-adaptive Diffusion Transformer (DiT) bottleneck is inserted into the denoising decoder to refine fused features at different diffusion timesteps. Comprehensive experiments on USOD10K, USOD, CSOD10K, MAS3K, and RMAS demonstrate that DCGNet significantly outperforms existing state-of-the-art methods, verifying its potential for complex underwater visual applications.
Abstract (translated)
URL
https://arxiv.org/abs/2607.01825
PDF
-
LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression
2026-07-02 04:59:56Bowen Yuan, Zijian Wang, Yadan Luo, Shijie Wang, Zi HuangAbstract
Large vision-language models (LVLMs) exhibit strong reasoning ability but suffer from visual forgetting during long-horizon decoding, where attention progressively drifts away from visual evidence. Existing methods largely treat this issue as a late-stage attention decay problem or attempt to mitigate it through heuristic reminders or post-hoc attention lifting. Through systematic empirical analysis, we find that performance degradation under visual forgetting is largely driven by two overlooked factors: early-stage attention decay disrupts evidence acquisition, and attention concentration on a subset of task-irrelevant visual sink tokens. Motivated by these insights, we propose LASER, a post-training framework that regulates both the visual attention trajectory and intra-visual token attention distribution during reasoning. Technically, LASER introduces two complementary rewards: a Visual Grounding Reward, which encourages the model to maintain attention on semantically salient visual tokens throughout decoding, and a Sink Suppression Reward, which penalizes excessive attention concentration on visual sink tokens. Together, these rewards preserve early-stage grounding while preventing attention collapse onto uninformative regions. Extensive experiments on eight benchmark datasets demonstrate that LASER consistently outperforms strong baselines, validating attention-aware training as an effective remedy for visual forgetting.
Abstract (translated)
URL
https://arxiv.org/abs/2607.01707
PDF
-
Post-Training Pruning for Diffusion Transformers
2026-07-01 13:30:49Chengzhi Hu, Xuewen Liu, Jing Zhang, Mengjuan Chen, Zhikai Li, Qingyi GuAbstract
Diffusion Transformers (DiTs) have demonstrated impressive performance in image generation but suffer from substantial computational overhead and resource consumption. Post-training pruning offers a promising solution; however, due to DiTs' unique architectural design and parameter distribution, traditional pruning methods are inapplicable, leading to significant performance degradation. Specifically, prior methods developed for LLMs, which derive metrics through a series of approximations, amplify the relative contribution of weights in the saliency metric. In addition, weights in DiTs exhibit significantly larger magnitudes than those in LLMs. Moreover, existing pruning granularity overlooks variations in model structures. In this paper, we propose DiT-Pruning, which improves pruning performance by introducing customized saliency criteria and pruning granularity. We design a novel metric that balances the contributions of weights and activations from an energy-based perspective, enabling more effective identification of important elements. Furthermore, we observe distinct clustering patterns in the two-dimensional weight space. Accordingly, we adopt a clustering-aware pruning granularity, enabling effective sparse allocation. Extensive evaluations on various DiTs show that our method consistently preserves image quality, especially under high sparsity. For FLUX.1-dev at 512x512 resolution on MJHQ, DiT-Pruning achieves only a 0.001 loss in CLIP score at 50% sparsity, dramatically outperforming recent pruning methods.
Abstract (translated)
URL
https://arxiv.org/abs/2607.00927
PDF
-
Beyond Pixel Overlap: A Framework for Decomposing Segmentation Evaluation Metrics
2026-07-01 12:53:25Youwei Pang, Xiaoqi ZhaoAbstract
Evaluation metrics are central to binary target segmentation because they determine how progress is measured, compared, and interpreted. In this paper, target denotes the task-defined positive region to be segmented rather than a generic foreground object. It may be salient, camouflaged, transparent, glass-like, mirror-like, shadow-like, lesion-like, or defined by other application-specific semantics. We treat existing metrics as compositions of modular design choices rather than isolated formulas. The proposed framework decomposes each metric into five stages covering prediction representation, target extraction, target matching, score computation, and metric reporting. We use this framework to analyze representative metrics and show how newer metrics address specific limits in earlier protocols. The stage choices keep each metric's assumptions visible. We then discuss the design space opened by the framework and its implications for task-aware evaluation protocols. Reference code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.00886
PDF
