# Research Papers — 2026-09 · bundle page 5 of 266 > Full-text markdown of papers #201–250 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/5 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/4.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/6.md) ### LatentHarness: Learning Latent Actions for Memory and Reasoning via Counterfactual Policy Distillation Authors: Xiaoqiang Wang, Suyuchen Wang, Bang Liu Published: 2026-09-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.39740v1 Long-context reasoning faces two complementary bottlenecks: retaining evidence across long inputs and sustaining computation across many reasoning steps. Existing approaches largely address them separately, with external memory extending access to distant evidence and latent reasoning compressing multi-step computation. We introduce LatentHarness, which unifies memory access and latent reasoning as sequential latent action selection. At each internal step, the model chooses THINK for further computation, RECALL from a fast-weight memory of input evidence and intermediate reasoning states, or EXIT to emit the next token. We train this policy with counterfactual policy distillation, which branches every action for one step and scores its effect on the emitted token. These gains teach the policy when memory is more useful than further reasoning, while gradients through counterfactual recall teach which intermediate states should be retained in memory for future use. Across six general and long-context reasoning benchmarks, LatentHarness at 1.4B improves on the strongest baselines by 2.8% and 10.0% relative, respectively, and runs 5.9x faster than the strongest long-context baseline. --- ### Stable Transformers for Graph Generation Authors: Luca Miglior, Alessio Gravina, Davide Bacciu Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39739v1 Graph generative models increasingly rely on Graph Transformers (GT) to capture complex dependencies among nodes and edges. While deeper architectures should provide greater expressive capacity and a broader receptive field, their effectiveness can decline with depth: repeated self-attention progressively contracts node representations, impeding information flow and gradient propagation. We analyse this phenomenon from a dynamical systems perspective, focusing on how the denoiser's spectral dynamics affect graph generation. We show that standard GT denoisers become increasingly dissipative as depth grows, leading to vanishing gradients and representation collapse. To isolate the effect of these dynamics, we construct a permutation-equivariant GT with inherently stable, non-dissipative transport. We also introduce a damping mechanism that continuously interpolates between non-dissipative and increasingly contractive regimes, enabling a direct assessment of how dissipation influences generation. Experiments on synthetic and molecular graph generation benchmarks show that the gap between these regimes widens with depth: non-dissipative dynamics preserve representation diversity and gradient flow, sustaining strong generative performance, whereas greater contraction progressively impairs it. These findings identify the denoiser's dynamical regime as a key design factor for deep graph generative models. --- ### CNCGEN: A Dataset and Framework for Machining Process Planning and Toolpath Generation from B-rep Models Authors: Xiaolei Zhou, Boyi Lin, Yuchao Feng, Jianwei Zheng Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39738v1 Learning to generate machining process plans and toolpaths from B-rep CAD requires coupling discrete operation decisions with continuous tool motion as the workpiece evolves. Correctly predicting an operation sequence does not by itself ensure correct material removal, because each toolpath acts on the stock left by preceding cuts. We formulate this problem around persistent manufacturing objects: object identity determines the target of an operation, while the evolving stock state conditions the generation of its toolpath. Based on this formulation, we propose CNCGEN, a dataset and learning framework for three-axis machining. CNCGEN-Dataset contains approximately 50k geometrically verified synthetic machining flows and 800 held-out real CNC records. Each flow aligns B-rep geometry with object-referenced operations, parameterized toolpaths, intermediate stock states, and verification outcomes, enabling supervision of the correspondence between planning decisions and their geometric effects. CNCGEN generates operations and toolpaths for selected objects step by step, updating a compact machining state to guide subsequent predictions. During training, a learned surrogate verifier provides material-removal feedback that links local predictions to their geometric consequences. Experiments on synthetic and held-out real CNC records show that CNCGEN improves the resulting workpiece geometry and reduces residual material and overcut compared with adapted CNC generation baselines. --- ### A library for differentiable signal processing and machine learning on the sphere Authors: Thorsten Kurth, Max Rietmann, Mauro Bisson, Andrea Paris, Alberto Carpentieri, Jean Kossaifi, Anima Anandkumar, Christian Hundt, Boris Bonev Published: 2026-09-30 Categories: cs.LG, physics.ao-ph, physics.geo-ph arXiv: https://arxiv.org/abs/2609.39737v1 The two-dimensional sphere embedded in three-dimensional Euclidean space S2, plays a central role in a variety of scientific and engineering domains, including geophysics, planetary science, geodesy, atmospheric physics, quantum chemistry, cosmology, and virtual reality, among many others. As machine learning increasingly permeates these fields, the demand grows for robust tools that process and model functions on the sphere, while respecting the inherent topological and symmetry properties of the domain. We present torch-harmonics, a comprehensive library that offers efficient, differentiable implementations of advanced signal processing and machine learning (ML) methods for spherical data. These include the spherical harmonic transform (SHT), the spherical analogue of the Fourier transform, vector spherical harmonics, discrete-continuous and spectral convolutions, as well as both global and neighborhood spherical attention mechanisms. Beyond traditional representations, torch-harmonics provides the building blocks for state-of-the-art spherical ML architectures such as spherical transformers in order to enable scalable, rotationally-aware learning and inference in modern scientific and engineering applications. --- ### OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation Authors: Oana Madalina Fron, Ojas Shirekar, Chirag Raman Published: 2026-09-30 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2609.39727v1 Cooperative language-model agents must coordinate over long horizons and adapt to changing environments and to partners with unfamiliar conventions, yet existing agents map observations to actions without separating persistent coordination strategies from their tactical execution. We introduce OverForge, a training-free hierarchical architecture that separates strategic reasoning over roles and divisions of labour from tactical reasoning over actions within each agent's private, partner-conditioned world model. A metacognitive Prefrontal Cortex Module couples the two levels by forming strategy-action branches, imagining their consequences with a forward model, and committing when confident. In OvercookedV2, OverForge delivers 7 soups in a connected kitchen versus 3 for each flat LLM baseline, retains agreed roles, and adopts roles proposed by unfamiliar partners. Ablations and a fixed-strategy probe show that persistent strategies guide tactical adaptation while each reasoning level contributes to coordination. Memory restarts show that cross-episode partner knowledge supports task performance and partner prediction, linking the hierarchy to continual adaptation. --- ### Let the Carrier Carry the Attack: Preserving the Subject in Adversarial Image Generation Authors: Linfeng Jiang, Steven McDonagh, Yuhang Chen, Xingyu Zhao, Siddartha Khastgir, Andi Zhang Published: 2026-09-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.39723v1 Strong unrestricted adversarial attacks can distort the primary object of an image, hereafter referred to as the subject. To preserve subject integrity without compromising attack magnitude, we introduce the carrier: a secondary visual element that provides an auxiliary region to facilitate the attack under global classifier guidance. We demonstrate three key findings: 1. A carrier mitigates subject distortion by absorbing a larger share of globally normalized attack updates. 2. A carrier improves cross-model transferability, governed by the strength of target-related features that balance semantic separation and transfer performance. 3. Successful targeted attacks retain the personalized subject as the primary content perceived by humans while successfully misleading the classifier. Our results demonstrate that a visually secondary carrier offers an auxiliary spatial pathway for adversarial changes, enabling strong and transferable attacks while improving subject preservation. --- ### Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents Authors: Serhii Zabolotnii Published: 2026-09-30 Categories: cs.AI, cs.CY, cs.SE arXiv: https://arxiv.org/abs/2609.39717v1 Benchmarks, audits, and agent protocols describe performance, permissions, and repair, but not how observed evidence should change an agent's authority during a consequential task. We call this the assurance-transition gap. We propose a Runtime Assurance Contract (RAC), a policy-level formal schema binding autonomy boundaries, component eligibility, evidence state, transition policy, human-review capacity, and non-compensatory gates. Under RAC, soft metrics may inform routing, whereas a failed or unknown mandatory gate forces retry, switch, escalation, deferral, or stop; aggregate performance cannot authorize action. We define the contract, an evidence record, a permission rule, and five invariants, and illustrate them in clinical, industrial, and judicial failure probes. We then report a deterministic failure-injection study in agentic coding: 280 constructed cases evaluated by a gate conjunction, a score-only rule, and a restricted protocol baseline. At the published example weights and threshold, the score rule admits 80 of 100 block-required injections and all 40 review-required injections. Tuned in hindsight, it matches the conjunction on this corpus. For positive weights, a positive threshold, binary risk signals, zero-signal controls, and an injected case firing each signal alone, we show that exact agreement holds if and only if the threshold does not exceed the smallest weight. A separate set of 18 hand-authored traces checks version-pinned evidence and review transitions against simpler policy variants. In a further prospective synthetic holdout of 24 episodes, two blinded LLM judges assign identical labels to all 72 action attempts; RAC and a separately implemented full stateful baseline both match these labels. These studies test mechanisms on synthetic cases; they establish neither deployed safety nor cross-domain effectiveness. --- ### ArchitectureIQ: On the Measure of Training Intuition Authors: Zirui Ren, Shaoyang Guo, Chencheng Tang, Jinxin Wang, Chengyu Xiong, Shanbin Yu, Peihang Li, Yidi Wu, Bangzhe Huang, Qingyu Qu, Leqian Yang, Ziming Liu Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.39714v1 Top researchers have good intuition, but do language models have as good intuition about model training as top AI researchers? To measure model intuition of LLMs and humans, we introduce the ArchitectureIQ benchmark. Each question presents a synthetic dataset and several training recipes, and the test-taker is asked to predict the recipe yielding the best test metric. Overall, we find that LLMs' model intuition is good but has four limitations: (1) The intuition is imperfect, or even sub-human in some cases. Frontier models achieve around 76% accuracy (random choice 33%) vs best human researcher (66.0%), yet remain far from perfect. For architecture-only questions, best human achieves 65% while GPT-6 Astra only has 38%. (2) The intuition is empirical, not structured, supported by the fact that more CoT compute does not lead to substantial improvement. Unlike math, we still lack a "Science of AI" language that enables structured reasoning on AI. (3) The intuition is not maximally condensed, and can be further compressed into a knoledge base. Our constructed knowledge base with only 20 items yields large gains for weak models: GPT-4o equipped with the accumulated knowledge almost matches the performance of Claude Opus 5. (4) The intuition is insensitive to dataset properties, but the best model should in general depend on data properties. This suggests that data is the real "dark matter" in AI -- LLMs (so do human researchers) understand too little about data, even less than model architectures. --- ### Amortized ratio-estimation importance sampling and localized simulation-based calibration for intractable likelihoods Authors: Umberto Picchini Published: 2026-09-30 Categories: stat.ME, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2609.39712v1 We consider simulation-based Bayesian inference (SBI) for the parameters of models with intractable likelihoods but tractable forward simulation. Building on Gaussian mixtures-of-experts surrogates, as a first contribution we develop a sequential procedure for posterior estimation in which progressively localized, data informed, conditional density approximations are used as proposal distributions. A final surrogate of the posterior distribution is then corrected using an importance sampling step that introduces a locally amortized likelihood-to-evidence ratio estimator. A second contribution is localized simulation-based calibration (SBC). Localized SBC probe calibration over neighborhoods that are deliberately broader than the available posterior, at low additional computational cost. Rather than repeatedly running the full inference procedure for each simulated pseudo-observation, localized SBC fits the local surrogate and ratio estimator only once for each local design, and reuses them across all pseudo-observations. This approach is particularly appealing for SBI applications. We evaluate both contributions on three case studies, including a real-data epidemiological application. --- ### Drift Inspector: Exploring and Measuring Scientific Drift with Atomic Contribution Claims Authors: Vsevolod Karimov, Stepan Ostarkov, Anastasia Poroshina, Anatoly Frolov, Alexander Panchenko Published: 2026-09-30 Categories: cs.CL, cs.DL arXiv: https://arxiv.org/abs/2609.39710v1 Scientific abstracts mix contributions with background, motivation, and meta-language, so tools that read them as-is cannot separate what a field produces from what it discusses. We present Drift Inspector, an open-source system for measuring and exploring how a research field changes over time at the level of Atomic Contribution Claims (ACCs): decontextualized, contribution-bearing propositions an LLM extracts from each abstract before analysis. The system clusters these claims across years into an interactive map where every trend traces back to the claims and papers behind it. Applied to six years of EMNLP, it shows the field shifting away from classic NLP tasks toward LLM-era capabilities such as reasoning and multimodality -- a movement that keyword or whole-abstract counts blur. The released data extend beyond EMNLP: the same pipeline has processed the full ACL Anthology (346k claims, 80k abstracts, 423 venues). Extraction is human-validated and clustering checked against an external manually constructed taxonomy. --- ### BTC3D: Blended Tile Conditioning for Detail-Enhancing Image-to-3D Generation Authors: Junyu Li, Qiuyu Chen, Pengcheng Wang, Shiqi Yang, Alexandra Gomez-Villa, Joost van de Weijer, Ruilin Li, Kai Wang Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39709v1 Recent diffusion-based pipelines have achieved promising progress in image-to-3D synthesis. However, generating high-fidelity details remains challenging, especially when the input image contains rich details. Existing approaches often rely on globally encoded conditioning features, which compress spatial information and limit the model to reproduce fine-grained details. This common design often leads to a phenomenon we term detail attenuation. Moreover, improving image-to-3D synthesis quality typically requires retraining or fine-tuning large diffusion models, which can be computationally expensive and impractical for complex 3D pipelines. In this work, we present Blended Tile Conditioning for image-to-3D generation (BTC3D), a training-free inference time framework that enhances fine-grained detail preservation in image-to-3D diffusion pipelines. To alleviate detail attenuation, we first examine the image feature additivity in image-to-3D models. Based on this property, we introduce a blended tile embedding that extracts local conditioning signals from split image regional patches, allowing the diffusion model to better preserve fine-grained visual details. To integrate the global and local conditioning guidance stably, we propose a dynamic conditioning schedule that gradually increases the influence of tile-level conditioning during later low-noise stages of diffusion. Our proposed method BTC3D operates entirely at inference time and can be seamlessly integrated into existing image-to-3D diffusion pipelines. Experimental results demonstrate that the proposed approach significantly improves texture quality and visual fidelity of the base model while maintaining global structural consistency in a training-free manner. --- ### When Masking Helps or Hurts Robustness in Compressed CLIP: A Pre-Deployment Diagnostic Authors: Muhammad Zawish, Steven Davy Published: 2026-09-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.39704v1 This paper demonstrate that whether masking-based token pruning helps or hurts worst-group robustness can be predicted before deployment, without labels or fine-tuning. A systematic study of semantic masking across 8 spurious-correlation benchmarks shows its effect on worst-group accuracy is highly unstable: it improves accuracy by up to 82.5\% relative on some datasets and degrades it by up to 100\% on others. We trace this instability to spurious inversion: background patches receive higher CLIP text-similarity than the true object when the spurious attribute is background-separable, inverting the assumption every text- and attention-guided pruning method relies on. We introduce the Spurious Inversion Metric (SIM), a label-free, pre-deployment diagnostic whose sign predicts this effect with statistical significance (binomial $p=0.035$) across all 8 datasets, and remains dependable across 6 CLIP architectures with a clean foreground/background split. Naive masking is itself a major source of risk: it causes the largest average-accuracy loss of any method we evaluate, and its own per-image segmentation step is a significant runtime bottleneck. To address this, we design a batched, synchronization-free GPU segmentation routine that cuts this overhead from 3.5$\times$ to 1.75$\times$ baseline. Gating deployment by SIM's sign recovers masking's benefits while avoiding its worst failures, matching or exceeding a strong pruning baseline on 7 of 8 datasets. --- ### A helps B while B hurts A: directed transfer in instruction-tuning mixture Authors: Nima H. Siboni, Vahid Rostami Published: 2026-09-30 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.39702v1 Adapting a language model to a specialized corpus means choosing which instruction-tuning tasks to train on under a fixed budget, and testing one choice costs a fine-tuning run. Common heuristics add more source tasks or pick sources similar to the target. The first assumes transfer is never negative; the second, that it is symmetric. We show that both assumptions fail: task $A$ can help task $B$ while $B$ hurts $A$, so helpfulness is a signed property of ordered source--target pairs. We introduce the transfer map, a signed estimate of how much each source helps or hurts each held-out target. We fit the map in hundreds of fine-tuning runs on Qwen3 and Mistral models from 0.6B to 32B parameters, with all sources drawn from one corpus and no training examples from the target. The map predicts a held-out target's accuracy on unseen mixtures: recorded before those runs, its predictions have less than half the error of a mixture-agnostic baseline. The map is specific to its target and corpus but transfers across model scale: a mixture selected in advance at one size beats training on all source tasks at every other size we tested. Transfer is thus a property of the data. The map selects the tasks that help and drops the one that interferes: accuracy on the reasoning targets (causal explanation, multi-hop questions and methodological critique) rises by up to 14 percentage points over training on all source tasks. --- ### Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering Authors: Jiale Dai, Hongcan Deng, Liuxian Ma, Xiaoke Niu, Guojie Song Published: 2026-09-30 Categories: cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2609.39701v1 Value steering should change an LLM's normative priorities while preserving the scenario, facts, and task constraints underlying its answer. Conventional activation edits often change both. We introduce an editable semantic-value interface on frozen residual states, with a one-way semantic-to-value pathway that grounds value recognition in context. Stop-gradient blocks feedback through this pathway; swap consistency, topic de-confounding, and decorrelation encourage selective codes. At inference, editing the value code produces a residual delta while holding the semantic code fixed. On two instruction-tuned backbones, this interface improves semantic preservation and reduces benign refusals at comparable value alignment. A matched mixing-by-gating ablation separates representation learning from selective edit activation, and dimension-matched probes establish improved code selectivity. Against validation-selected prompting on LLaMA-3.1-8B, the method achieves comparable alignment (0.750 vs. 0.748), higher BERTScore (0.938 vs. 0.923), and fewer contradictions (5.1% vs. 7.6%). Human ratings and cross-taxonomy controls provide complementary evidence for low-damage value steering. --- ### GFD-OPD: Guidance-Folded On-Policy Distillation of Diffusion Models Across Scales Authors: Zhenxing Zhang, Jiayan Teng, Wenxu Wu, Zhuoyi Yang, Jiazheng Xu, Wendi Zheng, Jie Tang, Dan Guo, Meng Wang Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.39692v1 On-policy distillation (OPD) has demonstrated two important capabilities in language models: compressing large teachers into smaller students and merging expert models into a single model. Existing diffusion OPD, however, mostly focus on the latter, with teachers and students sharing the same backbone and scale. We investigate large-to-small diffusion opd from large teachers to a small student and find that the standard recipe fails. To find the underlying cause, we propose Fixed-State KL, an effective and fair way to measure the distribution gap between student and teacher during OPD training for diffusion models. We are the first to clarify why large-to-small OPD is challenging for diffusion models: a smaller student struggles to perfectly match the distribution of a larger teacher, while classifier-free guidance can accumulate and amplify the distributional discrepancies between the student's conditional and unconditional branches and those of the teacher. To solve this problem, we propose GFD-OPD, a simple yet effective method that reduces the student-teacher gap while avoiding the error amplification of the CFG composition. Across numerous experiments, GFD outperforms previous baselines in both training efficiency and final performance, achieving state-of-the-art results on all benchmarks. --- ### ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models Authors: Tobia Poppi, Silvia Cappelletti, Samuele Poppi, Marcella Cornia, Lorenzo Baraldi, Diego Garcia-Olano, Rita Cucchiara Published: 2026-09-30 Categories: cs.CV, cs.AI, cs.CL, cs.MM arXiv: https://arxiv.org/abs/2609.39688v1 Multimodal encoders such as CLIP underlie many downstream systems, but their web-scale training data embed harmful associations that safety alignment must suppress without unnecessarily changing benign representations. Because ethical and practical constraints prevent collecting real unsafe content at scale, existing datasets pair safe real samples with generated counterparts, but label every generated sample unsafe, even when one modality is individually safe. To address this, we introduce ShieldCLIP, the first framework to condition safety alignment on the observed safety state of each modality rather than the origin of a sample, preserving safe content while redirecting only what is unsafe. We also introduce ViSUv2, a 195k-quadruplet dataset with independent per-modality safety labels across 578 concepts and 28 categories. Using these labels, ShieldCLIP defines a four-way conditional objective beyond pair-level supervision: safe content is anchored, unsafe modalities are redirected to their safe counterparts, mixed pairs update only the unsafe branch, and coherence is enforced when both are unsafe. We evaluate ShieldCLIP on cross-modal retrieval, text-to-image generation with Stable Diffusion v1.4 and SDXL, and image-to-text generation with LLaVA. Across these settings, ShieldCLIP consistently reduces harmful outputs over prior safety-aligned encoders and strong mitigation baselines, while preserving the utility of the original embedding space. Extensive ablation studies further show that both modality-specific supervision and the selective alignment objective contribute to these gains. Source code, trained models, and ViSUv2 (under a controlled-access protocol) will be made publicly available at https://aimagelab.github.io/ShieldCLIP/. --- ### Better Supervision Is Nearby: Neighborhood On-Policy Self-Distillation Authors: Xincheng Wei, Yifan Ding, Yoshua Li, Yuquan Lu, Ziheng Li, Yi Lu, Dongsheng Ma, Rongxiang Weng, Xunliang Cai Published: 2026-09-30 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.39687v1 On-policy self-distillation (OPSD) trains mathematical reasoning models using a privileged teacher that sees a reference solution and supervises student-sampled prefixes. Standard OPSD uses one fixed parameter setting at every state, but nearby settings may offer additional supervision. We find that local parameter perturbations reveal complementary reference-aligned corrections under the same reference context. Different experts supply these corrections at different reference positions. Their pool covers more such positions than the unperturbed privileged teacher. We introduce Neighborhood OPSD (N-OPSD) to turn these corrections into supervision at student-visited states. Offline, greedy selection builds a compact pool of frozen experts by rewarding filtered reference-token gains beyond the pool's current best at each position. The highest-peak expert need not provide the best training target. Online routing therefore separates the anchor direction from its level of support. MaxPeak selects the anchor token, and quantile selection chooses among experts whose top token matches it. The student learns from the chosen expert's full next-token distribution through the clipped forward-KL objective inherited from OPSD. We evaluate on AIME 2024, AIME 2025, and HMMT February 2025. Across three independent runs per method, Neighborhood OPSD improves the three-benchmark Average@12 over OPSD by 2.75, 1.67, and 1.94 points on Qwen3-1.7B, 4B, and 8B, respectively. Student-prefix continuations support using the pool beyond the reference trajectories used for selection. Matched ablations support filtered reference-token gains as a selection criterion. Accounting for overlap within the pool and routing by state further improve student accuracy. Inference uses only the distilled student. --- ### RoboCoach: World Models as Active Coaches for Compositional Robot Skills Authors: Jiajun Liu, Yifan Chen, Yichao Liu, Jiayi Zhang, Ruoqu Chen, Shaoxuan Xie, Guocai Yao, Mengdi Xu, Sen Cui, Changshui Zhang Published: 2026-09-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.39685v1 Long-horizon robot manipulation reuses skills across many task compositions, but improving these compositions with additional end-to-end demonstrations is costly. A practical self-improving system must decide both what to teach next and where to apply that supervision. We present ROBOCOACH, a world-model-guided coaching framework that uses imagined failures to guide demonstration requests and expert updates. Its Route-Imagine-Diagnose-Improve (RIDI) loop executes reusable skill experts inside COACHWORLD, our shared action-conditioned world model, and uses a progress judge to record the first subtask that fails to complete. Aggregated records select which subtask demonstrations to acquire and which expert adapters to update. Across two simulation suites and two real-robot platforms, imagined and deployed success correlate over 22 task-policy pairs (rho = 0.840). Controlled comparisons show that our coaching method outperforms matched baselines under matched data budgets and update schedules. With only 150 additional subtask demonstrations, success rises from 13.3% to 75.0% on Franka and from 40.0% to 83.8% on AgileX. The coached experts also transfer to four held-out compositions, achieving an average success of 35.0%, compared with 0% for a shared-policy baseline updated with uniformly acquired demonstrations. Together, these results show that world models can serve as active coaches, turning imagined failures into targeted supervision for modular policy improvement. Project Page: https://robocoach-ai.github.io/ --- ### Unapologetically Distributed: A Call for Decentralized Document Analysis Authors: Adrià Molina, Oriol Ramos Terrades, Josep Lladós Published: 2026-09-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.39684v1 Privacy has become an increasingly important concern in the Document Analysis community, to the extent that in many environments such as archives, governmental institutions, and local businesses, the adoption of automation is restricted by legal and policy constraints. While federated learning has often been regarded as a ``necessary evil'', implying an unavoidable performance trade-off in exchange for decentralization and privacy, many prior works overlook its potential to improve robustness to out-of-distribution data. In this paper, we present Unapologetically Distributed, the first comprehensive study evaluating distributed learning in Document Analysis along three key axes simultaneously: the tasks addressed, the architectures employed, and the fine-tuning strategies applied. Specifically, we demonstrate how various distributed training approaches enhance generalization capabilities across diverse tasks such as Table Recognition, handwriting recognition, and Word Spotting, particularly during transfer learning stages. Our results provide strong evidence that decentralization is not merely a constraint, but a valuable opportunity to improve model robustness and adaptability in real-world Document Analysis scenarios. --- ### MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentation Authors: Ivan Martinović, Josip Šarić, Yuki M. Asano, Siniša Šegvić Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39681v1 Unsupervised domain adaptation (UDA) reduces the annotation burden in panoptic segmentation by leveraging a cost-effectively labeled source domain (e.g., synthetic) and an unlabeled target domain to bridge the distribution gap. Existing panoptic UDA methods rely on teacher-student consistency learning built upon suboptimal per-pixel segmentation architectures. In contrast, state-of-the-art mask transformers are rarely adopted due to their pronounced vulnerability to confirmation bias in consistency learning, where erroneous teacher predictions are reinforced during training. Our earlier approach, MC-PanDA, mitigates this issue through fine-grained confidence estimation, which suppresses gradients from unreliable masks while sampling informative yet reliable locations for loss computation. However, this method entails a complex multi-stage training and requires careful hyperparameter tuning. This work presents MC-PanDA++, which addresses these limitations by introducing: (i) self-supervised vision encoders that provide a stronger and more robust initialization, further reducing the reliance on human annotations, (ii) per-class, self-adapting mask-wide loss scaling that stabilizes training and enables the usage of a single set of hyperparameters across domains, and (iii) a single-stage training pipeline that decreases overall conceptual complexity. Together, these improvements result in a conceptually simpler, better-performing, and more robust method for domain-adaptive panoptics. Source code: https://github.com/martinovicivan/MC-PanDA --- ### SE-ADD: Self-Evolving Audio Deepfake Detection with Mistake-Driven Supervision Authors: Rong Wan, Wei Xie, Jiaxi Li, Wenwu Wang, Lu Yin, Yiliao Song, Xilu Wang Published: 2026-09-30 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2609.39679v1 Audio deepfake detection (ADD) must remain effective when new spoofing attacks emerge after deployment. Emerging audio language model (ALM)-based ADD methods are built on predefined supervision from ground-truth labels or verified forensic rationales. However, this paradigm overlooks an ALM's own mistakes, which indicate where targeted supervision is most needed. To this end, we first introduce evolving spoofing environments for ALM-based ADD, where a new attack becomes dominant while previously observed attacks persist. Motivated by the above learning-from-mistakes perspective, we further propose SE-ADD, a self-evolving framework that iteratively adapts an ALM via low-rank adaptation (LoRA) using mistake-driven supervision built from its verdicts and self-generated forensic cues. All training samples receive direct authenticity supervision, while misclassified ones receive additional cue-augmented supervision. As verdicts and cues are regenerated by the updated ALM, the resulting supervision evolves accordingly. Experiments on two ALMs demonstrate the effectiveness of SE-ADD in generalizing to unseen attacks, reducing the equal error rate (EER) from $36.72\%$ to $7.52\%$ for Qwen2-Audio and from $19.93\%$ to $3.97\%$ for MOSS-Audio. --- ### NodeGround: A Node Classification Benchmark in the Graph Foundation Model Era Authors: Jinmo Lee, Dooho Lee, Minho Jeong, Jaemin Yoo Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39673v1 Can a pretrained graph model replace training and tuning a separate predictor for each dataset? Answering this requires evaluating prediction quality alongside computational cost. We present NodeGround, a node classification benchmark that puts graph foundation models (GFMs) and dataset-specific supervised learning under a common evaluation framework. The benchmark spans 51 datasets and evaluates six GFMs alongside 15 supervised methods under two label-availability regimes. Shared data partitions, validation-only model selection, controlled hyperparameter searches, and multiple predictive metrics make comparisons systematic, while workflow measurements account for adaptation, training, tuning, and inference. The results favor carefully tuned graph neural networks overall. GraphPFN reaches third place by Elo when more labels are available, yet its relative strengths vary substantially with dataset properties. Efficiency comparisons further qualify the benefits of pretrained reuse: GVT and GraphPFN appear on the Pareto frontiers when supervised methods are represented by their default and fully tuned configurations. Adding intermediate tuning budgets removes this advantage for GVT and leaves GraphPFN extending the estimated frontier in the label-rich setting alone. Thus, reusing pretrained parameters does not yet provide a broadly reliable route to either stronger predictions or cheaper workflows. We release the evaluation pipeline, run-level records, and an open leaderboard at https://github.com/nums-ai/nodeground. --- ### ChronoGraph: Functional 4D Scene Graphs with Vision-Language Models for Interaction Understanding and Grounded Planning Authors: Chenyangguang Zhang, Malgorzata Gwiazda, Guanlong Jiao, Yuanchen Ju, Federico Tombari, Koushil Sreenath, Marc Pollefeys, Sunghwan Hong Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.39665v1 Embodied agents must determine where to act, anticipate the resulting scene changes, and interpret observed outcomes to guide subsequent actions. This requires connecting 4D interaction understanding, which explains how past actions changed the scene, with spatially grounded planning, which determines how and where to act toward a goal and anticipates the resulting scene changes. We introduce ChronoGraph, a functional 4D scene graph that links actions on affordance parts to semantic and geometric state changes. By representing observed and anticipated transitions in the same form, it provides a shared basis for understanding and planning. We construct ChronoGraphBench through an automatic data engine that converts human-interaction videos and simulated robot trajectories into graph-annotated questions for training and evaluating Vision-Language Models (VLMs) on both tasks. Using these annotations, we train ChronoGraphVLM by adapting pretrained VLMs in two stages. Graph-as-Chain-of-Thought supervised fine-tuning teaches the models to reconstruct observed transitions and predict future ones as graph traces before answering. Subsequent joint 4D graph reinforcement learning directly rewards graph properties and answer correctness. Experiments across model scales show improvements over the corresponding pretrained baselines and zero-shot transfer to VLM4D. Real-world demonstrations further show that graph-based planning and affordance grounding support mobile manipulation through existing robot skills without additional fine-tuning. --- ### Typographic Attack Against VLM-based AI-generated Image Detection Authors: Eunmin Lee, Jungwoo Kim, Jong-Seok Lee Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39662v1 Vision-language models (VLMs) are increasingly used for AI-generated image (AIGI) detection, providing natural-language explanations for authenticity judgments. However, their ability to interpret text within images may also expose these judgments to misleading semantic cues. We systematically evaluate typographic attack strategies across detection-oriented, open-weight, and commercial VLMs, considering both real-to-fake and fake-to-real attacks. Our results show that reasoning modes generally exhibit greater vulnerability than direct modes and that attack effectiveness exhibits pronounced directional asymmetry. Moreover, larger models tend to exhibit higher clean detection accuracy but also higher attack success rates. We further examine attack robustness under image and text transformations and investigate whether overlays indicating the correct class can aid error correction. Together, these analyses characterize how typographic attacks influence authenticity judgments and expose limitations of current VLM-based AIGI detection systems. --- ### The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends Authors: Zhentao Tan, Jingyi Shen, Yanbo Li, Yao Liu, Yue Wu, Jieping Ye Published: 2026-09-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.39661v1 Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value cache growing with context length. Research thus spans explicit-memory compression, sparse access, recurrent state construction, structured state dynamics, and heterogeneous mechanism composition. This survey analyzes these developments as model-internal contextual memory. We introduce a five-dimensional lens---Memory Representation, Memory Update, Access, Readout, and Integration---describing what is represented, how it changes, what is query-eligible, how it is read, and how readouts form outputs. This lens compares overlapping research lines without imposing one computational model. We reconstruct mechanism-level developments and architectural adoption using 59 release-level records from 14 major model lineages and 11 high-performing open-weight endpoints. First, explicit-memory and recurrent-state methods retain distinct interfaces but increasingly control overlapping memory functions. Second, heterogeneous architectures increasingly coordinate across network depth: layer-wise composition distributes complementary memory processing across representational stages, while cross-layer reuse carries selected memory and routing artifacts forward. Depth thus becomes a dimension along which contextual memory is constructed and managed. Third, these developments motivate a stateful multidimensional memory-routing hypothesis: persistent memory is organized across temporal scope, network depth, substrate type, and representation granularity, while coordinated Sparse Write and Sparse Read determine what is maintained and what contributes to each query. Overall, efficient sequence architecture design increasingly concerns the organization, lifecycle, and selective use of contextual memory rather than an isolated Attention operator. --- ### BAM! Bayesian Anything Model: a foundation model for generative computational imaging Authors: Alessio Spagnoletti, Charlesquin Kemajou Mbakam, Jonathan Spence, Andrés Almansa, Marcelo Pereyra Published: 2026-09-30 Categories: cs.CV, stat.ML arXiv: https://arxiv.org/abs/2609.39660v1 Generative models are transforming Bayesian computational imaging, yet the field still lacks physics-aware foundation models. Current practice falls into two camps. Large foundation image models are deployed as plug-and-play priors with zero-shot approximate likelihood guidance, which introduces significant bias and computational cost. Physics-aware generative models avoid this bias, but each is tied to a specific dataset, task and instrument. We introduce BAM (Bayesian Anything Model), a lightweight foundation model for few-step, physics-aware posterior sampling that generalises robustly to unseen data and tasks, zero-shot or with minimal finetuning. BAM upgrades the operator-conditioned Reconstruct Anything Model (RAM) backbone (Terris et al.) into a conditional flow map, so instrument physics is specified at inference time rather than fixed during training. BAM has just 36M parameters and is pre-trained jointly on large image corpora and libraries of forward operators. A single network then draws posterior samples in a few steps, with no likelihood approximation and no guidance weights to tune. Across linear inverse problems on FFHQ, AFHQ, LSUN, DIV2K and the Kohler camera-shake benchmark, BAM outperforms in just 3 steps both specialised models and leading zero-shot methods in sample quality, at a fraction of their computational cost. BAM gives the community an accessible entry point to generative computational imaging, lowers the economic and environmental cost of training imaging models, and opens a new path for research on physics-aware Bayesian computational imaging. Official page: https://bayesian-anything-model.github.io/ --- ### Graph Residual Conjugate Diffusion: SNR-Equalized Heat Flow for Graph Signals Authors: Jinwei Li, Daniel Tenbrinck Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39658v1 Diffusion models generate data by reversing a forward corruption process that typically approaches a simple Gaussian prior. Recent work has extended this framework to signals supported on fixed graphs, e.g., road-network traffic and sensor-network measurements. Many graph signals have nonuniform spectral energy, whereas isotropic corruption adds the same conditional noise variance to every graph-frequency mode. Driving all modes to near-zero terminal signal-to-noise ratio (SNR) requires strong corruption, which increases the noise range that must be covered under a fixed sampling budget. We introduce Graph Residual Conjugate Diffusion (GRCD), which replaces the shared clock of graph heat diffusion with a mode-dependent clock that gives every graph-Fourier mode the same conditional SNR. GRCD fits a zero-mean graph-spectral Gaussian reference on the training split and stops at a finite terminal SNR at which the propagated reference still carries the fitted spectral variances. The Gaussian component has an exact modewise propagator in the probability-flow ODE, so sampling advances it analytically and integrates only the learned residual score numerically. We evaluate GRCD on five settings (METR-LA traffic, Molene weather, and three stochastic block models) against seven comparators under a matched protocol: Graph-Aware Diffusion (GAD), EDM (graph backbone), two adaptations of Whitened Score Diffusion (WSD), and three preconditioning controls. At four function evaluations (NFEs), GRCD lowers averaged maximum mean discrepancy (aMMD) by 22 to 36 times over the best comparator on all five settings, reaching 0.054 on METR-LA, where it clears an aMMD 0.1 target with 87% less sampling wall-clock time than the cheapest comparator that reaches it. Fitting the terminal reference reduces aMMD by 2.7 to 7.3 times at finite terminal SNR, while the factors shrink to 1.00 to 1.01 near zero. --- ### Diffusable Latents from Structure-Agnostic Distillation Authors: Adrien Ramanana Rahary, Nicolas Dufour, Patrick Pérez, David Picard Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39657v1 Distilling pretrained foundation models into an autoencoder bottleneck improves latent diffusability, enabling diffusion models to converge faster and reach higher sample quality. Standard distillation aligns the latent at each position to a co-located teacher feature, tying the latent layout to the teacher's. We show this constraint is unnecessary: aligning a single pooled image-level descriptor to the teacher's performs as well as or slightly better than dense position-wise distillation. We compare first-order and relational pooled objectives across latent shapes and teacher modalities. First-order matching extends naturally to 1D token-sequence latents and across modalities, where distilling a text encoder into an image autoencoder still improves diffusability; a relational objective based only on each image's nearest neighbours improves it as well. Code and blog post are available at https://github.com/AdrienRR/structure-agnostic-distillation and https://kyutai.org/blog/2026-09-28-structure-agnostic-distillation/. --- ### FANVIDv2: Evaluating Video Super-Resolution by Face and Licence-Plate Recognition Under Compound Degradation Authors: Kavitha Viswanathan, Vrinda Goel, Shlesh Gholap, Devayan Ghosh, Madhav Gupta, Dhruvi Ganatra, Sanket Potdar, Amit Sethi Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39649v1 Video super-resolution (VSR) is normally judged by PSNR and SSIM on clips that were downsampled bicubically, although in surveillance its purpose is to make faces and licence plates \emph{recognisable}. We present FANVIDv2, a benchmark that scores VSR by what a recognition pipeline can do with its output. FANVIDv2 provides $320\times180$ low-resolution (LR) clips with high-resolution (HR) references for 48 public figures (with one HR gallery image each) and 375 licence-plate clips covering 360 distinct plate strings. LR clips are generated with a randomised compound degradation (blur, resize jitter, sensor noise, JPEG compression, final downsampling) rather than bicubic downsampling alone. Two metrics score recognition \emph{inside} detections: FaceRecBox rewards a face only if it is localised and correctly identified, and TextRecBox scores plate transcriptions by normalised edit distance weighted by localisation quality. With a 2.3\,M-parameter VSR baseline (RCDM), FaceRecBox rises from 0.6864 to 0.7222, identity accuracy on matched faces from 84.35\% to 86.93\%, and TextRecBox from 0.3088 to 0.3667; a residual-map gated variant (RCDM-RMGF) reaches 0.3801 on plates. We describe the degradation model, the baseline architectures and the scorers in detail, and release annotations, metadata, download and degradation scripts and evaluation code. --- ### From Modes to Memories: Characterizing the Scale-Space Dynamics of Diffusion Models Authors: Cristina López Amado, Marco Fumero, Francesco Locatello Published: 2026-09-30 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.39648v1 Diffusion models are typically viewed as stochastic processes that transform noise into data. We take a complementary perspective: a diffusion model defines a family of deterministic dynamical systems indexed by noise scale. At each fixed scale $σ$, we treat the denoiser as a self-map and study its dynamics. For an exact denoiser, fixed points correspond to critical points of the smoothed data density, while attractors correspond to its modes; as $σ$ increases, sample-level modes merge into progressively coarser ones. This suggests a geometric view of memorization: examples that receive excess probability mass due to duplication or overfitting, as well as outliers, should remain distinguishable under stronger smoothing than ordinary examples. We quantify this persistence by the critical scale $σ_c$, the largest noise scale at which an example is retained by the fixed-scale dynamics. In conditional models, the same construction extends naturally to image--caption pairs. Experiments in controlled settings and on large-scale models show that $σ_c$ tracks memorization arising from duplication, overfitting, and outliers, and identifies both memorized and partially memorized examples in Stable Diffusion. Moreover, $σ_c$ yields interpretable measures of the image spatial distribution and caption dependence of memorization. --- ### Beyond Uniform Compression: Budgeted Transmission Allocation for Extreme Federated Learning Authors: Pengfei Li, Mohammad Khalil Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39646v1 Federated learning faces severe communication bottlenecks when clients upload high-dimensional model updates. Existing methods often compress these updates uniformly across all layers. This uniform approach ignores the heterogeneous value of different parameter blocks and wastes limited bandwidth on insensitive layers. To address this issue, we propose Layer-wise Budgeted Adaptive Transmission (LBAT). LBAT reframes federated communication under extreme uplink budgets as a resource allocation problem. Our framework dynamically estimates the transmission value of different layers utilising local training signals. It then employs an exact byte dynamic programming allocator to determine optimal rank and bit configurations under strict budgets. We validate LBAT on highly heterogeneous federated tabular prediction and data generation tasks. Extensive experiments demonstrate that LBAT consistently outperforms uniform rank, uniform quantisation, and fixed compression baselines across various extreme budget regimes. Furthermore, it achieves significantly better communication and utility tradeoffs while preserving essential distributional fidelity. --- ### SEPAL: Separated Expert Pairs with Answer-Level Fusion for Reliable LLM Collaboration Authors: Weijie Ren, Yanwen Zhang, Hao Li, Zhuolin Qi, Hengyi Zhang, Naibo Wang Published: 2026-09-30 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.39645v1 Multi-agent collaboration lets large language models (LLMs) improve question answering through deliberation and feedback. Yet shared discussion couples correction with exposure to the same mistakes, which can erode the diversity needed for voting. Self-consistency offers sampling diversity without feedback, while single-pair Actor-Critic collaboration refines only one candidate. We introduce SEPAL, which assigns three private Actor-Critic teams to direct reasoning, evidence grounding, and verification. Role-specific training gives the teams different reasoning objectives beyond sampling variation. Each Critic guides revisions within its own team, preventing feedback from carrying errors across candidates. Once revision ends, majority voting combines only the final answers, keeping the reasoning histories separate until the decision. Across five open-weight backbones and five question-answering benchmarks, SEPAL improves mean accuracy by 1.81 percentage points over a matched single Actor-Critic pair, with improvements across all five backbones. Code is available at https://github.com/zhansan114514/SEPAL. --- ### RiboUnmix: Learning Shared Translational Dynamics from Biased and Noisy Ribo-seq Measurements Authors: Gabriele Martino, Denis Skibinski, Ivo L. Hofacker, Sebastian Tschiatschek Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39644v1 Ribosome profiling (Ribo-seq) measures ribosome distributions along mRNAs, but observed occupancy profiles also contain experiment-specific distortions and stochastic variability. Consequently, models that accurately predict measured profiles may reproduce technical effects rather than recover the underlying biology. We ask whether jointly modeling datasets collected under different experimental conditions can reveal shared, sequence-dependent patterns of ribosome occupancy. We introduce RiboUnmix, a probabilistic multi-dataset framework in which each expected measured profile is represented as a shared sequence-dependent signal modulated by a dataset-specific multiplicative factor. A negative-binomial observation model captures variability across replicates. We evaluate RiboUnmix on a controlled synthetic benchmark combining programmed translation kinetics, ribosome traffic, stochastic count sampling, and sequence-dependent experimental distortions. Because the underlying kinetics and distortions are known, recovery of the shared profile and dataset-specific effects can be assessed separately. Both inferred components correlate strongly with their targets, demonstrating that RiboUnmix can disentangle shared kinetic patterns from experimental effects. Across four organism-specific real-data benchmarks, RiboUnmix outperforms sequence-to-profile baselines in predicting measured profiles. Models trained independently on subsets of 114 HEK-derived datasets recover concordant shared profiles for held-out transcripts, and experiments varying the number and composition of training datasets show that the learned representation remains stable. RiboUnmix thus converts variation across experiments into evidence for reproducible sequence-dependent patterns of ribosome occupancy, supporting biological hypothesis generation from diverse Ribo-seq datasets. --- ### Zero-Compute Cross-Lingual Transferability Estimation Using Typological Feature Proxies Authors: Dalton Raphael Harmsen, Swier Garst, Thomas van Osch, Zarè Palanciyan, Joaquin Vanschoren Published: 2026-09-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.39640v1 Cross-lingual transfer describes how knowledge in a source language benefits a target language. Measuring it quantitatively requires broad multilingual pre-training, as prior work has done with cross-lingual transfer matrices. We ask whether transfer is predictable from freely available typological features, and whether the prominence of high-resource source languages reflects typology or data quality and quantity. We show that typological databases contain cheap and dense signals about cross-lingual transfer. Our typology-only random forest on a 24-language prior-work transfer matrix scores leave-one-language-out $ρ{=}0.705$ and $R^2{=}0.49$, beating a non-typological control at $ρ{=}0.62$, which verifies the ability of typology-only predictions to reconstruct costly measured cross-lingual transfer. The signal survives leave-one-script-out and leave-one-family-out protocols, so script and family confounding do not explain the effect. By decomposing the transfer into a typology term and a resource-and-script bias term, we find the best-source ranking sensitive to this bias. In contrast, typology is not affected by this bias, which makes it a zero-compute screening tool that replaces hundreds of training runs with a model fit. Our code is available \href{https://github.com/dharmsen/typo-x-ling-transfer}{here}. --- ### Marginal Response Surface Elicitation for Zero-Label Tabular Learning Authors: Liangyu Teng, Yicheng Ding, Jing Liu, Hengsong Liu, Juncen Guo, Hongru Li, Jingyu Zhang, Liang Song Published: 2026-09-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.39639v1 Tabular learning uses structured data to predict target outcomes. Traditionally, this process has relied on labeled data. However, large language models (LLMs) can be used to elicit domain priors based on the task description and feature semantics, thereby enabling predictions without labeled data. We propose Marginal Response Surface Elicitation (MARS), a method that transforms feature-level LLM priors into a reusable, zero-shot tabular classifier. To construct this classifier, MARS selects representative values for each feature from unlabeled data and prompts the LLM to provide corresponding class support scores and feature weights. It then aggregates multiple responses using the median to construct feature response functions, and makes predictions through their weighted sum without further LLM queries. Across eight tabular benchmark tasks, MARS achieves the highest average AUC and AP, outperforming direct prompting by 1.97 and 6.21 percentage points respectively, while substantially reducing end-to-end costs. Evaluations with LLMs of different sizes further demonstrate its predictive advantage over direct prompting. --- ### SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations Authors: Shuang Liang, Lejun Liao, Shiyuan Zhang, Max C. Zhang, Xiaolong Luo, Han Wang, Stefano Anzellotti, Yuan Yuan Published: 2026-09-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.39635v1 Given a target dataset, such as faces with eyeglasses, and a background dataset, such as faces without, contrastive analysis separates \textit{salient} factors specific to the target from \textit{common} content shared by both. We aim for salient representations that capture target-specific detail in each image, such as the shape, color, and position of the glasses, so that they reveal subtypes without subtype labels and guide the generation of new examples of a discovered subtype, even one with no name or text description. We introduce SAGE, which learns both factors directly in the high-dimensional spatial latent of a frozen representation autoencoder and conditions a diffusion transformer on the learned salient representation of a reference image. On Digits-ImageNet and FFHQ eyeglasses, SAGE combines high-fidelity \textit{reconstruction} (rFID below $2$) with unsupervised \textit{subtype discovery}, recovering the digits better than baselines (probe accuracy $0.950$ vs.\ at most $0.281$) and revealing eyewear types, finer sunglasses styles, and mislabeled images; salient-conditioned \textit{generation} raises Digits-ImageNet subtype accuracy over the unfactorized latent ($90.5\%$ vs.\ $27.7\%$) and diversity on both datasets. On retinal OCT, SAGE's salient space separates three diseases using only normal/disease labels. --- ### Free Everywhere, Exact on Trees: PPO's Dropped Correction Buys Sample Efficiency Under Aggressive Reuse Authors: Nima H. Siboni Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.39634v1 Common policy improvement methods, including TRPO, PPO, and GRPO, estimate policy improvement under the behavioral policy's state-visitation distribution rather than the improved policy's own. The substitution makes the objective estimable from the behavioral policy's rollouts but adds a bias growing with policy divergence, hence the trust region or clip, and hence no reuse of a batch far off-policy. We show that under history-injective dynamics, where each state is reached by exactly one history, the dropped state-visitation ratio equals the product of per-step policy ratios along the sampled prefix, on every trajectory and not only in expectation. The ratio is therefore restored exactly, from log-probabilities PPO already computes. Autoregressive generation and canonical-order constructive optimization are both history-injective. The exact correction pays importance-sampling variance that grows with the horizon, so we generalize it to a one-parameter family with PPO ($α{=}0$) and the full correction ($α{=}1$) as endpoints: a single bias--variance knob. A gradient-level analysis of the unclipped surrogate identifies two channels the correction acts through and three conditions under which it carries signal; an enumerable testbed confirms the conditions' predictions. On hard credit-assignment scheduling tasks, a short corrected warmup with aggressive early sample reuse learns faster than PPO and than the same reuse uncorrected; the marginal gain grows with task difficulty ($+0.02$ to $+0.09$ learning-curve AUC), and the early win over PPO tracks the prefix bias that reuse incurs. A correction held throughout, or applied where clipping already contains the reuse bias, is null to harmful. --- ### Towards Better Exploration in Sequential Test-Time Scaling Authors: Joseph Rance, Fabio Pizzati, Juil Sock, Woody Bayliss, Marc Górriz Blanch, Philip Torr, Adel Bibi Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39632v1 Test-time scaling improves language model reasoning by spending additional compute at inference. However, both classes of existing methods often fail to continue improving over long timescales. Parallel methods repeatedly sample independent answers from the model, scaling poorly on problems the model is unlikely to solve in a single attempt. In contrast, sequential methods build on previous answers to access new ideas, yet so far have not been shown to reach answers beyond those found by parallel scaling. First, we show that sequential scaling often stops improving because it becomes prematurely trapped in an attractor: a set of answers that prevents exploration of different answers once entered. Across 27 combinations of scaling methods, models, and benchmarks, we find that 53.8% of sequential scaling trajectories enter an attractor within four iterations. Second, we show that a simple model-mixing intervention helps escape attractors. This reduces the attractor hit rate by 21.2 percentage points on average, expands solution coverage beyond a compute-matched parallel baseline, and improves accuracy of recursive self-aggregation by at least 2.2 percentage points. Our results motivate refocusing long-horizon test-time scaling from parallel methods to sequential methods that improve previous answers. --- ### PEG-Tab: Sampling-Time Record Repair and Release Control for Tabular Synthesis Authors: Pengfei Li, QinYi Liu, Mohammad Khalil Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39630v1 Pretrained tabular generators can reproduce training records even when aggregate utility remains high. When retraining is unavailable or too costly, sampling and release are the remaining intervention points. We present PEG-Tab (Post-Training Energy Guidance for Tabular Synthesis), a post-training repair and release-control framework for frozen tabular generators. For each generated row, a generator-native operator creates two alternatives. A shared calibrated score compares the three candidates, favours lower-risk records, and applies a final release check. We instantiate this interface for GReaT, CTGAN, TVAE, and TabDDPM without updating their parameters. Across five datasets and four generator families, PEG-Tab reduces mean Near Copy from $0.078$ to $0.027$ and lowers aggregate Exact Copy to zero. Relative to a $3\times$ post hoc filter, it retains higher utility in 12 of 16 transfer settings and Pareto-dominates the filter in eight. Gains are concentrated in copy and proximity-related risks. --- ### Certification-Based Differentially Private Learning Authors: Mihnea Ghitu, Matthew Wicker Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39629v1 Differential privacy (DP) in machine learning is typically achieved by adding noise to model parameters (private learning) or to model outputs (private prediction). Recent work uses formal methods, namely abstract interpretation, to provide tighter privacy guarantees, but only for private prediction in classification settings. In this work, we investigate the use of formal methods as a general tool for tighter privacy analysis. First, we generalize the abstract gradient training (AGT) framework to private prediction in continuous, unbounded regression. Second, by reducing learning in parameterized models to a regression problem over the parameter space, we introduce Abstract Gradient Sampling (AGS), an algorithm that enables reachability-based analysis to provide guarantees for private learning. In both private prediction and private learning, we provide tightened privacy accounting for the AGT framework and a theoretical analysis demonstrating when our smooth sensitivity upper-bounds yield favourable privacy-utility trade-off. In practice, we validate that our regression bounds are tighter than global-sensitivity baselines on regression benchmarks, and, notably, yield the first finite privacy guarantees in settings where global prediction sensitivity is a priori unbounded. We also find that under matched conditions, our private learning algorithm can outperform standard private learners. --- ### MIND: Marginal-Invariant Neural Dependency Diffusion for Mixed-Type Tabular Generation Authors: Pengfei Li, Mohammad Khalil Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39628v1 This paper proposes MIND, a marginal-invariant neural dependency diffusion model for mixed-type tabular data. MIND does not directly learn the joint distribution in the original heterogeneous feature space. Instead, it first maps different variable types into a unified latent dependency space via column-wise marginal transport. A conditional diffusion model then learns cross-column relationships. Copula-tangent denoising separates known marginal components from learnable dependency residuals. Rank projection during the sampling phase further mitigates marginal shift in reverse diffusion. Experiments across nine diverse tabular benchmarks show that MIND consistently improves marginal fidelity and dependency preservation over existing unified approaches. By explicitly isolating marginal modelling from dependency learning, MIND achieves a strong and stable balance among marginal fidelity, joint dependency preservation, and downstream prediction utility. This work supports separating marginal and dependency modelling as a principled and highly effective paradigm for complex mixed-type tabular generation. --- ### Introduction to Computer Vision Authors: Stan Birchfield Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39627v1 This book presents a code-first introduction to computer vision, spanning classical 2D image processing, classical 3D vision, and deep learning. Organized as 44 short chapters across three parts, the book builds each topic from first principles: image arithmetic and morphology; convolution, pyramids, and frequency-domain filtering; feature detection, optical flow, and stereo; projective geometry, camera calibration, and structure from motion; and the full arc of modern deep learning, from a single neuron through convolutional networks, backpropagation, classic architectures, transfer learning, object detection, and semantic and instance segmentation, concluding with engineering considerations like mixed-precision and parallel training. Every technique is implemented directly in Python and NumPy or PyTorch and checked numerically against the corresponding OpenCV or PyTorch library function, so readers see not just the mathematics but its concrete behavior on real and synthetic data. The material was distilled with AI assistance from freely available online course notes, condensing extensive working code into concise mathematical exposition while preserving verified, reproducible results throughout. It is intended as a self-contained reference for students and practitioners who want to understand computer vision algorithms and their Python implementations. --- ### Parameterization method of reservoir properties for ensemble-based data assimilation using intermediate latent space of StyleGAN Authors: Marcio A. Sampaio, Paulo H. Ranazzi, Martin J. Blunt Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.39626v1 Ensemble smoothers are the most successful and efficient techniques currently available for history matching. However, because these methods rely on Gaussian assumptions, their performance is severely degraded when the prior geology is described in terms of complex facies distributions (non-Gaussian). In this way, for these methods, we need to apply efficient parameterization techniques. Currently, the most efficient methods for performing parameterization are deep learning models. However, given the variety of existing deep learning models, studies have not identified which is most suitable for use with ensemble-based methods, although some important models had already been evaluated. Based on a recent literature review, the most promising models selected were VAE-GAN, Latent Diffusion, and StyleGAN models. As a novel aspect of this work, data assimilation with the second generation of StyleGAN (StyleGAN2) model was performed using the latent z-space and intermediate w-space, separately. They were applied in two 2D case studies: one categorical (three facies) and the other continuous. The results demonstrated that all three models are highly efficient, with the StyleGAN2 model standing out for generating samples with geological realism and achieving excellent data matching in the cases studied. Our findings show that performing data assimilation with StyleGAN2 using the intermediate space (w-space) yielded better results than the traditional application in the latent space (z-space). This is due to the fact that ESMDA uses linear updates and the w-space is much more linear and disentangled than the highly entangled z-space, thereby ensuring that the updated vectors remain close to realistic geological patterns. These results were validated using main geostatistical and history matching metrics. --- ### D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders Authors: Xinyue Xu, Jiahao Zhang, Lijie Hu, Peter Hase, Hao Wang Published: 2026-09-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.39625v1 Sparse autoencoders (SAEs) reveal visual structure in diffusion transformers (DiTs), but interpreting a feature does not establish whether it can be used to control generation. We introduce D-Scope (Diffusion Scope), a framework that connects feature interpretation to generation control through shared visual evidence. D-Scope aggregates SigLIP~2 embeddings of highly activating image patches into visual centroids. Matching target text descriptions against these visual centroids in the shared image-text embedding space then enables retrieval of individual features without per-feature text annotations. The underlying patches provide evidence for inspecting each selection, while spatially masked interventions test the corresponding decoder direction at varying strengths under fixed generation conditions. We characterize 150 SAEs across two model families and five layers, and introduce a benchmark of 100 target concepts with ten contexts each spanning under-specified and explicit-conflict conditions. Our empirical results show that high reconstruction fidelity can coexist with low dictionary utilization and limited visual-evidence coverage. Under per-case best-of-sweep strength selection, contrastive retrieval yields larger mean regional SigLIP~2 gains than direct retrieval across the tested steering configurations, without consistently improving outside-region preservation. D-Scope provides an inspectable framework for evaluating sparse DiT features through their visual evidence and the effects of their decoder directions on generation. The demo is available at https://jiahaozhang-public.github.io/d-scope/. --- ### ExpandDiff: Dynamic Range Expanding Diffusion for Single-Image HDR Reconstruction Authors: Mehmet Emre andıran, Zhuoqian Yang, Liying Lu, Mathieu Salzmann, Sabine Süsstrunk Published: 2026-09-30 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2609.39624v1 Single-image HDR reconstruction requires inferring missing detail while preserving the visible content of an LDR image. Differences in sensor dynamic range and exposure cause LDR images to lose varying amounts of information in shadows and highlights. We present ExpandDiff, a conditional diffusion pipeline that jointly reconstructs clipped shadows and highlights. To account for this variation, we introduce Dynamic Clipping Synthesis (DCS), which randomly samples shadow and highlight clipping percentiles when constructing training inputs from HDR targets. A pixel-space diffusion model guided by spatially-adaptive normalization then predicts perceptually encoded HDR through a bounded output head, reconstructing both clipping directions in one sampling trajectory. On the SI-HDR benchmark, ExpandDiff variants improve HDR reconstruction accuracy by 3.43 dB in PU21-PSNR over the strongest evaluated competing method, and by 7.34 dB under two-sided clipping. The code and supplementary material are available at https://memreandiran.github.io/expanddiff/. --- ### Semantic Watermarking for Malicious Image Manipulation Detection Authors: Yoonseo Kim, Seungwoo Baek, Junyoung Park Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39623v1 The proliferation of high-fidelity generative editing models has made it possible to inject violent or sexual content into otherwise ordinary images while preserving visual plausibility, with concrete consequences for public discourse and vulnerable populations. We propose a robust semantic watermarking framework that reframes the watermark as a recoverable semantic reference rather than an opaque identifier. Our framework combines a $β$-VAE-based binary watermark (CLIP-VAE) with explicit channel-aware training---random bit-flip noise is injected during training so that the decoder learns graceful degradation under the noisy watermarking channel. As a downstream application, a lightweight module SDA-Net uses the recovered semantic embedding to expose not only whether but in which semantic direction an image has been altered. In a 5-way comparison against representative binary hashing baselines (SimHash, ITQ, HashNet, and their robust-MLP variants), CLIP-VAE achieves the highest reconstruction cosine similarity to the original CLIP embedding under realistic InstructPix2Pix bit-error rates, and uniquely supports direction-of-drift detection---a forensic complement to existing content-moderation pipelines. --- ### Hybrid Methods for Robust Tabular Data Imputation Authors: Jinwei Li, Michelle Bruch, Daniel Tenbrinck Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39613v1 Missing data are a fundamental challenge in statistical analysis and machine learning, as the choice of imputation method substantially impacts downstream inference. In this work, we propose two hybrid imputation methods called NuclearForest and SoftForest, which combine nuclear-norm-based low-rank initialization using Singular Value Thresholding (SVT) and SoftImpute, respectively, with a non-iterative Random Forest refinement. For the SVT-based component, we further introduce an adaptive step-size rule, prove adaptive step-size bounds, and establish convergence for the corresponding zero-initialized iteration. The low-rank initialization provides a structured warm start that captures the global covariance patterns in the data, while the subsequent Random Forest step recovers residual nonlinear signals encoding local dependencies. We conduct an extensive benchmark on diverse datasets from different application domains, comparing the proposed methods with seven established imputation methods under the Missing Completely at Random (MCAR), Missing at Random (MAR), and Missing Not at Random (MNAR) mechanisms across varying missingness rates. Our results demonstrate that NuclearForest and SoftForest match or exceed the imputation fidelity of state-of-the-art iterative methods such as MissForest, while significantly reducing computational cost. In particular, they achieve speedups of approximately 5.81 times and 9.52 times over MissForest by replacing iterative cycles with a single refinement step. Our approach effectively exploits the low-rank structure of real-world tabular data and accommodates mixed-type variables, providing an efficient and robust solution for data imputation in bioinformatics, economics, and beyond. --- ### Is This Evidence Decision-Critical? Learning to Verify Rule-Governed Decisions Authors: Haoyang Zhang, Jianpeng Zhao, Qi Hao, Pengyang Wang Published: 2026-09-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.39608v1 Rule-based reasoning, as in eligibility checks and contract reviews, requires language models to assess evidence against individual conditions and combine their judgments under explicit rules. Errors in evidence assessment can leave a decision unchanged, but misinterpreting or overlooking decision-critical evidence can reverse it. Identifying such evidence allows more capable models to focus on checking the corresponding condition judgments, supporting accurate and safe decisions. Recognizing the evidence's criticality requires understanding how evidence affects a condition judgment and how that judgment affects the decision. To achieve the goal, we propose a INTERvention-based imPACT learning framework (InterPact), which enables counterfactual verification of evidence criticality in rule-governed decisions. Specifically, its evidence intervention constructor generates training pairs for a propagation verifier by editing case facts with a frozen language model while holding rules and non-target conditions fixed. Human-reviewed labels record the resulting condition and decision changes, while complete state-to-decision mappings supervise consequences beyond the observed edit. During training, the verifier weights learned conditional decision predictions by evidence-based condition probabilities through a fixed composition operation, propagating decision-change supervision into the base model. At inference, the trained base model directly judges criticality from the original case and target evidence, without human or stronger-model supervision. On single-case evidence criticality verification over adapted rule-governed decision cases, InterPact achieves 68.28% accuracy, outperforming all six baselines. These results support learned decision sensitivity as a basis for prioritizing evidence checks. --- ### Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents Authors: Tobias Kaisar, Aritra Dhar Published: 2026-09-30 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.39607v1 Skills extend an agent's capabilities by injecting instructions and information into the context, and are widely used by agents such as OpenClaw and Claude Code. Prior work shows third-party marketplaces host malicious skills that give attackers direct influence over the victim's agent. The emerging defense scans skills before installation, pairing deterministic static checks with an LLM-based semantic judge, as in NVIDIA's SkillSpector. We show that such defenses fall to an attacker who knows the detector. Our white-box LLM attacker, Pretext, iteratively crafts skills that evade detection while still delivering the payload and performing the benign task: moving the payload from code into natural language leaves static analysis inert, while framing it as the skill's legitimate purpose and splitting instructions across files keeps the LLM stage below its blocking threshold. Across three open-source models, Pretext achieves up to 97\% and 77\% against a frozen detector and a co-adaptive one, respectively, revealing major gaps in current skill scanners. --- ### FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning Authors: Łukasz Rudnik, Agnieszka Polowczyk, Alicja Polowczyk, Przemysław Spurek Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39605v1 The rapid advancement of generative video models has enabled the synthesis of increasingly realistic and temporally coherent videos, while also raising concerns about the generation of harmful content. The reliance on large-scale web datasets during training inevitably exposes these models to undesirable material, making concept unlearning an essential mitigation. Existing methods mainly target static visual concepts, such as objects, identities, or unsafe appearance, largely overlooking motion unlearning. Furthermore, these approaches often pay little attention to preserving the surrounding scene. As a result, successful concept removal may unintentionally alter the background, composition, or overall video dynamics. We argue that effective unlearning should ideally change only what is targeted, while minimizing unnecessary changes to the remaining scene. In this work, we introduce FOMO, to the best of our knowledge the first training-based selective video unlearning method that directly treats preservation of the original scene as a priority. We formulate unlearning around two complementary objectives: what to change and what to preserve. Our method localizes concept-related representations and modifies them, while the preservation mechanism maintains non-target scene information without requiring auxiliary data. Beyond simply erasing unwanted concepts, FOMO explicitly redirects the generation toward a specified safe alternative. We further extend this formulation to motion unlearning, where the concept is defined by temporal behavior rather than a fixed spatial region. Our solution achieves effective unlearning across unsafe content, object, and motion concepts, while achieving the best trade-off between concept removal and scene preservation. Code: https://github.com/gmum/FOMO Project Page https://gmum.github.io/FOMO ---