# Research Papers — 2026-07 · bundle page 19 of 222 > Full-text markdown of papers #901–950 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/19 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/18.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/20.md) ### ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale Recommendation Authors: Yuxin Chen, Liang Luo, Buyun Zhang, Jian Jiao, Boda Li, Haoyu Wang, Tongyi Tang, Ao Cai, Zijian Shen, Zhengkai Zhang, Wenyi Xie, Ryan Dick et al. Published: 2026-07-30 Categories: cs.LG, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2607.27744v1 Modern recommendation models gain prediction quality by scaling feature-interaction and sequence modules, but production cost constraints cap how far systems can scale. In this work, we propose Request-Oriented Compute Sharing (ROCS), a modeling and inference paradigm that exploits a unique property of recommendation inference: each user request is evaluated against many candidates, while request-side features are shared across candidates. ROCS defers request-candidate interactions as late as possible, isolates candidate-dependent representations, and evaluates substantial portions of the model once per request rather than once per candidate, significantly improving inference efficiency while maintaining or improving prediction quality. To realize this paradigm, we develop Generalized Layer Masking (GLM) to enforce candidate isolation in feature-interaction architectures, and Deep Cross Attention (DCA) to extend request-oriented sharing to sequence architectures. To support efficient GPU deployment, we co-design In-Kernel Broadcast Optimization (IKBO) that significantly accelerates ROCS model execution. Experiments on public benchmarks show that ROCS consistently improves the quality-efficiency tradeoff across recommendation backbones. On production-scale workloads, ROCS achieves up to a 3x QPS improvement on retrieval models without quality degradation and a 0.5% relative LogLoss improvement with a 50% QPS gain on a short-form video ranking model. ROCS has been deployed across large-scale recommendation systems spanning ads and organic surfaces, retrieval and ranking stages, and more than two orders of magnitude in inference complexity, delivering significant online gains at reduced infrastructure cost. --- ### Three-Photon Bayesian Imaging of Ortho-Positronium Authors: L. Raczynski, W. Krzemien, A. Coussat, M. Bala, B. C. Hiesmayr, K. Klimaszewski, M. Obara, R. Y. Shopa Published: 2026-07-30 Categories: physics.med-ph, cs.CV, physics.comp-ph arXiv: https://arxiv.org/abs/2607.27741v1 PET provides functional images relying on two-photon coincidences from positron-electron annihilation. In human tissue, about 40\% of annihilations are preceded by Ps formation, of which o-Ps component partially decays into three photons, with the remainder annihilating via pick-off or spin-exchange into two photons. This three-photon channel carries additional information about the surrounding micro-environment, including the three-to-two-photon yield ratio as a potential diagnostic marker. We propose the TRIO algorithm, a novel three-photon event-by-event image reconstruction algorithm formulated as a Bayesian maximum a posteriori inference problem. TRIO unifies time-based trilateration, energy-based reconstruction and, for the first time, a physics-informed prior derived from the QED description of Ps decay within a single probabilistic framework. In contrast to positronium lifetime imaging, which requires a prompt photon and is therefore restricted to specific radionuclides, TRIO relies solely on the three photons and is fully compatible with standard radionuclides such as 18F. Monte Carlo simulation modelled after the Siemens Biograph Quadra scanner demonstrates a mean position error of 1.62~cm, improving by approximately a factor of two over the time-based trilateration (3.05 cm) and by about an order of magnitude over energy-based reconstruction alone (18 cm). More importantly, the proposed Bayesian approach is compatible with existing TOF-PET scanners that can register three-photon annihilation coincidences. --- ### Measuring Alignment With Reader Highlights Net of Position and Length Authors: Kazuki Nakayashiki, Keisuke Watanabe Published: 2026-07-30 Categories: cs.IR, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2607.27739v1 Context compression discards most of a document before a language model reads it, and is normally evaluated by downstream task accuracy - which makes another model the judge of what mattered. Naturalistic social highlighting offers a non-circular reference: many people independently marking passages on the same page. But the obvious metric, the fraction of crowd-marked sentences a compressor keeps, is confounded twice: crowd marks are front-loaded and crowd-marked sentences are longer, so any method favouring early or long sentences scores well regardless of readers. We remove both by matching each marked sentence against unmarked sentences of the same document at equal relative depth and equal within-document length rank, and we calibrate every estimator on synthetic nulls built from position and length alone - a step that matters, since depth-only stratification returns a false positive on 20-36% of nulls containing no effect. On 120 web documents (at least 12 independent readers each), a language-model importance ranking keeps 38.4% of crowd-marked sentences against 19.9% of their matched neighbours: an enrichment of +0.196 (+0.148, +0.239), at p = 0.0005 under an exact randomization test that assumes nothing about clustering, and replicated cross-vendor. Naive truncation, whose keep rule is position, correctly falls to +0.003. To give the number a scale: scored identically, on the same budget, against a crowd label recomputed to exclude them, a single human reader reaches +0.182 - indistinguishable from GPT-5.4 (+0.002 (-0.081, +0.088)) and below Claude Opus 5. Classical methods are not null - Luhn's 1958 heuristic reaches +0.088 - so reader selection is partly recoverable by counting words; conditioning additionally on lexical centrality removes only 0.010, so the agreement is not centrality. We also report that a claim in our own prior work does not reproduce on this corpus. --- ### Improving the Robustness/Accuracy Tradeoff Against Adversarial Attacks Using Information Bottleneck Distillation Through Dual Teachers Authors: Vincent Ryusuke Takahashi, Yoshinari Takeishi, Jun'ichi Takeuchi, Kave Salamatian Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27737v1 Deep neural networks (DNNs) have achieved remarkable success in classical machine learning problems. However, they are known to be vulnerable to adversarial attacks. Countermeasures proposed in the literature, notably Information Bottleneck Distillation (IBD) introduced by Kuang et al., degrade the classification accuracy on clean inputs while improving the robustness to adversarial inputs. In this work, we extend the IBD framework by introducing an extra teacher model (clean teacher) trained with only clean inputs, into the distillation process from a robust teacher model trained by adversarial training. The features of both clean and robust teachers are transferred to the student through a cross-layer attention matrix. Experimental results on the CIFAR-10 and CIFAR-100 datasets show that the proposed method improves classification accuracy on clean samples compared to the original IBD, while maintaining similar accuracy on adversarial samples. Furthermore, our methods are competitive with state-of-the-art approaches, including the recent dual-teacher distillation framework B-MTARD, particularly in terms of the harmonic mean between clean and robust accuracy. We also analyze the impact of different training settings that have different influences on the attention module. --- ### A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Authors: Yuesong Liu, Yuan Zeng, Min Lyu, Ruilin Liu, Yu Guo, Yinlong Xu Published: 2026-07-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.27735v1 Speculative decoding alleviates the memory-bandwidth bottleneck in large language model inference, but its acceleration is jointly constrained by drafting overhead, token acceptance, and speculation length. We present a unified efficiency analysis showing that extending the speculation horizon can reduce rather than improve speedup when the marginal acceptance probability falls below the relative drafting cost. Guided by this analysis, we introduce SparseSpec-L, a training-free self-speculative decoding framework for long-context inference. SparseSpec-L generates lightweight drafts directly from the target model using a dynamically sparsified and recallable KV cache. It recycles per-head attention statistics produced during full-context verification as a no-extra-forward importance signal, allowing critical historical tokens to be recalled without permanently discarding the dense KV cache. An online entropy-based controller further selects the speculation length according to expected step-wise efficiency. Experiments across multiple long-context tasks and model scales show consistent end-to-end acceleration, with up to speedup over autoregressive decoding while preserving the target model's output distribution. --- ### VeriSkill: A Self-Evolution Framework for Program Verification Skills Authors: Changguo Jia, Tianqi Zhao, Zhiyou Xiao, Weiming Zhang, Minghui Zhou Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27733v1 Automating program verification with LLM agents requires generating specifications, annotations, auxiliary lemmas, and tool invocations, all of which depend on reusable skills. A natural remedy is skill self-evolution: distilling skills from trajectories and refining them through feedback. However, existing evolution methods struggle with program verification tasks because they cannot reliably identify skill-specific failures or extract actionable signals from opaque verifier feedback. In this paper, we propose VeriSkill, a self-evolution framework built for program verification. It attributes verification failures to skill deficiencies, distills diagnostic signatures into reusable lessons, and iteratively refines candidate skills, admitting only revisions that improve verification performance while preserving program semantics. Experiments show that VeriSkill consistently outperforms all baselines across multiple verification tools, agent frameworks, and LLM backends. --- ### Towards joint scaling laws with optimal batch size schedules Authors: Jiaxiang Li, Zhiqi Bu, Shiyun Xu Published: 2026-07-30 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2607.27731v1 Modern deep learning typically keeps the batch size static throughout training, thus overlooking the joint effect of learning rate and batch size on the training dynamics. In this paper, we study the deep learning dynamics through the lens of convex optimization and derive a joint characterization of loss in terms of both schedules, applicable to general optimizers and model architectures. This characterization yields a closed-form optimal batch size schedule for any prescribed learning rate schedule, and further leads to joint scaling laws that consistently outperform static batch size baselines, highlighting the significance of dynamic batch size schedule in large language model training. --- ### PrintAnything: Learning an Intermediate Representation for 3D printing G-code Generation Authors: Sangmin Hong, Daniel Sungho Jung, Heewon Kim, Kyoung Mu Lee Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27729v1 Point clouds are one of the most fundamental and widely used 3D representations, serving as the most basic geometric representation of 3D shapes. Nevertheless, most existing 3D printing pipelines require a watertight mesh as input, preventing the direct use of point clouds for fabrication. A common workaround is to reconstruct meshes from point clouds; however, the resulting meshes often contain geometric artifacts, such as incorrect faces or topological inconsistencies, that are difficult to repair and may lead to printing failures. To overcome these limitations, we propose PrintAnything, a novel framework that learns to produce executable 3D printing G-code directly from 3D point clouds without requiring mesh reconstruction. To enable point clouds to serve as direct input for slice-wise toolpath generation, we introduce a slice-wise point projection strategy that transforms unstructured 3D point clouds into slice-aligned 2D representations consistent with layer-by-layer nature of fused deposition modeling in 3D printing. To eliminate mesh dependency and provide a unified representation that bridges point clouds and G-code, we propose Geometric plan (G-plan) map, a compact 2D representation composed of occupancy, region, and flow maps that encode the geometric and extrusion properties required for toolpath synthesis in 3D printing. As a result, our proposed method accurately generates printable G-code directly from point clouds, enabling a practical and fully mesh-free pipeline for 3D printing. The code is publicly available at \href{https://github.com/Sangminhong/PrintAnything}{https://github.com/Sangminhong/PrintAnything}. --- ### Baikal: Structured Search for Deep Research over Data Lakes Authors: Dhruv Agarwal, Rishitha Guttapalle Mohan, Aarti Kumari, Ashi Sinha, Athulya Anil, Kavitha Srinivas, Horst Samulowitz, Andrew McCallum Published: 2026-07-30 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.27726v1 Deep research over data lakes requires an LLM agent to investigate evidence across thousands of heterogeneous tables and passages to synthesize a report. Existing methods perform iterative retrieval and generation, letting accumulated context determine what to investigate next, which can overexploit locally promising evidence and fail to cover distinct semantic regions under a fixed budget. To address this, we cast deep research over data lakes as a budgeted search problem and present Baikal - a framework that clusters heterogeneous evidence into semantic regions, then searches over them adaptively to balance exploration and exploitation. Within each selected region, Baikal generates and investigates region-grounded subquestions, using finding quality as rewards to update region-level value estimates and guide search under policies ranging from random and LLM-guided selection to Bayesian $ε$-greedy and UCB. We evaluate Baikal on 15 queries each over HybridQA and TAT-QA data lakes containing 10,993 and 2,757 tables, respectively, together with 227K Wikipedia passages and 13K financial report passages. We assess research quality with a new rubric covering groundedness, relevance, diversity, and utility, and use GPT-5-mini to score Baikal and strong baselines, including DeepSearcher and an OpenCode research agent with retrieval and clustering variants. Across both data lakes, Baikal performs strongly under several region-selection policies; its best configuration improves report scores over the strongest baselines by 28% on HybridQA and 36% on TAT-QA. Our analyses attribute these gains to organizing and exploring semantic evidence regions, which improves groundedness and diversity and yields more useful findings under the same subquestion budget. These results demonstrate the value of structured semantic exploration for systematic research and discovery over heterogeneous data lakes. --- ### Error Analysis of Neural-Network-Based Engression Authors: Juntong Chen, Zijian Guo, Xinwei Shen Published: 2026-07-30 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2607.27723v1 Engression (Shen and Meinshausen, 2024) learns a conditional distribution by fitting a generative model $Y = f(X,\varepsilon)$ under the energy score, a strictly proper scoring rule. We provide a theoretical error analysis of engression implemented with deep neural networks. We decompose the excess risk into three components: the approximation error, the stochastic error, and the Monte Carlo error. Based on this decomposition, we establish convergence rates under the assumption that the target conditional generator admits a compositional smoothness structure. --- ### New Synchronous Computation Dynamics for Hopfield Networks Authors: Francisco Requena-Domínguez, Rafaela Benítez-Rochel, Ezequiel López-Rubio Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27720v1 The dynamics of the original Hopfield network is asynchronous (sequential) (updates the state of only one neuron per time step). In this paper, we propose a new tool and a new dynamics to reduce the processing time by updating one or more neurons simultaneously per instant while ensuring process convergence and aiming for the maximum energy decrease at each step, thus guaranteeing the shortest total processing time. From the point of view of synchronous dynamics, calculating the next network state at which energy decreases the most from the current state while ensuring convergence is itself a combinatorial optimization problem. We develop and use a new tool to solve it. We call this new tool Discrete Differential Filter (DDF) and, based upon it, we develop a new synchronous dynamics which we call SD-DDF (Synchronous Dynamics based upon Discrete Differential Filter). In this paper, we review the original asynchronous dynamics for Hopfield networks and present a new tool and a new synchronous dynamics with its theoretical justification and four computational experiments to assess the speed up in processing time empirically. --- ### VESTIGE: A Knowledge-Guided Masking Strategy for Corruption-Aware Fine-Tuning of Genomic Transformers, Validated on Ancient DNA Reconstruction Authors: Angshuman Chakravertty, Rahul Maheshwari Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27712v1 Standard masked-language-model fine-tuning applies a uniform masking probability across every token position, assuming reconstruction difficulty is position-agnostic. When the degradation process is characterised and concentrated at predictable positions, this assumption fails: at peak damage sites the model can underperform a frequency-matched random predictor. We introduce VESTIGE, a parameter-free, drop-in replacement for the standard MLM collator that aligns the masking distribution with an empirically measured per-position corruption profile. We apply it to ancient DNA (aDNA) reconstruction, where cytosine deamination produces a position-dependent C-to-T / G-to-A gradient quantified per-position by mapDamage2. Rescaling so the mean C/G masking rate equals 15% - identical to standard MLM - isolates spatial redistribution as the sole variable, with model, data, seed, and hyperparameters held fixed across both DNABERT-2 runs on a mammoth CDS corpus (two specimens, seven genes). Across six terminal-zone widths and 626 paired windows, VESTIGE leads standard MLM at every width (Delta = +4.18 to +10.35 pp, all p < 10^-8), cuts validation cross-entropy by 13% (3.274 vs. 3.757), and yields ESMFold reconstructions with TM-score > 0.95 across all six reconstructions (three genes) even under damage amplified 10-30x beyond authentic PMD rates. A 1D CNN biosecurity classifier returns AUC = 0.935 and clears 98.2% of reconstructed windows, the 1.76% remainder attributable to reference-genome features, not reconstruction artefacts. The principle is domain-agnostic: any measurable position- or context-specific corruption profile - FFPE, bisulfite, metagenomic, or nanopore - substitutes directly for the PMD array, making VESTIGE a knowledge-guided training routine for intelligent systems operating on degraded or noisy sequence inputs. --- ### NMINE: Normalized Mutual Information Neural Estimation Authors: Petra Eerikinharju, Marko Tuononen, Ville Hautamäki Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27710v1 Mutual information is a general measure of statistical dependence that captures both linear and nonlinear relationships between random variables. For continuous and multidimensional variables For continuous multidimensional variables, mutual information must be estimated from samples. Because mutual information is unbounded, its values are not directly comparable across datasets, dimensions, or applications. Normalized mutual information addresses this limitation by converting mutual information into a normalized dependency score. Recent work has demonstrated the practical value of normalized mutual information in applications such as molecular dynamics {arXiv:2405.04980} and interpretable machine learning {arXiv:2409.16768}, but existing estimators remain sensitive to dimensionality and numerical stability {arXiv:2410.07642}. In this paper, we propose a fully neural normalized mutual information estimator for continuous variables. The proposed approach combines a MINE-based neural mutual information estimator {arXiv:1801.04062} with MI-NEE-inspired neural marginal entropy estimators {arXiv:1905.12957}. Mutual information is estimated using the Donsker--Varadhan representation, while marginal entropies are estimated by learning the divergence between each marginal distribution and a uniform reference distribution, from which entropy is recovered. The resulting estimator provides a neural alternative to k-nearest-neighbor-based normalized mutual information estimation {arXiv:2405.04980}. Experiments on Gaussian data from one to eight dimensions show that the proposed estimator improves accuracy over a KSG-based normalized mutual information baseline. These results indicate that neural estimation is a promising direction for normalized dependency measurement in continuous multidimensional settings. --- ### MECA: A Mechanism-Centered Agent for Constructing Well-Specified and Valuable Mathematical Conjectures Authors: Wentao Long, Yunfei Zhang, Chenyi Li, Zaiwen Wen Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27709v1 Automatically constructing well-specified and valuable mathematical conjectures remains a central challenge in AI-assisted mathematical discovery. Many existing open problems and conjectures are often too broad, underspecified, or difficult to connect to plausible proof or refutation strategies. We view a mathematical mechanism as a structure or reasoning principle that connects the assumptions of a candidate problem to its target conclusion, such as an inequality, invariant, decomposition, or reduction to an intermediate claim. We present MECA (MEchanism-centered Conjecture Agent), a multi-agent framework that constructs conjectures by jointly developing candidate statements and their supporting mechanisms. Explorer agents propose mechanisms, test how they apply, and revise the candidate conjecture accordingly, while critic agents assess their mathematical validity and research value. Their feedback guides changes to the assumptions, scope, and conclusion. Through this process, MECA transforms broad research directions into precise conjectures with substantive mathematical support while retaining a clearly identified unresolved core. We evaluate MECA in two complementary settings. First, we compare it with a generate-and-revise baseline on reconstructing preselected target-paper conclusions from target-conditioned but article-blind source materials. Second, we construct 100 semi-open problems from literature-derived seeds and existing open problems and evaluate them through independent proof and refutation attempts by automated provers. Our results indicate that mechanism-centered refinement produces well-specified and research-worthy conjectures that remain challenging for current automated provers. --- ### Albilich: Steerable Proof-State Orchestration for LLM-Based Mathematical Research with CAS Integration Authors: Ting Gong, Michael Ruofan Zeng, Yong Yang Published: 2026-07-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.27705v1 Large language models can contribute useful ideas to mathematical research, yet long-horizon proof attempts remain difficult to coordinate, evaluate, and reproduce. We present Albilich, an open-source agentic harness for autoresearch in mathematics that combines long-horizon reasoning, computer algebra systems (CAS), literature retrieval, and persistent SQLite-based context management. We evaluate Albilich on the RealMath benchmark (Zhang et al. 2025) and on open problems in group theory from the Kourovka Notebook (Khukhro and Mazurov 2026). It solved 10/10 problems on RealMath with CAS and 9/10 with no CAS. On the Kourovka problems, Albilich produced a counterexample to Problem 21.142 and a proof of a strengthening of Problem20.2. Anablation on Problem 17.91 demonstrates 32.0% token reduction when CAS is enabled. An ablation on Problem 21.142 demonstrates higher verifier-rejection rate and failure to synthesize proof routes in the absence of the advisor agent. These results support Albilich as a human-steerable, CAS-boosted environment for scalable AI-assisted mathematical research. --- ### LightRot: A Light-Weighted Rotation Scheme and Architecture for Accurate Low-Bit Large Language Model Inference Authors: Sangjin Kim, Yuseon Choi, Jungjun Oh, Byeongcheol Kim, Hoi-Jun Yoo Published: 2026-07-30 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2607.27704v1 As large language models (LLMs) continue to demonstrate exceptional capabilities across various domains, the challenge of achieving energy-efficient and accurate inference becomes increasingly critical. This work presents LightRot, a lightweight rotation scheme and dedicated hardware accelerator designed for low-bit LLM inference. The proposed architecture integrates Grouped Local Rotation (GLR) and Outlier Direction Aligning (ODA) algorithms with a hierarchical Fast Hadamard Transform (FHT)-based rotation unit to address key challenges in low-bit quantization, including the energy overhead of rotation operations. The proposed accelerator, implemented in a 28nm CMOS process, achieves a peak energy efficiency of 27.4 TOPS/W for 4-bit inference, surpassing prior state-of-the-art designs. Unlike conventional approaches that rely on higher-precision inference or evaluate on basic language modeling tasks like GPT-2, LightRot is optimized for advanced models such as LLaMA2-13B and LLaMA3-8B. Its performance is further validated on MT-Bench, demonstrating robust applicability to real-world conversational scenarios and redefining benchmarks for chat-based AI systems. By synergizing algorithmic innovations and hardware efficiency, this work sets a new paradigm for scalable, low-bit LLM inference, paving the way for sustainable AI advancements. --- ### SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them Authors: Yang Zhou, Zixuan Huang, Sunzhu Li, Zhuo Yang, Chen Zhang, Shunian Chen, Caijun Yan, Jianyao Xu, Shunyu Liu, Weijie Fu, Peiliang Li, Xiaozhi Chen et al. Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27703v2 Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task-level decisions based on that reasoning. However, a fundamental capability mismatch remains: general VLMs can reason about the overall task but often miss the visual details that determine success, while specialist vision models can capture those details but cannot translate them into task-level decisions. In this work, we propose SpatialCLI, a framework that teaches VLMs to reason with spatial tools and progressively internalize the specialist perceptual capabilities they provide. SpatialCLI proceeds in three stages: (1) Call exposes specialist vision models as spatial tools to augment the VLM's perception; (2) Learn uses Cold-Start SFT and agentic RL to improve tool use; and (3) Internalize verbalizes successful tool-use trajectories to internalize specialist perceptual capabilities. We further introduce SpatialCLI-Bench, a 516-example benchmark for compositional perception across localization, segmentation, depth, and pose. On MindCube, SpatialCLI raises Qwen3-VL-8B-Instruct from 29.3% to 84.6% with tools, surpassing GPT-5.6 Sol with tools (72.1%), while retaining 73.8% without tools after internalization. --- ### Calibrate Before Reason: Robust Visual Token Reduction against Semantic Drift in VLMs Authors: Jiasheng Li, Zhong Ji, Yan Zhang, Huihui Li Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27700v1 Large Vision-Language Models (VLMs) suffer from prohibitive inference overhead due to long sequences of visual tokens. However, existing visual token reduction methods mainly improve efficiency by pruning or compressing redundant tokens without examining whether the resulting representation remains semantically consistent with the original representation. Mapping the original N-token visual sequence to K tokens may discard, dilute, or misassign critical visual cues, triggering severe semantic drift that deviates the VLM's understanding. In this paper, we first introduce the principle of 'Calibrate Before Reason' to visual token reduction and propose CaRe, a training-free robust framework that calibrates compact visual representations before reasoning to preserve semantic fidelity in VLMs. CaRe consists of two mutually complementary modules: 1) Perturbation-Robust Calibration Anchoring, which identifies calibration anchors with stable model-side influence under multi-directional perturbations; 2) Confidence-Gated Token Calibration, which extracts reliable calibration signals from unselected tokens and injects them into anchors. Extensive evaluations across diverse VLM architectures and benchmarks verify that CaRe outperforms state-of-the-art token reduction baselines. While pruning 94.4% of visual tokens, our method retains 96.4% of the original full-token performance, delivering up to 2.30 times faster end-to-end inference speed relative to unpruned vanilla models. --- ### RefineSVG: Visual Feedback-Driven Reinforcement Learning for Image-to-SVG Generation Authors: Shaobo Liu, Feiqiao Mao, Shuaishuai Zhou, Yan Zhan, Weiqi Tan, Zhiqiong Lu, Zhengping Liang Published: 2026-07-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.27699v1 We propose RefineSVG, a single-step closed-loop visual feedback framework that enables multimodal large language models (MLLMs) to perform high-fidelity image-to-SVG generation through self-correction. Existing MLLM-based approaches rely on single-pass open-loop inference, where the model receives visual input only once and must generate thousands of SVG code tokens without intermediate verification. This paradigm inevitably leads to geometric drift, error accumulation, and visual hallucination on complex images. RefineSVG overcomes this limitation by invoking an external rendering engine after an initial SVG generation pass to compare the rendered output against the target image. The comparison yields a multi-dimensional visual residual map (Diff-Map) that is fed back to the model as a ReAct-style correction signal, driving a targeted correction step. To support this render-observe-correct interaction, we further introduce an SVG-oriented semantic vocabulary that compresses token sequences by over 52%. A progressive training pipeline spanning supervised fine-tuning, rejection-sampling cold-start data construction, and end-to-end agentic reinforcement learning aligns the model with closed-loop visual correction. Extensive experiments show that RefineSVG consistently outperforms existing baselines in reconstruction fidelity, structural accuracy, and code efficiency.Code is available at https://github.com/liuxiaobo66/RefineSVG. --- ### Guiding Large Language Models with Genetic Programming-Evolved Heuristic Knowledge for Dynamic Multi-Mode Project Scheduling Authors: Yuan Tian, Yi Mei, Mengjie Zhang Published: 2026-07-30 Categories: cs.AI, cs.NE arXiv: https://arxiv.org/abs/2607.27698v1 In dynamic multi-mode project scheduling, activities have alternative execution modes and uncertain durations, while precedence relations and limited resources constrain their execution. Heuristic priority rules support fast online decisions, but their design requires substantial domain expertise. Genetic programming (GP) hyper-heuristics can automatically evolve such rules. Large language models (LLMs), meanwhile, provide a flexible interface for interpreting scheduling information and explaining decisions. However, zero-shot LLM decisions may lack domain knowledge, consume many tokens, and vary across repeated queries. GP-evolved rules therefore provide a potential source of scheduling knowledge for guiding LLM decisions. Unlike existing LLM--GP hybrids that use LLMs to support heuristic evolution, we transfer knowledge in the reverse direction, using knowledge extracted from high-quality GP rules to guide an online LLM decision maker. We extract knowledge from high-quality GP rules and inject it through Feature Selection, Feature Hint, Rule Reference, and Rule Follow. These mechanisms are evaluated in terms of scheduling performance, token consumption, decision stability, and the feature focus expressed in generated rationales. GP-derived guidance generally improves the unguided LLM, but its representation matters. Simplifying the decision context or supplying explicit decision logic is more effective than highlighting important features. Feature Selection offers the best token efficiency, whereas Rule Follow achieves strong performance at greater token cost. Guidance also improves decision stability and changes the features expressed in generated rationales. --- ### GyRot: Leveraging Hidden Synergy between Rotation and Fine-grained Group Quantization for Low-bit LLM Inference Authors: Sangjin Kim, Yuseon Choi, Byeongcheol Kim, Jungjun Oh, Hoi-jun Yoo Published: 2026-07-30 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2607.27694v1 Low-bit quantization is essential for efficient LLM inference, and both rotation and fine-grained group quantization have shown individual promise. However, their combination often leads to accuracy degradation or hardware overhead due to a mismatch between the global nature of rotation and the localized behavior of group scaling. We propose GyRot, a quantization framework and hardware accelerator that bridges this gap through algorithm-hardware co-design. GyRot introduces Coarse Rotation, Fine Grouping (CoRFiG) and Harmonic-Aligned Permutation (HAP) to enable cooperative integration of rotation and group quantization, enhancing quantizability while relaxing scaling factor precision. To further reduce hardware cost, we reformulate asymmetric quantization and introduce a zero-point rounding strategy that enables fully integer dequantization. Implemented on an INT4-based tensor PE architecture, GyRot achieves state-of-the-art 4-bit accuracy across LLaMA-family models, while delivering up to 3.4x speedup and 3.6x energy efficiency over baseline LLM accelerators. These results validate GyRot's practical effectiveness for scalable and energy-efficient LLM deployment. --- ### Recall Before You Rank: Similarity-Guided Top-$K$ Reuse for Efficient Long-Context Attention Authors: Wenshuai Yao, Wenyong Zhou, Hanyong Shao, Yizhe Chen, Zhiyuan Ning, Yuannuo Feng, Ru Huang, Kechao Tang Published: 2026-07-30 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.27692v1 Top-$K$ sparse attention reduces the cost of Softmax and value aggregation by attending to only a small subset of key--value (KV) entries. However, identifying this subset still requires scoring the current query against the full KV cache and performing global Top-$K$ selection, leaving selector cost linear in context length and limiting the practical efficiency of sparse attention for long-context decoding. In this paper, we introduce ReTopK, a training-free method that accelerates dynamic Top-$K$ attention by reusing historical retrieval decisions. ReTopK builds on the observation that similar queries often attend to overlapping supports and that partially overlapping supports can still preserve most of the Exact Top-$K$ attention mass. For each attention head, it maintains a bounded cache of historical query--support pairs, retrieves the most similar cached queries for each new query, unions their stored supports with a recent window, and reranks only the resulting compact candidate set using exact current-query scores. A similarity-based fallback invokes full-history Exact Top-$K$ when reuse is unreliable, while periodic exact refreshes limit cache drift. ReTopK retains the complete KV cache and reuses only selected indices, rather than historical scores, attention weights, or outputs. Across 16K--128K contexts, ReTopK achieves the lowest PG19 perplexity and the highest NIAH and LongBench scores among the evaluated approximate methods. At 128K with $K=512$, ReTopK incurs only a 0.50\% perplexity increase over Exact Top-$K$ while accelerating attention computation by $3.07\times$. --- ### LabEvolver: Training-Free Experience Evolution for Safe and Grounded Wet-Lab Agents Authors: Jingya Wang, Yuyang Gao, Liuzhenghao Lv, Yonghong Tian, Yuyang Liu Published: 2026-07-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.27690v2 We introduce LabEvolver, a training-free framework that equips safe and grounded wet-lab agents with episodic memory from execution experience. LabEvolver couples a state-grounded inner trial loop for adaptive perception, online planning, and safety validation with an outer evolution loop that distills completed trajectories into reusable skill, strategy, and safety experience. On robotic solution-preparation tasks, LabEvolver demonstrates real-world feasibility, reducing pH-regulation completion time and safety-gate intercepts by 48.2% and 60.0%, respectively. On ALFWorld, it further improves cumulative success rate within 20 steps from 76.2% with ReAct to 91.4% over 500 continual tasks, showing generality beyond wet-lab settings. These results support learn-by-doing experience evolution as a feasible path toward closed-loop automated scientific discovery. The project page is available at https://andygao6186.github.io/LabEvolver/. --- ### Rehearse: Stepping Back from the Confidence Cliff in Self-Improving Autoresearch Authors: Jiazhen Ji, Shouhong Ding Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27687v1 Autoresearch improves machine-learning code by proposing changes, running full training jobs, and keeping changes that improve the metric. The efficiency of this loop depends not only on generating ideas, but also on the agent's ability to decide, before spending a training run, whether a proposed modification is likely to work. We study how the reliability of this pre-execution judgment changes over the course of an autoresearch trajectory. In public AutoSOTA logs (Li et al., 2026; Tsinghua FIB Lab, 2026), the fraction of helpful modifications falls from 70% in the first two iterations to 43% by iteration 6+. On 296 same-baseline modification pairs from 39 paper-derived AutoSOTA tasks, each containing one modification that improved the metric and one that did not, with measured outcomes hidden, an LLM judge given candidate rationales but no prior-attempt history reaches 79.5% accuracy on the pairs where strict consensus returns a verdict. On the full 366-pair benchmark, however, this ability weakens substantially late in the loop. As successful changes accumulate, selective accuracy - accuracy conditioned on a strict-consensus verdict - falls from 82.8% to 56.9%, while the judge remains willing to decide. We call this operational pattern the confidence cliff. Rehearse implements the loop change as a lightweight skill for autoresearch loops: propose several ideas, compare them before execution, run the most promising, and judge with a focused memory of similar past attempts and outcomes. This focused outcome memory raises late selective accuracy to 83.5%. Across 4,000 budgeted training runs over three loops, Rehearse improves the endpoint under the same training-run budget on nanochat, image classification, and time-series forecasting. --- ### Evaluating and Pricing Advertisements in AI-Generated Responses Authors: John L. Turner-Smith, Zimeng Huang, Yuhan Fu, Yihang Zhang, Tonghan Wang Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27686v1 As search increasingly shifts toward LLM-driven answer engines, advertising is becoming embedded within the generated response itself and should therefore be evaluated for both user utility and commercial value. The key challenge is click-through intent: behavioural logs are unavailable, human annotation resists calibration, and frontier LLM judges conflate intent with linguistic fluency. These gaps compound, as principled pricing presupposes a continuous intent signal, while generating such a signal presupposes supervision that is currently unavailable. We construct the missing supervision through a psychologically grounded agent simulation framework, and distil it into a parameter-efficient evaluator that predicts click-through intent, together with the three companion dimensions of ad quality, as smooth, differentiable estimates. Validated through sign-certain behavioural perturbations, the evaluator surpasses frontier zero-shot judges on relevance sensitivity (79% versus 60-67%), tracks graded content degradation, generalises without error to 103 fictional products, and agrees with human preference in 86% of pairwise judgements across five annotators, with agreement rising in the evaluator's confidence. Upon its estimates we build the pricing layer directly, deriving the unique payment rule under which truthful bidding is optimal, demonstrating it on a best-of-k allocation, and extending the mechanism to non-monotone allocations. The same differentiable signal stands ready as a training objective for ad generation. --- ### Event-Structured Physics-Informed Neural Networks for Differentiable Critical Clearing Boundaries Authors: Baoli Hao, Chenxi Hu, Ming Zhong, Ren Wang Published: 2026-07-30 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2607.27681v1 Transient-stability assessment determines whether a power system can recover after a disturbance and is therefore essential to preventing generator trips and cascading outages. A key metric is the critical clearing time (CCT), which specifies the maximum time available to clear a fault before synchronism is lost. Reliable CCT estimation is challenging because complicated fault-clearing dynamics require repeated simulations over many fault severities and clearing times. We propose an event-structured physics-informed neural network (ES-PINN) that aligns its representation with the pre-fault, fault-on, and post-clearing swing dynamics and enforces exact state chaining across event interfaces. A smooth trajectory-induced stability margin defines a differentiable approximation of the CCT boundary, enabling accurate boundary extraction, local sensitivity analysis, and optional direct CCT prediction through a distilled readout. We further prove a local residual-to-trajectory-to-CCT error estimate, in which exact event chaining eliminates separate state-interface defect terms. Experiments on IEEE 9-, 14-, and 30-bus systems show that ES-PINN consistently improves held-out trajectory and stability-boundary accuracy over matched neural-surrogate baselines across mechanical and electrical contingencies with multiple clearing configurations. Additional full-network DAE validation, multi-fault experiments, and runtime analyses further demonstrate the effectiveness and computational efficiency of the proposed framework. --- ### Tight Sample Complexity for Low-Rank Adaptation: Matching Bounds and Rank Selection Authors: Arunan J Published: 2026-07-30 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.27680v1 Low-Rank Adaptation (LoRA) has become the standard mechanism for fine-tuning large pretrained models, yet its statistical properties remain only partially understood. Existing generalization results provide upper bounds of the form O~(sqrt(rd/n)) or O~(rd/n), but a matching lower bound is missing, and the question of how to choose the LoRA rank r has no formal answer. Both gaps are closed here. A local Rademacher argument establishes an upper bound of O~(rd/n) on the excess risk of the empirical risk minimizer over rank-r LoRA, whenever the target adaptation has rank at most r. A matching minimax lower bound of Omega(rd/n) is then proved via a Fano-type packing of the rank-r subspace of R^{d x d}; the bound applies to any estimator whose output lies in the rank-r LoRA class. Combining the two yields a rank-selection dichotomy. For the constrained empirical risk minimizer, the optimal rank equals the intrinsic rank r*, and over-ranking strictly hurts. For adaptive estimators of the nuclear-norm-then-truncate type, over-ranking is harmless and the rate saturates at Theta~(r* d / n) regardless of r. Taken together, the three results characterize the statistical complexity of LoRA fine-tuning within the well-specified locally quadratic regime, and identify the empirically observed over-parameterization penalty as a property of unregularized empirical risk minimization rather than of the LoRA class itself. Predictions of the theory are verified on a synthetic trace-regression benchmark and on real LoRA fine-tuning across three (model, task) configurations covering DistilBERT and RoBERTa on SST-2 and MRPC. All configurations exhibit the predicted U-shape in validation loss, with two showing statistically significant loss inflation at large ranks (paired permutation p = 0.016). --- ### Stop Shipping AI Agents on Faith: Capability Is Not Production Readiness Authors: Fouad Bousetouane Published: 2026-07-30 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2607.27677v1 AI agents are moving into production workflows where they retrieve information, call tools, maintain state, and act on behalf of users or organizations, but many release decisions still rely on capability signals, demos, or behavioral tests that do not show whether an agent is ready to operate under production constraints. Capability is therefore not production readiness. This paper introduces the ProofAgent Index (PAI), a governance readiness index for AI agents. PAI combines four dimensions of deployment evidence: Evaluation, Context, Compliance, and Governance. Evaluation measures observed behavior, Context measures the operating environment that shapes that behavior, Compliance measures alignment with applicable rules and controls, and Governance measures whether the organization can authorize, monitor, audit, and control the agent during operation. PAI is implemented inside ProofAgent Harness, an open source infrastructure for auditable AI agent evaluation and governance. Validation across two heavily regulated domains, healthcare and finance, shows that PAI carries held out readiness signal and separates higher risk from lower risk configurations. The results show that context engineering strongly changes reliability, capability improves behavior but does not determine readiness, and governance evidence must remain visible rather than averaged away. PAI reframes agent release from a faith based deployment decision into an auditable readiness decision. --- ### ICLE++: Modeling Fine-Grained Traits for Holistic Essay Scoring Authors: Shengjie Li, Vincent Ng Published: 2026-07-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.27671v1 The majority of the recently-developed models for automated essay scoring (AES) are evaluated solely on the ASAP corpus. However, ASAP is not without its limitations. For instance, it is not clear whether models trained on ASAP can generalize well when evaluated on other corpora. In light of these limitations, we introduce ICLE++, a corpus of persuasive student essays annotated with both holistic scores and trait-specific scores. Not only can ICLE++ be used to test the generalizability of AES models trained on ASAP, but it can also facilitate the evaluation of models developed for newer AES problems such as multi-trait scoring and cross-prompt scoring. We believe that ICLE++, which represents a culmination of our long-term effort in annotating the essays in the ICLE corpus, contributes to the set of much-needed annotated corpora for AES research. --- ### JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles Authors: Shawn Li, Wei Yang, Jike Zhong, Jiate Li, Jiawei Yang, You Qin, Ryan Rossi, Franck Dernoncourt, Roger Zimmermann, Yue Wang, Zhengzhong Tu, Vicente Ordonez et al. Published: 2026-07-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.27670v2 Jigsaw puzzle solving requires jointly reasoning about visual content and geometric constraints, yet existing benchmarks use rectangular cuts that create ambiguous ground truth in texture-repeated regions. We introduce \textit{\ours{}}, a benchmark with tab-and-blank interlocking pieces where geometric constraints provide strong local compatibility requirements that, combined with visual content, yield unambiguous ground truth. Across 95K instances at four grid densities (4$\times$4 to 16$\times$16), we find that \textbf{zero-shot VLMs largely lack geometric reasoning}: only one of five frontier models (GPT-5.5) exceeds random baseline on 4$\times$4 puzzles, while all others perform at chance level. While supervised fine-tuning achieves $>$97\% on 4$\times$4, \textbf{all models collapse on larger grids}: GPT-5.5 drops from 70\% to near-random on 8$\times$8, and even fine-tuned models fall below 5\% on 12$\times$12. This ``scaling cliff'' suggests current architectures cannot maintain consistent constraint satisfaction as the number of pieces increases. \ours{} establishes scalable geometric reasoning as an open challenge for vision-language models. --- ### Witness Evidence Portfolios: Single-Prefill Risk Detection for Closed Multimodal Answers Authors: Fexiang Liu, Shiye Wang, Qiang Qiu, Zheng Wang Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27667v1 Reliable deployment of multimodal large language models (MLLMs) requires deciding whether a confident visual answer should be trusted, reviewed, or routed to a stronger system. Confidence scores capture candidate margins, but not where the estimated signed visual readouts associated with those margins come from or how they are distributed. We study inference-time risk detection for closed visual answers using the same white-box prefill path that produces the answer. Witness Evidence Portfolios (WEP) first estimates, layer by layer, which visual contributions support or contradict the predicted candidate. It summarizes these contributions through two interpretable route families: question-related evidence provenance and signed evidence concentration. Nested grouped validation chooses the more reliable family and a sparse top-k route portfolio, which is fused with candidate confidence. WEP needs no image perturbation, decoding change, backward pass, or external verifier. Across three MLLMs and four binary-answer benchmarks, WEP improves mean error AP by 0.134. All 12 model--dataset gains are positive, and image-cluster bootstrap intervals are strictly positive on 10 pairs. WEP targets white-box closed-answer systems and uses a labeled calibration slice. --- ### FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learning Authors: Zekai Chen, Haodong Lu, Shihao Li, Weiwei Ji, Xunkai Li, Xun Wu, Yinlin Zhu, Rong-Hua Li Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27665v1 Federated graph learning enables collaborative training over decentralized graph data without sharing raw graph information. As such risks evolve, clients must learn emerging classes from private multimodal graph streams, retain historical categories, and reject samples outside the known class space. In this setting, clients must learn emerging classes from private multimodal graph streams while preserving historical categories and rejecting samples outside the current known class space. The core challenge is catastrophic forgetting, which in federated multimodal graphs is not merely a classifier-level failure: old knowledge can be erased through modality-semantic overwriting, topology-induced structural erosion, and federated memory fragmentation. To address this challenge, we propose \textbf{FedOGL}, a semantic-structural memory preservation framework. On the client side, FedOGL preserves historical decision behavior through replay and task-start distillation, while protecting graph-propagation memory via projection onto a globally shared structure basis. On the server side, FedOGL maintains and transfers compact category prototypes to facilitate cross-client knowledge sharing without exposing raw graph data. Extensive experiments demonstrate that, compared with the best-performing baselines, FedOGL reduces performance degradation caused by catastrophic forgetting by \textbf{42.67\%}, while maintaining or improving performance on downstream tasks. --- ### Understanding Submodular Information Measure Based Objectives for Representation Learning: A Variance and Separation Perspective Authors: Rishabh Iyer, Truong Pham, Anay Majee Published: 2026-07-30 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.27660v1 Submodular Information Measures (SIMs) have recently emerged as a powerful framework for representation learning and multimodal learning. In particular, the SCORE framework~\cite{majee2024score} demonstrated that SIMs can serve as effective objectives for supervised contrastive learning. Despite their empirical success, however, the geometric and statistical properties induced by different submodular information measures remain poorly understood. In this work, we develop a unified theoretical framework connecting SIMs to classical concepts in representation learning and statistical pattern recognition. We show that Total Information (TI) objectives characterize intra-class structure: Graph Cut TI recovers within-class variance, LogDet TI recovers generalized variance and covariance volume, and Facility Location TI induces imbalance-aware separation that emphasizes rare and confusable classes. We further show that Mutual Information (MI) objectives capture complementary notions of inter-class structure: Graph Cut MI is closely related to centroid separation and Fisher-style discrimination, LogDet MI captures covariance-aware separation through Mahalanobis distance, and Facility Location MI measures nearest-mode representational overlap. We validate these theoretical characterizations using controlled synthetic experiments that independently vary variance, covariance, class imbalance, class separation, and multimodal overlap. Across all settings, the empirical behavior closely matches the proposed theory. Our results provide the first unified geometric and statistical understanding of submodular information measures and offer principled guidance for selecting and designing SIM-based objectives for representation learning. --- ### Learning Color Grading, No Photo Sharing: Federated Aesthetic Preference Learning for Personalized Image Enhancement Authors: Chuanzhi Xu, Ziyuan Tao, Jean Julien KNell, Yanrong Chen, Haolan Guo, Xuanhua Yin, Adnan Mahmood, Weidong Cai Published: 2026-07-30 Categories: cs.CV, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2607.27659v1 Personalized image enhancement should reflect individual aesthetic taste, yet learning such preferences commonly depends on private photos and ratings that are unsuitable for centralized collection. The task must infer preference from sparse, heterogeneous feedback and translate it into natural-looking color transformations on resource-constrained user devices. We introduce FedPAIE, a federated personalized aesthetic image enhancement framework for user-adaptive color grading without centralizing raw photos or ratings. FedPAIE trains a lightweight dual-cue aesthetic scorer, calibrates it into a personalized scorer on a small local support set, and freezes it to guide regularized adaptation of a lightweight CLUT enhancer from unpaired local photographs. Fidelity constraints and an excess-gap penalty regularize scorer-guided adaptation to limit proxy-score over-optimization while preserving content and natural appearance. Training remains lightweight throughout the pipeline: scorer learning updates at most 0.787M parameters, enhancer adaptation updates 0.265M, and inference retains only a 0.293M-parameter personalized enhancer. Experiments on MIT-Adobe FiveK and Flickr-AES demonstrate effective open-world personalization and a favorable balance between user preference and image fidelity. FedPAIE thus connects decentralized preference learning with efficient personalized image transformation without requiring paired user retouches. --- ### Looped Transformers with Source-Centered State Evolution Authors: Bum Jun Kim, Kohei Hayashi, Shunsuke Kamiya, Masanori Koyama, Yusuke Iwasawa, Yutaka Matsuo Published: 2026-07-30 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.27656v1 Looped Transformers create a useful train- and test-time compute axis by reusing the same Transformer block over recurrent depth, increasing effective depth at a fixed parameter count. However, that shared block must then govern an entire trajectory of varying hidden states over trained and extrapolated depths. Furthermore, in additive-injection looped Transformers, an input-conditioned signal is reintroduced at every recurrent step, so applying the shared transition at an input-conditioned reference can still move the hidden state. In this paper, we propose Source-Centered State Evolution (SCSE), which is designed to reconcile input conditioning with reference-preserving shared recurrence. Specifically, SCSE retains input dependence through its learned anchor and initial deviation, allows nonzero deviations to drive recurrent computation while mapping zero deviation to zero, and guarantees exact anchor invariance through its zero-deviation mask. The designated anchor is thereby a one-step fixed point by construction. The zero-deviation forcing bias is the next deviation produced from the anchor itself and vanishes in SCSE, while nonzero deviations remain active and support state-dependent recurrent computation. Our theory shows that the zero-deviation forcing bias is a design degree of freedom whose task effect can be harmful, neutral, or beneficial; SCSE resolves this choice in favor of exact anchor invariance by setting the bias to zero. Across WikiText-2, WikiText-103, direct web-corpus pretraining, held-out web-text transfer, and LAMBADA completion, SCSE improves the controlled recurrent quality frontier. Ablation studies identify the learned anchor and the anchor-coordinate deviation recurrence as the primary contributors to the gain, and a trained-model case study grounds the anchor-response diagnostic in observed recurrent motion. --- ### Checkpoint Selection and Evaluation in EEG Emotion Recognition Authors: Hanting Suo, Hongxun Wang, Yuwen Li Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27655v2 Checkpoint selection can improve an electroencephalography (EEG) emotion-recognition score without improving performance on other trials. We compared selection and scoring on disjoint trial pools along fixed training trajectories. A same-session SEED study comprised 300 trajectories from 15 participants, two models and five trial-role rotations. Another 276 trajectories extended the comparison to separate training, validation and target sessions in SEED, SEED-IV and SEED-V, with 15, 15 and 16 participants, respectively. Increasing the candidate set from five to 80 checkpoints raised the same-session dynamical graph convolutional neural network (DGCNN) selection-pool score by 6.24 percentage points, while the other-pool change was -1.24 (descriptive 95% participant-bootstrap interval -2.67 to 0.26). Under the cross-session design, DGCNN retained gains of 4.47 (1.79, 7.25), 4.27 (2.00, 6.53) and 2.75 (0.79, 4.78) points across the three datasets. Multilayer perceptron results varied across datasets. Common-time-range analysis and trial-level scoring supported the respective patterns. Both target pools supplied labels for symmetric checkpoint selection; these results concern retention across trials, not evaluation without target labels. Complete policy curves and executable reconstruction support reporting selected-score improvements alongside performance on other trials, rather than assuming a universal penalty for checkpoint search. --- ### Evaluation Protocols and Cross-Subject Generalization in EEG Emotion Recognition Authors: Hanting Suo, Yuwen Li Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27655v1 Reported accuracy in electroencephalography (EEG) emotion recognition depends on the complete evaluation procedure, not only the classifier. We separate the target quantity, development procedure, and reporting rule, then use one archived dynamical graph convolutional neural network (DGCNN) pathway on SEED and SEED-IV as an illustrative case. In a protocol-matched subject-dependent check, the SEED result was within 1.47 percentage points of the public reference value; the 3.40-point SEED-IV difference remained unresolved. Across 30 matched SEED subject-session trajectories, checkpoint selection based on repeated test-set evaluation increased mean window accuracy from 0.7855 at epoch 80 to 0.8892. Under five-fold subject-disjoint evaluation, validation-selected checkpoints achieved training-participant trial accuracies of 0.9990 on SEED and 0.9920 on SEED-IV. Accuracy for entirely held-out participants was 0.5348 (95% conditional subject-level bias-corrected and accelerated (BCa) interval (0.4667, 0.5985)) on SEED. The SEED-IV estimate was 0.3954 ((0.3343, 0.4648)) and is reported only as secondary sensitivity evidence because its protocol-matched compatibility check remained unresolved. The observed train-to-held-out-subject gaps are inconsistent with simple optimization underfitting, but they do not isolate subject identity from implementation, preprocessing, representation, or distributional factors. Supporting analyses further showed that participant rankings depended on representation and time scale, while a development-selected tail-risk ensemble did not establish a positive gain in a separate final evaluation. Subject-dependent, subject-disjoint, and cross-session results should therefore be reported as answers to different questions. --- ### From Single- to Cross-Document: Benchmarking Multi-Granularity Event Analysis of Large Language Models Authors: Tao Wen, Shuai Shao, Pei Ke, Xu Han, Jie Zou, Guannan Li, Tao Tian, Jinjie Qiu, Lan Wang, Ke Qin Published: 2026-07-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.27654v1 Event analysis is an essential and fundamental direction of information extraction, involving various event-centric tasks at different granularity of documents. While large language models (LLMs) have preliminarily achieved promising performance in part of these tasks individually, their capability in event analysis still lacks comprehensive understanding due to restricted document granularity, task designs, and data source of existing benchmarks. To address these limitations, we introduce MiGUE-Bench, a systematic benchmark for assessing the performance of LLMs in multi-granularity event analysis. To support large-scale evaluation, we first develop an LLM-driven self-correcting annotation framework called MiGUE-Pipeline, enabling scalable acquisition of high-quality source data of events with automatic labels. Then, we design four core tasks in our benchmark, i.e., event detection, relation reasoning, structure induction, and future prediction, to probe model competence at different levels, from atomic event details to complex cross-document narratives. Extensive experiments on state-of-the-art LLMs and retrieval-augmented generation (RAG) methods delineate the current capability boundary and identify critical deficiencies, providing insights into the future improvement of LLMs in challenging event analysis tasks. --- ### Harness-G: A Graph-Structured Harness for Search Agents Authors: Yanning Hou, Haoyuan Chen, Sihang Zhou, Xiaoshu Chen, Xirui Liu, Duanyang Yuan, Lingyuan Meng, Siwei Wang, Quan Liu, Jian Huang Published: 2026-07-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.27652v3 Reinforcement learning (RL) search agents commonly model retrieval as free-form natural-language query generation and optimize multi-turn interactions using final-answer rewards. Current studies mainly improve training with denser or more structured credit signals, but rarely examine whether retrieval is properly formulated at the policy-environment interface. We observe pronounced retrieval aliasing during Search-R1 training: rollouts for the same question continue to generate distinct query strings, yet their accumulated evidence sets increasingly overlap. We call this phenomenon retrieval-equivalence collapse; in this regime, trajectories approach utility equivalence with respect to retrieval decisions, leaving within-group returns with little effective retrieval contrast. To address this problem, we propose Harness-G, a graph-structured retrieval framework that redesigns this interface. It reformulates free-form query generation as finite action selection: the policy selects an evidence sentence or entity, or chooses to answer, while the environment constructs the menu, tracks retrieval state, and validates and executes each choice. This interface reduces linguistic aliasing and makes same-state alternatives directly comparable. Building on this interface, we introduce Structured Non-myopic Credit (SNC), which uses a frozen answer scorer to compare the selected action with its alternatives and assigns downstream gains to the earlier actions that enabled them. Across six QA benchmarks, Harness-G achieves the highest average F1 at both evaluated model scales, outperforming the strongest baseline, Graph-R1, by 10.74 points at 1.5B and 3.98 points at 3B. --- ### Harness-G: A Graph-Structured Harness for Search Agents Authors: Yanning Hou, Haoyuan Chen, Sihang Zhou, Xiaoshu Chen, Xirui Liu, Duanyang Yuan, Lingyuan Meng, Siwei Wang, Quan Liu, Jian Huang Published: 2026-07-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.27652v2 Reinforcement learning (RL) search agents commonly model retrieval as free-form natural-language query generation and optimize multi-turn interactions using final-answer rewards. Current studies mainly improve training with denser or more structured credit signals, but rarely examine whether retrieval is properly formulated at the policy-environment interface. We observe pronounced retrieval aliasing during Search-R1 training: rollouts for the same question continue to generate distinct query strings, yet their accumulated evidence sets increasingly overlap. We call this phenomenon retrieval-equivalence collapse; in this regime, trajectories approach utility equivalence with respect to retrieval decisions, leaving within-group returns with little effective retrieval contrast. To address this problem, we propose Harness-G, a graph-structured retrieval framework that redesigns this interface. It reformulates free-form query generation as finite action selection: the policy selects an evidence sentence or entity, or chooses to answer, while the environment constructs the menu, tracks retrieval state, and validates and executes each choice. This interface reduces linguistic aliasing and makes same-state alternatives directly comparable. Building on this interface, we introduce Structured Non-myopic Credit (SNC), which uses a frozen answer scorer to compare the selected action with its alternatives and assigns downstream gains to the earlier actions that enabled them. Across six QA benchmarks, Harness-G achieves the highest average F1 at both evaluated model scales, outperforming the strongest baseline, Graph-R1, by 10.74 points at 1.5B and 3.98 points at 3B. --- ### Held-out evidence resolves follow-up measurement decisions in biological screens Authors: Jia Bi, Samuel Pinilla, Chenyang Zhu Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27651v3 Machine learning determines which follow-up measurements biological screens collect. In a six-rule Cell Painting battery, the highest-value rule would re-image 96.01% of the library and had a 97.14% false-activation upper bound, showing why predicted value alone cannot justify replacing a fixed plan. We developed OPAL, a held-out decision test that freezes a rule and judges unnecessary measurement, coverage and value after cost against archive-specific criteria fixed before final evaluation. A development-selected sparse Cell Painting rule had 18.2-fold lower added-well burden, but its false-discovery bound exceeded 35%, so the fixed plan remained. LINCS--LJP favored broad acquisition under point-estimate criteria set during development, not selective saving. CTRP required fallback because its frozen score missed measured opportunity. OPAL separates optimization from evidence sufficient to change an experiment. --- ### Certifying when decision-time information justifies adaptive experimentation Authors: Jia Bi, Samuel Pinilla, Chenyang Zhu Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27651v1 Adaptive laboratories choose measurements during experiments, yet most methods begin after adaptation is permitted. We introduce Opportunity-aware Policy Authorization for Laboratories (\OPAL{}), a framework that decides whether adaptation should be enabled at all. \OPAL{} uses a precommitted contract to require non-trivial adaptation, controlled target risk and positive executed value after cost. We establish an impossibility boundary: source outcomes and unlabelled target covariates cannot uniformly support non-trivial authorization under unrestricted conditional outcome shift, and derive a target-calibrated recovery. Applied to an unseen 11,265-compound Cell Painting partition, the frozen gate selected 595 compounds, captured 384 positive opportunities and achieved strictly positive executed value under least-favourable completion; its 5.18\% false-activation upper bound remained below a 7.5\% limit. Among six methods, only \OPAL{} combined non-zero activation with this risk control. Locked pharmacogenomic and finite-campaign studies distinguish policy misalignment from non-certifiability, establishing authorization as a distinct layer for safe adaptive science. --- ### Robust Wavelength Selection for Partial Least Squares Sugar Content Estimation Using Combinatorial Bayesian Optimization Authors: Mitsunobu Kanebako, Ami S. Koshikawa, Masaru Hitomi, Takuro Tanaka, Mahito Chiba, Maiko Mori, Masayuki Ohzeki Published: 2026-07-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.27645v1 Wavelength selection is one of the important preprocessing methods in near-infrared spectroscopy to improve prediction accuracy and interpretability of spectral data. We formulate wavelength-region selection for sugar content estimation as a binary black-box optimization problem and propose a method based on Bayesian optimization. The proposed method constructs a sparse quadratic surrogate model and sequentially extracts interested wavelength regions by Thompson sampling. Minimizing an acquisition function is performed as a quadratic unconstrained binary optimization problem by simulated or quantum annealing. Experiments show that the proposed method improves the prediction accuracy of partial least squares regression and yields more consistent wavelength regions than genetic-algorithm-based selection and simulated annealing. Under one-bit local perturbations, the selected wavelength regions show minimal fluctuations in root mean square errors between observed and predicted values of a validation set. This local stability suggests that our method converges to a smoother error landscape and avoids isolated overfitted solutions. These results indicate that combinatorial Bayesian optimization is a useful framework for robust feature selection in spectroscopic prediction tasks. --- ### MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models Authors: Wenjie Zhu, Yabin Zhang, Wenjun Zeng, Lei Zhang Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27637v2 Multimodal Large Language Models (MLLMs) have achieved strong performance on a wide range of vision-language tasks, but often fail under imperfect or shifted contexts. A reliable MLLM should refuse truly out-of-context (OOC) questions with subject-level context shifts while still answering shifted in-context (Shifted IC) questions with non-subject context shifts. Existing benchmarks mainly target OOC or visually unanswerable questions, but overlook answerable Shifted IC cases and cover limited OOC shifts. To fill this gap, we present MMOOC, a large-scale benchmark for evaluating refusal and robust answering abilities of MLLMs. MMOOC contains over 41K image-question pairs, including answerable Shifted IC cases and unanswerable OOC cases, spanning three question formats, eight shift types and six visual scenarios, with data quality ensured through MLLM-based filtering and human verification. We evaluate model responses using Accuracy and Refusal Rate, and further introduce an LLM-as-a-Judge metric to assess the correctness of model reasoning. Experiments on diverse MLLMs show that current models still struggle to balance answer-ability and refusal under shifted contexts. We further analyze key failure patterns and show that post-training can improve robustness. MMOOC will be made publicly available. --- ### HALO: Heterogeneous Admission through Localized Obligations for Safe Agentic Execution Authors: Taewoo Park, Kyeonghyun Yoo, Kiseok Kim, Seunghyun Yoo, Hwangnam Kim Published: 2026-07-30 Categories: cs.AI, cs.RO, cs.SE arXiv: https://arxiv.org/abs/2607.27636v1 Recent agentic AI systems may return a heterogeneous response containing notices, requests, handoffs, and actions. Conditions can change before external use, so components from the same response need not remain supported together. Rejecting the whole response discards useful components, whereas checking components independently can leave a dependent without its prerequisite. We present Heterogeneous Admission with Localized Obligations (HALO), a runtime protocol that preserves supported components whose declared prerequisites also remain supported, rechecks each exact action before dispatch, and allows blocked actions to be replaced only by fresh candidates. HALO matched all 96 admission expectations and passed all 20 protocol tests. In structured-response replay, it retained 248/248 supported components, including 128/128 unaffected by unrelated changes, while a whole-response policy retained 0/248. Across ten cold-start PX4/Gazebo sessions, HALO blocked every tested stale route, observed no matching stale setpoint, and completed all fresh recoveries. --- ### HealthCAT: An Interpretable Encoder-only Transformer Framework for Health Indicator Prediction and Temporal Interpretation of Wearable Sensor Data Authors: Xiaotong Yu, Joshua Y. Kim, HaeJin Lee, Kalina Yacef Published: 2026-07-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.27635v1 Wearable sensors continuously capture fine-grained multivariate time-series data, providing opportunities to model behavioural patterns associated with health outcomes. However, existing deep learning methods prioritise predictive accuracy over interpretability, limiting their application in health research. In this study, we present HealthCAT, a flexible framework that integrates an Encoder-only Transformer with an Attentive Class Activation Token (AttentiveCAT) to generate class-specific, time-step-level interpretations. These interpretations can be mapped back onto behavioural cycles that are relevant to the domain (e.g., time-of-day), supporting individual-level analysis of wearable sensor data. We evaluated HealthCAT using two real-world wearable sensor datasets (306 participants in total). HealthCAT outperformed deep learning baselines by up to 17\% in F1-score and 12\% in accuracy on both datasets ($p<0.05$). In masking experiments, the time steps identified by HealthCAT carried significantly more predictive value than random selection across all masking conditions ($p<0.05$), indicating that the identified time steps are predictively informative. By coupling predictive performance with validated time-step-level interpretability, HealthCAT moves wearable sensor analysis beyond aggregated metrics towards temporal patterns that support health monitoring, behavioural pattern analysis, and intervention design in health research. The significance of this work is that it enables accurate prediction of health indicators from wearable sensor data while providing insights into when and how physical activity patterns occur, rather than relying solely on aggregated summary measures. --- ### 4DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans Authors: Renlong Wu, Haoran Chen, Yuxiang Wei, Xiaowei Jin, Wangmeng Zuo, Hui Li Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.27634v1 Generating high-quality 360-degree dynamic human assets from text prompts is challenging. Existing methods usually synthesize monocular or multi-view videos first and then fit a 4D representation, which is expensive and often causes incomplete geometry or view-inconsistent renderings. We present 4DHumanDiff, a diffusion framework that directly generates dynamic humans represented by 4D Gaussian Splatting (4DGS) from text prompts. By modeling the structured 4D representation space end-to-end, 4DHumanDiff avoids video pre-generation and per-scene reconstruction, making it better suited for view-consistent and temporally coherent asset generation. The model uses a 3D U-Net backbone with temporal attention for motion-aware generation. We further construct a large-scale text-to-4DGS dataset with 60,000 high-quality pairs, and introduce 2D regularization and training-free 4D interpolation to improve rendering quality and motion smoothness. Experiments show that 4DHumanDiff generates consistent 360-degree dynamic humans within one minute, achieves better temporal and multi-view consistency, and reduces inference time by more than 10x. --- ### First-order Constrained Trilevel Optimization Over Distributed Networks for Robust Coreset Selection Authors: Yang Jiao, Kaixuan Jiao, Kai Yang, Nadjib Aitsaadi, Ilhem Fajjari, Renwei, Li Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.27632v1 With the rapid advancement of the Internet of Things (IoT), massive amounts of data are generated across distributed edge networks. Training models on full data incurs significant computational overhead and storage bottlenecks, rendering coreset selection a critical paradigm. Furthermore, given the privacy-sensitive nature of local data and the escalating demand for model robustness in real-world deployments, developing an effective distributed optimization framework for robust coreset selection is vital, yet remains largely unexplored. To this end, this work first characterizes the hierarchical dependencies among coreset selection, robust optimization, and distributed learning, and formulates the distributed robust coreset selection as a trilevel optimization problem with level-wise constraints. Furthermore, to effectively solve the trilevel problem in a distributed manner, the \underline{F}ederated \underline{F}irst-order \underline{C}onstrained \underline{T}rilevel \underline{O}ptimization (F$^2$CTO) is proposed, which synergistically integrates a hierarchical composite value-function reformulation and a distributed alternating projected gradient algorithm. To the best of our knowledge, F$^2$CTO is the first method developed for distributed robust coreset selection, as well as the first distributed optimization approach for trilevel optimization problems with level-wise constraints. Additionally, we prove that the proposed method achieves a non-asymptotic convergence rate of $\mathcal{O}(ε^{-3/2})$ for finding an $ε$-stationary point. Extensive empirical evaluations on reliable continual learning demonstrate the effectiveness and efficiency of the proposed F$^2$CTO. --- ### ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning Authors: Zhenrong Zhang, Fei Wu, Jun Du, Jianshu Zhang, Si Wei Published: 2026-07-30 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.27631v1 Reinforcement learning has emerged as an effective paradigm for enhancing the mathematical reasoning capabilities of large language models. Among existing policy optimization methods, Proximal Policy Optimization (PPO) remains particularly appealing because its learned critic can, in principle, provide token-level credit assignment. However, in mathematical reasoning tasks characterized by long reasoning horizons and sparse outcome rewards, reliable token-level credit assignment remains challenging. The standard critic often fails to accurately evaluate intermediate reasoning states, resulting in noisy advantage estimates and suboptimal policy updates. In this paper, we propose ReDiPPO, a Reference-guided and Discrepancy-aware PPO framework for mathematical reasoning. ReDiPPO introduces a reference-guided critic that uses reference answers as training-time privileged signals to provide more accurate value estimation. Meanwhile, it retains a standard critic and quantifies the token-level reference-standard discrepancy between the standard value estimate and the reference-guided value estimate. This discrepancy serves as an indicator of difficult reasoning states and is used to reweight the corresponding token-level advantages during PPO optimization. Extensive experiments on diverse mathematical reasoning benchmarks demonstrate that ReDiPPO improves value-estimation accuracy and consistently outperforms strong policy optimization baselines, including PPO, DAPO, and GSPO, in final reasoning performance. Our code is available on https://github.com/cii030/ReDiPPO. --- ### SCOPE: Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimization Authors: Nguyen Viet Tuan Kiet, Nguyen Huu Duc, Le Cong Bang, Tran Cong Dao, Huynh Thi Thanh Binh Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.27630v1 Black-box combinatorial optimization requires systematically identifying high-quality solutions under a limited evaluation budget, yet the unknown objective function provides little guidance for deciding where the search should explore next. We introduce SCOPE, a general framework for Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimization. Rather than directly optimizing the inaccessible objective, SCOPE learns a set of synthetic objectives conditioned on the accumulated search history, where each objective is designed to expose a distinct and potentially useful preference over candidate solutions. These objectives are then used to evolve search policies that generate diverse candidates, whose true quality is subsequently assessed through black-box evaluations. The outer loop adaptively updates and selects synthetic objectives according to how effectively their induced policies discover promising regions. In contrast, the inner loop returns a portfolio of top-performing policies to reduce the risk of relying on a single surrogate preference. This formulation reframes objective design as a mechanism for guiding policy exploration, enabling the search process to exploit observed evidence while maintaining structured diversity across discrete solution spaces. Extensive experiments across multiple benchmark problems demonstrate that SCOPE consistently improves black-box search performance under limited evaluation budgets and generalizes well across diverse combinatorial structures. ---