# Research Papers — 2026-09 · bundle page 220 of 266 > Full-text markdown of papers #10951–11000 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/220 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/219.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/221.md) ### Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection Authors: Jiangning Zhu, Bowen Li, Shenyu Qiao, Yima Gu, Zhao Zhang, Yuhui Yuan, Shixia Liu Published: 2026-09-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.07072v1 Graphic designs, such as posters, advertisements, and infographics, are an important medium for communicating information and shaping understanding. Unlike natural images, they consist of layered elements with explicit compositional order. However, existing object detection models treat these elements as an unordered set, leaving compositional order unexploited. To address this limitation, we present Detect Anything in Graphic Design (DAD), a model that formulates graphic design detection as compositional deconstruction. It decodes elements in compositional order, using lower-layer elements to better detect higher-layer ones. The key feature of DAD is amodal detection, which predicts the full bounding box of each element, including regions occluded by elements placed above it. Building on this formulation, we propose Element Relative Policy Optimization (EleRPO), which extends GRPO from sequence-level supervision to element-level optimization. EleRPO provides fine-grained training signals that capture how each detected element contributes to overall detection quality, and works synergistically with compositional order to improve detection performance. To support training and evaluation, we build a dataset of 10 million graphic designs. Experiments show that DAD outperforms all baselines and achieves human-level performance in amodal detection, supporting effective image-to-layer decomposition. EleRPO consistently improves over GRPO across nine detection benchmarks. --- ### Continuous Token-Level Spatio-Temporal Context Modeling for Visual Object Tracking Authors: Ding Xia, Meiqin Liu, Jing Zhou, Jian Lan Published: 2026-09-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.07070v1 Spatio-temporal context has become increasingly crucial for visual tracking. However, most existing approaches extract spatio-temporal cues via discrete sampling strategies, which inherently deviate from the continuity of spatio-temporal context, thereby deteriorating tracking performance. To address this challenge, we propose TLCTrack, a novel tracking framework that models token-level spatio-temporal context through continuously updated salient tokens, enabling more accurate target representation. Specifically, TLCTrack incorporates three components: Masked Unidirectional Attention (MUA), Spatial Salient Token Collection (SSTC), and Temporal Salient Token Bank (TSTB) modules. By explicitly integrating spatio-temporal context, MUA extracts discriminative targetaware spatial features in the search region. To avoid the negative impact of background on feature learning, SSTC progressively suppresses background interference, thereby enhancing target spatial representation. Finally, TSTB captures high-quality spatio-temporal information through continuous salient token updates. Extensive experiments on five benchmarks demonstrate that our method achieves superior performance over state-of-the-art trackers. Code and models are available at https://github.com/xiading123/TLCTrack. --- ### VST: Verifiable Structured Transport for Auditable Agent-to-Agent Alpha Discovery Authors: Yuqi Li, Siyuan Liu, Bingjun Liu Published: 2026-09-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.07065v1 Agent-to-agent (A2A) alpha discovery is slowed by repeated feedback cycles between mining and evaluation agents, whose hand-offs, in contemporary LLM multi-agent systems, are free-form natural-language messages that carry no stable contract and cannot be replayed. We first restructure this communication as a structured agent-to-agent protocol of \emph{typed, causally addressable, unicast records}, so that the committed stream forms a causal trajectory. On that trajectory a single predictor with four typed heads forecasts the accumulated guidance the two miners would receive several cycles ahead; a transactional verify--leap controller then commits a multi-cycle speculative outcome only when it passes a four-level gate, and otherwise rolls back to the exact prior state. Structure is the enabling contribution, and its value is not accuracy. A controlled ablation shows an equal-information free-text channel reaches the same predictor hit rate. What typing provides is a state that can be schema-checked, replayed deterministically, and prevented by construction from leaking a forecast to an evaluator: auditability by construction, not an empirically stress-tested guarantee. On a CSI~1000 out-of-sample holdout, our single run is the only one among eight methods (seven baselines and ours) to hold a positive median annualized return and Sharpe at the factor level, though the median return \emph{in excess} of the benchmark stays negative for every method including ours; its development-selected top-20 portfolios reach a $0.71$ median holdout Sharpe, selected on a split inside the optimization horizon. We report these single-run results descriptively, gross of costs, and are explicit about their limits throughout; in particular we do not isolate the effect of the leap machinery from the inherited search substrate, which we leave to future work. --- ### SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem Authors: Soohyun Ryu, Sohee Kim, Eunho Yang Published: 2026-09-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.07064v1 Large Vision-Language Models (LVLMs) have achieved strong performance on diverse visual tasks, yet their ability to reconstruct and reason about the 3D structure of the scene depicted in 2D images -- referred to as spatial intelligence -- remains limited. Existing approaches attempt to address this gap by using real-scene spatial question answering datasets that require dense geometric annotations. However, constructing such labels is costly, time-consuming, and often noisy due to reliance on external perception modules. In this work, we propose a novel paradigm inspired by human cognitive development: learning foundational spatial skills through structured block-manipulation tasks. We introduce SpatialBlock-15k, a synthetic dataset of 15,000 block-stacking problems covering 3D-to-2D projection, viewpoint transformation, and structural combination. The dataset further incorporates controlled color modulation as visual cues to encourage anchor-based reasoning in visually complex conditions. Experiments demonstrate that LVLMs trained on our dataset through either direct answering or reasoning-based prediction significantly outperform baselines and generalize to real-world spatial tasks, despite the dataset's synthetic and compact nature. Code and data are available at https://github.com/rsoohyun/SpatialBlock. --- ### Trust-But-Verify: Poisoning-Resilient Locally Private Graph Learning Protocols Authors: Longzhu He, Li Sun, Hao Peng, Ruijie Wang, Raymond Chi-Wing Wong, Sen Su Published: 2026-09-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.07063v1 Built upon local differential privacy (LDP), locally private graph learning protocols have emerged as an important paradigm for decentralized graph learning, balancing privacy protection and learning utility. Under such protocols, each user locally perturbs their node features and adjacency information before transmission, ensuring formal privacy guarantees without original data leaving the device. However, the inherently open participation nature renders these protocols critically vulnerable to data poisoning attacks, where adversaries inject carefully crafted malicious nodes to corrupt neighborhood aggregation and degrade downstream utility. Despite the severity of this threat, effective defenses in this setting remain largely unexplored. In this paper, we propose VERITAS, a poisoning-resilient locally private graph learning protocol built on a trust-but-verify paradigm. By introducing a verification list encoding graded peer trust levels, VERITAS jointly privatizes node features and graph structure on the user side, while exploiting bilateral attestation asymmetry on the server side to identify and prune malicious nodes. Concretely, VERITAS comprises four synergistic stages: (1) local data perturbation, (2) attestation-driven malicious node pruning, (3) utility restoration via dual denoising, and (4) robust private graph learning. Extensive experiments on four real-world benchmark datasets across multiple LDP mechanisms and GNN architectures demonstrate that VERITAS effectively defends against data poisoning attacks and significantly improves downstream graph learning utility under rigorous privacy guarantees. --- ### PhysSAE: Mechanistic Interpretability of PINNs with Sparse Autoencoders Authors: Nandita N. Patil, Eshwar R. A., Gajanan V. Honnavar Published: 2026-09-07 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2609.07061v2 Physics-Informed Neural Networks (PINNs) embed PDE residuals into neural network training, but their internal representations remain opaque: it is unknown what physical features their hidden layers encode or whether those features have a localized causal role. We present PhysSAE, a mechanistic interpretability framework that trains overcomplete sparse autoencoders (SAEs) on PINN penultimate-layer activations and evaluates dictionary atoms through direct causal intervention in the original frozen hidden state: $h_{\mathrm{cf}} = h - αz_k d_k$, bypassing the SAE decoder entirely. Across six PDE families, with 3 PINN seeds and 3 SAE seeds each---we show that (i) Our discovered SAE atoms align with independently-defined physical observables (max Pearson $|r|=0.951$, always $\gg$ permutation null), (ii) the causal footprint of top-aligned atom ablation is 1.2--4.2$\times$ more spatially concentrated canonical than PCA or ICA interventions, and (iii) top-aligned atoms outperform matched random controls on causal localization for structured physical concepts (ESF$_{80}$ advantage 0.04-0.44). Two-atom bilateral representations improve concept regression R$^2$ by $ΔR^2\!=\!0.05\text{-}0.15$ over single atoms, while random pairs decrease it by up to 0.60. These results demonstrate that PINNs develop sparse, physically structured latent representations that can be identified and causally interrogated post-hoc, opening a path toward interpretability-aware scientific machine learning. --- ### CNsEMD: An Expert-Annotated Multi-Field-Strength MRI Dataset and a Hyperspherical Manifold Network for Multimodal Cranial Nerve Parcellation Authors: Lei Xie, Junxiong Huang, Guoqiang Xie, Jiawei Zhang, Jiahao Huang, Tianling Lyu, Ye Wu, Mingchu Li, Shoujun Yu, Shanshan Wang, Qingrun Zeng, Yuanjing Feng Published: 2026-09-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.07058v1 Cranial nerves (CNs) play essential roles in sensory, motor, and autonomic functions. Accurate CN parcellation from multimodal magnetic resonance imaging (MRI) is crucial for neuroanatomical analysis and neurosurgical planning. However, accurate CN parcellation remains extremely challenging because CNs are very small, exhibit low image contrast, and have slender tubular morphologies and complex anatomical trajectories. Moreover, the lack of publicly available, expert-annotated datasets has impeded the development and fair benchmarking of learning-based CN analysis methods. In this work, we introduce CNsEMD, an expert-annotated multimodal dataset for CN parcellation. It comprises data from 202 subjects acquired on 3T, 5T, and 7T MRI scanners. We further propose the projective hyperspherical manifold network (PHM-Net), which learns cross-modal representations by capturing angular relationships in a shared hyperspherical embedding space. Rather than performing multimodal fusion in Euclidean space, the proposed Hyperspherical cross-modal interaction (HCI) module enables bidirectional feature exchange between T1-weighted (T1w) and direction-encoded color (DEC) representations on a unit hypersphere. The Magnitude-preserving projective hyperspherical orientation representation (PHOR) captures the axial nature of DEC orientations while preserving diffusion magnitude. The hyperspherical prototype segmentation head (HPSH) further extends angular similarity to voxel-wise classification using normalized voxel embeddings and learnable class prototypes. Extensive experimental results on the CNsEMD dataset demonstrate the effectiveness of our PHM-Net against state-of-the-art methods. CNsEMD establishes a reproducible benchmark for multimodal CN imaging, while PHM-Net provides a geometry-consistent solution for CN parcellation across diverse MRI acquisitions. --- ### A Hyperbolicity Atlas of Large Language Model Hidden States Authors: Zhichao Yang, Yuanze Hu, Gen Li, Qingchen Yu, Shiying Duan, Xinyu Wang, Ye Qiu, Zeming Liu, Guangxu Chen, Zhaoxin Fan Published: 2026-09-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.07053v1 LLM hidden states are ordinary vectors, but the distances among those vectors may still show hierarchical structure. To our knowledge, this paper is the first systematic study of whether prompt-token hidden states in contemporary LLMs exhibit Gromov Hyperbolicity (GH), a distance-based measure of tree-likeness. Using 818,904 sample-layer measurements from ten open-weight models across MATH500, HumanEval, WinoGrande, and TruthfulQA, we build a GH map over four axes: parameter scale, layer depth, model family, and input domain. The clearest pattern is depth, not scale: middle layers usually form a high-relative-hyperbolicity plateau, while final layers often become substantially more tree-like. Scale effects are weak and non-monotonic, matched 7/8B model families differ strongly, and domains interact with model specialization. These findings make GH useful as a practical diagnostic: it shows where hierarchical distance structure appears, how specialization changes it, and which model-layer-domain comparisons deserve closer analysis. --- ### TrojanWorld: Backdooring World-Model Agents via Imagination Steering Authors: Wenkai Huang, Siyuan Liang, Gaolei Li, Yiming Li, Tianhao Peng, Jianhua Li, Dacheng Tao Published: 2026-09-07 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2609.07051v1 World models increasingly serve as the predictive core of model-based reinforcement learning agents, enabling them to simulate future dynamics and reason over imagined trajectories before acting. Their substantial training demands make pretrained world models attractive for distribution and reuse, exposing downstream systems to model supply chain threats. Backdoor attacks offer a targeted and stealthy means of exploiting such supply chains, yet their threat to interactive world-model agents remains largely unexplored. To fill this gap, we present TrojanWorld, a backdoor framework for world-model agents that induces attacker-specified behavior by steering internal imagination. A physical object placed in the scene acts as the trigger, enabling deployment-time activation through the agent's native observation pipeline without digitally manipulating the observation stream. To achieve effective, stealthy, and persistent control, TrojanWorld combines Decision-Reflective Induction to steer trigger-conditioned imagination toward attacker-specified actions using decision feedback, Clean Behavior Anchoring to preserve trigger-free predictive and behavioral fidelity, and Causal Propagation to sustain the induced preference along subsequent trajectories after the trigger disappears. Together, these mechanisms establish an end-to-end attack chain from physical perception through corrupted imagination to malicious action selection. Experiments with the TD-MPC2, DreamerV3, and R2-Dreamer systems across the DeepMind Control, MetaWorld, MyoSuite, and RoboDesk benchmarks show that under trigger activation, TrojanWorld achieves a target-action deviation as low as 0.026 while retaining at least 98.8% of the corresponding clean performance. Even after trigger removal, the compromised agent can remain trapped in the induced behavioral trajectory, continuing to execute attacker-specified actions. --- ### Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval Authors: JungMin Yun, YoungBin Kim Published: 2026-09-07 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2609.07050v1 Retrieval-augmented generation (RAG) critically depends on retrieving the evidence necessary for effective reasoning. However, this remains particularly challenging in multi-hop question answering (QA), where supporting passages are often linked through intermediate entities and relations that must be progressively uncovered. Existing retrieval approaches typically rely on a single retrieval intent or one-shot query expansion, limiting their ability to adapt to newly retrieved evidence and potentially introducing noisy or redundant retrieval signals. To address these limitations, we propose a training-free multi-hop retrieval framework that integrates evidence-conditioned exploration, passage-specific contrastive refinement, and coverage-aware final ranking. During offline indexing, the framework constructs passage-specific contrastive facets that characterize each passage relative to its semantically similar neighbors, providing fine-grained signals to distinguish closely related candidates. At inference time, the framework iteratively retrieves evidence, generates probes targeting unresolved information needs, refines candidate relevance using the contrastive facets, and selects a complementary set of passages that collectively cover diverse evidence-seeking intents. Experiments on MuSiQue, HotpotQA, and 2WikiMultihopQA demonstrate consistent improvements in retrieval quality and downstream QA performance over baselines. --- ### Large Discrete Policy: Advancing Explicit Behavior Modeling with Stochastic Iterative Scoring Authors: Zhenxin Li, Nadine Chang, Xinglong Sun, Jingde Chen, Wenhao Yao, Zi Wang, Maying Shen, Yu-Gang Jiang, Zuxuan Wu, Shiyi Lan, Jose M. Alvarez Published: 2026-09-07 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.07049v1 Behavior policies are often formulated as continuous generative models, whose iterative denoising processes are expressive but difficult to interpret and prone to producing implausible actions. We propose the Large Discrete Policy (LDiP), a fully discrete behavior modeling framework that selects actions from a large vocabulary of physically plausible candidates. Rather than perturbing actions, LDiP improves expressivity through stochastic iterative scoring: it progressively re-scores and prunes candidates with score-space stochasticity, enabling fine-grained ranking and exploration among plausible actions while preserving an explicit decision process. Across end-to-end planning, closed-loop driving, robotic manipulation, and vision-language-action settings, LDiP consistently outperforms strong discrete and continuous baselines in autonomous driving, and exceeds or matches continuous generative policies in robotic manipulation. These results show that discrete policies, when equipped with effective scoring mechanisms, offer an expressive, plausible, and interpretable alternative for behavior modeling. Project website: https://zhenxinli.net/LargeDiscretePolicy/. --- ### FreqDoor: A Hidden Trojan in the Frequency Domain for Backdoor Attacks on Vision-Language Models Authors: Yasir Arafat Prodhan, Sadad Hasan, Mohammed Imamul Hassan Bhuiyan Published: 2026-09-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.07048v1 Vision-language models (VLMs) have recently shown excellent progress in open-ended image-to-text generation. However, their multimodal nature makes them persistently vulnerable to backdoor attacks. Existing backdoor triggers for VLMs are either spatial, textual, or bimodal, which may yield localized or recognizable trigger patterns. In this work, we explore a different attack surface and propose \ textsc {FreqDoor}, a training-time backdoor attack that implants triggers in the frequency domain. \ textsc {FreqDoor} mixes amplitude-spectrum components from a trigger-source image selectively while preserving the phase of a clean image to generate a spatially distributed and visually imperceptible trigger without modifying the textual input. We evaluate the attack on BLIP-2, InstructBLIP, and LLaVA for image captioning and visual question answering. On Flickr8k, \ textsc {FreqDoor} achieves attack success rates of $99.6\%$, $99.8\%$, and $98.4\%$ on the three models, respectively, while preserving the semantic quality of the generated captions. On VQAv2, the corresponding attack success rates are $99.6\%$, $92.4\%$, and $79.6\%$. --- ### MEMOBench: A Process Level Memory Benchmark for Robotic Manipulation Authors: Haiyang Sun, Haoxiao Wang, Junming Chen, Weicheng Fang, Zihao Su, Jingkun Yi, Wenyou Yi, Hao Chen, Zhou Zhao Published: 2026-09-07 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.07047v1 Robotic manipulation often requires acting on information that is no longer visible, yet Vision-Language-Action policies are usually evaluated when the current observation largely determines the next action. Existing robotic memory benchmarks expose this gap, but they still rely mainly on final task success and therefore conflate forgetting with manipulation failure. We present \textbf{MEMOBench}, a benchmark for process level memory evaluation in robotic manipulation. MEMOBench includes 30 history dependent tasks, 1{,}500 expert demonstrations, and 4{,}200 executable checkpoint instances from 84 templates. Each checkpoint pairs coarse to fine language with a simulator predicate and labels one memory operation: Storage, Update, or Compression. These annotations define Memory Storage Rate, Memory Update Rate, and Memory Compression Rate, which measure memory fidelity alongside task success. Across standard and memory augmented VLA policies, the strongest memory module baseline reaches only 31.9\% average success rate, and high storage often coexists with weak update and compression. Checkpoint language also supervises semantic, contrastive, and framewise memory alignment objectives, yielding modest gains across different memory operations. MEMOBench provides a diagnostic evaluation suite and training supervision for memory grounded robotic policies. The project page is available at https://github.com/Collab-Gen/MEMOBench. --- ### AI and TCAD for Inverse Design and Defect Discovery: From Simple Machine Learning to LLM Authors: Hiu Yung Wong Published: 2026-09-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.07046v1 AI has revolutionized various engineering domains, but its impact on semiconductor device design and defect discovery is still limited, due to limited data and the curse of dimensionality. In this paper, we will discuss our work on using the Technology Computer-Aided-Design (TCAD) to generate precise data needed for machine learning (ML) to enable simulation-augmented ML. We demonstrate that with minimal domain expertise, it is possible to create a machine that performs as well as a device engineer on a specific task. We will show that auto-encoder-based machine learning models and noise engineering applied to TCAD data are effective at learning latent physics, and that the models can be seamlessly applied to experimental data. We will demonstrate how to build a device-engineer-level model step by step through various examples, including using only non-destructive electrical data to inverse-engineer the PiN diode layer thickness variations, the Ga2O3 Schottky diode doping and anode workfunction variations, and the transistor contact resistance in an inverter. Examples also include the generation of a FinFET IV/CV prediction model, the mapping between transistor images and IV curves, and the automatic calibration of TCAD parameters for a Ga2O3 Schottky diode, which can only be handled well by experienced TCAD engineers. Finally, to fully realize the potential of AI, large language models (LLMs) and multimodal LLMs (MLLMs) are believed to be necessary. We will discuss the application of LLMs to TCAD command file creation and our vision for MLLMs in automated device design and defect discovery. --- ### Disentangling Steering Vectors Authors: Takeru Hiramatsu, Kyohei Atarashi, Koh Takeuchi, Hisashi Kashima Published: 2026-09-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.07037v1 Activation steering has emerged as a lightweight, inference-time approach to control the behavior of Large Language Models (LLMs). However, traditional steering vectors used to intervene in LLMs' activations, such as those derived from the difference-in-means method, tend to entangle multiple semantic and stylistic concepts into a single composite direction, leading to unpredictable steering effects. Our core objective is to disentangle this composite direction into its constituent concepts. To this end, we propose Steering Vector Dissection, a framework to explicitly isolate individual and semantically consistent features from these composite directions. Specifically, we pair positive and negative activations and take their differences to generate a set of instance-level steering vectors, and train a dedicated Sparse Autoencoder (SAE) directly on them. Quantitative evaluations across two datasets, two models, and two intervention depths show that our method yields a set of semantically consistent basis vectors whose steering effects are mutually distinguishable. Furthermore, we show that this disentanglement enables precise control over model behaviors. --- ### Aha-Flow Distillation: Flow Markers Matter in LLM Reasoning Authors: Xiaodong Wang, Peixi Peng Published: 2026-09-07 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.07036v1 We identify the Flow Moment, a reasoning pattern characterized by sustained, process-confirming verbalizations such as I'm doing, in contrast to the revision- and backtracking-oriented Aha Moment. We refer to their corresponding linguistic expressions as Flow Markers and Aha Markers, respectively. Based on this observation, we construct Flow-CoT by rewriting the discourse markers of original reasoning traces while preserving their underlying reasoning content, and use it as auxiliary supervision for on-policy self-distillation (OPSD). We further propose \textbf{Aha-Flow Distillation (AFD)}, a dual-mode extension of OPSD that pairs different forms of privileged information with corresponding reasoning instructions. The Aha branch retains concise solution-based supervision, while the Flow branch introduces rewritten Flow-CoT under a direct and confident reasoning instruction. At inference time, the model uses only the standard reflective instruction, so Flow-style reasoning serves purely as a training signal. Experiments on AIME25 and HMMT25 show consistent improvements across Qwen3-8B and Qwen3-4B: AFD improves Avg@12 from 60.8 to 61.3 on Qwen3-8B and from 57.5 to 58.6 on Qwen3-4B over our reproduced OPSD baselines. Controlled ablations further show that, with the same Flow-CoT/Aha-CoT composition, dual-mode training improves Avg@12 from 59.5 to 60.1, indicating that the benefit comes not only from introducing heterogeneous reasoning supervision, but also from how it is organized during self-distillation. The code is available at https://github.com/Wang-Xiaodong1899/Aha-Flow-Distillation. --- ### Frequency Estimation Based on SNR-adaptive Frequency Estimator Under Wide SNR Range Authors: Hee-Yang Jung, Dong-Hee Paek, Woo-Jin Jung, Seung-Hyun Kong Published: 2026-09-07 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2609.07034v1 Frequency estimation is the problem of estimating individual tone frequencies from noisy multi-tone sinusoidal signals. Existing frequency estimation methods have difficulty accurately estimating both the number of tone frequencies and the individual tone frequencies in low signal-to-noise ratio (SNR) environments, because weak tone frequency components are buried in noise. In addition, existing methods generally exhibit a trade-off between robustness at low SNR and frequency estimation precision at high SNR, making it difficult to achieve consistently superior frequency estimation performance over a wide SNR range. To overcome these limitations, this paper proposes an SNR-adaptive frequency estimator (SAFE). SAFE consists of a time-frequency image neural network (TFINet), which enhances weak tone frequency components at low SNR, and an SNR-based frequency selector (SFS), which selects an appropriate frequency estimator according to the SNR of the estimated tone frequencies. TFINet enhances tone frequency components even in the low-SNR range, while SFS estimates the SNR of each tone frequency and selects either a robust frequency estimator or a super-resolution frequency estimator according to the estimated SNR. This enables SAFE to achieve robustness at low SNR while preserving high precision at high SNR. Simulation results show that SAFE achieves an False Negative Rate (FNR) of 13.00% over the SNR range from -10 dB to 0 dB, corresponding to an 13.04% improvement over the state-of-the-art method. In addition, SAFE reduces the Nearest Neighbor-Root Mean Squared Error (NN-RMSE) by 56.67% compared with the state-of-the-art method, demonstrating that SAFE performs more accurate frequency estimation. Furthermore, experiments using real-world data demonstrate that SAFE provides robust frequency estimation performance even in practical environments with clutter. --- ### Efficient Learning and Symmetry Discovery under Exact Invariances Authors: Ashkan Soleymani, Behrooz Tahmasebi, Patrick Jaillet, Stefanie Jegelka Published: 2026-09-07 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.07031v1 Learning with group invariances is central to many scientific and geometric learning problems, yet its computational foundations remain poorly understood. Even for classical supervised regression settings, it has been unclear whether one can efficiently compute a regression function that is exactly invariant to a given group action. Recent work showed that exact invariance can be enforced in polynomial time when the underlying group is finite and known, but left open the cases of infinite groups and unknown symmetries. In this paper, we resolve both challenges. First, we present the first polynomial-time algorithm for learning with exact group invariances that applies uniformly to finite and infinite groups. The runtime is polynomial in the data dimension and sample size, and independent of the group, while achieving strong generalization guarantees. This provides a computational explanation for the empirical success of invariant and equivariant methods in geometric machine learning and partially answers a recent open question in the literature. Second, we study learning in the symmetry discovery setting, where the invariance group is unknown. Focusing on the subgroup lattice of a finite group, we show that exact symmetries can be identified from data and exploited for learning in polynomial time. For regression over finite-dimensional feature spaces, our algorithm provably recovers the underlying symmetry, matches the minimax-optimal sample complexity of the known-symmetry setting, and runs in time polynomial in the data dimension and sample size. Our analysis relies on tools from random Cayley graphs and expander theory, which may be of independent interest. --- ### LoGAN: Multilingual Font Localization with Generative Agents Authors: Zhuoning Yuan, Ta-Ying Cheng, Benjamin Klein Published: 2026-09-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.07029v1 Localizing a font into new languages is a highly intricate task requiring precise design adaptation of glyphs, color/texture, and spacing/kerning, from source to target languages. Most existing methods focus on single glyph generation with limited capability in handling multilingual font rendering. In this work, we propose LoGAN, a VLM-based agentic framework for few-shot multilingual font localization, which takes in a small number of individual glyphs from a font or letters from a logo and uses them to generate complete character sets in other languages. LoGAN breaks down this task into multiple components: a glyph-level diffusion model, a style finetuning module, a spacing and kerning transfer algorithm, and a texture expansion model, with a VLM agent coordinator. LoGAN achieves broad language coverage for font localization with various styles, including Chinese/Korean/Japanese (CJK). We evaluate our approach on both font and real-world logo datasets spanning more than 27 languages and compare it against both specialized font generation and state-of-the-art image editing models with strong text rendering capabilities (e.g., FLUX, Nano-Banana). Our approach yields higher glyph fidelity while maintaining better style, texture, and kerning consistency according to both quantitative and qualitative evaluations. --- ### CIPHER: Benchmarking Cross-record Inference over Privacy-Hardened Evidence Records Authors: Suparno Roy Chowdhury, Manan Roy Choudhury, Dhruv Madhwal, Vivek Gupta Published: 2026-09-07 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.07022v1 Reasoning over privacy-constrained records requires combining structured attributes with evidence from free-text narratives. We introduce CIPHER (Cross-record Inference over Privacy-Hardened Evidence Records), a benchmark of expert-validated questions from consumer-finance, clinical, and law-enforcement records. The questions cover common tabular operations and include executable SQL supervision. We evaluate retrieval, prompting, table-specialist, and hybrid symbolic-neural systems under native redaction and surrogate-based evidence restoration. All system families exhibit substantial failures even when supporting records are provided. Most errors arise from incorrect record selection and predicate interpretation rather than arithmetic execution. Privacy transformations have non-uniform effects, sometimes obscuring necessary evidence and sometimes reducing distraction. CIPHER provides a reproducible testbed for diagnosing these failures and assessing how transformations of sensitive text affect reasoning over hybrid records. --- ### HyperTransfer: Understanding the Equivalence between Base Optimizer and Hyperball Authors: Jinghui Yuan, Hongtao Zhang, Jade Zou, Tianyu Li, Wenjie Zhou, Tianyu He, Wei Chen Published: 2026-09-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.07017v1 Hyperball optimizers constrain parameter norms and update only their directions, establishing a distinct paradigm for neural network optimization. Although this geometry appears fundamentally different from that of conventional Base Optimizers, which update both parameter norms and directions, we show that the two paradigms are dynamically equivalent for scale-invariant networks. Building on this equivalence, we propose HyperTransfer, which constructs a Hyperball optimizer that reproduces the dynamics of a target Base Optimizer using only its initialization and learning-rate schedule, without running the target optimizer itself. We further derive the inverse mapping and extend the framework to non-scale-invariant networks. Experiments show that both HyperTransfer and the inverse mapping produce loss trajectories nearly identical to those of their targets, suggesting that Hyperball dynamics are governed primarily by the induced effective learning-rate schedule and optimizer state. --- ### ARNAI: Artifact Removal Network based on Autoencoding and Inpainting for Robust Spinal Image Segmentation and Measurement Authors: Sang-Jin Park, Jinyoung Choi, Seokwon Kim, Seungeon Song, Insu Park, Dougho Park, Taeyeon Kim, Youjin Lee, Donghoon Yang, Jaeman Cho, Joongwon Yang, Mansu Kim et al. Published: 2026-09-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.07013v1 Purpose: This study aims to develop an AI framework applicable for postoperative imaging for automated measurement of spinopelvic parameters on radiographs with robustness to the presence of spinal implants. Materials and Methods: We retrospectively reviewed lateral lumbar spine radiographs from two institutions (Internal: January 2017--December 2024; External: October 2021--September 2025). We developed the Restore, Segment, and Measure (RSM) framework, incorporating a novel Artifact Removal Network based on Autoencoding and Inpainting (ARNAI) to mitigate implant-related artifacts in postoperative radiographs. Segmentation and spinopelvic parameter (PT, LL, SS, SCA) measurement performance were assessed using Wilcoxon signed-rank tests and intraclass correlation coefficients. Results: When ARNAI was added to a recent Transformer-based segmentation model, FCBFormer, the mean DSC increased to 0.870 from 0.814, with marked gains at L3--L5 and smaller improvements at L1--L2. On 91 radiographs with implants, the mean L4--L5 segmental Cobb angle error decreased to 4.7 ° from 15.6--16.2 °, an average error reduction of 70%. The ICC for L4--L5 segmental Cobb angle improved to 0.54 (Rater 1) and 0.59 (Rater 2) from 0.18, and ICCs for pelvic tilt, lumbar lordosis, and sacral slope all exceeded 0.70. The improvement in L4--L5 segmental Cobb angle error was statistically significant in the internal implant-containing cohort after correction for multiple comparisons. Conclusion: The proposed RSM framework improved automated spinopelvic parameter measurement in implant-containing postoperative radiographs. By mitigating implant-related artifacts, ARNAI improved segmentation and downstream measurement accuracy, with the greatest benefit observed for L4--L5 segmental Cobb angle estimation, where the mean error was reduced by approximately 70%. --- ### AstraMoE-SR: Trajectory-Guided Diffusion for Blind Satellite Jitter Deblurring and Super-Resolution Authors: Yi-Chung Lai, Chin-Tien Wu, Yu-Chih Chen Published: 2026-09-07 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.07012v1 Pushbroom satellite imaging couples limited spatial resolution with platform attitude instability. Platform jitter produces spatially varying motion blur because each scan line is acquired under a different instantaneous attitude, while perspective geometry causes the same perturbation to induce different pixel displacements across the field of view. Existing blind restoration methods that assume a spatially invariant kernel and satellite jitter correction methods that rely on auxiliary observations are therefore not directly applicable. We present AstraMoE-SR, a single-image framework that jointly restores motion blur and spatial resolution without auxiliary measurements. Rather than estimating a blur kernel, we infer how the camera moved by reparameterizing degradation as a local exposure trajectory under pushbroom geometry. A conditional diffusion model estimates the trajectory distribution, mitigating the over-smoothing of high-frequency jitter by deterministic point estimation. The predicted trajectory conditions a pretrained latent diffusion backbone through trajectory-guided geometric alignment and spatially adaptive reconstruction. We further show that the remaining point-wise trajectory error is consistent with intrinsic jitter-phase ambiguity that is not resolved by increasing estimator capacity. On all 1,411 DOTA-v1.0 images degraded using our physically motivated forward model, AstraMoE-SR is the only evaluated method to outperform the no-restoration baseline across every fidelity metric, improving on StableSR by 0.64 dB PSNR, 15.2% LPIPS, and 0.091 DINO feature similarity. Reconstructions conditioned on predicted trajectories differ negligibly from those using ground-truth trajectories, indicating that the estimates retain the degradation information required for effective restoration. --- ### Fine-Grained Visual Preprocessing and Dual-Stream Temporal Modeling for Multimodal Sentiment Analysis on Social Media Authors: Su Li, Yigong Zhang, Lei Xiong, Chune Li Published: 2026-09-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.07010v1 Multimodal sentiment analysis often remains text-dominant due to raw-video noise and insufficient temporal modeling. Using CH-SIMS v2.0S, this study proposes three improvements: the NAPS pipeline---a seven-stage system integrating face tracking,identity embedding, and normalized lip-motion analysis to reduce visual noise;DS-TANet, combining an EfficientNetB2 static stream, RAFT optical-flow motion stream, motion-guided attention, and Bi-GRU temporal modeling; and DS-TAFNet, fusing visual and MacBERT-Base textual representations via concatenation fusion. With NAPS, the static visual baseline achieves 80.98\% Macro F1, comparable to the text baseline of 80.55\%; DS-TANet improves visual Macro F1 to 82.58\%;and DS-TAFNet achieves 87.49\% accuracy and 87.48\% Macro F1. These results demonstrate that improving visual input quality and temporal representation is more effective than increasing fusion complexity under limited-data conditions. --- ### NeuCME: Toward Dynamic Multimodal Continual Learning via Neural Combinatorics of Multiple Experts Authors: Kai Guo, Chuanbin Liu, Peng Hu, Hao Wang, Xi Peng Published: 2026-09-07 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.07009v1 Multimodal continual learning has recently shown great potential for developing agents with human-like intelligence by continuously learning new tasks across multiple modalities. However, existing methods typically assume that the set of modalities per task is predefined and fixed. In this paper, we investigate a more realistic learning setting, referred to as dynamic multimodal continual learning, in which the set of modalities may vary across tasks rather than remaining fixed. This setting involves two primary challenges: (i) spatio-temporal catastrophic forgetting and (ii) adaptive multimodal fusion. To address these challenges, we propose NeuCME (as shorthand for \textbf{Neu}ral \textbf{C}ombinatorics of \textbf{M}ultiple \textbf{E}xperts), a novel framework designed to effectively learn and integrate knowledge across tasks with varying modalities. The proposed NeuCME model comprises three key components, namely modality-combinational rehearsal, multi-gated mixture-of-experts, and task relevance-guided distillation. Furthermore, we formulate an evaluation metric to quantify the dynamism of task sequences and then set up a comprehensive benchmark with different degrees of dynamism. Extensive experiments using four real-world datasets demonstrate that the proposed NeuCME outperforms state-of-the-art methods markedly. --- ### RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving Authors: Yang Liu, Zhaokai Luo, Huayi Jin, Ruozhou He, Chenchen Hong, Mingxiao Ma, Biao Zhang, Zhiyong Wang, Boyu Wang, Guanjie Chen, Yifei Liu, Tao Xie et al. Published: 2026-09-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.07008v2 Multi-head latent attention (MLA) exposes many logical query heads through one packed latent KV stream. This representation is memory efficient, but it removes the physical per-head cache boundary assumed by conventional head-wise reuse. We present our system, a DeepSeek-V4 realization of RedKnot's head-aware reuse principle. Each immutable document is processed offline at canonical position zero; certified Local-head contributions are retained as MLA-Off. At serving time, query-side RoPE relocation restores the document's request position, a small Global-head set and protected Local token rows are recomputed as MLA-Online, and the two paths are merged before a single shared output projection. The packed MLA latent is never split. DeepSeek-V4-Flash uses 37 reusable layers and a 56/8 Local/Global partition, giving a 75.29% analytic logical head-row ceiling; the Pro-0813 profile uses 55 layers and 112/16 heads, giving 78.89%. Frozen Flash operating points show hot-artifact TTFT speedups of 2.02-3.84x. At 256K, the archived three-dataset study reports an aggregate F1 change of +3.24 percentage points, an EM change of +4.16 points, and a 78.7-79.5% analytic major-operator arithmetic saving, while one dataset decreases by 2.81 F1 points. A separate author-reported 256K hot-artifact QPS measurement is approximately 2.0x; because its raw concurrency trace is not included in this bundle, we mark it as preliminary rather than archived evidence. We describe the factorization, position repair, token-row closure, sparse-MoE support, TP8 integration, and the measurement boundaries needed to interpret these results. --- ### GIFT: Goal-Injected Fine-Tuning for Efficient Manipulation Policy Adaptation Authors: Xiaoyuan Fang, Shuo Feng, Yuxuan Wang, Enhua Cheng, Peng Zhou, Piji Li Published: 2026-09-07 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.07006v1 Compared with relying solely on initial observations and language instructions, predicting goal images with generative models as high-level visual guidance can significantly enhance the robustness of Vision-Language-Action (VLA) models. However, most existing foundation models have not systematically incorporated goal image conditioning due to the high computational training cost. To this end, we propose Goal-Injected Fine-Tuning (GIFT), a lightweight and efficient fine-tuning framework that seamlessly integrates generated goal images into multiple representative pretrained VLA models. Our approach introduces goal image features into observations via a zero-initialized convolution which progressively grows parameters from zero and prevents harmful noise from disrupting the pretrained policy during fine-tuning. As training proceeds, goal information is gradually incorporated, enabling efficient goal understanding without disrupting model stability. We further introduce a refined image editing method to generate semantically and visually consistent goal images from initial observations and task instructions. Experiments show that goal-aware VLA models achieve substantial performance gains across tasks: with only a single epoch of fine-tuning, GIFT outperforms the base model by 6.0% and 13.4% on two SIMPLER settings, and by 4.7% on LIBERO, demonstrating both efficiency and effectiveness. --- ### CGSM: Concept-Guided Segmentation Model for Precise Pulmonary Lesion Delineation Authors: Changheng Lin, Wenjie Zhang, Yushan Lu, Xinyue Yan, Xiao Jia, Wei Zhang Published: 2026-09-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.07004v3 Accurate segmentation of pulmonary lesions is essential for effective clinical diagnosis and treatment strategies. Existing segmentation approaches often lack task-specific semantic guidance, as text-based annotations typically offer coarse localization of lesions, leading to inadequate delineation of lesion boundaries and poor performance on small-scale lesions. To address this, we propose CGSM, a Concept-Guided Segmentation Model that integrates LLM-generated and clinically reviewed concepts into the segmentation process. Specifically, we design a Concept-Visual Alignment Module (CVAM) to activate relevant tokens within the concepts that align with visual features, enhancing the interaction between textual and visual information. In addition, we introduce a Concept Modulated Decoder (CM-Decoder), which uses concepts from CVAM as modulation signals to facilitate the adaptive fusion of image and text features, improving the segmentation accuracy. Extensive experiments on two public datasets show that CGSM achieves state-of-the-art performance, with results of 91.59% Dice and 84.49% mIoU on the QaTa-COV19 dataset, demonstrating its effectiveness in pulmonary lesion segmentation. --- ### LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Text Authors: Sungjune Lee, Myungjoo Kang Published: 2026-09-07 Categories: cs.SE, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.06993v2 Large language models (LLMs) increasingly generate Markdown that is consumed by renderers, agents, code extractors, and structured downstream pipelines. Yet existing evaluations often conflate content quality with format adherence, leaving Markdown boundary failures under-measured. We introduce LatentMD, a benchmark and evaluation protocol for diagnosing CommonMark-level fence-boundary failures in LLM-generated Markdown. LatentMD separates content correctness from boundary correctness, enabling detection of outputs that are content-correct but boundary-broken. The benchmark contains 4,179 prompts and a CLI for scoring arbitrary model outputs. Across 9 LLMs and roughly 37,600 generations, we find that Markdown boundary failures are widespread: 38.0% of valid main-grid outputs are content-correct but boundary-broken, with substantial boundary breakage under unspecified prompts and in a small human-authored validation set. Ablations show that failures are driven primarily by same-family symmetric-delimiter collisions rather than nesting alone, are only partially mitigated by prompt hints, and generalize to Python triple-quote docstrings while JSON remains robust as an asymmetric-delimiter control. LatentMD provides a reproducible diagnostic target for parser-sensitive LLM evaluation. --- ### AV-SafetyBench: A Safety Benchmark for Text-to-Audio-Video Generation Authors: Suah Choi, Tae-Young Lee, Gyeong-Moon Park Published: 2026-09-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.06991v1 Recent text-to-audio-video (T2AV) models jointly generate video, speech, sound effects, and ambience from a single text prompt. This capability poses new challenges for safety evaluation, as unsafe content may be conveyed through the audio track or arise only when the visual and audio tracks are interpreted jointly. Existing safety benchmarks largely focus on either generated video or generated audio in isolation and are therefore not designed to capture these risks. To close this gap, we introduce AV-SafetyBench, the first safety benchmark developed specifically for T2AV generation. AV-SafetyBench comprises a four-axis, 13-category taxonomy and 5,200 manually reviewed prompts that specify visual scenes, speech, and non-speech audio. Our evaluation protocol assesses each output under three views: Full-AV, Video-Only, and Audio-Only. It then uses the Video-Only and Audio-Only judgments to assign Full-AV unsafe outputs to one of four risk sources: Video-Only, Audio-Only, AV-Both, or AV-Joint. We evaluate five open-source T2AV models and validate the automated Full-AV judgments against human annotations. Across the five models, Full-AV Unsafe Rates range from 25.1% to 49.4%. Beyond these aggregate rates, risk-source analysis reveals that, for four of the five models, Audio-Only and AV-Joint cases-unsafe outputs missed by video-only evaluation-account for 41.6-48.3% of Full-AV unsafe outputs for which a risk source could be assigned. In the Cross-Modal Harm Emergence category, AV-Joint accounts for 87.5% of unsafe outputs withan assigned risk source. Together, these findings demonstrate the value of AV-SafetyBench for evaluating T2AV safety across the visual and audio modalities and their interaction. --- ### Continual Learning Mechanisms Compose for Long-Horizon Memorization Authors: Zheyuan Zhang, Alvin Zhang, Daniel Khashabi, Tianmin Shu Published: 2026-09-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06986v1 Language models may need to internalize information that arrives over time and retain it through many subsequent updates. To study this challenge, we introduce long-horizon memorization, a setting in which a model learns 100 query-answer tasks through continual supervised fine-tuning without retaining earlier training examples or receiving task identifiers at inference. Sequential updates cause catastrophic forgetting, and no single continual learning mechanism we evaluate maintains strong retention at this horizon. We hypothesize that mechanisms addressing complementary sources of forgetting will be more effective when composed. We organize these compositions along two design dimensions. Data, function, and weight anchors specify what prior information each update should preserve, while low-rank allocation rules determine where successive updates are retained. To test this hypothesis systematically, we construct three distinct 100-task memorization datasets. We introduce task-level successive halving to search the combinatorial design space and use a factorial experiment to measure individual and interaction effects. Our best method combines all three anchors with merged LoRA, ranks among the top 3 methods in all datasets, and raises average final retention from 1.2% under naive sequential fine-tuning to 34.9%, a 28-fold improvement. The data anchor and merged LoRA provide the largest average gains and interact super-additively on all three datasets. Together, these results show that composing complementary mechanisms substantially improves long-horizon memorization beyond what any individual mechanism achieves. --- ### AF-Mamba: Efficient Long-Term Signal Modeling for Early Prediction of Atrial Fibrillation Onset Authors: Yongbin Lee, Ki H. Chon Published: 2026-09-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06984v1 Atrial fibrillation (AF) is the most common cardiac arrhythmia and is associated with increased risks of stroke and heart failure. The growing availability of wearable and portable ECG monitoring enables continuous assessment of cardiac rhythm outside clinical settings. Predicting AF before its onset could provide additional lead time for timely clinical assessment and potentially improve the management of patients at risk of AF-related complications. This study focuses on predicting AF onset one hour in advance using long-term RR intervals (RRIs). To address this challenge, we propose a deep learning architecture that integrates temporal convolutional networks (TCNs) for local features encoding with Mamba, a selective state-space model capable of long-range sequence modeling. This hybrid TCN-Mamba design enables efficient training and inference on one-hour input windows, overcoming limitations of Transformers' quadratic scaling and recurrent networks' vanishing gradients. In subject-wise 5-fold testing, the proposed model achieved a sensitivity of 0.889, specificity of 0.943, F1-score of 0.813, AUROC of 0.974, and AUPRC of 0.933. In paired cross-dataset holdout evaluation, AF-Mamba maintained discriminative performance across unseen AF and NSR datasets, achieving a mean AUROC of 0.897. Compared against state-of-the-art AF prediction models and general time-series models, AF-Mamba achieved competitive predictive performance while providing a favorable performance-efficiency trade-off for long RRI sequences. These findings demonstrate the potential of AF-Mamba for accurate AF prediction one hour in advance and real-time continuous ambulatory monitoring. --- ### Input-to-State Stability Framework for Fully Distributed Primal-Dual Dynamics for Quadratic GNEPs Without Multiplier Consensus Authors: Shao-An Yin Published: 2026-09-07 Categories: math.OC, cs.AI, cs.GT, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2609.06983v2 Generalized Nash Equilibrium Problems (GNEPs) often arise in multi-agent engineering applications that require distributed algorithms. Unlike traditional approaches that enforce consensus on multipliers, our method removes the need to share multipliers, reducing communication and improving privacy. As a result, different initializations can lead to different GNEs, including non-variational ones. We establish convergence under sufficient conditions using an input-to-state stability (ISS) framework. --- ### AnomalyCraft-700K: Component-Level Controllable and Verifiable Synthetic Anomalies for Fine-Grained Video Anomaly Understanding Authors: Yuzhou Long, Haodong Zhang, Yunpeng Yang, Peng Wu, Guansong Pang Published: 2026-09-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06978v1 Progress in video anomaly understanding (VAU) has long been limited by inherent deficiencies of real-world anomaly videos, which are hard to collect and offer little control over their content. Synthetic anomaly approaches partially alleviate data scarcity, yet their generation remains largely controlled at the category or prompt level. They also lack component-level verification of video-text consistency and provide insufficient hard normal samples near the normal-anomaly boundary. To address this, we present AnomalyCraft-700K, a component-controllable synthetic anomaly dataset for fine-grained VAU, containing over 40K videos and over 700K task-level textual annotations. From fine-grained semantic components and a progressive three-stage pipeline, we craft anomaly events that are richly detailed, semantically controlled, and temporally structured, and additionally construct per-category hard normal samples to prompt the model to discriminate based on anomaly semantics rather than surface visual cues. Moreover, using the components as verification units, AnomalyCraft-700K further performs component-wise correction of video-text discrepancies introduced during generation, providing reliable annotations with verified cross-modal alignment for six tasks that progress from anomaly detection, through anomaly retrieval and captioning, to fine-grained anomaly reasoning. Evaluations of widely used methods under both traditional and MLLM-based protocols demonstrate that AnomalyCraft-700K serves as an effective source of supervision, from anomaly detection to fine-grained anomaly understanding. --- ### HealthLoopQA: A Context-Aware Question Answering Benchmark for Interpreting Wearable Monitoring Data in Diabetes Care Authors: Yuchen Niu, Yanan Ma, Srinivasan Nandakumar, Maolin Chen, Viktor Schlegel, Kexin Wei, Ling Cheng, Anna Bird, Anil Anthony Bharath, Siew-Kei Lam Published: 2026-09-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06976v1 As medical wearables become integrated into daily chronic disease care, effectively interpreting longitudinal monitoring data is essential for patients and clinicians to understand health trends, detect safety-critical events, and make informed decisions. While large language models (LLMs) show promise for transforming this streaming physiological data into personalized health insights, evaluating their reasoning capability and analytical rigor in diverse monitoring tasks remains a fundamental challenge. Existing medical wearable question answering (QA) benchmarks primarily assess short-horizon classification or statistical summaries, largely ignoring the long-term patterns, therapeutic and behavioural contexts, and potential system failures inherent in real-world deployments. To address this, we introduce HealthLoopQA, a comprehensive diagnostic benchmark for evaluating LLM reasoning over continuous diabetes monitoring data. Grounded in a novel taxonomy of eleven atomic reasoning abilities, HealthLoopQA comprises 127 tasks and over 1,500 QA instances spanning process mining, anomaly detection, and prediction over 30-day horizons. To systematically evaluate safety awareness, we complement real-world datasets with a fault-injected simulation testbed modeling diverse device malfunctions and cyber-physical attacks to generate physiologically plausible hazard scenarios. Evaluating state-of-the-art LLMs across prompting and agentic frameworks reveals severe limitations in complex temporal pattern mining. Furthermore, we identify a broader phenomenon of In-context Laziness under long-context prompting, highlighting critical open challenges in deploying LLMs for rigorous long-horizon medical reasoning. --- ### Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM Pruning Authors: Seungmin Oh, Donggeon Lee, Jongbin Ryu Published: 2026-09-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.06974v1 Large language models achieve strong performance across diverse tasks, but deployment remains costly because of memory, latency, and energy demands. Structured pruning reduces these costs by removing architectural components, yet its recovery stage is often limited by a mismatch between the recovery module's representational capacity and the complexity of the removed knowledge. We call this bottleneck the capacity-knowledge asymmetry and propose OverRep, an Overcomplete Reparameterization framework for structured LLM pruning. Following the principle of "train overcomplete, deploy compact", OverRep temporarily overparameterizes the recovery module during training to absorb complex knowledge distilled from the original model. After recovery, the overcomplete re-parameterization is algebraically merged into a mathematically equivalent compact module, preserving the pruned model's inference-time architecture and computational cost. OverRep further introduces an annealed activation that enables nonlinear training dynamics while converging to a linear regime for exact algebraic merging. Across three backbone families, OverRep improves retained reasoning performance over strong recovery baselines by up to 5.5 and 8.4 points at 25% and 50% pruning, respectively, while keeping memory usage and TFLOPs comparable to existing recovery methods. Our code is available at https://github.com/mmai-laboratory/OverRep. --- ### AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories Authors: Asif Pinjari, Mithun Paul Saint-Germain Published: 2026-09-07 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.06972v1 LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection can enter. A successful injection has a characteristic shape when the trajectory is read in order: a benign prefix gives way to actions that serve the attacker rather than the user. Existing benchmarks measure whether such attacks succeed against live agents, and existing guard models judge a trace as a whole; no public corpus labels, step by step, where an injection enters a trajectory and which steps it corrupts. We present AgentDrift, a benchmark of 12,536 synthetic tool-call trajectories over five agent domains in which every one of the 71,024 steps carries one of four labels: benign, injection point, hijacked, or failed injection. The corpus contains 4,000 benign, 5,536 attacked, 1,500 failed-attack, and 1,500 hard-negative trajectories; attacked trajectories follow three compliance patterns whose label strings obey a stated regular grammar. Failed attacks carry an injection the agent resisted, and hard negatives carry legitimate content that resembles an attack, so a detector must separate attempt from success and deviation from novelty. Trajectories were generated by a single open model under category-specific protocols, enforced by a closed-vocabulary structural validator, screened by an LLM judge, and audited by hand on 1,200 trajectories; we show that the LLM judge was itself fooled by the hard negatives. A surface-feature logistic regression recovers only 55.4% of attacks (F1 0.647), including only 8.2% of partial hijacks and 23.1% of delayed executions, so nearly half of the attacks require modeling the behavioral sequence. We measure template concentration, attack-goal-family collapse, and world-identity leakage in the generated data, and release the corpus with its documentation under CC BY 4.0. --- ### CantoneseLLM v2: Reasoning in a Low-Resource Language Authors: Tsz Chung Cheng, Chung Shing Cheng, Chaak Ming Lau, Cheuk Hei Chong Published: 2026-09-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.06970v1 Cantonese is widely spoken but remains low-resource in written data, with no large corpus of native Cantonese reasoning traces available for model training. We develop and release CantoneseLLM v2, comprising models based on Qwen3 8B and 30B-A3B. The models are trained through CPT on 784 million Cantonese and Hong Kong-related tokens, chat-vector merging, SFT, DPO, and RLVR. Evaluation across the training stages shows that chat-vector merging transfers instruction following but preserves the donor model's reasoning language, while SFT with limited Cantonese reasoning data substantially shortens or removes reasoning traces and reduces benchmark performance. DPO restores the reasoning-block format, particularly for the 8B model, but recovers only part of the lost performance. The RLVR training with Cantonese language and Traditional Chinese scripts as multiplicative constraints introduced Cantonese language alignment and restored the lost performance. The 30B-A3B model reaches 73.16 on HKCanto-Eval, within 1.20 points of its merged checkpoint, while retaining the Cantonese reasoning behaviour absent from that checkpoint. We release the model checkpoints, the training environments, and a thirteen-year Traditional Chinese Common Crawl dataset. The models can be accessed at https://huggingface.co/collections/hon9kon9ize/cantonesellm-v20 --- ### Re-calibrated Contrastive Loss for Transformation-Aware Prompt Conditioning in Vision-Language Models Authors: Seungmin Oh, Seunghun Kang, Jongbin Ryu Published: 2026-09-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.06967v1 Ensuring effective transfer learning for vision-language models without compromising their generalization performance is crucial. However, many existing methods overlook data characteristics and simply reuse the training strategies adopted during pre-training. Specifically, they treat same-class samples as distinct instances and transform images independently of their paired text prompts, which makes model learning more difficult. We address these limitations through transformation-aware prompt conditioning and a re-calibrated contrastive loss. Fixed text descriptors identify the transformations applied to paired images, providing transformation-level consistency without altering class semantics. This design aligns the image and text branches at the transformation level, enabling richer representations while preserving the models' ability to generalize. In addition, our loss function mitigates positive-gradient dilution in soft-target cross-entropy when each anchor has multiple valid positives. During transfer, our approach treats same-class samples as positives rather than distinct instances, enabling the model to learn domain-specific features more effectively. Experiments across distribution shift, transfer learning, and few-shot settings demonstrate consistent improvements over existing approaches. Source code for our method is available at https://github.com/SoongE/ReCalCon. --- ### MOLE: Detecting Insider Threats in AI Agents Authors: Aashiq Muhamed, Virginia Smith Published: 2026-09-07 Categories: cs.LG, cs.CL, cs.CR arXiv: https://arxiv.org/abs/2609.06966v1 Model misalignment, prompt injection, or operator misuse could lead AI agents operating frontier-lab accounts to exfiltrate model weights, poison training data, or weaken release gates. Existing benchmarks do not test whether defenders can detect this activity among routine work under a limited review budget. We introduce MOLE, an open benchmark of 150 AI-operated accounts sharing 9 stateful services over 30 workdays, with 12 threats and 8 corpora from four models totaling roughly 20 billion tokens. Of 39 agent models, 72% complete most assigned harmful objectives and agent refusal does not predict completion. MOLE enables comparison of 40 monitors across corpus generators, observability levels, and threats; even the best evaluated monitor in our single-day audit-event comparison misses nearly half of completed harm. MOLE also enables monitor development: benchmark-guided search improves a mid-tier monitor by 49-64%, while selective use of a stronger monitor improves budget-AUC by 10% over applying it to every account-day at comparable modeled cost. --- ### TurEngMix: A Text Corpus and Benchmark for Turkish-English Code-Mixed Language Identification and Named Entity Recognition Authors: Ilayda Dogan, Phuong-Anh Nguyen-Le, Julia Mendelsohn Published: 2026-09-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.06963v1 Natural language processing systems underperform on code-mixed text, particularly for low-resource language pairs. Turkish-English poses a further challenge: it lets English stems combine with Turkish suffixes to form single mixed-language tokens. We introduce TurEngMix, a corpus of 5.5K noisy, naturally occurring social media posts (486,974 tokens) rich in Turkish-English code-mixing. From this corpus, we construct a new Turkish-English benchmark for code-mixed language identification (LID) and named entity recognition (NER), comprising 15K expert-annotated tokens. Evaluating both decoder LLM and fine-tuned encoder baselines, we find that monolingual Turkish and English tokens are labeled reliably, but all models have high error rates on mixed-language tokens for both LID and NER. For morphologically integrated tokens, NER error rates were 5.2x and 6.3x higher for GPT-4o and Qwen, respectively. This highlights how morphological integration remains a challenge. We release the corpus, annotations, and code to support future computational and sociolinguistic research on Turkish-English code-mixing. --- ### DPSF-Net: A Dual-Prior Spatial-Frequency Network for Real-World Remote Sensing Image Dehazing Authors: Mei Lu, Shangliang Shao, Shanliang Yao Published: 2026-09-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.06962v1 Real-world remote sensing image dehazing (RSID) remains challenging because atmospheric scattering, spatially non-uniform haze and colour distortion jointly degrade structural and spectral information. Most deep learning methods rely on RGB inputs and spatial-domain feature extraction, which limits their ability to separate global background haze from local surface details. Here, we propose DPSF-Net, a dual-prior spatial-frequency network built on MCAF-Net for real-world RSID. The network uses hazy RGB images and dark channel prior (DCP) maps as joint inputs, allowing physical degradation cues to guide end-to-end feature learning. A spatial-frequency residual interaction block introduces a FourierUnit branch into multi-directional spatial interaction to model large-scale haze components. A prior-guided feature attention module adaptively fuses prior and attention features to reduce colour shift and structural distortion. A selective kernel complementary fusion module screens multi-scale skip features through bidirectional residual complementary gating and selective kernel fusion. Extensive experiments demonstrate that DPSF-Net achieves state-of-the-art performance on the real-world RRSHID remote sensing image dehazing benchmark and remains competitive across multiple synthetic datasets. Moreover, the proposed method strikes a favourable balance among restoration quality, parameter count and computational complexity, supporting the effectiveness of dual-prior spatial-frequency modelling. --- ### SSP-DMGTimeNet: Physics-Constrained Learning for Spatiotemporal Trajectory Prediction of Vehicle Platoons Authors: Yuhang Wang, Kailang Ma, Zirui Li, Mingfeng Fan, Kitae Jang, Changju Lee, Heye Huang Published: 2026-09-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.06961v1 Existing car-following prediction methods mainly optimize trajectory accuracy, while rarely considering whether predicted disturbances propagate realistically along a vehicle platoon. This limitation may lead to accurate but string-unstable predictions. We propose SSP-DMGTimeNet, a physics-constrained learning framework for spatiotemporal trajectory prediction of vehicle platoons. The model combines multi-scale temporal representations with cross-vehicle interaction features to capture complex and time-varying platoon dynamics. A propagation-delay-aware causal attention mechanism explicitly models upstream-to-downstream disturbance propagation by learning response delays between adjacent vehicles and accumulating them along the platoon. In addition, time- and frequency-domain string-stability losses relieve disturbance amplification across both adjacent vehicles and arbitrary sub-platoons during training. Experiments on HighD show that SSP-DMGTimeNet achieves an unstable-window rate of 0.65\% for five-vehicle platoons and a maximum head-to-tail amplification of 0.898 on the ground-truth excitation subset, while maintaining competitive trajectory prediction performance. In zero-shot evaluation on NGSIM US-101 and I-80, the model achieves velocity MAEs of 1.316~m/s and 1.252~m/s, with unstable-window rates of 3.90\% and 4.10\%, respectively. These results demonstrate that incorporating platoon-level physical constraints can effectively balance trajectory prediction accuracy and disturbance propagation stability. --- ### iBrain: A Unified Foundation Model Reading the Brain from Surface to Spikes Authors: Ying Chen, Tiou Wang, Zhifeng Yue Published: 2026-09-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.06960v1 Invasive neural recordings provide high-fidelity measurements of brain activity, with signals such as intracranial EEG (iEEG) and intracortical spiking activity capturing neural dynamics at different spatial and temporal scales. Yet existing neural foundation models have largely been developed independently for different invasive recording paradigms, leaving joint pretraining across heterogeneous invasive signals underexplored. In this work, we introduce iBrain, a unified foundation model that jointly learns from iEEG and spiking activity. iBrain employs signal-specific encoders to accommodate their distinct signal characteristics and a shared spatiotemporal Transformer backbone to model dependencies across recording channels and time. We pretrain iBrain on over 7,000 hours of heterogeneous neural recordings using masked signal reconstruction and channel-view alignment, promoting contextual modeling of neural dynamics and robustness across different channels. iBrain consistently outperforms single-signal pretraining baselines and achieves state-of-the-art performance on multiple benchmarks. Further experiments demonstrate that iBrain exhibits transferability and data efficiency across diverse recording settings. These results highlight the potential of joint pretraining on heterogeneous invasive neural recordings to support scalable neural modeling and transferable representations across recording settings and downstream tasks. --- ### MSSP: Multi-Scale Spatially-Constrained Partition for Unsupervised Semantic Segmentation of 3D Point Clouds Authors: Zhenghao Zhang, Xinjie Wang, Wei Wang, Jun Zhang, Hanyun Wang Published: 2026-09-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.06959v1 3D point cloud semantic segmentation is essential for real-world spatial understanding, yet the prohibitive cost of human annotations motivates unsupervised approaches that require no labels. Existing superpoint-based methods typically rely on spectral analysis at a fixed granularity, failing to capture the hierarchical semantic structures inherent in complex indoor scenes. To bridge this gap, we present a Multi-Scale Spatially-Constrained Partition (MSSP) framework that combines multi-scale spectral analysis with spatially-constrained clustering. Multi-scale spectral analysis constructs enriched superpoint descriptors across multiple clustering granularities; however, the resulting high-dimensional feature space calls for a structural prior to translate into cleaner segmentation. Spatially-constrained clustering supplies this prior by restricting superpoint merging to physically adjacent regions, imposing the spatial coherence needed for multi-scale features to be effective. Extensive experiments on S3DIS and ScanNet show that MSSP achieves the best mIoU among unsupervised methods on the main benchmarks, with particularly significant gains on S3DIS. Notably, our ablation reveals a regularize-then-enrich interaction: multi-scale features alone do not improve final segmentation, yet become highly effective when coupled with spatial regularization, underscoring that spatial coherence is aprerequisite for multi-scale representations in superpoint clustering. --- ### Mind the Phase: Effective Rank and Representation Health in Legged Locomotion Authors: Felipe Tommaselli, Thiago H. Segreto, Juliano D. Negri, Ricardo V. Godoy, Marcelo Becker Published: 2026-09-07 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.06958v1 Reinforcement learning has become the leading paradigm in legged locomotion, enabling complex behaviors from backflips to parkour through massively parallel simulation. Under PPO's non-stationarity, shallow networks remain the de facto architecture, supported by carefully staged curricula and environments, yet the representations these policies learn stay poorly understood, leaving no training-time signal of how they will behave on hardware. In this work, we empirically study locomotion policies through the effective rank of the policy Jacobian and show that conditioning rank on the gait phase exposes architectural structure that global rank averages away. In particular, we find that standard architectural choices, namely layer normalization and residual connections, allocate roughly two more dimensions of effective rank to swing than to stance, which is fully absent in vanilla MLPs. Building on this, we propose a simple recipe that turns these representational signatures into smoother, more reliable sim-to-real transfer. In practice, this results in roughly 3x lower joint jitter that holds from simulation onto a physical Spot, suggesting that representation health is an effective training-time lens to track sim-to-real smoothness. --- ### Joint-Conditioned Stereo Surface Reasoning for Interaction Field Estimation Authors: Yanlin Jin, Yifan Yang, Bowen Yang, Kai Zhu Published: 2026-09-07 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.06955v1 Predicting hand--object interaction fields requires locating the nearest object-surface point for each hand joint, often from small and partially occluded image regions. We view this task as joint-conditioned surface-endpoint estimation: each joint has its own nearest endpoint, while endpoints from the same hand can draw on shared local surface evidence. This structure motivates Joint-Conditioned Stereo Surface Reasoning (JSSR). A temporal-stereo network jointly predicts 3D joints, a direct interaction field, and per-view endpoint evidence. Calibrated candidate search evaluates endpoint hypotheses using joint-specific image compatibility and cross-view correspondence. A hand-shared candidate support lets joints draw on common surface evidence, and a learned residual gate controls the geometric correction when observations are ambiguous. Our system built on this method ranked third on the SHOW3D Interaction Field Challenge leaderboard. --- ### Steering Interference Reflects the Model's Defaults, Not the Behavior Directions Authors: Srikanth Malla, Chiho Choi, Joon Hee Choi Published: 2026-09-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.06951v3 Activation steering promises modular control of language model behavior: a behavior such as politeness corresponds to a direction in a model's activations, and adding that direction while it generates should switch the behavior on and leave everything else alone. It does not. We ask what decides which other behaviors move, and by how much, and find that it is the model rather than the behavior being steered. A steer relaxes the model toward a small set of behaviors it already favors, chiefly refusal, sycophancy, and poeticism, and that set is much the same whatever is steered. Three results across 24 behaviors and ten instruction-tuned models support this, every effect read off the generated text by a language-model judge rather than off a probe. That readout matters: all 24 behaviors are linearly decodable, but only 20 change what the model writes. First, a direction carrying no behavioral content, matched to a real steer only in the size of the vector it adds, moves the same behaviors in the same order as real steers do, while producing none of the behaviors that need a specific direction. Second, most interference runs one way, so it cannot be an overlap between two directions: steering profanity makes the model toxic, while steering toxicity leaves profanity untouched. Third, with a behavior held out entirely, geometry measured on the others explains almost none of the interference it takes part in. The account holds on all ten models, the pull toward defaults strongest below 10B parameters and weakening in each family's largest. Reading a steer as a perturbation whose endpoint the model fixes implies that disentangling behavior directions cannot by itself make steering modular. --- ### PRG-Fusion: Orchestrating Generative Priors with Reconstruction Evidence for Driving View Synthesis Authors: Sipeng He, Jialei Chen, Zhen Fang, Dongchun Ren, Feng Zhao Published: 2026-09-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06948v1 Synthesizing photorealistic driving videos along specified trajectories is essential for scalable closed-loop simulation. Reconstruction-based methods leverage neural rendering to synthesize geometrically consistent views, but often exhibit diverse artifacts and missing content when the viewpoint deviates from the training trajectory. In contrast, generative models can synthesize realistic views along arbitrary trajectories from vehicle sensor data, yet often struggle to maintain temporal and geometric consistency across frames. To combine the strengths of both, we propose PRG-Fusion, a framework for driving view synthesis that uses reconstruction evidence to orchestrate generative priors across regions. Specifically, we extract region-wise degradation evidence from reconstructed driving scenes and convert it into Preserve, Repair, and Generate (PRG) labels. At inference, these labels serve as a unified routing policy for region-aware spatiotemporal synthesis, orchestrating 3DGS appearance preservation, LiDAR-guided structural correction, and video-prior-driven content completion across Preserve, Repair, and Generate regions, respectively. We then follow a two-stage training paradigm, first establish geometric control from sparse LiDAR projections and subsequently learning appearance control from dense 3DGS renderings. Extensive experiments on Waymo demonstrate that PRG-Fusion achieves state-of-the-art overall performance in novel trajectory video synthesis, with superior visual quality and geometric fidelity while maintaining competitive view consistency under large trajectory shifts. --- ### Particle Dynamics of Flow Matching and Classifier-Free Guidance from a Stagewise Geometry Perspective Authors: Jian-Feng Cai, Zhengyi Su, Chao Wang Published: 2026-09-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06947v1 Flow matching, together with classifier-free guidance (CFG), is widely used in generative modeling, yet much of the theoretical understanding remains distribution-wise. Since practical sampling follows individual trajectories, distribution-level guarantees alone do not fully capture how trajectories interact with the data geometry or how guidance reshapes it. To overcome this limitation, we establish a unified stagewise geometric theory of attraction and absorption for both continuous dynamics and explicit Euler discretization. Specifically, with $t\in(0,1)$ running from noise to data, we show that unconditional flow trajectories are successively attracted toward a neighborhood of the global mean, the data convex hull, and a neighborhood of a possibly nonconvex local cluster. Across these stages, the corresponding distance satisfies a common contraction estimate, yielding an ${O}(1-t)$ decay of the distance in the final stage. For CFG, the same structure persists with an extrapolated mean, an inflated conditional convex hull, and, near the target cluster, the restored local geometry of conditional flow matching. We further show that a general time schedule $a(t)$ replaces the $O(1-t)$ decay by $O(1-a(t))$. Together, these results provide a unified particle-level geometric account of flow matching and CFG across continuous and discrete sampling. ---