# Research Papers — 2026-07 · bundle page 18 of 222 > Full-text markdown of papers #851–900 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/18 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/17.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/19.md) ### Nanoparticle Networks for Neuromorphic Computing Authors: Jonas Mensing, Wilfred G. van der Wiel, Andreas Heuer Published: 2026-07-30 Categories: cs.ET, cond-mat.mes-hall, cs.AR, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2607.27844v1 Physical computing leverages complex dynamical systems for energy-efficient data processing. In this work, we present a neuromorphic architecture based on metallic nanoparticles interconnected by molecular junctions on a $\text{SiO}_2$/Si substrate. We demonstrate that surrounding static control electrodes transform this nanoparticle network from a passive reservoir into a tunable nonlinear dynamical system. By analyzing how these electrodes route simple one-dimensional voltage inputs into multidimensional signal responses, we establish three core design rules to maximize computational performance. First, operating near the system's cutoff frequency achieves an optimal balance between nonlinear charge tunneling and linear capacitive memory. Second, tuning the underlying $\text{SiO}_2$ thickness sets the electrostatic screening length and dictates the memory type. Thick oxide layers reduce the screening length, causing networks larger than this length to transition into a persistent, non-volatile-like regime. Conversely, networks smaller than the screening length exhibit only fading memory. Third, introducing structural disorder via heterogeneous molecular junctions overcomes inherent limits on expressivity. While a network's computational expressivity scales with its physical size, it is ultimately capped by the screening length. Breaking internal spatial symmetries with localized disorder bypasses this saturation, allowing control voltages to independently manipulate specific signal amplitudes and phases, universally maximizing performance for dynamic neuromorphic applications. --- ### VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detection Authors: Songsong Duan, Xi Yang, Nannan Wang Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27843v1 Camouflaged Object Detection (COD) aims to identify and segment camouflaged objects in complex environments, which are often concealed because their color and texture are similar to the background. Several existing COD methods introduce depth maps to boost detection performance via learning complementary RGB-D features, ignoring modality-specific characteristics of concealed objects in the depth domain. To address this issue, we propose a depth collaborative network, called VCP-DCN, to mine distinguishable multi-modality features beyond visual concealed prototype in depth domain. Specifically, VCP-DCN progressively performs multi-modality alignment, interaction, and fusion for the COD task. In the \textbf{alignment} stage, we propose a Separable Prototype Embedding (SPE) module to learn modality-consistency and modality-specific RGB/depth prototype tokens through prototype contrastive learning. Furthermore, we develop a Multi-modality Dual Attention (MDA) module to enhance the cross-modal feature representation through local response maps between modality-consistency RGB/depth prototype tokens and visual tokens on the \textbf{interaction} stage. Finally, we design a Depth Adaptive Injection (DAI) module to adaptively measure contribution of RGB/depth features with a decision-making mechanism, which calculates similarity distance between RGB/depth modality-specific prototype tokens and modality-consistency ones on the \textbf{fusion} stage. Extensive experiments demonstrate the effectiveness of our VCP-DCN on three authoritative datasets. --- ### FeatFix: Reuse What You Verify through Local Exact-Feature Correction for Faster Cached Diffusion Inference Authors: Hanshuai Cui, Zhiqing Tang, Zhi Yao, Qianli Ma, Fanshuai Meng, Weijia Jia Published: 2026-07-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.27842v1 Diffusion models are widely used to generate high-quality images and videos, but their iterative denoising process remains computationally intensive. A growing class of training-free accelerators reduces this cost by reusing cached intermediate features or forecasting future ones. To control draft drift, these methods sometimes compute an exact block feature for verification. Yet the resulting exact feature is typically used only to measure discrepancy or guide a later decision and is then discarded. We find that this previously computed feature can instead be reused for correction. Forwarding it at the verification site resets the local draft residual and reduces downstream feature error. Based on this observation, we introduce FeatFix, a local exact-feature correction method for cached diffusion inference. FeatFix operates at a fixed sparse set of layer--timestep sites. At each selected site, it replaces the complete draft block output with the exact output computed from the same incoming state, avoiding token- or channel-level partial replacement and full-timestep recomputation. Experiments across four image and video backbones show that FeatFix consistently accelerates generation, achieving a speedup of up to $6.70\times$ over Vanilla while maintaining competitive output quality. --- ### Virtual Process Dossier: A Process-Aware Data Catalogue Authors: Lukas Kubelka, Alexander Bott, Frank Döhner, Saksham Kiroriwal, Georg Zeeb, Julia Butte, Julius Pfrommer, Jürgen Beyerer, Tobias Käfer Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27840v1 We propose the Virtual Process Dossier (VPD), a Knowledge Graph-based data catalogue that also captures workflow provenance. We developed VPD for multi-stage manufacturing use-cases where downstream AI-based optimization tasks require to distinct between datasets generated during individual workflow steps. VPD provides these datasets in a FAIR manner and makes both prospective and retrospective workflow provenance explicit. Our contributions are: (1) the VPD ontology that serves as the catalogue's semantic core; (2) the VPD provenance framework that integrates ontology instantiation into the production environment; and (3) the VPD user interface that provides human-centered interaction with the VPD Knowledge Graph. The ontology and code are available at https://github.com/kubeluk/VirtualProcessDossier . --- ### Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration Authors: Xiangyu Yin, Jiaxu Liu, Zhen Chen, Chih-Hong Cheng Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27836v2 Large language model unlearning is consistently fragile under relearn attacks. On TOFU, fine-tuning on twenty forget examples substantially recovers held-out forget-set ROUGE for every method we evaluate, and we trace this fragility to optimization geometry. The per-token answer margin of fourteen post-hoc methods spanning gradient, preference, and distillation families converges into a narrow band above the retain reference in 41 of 42 method--size cells, a regularity we call the margin cliff. We prove that this cliff follows whenever the retain coupling holds the diagnostic log-odds of forget content above a floor, a condition that token-saturating losses induce at stationarity and that we verify directly on 34 of 42 cells. Margin Calibration (\textsc{MC}) is a plug-in polish adding a non-saturating margin hinge anchored at the reference's per-token margin plus a KL probe on a disjoint instruction corpus, restoring forget-side pressure where the native loss saturates. Under a stated gradient-dominance condition, whose on-trajectory gradient signature we measure by instrumenting the polish, its stationary set lies on the cliff-crossing side, yielding an attack-budget upper bound on the relearn margin lift. Across TOFU (three Llama-3 sizes, three forget tiers), MUSE-News on Llama-2-7B-hf, and a Phi-3.5 panel, a single frozen configuration wins all 14 head-to-head forget aggregates and all populated relearn cells (panel-mean post-attack ROUGE-L $0.41$ to $0.18$) and lowers raw membership AUC on 13/14, with reduced retain-side utility as the main cost. A deployment variant matches these gains without a retain-trained reference. --- ### Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration Authors: Xiangyu Yin, Jiaxu Liu, Zhen Chen, Chih-Hong Cheng Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27836v1 Large language model unlearning is consistently fragile under relearn attacks. On TOFU, fine-tuning on twenty forget examples substantially recovers held-out forget-set ROUGE for every method we evaluate, and we trace this fragility to optimization geometry. The per-token answer margin of fourteen post-hoc methods spanning gradient, preference, and distillation families converges into a narrow band above the retain reference in 41 of 42 method--size cells, a regularity we call the margin cliff. We prove that this cliff follows whenever the retain coupling holds the diagnostic log-odds of forget content above a floor, a condition that token-saturating losses induce at stationarity and that we verify directly on 34 of 42 cells. Margin Calibration (\textsc{MC}) is a plug-in polish adding a non-saturating margin hinge anchored at the reference's per-token margin plus a KL probe on a disjoint instruction corpus, restoring forget-side pressure where the native loss saturates. Under a stated gradient-dominance condition, whose on-trajectory gradient signature we measure by instrumenting the polish, its stationary set lies on the cliff-crossing side, yielding an attack-budget upper bound on the relearn margin lift. Across TOFU (three Llama-3 sizes, three forget tiers), MUSE-News on Llama-2-7B-hf, and a Phi-3.5 panel, a single frozen configuration wins all 14 head-to-head forget aggregates and all populated relearn cells (panel-mean post-attack ROUGE-L $0.41$ to $0.18$) and lowers raw membership AUC on 13/14, with reduced retain-side utility as the main cost. A deployment variant matches these gains without a retain-trained reference. --- ### SAFViT: Spatial Attention Fusion Gating for Vision Transformer-Based Nucleus Segmentation and Classification Authors: Harshit Mittal, Arash Rabbani Published: 2026-07-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.27835v1 Accurate cell segmentation and classification are foundational to digital pathology, enabling quantitative tissue analysis for diagnosis and treatment planning. Encoder-decoder architectures that fuse multi-scale features through skip connections have become the dominant paradigm for this task, yet standard direct skip connections treat every spatial location equally, which leads to redundant and potentially conflicting information reaching the decoder. To overcome this problem, various gating mechanisms have been introduced, but most of them operate solely on filtering encoder information, neglecting the benefit of global contextual information from the decoder. This study proposes replacing conventional skip connections in a CellViT-based model with a novel Spatial Attention Fusion (SAF) Gating module. Each SAF gate concatenates the encoder skip and upsampled decoder features, compresses them through two pointwise convolutions with an intermediate ReLU, and applies a channel-wise softmax to produce a per-pixel "heatmap of trust" that sums to unity at every spatial location, allowing the network to learn where each source is most trustworthy. The resulting fused features improve the model's ability to detect the minority "Dead" class, which in turn enhances the multi-class panoptic quality (mPQ) on the PanNuke dataset. SAF Gating is compared against six gating alternatives including no gating, attention gates, squeeze-and-excitation, CBAM, cross-attention, and attentional feature fusion on PanNuke and MoNuSeg datasets. SAF Gating achieves the highest mPQ (0.471), a gain driven primarily by a 14.5-point improvement in Dead-class F1 score compared to ungated CellViT baseline. --- ### MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory Authors: Hanshuai Cui, Zhiqing Tang, Zhi Yao, Fanshuai Meng, Qianli Ma, Weijia Jia Published: 2026-07-30 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.27834v1 Persistent memory lets long-running large language model agents reuse information across sessions and tasks. Yet errors in writable memory can persist and corrupt future behavior. Existing systems improve storage and retrieval, but they do not provide a transaction boundary for reliable updates and recovery. We therefore propose MemTxn, a governance layer outside the answer model. MemTxn verifies whether an update is supported by its source. It also selects the visible version when facts conflict and restores the application-visible state after a fault. The system uses Ordered PatchTest to validate writes, a Temporal Resolver to select versions, and a durable snapshot journal to recover state. On an item-disjoint audit, MemTxn accepts all 60 supported originals and rejects all 179 hard negatives. Under persistent multi-key faults on LongMemEval-S and LoCoMo states, it restores the complete declared active map without knowing the actual physical write set. On MemoryAgentBench FactConsolidation, MemTxn achieves the highest average F1 across all twelve answer-model configurations. It outperforms Dense by 17.06--24.07 points in five representative settings. --- ### Thinking Once Is Enough: Intermediate-Layer Evidence Routing for High-Resolution VQA Authors: Zhongkuan Mao, Xianjie Liu, Tianyu Meng, Yidong Wang, Wenzhuo Zhao, Ronghao Xian, Yao Jiang, Fei Shen, Junfeng Fang, Yong Dai, Yi Zhang, Keren Fu Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27830v1 High-resolution visual question answering (HR-VQA) is often treated as a problem of insufficient evidence acquisition, where failing multimodal large language models must inspect images again through cropping, re-encoding, or multi-round search. We show that this view is incomplete: in many cases, fine-grained evidence has already survived visual encoding and become identifiable and influential within an intermediate-layer routing window, but is later diluted before answer generation. We propose Thinking-Once, a \textbf{training-free, single-visual-pass} evidence-routing method that reconstructs question-conditioned attention at this window, preserves core entity tokens and compact background context, and routes this evidence to later layers without extra visual encoding. Across five base models, Thinking-Once consistently improves or matches the corresponding base setting, increasing the average scores on V$^*$Bench, HRBench-4K, and HRBench-8K by \textit{+3.1}, \textit{+3.0}, and \textit{+2.7} points while reducing the average peak memory by about 4,GB. On Qwen2.5-VL-7B, it improves the three benchmarks by \textit{+9.9}, \textit{+4.6}, and \textit{+5.5} points, raising the cross-benchmark mean from 72.5 to 79.1. With the ZwZ-8B base model, Thinking-Once reaches a mean score of 82.7. Against 11 open-source HR-VQA baselines, it obtains the best or tied-best score on all three benchmark averages and the best overall mean; for example, compared with DeepScan, it reduces V$^*$Bench inference time by \textbf{97.2\%} while improving the cross-benchmark mean from 77.8 to 79.1. These results show that HR-VQA can be improved by routing already encoded evidence rather than repeatedly acquiring new visual inputs. Code is available in the appendix. --- ### Sign Language Question Answering: A New Task, Benchmark, and Baseline for Sign Language Understanding Authors: Shiwei Gan, Lichen Wang, Xiao Liu, Yafeng Yin, Kuizhuang Liu, Sanglu Lu, Lei Xie Published: 2026-07-30 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.27826v1 Recent advances in sign language (SL) understanding (SLU) have led to remarkable progress in tasks such as continuous SL recognition and SL translation. However, these tasks are designed with predefined objectives, requiring models to learn a fixed mapping from sign videos to glosses or spoken-language sentences. As a result, they provide only a limited assessment of whether a model truly understands the semantic content of SL videos. To address this limitation, \textbf{we first propose a new task, Sign Language Question Answering (SLQA)}, which evaluates SL understanding by requiring models to answer arbitrary natural language questions about SL videos. Unlike previous SLU tasks, SLQA provides a more flexible and comprehensive evaluation framework that assesses multiple reasoning capabilities beyond recognition and translation. To facilitate this task, \textbf{we further construct two SignQA benchmarks} based on PHOENIX14T and CSL-Daily by automatically generating question-answer pairs from existing gloss and sentence annotations using carefully designed templates. The resulting datasets cover five complementary question categories, including position reasoning, structural reasoning, visual search, gloss recognition, and translation understanding. \textbf{Finally, we propose a simple yet effective baseline model} equipped with a Question-Conditioned Modulated Temporal Downsampling module and an in-domain knowledge transfer strategy, enabling effective knowledge transfer from existing SLU tasks while enhancing question-aware temporal feature modeling. Extensive experiments demonstrate that our baseline consistently outperforms representative vision-language models across all question categories, establishing a strong benchmark for future research on SLQA. Datasets are available at:{https://huggingface.co/datasets/hulala/SignQA-2026}. --- ### Endo-NeRF++: Uncertainty-Aware Neural Rendering with Multi-Resolution Hash Encoding for Dynamic Surgical Scene Reconstruction Authors: Gousia Habib, Laura Ruotsalainen Published: 2026-07-30 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2607.27825v3 Reconstructing dynamic surgical scenes is crucial for robot-assisted minimally invasive surgery; however, it continues to be difficult because of tissue deformation, occlusions, specular reflections, and restricted viewpoints. In this study, we introduce Endo-NeRF++, a neural rendering framework that accounts for uncertainty in the reconstruction of dynamic surgical scenes. Expanding on EndoNeRF, the suggested approach incorporates multi-resolution hash-grid encoding, temporal feature merging, and uncertainty-informed adaptive sampling to enhance reconstruction accuracy and temporal coherence in deformable endoscopic scenes.The multi-resolution hash-grid representation within the framework effectively captures both coarse and fine anatomical details, while temporal feature blending ensures stable reconstruction during tissue deformation and surgical tool occlusions. Additionally, uncertainty-driven adaptive sampling assigns more samples to uncertain areas to enhance rendering quality and geometric coherence. Experiments on robotic surgical video sequences demonstrate that the proposed uncertainty-guided adaptive sampling improves PSNR by up to 1.22dB (4.3%), increases SSIM by up to 5.3%, and reduces LPIPS by up to 55.1% compared with the EndoNeRF baseline. --- ### Endo-NeRF++: Uncertainty-Aware Neural Rendering with Multi-Resolution Hash Encoding for Dynamic Surgical Scene Reconstruction Authors: Gousia Habib, Laura Ruotsalainen Published: 2026-07-30 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2607.27825v2 Reconstructing dynamic surgical scenes is crucial for robot-assisted minimally invasive surgery; however, it continues to be difficult because of tissue deformation, occlusions, specular reflections, and restricted viewpoints. In this study, we introduce Endo-NeRF++, a neural rendering framework that accounts for uncertainty in the reconstruction of dynamic surgical scenes. Expanding on EndoNeRF, the suggested approach incorporates multi-resolution hash-grid encoding, temporal feature merging, and uncertainty-informed adaptive sampling to enhance reconstruction accuracy and temporal coherence in deformable endoscopic scenes.The multi-resolution hash-grid representation within the framework effectively captures both coarse and fine anatomical details, while temporal feature blending ensures stable reconstruction during tissue deformation and surgical tool occlusions. Additionally, uncertainty-driven adaptive sampling assigns more samples to uncertain areas to enhance rendering quality and geometric coherence. Experiments on robotic surgical video sequences demonstrate that the proposed uncertainty-guided adaptive sampling improves PSNR by up to 1.22dB (4.3%), increases SSIM by up to 5.3%, and reduces LPIPS by up to 55.1% compared with the EndoNeRF baseline. --- ### STEREODISCO: Discovering Stereotypicality in LLMs Authors: Farane Jalali Farahani, Corina Dima, Mojtaba Nayyeri, Raphael H. Heiberger, Steffen Staab Published: 2026-07-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.27824v1 LLMs encode, convey, and perpetuate stereotypes. Prior computational research focuses on a small set of semantic axes investigated in social psychology, and operates on word embeddings produced by language models, leaving open which other semantic axes carry stereotypical associations in LLMs and how LLMs internally represent such axes. We introduce STEREODISCO, a framework that adapts the semantic differential method (Osgood et al., 1957) to the systematic study of stereotypes in LLM internal representations. STEREODISCO constructs approx. 2,000 candidate semantic axes from WordNet antonym synsets, recovers each as a geometric axis in the LLM's activation space via probing, and identifies stereotypical axes via a statistical test over concept projections. As a case study, we apply STEREODISCO to social group stereotypes with LLAMA-3-8B-INSTRUCT and MISTRAL-7B-INSTRUCT. We find that the two LLMs agree with each other on social group ratings more than with humans, suggesting that LLM-encoded stereotype content diverges from that documented in social psychology. We also discover stereotypical axes not investigated in prior work -- including humble vs. proud, narrow-minded vs. broad-minded, and cowardly vs. brave, which human annotators independently confirm. --- ### Hallucinations Leave a Grounding Signature:Verifier-Guided Decoding for Selective Object Correction Authors: Lei Yang, Xinze Liu, Dayan Wu, Ding Wang, Hengjie Zhu, Zihao Zhang, Tianzhu Hu, Hanqi Wu, Peng Fu, Zheng Lin Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27823v1 Large vision-language models (LVLMs) often hallucinate objects that are absent from an image. Despite recent progress, existing mitigation methods still lack reliable object-level grounding diagnostics and therefore tend to apply coarse-grained interventions, which can impair visual understanding, shorten responses, and reduce coverage of genuinely grounded objects. The key challenge is thus to detect, during generation, whether each emerging object mention is supported by reliable visual evidence, so that hallucination can be mitigated selectively. Yet output confidence reflects next-token plausibility rather than visual support, allowing language priors to make absent objects appear certain. We show that the missing diagnostic evidence is encoded in an Intrinsic Grounding Signature (IGS), a distributed signed attention pattern that remains informative for such confident hallucinations. Based on IGS, we propose Verifier-Guided Decoding (VGD), a decoding framework in which a lightweight verifier examines each emerging object mention, rolls back the KV cache when the mention is identified as high risk, suppresses the object and its synonyms, and regenerates the affected continuation. Because VGD intervenes only on object mentions identified as high risk, it reduces object hallucination while preserving the model's original visual understanding and grounded object coverage. Experiments on CHAIR and AMBER-G show that VGD achieves state-of-the-art object hallucination reduction: at @rec90, it cuts AMBER-G CHAIR by 43.6\% while retaining 99.6\% of grounded-object coverage, and reduces CHAIR-MSCOCO CHAIR$_i$/CHAIR$_s$ by 37.0\%/30.4\% without shortening captions. --- ### Deep Learning for Accelerated Long-Horizon Forecasting of Multicomponent Multiphase Microstructure Evolution in High-Entropy Alloys Authors: Hamidreza Razavi, Nele Moelans Published: 2026-07-30 Categories: cond-mat.mtrl-sci, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2607.27820v1 Phase-field modeling provides a powerful approach for predicting microstructure evolution but becomes computationally prohibitive for multicomponent and multiphase systems over large spatial and temporal scales. This work presents an AE-GCN-LSTM surrogate framework for long-horizon forecasting of microstructure evolution in the multicomponent AlCrFeNi high-entropy alloy system containing coexisting BCC and FCC phases. A multi-head autoencoder compresses the four elemental concentration fields and phase-field order parameter into latent representations, which are formulated as graphs for learning their spatial and temporal evolution. The framework accurately forecasts microstructure evolution over horizons extending to 3,000,000 simulation timesteps. Its robustness is systematically evaluated under previously unseen conditions without retraining, fine-tuning, or parameter adaptation. These evaluations include variations in FCC precipitate size and initial position, microstructures containing one, two, and five FCC precipitates, and complex phase interactions involving precipitate merging and splitting. Although trained only on 100 x 100 computational domains containing a single nominal alloy composition, the framework is successfully transferred to larger 256 x 256 and 512 x 512 systems and to previously unseen AlCrFeNi compositions. Across the evaluated configurations, the model preserves the dominant phase morphology and compositional evolution while providing computational speedups ranging from approximately 7200 to 62300 relative to conventional phase-field simulations. These results demonstrate that latent graph-based AE-GCN-LSTM forecasting provides a scalable and computationally efficient surrogate for long-horizon simulation of multicomponent, multiphase microstructures and offers a promising foundation for high-throughput alloy design. --- ### Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation Authors: Yuhang Zhu, Mingxuan Du, Benfeng Xu, Jie Gao, Lingyun Yu, Hongtao Xie Published: 2026-07-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.27816v2 Role-playing agents (RPAs) have become one of the most important consumer applications of large language models. Users engage in multi-turn conversations with RPAs for experiences such as emotional comfort, making reliable evaluation essential for measuring capability, comparing systems, and guiding further improvement. Existing benchmarks, however, typically require an RPA to continue a fixed dialogue history and then evaluate the continuation using a fixed rubric detached from the user. We identify and empirically demonstrate two limitations of this design. First, an RPA's output is shaped by the preceding dialogue history, preventing a scientifically grounded assessment of its role-playing ability in real multi-turn settings. Second, user experience varies substantially across individuals, and conventional fixed rubrics need not align with user satisfaction. We therefore introduce PALATE (Person-Aligned LLM-Simulated-User Assessment with Tailored Evaluation), a scalable RPA benchmark built on user simulators. PALATE is accompanied by a pool of 300 character profiles. Its main evaluation trains five per-user simulators and lets them engage candidate RPAs in free-form, multi-turn conversations over a pre-frozen panel of character profiles. Alongside a general quality rubric, we construct personalized rubrics to measure user satisfaction; on held-out annotated data, the personalized rubrics show higher agreement with human judgments than the general rubric. In the main evaluation of 16 candidates, PALATE separately characterizes generic turn quality, long-horizon session capability, and per-user experience on multi-turn trajectories co-constructed by each candidate. It thereby produces interpretable evaluations of specific user-RPA pairs rather than compressing systems into a single user-independent ranking. --- ### Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy Authors: Puning Zhao, Zhikun Zhang, Shaowei Wang, Sheng Yue, Bangzhou Xin, Tianhang Zheng, Pengfei Zhang, Xiaochun Cao Published: 2026-07-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.27815v1 Local differential privacy (LDP) protocols are vulnerable to poisoning attacks. Existing research have proposed efficient defense strategies for single-item users. However, in practice, a user may possess multiple items. The defense against poisoning attacks for multi-item users is challenging, because due to larger output spaces, the adversary can conduct more powerful attacks without being detected. In this paper, we address the robust sparse vector mean estimation problem, in which each user has a vector with $m$ nonzero coordinates. We propose Randomized Projection with Clipping (RPC). Firstly, the server sends a random binary vector to each user. The user then projects its local data on the vector, and clip the value to restrict the attacker's capability. To handle clipping bias, we propose a correction method based on a careful analysis that gives an exact expression of the bias. As a result, bias-variance tradeoff is no longer needed, thus the clipping threshold can be further reduced to shrink the output space and enhance robustness. We provide a rigorous theoretical guarantee of the estimation error under all possible attacks. Numerical experiments show that under trusted environments, our new method achieves comparable or better performance than existing methods, indicating that our method is already an efficient estimator in its own right. Under untrusted environments, our method is also significantly more robust to poisoning attacks. --- ### SPFM-Net: Semantic-Prior-Guided Frequency-Constrained Mamba for Invisible Watermark Attack Authors: Chunpeng Wang, Yanan Shi, Zhiqiu Xia, Jidong Yang, Suo Gao, Qi Li Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27811v1 Existing watermark attacks typically rely on predefined signal-processing operations or locally constrained restoration networks, making it difficult to capture the long-range dependencies of globally distributed watermark signals and resulting in an unfavorable trade-off between removal effectiveness and visual fidelity. In this paper, we propose SPFM-Net, a semantic-prior-guided and frequency-constrained Mamba framework for invisible watermark attack. SPFM-Net first employs high-ratio masking to disrupt the spatial coherence of invisible watermark signals, and then utilizes a partially fine-tuned pretrained Masked Autoencoder to reconstruct semantically consistent image from sparse observations while suppressing watermark-related information. A Multi-scale Residual Frequency Feature Interaction module subsequently aggregates watermark-related residual features across multiple receptive fields, while adaptively suppressing responses from watermark-irrelevant regions. To further capture the long-range dependencies of globally distributed watermark signals, a lightweight Mamba-based Global State-space Feature Modeling (GSFM) unit is introduced to separate watermark-related features from natural image content and suppress the remaining watermark traces. In addition, SPFM-Net is optimized using a multi-level objective that jointly imposes spatial-, frequency-, and edge-domain constraints, enabling effective watermark suppression while preserving perceptual quality. Extensive experiments on representative spatial-domain, transform-domain, orthogonal moment-based, and deep learning-based watermarking schemes demonstrate that SPFM-Net achieves a favorable trade-off between watermark attack effectiveness and perceptual fidelity. --- ### Learning-Augmented and Randomized Algorithms for Line Aggregation with Delays Authors: Tianhang Lu, Runtian Ren, Shengcai Liu, Ke Tang Published: 2026-07-30 Categories: cs.LG, cs.CC arXiv: https://arxiv.org/abs/2607.27807v1 This paper studies learning-augmented and randomized online aggregation with delays on a line metric. We consider advice given as online suggested service lengths, and evaluate the algorithms in terms of robustness and consistency. For each $λ\in (0,1)$, we first propose a deterministic learning-augmented \textsc{Balance} algorithm that is $(4/λ+1/λ^2)$-robust and $(4+λ)$-consistent. We also propose a randomized algorithm for the problem in the classical adversarial model, which is $(e+1)$-competitive against an oblivious adversary, improving over the deterministic $5$-competitive \textsc{Balance} benchmark~\cite{bienkowski2013chain}. Notably, this competitive ratio is even lower than the lower bound of $4$ for deterministic online algorithms. Moreover, we establish a lower bound of $e$ on the competitive ratio of randomized online algorithms, improving the previous lower bound of $e/(e-1)$. Besides, we combine the two ideas and obtain a randomized learning-augmented algorithm that is $(e/λ+1/λ^2)$-robust and $(e+λ)$-consistent. Finally, we conduct numerical experiments to complement our theoretical analysis and evaluate the empirical performance of our algorithms. --- ### LoMeVQA: A Comprehensive Benchmark for Longitudinal Medical VQA Authors: Zhilin Wu, Zhangkai Ni, Chengmei Yang, Longzhen Yang, Yihang Liu, Ying Wen, Lianghua He Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27806v1 In clinical practice, patients often undergo multiple imaging examinations over successive visits, yielding longitudinal data. Modeling such temporal information is crucial for reliable assessment of disease progression and treatment response. However, despite the rapid advancement of multimodal large language models (MLLMs), longitudinal medical visual reasoning remains largely underexplored. To fill this gap, we propose LoMeVQA, a comprehensive benchmark consisting of 206K longitudinal visual question answering (VQA) pairs for temporal medical image analysis. LoMeVQA covers five tasks: progress classification, progress description, progress report generation, differential region grounding, and differential region description. To construct the dataset, we develop an automated pipeline that (1) organizes patient records chronologically, (2) extracts clinically meaningful entities via a medical knowledge graph, and (3) models their temporal evolution to guide large language models in generating high-quality longitudinal VQA pairs. Extensive evaluations demonstrate that both general-purpose and medical-domain MLLMs perform poorly on LoMeVQA, revealing substantial limitations in temporal reasoning. To address these limitations, we introduce MedLong-8B, which achieves state-of-the-art performance across all tasks. Beyond benchmarking, we conduct detailed analyses that uncover key failure modes and shed light on how to improve longitudinal medical visual reasoning. Our data is available at: https://github.com/pepperbubble/LoMeVQA --- ### FDDWAN: A Frequency-Decoupled Diffusion Network for Watermarking Attack Authors: Chunpeng Wang, Yuxin Li, Xiaoyu Wang, Jidong Yang, Suo Gao, Qi Li Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27800v1 Existing invisible watermark removal methods often struggle to accurately capture the watermark-bearing features, leading to an unfavorable trade-off between watermark suppression and perceptual fidelity. In this paper, we propose the Frequency-Decoupled Diffusion Watermark Attack Network (FDDWAN), a coarse-to-fine framework that performs watermark removal through wavelet-domain decomposition and residual diffusion refinement. In the initial stage, the Wavelet-based Frequency-domain Preliminary Attack Module (WFPAM) decomposes the watermarked image into low- and high-frequency subbands and applies frequency-specific attack strategies tailored to their respective contributions to watermark robustness and perceptual quality. In the next stage, the Frequency-domain Residual Diffusion Attack Module (FRDAM) separately models the residual distributions between the preliminarily attacked outputs and the corresponding watermark-free references during training. Rather than reconstructing the entire image, FRDAM selectively refines frequency-domain residuals, directing the diffusion process toward the remaining watermark related discrepancies while minimizing modifications to image content. Extensive experiments on CelebA and ImageNet across four representative watermarking schemes demonstrate that FDDWAN achieves a more favorable trade-off between watermark removal effectiveness and visual fidelity than conventional and learning-based attack methods. --- ### MemeBench: What LVLMs Miss When Interpreting Culture-Dependent Memes Authors: Weihang Wang, Kainan Tu, Jielei Zhang, Run Yang, Boheng Sheng, Yuchen He, Yu Xie, Pengyu Chen, Peiyi Li, Huyang Sun, Longwen Gao, Zhouhui Lian Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27798v1 Large vision-language models have improved at describing visual content, but accurate descriptions do not ensure interpretation when meaning depends on knowledge beyond the pixels. Memes expose this gap because they rely on cultural entities, background knowledge, and community conventions. Most meme benchmarks reduce interpretation to labels or holistic scores, obscuring where an explanation breaks down. We introduce MemeBench, a diagnostic benchmark of 1,253 Chinese and English memes with human-written references and quality-controlled VIKR annotations, centered on anime, comics, games, and adjacent online subcultures. Its VIKR schema decomposes explanations into Visual clues, Identity links, Knowledge units, and Reasoning mechanisms. Across 26 LVLMs, every model covers visible content more reliably than the knowledge needed to interpret it, and even the strongest retains a 22.6% Visual-Knowledge gap. To test whether this diagnosis can guide improvement, we introduce KAR, an entity-guided retrieval baseline built on CultureBase. Across four controlled models, KAR raises VIKR Success by 3.6-7.4% and, compared with generic retrieval, repairs more answers and breaks fewer. Yet both retrieval conditions improve Identity and Knowledge while reducing Visual coverage in every comparison. MemeBench reveals whether an interpretation succeeds, what is missing, and whether targeted evidence fills the diagnosed gap. --- ### Revisiting Predictive Process Monitoring in the Age of Foundation Models: A Comparative Study of Sequence, Tabular, and LLM Approaches Authors: Lennart Fertig, Lukas Kirchdorfer, Tobias Sesterhenn Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27797v1 Predictive process monitoring (PPM) leverages event logs to forecast the future of running process instances, for instance, predicting the next activity, the remaining time until case completion, or the time to the next event. While PPM research in recent years has been dominated by deep sequence models trained from scratch, such as Long Short-Term Memory (LSTM) models, foundation-model approaches---particularly large language models (LLMs)---are increasingly explored for PPM. At the same time, tabular foundation models with in-context learning capabilities offer a promising alternative but have not yet been systematically benchmarked for PPM. Thus, it remains unclear whether classical sequence-based models remain competitive in this evolving landscape. This paper compares the three modeling paradigms both conceptually and empirically through a controlled benchmark across multiple datasets and prediction tasks. The results show that sequence models consistently perform best for next activity prediction, whereas tabular foundation models are competitive on temporal tasks, with LLMs usually lagging behind despite higher cost. --- ### Can AI Follow In Einstein's Footsteps? Authors: Michael Shalyt, Nathan Regev, Marin Soljačić, Ido Kaminer Published: 2026-07-30 Categories: physics.hist-ph, cs.AI, physics.pop-ph arXiv: https://arxiv.org/abs/2607.27794v1 AI is accelerating physics discovery, but perhaps away from Einstein-level theory building. To understand this gap, we must recognize a striking trend: while being very successful, the most visible AI contributions to physics discovery appear to mirror the historical development of physics, but in reverse. Human discovery in physics progressed, in broad strokes, from ancient pattern prediction, through phenomenological laws such as Kepler's, to principle-based universal theories such as relativity and the Standard Model. On the AI side, prominent contributions to physics discovery point in the opposite direction: early milestones emphasized explicit equation-discovery methods, such as symbolic regression, whereas more recent frontier contributions are powerful predictors such as AlphaFold and GraphCast, which can be remarkably accurate yet do not provide clear theoretical understanding. If this trend continues, AI would become extraordinarily good at prediction but may struggle to ever propose its first serious contender to quantum gravity or other paradigm-level theories. We review the current landscape of AI for physics discovery and highlight a critical missing skill: the ability to pose the right questions or invent the right principles to guide the development of new theories and the tests to falsify them. This mode of discovery has driven many of the deepest advances since the 17th century, where symmetry, simplicity, and new mathematical frameworks guided theory construction before experimental tests. Equipping AI systems with such skills could move them from predicting within known frameworks to proposing the next paradigm-level discovery in physics. --- ### Annotating Topical Legal Insights from Case Proceedings Authors: Subinay Adhikary, Dwaipayan Roy, Debasis Ganguly, Shouvik Kumar Guha, Kripabandhu Ghosh Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27792v1 In this paper, we mainly concentrate on finding concepts or topics from the legal case proceedings, since adopting a structured representation for legal documents, as opposed to a mere bag-of-words flat text representation, can significantly enhance processing capabilities. To achieve this objective, we put forward a set of diverse concepts for legal case proceedings. With this motivation, we propose LeDA, a system for Legal Data Annotation. The system offers the generic functionality of annotating and adjudicating entities or concepts within documents via a web-based interface. A novel feature of our system is that it allows to dynamic create new tags for annotation, which is a particularly useful provision for situations where there exists no pre-defined ontology for the entities (concepts) that need to be annotated - these being rather discovered by annotators as they continue examining more documents. The system that we demonstrate is currently in use to annotate a set of concepts from legal documents to construct semantic representations of documents as bags of concepts that can then be used for several downstream tasks, such as prior case retrieval, judgment prediction, and so on. Along with the system features in general, we also describe how LeDA was used by 3 assessors to annotate and adjudicate legal concept names from Indian Supreme Court case proceedings. --- ### Semantic-Aligned Structural Abstraction for Multimodal Sentiment Analysis Authors: Wei Chen, Junkai Li, Tongguan Wang, Hui Liu, Feiyue Xue, Chuanxiang Ma, Ying Sha Published: 2026-07-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.27790v1 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{https://github.com/especiallyW/SentiLLM}. --- ### SpecCal: Ambiguity-Aware Candidate Calibration for Infrared Spectrum-Based Molecular Structure Reconstruction Authors: Yixuan Chen, Bo Liu, Yusen Tan, Guokun Yang, Wenjie Du, Jun Xia Published: 2026-07-30 Categories: cs.AI, cs.CE arXiv: https://arxiv.org/abs/2607.27788v1 Inferring molecular structures from infrared (IR) spectra is a fundamental yet challenging problem. A key difficulty is that an IR spectrum provides limited structural information: different molecules may share similar functional groups and local vibrational patterns, leading to highly similar spectral responses. Thus, even when an observed spectrum has a unique underlying structure, reconstructing it from the spectrum remains ambiguous. Existing IR-to-molecule models usually generate a ranked set of candidate molecules, but this set is largely determined by the model's learned generation preference and may not fully capture the structures that best satisfy the observed spectral constraints. To address this limitation, we propose SpecCal, a training-free candidate calibration framework for IR-to-molecule prediction. SpecCal operates on the candidate outputs of existing base models and improves the prediction set by re-ranking current candidates while introducing additional structurally plausible alternatives guided by spectral consistency. The framework is plug-and-play and model-agnostic, requiring no parameter updates for integration with diverse base models. Experiments on multiple benchmarks show that SpecCal consistently improves top-k reconstruction at both SMILES and scaffold levels across different base models. Further analyses demonstrate that calibrating candidate sets under spectral ambiguity provides a practical way to improve molecular reconstruction from IR spectra. The code is available at: https://anonymous.4open.science/r/SpecCal-B18A. --- ### LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Authors: Ken Ding Published: 2026-07-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.27787v1 Reinforcement learning from verifiable rewards (RLVR) for mathematical reasoning suffers from a structural blind spot: on "cliff" prompts-those on which every sampled rollout in a group fails-the group-normalized advantage is identically zero, so GRPO produces no gradient on precisely the prompts at the frontier of the model's capability. We introduce LoRA Scaffolded Policy Optimization (LSPO), a sampling-time mechanism that recovers this lost gradient. Each RL step, LSPO detects cliff prompts, fits a small low-rank (LoRA) adapter by a brief supervised step on their ground-truth solutions, re-rolls the cliffs with the base-plus-adapter model, splices the now-successful completions back into the RL batch with an importance-sampling correction, and takes a GRPO step on the base alone; the adapter receives only the supervised gradient and is discarded at checkpoint, yielding a base-only model. On DeepMath-103K with DeepSeek-R1-Distill-Qwen-1.5B, evaluated over n=5 paired seeds per arm at a matched 1000-step reporting horizon, LSPO's 5-seed mean matches or beats a DAPO baseline on all 16 (benchmark, pass@k) cells (15 strict wins and one exact tie), with gains of up to +10.7 points on AIME24/pass@4, +6.7 points on AIME24 and AIME26 at pass@16, and +2.4 points on MATH500/pass@1; averaged over the 16 cells the improvement is +3.8 points. --- ### Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation Authors: Amruta Parulekar, Jinu Lee, Dilek Hakkani-Tür, Hari Sundaram Published: 2026-07-30 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.27783v1 Large Language Models (LLMs) explore problems through chain-of-thought, but this exploration is buried in unstructured prose. On high-stakes tasks, users cannot tell which steps are well-supported, which alternatives were seriously considered, or how the final conclusion compares to those the model discarded. We propose a framework that ensembles the reasoning structure, not just the answers, of multiple LLMs by weighted merging of Directed Acyclic Graphs (DAGs) extracted from reasoning chains. We weight each step by how many traces independently attest to it, to return "Consensus Reasoning". Across six benchmarks spanning statutory interpretation, graduate-level science, narrative multi-hop reasoning, and first-order logic, our ensemble outperforms a matched-budget majority-vote baseline, with a maximum accuracy gain of 3.1% on MuSR-MM (narrative multi-hop reasoning). On a single model, the framework matches or exceeds self-consistency at the same trace budget while additionally exposing an inspectable consensus reasoning graph. Ensemble weights correlate with LLM-judge rankings of reasoning quality at Spearman $ρ= 0.30$-$0.51$, and consensus subgraphs are preferred over alternatives leading to the majority-vote answer in 54.4-65.4% of head-to-head comparisons across five of six datasets. We observe that our framework can also be used to analyze diverse reasoning perspectives for a problem. --- ### RedFlow: Redirect Failure into Action-level Corrections for Flow-matching VLA Policy Authors: Zhengyang Yan, Junhao Li, Fangqi Zhu, Zijun Wang, Quanxin Shou, Yikun Miao, Xiaoyi Pang, Zicong Hong, Song Guo Published: 2026-07-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.27782v2 Reinforcement learning (RL) can improve Vision-Language-Action (VLA) policies from deployment experience, but reward- and preference-based RL primarily identifies desirable behaviors without specifying how to correct failed actions, underutilizing failure trajectories and limiting sample efficiency. Can such corrections be derived from fixed rollouts? Our key insight is that rollouts with different outcomes may contain action chunks executed in similar states, enabling higher-quality chunks to provide locally supported corrective references. Building on this insight, we introduce \textbf{RedFlow}, an offline post-training method for flow-matching VLA policies. \emph{Execution-Context Matching} groups chunks using a compact representation of estimated task progress and robot proprioception. \emph{Quality-Guided Action Redirection} assigns signed chunk-quality scores and aggregates higher-quality chunks into corrective targets, reinforcing high-quality chunks, suppressing low-quality chunks, and redirecting correctable chunks toward their targets. RedFlow requires neither external HIL corrections nor online data collection during post-training. Across four LIBERO suites, RedFlow improves average success from 56.2\% to 68.2\%, outperforming the strongest evaluated offline baseline, AWR (62.3\%), by 5.9 points. Across three real-robot tasks, it improves average success from 56.7\% to 74.7\%. On LIBERO-Spatial, RedFlow reaches 75.8\% success with 1{,}536 fixed rollouts, while the evaluated online methods require 8.7--16$\times$ as many fresh post-training rollouts to reach the same threshold. --- ### RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy Authors: Zhengyang Yan, Junhao Li, Fangqi Zhu, Zijun Wang, Quanxin Shou, Yikun Miao, Xiaoyi Pang, Zicong Hong, Song Guo Published: 2026-07-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.27782v1 Flow-matching Vision-Language-Action (VLA) policies have shown strong potential for robotic manipulation but often suffer from compounding errors caused by distribution shifts during deployment. While offline reinforcement learning (RL) provides a practical way to improve deployed policies using rollout data, existing methods either ignore failure data or exploit it only at the trajectory level, resulting in low learning efficiency and persistent errors. We propose **RedFlow**, a fine-grained offline RL framework that redirects failure experiences into action-level corrective supervision for flow-matching VLA policies. RedFlow consists of two key components: (1) a **Context-Aware Corrective Matching** mechanism that identifies failure-inducing actions and retrieves successful alternatives from similar contexts as corrective targets, and (2) an **Adaptive Redirection Objective** that jointly reinforces successful actions, suppresses undesirable ones, and redirects recoverable failures toward corrective targets. By converting both successful and failed experiences into dense supervision, RedFlow enables robust recovery learning from mixed-quality data. Experiments on the LIBERO benchmark and three real-world manipulation tasks show that RedFlow consistently outperforms state-of-the-art offline RL baselines, improving the real-world success rate from 56.7% to 74.7%. It also matches strong on-policy methods (PPO, GRPO, and DDPO) while requiring roughly an order of magnitude fewer training samples. --- ### Fractional Parabolic Partial Differential Equations in Anisotropic Spectral Barron Spaces: Regularity and Neural Approximation Authors: Jae-Hwan Choi, Hyojae Lim, Jinsol Seo, Young-Jin Sim, Changhoon Song Published: 2026-07-30 Categories: math.AP, cs.LG arXiv: https://arxiv.org/abs/2607.27781v2 We study fractional parabolic initial-value problems with lower-order drift and potential terms in anisotropic spectral Barron spaces, defined by weighted space--time Fourier $L^1$ norms adapted to parabolic scaling. We prove existence, uniqueness, and maximal regularity with a gain of one derivative in time and $γ$ derivatives in space, where $γ>0$ is the order of the fractional Laplacian. The evolution is defined only for $t\geq0$, whereas the finite-time norm requires a global extension with sufficient temporal Fourier decay. We construct a finite reflected semigroup extension using a Vandermonde system to match derivatives at $t=0$, obtaining temporal Fourier estimates uniform in the semigroup parameter. Combined with Fourier multiplier estimates for the damped principal operator, it yields maximal regularity. Dimension-independent multiplication estimates support a finite regularity bootstrap, while interpolation and sufficient damping absorb the lower-order terms in the base estimate. The a priori estimate and the method of continuity yield maximal regularity without smallness assumptions on the lower-order coefficients. A frequency-localized counterexample shows that a uniform-in-time spatial Barron bound on the forcing does not imply the corresponding two-derivative solution bound, even for the one-dimensional heat equation. Using this regularity, Fourier sampling yields $n^{-1/2}$ approximation rates for the solution in mixed space--time Sobolev norms using shallow networks with suitable activations. Sampling in a product Hilbert space yields a population-level PINN consistency estimate for shallow cosine networks on a bounded cylinder. There exists a single width-$n$ network for which the sum of the squared mixed-Sobolev solution error, the squared $L^2$-norm of the residual for the whole-space fractional equation, and the squared initial-data error is $O(n^{-1})$. --- ### Neural Network Approximation of Solutions to Fractional Parabolic Partial Differential Equations Authors: Jae-Hwan Choi, Hyojae Lim, Jinsol Seo, Young-Jin Sim, Changhoon Song Published: 2026-07-30 Categories: math.AP, cs.LG arXiv: https://arxiv.org/abs/2607.27781v1 We establish a dimension-efficient neural network approximation theory for solutions to fractional parabolic equations with lower-order drift and potential terms. By introducing anisotropic spectral Barron spaces, which measure temporal and spatial regularity separately in frequency space, we first develop a dimension-independent maximal regularity theory for these equations, using dimension-independent multiplication estimates and the method of continuity to incorporate the lower-order terms. A key technical novelty is the application of the Vandermonde matrix to the global-in-time extension of the finite-time fractional heat semigroup with sufficient regularity at the initial time, thereby enabling analysis of the forward-in-time evolution via the global space-time Fourier structure of anisotropic Barron norms. We also show that a corresponding uniform-in-time estimate of the spectral Barron regularity generally fails. Finally, we derive $n^{-1/2}$ two-layer approximation bounds in mixed Sobolev norms for non-constant periodic activations and, under additional anisotropic Barron regularity, for non-periodic activations satisfying a polynomial-decay condition. --- ### CXR-Retrieve: Compositional Text-to-Image Retrieval in Chest Radiography Authors: Tomer Erez, Moshe Kimhi, Chaim Baskin, Ehud Rivlin Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27779v1 Large chest radiography archives are difficult to search because most studies are paired only with free-text reports rather than structured clinical annotations. Vision-language models offer a natural interface for text-to-image retrieval, but current biomedical models are primarily optimized for report-to-image matching rather than for satisfying short clinical search queries. This creates an objective mismatch: a model may retrieve images related to words in the query while failing to satisfy the full clinical constraint, especially for conjunctions and negations such as ``atelectasis and no pneumonia.'' We introduce CXR-Retrieve, a structured benchmark for compositional chest X-ray text-to-image retrieval. The benchmark contains 5,159 test images from the official test-split of MIMIC-CXR-JPG and 145 textual queries spanning single and conjunction findings, both positive and negative. Relevance is defined by whether a retrieved image satisfies all asserted pathology constraints, rather than by whether it matches a paired report. We further propose a label-aware contrastive fine-tuning objective for clinical retrieval. Our method attracts image-text pairs with compatible asserted pathology constraints, including shared confirmed absences, while explicitly repelling contradictory pairs. Starting from the in-domain CXR-CLIP checkpoint, our method improves Precision@5 over CXR-CLIP by 8.5 percentage points on two-pathology conjunctions and by 22.0 percentage points on negation queries. These results show that reliable chest X-ray retrieval requires training objectives that model not only which findings are mentioned, but also how they are clinically asserted. --- ### RIPPLE: Generating Multi-Channel Phase, Not Recovering It Authors: Jaehyuk Lee, Yeajin Lee, Dayeon Shin, Donghun Lee Published: 2026-07-30 Categories: cs.LG, cs.SD arXiv: https://arxiv.org/abs/2607.27775v2 Generative models synthesize magnitude spectra with high fidelity, while phase is delegated to a recovery module---Griffin--Lim, a vocoder, or a latent decoder---applied independently to each channel. For multi-channel waveforms this delegation is costly: the physical content of spatial audio and three-component seismograms lives in the phase relationships between channels, precisely what channel-independent recovery cannot produce. The cost is also invisible, since the magnitude-based metrics common to both fields barely move when inter-channel phase coherence collapses---so a pipeline can discard the physical information in its output while still scoring well. We argue that phase should be generated, not recovered, and present RIPPLE (Rectified Inter-channel Phase with Prior-based LEarning), which reinterprets Griffin--Lim as a phase **prior** rather than a final estimator: initialized from the source phase, this prior carries the inter-channel structure to be preserved, and a rectified flow refines it toward the target under an explicit inter-channel phase loss. Tested on first-order ambisonics environment transfer and seismic cross-station translation---two physically unrelated domains---RIPPLE outperforms recovery-based pipelines on the coherence metrics that downstream analyses consume. The seismic case is decisive: across architecturally distinct generators, per-channel recovery leaves S-wave polarization error near the $57.3^\circ$ random expectation, whereas learned phase reduces it to $33.8^\circ$. --- ### ChronoMem: Version Control and Semantic Rollback for Large Language Model Agent Memory Authors: Yongye Su, Wujiang Xu, Chaoji Zuo, Elisa Bertino Published: 2026-07-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.27773v2 LLM agents increasingly rely on long-term memory to support multi-session interaction and personalization. However, existing agent memory systems are designed around forward-only evolution, continuously accumulating, consolidating, and overwriting knowledge, with no principled mechanism to inspect, version, or revert prior states. This makes agents brittle under corrections, concept drift, and memory corruption, particularly after they have already been exposed to subsequent information. We present ChronoMem, a semantic version-control layer for agentic memory integrated into the production-ready, open-source Agent Development Kit by Google. ChronoMem commits whole-memory snapshots at each memory write, maintains structured version histories, and supports natural-language rollback requests by mapping undo intents to concrete historical versions through hybrid lexical and semantic retrieval, rank fusion, and reranking. We further introduce a post-exposure evaluation protocol that tests whether an agent can behave counterfactually after rollback by answering queries and summarizing history as if future updates had never occurred. On long-horizon conversational benchmarks augmented with evolving memory states and rollback tasks, ChronoMem substantially improves rollback-consistent question answering and history summarization relative to prompt-only and retrieval-only baselines, while achieving strong performance in semantic version selection. To our knowledge, ChronoMem is the first open-source system and benchmark for systematic semantic global memory rollback in LLM agents. --- ### Beyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold Authors: Songshuo Lu, Zhi Chen, Yaohua Tang Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27770v1 A single reinforcement-learning run can produce a strong reasoner yet an incomplete teacher: it often amplifies only a subset of the valid solution modes. We argue that reinforcement learning (RL)-trained policies should therefore be viewed as local probes of a multi-basin reasoning solution manifold, rather than as globally reliable supervisors. Based on this view, we propose an expand-then-compress framework that couples teacher construction with multi-teacher policy distillation. In the expansion stage, Residual Group Relative Policy Optimization (RGRPO) trains a sequence of teachers from a common initialization and redirects each later round toward examples not yet covered by the accumulated teacher union. In the compression stage, reliability-gated Teacher-Union On-policy Distillation (TU-OPD) lets the student learn from its own response prefixes. For each example, only reliable teachers contribute, and their sampled-token OPD losses are weighted by their per-example quality. We further introduce Consensus-Residual Decomposition, which preserves a winner teacher's excess token preferences over its reliable peers, preventing specialist behavior from being suppressed during teacher aggregation. Experiments on mathematical reasoning, code generation, and instruction following show that the resulting Qwen3-1.7B student consistently outperforms the strongest individual teacher across all three domains, yielding relative improvements of 2.0%, 8.3%, and 6.9%, respectively, while retaining single-model inference. These results establish a simple but powerful principle: stronger students can be obtained not by selecting a single better teacher, but by deliberately constructing and compressing a complementary teacher union. --- ### VocalRender: Score-Native Singing Voice Synthesis for Real-World Composition Authors: Yukun Chen, Tianrui Wang, Zhaoxi Mu, Xinyu Yang, EngSiong Chng Published: 2026-07-30 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2607.27768v1 Existing singing voice synthesis systems often require predefined durations, explicit duration prediction, or time-aligned acoustic guidance, which limits their compatibility with practical composition workflows. We propose VocalRender, a score-native system that directly synthesizes singing from lyrics, pitches, symbolic note values, and tempo. It uses an interleaved lyric--note representation and an autoregressive diffusion model to generate continuous acoustic latents while predicting the output length, eliminating the need for explicit duration prediction. Trained on a 2,300-hour singing dataset, VocalRender achieves strong intelligibility, strong melody control, and high speaker similarity across both in-domain and out-of-domain benchmarks. Notably, it outperforms the strongest baseline by $0.42$ points in naturalness CMOS, demonstrating the effectiveness of our proposed score-native architecture. --- ### Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization Authors: Robert Jankowski, Pedro Almagro-Blanco, Marián Boguñá, Melanie Weber, M. Ángeles Serrano Published: 2026-07-30 Categories: cs.LG, cs.AI, physics.soc-ph arXiv: https://arxiv.org/abs/2607.27767v1 Graph neural networks (GNNs) can operate on large graphs but become infrastructure-sensitive at the scale of millions of nodes and typically require scalable training techniques for even larger graphs. This raises a central question: when can a model trained on a smaller, scaled-down replica of a graph be deployed on the full-resolution graph without retraining? We introduce a zero-shot transfer protocol in which a GNN is trained on a graph coarse-grained by geometric renormalization (GR), and the resulting weights are transferred directly to the original network. Across synthetic and real-world networks, training on GR scaled-down replicas preserves much of the original-scale predictive performance while significantly reducing training cost. We further find that learned representations and predictive trajectories remain aligned across scales. These findings suggest that structural similarity may be more important than network size in determining GNN transferability, opening a path toward scale-equivariant graph architectures. --- ### Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning Authors: Xinyu Luo, Hui Liu, Yihua Shao, Junyi Yang, Arindam Basu, Haoliang Li Published: 2026-07-30 Categories: cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2607.27766v1 On-device in-context learning (ICL) relies on pre-inference retrieval to select demonstrations for useful context before downstream model inference. This retrieval must exploit task-specific information while operating over local memories under limited computation, memory, and data-exposure budgets. We propose Conditional Retrieval Alignment (CoRA), a gradient-free framework that converts a frozen encoder into a task-conditioned retriever using paired candidate inputs and outputs. CoRA selects complementary encoder layers, constructs an output-derived conditioning space from candidate memory, and aligns candidate input representations to this space through closed-form ridge regression. Low-rank factorization then produces a compact retrieval basis where candidate outputs are used only during offline index construction, whereas query-time retrieval requires only the query input and precomputed index. We show that CoRA's rank-constrained basis is the optimal low-rank compression of the output-conditioned fitted representation, and derive an exact two-pass streaming construction that avoids materializing the full fitted matrix. We further extend the framework to multimodal exemplar retrieval by incorporating visual representations into the conditioning and retrieval spaces. Experiments across ten textual datasets and four multimodal benchmarks with Llama-3.2-1B, MobileLLM-Pro, OpenFlamingo-3B, and Qwen3.5-2B, as well as end-to-end Raspberry Pi~5 deployment demonstrate that CoRA supports effective task-conditioned retrieval without retriever fine-tuning, backpropagation, or target-model calls. --- ### Private Face Recognition Training Dataset Publication via Identity-Decoupled and Geometry-Preserving Face Distillation Authors: Shuhuan Chen, Xiangyu Zhu, Weisong Zhao, Siran Peng, Tianshuo Zhang, Haoyuan Zhang, Haichao Shi, Xiao-Yu Zhang, Zhen Lei Published: 2026-07-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.27764v1 Publishing private face recognition~(FR) training datasets is privacy-sensitive because faces expose identity information. Private FR training dataset publication mitigates this risk by releasing protected proxies as substitutes for private training faces. However, training FR models with such data introduces an identity paradox: \emph{the identity cues that make released faces useful for recognition supervision are also the cues that make them linkable to real individuals.} A protected face should be decoupled from the original identity, yet still behave as a reliable identity sample for training. Removing these cues too aggressively may destroy the class structure needed for recognition learning, whereas preserving them too faithfully may increase source-identity linkability. We argue that this paradox stems from conflating source-aligned identity semantics with recognition-useful proxy identity geometry. The former should be suppressed to reduce linkage to private individuals, while the latter should be preserved for FR learning. Based on this insight, we propose \textbf{Private Face Distillation}, an identity-decoupling and geometry-preserving framework. It uses Orthogonal Geometry Preservation to construct decoupled proxy identities from private identity representations while maintaining hyperspherical geometry, and Relational Topology Alignment to preserve identity relations for recognition learning. Experiments across multiple domain-shifted FR scenarios show that Private Face Distillation achieves stronger utility than the evaluated publication baselines. On IJB-C surveillance, it improves $\mathrm{TAR}@\mathrm{FAR}{=}1\text{e-}{3}$ by 3.94\% over the baseline while reducing source-identity linkability. These results suggest that private FR training dataset publication should decouple source-identity correspondence while preserving proxy identity geometry. --- ### DS@GT ARC at ImageCLEFmedical 2026: Architectural Diversity for Concept Detection and Foundation-Model Scaling for Caption Prediction in Medical Image Analysis Authors: Bowen Wang, Youwen Zhang, Ritesh Mehta Published: 2026-07-30 Categories: cs.CV, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2607.27763v1 We describe the DS@GT submissions to the ImageCLEFmedical Caption 2026 challenge, which continues a long-running benchmark on the ROCOv2 dataset with two tracks: Concept Detection (Task 1), assigning UMLS Concept Unique Identifiers (CUIs) to radiology images, and Caption Prediction (Task 2), generating natural-language captions. For Task 1, our primary submission was a three-way late-fusion ensemble of ConvNeXt-V2, BiomedCLIP ViT-B/16, and DenseNet-169 with a regularized ''Honest Threshold Tuning'' procedure designed to avoid validation overfitting on rare concepts; this submission ranked first on the official submission with a primary $F_1$ of $0.5790$ and a secondary $F_1$ of $0.9657$. In parallel, we submitted a training-free KNN retrieval pipeline over frozen BiomedCLIP embeddings, which reached a primary $F_1$ of $0.5780$ and a secondary $F_1$ of $0.9599$-essentially matching the fine-tuned ensemble on the primary track at a fraction of the cost. For Task 2, our submissions included a fine-tuned Gemma-3 27B model (overall $0.3571$, ranking third in the official submission), a fully fine-tuned BLIP pipeline with custom Vizwins merging ($0.3564$), and a zero-shot MedGemma-4B run with a PubMed-style prompt ($0.3186$), spanning a wide range of model scales and training costs. Code: https://github.com/dsgt-arc/imageclef-caption-2026. --- ### DAS-PMVC: A Framework for Partial Multi-View Clustering via Dual Alignment and Structure Enhancement Authors: Shubin Ma, Liang Zhao, Chuanye He, Zhenjiao Liu, Liang Zou, Lin Yuanbo Wu, Yu Shao Published: 2026-07-30 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2607.27761v1 In recent years, multi-view clustering has attracted widespread research interest. However, due to limitations in data collection devices, data across different views often suffer from misalignment, leading to the partial view alignment problem (PVAP). To mitigate the impact of view asymmetry and irrelevant samples, this paper proposes a framework for partial multi-view clustering via dual alignment and structure enhancement (DAS-PMVC), which leverages view structure consistency and semantic relevance. Specifically, DAS-PMVC includes three parts: \textbf{anchor graph structure alignment}, where sample joint embedding representations with consistent latent space are derived from anchor point relationships for initial view alignment; \textbf{structure-enhanced feature learning}, where the model learns view structure information through pretraining and combines multi-view graph convolutional networks to further extract deep latent features from the aligned graph structure to improve the discriminative power of representations; and \textbf{a dual alignment strategy}, where initial alignment is performed through the anchor graph in the pretraining phase, and contrastive learning loss and the Hungarian algorithm are introduced in the training phase to further optimize the alignment of latent features. Experimental results on various datasets demonstrate that the DAS-PMVC framework outperforms existing state-of-the-art methods in clustering performance, showcasing its effectiveness and superiority. --- ### Hierarchical Latent Reasoning for LLM-based Recommendation Authors: Peiyu Hu, Siying Gu, Weihai Lu, Zhuodong Liu, Yuntian Tang, Jiahao Liang, Yiying Xie, Jiang Rong, Zhaokai Luo, Zhiyong Wang, Jia Wang Published: 2026-07-30 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2607.27760v1 Large Language Models (LLMs) have shown strong potential for recommendation by leveraging their semantic understanding and contextual modeling capabilities. Recent studies further introduce reasoning mechanisms to improve user preference modeling. However, explicit natural-language reasoning incurs substantial inference overhead, whereas existing latent reasoning methods mainly focus on generating or verifying intermediate states, leaving their layer-wise preference roles and contributions insufficiently characterized. We propose HiLaR, a Hierarchical Latent Reasoning framework with layer-aware reinforcement optimization for LLM-based recommendation. HiLaR constructs temporal-guided hierarchical user preference representations, aligns them with multiple LLM latent reasoning states, and organizes the reasoning process from broad preferences to fine-grained current intents. To further optimize the reasoning trajectory, HiLaR combines final recommendation feedback with layer-aware process rewards derived from the marginal target-likelihood gain of each state. Experiments on four Amazon benchmark datasets show that HiLaR generally outperforms strong sequential, generative, and LLM-based recommendation baselines. Ablation and sensitivity analyses further verify the contribution of hierarchical representation learning, latent alignment, and process-level optimization. Our code is available in https://github.com/hupeiyu21/HiLaR. --- ### Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Authors: Xilin Jiang, Riki Shimizu, Sukru Samet Dindar, Junkai Wu, Zhongweiyang Xu, Nima Mesgarani Published: 2026-07-30 Categories: cs.SD, cs.CL, cs.MM, eess.AS arXiv: https://arxiv.org/abs/2607.27756v1 Spoken dialog systems are typically designed for clean, dyadic interactions in which a single user and an assistant take turns speaking. Real-world social conversations, however, are often more ambiguous: multiple speakers may participate in the same conversation amid irrelevant speech and background noise. Each utterance may be directed to the assistant, addressed to another speaker, or completely irrelevant. In such settings, the assistant must decide not only what to say, but also whether to speak at all. In this paper, we introduce Cocktail-Talker, a speech LLM framework for multi-speaker spoken dialog modeling in noisy social environments. We model the assistant's behavior with three action tokens: <|respond|>, <|listen|>, and <|ignore|>, placed before a response or silence. Cocktail-Talker is trained via supervised finetuning and reinforcement learning to generate the appropriate action token and, only in <|respond|> mode, a speech response. To prepare the training data, we develop Cocktail-DialogGen, an LLM-based data pipeline that simulates realistic multi-speaker dialogs with speaker roles across diverse social settings. Together, these components take a step toward spoken dialog systems that interact more naturally and selectively in complex social environments. --- ### EgoGVAE: Ego-body Mesh Reconstruction via Guided Variational Autoencoder Authors: Jaehun Jung, Wonjun Kim Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27755v1 We address the problem of recovering the full-body mesh from only the head pose. This task has become essential for various applications based on head-mounted devices or smart glasses. The challenge of this task lies in estimating the pose information of unobserved body parts based solely on a single joint (i.e., head) trajectory. Several studies have begun to adopt head-conditioned generative models, however, such previous methods are costly and time-consuming due to the diffusion-based iterative process. As an alternative, we propose a simple yet novel method that leverages the latent space of the guidance network, which is designed as a variational autoencoder taking full-body poses as inputs. By enforcing latent distributions of this guidance network and our head-to-motion network to be similar, latent features sampled from the 'guided' distribution, i.e., distribution learned in our head-to-motion network, can be reliably decoded for natural representations of full-body poses even only with the head pose. One important advantage of the proposed method is that one-step sampling scheme achieves remarkably fast inference (more than 50 times faster) compared to diffusion-based approaches. Experimental results on benchmark datasets show that the proposed method efficiently improves the performance of ego-body mesh reconstruction. --- ### Articulated Object Reconstruction from Rest-State Observation Authors: Daeun Lee, Jaeah Lee, Woosung Kim, Haebeom Jung, Jaesik Park Published: 2026-07-30 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2607.27749v1 Building interactive digital twins requires recovering both 3D geometry and the kinematic structures that govern how objects articulate. Yet existing methods for articulated object reconstruction require explicitly observable motion from multiple articulation states. We introduce a rest-state formulation that reconstructs articulated objects from a single closed configuration, an inherently ill-posed setting where geometry, semantics, and motion priors compensate for the absence of motion cues. Our framework adopts an explicit mesh as an intermediate representation for cross-model verification and fusion, reconciling noisy outputs from vision-language and segmentation models into spatially consistent part structures. To estimate joint parameters without observed motion, we use a video diffusion model to synthesize articulation hypotheses and validate them through geometric consistency. Our approach achieves accurate part decomposition and physically plausible articulation, performing competitively with motion-observing reconstruction-based, generation-based, and modular pretrained-model baselines. --- ### A Structured Knowledge Infrastructure for Domain-Specific Data Asset Discovery Authors: Mengdi Chen, Yuanxin Huang, Yulin Jiang, Wei Sun Published: 2026-07-30 Categories: cs.IR, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2607.27748v1 Enterprise data analytics agents face two structural failures: generic RAG retrieves the wrong asset (Hit@10=19.1%) and delivers no usage knowledge to prevent metric misinterpretation---stemming from four root causes (C1--C4) ranging from semantic gap and entity ambiguity to schema drift and asset-usage gap. We present a two-layer solution deployed in the commercial advertising data warehouse at Xiaohongshu (5,300+ Hive tables, 14 domains). A three-tier dual-purpose knowledge base (179 documents, eight-section annotation template) serves both retrieval and generation, with a closed-loop refresh pipeline maintaining day-level freshness (one yes/no approval, 30s hot-reload). The Graph-Guided Retriever (GGR) uses a 2,859-node knowledge graph as a candidate gate with intent routing to deliver 71.6x token reduction. The Scene-Aware Ranker (SAR) applies 19-class entity recognition and explicit scenario annotations; negative knowledge alone contributes 25 percentage points of Hit@10 gain. On two 100-question benchmarks, Hit@10 rises from 19.1% to 96.6% (+77.5pp) and knowledge coverage from 56% to 77%, at 4.84--5.33s end-to-end latency. --- ### Can LVLMs Uncover the Truth Behind Visual Illusions? An Analysis of Perceptual and Reasoning Capabilities Authors: Liangjie Zhao, Jiaqing Lyu, Kexin Tang, Zecheng Fang, Rong Yin, Yulan Hu, Da Li, Jianing Li Published: 2026-07-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.27747v2 Large Vision Language Models have integrated reasoning capabilities, elevating cognitive performance to new levels. However, existing evaluations either focus solely on perception or rely on specific domains such as maths or coding. Evaluation for reasoning capabilities that align with an open-world environment is still required, especially one that considers perception and reasoning jointly. To bridge this gap, we propose to evaluate LVLMs by exploiting visual illusions as a diagnostic tool. Visual illusions are phenomena in which the human visual system misinterprets objective signals, resulting in an understanding that deviates from reality. We constructed Illusion-Reasoning, a benchmark of illusion images collected from the real world, incorporating diverse annotated question-answer pairs. Based on Illusion-Reasoning, we show that the reasoning capabilities of a wide range of LVLMs are not as advanced as claimed. Our work provides new insights into LVLMs and offers future directions for optimisation. Our project is publicly available at https://github.com/zhaoliangjie55/EMNLP2026_Illusion. --- ### Can LVLMs Uncover the Truth Behind Visual Illusions? An Analysis of Perceptual and Reasoning Capabilities Authors: Liangjie Zhao, Jiaqing Lyu, Kexin Tang, Zecheng Fang, Rong Yin, Yulan Hu, Da Li, Jianing Li Published: 2026-07-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.27747v1 Large Vision Language Models have integrated reasoning capabilities, elevating cognitive performance to new levels. However, existing evaluations either focus solely on perception or rely on specific domains such as maths or coding. Evaluation for reasoning capabilities that align with an open-world environment is still required, especially one that considers perception and reasoning jointly. To bridge this gap, we propose to evaluate LVLMs by exploiting visual illusions as a diagnostic tool. Visual illusions are phenomena in which the human visual system misinterprets objective signals, resulting in an understanding that deviates from reality. We constructed IllusionReasoning, a benchmark of illusion images collected from the real world, incorporating diverse annotated question-answer pairs. Based on IllusionReasoning, we show that the reasoning capabilities of a wide range of LVLMs are not as advanced as claimed. Our work provides new insights into LVLMs and offers future direction for optimisation. ---