Salient
-
VGER: Voxel-Guided Global Event Ranking for Event Cloud Attribution
2026-08-02 20:07:28Youxin Jiang, Baoheng Fu, Hongwei Ren, Xiangqian WuAbstract
Event cameras produce sparse and asynchronous event streams that provide rich spatio-temporal information for efficient perception. Recent advances in event-based models have demonstrated strong performance by directly modeling asynchronous events without dense frame reconstruction. However, identifying the event-level evidence behind their predictions is crucial for improving model transparency and reliability. Directly adapting point-level saliency methods from point clouds provides fine-grained attribution but overlooks event-specific spatio-temporal structures. To address this limitation, we propose Voxel-Guided Global Event Ranking (VGER), a training-free attribution framework for point-based event cloud networks. VGER combines event-level gradient evidence with task-aware voxel perturbation evidence, transferring regional contribution into event-level attribution scores while preserving fine-grained resolution. Furthermore, VGER introduces a unified event ranking strategy, where high-ranked events are expected to be prediction-critical and low-ranked events are expected to have limited influence on predictions. We evaluate VGER on three event-based benchmarks with PointNet, PointNet++, and EventMamba. Across nine dataset-backbone settings, VGER consistently improves both high-tail and low-tail deletion performance over point-level saliency baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2608.01470
PDF
-
Unleashing the Power of Text: Text-Guided Flow Matching for Image Fusion under Complex Degradations
2026-08-01 08:43:26Axi Niu (School of Computer Science, Northwestern Polytechnical University, Xi'an, China), Jieheng Li (School of Computer Science, Northwestern Polytechnical University, Xi'an, China), Kang Zhang (School of Electrical Engineering, KAIST, Daejeon, Republic of Korea), Qingsen Yan (School of Computer Science, Northwestern Polytechnical University, Xi'an, China), Jinqiu Sun (School of Aeronautics and Astronautics, Northwestern Polytechnical University, Xi'an, China), Yanning Zhang (School of Computer Science, Northwestern Polytechnical University, Xi'an, China)Abstract
Infrared-visible image fusion under realistic degradation scenarios is a challenging task, as degradations not only cause a loss of reliable modality-specific information in observed images but also hinder the fusion process. Recent studies indicate that text can provide prior information about degradation characteristics, complementing the limited evidence available from corrupted input images and facilitating fusion. However, existing methods typically inject fixed global text representations into visual features, making it difficult for textual guidance to adapt to spatially varying degradations, local structures, and thermal saliency. To this end, we propose TGFusion, a text-guided latent-space flow matching framework that unifies degradation suppression and cross-modal fusion. TGFusion encodes task, degradation, and generation cues into structured prompts. To fully exploit these priors, we design a Prompt-conditioned Multi-stream Joint Flow Transformer that represents text as an independent semantic stream alongside fusion, visible, and infrared streams. Joint attention enables token-level bidirectional interaction and layer-wise updating among semantic and visual representations, allowing degradation semantics to dynamically guide reliable information selection and fusion latent generation. Extensive experiments on public benchmarks and complex degradation scenarios demonstrate that TGFusion achieves superior or competitive performance in perceptual quality, image naturalness, structural-detail preservation, and infrared-saliency retention, while remaining robust across diverse single and compound degradations.
Abstract (translated)
URL
https://arxiv.org/abs/2608.00530
PDF
-
TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding
2026-07-31 18:26:17Sparsh Rastogi, Tanmay Kumar, Baiyu Chen, Jatin Bedi, Zechen Li, Flora D. SalimAbstract
Wearable sensors capture fine-grained motion patterns that support rich behavioral understanding, yet most existing methods reduce these signals to activity labels. Recent LM-based approaches generate natural-language explanations for sensor data, but their reasoning is weakly grounded in the underlying signal, leading to fluent yet unverifiable explanations. We introduce TRACE-TS (Traceable Reasoning with Attribution-Grounded Evidence), a framework for structured and signal-grounded reasoning over wearable time series. TRACE-TS uses attribution from an expert classifier to identify salient spatio-temporal sensor regions, uses them to construct DAG reasoning traces with explicit evidence provenance, and trains a compact language model to generate these traces through gated cross-attention over sensor memory tokens. At inference, the adapted model jointly outputs the activity prediction and its reasoning trace, without requiring attribution computation or teacher guidance. We introduce Semantic Node Match(SNM), an LLM-as-judge metric that diagnoses reasoning fidelity at the observation, inference, and synthesis levels, localizing hallucinated observations and broken evidence chains missed by standard NLG metrics. Across seven wearable benchmarks, TRACE-TS achieves the best average accuracy and F1 among all evaluated methods (84.43%/81.24%), and outperforms the best LLM-based baseline by 17.96% in F1. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.00200
PDF
-
Functional Emotion Without Character: Large Language Models, Aristotelian Disposition, and the Limits of Behavioral Alignment
Abstract
Debates about whether artificial systems can feel are often forced between two unsatisfactory positions: behavioral equivalence is treated as sufficient for emotion, or phenomenal consciousness is treated as a prerequisite that makes the question empirically inaccessible. This article develops a structural alternative. It models emotions as context-sensitive regions, trajectories and attractor dynamics in high-dimensional representational state spaces. Recent mechanistic interpretability findings support the existence of causally active emotion-concept representations in large language models, but they do not establish subjective feeling or full emotional agency. Assessed against published adequacy standards for representation in language models, intervention provides strong evidence of causal use, while full affective role integration, uniformity across subject domains and coherence remain only partially established; there is no direct analogue of accuracy. These mismatches expose the need for a standard of affective appropriateness, which an account of character must supply. Such an account requires three further conditions: regulatory embodiment that gives valence endogenous stakes, temporal continuity that allows affective episodes to accumulate into a history, and an integrated self-model that binds that history to persistent values. Aristotle's concepts of pathÄ, hexis, mesotÄs and phronÄsis are translated into a state-space sketch in which practical wisdom includes competence in estimating normatively salient context, not merely acting on a context description already given. The framework reframes alignment as a problem of durable disposition rather than output conformity, and yields interventional tests with explicit control conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2609.22362
PDF
-
Is It Time for the Renaissance of Salient Object Detection in the Era of MLLMs?
2026-07-31 09:54:23Wenzhuo Zhao, Xiuzhi Li, Zhongkuan Mao, Ronghao Xian, Yao Jiang, Zhao Gao, Keren Fu, Qijun Zhao, Jian ChengAbstract
The zero-shot capabilities of multimodal large language models (MLLMs) are pushing salient object detection (SOD) beyond task-specific supervision. To disentangle MLLMs beyond conventional mask-based evaluation, we decompose SOD into localization and segmentation, and re-engineer datasets with phrases, boxes, and attributes, establishing a diagnostic benchmark for MLLM saliency perception (SaliLLM). SaliLLM uncovers a striking capability mismatch: MLLMs outperform state-of-the-art (SOTA) methods in localization, yet remain substantially weaker in segmentation. Further analyses attribute this gap primarily to mismatches between MLLMs and annotations over foreground cardinality, granularity, and extent. Motivated by this diagnosis, we recast zero-shot SOD as protocol-aligned Foreground Organization and introduce the first training-free framework that leverages Gestalt-inspired Collaborative attention for Unified SOD (FOCUS). FOCUS couples top-down Bayesian-surprise calibration of protocol-conditioned foreground granularity with bottom-up propagation of MLLMs evidence over entity-centric perceptual manifolds induced by self-supervised features, yielding coherent object extents as prompts for a general segmenter. Across 13 RGB, RGB-D, and RGB-T SOD benchmarks, FOCUS generally surpasses SOTA methods without training, reducing mean absolute error by 11\%, 34\%, and 48\% compared with fully, weakly, and self-supervised methods, respectively. Our findings signal the renaissance of SOD: from task-specific supervision to zero-shot foreground organization. Code is available in the supplementary material.
Abstract (translated)
URL
https://arxiv.org/abs/2607.29222
PDF
-
Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning
2026-07-31 03:51:09Jiahe Fan, Si Chen, Yinghao Hou, Aiyuan Zhang, Hong XieAbstract
Heterogeneous model fusion seeks to combine models that differ in tasks, initializations, architectures, or scales. We study an underexplored cross-scale setting: improving a small recipient language model with a stronger donor despite substantial architectural mismatch. We ask whether useful capabilities can be transferred without explicit neuron-wise semantic alignment. Building on the observation that truncating a large model to a smaller architecture and injecting it with a tiny mixing weight can already improve the recipient, we propose Activation-Prune-Merge (APM), an activation-guided framework for cross-scale fusion. APM constructs task-conditioned activation maps on the donor, selects salient layers, hidden dimensions, attention heads, and MLP neurons to prune it to the recipient architecture, and injects the resulting donor slice into the original recipient using a micro interpolation coefficient. This formulation treats the donor as a source of concentrated functional components rather than requiring precise structural transplantation. Across 16 benchmarks spanning reasoning, mathematics, code generation, instruction following, and classification, APM improves the overall average accuracy from 55.5% to 60.6% over the original 3B recipient. RTE accuracy increases from 64.3% to 82.3%, QNLI from 52.3% to 65.7%, and BoolQ from 70.8% to 79.2%. Analyses of injection ratios and sequential multi-stage fusion further suggest that activation-guided extraction improves the quality of the transferable donor slice while preserving the small-ratio fusion regime. These results provide evidence that cross-scale heterogeneous fusion can succeed without explicit semantic alignment when the donor contribution is sufficiently concentrated and carefully selected.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13596
PDF
-
Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning
2026-07-30 16:30:08Zheng Wu, Chenhao Xue, Shijie Zheng, Yijie Lu, Cheng Yang, Zhuosheng ZhangAbstract
As large language models (LLMs) continue to advance in complex reasoning tasks, they have learned to heavily prioritize explicit conditions provided in the input. However, in everyday commonsense reasoning, this mechanism exposes a critical vulnerability which we term Salience Bias: models become easily hijacked by useless explicit distractors (e.g., numerical values), leading them to ignore the implicit physical or commonsense prerequisites of a task. A critical open question is whether this failure reflects a genuine gap in commonsense knowledge or merely its suppression under misleading task framing. To investigate this, we construct the SaliTrap Benchmark, a high-quality dataset across four trap dimensions. Evaluating 12 state-of-the-art LLMs, we find that all mainstream models suffer significantly from salience bias, with severity scaling with distractor density and detecting the trap often decoupled from actually avoiding it. Crucially, by re-eliciting the same models with the task framing stripped away, we show that this is overwhelmingly a failure of \textbf{knowledge suppression rather than knowledge absence}: a context-free knowledge probe alone recovers over 90\% of sycophantic-compliance failures, revealing that the requisite commonsense is intrinsically present but actively crowded out by salient distractors that lure the model into over-compliant, unnecessary computation. Building on this diagnosis, we further show that lightweight, inference-time prompting alone substantially closes the gap without any retraining. Our findings relocate the bottleneck of commonsense reasoning failures from model competence to elicitation, and we release SaliTrap as a testbed for this blind spot. The codes are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.28478
PDF
-
BladeYOLO: Wind Turbine Blade Defect Detection with Limited Annotations and Weak-Saliency Awareness
2026-07-30 11:42:33Yabin Xu, Fangtao Zhang, Fan Wang, Zhan Wang, Honghua Chen, Mingqiang Wei, Haoran Xie, Sam KwongAbstract
Wind turbine blade defect detection remains highly challenging in real-world inspection scenarios due to limited on-site data and the subtle visual characteristics of defects. In practice, blade defects are often small-scale, low-contrast, and difficult to distinguish from complex backgrounds, which significantly limits the robustness of existing detectors. To address these challenges, we propose BladeYOLO, a defect detection framework for wind turbine blades. Specifically, we integrate a Vision Transformer (ViT) backbone initialized with DINOv3 self-supervised pre-trained weights into YOLOv12-L, enabling the transfer of large-scale generic visual priors to blade defect detection and improving feature representation under limited training annotations. To enhance the perception of subtle defects, we further develop a Mamba-guided Weak-Defect Enhancement module, which consists of a Detail-Enhanced Multi-scale Branch for preserving high-frequency structural cues and a Cross-Mamba module for progressively propagating high-level semantic guidance to shallow features. In addition, we introduce a lightweight Style-Injector module that captures environment-related style information via Fourier decomposition and injects it into selected ViT self-attention layers, thereby improving robustness against environment-induced appearance variations. Extensive experiments demonstrate that BladeYOLO achieves superior performance on the WTBlade-Defect dataset, with additional annotation-budget experiments showing its favorable performance under reduced training annotations. Evaluation on the public Wind Surface Defect dataset further provides supportive evidence for the cross-dataset robustness of BladeYOLO. In particular, on this public dataset, BladeYOLO outperforms the best competing method by 3.5\% in mAP$_{50}$ and 2.5\% in mAP$_{50-95}$.
Abstract (translated)
URL
https://arxiv.org/abs/2607.28065
PDF
-
Semantic-Aligned Structural Abstraction for Multimodal Sentiment Analysis
2026-07-30 07:23:27Wei Chen, Junkai Li, Tongguan Wang, Hui Liu, Feiyue Xue, Chuanxiang Ma, Ying ShaAbstract
Multimodal Sentiment Analysis (MSA) aims to interpret complex human emotions by integrating natural language with non-verbal modalities. Non-verbal modalities share a structural isomorphism with natural language, as both can be viewed as feature sequences evolving over time. This isomorphism enables the transformation of non-verbal modalities into text-like tokens for unified semantic reasoning. Large Language Models (LLMs), designed to understand and generate sequential data, can thus be utilized to interpret complex affective sequences. However, existing LLM-based methods primarily capture low-level superficial features, failing to model affective semantics arising from structural variations and contextual interactions. To address this limitation, we propose \textbf{SentiLLM}, a unified framework that leverages \textit{Semantic-Aligned Structural Abstraction} to distill continuous raw signals into compact, semantically meaningful tokens. Specifically, we introduce a \textit{Dual-Stream Salience-Context Calibration Mechanism}, which disentangles non-verbal feature sequences into a focus stream and an ambient stream. The focus stream captures salient sentiment shifts (e.g., facial expressions) guided by textual priors, while the ambient stream characterizes stable background states. Through calibrating these dynamic sentiment shifts against background states, SentiLLM effectively projects non-verbal modalities into a unified semantic space, making them naturally understandable for LLMs. Serving as a plug-and-play module, SentiLLM significantly improves discriminative performance with only a small number of trainable parameters. Our method achieves superior performance on four datasets, MOSI, MOSEI, CH-SIMS, and CH-SIMS v2, demonstrating the effectiveness of the structural abstraction paradigm in MSA. Our code is available at: \href{this https URL}.
Abstract (translated)
URL
https://arxiv.org/abs/2607.27790
PDF
-
MedARC: Training-Free Adaptive Redundancy Compression of Visual Tokens for 3D Medical Vision-Language Models
2026-07-29 07:27:09Yitao Zhu, Mengjun Liu, Yingji Fu, Haowen Pang, Anqi QiuAbstract
Integrating 3D medical images with vision-language models (VLMs) holds substantial promise for computer-aided diagnosis. However, volumetric images generate prohibitively long visual-token sequences with considerable spatial and inter-slice redundancy. Existing token compression methods typically apply uniform reduction or rely on a single importance signal, increasing the risk of removing regions that are clinically relevant to the query or structurally distinctive. To address this limitation, we propose MedARC, a unified, training-free framework for Adaptive Redundancy Compression of visual tokens in 3D medical VLMs. MedARC estimates token importance by integrating three complementary cues: self-attention from the VLM vision encoder, which reflects the model's intrinsic visual focus; similarity between projected visual tokens and text embeddings, which identifies query-relevant regions; and deviations of local visual foundation model features from the volume-level feature center, which highlight structurally distinctive anatomy. The resulting importance distribution guides a saliency-aware merging strategy that preserves informative tokens while consolidating redundant ones rather than simply discarding them. Experiments on CT-RATE and MR-RATE show that MedARC reduces visual-token overhead and inference time while preserving or improving diagnostic performance. Its multi-cue scoring cost is outweighed by the savings from processing fewer tokens, with greater benefits expected for larger language models.
Abstract (translated)
URL
https://arxiv.org/abs/2607.26554
PDF
-
BG-REAL: A Public Real-Data Anchored Benchmark for Background Manipulation Detection and Localization
2026-07-28 20:11:26Bugra Alperen Uluirmak, Rifat KurbanAbstract
Background manipulation is a practical but under-specified image-forensics setting: the manipulated evidence can sit outside the salient foreground object, while many evaluations emphasize object-centric copy-move, splicing, or generic synthetic edits. We introduce BG-REAL, a public real-data anchored benchmark package for background manipulation detection and localization. The current release is built from Open Images V7 instance-segmentation sources and contains 7,000 processed samples over 1,200 source groups, including 6,000 public-data anchored samples and 1,000 synthetic control samples. BG-REAL covers six edit families, matched authentic controls, source-group splits, mask and leakage QA, 599 human-assisted quality-control rows, three completed external baselines (TruFor, MVSS-Net, and HiFi-Net), and five-seed model evaluation. Beyond aggregate accuracy, we use matched-authentic-control diagnostics to measure how often baselines misclassify re-encoded authentic images as manipulated at a threshold fixed on held-out validation data; false-positive rates range from 0.57 (TruFor, the lowest) to 1.00 (several weak or mask-informed baselines), indicating that re-encoding artifacts are a shared shortcut risk across baselines rather than a problem specific to any one model. The release provides the construction pipeline, evaluation protocol, paper-ready figures, and reproduction documentation. We frame BG-REAL as a background-manipulation-focused complement to general image-manipulation-localization benchmarks, not as a fully real-only or general-purpose benchmark.
Abstract (translated)
URL
https://arxiv.org/abs/2607.26232
PDF
-
Lens: Bringing the Right Semantic Perspective into Focus for Training-Free Multimodal Representation Learning
2026-07-28 11:39:44Xinran Liu, Shouqian Shi, Yixian Chen, Ruizhi Chen, Xin-Wei Yao, Sheng ZhongAbstract
High-quality representations are essential for a wide range of downstream tasks. Dedicated embedding models are explicitly optimized for representation learning, yet their training data are often more limited in scale and diversity than the massive corpora used to pretrain modern large language models and multimodal large language models. Large-scale pretraining and instruction following enable autoregressive models to select relevant evidence, integrate multimodal information, and infer semantics under different task perspectives, creating a distinctive opportunity for training-free representation learning. However, our analysis reveals that existing semantic-elicitation methods do not reliably orient the extracted states toward the semantic perspective required by the downstream task. Consequently, the resulting representations often remain dominated by salient input content. We characterize this problem as semantic perspective misalignment and propose Lens, a training-free framework that makes representation readout task-directed. Semantic Perspective Anchoring associates the task-required perspective with a task-specific readout phrase, specifying the interpretive role of the positions later used for extraction. Contextualized Phrase Readout places the same phrase after the complete input and aggregates its token states, combining full-context access with the anchored perspective. The resulting representation reflects task-conditioned evidence integration and inference rather than a generic summary of salient content. Without parameter updates, architectural modification, or reranking, Lens achieves an overall Precision@1 of 63.9 across all 36 MMEB datasets, outperforming the closest same-backbone training-free embedding baseline by 10.2 points.
Abstract (translated)
URL
https://arxiv.org/abs/2609.20252
PDF
-
DensFiLM: Density-Conditioned Video Saliency for Crowd Scenes
2026-07-28 08:57:18Anis Ur RahmanAbstract
Video saliency models typically apply a single fixation strategy across crowd scenes, despite systematic changes in attention with crowd density. Sparse scenes encourage tracking individuals, whereas dense scenes shift attention toward collective motion and scene-level landmarks. We introduce DensFiLM, a density-conditioned video saliency model that inserts a lightweight Feature-wise Linear Modulation layer at the bottleneck of a Video Swin Transformer. A learned density embedding produces channel-wise scale and shift parameters, allowing the decoder to reconstruct saliency from features selected for each density regime. The module adds only ~100K parameters and can use either CrowdFix density labels or the model's own density prediction. On CrowdFix, DensFiLM achieves mean NSS 1.434 and CC 0.517 over four seeds, improving over ACLNet by 14.7% and 14.9%, respectively, while predicted-density conditioning matches oracle-label performance. Ablations show that explicit RAFT optical flow and larger temporal and social-force extensions provide no further improvement in this setting. In a centre-prior-subtraction diagnostic, density conditioning yields an NSS gain of 0.462 over the unconditioned backbone, compared with 0.124 under standard evaluation. These results show that lightweight bottleneck conditioning provides a more effective inductive bias than increasing model capacity for crowd-video saliency. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.25465
PDF
-
Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering
2026-07-28 08:20:40Noor Islam S. Mohammad, Ulu\u{g} Bayaz{\i}tAbstract
Knowledge-intensive multimodal question answering (KI-MMQA) sits at the intersection of three expensive primitives: long visual token sequences, dense retrieval over large external corpora, and full cross-modal fusion. Existing systems pay all three costs uniformly per query, even though only a small fraction of visual content and retrieved knowledge is actually relevant to any given question. We introduce SKIP (Salient Knowledge-Injected Pathways), a unified inference architecture that routes computation along sparse pathways jointly conditioned on the question, the image, and a difficulty estimate. SKIP combines question-guided visual token pruning, region-conditional sparse retrieval, bipartite sparse cross-attention, and speculative knowledge verification with an adaptive budget controller that allocates compute proportional to predicted question difficulty. We derive an information-bottleneck bound showing that the optimal visual sparsity rate scales as $O(1/\sqrt{N})$ under realistic question-image mutual-information assumptions, with retained accuracy guarantees. Across five KI-MMQA benchmarks (OK-VQA, A-OKVQA, InfoSeek, Encyclopedic-VQA, and ViQuAE), SKIP matches or exceeds the accuracy of strong dense baselines while using $3.4$--$6.8\times$ fewer FLOPs and $2.7\times$ less end-to-end latency. Code available at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2607.25422
PDF
-
RDVSv2: A Large-scale Benchmark for RGB-D Video Salient Object Detection
2026-07-28 07:54:03Tianyu Li, Jiahao He, Keren Fu, Qijun ZhaoAbstract
We introduce RDVSv2, a large-scale benchmark for RGB-D video salient object detection (RGB-D VSOD) with dense frame-level annotations. Existing datasets in this emerging field are often limited in scale and annotation quality, while also relying on less geometry-consistent depth cues. To address these limitations, RDVSv2 is built from publicly accessible stereoscopic online videos and contains 249 video sequences with 29,077 annotated frames. It includes depth maps derived from stereoscopic videos, together with frame-wise salient object masks annotated with eye-tracking guidance. Compared with existing datasets, RDVSv2 is much larger in scale and covers more diverse and challenging scenarios. In addition, we establish a strong baseline for RGB-D VSOD based on Segment Anything Model 2 (SAM2). Specifically, we employ a parameter-efficient fine-tuning (PEFT) strategy to adapt the SAM2 encoder to jointly encode RGB, depth, and optical flow cues. Extensive experiments show that RDVSv2 is substantially more challenging for existing RGB-D VSOD methods. Meanwhile, the proposed baseline achieves state-of-the-art results on RDVSv2 and existing RGB-D VSOD benchmarks. We hope that RDVSv2 and the provided baseline will serve as useful resources for future research on RGB-D VSOD and related multi-modal video understanding tasks. Our dataset and code will be available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.25392
PDF
-
Beyond Background Bias: Saliency-Driven Prototype Alignment for Dataset Distillation
2026-07-28 06:05:12Yawen Zou, Wenqi Cai, Guang Li, Ling Xiao, Chunzhi Gu, Chao ZhangAbstract
Dataset distillation aims to synthesize compact datasets that can approximate the performance of full-data training while significantly reducing computational and storage costs. However, diffusion-based distillation methods often struggle to preserve structural coherence and generalization, especially in visually complex domains. This issue often stems from latent prototypes that are weakly aligned with class-discriminative regions and contaminated by irrelevant background, thereby degrading generation quality and generalization. To address this limitation, we propose a saliency-driven distillation framework that constructs class-discriminative latent prototypes to enhance representativeness and generalization. The framework proceeds in two stages: (1) ensemble Grad-CAM saliency is used to construct prototypes emphasizing high-confidence regions, and (2) hard prototype refinement is then applied to construct challenging yet class-consistent prototypes, thereby enhancing discriminability and diversity. Importantly, the diffusion backbones (e.g., LDM and DiT) remain frozen; only lightweight classifiers used for saliency extraction are trained. Extensive experiments across multiple benchmarks demonstrate consistent performance improvements over strong baselines. Code will be released.
Abstract (translated)
URL
https://arxiv.org/abs/2607.25318
PDF
-
MEDit-Bench: A Dataset for Evaluating Message-Driven Narrative Video Editing
2026-07-28 05:24:10Katsuya Ogata, Zongshang Pang, Mayu Otani, Yuta NakashimaAbstract
Video editing is fundamentally message-driven: even from the same source footage, the selected shots change depending on the narrative the editor wishes to convey. Benchmarks for a closely related task, video summarization, reduce editorial intent to a single, message-agnostic notion of saliency and thus do not account for this diversity. For evaluating message-driven video editing, we present \textbf{MEDit-Bench}, a dataset and benchmark, which pairs long-form videos with multiple editing messages and multiple professionally produced edits per message, demonstrating that different messages yield substantially different edits from the same source. We define an automatic evaluation protocol based on temporal alignment metrics, and find that an LLM-as-a-judge preference, a natural proxy for narrative quality, is unreliable for this task due to severe position bias. We additionally annotate each message with ambiguity and contextfulness scores, and show that both dimensions negatively correlate with model performance, establishing message difficulty as a meaningful stratification factor. Experiments with state-of-the-art MLLMs and reinforcement fine-tuned baselines show that while strong models approach human temporal alignment at lenient thresholds, all models fall behind humans at stricter criteria. A human perceptual study further confirms a large quality gap, with professional human edits remaining consistently preferred over model outputs.
Abstract (translated)
URL
https://arxiv.org/abs/2607.25300
PDF
-
CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention
2026-07-28 04:57:19Yufei Xue, Lin Niu, Hong Liu, Siran Liu, Hanyong Shao, Wei Liu, Guanghua Yu, Jianchen Zhu, Jun ZhangAbstract
The quadratic cost of self-attention makes long-context inference prohibitively expensive, and proxy-based block-sparse attention has become a practical remedy. Existing methods typically rely on a proxy to predict a binary sparse mask and a kernel to consume this mask and perform sparse attention computation. Such an approach is effective under moderate budgets. However, as the budget tightens, the estimated proxy inevitably drops some salient blocks, while the kernel can only apply the sparse mask mechanically, leading to an evident drop in model accuracy. We propose CoSA, a two-stage training-free Sparse Attention under proxy-kernel CO-design, which couples a Kernel-Aware Proxy (KAP) with an Ordered-Skipping Kernel (OSK). In the first stage, the KAP selects blocks under a moderate budget and produces an ordered mask that prescribes the order in which KV pages are visited in the kernel inner loop. In the second stage, the OSK applies this mask and skips more blocks under a tightened budget given online-softmax statistics. Across mainstream LLM backbones and long-context benchmarks, CoSA attains higher accuracy at lower budgets. Impressively, CoSA achieves a 4.93$\times$ attention speedup and reduces end-to-end Time-to-First-Token by 2.53$\times$ under a context length of 128K with negligible performance degradation.
Abstract (translated)
URL
https://arxiv.org/abs/2607.25291
PDF
-
A Cross-lingual Comparison of Human and Classification Model Entrainment Behavior in Code-switched Speech Settings
2026-07-28 02:16:41Debasmita Bhattacharya, Siying Ding, Alayna Nguyen, Julia HirschbergAbstract
Conversational entrainment is well-studied in monolingual and written contexts, but remains underexplored in spoken code-switching (CSW). We present a novel cross-lingual analysis of entrainment in Mandarin-English, Hindi-English, and Spanish-English dialogue and show that, while lexical entrainment generalizes across language pairs, entrainment over acoustic-prosodic and CSW style aspects exhibits context-specific variation. We build on these findings by asking whether classification models capture these human behavioral patterns. Applying feature importance and ablation analyses, we find that classical and Transformer-based classifiers detect entrainment reasonably well but consistently prioritize features other than those most salient to human entraining behavior. Our approach introduces a human-grounded framework for evaluating model decision-making in multilingual stylistic contexts, and suggests future challenges for developing conversational agents capable of producing naturalistic code-switched speech.
Abstract (translated)
URL
https://arxiv.org/abs/2607.25202
PDF
-
KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability
2026-07-27 17:57:02Krithi Shailya, Ananya Lakshmi Ravi, Venkatanathan K. V., Sowmya S. Sundaram, Gokul S. Krishnan, Aditi Anand, Balaraman RavindranAbstract
Computer vision models have become highly effective for medical applications, yet their black-box nature continues to undermine clinician trust. In clinical workflows, chest X-ray classifiers are increasingly paired with Vision-Language Models (VLMs) to generate natural-language explanations. However, these systems add linguistic fluency without addressing the underlying opacity of the visual model. With the emergence of Kolmogorov-Arnold Networks (KANs), whose spline-based components provide inherently interpretable functional units, we investigate whether this architectural transparency can be leveraged to produce more trustworthy textual explanations. We introduce KANEx, the first ever framework that leverages the symbolic transparency of KANs to ground VLM reasoning. This interpretability also made it possible to design KAN-Map, a novel heatmap generation method derived directly from KAN models rather than gradient approximations. We feed these grounded contexts into downstream VLMs for enhanced explainability. Benchmarked on the MIMIC-CXR dataset, we demonstrate that KAN-based architectures with ResNet/ViT baselines demonstrate improved semantic similarity while producing significantly more faithful saliency maps. KAN architectures improve visual localization and downstream reasoning quality by 10%. Our findings suggest that grounding linguistic explanations and visual attributions in mathematically interpretable units is a necessary step toward trustworthy medical AI.
Abstract (translated)
URL
https://arxiv.org/abs/2607.24730
PDF
