Attention
-
One Model to Loop Them All: Elastic Latent Recurrence for Language Models
2026-10-08 18:05:42Faisal Ladhak, Shantanu Acharya, Santiago Akle Serano, Simeng Sun, Boris Ginsburg, Krishna C PuvvadaAbstract
A latent recurrent language model applies a shared block of layers repeatedly, so one checkpoint can trade inference compute for accuracy by changing the loop count. At one loop, however, such models typically fall well short of a non-recurrent model of the same size, a one-loop tax that makes a separate non-recurrent model the better choice whenever latency matters. We present Elastic Latent Recurrence (ELR), a recipe for training looped language models without this tax. At one loop, an ELR model costs the same to serve as a non-recurrent model of the same size and, trained on the same data, reaches similar accuracy. Each additional loop then buys more accuracy for more inference compute. Three choices make this work: a gated state update with a learned step size, loop counts mixed within each optimizer update, and conditioning each pass on its loop index and budget. The first two preserve one-loop accuracy, and the third lowers loss at every additional loop. Mixed depths can be introduced late in pretraining to limit the added training cost, and with zero-initialized conditioning added at the switch, this late schedule reaches lower loss than mixed-depth training from scratch. In MoE models, reusing first-loop expert routes on later loops cuts mixed-depth update time by 11.7% with no measurable change in accuracy. At inference, keeping only the last loop's attention KV cache holds attention KV memory at its one-loop level while retaining most of the gain from additional loops. On 4B dense and 30B-A3B MoE hybrid models, ELR at one loop is 0.52 points below and 1.04 points above its matched baseline on a ten-task average, and four loops add 7.25 and 4.75 points. Carried through post-training, the recipe yields Koi-4B, a single checkpoint that scores an estimated 18 on the Artificial Analysis Intelligence Index at one loop, matching Qwen3.5-4B, and 29 at four loops.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12582
PDF
-
Scaling Multi-Teacher Distillation for Digital Pathology
2026-10-08 18:02:09Sofi\`ene Boutaj, Pierre Marza, Varun Belagali, Dimitris Samaras, Maria Vakalopoulou, Stergios ChristodoulidisAbstract
Multi-teacher distillation allows transferring knowledge from multiple "teacher" networks to a single "student" network. This method is promising in fields such as digital pathology, where many powerful foundation models were proposed recently. However, as we show in this paper, the standard multi-teacher distillation approach reacts poorly to an increase in the number of teachers used to train a student encoder. We demonstrate that learning teacher-specific representations is a key to scaling in MTD. Importantly, different design choices, such as learnable teacher tokens, a tailored attention scheme, additional mixture-of-experts layers and a contrastive loss, are proposed to better learn such teacher-specific representations. We show that our method better scales with respect to the number of considered teachers, allowing us to train compact student encoders, up to 10x more efficient than larger teacher foundation models, while matching their performance and even outperforming them on a large set of tile-level and slide-level tasks. We conduct a thorough empirical validation, evaluating more than 10 foundation models on 39 tasks spanning tile and slide levels. As a result, we release a new collection of strong and efficient foundation models, named OMNI, trained from the knowledge of 10 state-of-the-art foundation models. We finally conduct an analysis of the learned teacher-specific representations, highlighting their complementarity and explaining why they can be easily aggregated at downstream time.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12574
PDF
-
Contextual Correction of Parallel Draftsfor Speculative Decoding
2026-10-08 18:01:03Roy Eisenstadt, Harel Lidar, Tal Gonen, Omer Luxembourg, Itamar Zimerman, Lior Wolf, Eli David, Ilan NaimanAbstract
Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target model. Recent diffusion-based drafters make this paradigm particularly attractive: deep attention-based neural backbones provide strong predictions, while drafting multiple future positions in parallel avoids the sequential cost of autoregressive generation. This parallelism, however, comes at a cost. Tokens within a draft block are predicted without access to the realized identities of preceding draft tokens, removing intra-block dependencies that would naturally be available under autoregressive generation. We introduce DCOCO (DFlash Contextual Corrector), a lightweight mechanism that restores these dependencies while preserving parallel drafting. Rather than committing to each position's top prediction, DCOCO retains multiple candidate tokens and evaluates their contextual compatibility across adjacent draft positions in parallel, enabling contextually informed token selection at low additional cost. Across four verifier backbones and ten benchmarks, DCOCO achieves the highest average throughput in every evaluated configuration, spanning greedy and stochastic decoding with and without extended reasoning, with speedups of up to 6.6x over vanilla decoding. Its advantage persists under concurrent serving: DCOCO outperforms the strongest competing method by 6-23% across 4-32 concurrent requests, while other sequential correctors fall below uncorrected DFlash at these loads. These results demonstrate that recovering intra-block dependencies through parallel contextual scoring delivers consistent acceleration across decoding regimes and serving loads.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12570
PDF
-
Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models
2026-10-08 17:39:44Xingang Guo, Jing Gu, Brian Jang, Renxiong Wang, Utkarsh Tyagi, Daniel Quigley, Steven Li, David Yan, Daniel Yue Zhang, Darvin Yi, Forrest Huang, HiJae Kim, Tianyi Zhang, Jared Lichtarge, Jihua Huang, Le Xue, Manan Tomar, Qiuyi Richard Zhang, Ruofei Yu, Seth Neel, Yaning Hu, Marcella Valentine, Xinzhe Jiang, Daniel Evans, Chenguang Wang, Dustin Tran, Tong Zhao, Yinfei Yang, Yunzhong HeAbstract
Humans perceive far more in a scene than what is explicitly depicted: a single glance captures past causes and future trajectories; a quick peek determines if a vehicle can fit between two parked cars; a few seconds of video reveals who holds authority in a room; and a fleeting clip highlights subtle abstract patterns like unwritten rules or hidden labels. This capacity reflects a form of humanity's sixth sense: an intuitive reasoning mechanism that recovers implicit information beyond raw sensory perception. Crucially, this rapid, zero-shot visual intuition underpins everyday navigation and social interaction, making it a vital capability for Multimodal Large Language Models (MLLMs) deployed alongside people. Existing visual benchmarks, however, target either deliberate expert-level analysis in academic and mathematical domains or low-level perception, leaving the intuitive reasoning that people perform largely untested. To bridge this gap, we introduce Humanity's Sixth Sense (HSS), a benchmark for intuitive visual reasoning. HSS spans diverse image and video inputs, organizes items under a structured taxonomy, and pairs each with human-written prompts probing the implicit temporal, spatial, social, and abstract structure that people infer at a glance. Frontier MLLMs fall short of human performance: participants reach 93.1% accuracy, while the strongest model, GPT-6-astra, reaches only 53.6% even at maximum reasoning effort. Despite excelling in many complex tasks that require advanced perception and knowledge, current models still struggle significantly on these visual tasks that are intuitive for humans. We further explore agentic setup that apply dynamic visual manipulation to HSS, which narrows but does not close the gap. HSS establishes intuitive visual reasoning as a measurable axis and directs attention to a capability that scaling on current benchmarks has so far left behind.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08966
PDF
-
GenIA: Generative Reconstruction with Test-Time Input Alignment
2026-10-08 17:38:56Stefano Esposito, Naama Pearl, Polina Karpikova, Samuel Rota Bul\`o, Lorenzo Porzi, Peter Kontschieder, Andreas Geiger, Jonathon LuitenAbstract
Reconstructing complete 3D object assets from monocular or sparse multi-view observations remains challenging. Generative 3D foundation models can complete object geometry beyond the observed views, but their predictions may not faithfully reproduce the observed geometry, appearance, or pose. We introduce GenIA, a framework for test-time input-aligned generation that grounds SAM3D's generative prior in geometric and photometric observations without retraining the foundation model. We improve object pose by deriving translation and scale from geometry while retaining the learned rotation prior, and align appearance through visibility-biased attention, cross-observation fusion, and differentiable rendering guidance during denoising. An optional post-denoising refinement further adapts the appearance latent, lightweight decoder adapters, and object placement to the observations. Our framework also supports externally supplied geometry; when given temporal shapes of dynamic objects, it recovers a shared, input-aligned canonical appearance and stable world-space placement. Across synthetic and real benchmarks, GenIA improves pose prediction and object reconstruction from monocular, multi-view, and dynamic inputs, outperforming recent optimization-based, per-frame image-to-3D, and video-to-4D methods. Our project page is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12388
PDF
-
HANS: A Handwritten Answer Sheet Dataset for Noisy Hybrid Document Parsing
2026-10-08 17:27:12Xiazhen Wu, Wansong Qin, Yangbin Zheng, Liangda Fang, Zhan Li, Xiujie Huang, Liushen Zhou, Quanlong GuanAbstract
Intelligent grading and automated scoring technologies constitute critical infrastructure for smart education. However, existing document parsing and handwriting recognition benchmarks are predominantly designed for well-structured printed documents or isolated mathematical expressions, lacking datasets that capture the complex characteristics inherent to student answer sheets, including multi-line derivation processes, heterogeneous mixtures of text and mathematical formulae, and noise artifacts such as strikethroughs. To address this gap, we introduce HANS, the first dataset explicitly constructed for real-world educational scenarios, encompassing mathematical expressions, natural language text, hand-drawn tables, and diverse noise patterns including corrections and deletions, accompanied by fine-grained annotations that establish a reliable foundation for robust recognition research. Building upon HANS, we propose NA-GOT, an end-to-end framework that achieves two-stage noise suppression through a lightweight noise suppression module operating at the feature level, complemented by a noiseaware attention mechanism incorporated into the decoding stage. Experimental results demonstrate that HANS poses substantial challenges to existing methods, while NA-GOT achieves significant improvements in both accuracy and stability for answer process recognition. The dataset will be made publicly available upon publication.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12363
PDF
-
Looking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance
2026-10-08 16:53:45Zheng Huang, Sansheng Cao, Enpei Zhang, Weikang Qiu, Elynn Chen, Xiang Zhang, Yaoqing Yang, Rex Ying, Dawei Zhou, Yujun YanAbstract
Understanding large language model (LLM) reasoning requires looking beyond behavioral performance to examine how reasoning ability is reflected in internal organization. Inspired by neuroscience findings linking higher intelligence to stronger small-world organization in functional brain networks, we investigate small-world connectivity as a structural signature of LLM reasoning. We construct functional graphs from attention-head activation similarities and find that a higher small-world index (SWI), capturing local clustering and short global paths, consistently correlates with better fluid reasoning performance across models and training checkpoints. Since local clustering is central to small-world organization, we further examine how heads important for model performance connect within and across communities. We find that these heads tend to have a larger share of connection weight within their own communities (high core scores) and a more concentrated weight distribution across communities (low bridge scores). These observations motivate the hypothesis that high core and low bridge scores serve as structural indicators of head importance for reasoning capability. We validate this hypothesis through pruning, introducing Small-World Allocation (SWA), a hierarchical sparsity allocation method guided by these scores. Across six LLMs, SWA better preserves small-world organization and model performance than competing allocation strategies, reducing WikiText perplexity by up to 20%. Together, these findings identify small-world functional connectivity as a measurable signature of LLM reasoning performance, offering a structural perspective that complements behavioral evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12304
PDF
-
PLaW-VLA: Predictive Latent World Modeling for Vision-Language-Action Policies
2026-10-08 16:41:11Yu Liu, Hetian Guo, Tianlv Huang, Ziyi Cai, Wudi Chen, Hantang Wang, Qiutong Liu, Yingzhi Peng, Wei Han, Peijun Tang, Jianan Wang, Zipei Fan, Zhiyuan Zha, Xuan SongAbstract
Learning to predict how the world evolves can provide vision-language-action (VLA) policies with predictive context for long-horizon control, but its effectiveness depends on what future representation is modeled and how it conditions action generation. We introduce PLaW-VLA, which models task-relevant future states in a pretrained prediction-oriented representation space, reducing the need to predict control-irrelevant visual details. Built on a Mixture-of-Transformers architecture, PLaW-VLA conditions action generation on observation history, current task semantics, and predicted future states through structured causal attention. Experiments show a +11.8 percentage-point (pp) gain over reactive policies on RoboTwin Hard Horizon III and a +1.77 pp gain over reconstruction-oriented latent prediction on zero-shot LIBERO-Plus, supporting improved long-horizon control and generalization under distribution shift, respectively. By avoiding low-level visual reconstruction, PLaW-VLA lowers the burden of future prediction, enabling a lightweight latent world model with parallel future prediction and about 1/19 the inference latency of generative world-action modeling at comparable policy performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12285
PDF
-
Healthy Counterfactual Generation via Diffusion Inpainting for Mammography Classification
2026-10-08 15:31:56In\^es Cruchinho Garcia, Mariana Mour\~ao, Francisco Maria Calisto, Carlos Santiago, Jacinto NascimentoAbstract
False negatives remain a critical limitation of computer-aided diagnosis (CAD) systems for breast cancer screening due to delayed detection and treatment. To address this issue, we propose a counterfactual data augmentation strategy that generates healthy mammograms by "erasing" lesions from anomalous images, thereby enriching the training distribution. We train a Denoising Diffusion Probabilistic Model on BI-RADS 1 (healthy) mammograms and use a RePaint-based sampling strategy to inpaint realistic normal tissue within annotated lesion bounding boxes. The resulting healthy counterfactuals replace annotated lesion regions with realistic healthy tissue while preserving patient-specific anatomical structure, as supported by similarity metrics between real and generated images. Image realism was further assessed by radiologists and found to be consistent with the original dataset quality. We evaluate counterfactual augmentation across four representative classifier architectures: a convolutional neural network (ConvNeXt), a vision transformer (ViT), a vision-language model pre-trained on mammogram-report pairs (Mammo-CLIP) and a multi-scale attention-based multiple-instance learning framework (FPN-MIL). Experiments conducted on the VinDr-Mammo dataset show improvements in sensitivity across all architectures, particularly at 80\% fixed specificity, contributing towards more reliable CAD systems for breast cancer. Code is available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12147
PDF
-
Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning
2026-10-08 14:39:26Andrea Agostini, Simon B\"ohi, Moritz Vandenhirtz, Samuel Ruiperez-Campillo, Max Kr\"ahenmann, Silke M\"uhlstedt, Irene Cannistraci, Ece \"Ozkan Elsen, Julia E. Vogt, Thomas M. SutterAbstract
Cardiovascular diagnosis and treatment rest on integrating complementary modalities, such as electrocardiogram, echocardiography, and chest X-rays, each capturing distinct but complementary aspects of cardiac pathophysiology. Yet most medical foundation models remain modality-specific, combining modalities only for finetuning or post-training. This discards the cross-modal evidence clinicians naturally integrate and ignores the structure within each modality. We introduce Latent-Attention Masked Autoencoder (LAMAE), a multimodal, structure-aware masked autoencoder that jointly learns patient-level representations during self-supervised pretraining. Instead of fusing modalities post hoc, LAMAE exchanges information directly in the latent space through a shared latent-attention module operating over a study-view-entity hierarchy, enabling aggregation of variable observations and handling of missing modalities. Pretrained on over 500'000 MIMIC-IV hospital stays, LAMAE outperforms modality-specific pretraining and strong contrastive and vision-language baselines across multimodal hospital-stay tasks, such as in-hospital mortality, ICD-10 and DRG coding, and length of stay, while remaining competitive on unimodal tasks. Modeling this structure also pays off within a single modality: even without cross-modal information, the latent-attention module improves representations over modality-specific pretraining.
Abstract (translated)
URL
https://arxiv.org/abs/2609.12035
PDF
-
DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization
2026-10-08 14:12:28Wenxin Tang, Junliang Liu, Wenbin Li, Jingyu Xiao, Xi Xiao, Mingzhe Liu, Jinlong Yang, Xuan Liu, Yuehe Ma, Wang Luo, Qing Li, Lei Wang, Peng XiangliAbstract
Software vulnerability detection plays a critical role in ensuring system security, where real-world auditing requires not only determining whether a function is vulnerable but also pinpointing the specific lines responsible. However, existing approaches either rely on a single information source -- sequential, structural, or semantic -- failing to jointly exploit the complementary strengths across modalities, or treat statement-level localization merely as a byproduct of function-level detection without explicit line-level supervision. To address these limitations, we propose DCVD (Dual-Channel Cross-Modal Vulnerability Detection), a unified framework that performs joint function-level detection and statement-level localization. DCVD extracts control-dependency and semantic features through two parallel branches and integrates them via contrastive alignment coupled with bidirectional cross-attention, effectively bridging the cross-modal representation gap. It further introduces explicit supervision signals at both the function and statement levels, enabling collaborative optimization across the two granularities. Extensive experiments on a large-scale real-world vulnerability benchmark demonstrate that DCVD consistently outperforms state-of-the-art methods on both function-level detection and statement-level localization. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.11015
PDF
-
PulseBound: Future-Beat State Forecasting Under an Explicit Information Boundary
2026-10-08 14:10:56Chenyang Xu, Donglin Xie, Xi Xiang, Xiaoyu Li, Yufan Lu, Jiqiun Gao, Yi Zhao, Xin-Yi Li, Guangpu Zhu, Zijian Wang, Xiwen Yang, Dezhen Wang, Lin Chen, Shenda Hong, Leilei LiAbstract
Predictive representation learning from photoplethysmography (PPG) can violate causal information access even with causal attention, as normalization, nonlocal transforms, or companion views may depend on withheld samples. We introduce PulseBound, a PPG representation learner combining physiologically structured future-beat prediction with an explicit stored-window information boundary. A content-independent cutoff separates the visible prefix from the prediction target. Prefix-only normalization, suffix replacement before derived-view construction, and aligned masking ensure that encoder inputs depend only on the visible prefix and cutoff. This yields stored-suffix invariance: with fixed model state, randomness, prefix, and cutoff, changing the stored suffix cannot change the forecast context. A shared horizon-conditioned head predicts nine rhythm and morphology descriptors for up to four extractor-valid future beats, using elementwise validity masks; optional ECG-derived pulse-arrival-time supervision is restricted to training. On MIMIC and VitalDB groups held out from PulseBound backbone pretraining, PulseBound reduces nine-state transformed-space MAE relative to last-visible-beat persistence by 28.06% and 22.22%, respectively, with gains in MAE, MAE-Skill, and Spearman correlation across all 40 source-cutoff-horizon cells. In a separate comparison of seven models on 13 downstream tasks, PulseBound achieves the best mean on nine frozen linear-probe and seven full-fine-tuning tasks. Stored-suffix interventions cause zero recorded changes in forecast contexts or predictions, with zero suffix-input gradients at audited precision under the stored-window interface. These findings separate three testable aspects of predictive physiological representation learning: information access, supervised future structure, and transfer.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12010
PDF
-
Predicting Cable Dynamics with Physical Attention Bias
2026-10-08 13:51:30Avihai Giuili, Rotem Atari, Avishai Sintov, Maya Bechler-SpeicherAbstract
Learned simulators for deformable linear objects (DLOs) such as cables have to predict the motion of cables they were not trained on and stay stable over long rollouts. Most of their error occurs where the cable touches itself or the floor. Attention over all pairs of cable segments can represent contact between parts of the cable that are far apart along its length, but attention has no notion of geometry. A cable has two pairwise distances, which agree only while it is straight: the arc-length distance along the cable, which governs elastic forces, and the Euclidean distance in space, which governs contact. We add a physical attention bias, an additive term on the attention logits with a learned rate, and ask which distance it should use. We compare no bias, each distance alone, and both distances on disjoint sets of heads, keeping the rest of the model and the training protocol fixed. A physical bias improves prediction on unseen cables. The gain is largest when attention is the only mechanism that connects distant segments: there, the arc-length bias reduces prediction error by 15% and more than halves the drift in segment length. The Euclidean bias alone stays close to unbiased attention, while assigning both distances across heads is best or near-best on every metric we report. Code and per-run records: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11975
PDF
-
CAPABLE: Capability-Aware Policy Adaptation via Behavioral Latent Encoding
2026-10-08 13:46:52Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Deyuan Qu, Zhiyuan Gao, Yanxiang Zhan, Jeroen Schafer, Andrew Melnik, Qing Yang, Michael BeetzAbstract
Vision-language-action (VLA) policies assume the embodiment on which they were trained and can fail when a joint fault changes how commanded actions are physically executed. Existing fault-recovery methods often require task-specific retraining, fault labels, explicit diagnosis, or privileged embodiment information. We introduce CAPABLE, a unified capability-aware adaptation framework for frozen VLAs that integrates self-supervised capability inference with residual reinforcement learning. CAPABLE infers capability, how much of the commanded motion each joint actually realizes and how that motion contributes to end-effector behavior, online from command-response history and kinematics using a temporal encoder shared across joints, Jacobian grounding, cross-joint attention, and self-supervised physical prediction. The resulting representation conditions a residual policy that adds bounded corrections to the VLA arm action without fault labels or faulty-joint identifiers. Across 28 LIBERO tasks, CAPABLE raises success on an actuator excluded from fault training from 24.8% to 59.3%, outperforming a parameter-matched global-history baseline by 17.4 points while preserving healthy performance. Leave-one-actuator-out experiments across six joints show that this transfer is not specific to one actuator, and additional evaluations characterize transfer to unseen fault families and demonstrate recovery on a physical Franka Panda. this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.11971
PDF
-
TACROSS: An Efficient and Low-Cost Scalable Human Touch System Across Heterogeneous Tactile Sensors for Dexterous Robot Learning
2026-10-08 13:34:31Bo Chen, Huanzhang Hu, Junyang Ma, Bo Yue, Fangdi Yu, Haijier Chen, Xianxin Lai, Shuyu Pan, Zhen Yang, Xiaoquan Sun, Wenze Cui, Zhongliang Jiang, Shaopeng Liu, Jiayu ChenAbstract
Collecting tactile demonstrations on robots is costly and slow, motivating the use of lower-cost human tactile gloves for scalable data collection. However, human capacitive/piezoresistive gloves and robotic tactile sensors differ fundamentally in transduction principle, sensor layout, spatial resolution, and dynamic response, making alignment of raw sensor channels ill-posed. To address this problem, we present TACROSS, a scalable system for learning from human touch and transferring it to robots that bridges this heterogeneity by aligning tactile streams at the level of contact events rather than raw sensor values. The hardware component of TACROSS integrates a piezoresistive glove with five layers and a cost of USD 10.86 with 285 sensing points. To align contact semantics, we design canonicalizers and residual adapters that map heterogeneous signals into a shared tactile latent with 256 dimensions via a temporal Transformer with attention across fingers. We further introduce a robot-grounded policy learning scheme in which robot demonstrations provide the sole source of ground-truth action supervision, while human demonstrations support tactile representation learning and provide confidence-weighted auxiliary supervision through valid retargeted hand targets. We evaluate our system on four contact-rich manipulation tasks. Compared to conventional teleoperation, our proposed system achieves a 3.5-fold efficiency improvement while reducing demonstration acquisition equipment cost by 95.7%. We will open-source the TACROSS hardware and software system and publicly release a tactile dataset comprising over 150 hours of recordings. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11945
PDF
-
Relative Patch Response Learning for Generalizable AI-Generated Image Detection
2026-10-08 12:49:54Tianyu Wang, Ouxiang Li, Yanbin Hao, Zhenhua Tang, Shuo WangAbstract
Generative models can now synthesize highly realistic images, simultaneously increasing the risks of misinformation and visual forgery. Therefore, detecting AI-generated images becomes more essential, and a reliable detector must generalize to unseen generators and stay robust to unseen perturbations in the wild. Existing detectors are typically trained on either independently collected real and generated images or aligned real-generated pairs designed to mitigate content bias. Building on aligned pairs, recent methods form a mixed view by replacing some patches of the real image with their generated counterparts. However, we find that self-attention lets real and generated patches interact, so the feature of each patch no longer reflects its own source alone. This contextual shift makes a per-patch source label an imprecise target. To this end, we propose Relative Patch Response Learning (PRL). Instead of labeling each patch, PRL compares the same patch across two mixed views of an aligned pair and learns from its patch response, the change of its score between the views. (i) To give precise supervision under the contextual shift, a relative response objective measures the responses of source-changed patches against those of source-unchanged patches, which respond to the shift alone. (ii) To provide a reliable reference for the shift, a reference coherence objective keeps each group of source-unchanged patches moving as a whole. (iii) Since the two views contain different amounts of generated content, an area ranking objective asks the view with the larger generated area to have a higher mean patch score. Extensive experiments demonstrate the superior performance of PRL, which surpasses the best prior methods by 4.3% and 5.9% in average balanced accuracy across eight standard and three in-the-wild benchmarks, respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11876
PDF
-
Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement
2026-10-08 12:38:48Jingyi Pan, Dan Xu, Qiong LuoAbstract
3D scene inpainting aims to recover missing or occluded regions in edited 3D scenes, while ensuring geometric and textural consistency. Existing approaches, however, typically require accurately calibrated camera poses, which restricts their applicability in casual, in-the-wild scenarios and introduces additional preprocessing overhead. To overcome this limitation, we present FreeInpaint, a novel feed-forward framework that generates complete and 3D-consistent scenes directly from unposed multi-view images with masked regions. At its core, FreeInpaint extends a 3D foundation model to propagate masked regions from a reference view to other unposed views, bridging 3D reconstruction and scene inpainting while preserving the model's native ability to recover camera poses and scene geometry. Our method addresses two key challenges in adapting feed-forward 3D foundation models to masked inputs. First, masked regions can corrupt cross-view correspondence reasoning, degrading pose estimation and geometry recovery. To address this, we introduce a Learnable Mask Attention mechanism that preserves the spatial anchoring of reliable observations while allowing masked regions to progressively absorb useful context in deeper layers. Second, under severe occlusions, a single forward pass often lacks sufficient appearance evidence for high-fidelity completion. Therefore, we propose a Support Token Refinement strategy, which injects diffusion-generated support evidence as confidence-weighted auxiliary tokens to refine under-observed regions while preserving the original spatial anchor. Extensive experiments across diverse datasets demonstrate that FreeInpaint achieves superior inpainting quality, eliminating the reliance on pre-computed camera poses while keeping a fast inference speed. The project page is this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11857
PDF
-
Open-Vocabulary Audio-Visual Event Localization via Complex-Valued Fusion
2026-10-08 12:34:24Anirudh Praveen, Koteswar Rao Jerripothula, Pratik Joshi, Aveen Dayal, Neela SawantAbstract
Open-Vocabulary Audio-Visual Event Localization (OV-AVEL) labels each video segment with an event class, including classes that were never seen during training. The dominant pipeline uses a frozen multimodal foundation model (e.g. ImageBind) to embed the visual frame, the audio mel-spectrogram, and each candidate class name into a shared space, then computes two cosine similarities for each segment against each class: visual-text and audio-text. Existing methods then collapse this pair into a single scalar score with a fixed rule (geometric mean, weighted average) before taking the argmax. Instead, we compute complex-valued similarities and learn their fusion using a complex-valued neural network (CVNN). Each modality's standard representation becomes the real part of our pipeline, and a paired companion stream supplies the imaginary part. We use imaginary part of iHSV for visual modality and CycleGAN-translated phase spectrogram for audio modality as these companion streams. This results in two complex similarities, which are then fused. While the vision and audio encoders remain frozen, only the temporal-attention blocks and the fusion CVNN are trained. The four-stream complex architecture sets a new state of the art on both OV-AVEL benchmarks. On the open (unseen-class) split of OV-AVEBench we reach 66.5/59.1/54.1% Acc/Seg-F1/Event-F1 (+1.6/+4.1/+6.6 over the previously reported fine-tuned baseline), with consistent gains for seen classes as well. We also modify AVE dataset for this task and observe that our architecture reaches 60.7/51.9/50.4% Acc/Seg-F1/Event-F1, achieving state-of-the-art OV-AVEL results on it as well. We also propose a two-stream alternative, which also sees great improvements over the baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11846
PDF
-
When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression
Abstract
Training-free KV-cache compression methods such as SnapKV, H2O, and PyramidKV evict tokens at the end of prefill, aiming to preserve the attention mass that future queries are expected to use -optimizing what to keep. We show that this objective fails in two distinct ways. (1) Compensation: restoring the evicted attention mass can recover the attention-level target without recovering task quality. (2) Selection: covering more of the true decode-query mass can hurt quality when the recovered mass is fragmented rather than concentrated in coherent spans. These failures share a common cause: eviction occurs before the queries that determine the answer trajectory exist. We propose Draft-Guided Eviction (DGE), which defers eviction until after drafting the first k=2 answer tokens using the full cache - just one decode step beyond prefill. Because the draft is generated from the answer's own prefix, no cache entries are discarded before this trajectory signal becomes available. The per-head cache budget remains unchanged, and DGE can be applied directly to SnapKV, PyramidKV, H2O, and StreamingLLM without modifying their eviction scores. Unlike extra-pass methods, DGE changes when eviction occurs rather than what cache entries are selected. Extensive experiments demonstrate that DGE outperforms prior methods at every evaluated budget on five of six instruct-tuned backbones, achieving 44.2 on LongBench, nearly matching FullKV at 44.3. The timing-only control DGE-W achieves the same score, demonstrating that the gain comes from when eviction occurs rather than what is selected - an effect we term trajectory anchoring.
Abstract (translated)
URL
https://arxiv.org/abs/2609.33334
PDF
-
Phase-aware video generation for physics-grounded dynamics and interactions
2026-10-08 12:04:46Jingfeng Ou, Kun Wang, Rui Zhao, Jingwei Guan, Limin Wang, Chao Dong, Xingyu ZengAbstract
Generating physically plausible videos for solid-gas dynamics is challenging as different phases exhibit distinct dynamics yet remain coupled through physical interactions. We present PAVG, a Phase-Aware Video Generator for solid-gas dynamics and interactions. It employs a dual-branch architecture to explicitly model the distinct dynamics of solids and gases, while spatiotemporal cross-attention captures their physical interactions. This design enables PAVG to preserve phasespecific motion characteristics while producing physically consistent responses across phases. To facilitate this task, we further construct a simulation corpus comprising over 700K physical trajectories across diverse solid, gas, and solid-gas interaction scenarios. Extensive evaluations demonstrate that our PAVG produces videos with improved motion adherence, physical plausibility, and visual quality compared with existing approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2610.11791
PDF
