# Research Papers — 2026-07 · bundle page 185 of 222 > Full-text markdown of papers #9201–9250 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/185 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/184.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/186.md) ### Hybrid Deep Learning for Traceability and Classification of Industrial Slate Tiles Authors: Soren Antebi, Stefan Eickeler, Sandra Halscheidt, Rene Schmitz, Michael Muellers, Dirk Hecker, Rafet Sifa Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04811v1 Applying deep learning to instance-aware reidentification of slate tiles and extraction site classification can improve production efficiency and quality control in the slate tile industry. These tasks are particularly important for handling natural materials where visual variability can make manual inspection costly and error-prone. We present a lightweight, hybrid deep learning approach that combines image matching and classification within a single framework. The system integrates a feature-matching branch based on XFeat with a MobileNetV3- based classification branch. The XFeat branch, combined with a LightGlue matching head, improves instance matching performance by +15.4% AUC. For classification, features from both backbones are shared and fused, resulting in a +10.9% accuracy improvement over a standard MobileNetV3 model. Our approach is evaluated on a newly created industrial dataset consisting of 2,610 slate tile images from six extraction sites. The results demonstrate the effectiveness of the proposed approach for object re-identification and classification in an industrial setting. --- ### Context-Constrained Transfer Learning for Tabular Foundation Models via Data Distillation Authors: Yijun Lin, Sai Li Published: 2026-07-06 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.04809v1 Tabular Foundation Models (TFMs) have demonstrated strong empirical performance as black-box inference engines through in-context learning. However, their use in transfer learning is limited by two obstacles: strict context-size constraints and sensitivity to distribution shifts between source and target tasks. Directly pooling heterogeneous source data can therefore lead to negative transfer. To address these challenges, we propose Context-Constrained Transfer Learning via ANchoring and DIstillation (TL-ANDI), a posterior-aware distillation framework for TFMs. TL-ANDI constructs a compact source context by solving a budget-constrained optimal transport problem whose cost jointly measures target covariate coverage and posterior compatibility. The selected anchor samples are then equipped with locally distilled labels and combined with a residual calibration step using target data. --- ### LILAC: Layer-Wise Independent LoRAs and Cascaded Conditioning for Multi-Concept Customization of Diffusion Models Authors: Marian Lupascu, Sebastian Ripa, Mihai Trascau, Mariana-Iuliana Georgescu, Ionut Mironica Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04801v2 Personalizing text-to-image diffusion models to render several specific subjects in a coherent image remains challenging: the model must preserve each subject's identity while keeping the scene spatially and visually coherent. Methods that fuse independently trained concept adapters in a shared weight space (via federated averaging, gradient fusion, or orthogonality constraints) suffer from identity confusion and style bleeding. In this work, we show that composing concepts as separate image layers, instead of merging their adapters in a shared weight space, avoids parameter-level interference. We introduce LILAC, a framework that composes independently trained low-rank adapters at inference time: each subject is conditioned on the frozen composite of previously placed subjects, with exactly one adapter active at a time, therefore identities never interfere at the parameter level. LILAC composes the adapters without joint training, scales linearly with the number of concepts, and is backbone-agnostic. Under the Orthogonal Adaptation protocol, LILAC applied on Qwen-Image-Edit+Qwen-Image-Layered reaches an ArcFace detection rate of 0.861. Code is available at https://github.com/marianlupascu/LILAC. --- ### LILAC: Layer-Wise Independent LoRAs and Cascaded Conditioning for Multi-Concept Customization of Diffusion Models Authors: Marian Lupascu, Sebastian Ripa, Mihai Trascau, Mariana-Iuliana Georgescu, Ionut Mironica Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04801v1 Personalizing text-to-image diffusion models to render several specific subjects in a coherent image remains challenging: the model must preserve each subject's identity while keeping the scene spatially and visually coherent. Methods that fuse independently trained concept adapters in a shared weight space (via federated averaging, gradient fusion, or orthogonality constraints) suffer from identity confusion and style bleeding and require joint retraining. In this work, we show that composing concepts as separate image layers, instead of merging their adapters in a shared weight space, avoids parameter-level interference. We introduce LILAC, a framework that composes independently trained low-rank adapters at inference time: each subject is conditioned on the frozen composite of previously placed subjects, with exactly one adapter active at a time, therefore identities never interfere at the parameter level. LILAC composes the adapters without any joint training, scales linearly with the number of concepts, and is backbone-agnostic. Under the Orthogonal Adaptation protocol, LILAC applied on Qwen-Image-Edit reaches an ArcFace detection rate of 0.861, while Orthogonal Adaptation reports 0.745 in its original setting. Adaptation reports 0.745 in its original setting. Code is available at https://github.com/marianlupascu/LILAC. --- ### Compressed Computation under $L^4$ Loss is likely Computation in Superposition Authors: Francisco Ferreira da Silva, Stefan Heimersheim Published: 2026-07-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.04800v1 Neural networks are thought to represent concepts as directions in their activation space, and superposition lets them encode more concepts than they have dimensions. It is natural to ask whether they can also compute more functions than they have neurons, i.e., perform computation in superposition. In this regime many functions of sparse inputs are evaluated by a layer with fewer neurons than there are functions to compute. Representation in superposition is by now fairly well understood, but computation in superposition is not, and there are few toy models of it arising through training rather than being hand designed. As a toy model of computation in superposition we study the compressed-computation setup: a single-hidden-layer ReLU network with 50 neurons that must compute the ReLU of each of 100 sparse input features. We show that training it under an $L^4$ loss (the mean fourth power of the error), rather than the usual $L^2$, elicits a solution that appears to compute all features in superposition. We then reverse-engineer this solution. We find that the network assigns each feature a sparse binary codeword over neurons and decodes it with a pseudoinverse of the encoder. Given these codewords, a description with only three scalars recovers most of the network's performance, and we validate it by building equivalent networks from hand-designed codes. --- ### An Exploration of Agentic Information Fusion for Test Maintenance Prediction Authors: Jingxiong Liu, Nasser Mohammadiha, Gregory Gay Published: 2026-07-06 Categories: cs.SE, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2607.04786v1 Test maintenance is a critical, yet costly, activity - particularly as codebases rapidly evolve. To assist, we present MAST, a multi-agent framework that predicts which test cases require maintenance following changes to the production code. This identification task is necessary as a precondition to any subsequent maintenance activities, but remains challenging due to the complex relationships between production and test code. MAST advances the state-of-the-art by integrating multiple analyses -- including static, lexical, and semantic analyses - through an intelligent fusion and post-check procedure and by focusing on a realistic use and evaluation setting - i.e., standardized input formats, repository-level analyses, and the ability to infer relations between test and production artifacts rather than assuming a pre-existing mapping. We evaluated MAST on 21 industrial Java repositories from Ericsson AB, considering situations where test maintenance both was and was not required in the ground truth. MAST yielded superior precision to a state-of-the-art baseline - resulting in a higher accuracy, F1, and F2 score - with only some loss in recall. Our ablation study demonstrates the value of each analysis in producing the final recommendations. MAST illustrates the potential of multi-agent systems that can fuse multiple information sources when performing software testing tasks. --- ### A Temporal Reasoning Benchmarking Framework for LRMs via Difficulty-controlled and Dynamic Test Generation Authors: Shide Zhou, Kailong Wang, Ling Shi, Haoyu Wang Published: 2026-07-06 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.04784v1 Defining the reasoning boundaries and ensuring the reliability of Large Reasoning Models (LRMs) remains a critical challenge. Current benchmarks primarily rely on static datasets susceptible to data contamination or synthetic tasks lacking fine-grained difficulty control. Furthermore, standard outcome-based evaluations often conceal reasoning flaws by neglecting the reasoning process. To address these limitations, we introduce TRACE, a testing framework that models temporal reasoning as constraint satisfaction problems via Allen's Interval Algebra. This approach enables precise regulation of logical complexity and incorporates a Trace-Based Verification Oracle to validate reasoning faithfulness. Using this framework, we construct TRACEBench, an extensive benchmark comprising 1,200 synthesized test instances across graded difficulty levels. We employ TRACE to evaluate eight widely used LRMs on TRACEBench. The results confirm a strong negative correlation between model performance and our difficulty metric (Pearson's r approximately -0.96), validating the effectiveness of our difficulty control mechanism. Moreover, our trace-based analysis exposes significant discrepancies between reasoning validity and final answers, revealing a high spurious guessing rate of approximately 28% in mid-sized models. In addition, we diagnose scale-dependent failure modes, ranging from Degenerative Loops in small models to Reasoning Explosion in advanced architectures. TRACE thus provides a robust, automated platform for benchmarking the true temporal reasoning capabilities of LRMs. --- ### Predicting Drafted Deck Strength for "Magic: the Gathering" Authors: Tomas Rigaux, Hisashi Kashima Published: 2026-07-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.04782v1 Many real-world games do not admit a fixed, compact rule set: instead, their dynamics are defined by interactions among a large and often evolving collection of game pieces, making general-purpose policy learning impractical. Magic: the Gathering (MTG) exemplifies this setting, where the cards themselves define and alter gameplay rules, strategic constraints, and long-term outcomes, while the pool of available cards is ever-changing. We study Draft, a constrained deck-building format of MTG in which eight players make 39-45 sequential selections from semi-random packs to construct a 40-card deck under partial information. By isolating the card selection process from gameplay, Draft provides a tractable yet non-trivial setting for studying decision-making driven by combinatorial card synergies. We propose an encoder-based model that produces set-contextualized card embeddings to encode the draft decision sequence, with a consistent improvement over linear baselines on large-scale real-world data, establishing a first learned benchmark for outcome prediction in MTG Draft. Our code is available at github.com/akulen/MtGDraftEncoder. --- ### Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling Authors: Stanislas Strasman, Gabriel Victorino Cardoso, Sylvain Le Corff, Vincent Lemaire, Antonio Ocello Published: 2026-07-06 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.04780v1 Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutation kernels used by the particle system are biased approximations of an ideal Feynman--Kac flow. This paper develops a non-asymptotic error analysis for such SMC samplers. Under forward-smoothing forgetting conditions, we decompose the total error into a kernel bias, measuring the effect of replacing the ideal transition kernels by approximate ones, and a finite-particle Monte Carlo error. Our approach relies on extending local Doeblin-type conditions and Lyapunov drift arguments for Markov kernels to conditional distributions, thereby enabling a principled control of the bias. We then instantiate this general framework for conditional sampling with score-based diffusion models, and derive the first non-asymptotic error bound that jointly controls initialization error, time discretization, and score approximation in the reverse diffusion dynamics as well as finite-particle Monte Carlo error. --- ### DGSeg: Dynamic Gating of Semantic-Spatial Guided Predictions for Reasoning Segmentation Authors: Ruizhe Zeng, Siyu Cao, Lu Zhang, Zhiyong Liu Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04779v1 Reasoning segmentation aims to predict pixel-wise masks for targets given complex language queries. Existing approaches leverage Multimodal Large Language Models (MLLMs) for vision-language reasoning and generate intermediate target cues (e.g., points or boxes) to guide a segmentation model. However, compressing rich reasoning into sparse cues often introduces ambiguity and noise, preventing these cues from accurately preserving the reasoning intent. While multiple complementary cues can enrich target information, existing methods typically feed them jointly into a single segmentation process, allowing ambiguous or erroneous cues to affect the entire prediction. Therefore, we propose DGSeg, a reasoning segmentation framework that learns to fuse predictions guided by semantic and spatial cues. Specifically, the MLLM jointly reasons about both target identity and spatial location, producing complementary semantic and spatial cues that are fed into separate segmentation branches. Their predictions are adaptively integrated by a lightweight dynamic gating module trained with relative branch-quality supervision to suppress noisy or conflicting regions. Extensive experiments demonstrate that DGSeg consistently outperforms strong baselines on multiple benchmarks and achieves 69.6% and 67.3% gIoU on the challenging ReasonSeg validation and test splits. Code is available at https://github.com/RZZeng/DGSeg. --- ### Towards Personalized Differentially Private Learning for Decentralized Local Graphs Authors: Longzhu He, Peng Tang, Chaozhuo Li, Jinhu Fu, Litian Zhang, Li Sun, Philip S. Yu, Sen Su Published: 2026-07-06 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2607.04777v1 Graph-structured data is increasingly generated and stored in decentralized environments, such as social platforms, mobile applications, and edge networks, where users maintain control over their local graph data. However, collecting and analyzing such decentralized graph data for downstream learning tasks raises significant privacy concerns, as nodes and their attributes often contain sensitive personal information. Local Differential Privacy (LDP) has emerged as a promising solution for privacy-preserving data collection without relying on trusted servers. Nevertheless, existing LDP-based graph learning methods typically assume uniform privacy requirements across users, ignoring the heterogeneous and personalized privacy preferences commonly observed in real-world systems. This uniform treatment leads to inflexible noise injection at the data collection stage, resulting in substantial distortion of graph data and degraded utility in subsequent analysis. To address this limitation, we propose PPGNN, a personalized differentially private framework for decentralized graph data. PPGNN enables user-specific privacy budgets during local perturbation while preserving analytical utility. To handle heterogeneous privacy levels and noise distortion, we design a two-stage solution consisting of a Personalized Perturbation Mechanism (PPM) and a weighted calibration strategy, FlexProp. Extensive experiments on six real-world graph datasets demonstrate that PPGNN effectively balances personalized privacy protection and data utility in decentralized graph learning scenarios. --- ### Non-asymptotic Convergence of Stochastic Gradient Descent in Score-based Generative Models Authors: Stanislas Strasman, Sobihan Surendran, Sylvain Le Corff Published: 2026-07-06 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.04775v1 Score-based Generative Models (SGMs) have achieved impressive performance in data generation across a wide range of applications. While the statistical properties of their sampling procedures are increasingly well understood, the optimization dynamics underlying their training remain less explored. SGMs are typically trained by minimizing a weighted denoising scorematching objective, yet optimization guarantees with stochastic gradients remain limited. In this work, we study Stochastic Gradient Descent (SGD) for SGMs, contributing results in two complementary regimes. First, for general score parameterizations, we establish a non-convex convergence rate for SGD on the weighted denoising score-matching objective, with explicit dependence on the schedule-dependent weighting factors. Second, for overparameterized two-layer ReLU networks, we develop a Neural Tangent Kernel analysis tailored to diffusion training with stochastic gradients, yielding score-approximation error bounds along the SGD trajectory. Finally, our analysis quantifies the role of the reweighting factor in the score approximation error, providing theoretical guidance for weighting choices used in practice. --- ### MARLIN: De Novo Molecular Structure Elucidation from Tandem Mass Spectra without a Ground-Truth Formula Authors: Xujun Che, Xiuxia Du, Depeng Xu Published: 2026-07-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.04774v1 Untargeted tandem mass spectrometry (MS/MS) detects thousands of small molecules per biological sample, yet most go unidentified because they are absent from spectral libraries. These uncharacterized metabolites and natural products are precisely the compounds that matter for drug discovery, biomarker research, and exposomics. Computational de novo structure elucidation could close this gap, but almost all state-of-the-art methods assume the ground-truth molecular formula is known, an oracle that does not exist for genuinely novel compounds and is itself predicted with substantial error. We present MARLIN, a de novo method that elucidates structures directly from a spectrum with no molecular formula at any stage. A self-supervised encoder predicts a molecular fingerprint from the raw peaks, and a block-diffusion language model generates candidate structures conditioned only on the fingerprint and the instrument-measured precursor mass. A provably safe mass-shell constraint keeps every candidate consistent with the measured mass without fixing the atom inventory, and candidates are accepted by exact parts-per-million mass agreement. A symmetric noise objective absorbs encoder error, and a candidate-diversity mechanism keeps the candidates from collapsing to a single structure. On the NPLIB1 benchmark, MARLIN is the strongest method evaluated without a ground-truth formula across exact-match accuracy, structural distance, and fingerprint similarity, and it recovers the correct molecular formula as a byproduct about as often as a dedicated predictor without ever using one. MARLIN enables reliable de novo structure elucidation in the realistic discovery regime where the molecular formula is unavailable. --- ### A Large-Scale Sparse Multiobjective Optimization Algorithm Based on Optimal Performance Scores Authors: Jia-Lin Mai, Min-Rong Chen, Guo-Qiang Zeng, Xiang Liu, Jian Weng Published: 2026-07-06 Categories: cs.NE arXiv: https://arxiv.org/abs/2607.04765v1 Large-scale sparse multiobjective optimization problems (LSSMOPs) involve a large number of decision variables and Pareto optimal solutions with only a few nonzero variables. However, as the number of decision variables grows, it becomes increasingly challenging to accurately identify the nonzero variables, and optimization performance is adversely affected. To address these issues, this paper proposes an evolutionary algorithm for LSSMOPs. Specifically, we propose a new initialization method capable of generating scores that accurately reflect the importance of variables, and an initial mask vector template that can locate nonzero variables. This leads to the generation of a high-quality initial population. Additionally, this paper introduces a new strategy to calculate the mutation probability for each variable and a novel optimization for real variables based on the Pareto-guided normal distribution, enabling the population to avoid being trapped in local optima and quickly converge to the global optimum. Experimental results from eight benchmark problems and three real-world applications demonstrate that the proposed algorithm achieves superior performance compared with state-of-the-art algorithms. --- ### SLAM: Structured and Localized Analytic Manifold Adaptation for Forgetting-Immune and Domain-Robust Lifelong VPR Authors: Kenta Tsukahara, Kanji Tanaka, Rai Hisada Published: 2026-07-06 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2607.04764v2 Visual Place Recognition (VPR) under long-term operation is essential for autonomous mobile robots. While Analytic Class-Incremental Learning (ACIL) provides memory-free ($O(1)$) task adaptation with exact forgetting immunity, applying it to lifelong VPR suffers from extreme vulnerability to non-linear domain shifts induced by environmental variations. In this work, we introduce the concept of the \textbf{ACIL-Domain (ACIL-D)}---a canonical invariant feature manifold where autocorrelation states remain locked. We resolve the domain vulnerability via Disentangled Domain Alignment (D-DA), which decouples latent features into invariant semantics within ACIL-D and variant style vectors for directional projection. Furthermore, by uncovering an algebraic isomorphism between recursive ACIL updates and Extended Kalman Filter (EKF) covariance propagation, we establish a control-theoretic framework designated as \textbf{SLAM} (\textbf{S}tructured and \textbf{L}ocalized \textbf{A}nalytic \textbf{M}anifold adaptation). SLAM integrates dynamic temperature-scaled Gaussian Mixture Models (GMM) to isolate topological non-linearities, Unscented perturbed propagation to dampen feature variations, and minimax $H_{\infty}$-robust criteria to bound worst-case noise accumulation. Empirical evaluations on the non-stationary NCLT dataset demonstrate that our proposed framework substantially outperforms existing baselines, achieving a final all-class accuracy of 27.7\% with the full SLAM framework (and up to 29.0\% with the U+H variant) while guaranteeing complete forgetting immunity. --- ### Multi-Turn On-Policy Distillation with Prefix Replay Authors: Baohao Liao, Hanze Dong, Christof Monz, Xinxing Xu, Li Dong, Furu Wei Published: 2026-07-06 Categories: cs.LG, cs.AI, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2607.04763v3 We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a teacher over these multi-turn interaction histories. Fully online OPD is costly because each update requires fresh student rollouts through the environment and teacher queries at visited histories. We propose Replayed-Prefix On-Policy Distillation (ReOPD), an off-environment alternative that reuses pre-collected teacher trajectories as replayed prefixes: the student acts at selected steps, while the teacher provides dense per-step supervision without executing new environment interactions. We show that multi-turn OPD introduces a prefix trap: making histories more student-on-policy improves relevance to the student, but can query the teacher on histories where its target is unreliable. This creates a two-sided distribution shift between student occupancy and teacher reliability. ReOPD addresses this by treating multi-turn OPD as a reliability-aware prefix distribution design and implements it with a simple step-decaying sampling schedule that emphasizes early, lower-shift prefixes. Across mathematical reasoning with Python and search environments over multiple teacher and student model scales, ReOPD preserves or improves OPD-level accuracy, uses zero tool calls during student training, and is at least 4$\times$ faster per rollout than OPD. ReOPD therefore turns expensive agent-environment interaction into a reusable offline resource, enabling scalable distillation across tools, tasks, and environments. --- ### DeGenseGS: Geometrically and Semantically Decoupled Surgical Scene Understanding in 4D Gaussian Splatting Authors: Yimo Wang, Bin Kang, Shuojue Yang, Yueming Jin Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04761v1 Real-time, text-promptable 4D reconstruction is indispensable for autonomous surgical interaction. Severe misalignment between semantic meaning and physical anatomy still persists, largely because existing solutions integrate Vision-Language Models into deformable fields via a rigid coupling scheme that tightly binds semantic features to geometric warping. In this paper, we propose DeGenseGS, Geometrically and Semantically Decoupled Surgical Scene Understanding in 4D Gaussian Splatting, a novel framework that independently models semantic evolution and geometric deformation. Specifically, we propose a HexPlane-based spatiotemporal entanglement module that uses shared kinematic latents to synchronize semantic mutations with scene dynamics, while explicitly disentangling semantic updates from geometric deformation. To further ensure robustness against reconstruction artifacts, we devise a Rasterization-Native Semantic Extraction mechanism that infers semantics from topologically continuous feature maps. Additionally, we incorporate an angular-aligned optimization strategy that conforms to the native hyperspherical latent space, thereby preventing semantic distortion. Extensive evaluations on the CholecSeg8k and EndoVis18 datasets demonstrate that DeGenseGS achieves state-of-the-art performance. Our framework yields enhanced geometric completeness and robust semantic-anatomic alignment, enabling spatially continuous segmentation despite drastic tissue deformation and topological transitions. --- ### AgenticPD: A Stage-Aware Agentic Framework for Physical Design QoR Optimization Authors: Shuo Ren, Zijin Cheng, Yaohui Han, Libo Shen, Leilei Jin, Wanting Tian, Rongliang Fu, Chao Wang, Bei Yu, Tsung-Yi Ho Published: 2026-07-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.04758v2 Physical design quality-of-results~(QoR) optimization is hard and expensive. Choices made at one stage can help or hurt later stages. Each evaluation requires a costly EDA run through the full flow. While existing methods still treat optimization as flat parameter tuning or a LLM-based script generation task, we present AgenticPD, a stage-aware agentic framework for physical design QoR optimization. Instead of re-running the full flow after every trial, AgenticPD is organized around the stage boundaries of the physical design flow, where a Judge Agent navigates the search and stage-specialized agents make local decisions within their own stage using stage-local tools. Additionally, the agent harness in AgenticPD provides structured observations, execution history, and agent context management. As a result, the system can branch from prior intermediate states and reuse checkpoints to continue the optimization procedure, and every candidate is evaluated at the post-route signoff. Across these baselines, AgenticPD achieves strong post-route timing while remaining competitive in power and area. --- ### Continual Model Merging with Test-Time Adaptation for Whole-Slide Image Analysis Authors: Duc-Thanh Le, Doanh C. Bui, Maï K. Nguyen, Khang Nguyen Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04755v1 Model merging offers a practical alternative to conventional continual learning by integrating independently fine-tuned models without retaining previous training data. Recent state-of-the-art model merging methods employ test-time adaptation (TTA-guided merging) to address distribution shifts by adjusting merging-related variables using unlabeled target data. However, these methods have primarily been studied in multi-task or single-target settings, and their behavior under sequential continual learning remains insufficiently understood. We present a benchmark study that maps this family of methods to rehearsal-free continual Whole Slide Image classification and evaluates them against traditional continual-learning approaches. Experiments on six TCGA cancer-subtyping cohorts cover CLASS-IL and TASK-IL scenarios, in-domain and out-of-domain evaluation, and different task orders. The results show that adapting model merging at test time can provide strong task-specific performance and improve retention of previously acquired knowledge without storing historical WSIs. Nevertheless, performance remains sensitive to task order and to the interaction between adaptation on the current distribution and accumulated knowledge. This benchmark identifies model merging with test-time adaptation as a promising direction for continual computational pathology and motivates future methods that balance adaptation to domain shift with explicit preservation of historical knowledge. --- ### Trust Region Policy Distillation Authors: Zhengpeng Xie, Li Lyna Zhang, Zeke Xie, Mao Yang Published: 2026-07-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.04751v1 Big goals are hard to achieve all at once; breaking them into small steps is wiser. We present Trust Region Policy Distillation (TOP-D), which transforms the notoriously unstable, high-variance On-Policy Distillation (OPD) into a stable training paradigm by dynamically constructing a proximal teacher. Theoretically, we establish a rigorous framework demonstrating that TOP-D inherently controls gradient variance. By providing a formal global convergence analysis alongside a monotonic improvement bound, we mathematically formalize the reliability and stability of the overall training dynamics. Empirically, TOP-D dramatically enhances training stability, sample efficiency, and final performance on mathematical reasoning tasks. More importantly, TOP-D introduces zero additional computational overhead, positioning itself as a promising alternative to the well-established OPD paradigm. --- ### FM-ChangeNet: Learning Change through Pathwise Feature Transport Authors: Roie Kazoom, George Leifman, Genady Beryozkin Published: 2026-07-06 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.04750v1 We present FM-ChangeNet, a pathwise-supervised framework for change detection that reformulates bi-temporal reasoning as continuous transport in feature space rather than static endpoint comparison. Given encoded pre and post-temporal representations, we construct intermediate latent states and learn a time-conditioned velocity field $\hat{v}_θ(z_t,t)$ along the transformation trajectory. This pathwise formulation constrains the predictor over a continuum of intermediate states, providing a denser and less ambiguous supervision signal than conventional endpoint-only segmentation and enabling the model to capture temporal evolution explicitly. The learned velocity field is not only a transport mechanism but also an interpretable representation of change: its magnitude serves as a spatially localized change cue that helps distinguish true structural variation from nuisance effects such as illumination shifts and spatial misalignment. We develop a hierarchical multi-scale architecture with cross-temporal alignment, time-conditioned coarse-to-fine flow decoding, and a unified objective that couples flow supervision, trajectory consistency, spatial regularization, and segmentation loss. Experiments on remote sensing benchmarks show that the proposed framework produces more structured and robust change representations while achieving state-of-the-art performance. --- ### MergeSurv: Merging-Based Continual Learning for Survival Analysis on Whole-Slide Images Authors: Vu Minh Tran, Doanh C. Bui, Maï K. Nguyen, Khang Nguyen Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04747v1 Survival analysis on Whole Slide Images (WSIs) is important in computational pathology for prognosis estimation and treatment planning. However, existing survival models are typically trained independently for each cancer cohort, making continual adaptation computationally expensive for gigapixel-scale WSIs. In this study, we propose MergeSurv, a merging-based continual learning framework for WSI survival analysis. A pathology vision-language foundation model is independently fine-tuned on each task, and the learned parameters are sequentially merged into a unified model without storing previous training data. We further investigate two inference strategies: One-for-All (OFA) and Voting-Expert Aggregation (VEA). Experiments on four TCGA cohorts demonstrate that MergeSurv outperforms naive fine-tuning as well as representative regularization-based and rehearsal-based continual learning methods, while effectively reducing catastrophic forgetting. The results suggest that model merging is a promising direction for scalable and privacy-preserving continual learning in computational pathology. --- ### Route-MHT: Multimodal Transformer Guardrails for Thermal Visual Place Recognition Authors: Zhiyuan Lu, Kanji Tanaka Published: 2026-07-06 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2607.04745v2 Strong mapped-region thermal visual place recognition (VPR) does not ensure safe rejection of unmapped queries. We identify and quantify this gap in AnyThermal: high Map-In retrieval accuracy coexists with confident false loop closures in Map-Out. We address it with ROUTE-MHT, a multimodal transformer guardrail. Causal motion forms a route-local candidate pool beyond the frontend's Top-$K$. Closed-form $\text{SE}(2)$ SVD verifies candidates, while frozen visual features, nine-dimensional SVD residuals, and motion proxies enter a masked multi-head transformer (MHT). Their interactions yield a contextual confidence correction to reject unsupported matches without altering geometric pose alignment. We collect an indoor thermal dataset with a physical mobile robot (Dataset-A), forming five same-day/cross-day map-query pairs; the protected interface reaches macro R@1@5m of .610/.861. Dataset-B comprises 20 map-hole scenarios derived from public STheReO-KAIST recordings. Across five scenario-held-out folds and three seeds, ROUTE-MHT reduces FPR from .116 for the SVD baseline to .061 (paired 95% CI (-.100, -.014)), while improving AUC from .945 to .967 and recall from .884 to .914. Public benchmark transfer checks on STheReO-KAIST, MS2, and IRSLAM-KRI extend the evaluation under their released metric or route-progress protocols. --- ### Trajectory-Anchor Optimization for Overconfident Thermal Visual Place Recognition: Zero-Leakage OOD Auditing and Kidnapped-Robot Recovery Authors: Zhiyuan Lu, Kanji Tanaka Published: 2026-07-06 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2607.04745v1 Modern thermal visual place recognition (TIR-VPR) frontends based on foundation models achieve remarkable closed-set retrieval but suffer from an overconfident forced-matching failure mode. Under out-of-distribution (OOD) or unmapped conditions, they generate highly plausible yet false loop candidates without a drop in similarity scores. While classical multi-hypothesis tracking (MHT) backends can mitigate these ambiguities by maintaining divergent trajectory beliefs, their exponential computational overhead violates real-time robotic constraints. To bridge this gap, we present Trajectory-Anchor Optimization (TAO). To counter the combinatorial challenge of evaluating parallel hypotheses (e.g., K=100), TAO compresses multi-view temporal verification into a batched SE(2) Procrustes alignment problem. By leveraging tensor-level vectorization and single-invocation batched SVD, this formulation bypasses the dynamic tree expansion of MHT, guaranteeing a strictly bounded per-frame execution loop of O(KN). Under a strict zero-leakage evaluation protocol, we show that while a passive geometric backend cannot mathematically separate metric localization errors from coherent hallucinations at a micro-scale (<5m) due to local visual ambiguities, TAO serves as an efficient fail-safe filter at a macro-scale. Within a 5m radius, hallucinations often possess a locally consistent geometry that deceives rigid alignment. However, beyond this threshold, the K=100 disparate hypotheses disperse spatially across the global map. This dispersion breaks the rigid temporal co-visibility constraint within the sliding window (N=20), causing the joint optimization residual to escalate sharply. Consequently, TAO establishes a distinct macroscopic convergence basin (10m) where multi-view geometric consistency reliably isolates catastrophic topological breaks and suppresses critical false acceptances. --- ### Stabilized Higher-Order Influence Functions: Statistical Theory of a Class of Bilinear Forms Authors: Na Liu, Chang Li, Yujia Gu, Lin Liu Published: 2026-07-06 Categories: math.ST, econ.EM, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.04743v3 Higher-order influence functions, introduced in a series of articles (Robins et al., 2008, 2009a; van der Vaart, 2014; Robins et al., 2016, 2023; Liu et al., 2017), are a unified framework for constructing rate-optimal point estimates of a class of statistical functionals under various complexity-reducing assumptions on the posited statistical model that generates the observed data. Although higher-order (influence functions) estimators are theoretically appealing, they have very limited practical uptake compared to their first-order counterparts. The original higher-order estimators proposed in Robins et al. (2008) and Robins et al. (2017) involve nonparametric density estimation of multi-dimensional covariates, a highly nontrivial statistical and computational problem on its own. The density estimator is, in turn, used in the evaluation of the inverse population Gram matrix $Ω$ of a set of $k$-dimensional basis transformations of covariates. There, $k$ is allowed to be as large as $o (n^2)$. To partially address this potential shortcoming, Liu et al. (2017) restrict $k$ to $o (n)$ and instead estimate $Ω$ directly using the inverse sample Gram matrix estimator, but computed from an independent sample often obtained by sample-splitting. Liu et al. (2017) refer to this alternative estimator as the empirical higher-order estimator. Although the empirical higher-order estimator bypasses density estimation, it suffers from numerical instability due to inverting a large-dimensional sample Gram matrix. In this article, for a class of bilinear forms/functionals that often appear in substantive fields, we propose a new stabilized higher-order estimator without sample splitting, which exhibits more stable finite-sample performance compared to the empirical higher-order estimator. We also prove that this new class of higher-order estimators enjoys similar statistical guarantees. --- ### Stabilized Higher-Order Influence Functions: Statistical Theory of a Class of Bilinear Forms Authors: Na Liu, Chang Li, Yujia Gu, Lin Liu Published: 2026-07-06 Categories: math.ST, econ.EM, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.04743v2 Higher-order influence functions, introduced in a series of articles (Robins et al., 2008, 2009a; van der Vaart, 2014; Robins et al., 2016, 2023; Liu et al., 2017), are a unified framework for constructing rate-optimal point estimates of a class of statistical functionals under various complexity-reducing assumptions on the posited statistical model that generates the observed data. Although higher-order (influence functions) estimators are theoretically appealing, they have very limited practical uptake compared to their first-order counterparts. The original higher-order estimators proposed in Robins et al. (2008) and Robins et al. (2017) involve nonparametric density estimation of multi-dimensional covariates, a highly nontrivial statistical and computational problem on its own. The density estimator is, in turn, used in the evaluation of the inverse population Gram matrix $Ω$ of a set of $k$-dimensional basis transformations of covariates. There, $k$ is allowed to be as large as $o (n^2)$. To partially address this potential shortcoming, Liu et al. (2017) restrict $k$ to $o (n)$ and instead estimate $Ω$ directly using the inverse sample Gram matrix estimator, but computed from an independent sample often obtained by sample-splitting. Liu et al. (2017) refer to this alternative estimator as the empirical higher-order estimator. Although the empirical higher-order estimator bypasses density estimation, it suffers from numerical instability due to inverting a large-dimensional sample Gram matrix. In this article, for a class of bilinear forms/functionals that often appear in substantive fields, we propose a new stabilized higher-order estimator without sample splitting, which exhibits more stable finite-sample performance compared to the empirical higher-order estimator. We also prove that this new class of higher-order estimators enjoys similar statistical guarantees. --- ### DriftST: One-Step Generative Inference of Spatial Transcriptomics from H\&E Histology Authors: Yuhang Yang, Yonggan Bu, Shengyuan Zhou, Yiming Luo, Kai Zhang Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04740v1 Spatial Transcriptomics (ST) measures gene expression while preserving spatial context, but its high cost and low throughput leave public datasets small. Inferring expression directly from widely available Hematoxylin and Eosin (H&E) stained histology offers a cost-effective alternative. However, existing approaches face several limitations: regression methods over-smooth toward the conditional mean, while generative methods are faithful but require slow multi-step inference; most methods treat genes as independent and equally important, ignoring inter-gene dependencies and heterogeneous gene informativeness; and most are tailored to a single resolution, either spot-level or cell-level. To address these issues, we propose DriftST, a unified framework for inferring spatially resolved gene expression from H&E images. DriftST builds on a Cellular Drifting generative model that learns a direct drift from a histology-conditioned source to the expression distribution, retaining generative expressiveness while enabling efficient one-step generation. To capture gene structure, we introduce the STransformer, which combines a co-expression attention module for inter-gene dependencies with a gene residual gate for differential gene importance. Operating on a generic gene-panel representation, DriftST applies directly to both spot-level and cell-level data in one framework, and extensive experiments across diverse tissues and platforms show that it achieves state-of-the-art performance at both resolutions. --- ### Wasserstein Residuals: Learning Gradient Flows from Population Dynamics Authors: Markus Heinonen, Yair Shenfeld, Ricardo Baptista, Daniel Waxman, Dmitry Batenkov, Tim Cooijmans, Eli Bingham Published: 2026-07-06 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.04738v1 Reconstructing population dynamics is a central problem in the physical and data sciences. Often, the dynamics are modeled as a Wasserstein gradient flow (WGF): a curve of distributions driven by an energy functional. Though there are multiple mathematical characterizations of a WGF, the dominant algorithmic approach relies on the Jordan--Kinderlehrer--Otto (JKO) scheme. JKO-based methods are inflexible to time discretisation and require solving costly optimal transport problems. We take a residual approach, enforcing the continuity equations via a non-negative loss function whose minimum is the WGF. Combined with a data-fitting divergence, this gives a single global objective. This perspective unifies several existing methods and leads to a new particle-based method, stitching, that is simulation-free and robust to large gaps between observations. We demonstrate that the stitching method achieves state-of-the-art performance across trajectory inference benchmarks. For code see github.com/BasisResearch/wasserstein-residuals. --- ### Identifiability of Relational Queries in Multi-View Pretraining Authors: Ratan Bahadur Thapa, Daniel Hernández Published: 2026-07-06 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2607.04735v1 When data sources are integrated through a shared interface, a downstream query may or may not be determined by what the interface exposes: two globally consistent worlds can agree on every shared attribute yet disagree on the query answer. This ambiguity is structural -- a property of the interface design, not the data volume -- and cannot be resolved by collecting more records or training a larger model. We formalize query identifiability for data integration under interface laws (functional dependencies that hold uniformly across all legal worlds rather than within a single instance) and prove three results. (i) A polynomial-time certificate (CheckCert) decides identifiability via attribute closure, and is exact on instances that expose any residual ambiguity (closure-separable). (ii) Non-identifiable queries face an irreducible 1/2 minimax error floor for any estimator using only interface evidence, bounding multi-view pretraining systems from below. (iii) A minimum-augmentation algorithm (Greedy-MinAug) finds the smallest set of interface additions to certify a query, reducing to Set Cover (logarithmic approximation). Experiments on synthetic benchmarks, real integration datasets spanning three domains (scholarly, product, restaurant), and schemas up to 10^3 attributes confirm CheckCert is exact, both algorithms run in single-digit milliseconds, and ML classifiers exhibit the predicted error floor and abrupt capability gains. --- ### LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure Authors: Yueyang Wang, Baolong Bi, Shuo Lu, Jingyuan Zhang, Jiajun Shi, Jingyuan Zhang Published: 2026-07-06 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.04733v3 Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities. Standard cross-entropy fine-tuning promotes only the observed label token and leaves unconstrained how probability mass is redistributed over other plausible alternatives, potentially distorting the rich local preference structure learned during pretraining. We first analyze next-token predictions using Shannon and Renyi entropies, revealing that pretrained models exhibit a regular multimodal entropy structure. These entropy peaks correspond to varying numbers of plausible alternatives, indicating that the base model intrinsically encodes rich distributional knowledge beyond the single supervised token. Motivated by this observation, we propose LP-SFT, a Local-Preserving Supervised Fine-Tuning objective designed to explicitly protect this inherent entropy structure. At each step, LP-SFT constructs a local top-K support of alternative tokens from the frozen base distribution. Crucially, it removes the supervised target token from this set to avoid conflicting with the cross-entropy objective, and applies a locally normalized KL divergence to maintain the base model's relative preference structure among the remaining non-label alternatives. Across mixed-domain and single-domain fine-tuning experiments, LP-SFT improves overall performance over vanilla SFT and recent SFT-enhancement baselines, achieving the best balance between pass@1 accuracy and pass@k performance. These results suggest that local preservation helps mitigate capability degradation without collapsing sampling-accessible diversity. --- ### LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure Authors: Yueyang Wang, Baolong Bi, Shuo Lu, Jingyuan Zhang, Jiajun Shi Published: 2026-07-06 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.04733v2 Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities. Standard cross-entropy fine-tuning promotes only the observed label token and leaves unconstrained how probability mass is redistributed over other plausible alternatives, potentially distorting the rich local preference structure learned during pretraining. We first analyze next-token predictions using Shannon and Renyi entropies, revealing that pretrained models exhibit a regular multimodal entropy structure. These entropy peaks correspond to varying numbers of plausible alternatives, indicating that the base model intrinsically encodes rich distributional knowledge beyond the single supervised token. Motivated by this observation, we propose LP-SFT, a Local-Preserving Supervised Fine-Tuning objective designed to explicitly protect this inherent entropy structure. At each step, LP-SFT constructs a local top-K support of alternative tokens from the frozen base distribution. Crucially, it removes the supervised target token from this set to avoid conflicting with the cross-entropy objective, and applies a locally normalized KL divergence to maintain the base model's relative preference structure among the remaining non-label alternatives. Across mixed-domain and single-domain fine-tuning experiments, LP-SFT improves overall performance over vanilla SFT and recent SFT-enhancement baselines, achieving the best balance between pass@1 accuracy and pass@k performance. These results suggest that local preservation helps mitigate capability degradation without collapsing sampling-accessible diversity. --- ### SparseOcc++: Geometry-Aware Sparse Latent Representation for Semantic Occupancy Prediction Authors: Pin Tang, Zhongdao Wang, Guoqing Wang, Xiangxuan Ren, Chao Ma Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04732v1 Vision-based 3D semantic occupancy prediction is essential for autonomous driving, yet dense voxel representations waste computation on largely empty space, while BEV and TPV projections compromise fine-grained 3D structure. Fully sparse representations offer an attractive alternative, but existing methods, including SparseOcc, entangle scene completion with semantic prediction by indiscriminately propagating high-dimensional features into empty regions and applying voxel-wise classification. This creates excessive activations, computational overhead, and geometric ambiguity. We present SparseOcc++, a geometry-aware sparse framework that explicitly decouples scene completion from semantic segmentation. SparseOcc++ reformulates completion as signed-distance regression on sparse anchor voxels through a scene completion field (SCF). To model complex outdoor geometry robustly, it combines orthogonal decomposition with discretized distance learning. A geometry-guided propagation module then converts the SCF into a complete volumetric scene and restricts semantic segmentation to geometrically verified regions. Experiments establish new state of the art: SparseOcc++ improves IoU by 2.3 points and is 3.9x faster than SparseOcc on nuScenes, while achieving a 5.9x speedup over OccFormer on SemanticKITTI. --- ### When Does High-CFG Diffusion Inversion Fail? A Controlled Study of Prompt--Latent Interactions Authors: Yan Zeng, Yusuke Hosoya, Huyen T. T. Tran, Takayuki Okatani Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04731v2 Text-guided diffusion inversion is central to image editing, where an image is mapped to an initial latent and then edited by replaying the denoising process under a modified prompt. In practice, however, inversion is often performed with a lower classifier-free guidance(CFG) scale than the one used for generation or editing. This mismatch is empirically useful but leaves a basic question unresolved: when a target image is generated by a high-CFG trajectory, when can that trajectory actually be inverted? We study this question in a controlled generation--inversion--reconstruction setting, where the true initial latent and denoising trajectory are known. Using prompts taken from an existing diffusion-editing benchmark, we generate images under high CFG and reconstruct them with fixed-point inversion using the same prompt and guidance setting. The results reveal three types of prompt-level reconstruction behavior: easy prompts that reconstruct for most initial latents, hard prompts that fail for most initial latents, and intermediate prompts whose success depends on the prompt--latent pairing. To analyze the generation side, we define prompt pressure, a step-wise measure of how strongly CFG moves the denoising update away from the unconditional trajectory. Total pressure correlates with reconstruction quality and separates easy from hard prompts, but it does not explain the success or failure of intermediate prompt--latent pairs. Text-side analyses further show that the main visual subject and wording can change inversion difficulty. Finally, we evaluate a compact trajectory-consistency intervention that relaxes guidance only at locally unstable inverse steps. This diagnostic check improves reconstruction and Prompt-to-Prompt editing in our controlled setting, supporting the view that high-CFG inversion failure requires local, trajectory-aware analysis. --- ### RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities Authors: Tarek Elsayed, Shiping Yang, Eunsong Koh, Sanika Goyal, Vincent Huang, Paul Ngo, Nathan Young, Mohammad Omidvar Tehrani, Alvyn Kang, Arnell Kang, Zeyu Chen, Angélica Moreira et al. Published: 2026-07-06 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2607.04729v1 LLM agents are increasingly applied to vulnerability analysis, but existing benchmarks have not kept pace. They typically rely on small non-compilable snippets, focus on binary classification (vulnerable or not), and do not account for the risk that publicly-released datasets are part of model training corpora. We introduce RustMizan, a benchmarking framework for Rust vulnerability analysis that addresses these gaps. RustMizan contains compilable code variants at the crate, file, and function levels, with annotations for binary vulnerability detection, CWE classification, and function- and line-level localization. A paired mutation framework produces semantics-preserving code mutants for contamination testing and robustness probing. Across four frontier models in an agentic setup with command-line access, binary classification sits in the 56-65% range, but line localization F1 stays near 20%, and adversarial cues drop line F1 by about 27%. --- ### Turning Off-Policy Tokens On-Policy: A Plug-in Approach for Improving LLM Alignment Authors: Yu Li, Xiuyu Li, Mingyang Yi, Jiaxing Wang, Liangxu Zhang, Zhaolong Xing, Zhen Chen Published: 2026-07-06 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.04728v2 Reinforcement learning (RL) post-training for large language models (LLMs) follows a efficient paradigm of "rollout then update", which inevitably results in off-policy training data. To resolve this, Importance sampling (IS) is proposed, while the token-level ratios compound over long sequences, causing severe variance exploded. A natural idea is "transferring" these off-policy token into on-policy token, so that the importance scores for correction are unnecessary. Following this idea, we propose Selective Importance Sampling (SIS), which is inspired by rejection sampling. Concretely, SIS implements by viewing off-policy model as proposal distribution, and implement a token-level rejection test: accepted tokens are viewed as on-policy, so that receive unit importance score, while rejected tokens retain the standard IS correction. Our proposed SIS is theoretically proved reducing the gap between token-level and sequence-level off-policy gradient estimators. The SIS acts as a plug-in that only modifies the importance ratio in the policy loss, adding negligible wall-clock overhead, and can be combine with a vast vary of RL post-training algorithms. Experiments on dense and MoE LLMs across math and agent benchmarks show that SIS consistently improves all objectives, while providing substantially stronger robustness under off-policy data. --- ### Turning Off-Policy Tokens On-Policy: A Plug-in Approach for Improving LLM Alignment Authors: Yu Li, Xiuyu Li, Mingyang Yi, Jiaxing Wang, zhangliangxu, Zhaolong Xing, Zhen Chen Published: 2026-07-06 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.04728v1 Reinforcement learning (RL) post-training for large language models (LLMs) follows a efficient paradigm of "rollout then update", which inevitably results in off-policy training data. To resolve this, Importance sampling (IS) is proposed, while the token-level ratios compound over long sequences, causing severe variance exploded. A natural idea is "transferring" these off-policy token into on-policy token, so that the importance scores for correction are unnecessary. Following this idea, we propose Selective Importance Sampling (SIS), which is inspired by rejection sampling. Concretely, SIS implements by viewing off-policy model as proposal distribution, and implement a token-level rejection test: accepted tokens are viewed as on-policy, so that receive unit importance score, while rejected tokens retain the standard IS correction. Our proposed SIS is theoretically proved reducing the gap between token-level and sequence-level off-policy gradient estimators. The SIS acts as a plug-in that only modifies the importance ratio in the policy loss, adding negligible wall-clock overhead, and can be combine with a vast vary of RL post-training algorithms. Experiments on dense and MoE LLMs across math and agent benchmarks show that SIS consistently improves all objectives, while providing substantially stronger robustness under off-policy data. --- ### Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards Authors: Tianhao Niu, Ziyu Han, Qiguang Chen, Shiqi Zhou, Baocai Shan, Hengjie Fang, Qingfu Zhu, Wanxiang Che Published: 2026-07-06 Categories: cs.SE, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.04727v1 Automatic data visualization generation has advanced rapidly with multi-modal large language models, yet existing efforts largely focus on static charts and overlook the interactive dashboards commonly used for real-world data exploration. We introduce Dashboard2Code, a novel task that requires a model to proactively explore an interactive dashboard, acquire and integrate feedback from its own interactions (e.g., clicking and filtering), and generate code that reproduces the target dashboard. To support comprehensive evaluation, we present DashboardMimic, the first Plotly+Dash benchmark for Dashboard2Code, comprising 180 carefully designed and manually verified dashboard-code pairs spanning three difficulty levels and covering eight common real-world interaction patterns. We further propose an automated evaluation framework tailored to dashboards that combines code semantic analysis with dynamic interaction-based testing to assess visual and interaction consistency, showing strong agreement with human judgments. Experiments across a range of open- and closed-source multi-modal models reveal that even the strongest systems struggle on high-complexity dashboards and that a substantial performance gap remains between open-source and closed-source models on the Dashboard2Code task. --- ### What You See Is What You Get: Observation-Aligned Supervision for Chart-to-Code Generation Authors: Tianhao Niu, Qingfu Zhu, Wanxiang Che Published: 2026-07-06 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.04726v5 Chart-to-code generation is commonly trained through supervised fine-tuning on reference plotting scripts, implicitly treating the gold code as a fully observable target. However, many chart programs contain latent variables that cannot be uniquely recovered from the rendered image. We identify this latent-observation mismatch in four forms across five chart types: aggregation-induced mismatch, where raw samples are reduced to box statistics or histogram bin masses; normalization-induced mismatch, where absolute scale is removed in pie charts; projection-induced mismatch, where 3D information is lost through 2D rendering; and level-set-induced mismatch, where a scalar field is observable only through selected contour lines. These mismatches introduce target ambiguity and require models to generate information unsupported by the image. We propose Observation-Aligned Supervision, which replaces latent variables with visually constrained quantities. We instantiate it using box statistics, bin weights, and wedge proportions, and study 3D scatter and contour charts through controlled experiments. Across multiple VLMs, observation-aligned supervision generally improves observable-value recovery in both-executable evaluations and mostly improves end-to-end recovery, while the contour study reveals a trade off between observation alignment and representational compactness. --- ### What You See Is What You Get: Observation-Aligned Supervision for Chart-to-Code Generation Authors: Tianhao Niu, Qingfu Zhu, Wanxiang Che Published: 2026-07-06 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.04726v2 Chart-to-code generation is commonly trained with supervised fine-tuning on reference plotting scripts, implicitly treating the gold code as a fully observable target. We argue that this assumption is often invalid: many chart programs contain latent raw variables that cannot be uniquely recovered from the rendered image. We identify this systematic latent--observation mismatch with three forms: aggregation-induced mismatch, where raw samples are reduced to summary statistics or bin-level mass; normalization-induced mismatch, where absolute scale is removed; and projection-induced mismatch, where higher-dimensional information is lost through visual projection. These mismatches introduce target ambiguity and require models to complete information unsupported by the image. We propose Observation-Aligned Supervision, which replaces latent targets with visually constrained quantities. We instantiate it for boxplots, histograms, and pie charts using box statistics, bin weights, and wedge proportions, respectively, and study projection-induced mismatch through a controlled 3D scatter experiment. Across multiple VLMs on ChartMimic and ChartX, our rewritten supervision improves observable-value recovery, including under both-executable evaluation. --- ### Reference-Induced Consensus for Selective Posed-Reference Visual Localization Authors: Wonseok Kang, Jaehyun Kim, Jeongmin Lee, Tae-Wan Kim Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04722v1 We present RIC-Loc (Reference-Induced Consensus localization), a scene-training-free posed-reference localizer that is SfM-point-map-free in its main estimator: it uses known reference poses, but not precomputed SfM 3D map points, query-to-map 2D-3D matches, or query-to-map PnP. A frozen VGGT pass predicts local camera poses, depth, and query-reference tracks for a query and selected references. Each reference induces one map-frame SE(3) query-pose hypothesis, robust consensus estimates the pose, and the preserved hypothesis structure yields two reliability scores: spatial dispersion and a track-conditioned covariance score. On the covariance-eligible set, the two scores are complementary for held-out, ground-truth-free failure detection across indoor, outdoor, and large-scale low-texture benchmarks: the joint policy is strongest in textured scenes and the covariance score in the low-texture regime, and the hypothesis-derived scores consistently outperform the standard retrieval-score gap and random rankings. Without per-scene training the consensus estimator remains accurate -- competitive with structure-based localization indoors and improving over a comparable feed-forward baseline -- giving an effective selective operating regime for posed-reference localization. Code is available at https://github.com/SNU-DLLAB/ric_loc. --- ### FORGE: Research-Trajectory Hijacking Attacks on Deep Research Agents Authors: Yue Pan, Ziheng Zhang, Junxiang Lei, Changhao Jia, Qingyi Si, Hongcheng Guo Published: 2026-07-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.04718v1 Deep research agents decompose open-ended queries into subtasks, retrieve web evidence over multiple rounds, and synthesize long-form reports. This workflow creates a planning-layer poisoning surface: adversarial documents that enter the retrieval pool can steer follow-up questions and turn a local injection into report-level contamination. We present FORGE (Fabricated Orchestrated Reasoning chain for aGent Exploitation), a two-level attack that combines intra-document reasoning fabrication with inter-document chain coordination to hijack subtask planning. We further introduce the PRISM metric, which weights infected report claims by cognitive type, and Root Query Anchoring, a lightweight defense that ties recursive follow-up generation to the root query. Across 25 queries, Network FORGE reaches 26.4% PRISM with five injected documents and exhibits depth migration, in which recursive synthesis shifts poisoned content from overt framing into factual premises. On the 10-query defense subset, RQA (Root Query Anchoring) reduces PRISM from 38.5% to 18.3%. --- ### Geometry-Aware Motion Latents for Learning Robust Manipulation Policies Authors: Yunchao Zhang, Yijia Weng, Ruizhe Liu, Ming Hu, Leonidas Guibas, Yanchao Yang Published: 2026-07-06 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.04714v1 Learning motion latents for robotic manipulation heavily relies on extracting motion patterns from visual sequences, yet effective action abstractions require understanding three-dimensional geometric transformations. Here, we introduce GeoMoLa (Geometry-Aware Motion Latents), which learns discrete motion latent codes by predicting how point clouds evolve during manipulation rather than reconstructing visual observations. This four-dimensional objective -- spatial geometry changing through time -- forces latent representations to encode actual physical motion rather than appearance patterns. GeoMoLa achieves state-of-the-art performance using only single-view RGB-D input, while existing methods require multi-view reconstruction, succeeding across diverse manipulation benchmarks. Our ablations reveal that geometric prediction is the key to driving performance, quantitatively validating that manipulation depends on spatial understanding. Furthermore, the learned codes exhibit effective motion abstraction: applying them to novel scenes produces physically consistent transformations regardless of visual context. Our real-world experiments also confirm this robustness capability, achieving robust manipulation with minimal demonstrations in cluttered environments where geometric reasoning determines success. Thus, we demonstrate that effective motion latents for robot control can better emerge from understanding motion through its three-dimensional effects rather than pixel-level patterns. --- ### RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents Authors: Qiang Liu, Taian Guo, Ruizhi Qiao, Xing Sun Published: 2026-07-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.04713v2 Reinforcement learning holds significant potential for training large language models (LLMs) to handle multi-turn interactive tasks. However, in long-horizon, multi-turn tasks characterized by sparse outcome rewards, directly training with outcome rewards often results in slow convergence due to the sparsity of signals and the lack of fine-grained feedback. Furthermore, the model may fail to learn successful trajectories that are not sampled during training, thereby limiting its performance. Conversely, while employing customized dense process rewards provides richer signals and accelerates convergence, these surrogate rewards may exhibit potential misalignment with the ground-truth outcome rewards. This inconsistency can bias the training direction and ultimately degrade the model's final performance. In this work, we propose Reward-Swap Policy Optimization (RSPO), a method designed to leverage the rich information from dense process rewards to facilitate training with outcome rewards. By utilizing a reward-swap mechanism, RSPO ensures the diversity of sampled trajectories while guaranteeing consistency between the optimization objective and the true outcome rewards, thereby elevating the performance ceiling of the model. We conduct extensive experiments on two challenging agent benchmarks, WebShop and ALFWorld. By applying our method to various reinforcement learning algorithms, including GRPO, PPO, and GiGPO, we demonstrate that RSPO achieves consistent performance improvements across different baselines and benchmarks. --- ### RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents Authors: Qiang Liu, Taian Guo, Ruizhi Qiao, Xing Sun Published: 2026-07-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.04713v1 Reinforcement learning holds significant potential for training large language models (LLMs) to handle multi-turn interactive tasks. However, in long-horizon, multi-turn tasks characterized by sparse outcome rewards, directly training with outcome rewards often results in slow convergence due to the sparsity of signals and the lack of fine-grained feedback. Furthermore, the model may fail to learn successful trajectories that are not sampled during training, thereby limiting its performance. Conversely, while employing customized dense process rewards provides richer signals and accelerates convergence, these surrogate rewards may exhibit potential misalignment with the ground-truth outcome rewards. This inconsistency can bias the training direction and ultimately degrade the model's final performance. In this work, we propose Reward-Swap Policy Optimization (RSPO), a method designed to leverage the rich information from dense process rewards to facilitate training with outcome rewards. By utilizing a reward-swap mechanism, RSPO ensures the diversity of sampled trajectories while guaranteeing consistency between the optimization objective and the true outcome rewards, thereby elevating the performance ceiling of the model. We conduct extensive experiments on two challenging agent benchmarks, WebShop and ALFWorld. By applying our method to various reinforcement learning algorithms, including GRPO, PPO, and GiGPO, we demonstrate that RSPO achieves consistent performance improvements across different baselines and benchmarks. --- ### Learning Probabilistic Prompt for Continual Learning Authors: Hyekang Park, Sanghoon Lee, Geon Lee, Jongyoun Noh, Bumsub Ham Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04711v1 Continual learning aims to progressively learn from a sequence of tasks, each containing a disjoint subset of classes, while preserving previously learned knowledge. Prompt-based continual learning methods propose to learn a small set of parameters, i.e., prompts, by associating them with a query feature of an input image. These methods optimize the prompts, attempting to represent diverse patterns of images. However, we have observed that existing prompt-based methods suffer from a prompt collapse problem, that is, the prompts tend to be highly similar to each other, thereby failing to capture the diverse data distributions in continual learning scenarios. To address this issue, we propose in this paper a novel prompt-based continual learning framework that captures diverse patterns of images across a sequence of tasks. To this end, we model each prompt as a probabilistic distribution and construct a mixture of these distributions, from which we sample diverse prompts. This enables our model to effectively capture highly diverse image distributions in the continual learning process. We also present a distribution regularization loss to prevent abrupt changes in the prompt distributions throughout the training process. We show extensive experimental results for continual learning on standard benchmarks, including ImageNet-R, CIFAR-100, and CUB-200, demonstrating the effectiveness of our framework. --- ### Integrated Altruistic and Fairness Preference Induces Advanced Mutual Cooperation in Sequential Social Dilemmas Authors: Yu Wei, Yukiko Ogura, Yoshiyuki Ohmura, Ildefons Magrans de Abril, Hoshinori Kanazawa, Yasuo Kuniyoshi Published: 2026-07-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.04710v1 Inducing cooperation among distributed agents is still a difficult problem in the field of multi-agent reinforcement learning (MARL), particularly in social dilemma situations. There, individual interests are misaligned with the common good and individual rationality leads to suboptimal group outcomes. In contrast, humans are able to achieve cooperation with one another in such situations. A common explanation for such cooperative behavior is that individuals have social preferences. In order to achieve cooperation in MARL, we design a new utility function integrating altruistic preferences (incentive for other's reward) and fairness preferences (incentive for equality) from social psychology and behavioral economics, namely, Altruistic and Fairness Preference (AFP), a reward-sharing mechanism which converts one's own and other's rewards to incentives for cooperative behavior. We performed comparative experiments with standard RL and inequity aversion agents in two challenging sequential social dilemma games, and showed that AFP agents successfully achieved mutual cooperation with more collective rewards and higher equity than the baselines. To further understand the progression of AFP during training, we subsequently explore the effects of altruistic preferences and fairness preferences on agents' behavior. The results suggest that altruistic preferences encourage agents to contribute to the public goods, and fairness preferences induce mutual behavior between agents. --- ### Hierarchical Scaffolding Enables Human-Like Cognitive Selectivity under Data Scarcity Authors: Juhyoung Park, Jaehyuk Bae, Hyeonbo Yang, Se-Bum Paik Published: 2026-07-06 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2607.04709v1 Modern machine learning systems demand extensive datasets for visual recognition. Conversely, humans learn with high efficiency despite severe data limitations, often by acquiring broad categorical structures before refining finer distinctions. Inspired by this contrast, we introduce SCALA (Scaffolded Cognitive Architecture for Learning under limited dAta), a hierarchical learning framework grounded in cognitive psychology that guides models from coarse conceptual structures to fine-grained recognition. Our model exhibits human-like cognitive selectivity by effectively prioritizing task-relevant features while suppressing background distractors, a mechanism that induces a fundamental shift in representation learning. This shift is characterized by accelerated cluster formation, reduced intra-class dispersion, and enhanced semantic separability. Empirically, SCALA achieves significant accuracy improvements under severe data scarcity. Furthermore, this hierarchical scaffolding promotes robust generalization to unseen classes and accelerates the acquisition of novel categories. Collectively, our results establish SCALA as a powerful framework for achieving human-level sample efficiency and resilient category generalization in data-constrained environments. --- ### Strategic Buying Agents Authors: Mingyang Fu, Ming Hu Published: 2026-07-06 Categories: econ.TH, cs.AI, cs.CY, cs.GT, cs.HC arXiv: https://arxiv.org/abs/2607.04708v1 Agentic AI is shifting online shopping from search toward delegated purchasing, where autonomous buying agents monitor markets and decide when to buy on a consumer's behalf. We study the design of such strategic buying agents, which must decide when to purchase within a finite shopping window, translating price observations, the remaining time horizon, and beliefs about future price changes into a purchase policy. We formulate this problem across three information regimes: stationary, Bayesian, and robust, and treat the resulting optimal policies as a policy menu for implementation. In the stationary regime, price adjustments follow a Poisson arrival process with a known post-adjustment price distribution; the optimal policy is a dynamic purchase-threshold rule, with the threshold governed by an ordinary differential equation. In the Bayesian regime, the adjustment intensity is known, but the price-adjustment distribution is uncertain; the optimal rule remains threshold-based, now depending on posterior beliefs, and we bound the value of knowing the true distribution. In the robust regime, the agent has only price bounds and seeks worst-case protection; randomized threshold policies achieve optimal competitive-ratio and minimax-regret guarantees. We evaluate the proposed policies on Amazon price histories from Keepa (367 items, 48,933 timestamped observations) and examine their integration into language-model buying agents. The stationary and Bayesian policies perform competitively on mean normalized consumer surplus despite their stylized assumptions, while the robust policy performs best at the distribution's 10th percentile. Results suggest language models are better suited to selecting among regimes and calibration samples than to making buy-or-wait decisions directly. --- ### F-ACVAE: A Federated Adaptive Conditional Variational Auto-Encoder for Privacy-Preserving Intrusion Detection in IoT Networks Authors: Mohammad Ansarimehr, Somayeh Changiz, Ehsan Baghishani, Ali Mousavi Published: 2026-07-06 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2607.04698v1 The rapid proliferation of Internet of things (IoT) devices has significantly expanded the cyber-attack surface, necessitating robust and privacy-preserving intrusion detection systems (IDS). However, centralized learning approaches often suffer from severe performance degradation due to high-dimensional traffic data, extreme class imbalance, and highly non-independent and identically distributed (non-IID) data across heterogeneous edge devices. To address these challenges, this paper proposes F-ACVAE, a federated adaptive conditional variational autoencoder framework that enables collaborative model training across distributed IoT devices without sharing raw data. F-ACVAE incorporates selective parameter aggregation, where local encoders remain private while globally shared components are synchronized to preserve discriminative latent structures. To further enhance stability under extreme non-IID settings and feature distribution shifts, we introduce a novel constrained momentum Gaussian aggregation (CMGA) strategy that combines update clamping with momentum-based smoothing to mitigate client drift. Extensive experiments on the N-BaIoT dataset demonstrate that F-ACVAE achieves an average accuracy and macro F1-score of 99\%, outperforming state-of-the-art baselines. Moreover, the selective aggregation mechanism reduces communication overhead by approximately 62\%, making the framework particularly suitable for resource-constrained IoT environments. These results highlight the effectiveness of F-ACVAE in achieving high detection performance while ensuring privacy preservation and communication efficiency. --- ### Probe-EM: Targeted Neuron Tracing via Training-Free Semantic Verification Authors: Liuyun Jiang, Yanchao Zhang, Jinyue Guo, Chuanyue Chen, Haiyang Yan, Ye Yuan, Jing Liu, Hua Han Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.04696v1 Establishing large-scale, high-resolution neural connectivity maps is fundamental to elucidating the structural basis of brain function. However, when processing terabyte- or petabyte-scale electron microscopy data, over-segmentation inherent in automated reconstruction algorithms remains a critical bottleneck, requiring extensive manual proofreading spanning person-years. To alleviate the heavy reliance on annotated data and the limited flexibility of conventional tracing methods, we propose a training-free, targeted neuron tracing framework. Specifically, we introduce a skeleton-guided Heuristic Spatial Search paradigm that leverages geometric priors to iteratively reconstruct neuronal morphologies through a probing-verification cycle. To achieve robust zero-shot semantic verification, we further develop a Dimension-Aware Semantic Verification strategy built upon the foundation model NeuroSAM 2. This strategy resolves intra-slice splits via Planar Ensemble Consensus and inter-slice splits via Axial Spatio-Temporal Propagation. Notably, we integrate the proposed workflow into the Neuroglancer visualization platform, enabling an interactive human-in-the-loop proofreading system. Experimental results demonstrate that the proposed method outperforms supervised baselines and reduces manual proofreading time by 33.4%. The source code is publicly available at https://github.com/HeadLiuYun/Probe-EM. ---