# Research Papers — 2026-07 · bundle page 54 of 222

> Full-text markdown of papers #2651–2700 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/54
[← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/53.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-07/page/55.md)

### XGRVFL-MV: Residual-Coupled Graph-Embedded Multi-View Random Vector Functional Link Network with FleXi Guardian Loss

Authors: Yogesh Kumar, Mudasir Ganaie
Published: 2026-07-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2607.23149v1

Random Vector Functional Link (RVFL) networks provide an efficient randomized learning framework for classification. Existing multi-view RVFL methods utilize complementary information from multiple views. However, preserving view-specific geometric structure, limiting the influence of large prediction residuals, and modeling relationships between multiple views remain challenging. This paper proposes a Residual-Coupled Graph-Embedded Multi-View RVFL model with fleXi guardian loss (XGRVFL-MV) for multi-view classification. The proposed model constructs RVFL representation for each view, incorporates graph embedding with intrinsic and penalty graphs constructed using the Local Fisher Discriminant Analysis weighting scheme. It also uses the bounded and asymmetric FleXi Guardian (XG) loss for residual learning. A residual-coupling term is introduced to encourage consistency among view-specific prediction residuals while preserving view-specific representations. The resulting optimization problem is solved using an inversion-free first-order optimization procedure based on Nesterov accelerated gradient descent. We evaluate the proposed model on UCI, KEEL, AwA, and Corel5k benchmark datasets. Experimental results, together with statistical analyses and hyperparameter sensitivity analyses, show that XGRVFL-MV achieves competitive classification performance compared with the baseline methods across the evaluated benchmark datasets.

---

### False Prophets: On the Security of World Models in Agentic Systems

Authors: Erik Imgrund, Anna Wimbauer, Klim Kireev, Konrad Rieck
Published: 2026-07-25
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2607.23147v1

Large language models now power autonomous agents capable of complex, multi-step tasks in different environments. Accurate and reliable execution of these tasks requires the agent to predict the results of its actions. Recent research proposes to enhance predictive capabilities via specially trained environment simulators-world models. While world models can improve performance, they can also mislead agents into executing harmful actions, creating significant security and privacy risks. In this paper, we raise security concerns regarding the usage of world models in agentic systems. We discover a range of world model specific vulnerabilities, which can be exploited in terminal-based agents to execute malicious code or extract sensitive data. To facilitate future development, we introduce a security benchmark dataset designed for text-based world models. We argue that some risks are intrinsic to approximate world modeling, and show that attackers can induce mispredictions in agentic pipelines with up to 95% success rate, possibly resulting in unintended command execution, denial of service, drainage of wallet and private information extraction. Finally, we provide practical recommendations for practitioners to mitigate the discovered harms and harden agentic systems.

---

### Foundation Models and Fine-Tuning: Toward a New Generation of Models for Time Series Forecasting

Authors: Morad Laglil, Bertrand Pracca, Emilie Devijver, Eric Gaussier
Published: 2026-07-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2607.23146v1

Inspired by recent breakthroughs in large language models for natural language processing, foundation models have emerged as a promising paradigm for zero-shot time series forecasting, enabling accurate predictions on datasets never seen during pre-training. Ranging from tens to hundreds of millions of parameters, these models are pre-trained on vast and diverse collections of time series, learning generalizable representations that support both point and probabilistic forecasting. This approach alleviates the need for dataset-specific model design and manual tuning, offering a unified solution across forecasting problems. In this work, we review the main architectures, pre-training strategies, and optimization methods underpinning these models. We further investigate post-pre-training fine-tuning of selected foundation models to enhance their performance on specific datasets. Our empirical results demonstrate that this step consistently improves forecasting accuracy over the zero-shot baseline.

---

### Interview with Kalle Lyytinen on "Implications of Theories of Language for Information Systems"

Authors: Kalle J. Lyytinen, Pierre Maier, Paul Ackah Toffey
Published: 2026-07-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2607.23142v1

Over fourty years after the initial publication of "Implications of Theories of Language for Information Systems" in MIS Quaterly, Lyytinen reflects about the origins of his publication and the developments in this area of research over the past decades. In the here presented interview, Lyytinen discusses the linguistic core of information systems also in light of recent trends and developments in the field, especially with regards to large language models and generative AI. Future research directions following a linguistic perspective on Information Systems (IS) research are outlined.

---

### Diffusion-Guided Search via Exponential Tilting (DiffTilt): An Application to Falsification of Safety-Critical Systems

Authors: Tanmay Khandait, Preetom Biswas, Hideki Okamoto, Bardh Hoxha, Georgios Fainekos, Giulia Pedrielli
Published: 2026-07-25
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2607.23134v1

Discovering rare safety-critical failures in autonomous and cyber-physical systems is a fundamental challenge in verification and validation. Existing falsification approaches rely on conditional sampling strategies that factor the joint distribution over environments and system executions, and therefore suffer from multiplicative rarity effects: the simultaneous scarcity of failure-inducing inputs and failure-inducing traces makes exhaustive search prohibitively expensive. This paper develops DiffTilt, a distributional framework that exponentially tilts a diffusion model-induced joint distribution over environments and executions. We show that diffusion-guided sampling admits an exact interpretation as importance sampling in the joint space, where guidance scores induce a KL-optimal reallocation of probability mass towards failure-relevant behaviors. We further show that tilting provably amplifies failure probability and strictly outperforms conditional sampling, which is limited by multiplicative rarity. In this framework, the joint generative model serves as a reusable prior over scenarios and need not faithfully represent the system under test. Expensive system simulations are instead limited to learning a scoring function that characterizes scenario quality, enabling their selective and adaptive use. We study DiffTilt on ARCH-COMP benchmarks, and we propose an additional tractor-trailer benchmark showing the behavior of several approaches when scenario generation is guided by a well-defined specification rather than a reward. The proposed method achieves competitive or improved falsification performance compared to state-of-the-art approaches, with larger gains when specification definition is not limited to STL formulas.

---

### DispatchRAG: Grounding Emergency Dispatch Decisions in Real-World Protocols from Traffic Accident Video

Authors: Muhammad Sulthan Adhipradhana, Ehsan Javanmardi, Naren Bao, Manabu Tsukada
Published: 2026-07-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2607.23132v1

Assessing the severity of a traffic accident scenario is important to decide which emergency service to dispatch. Missing an ambulance dispatch on a pedestrian accident is a fatal issue that can lead to death. Recently, Vision-Language Models (VLMs) have been a promising tool for accident reasoning, yet many VLMs are not grounded in real-life accident response protocols, making them not usable in accident severity assessment off-the-shelf. We introduced DispatchRAG, an accident assessor and dispatcher framework grounded in real-life Japanese traffic-accident response protocols, designed to enhance VLMs to generate an appropriate emergency response during an emergency scenario. Utilizing a RAG-based retrieval mechanism to retrieve the most relevant accident protocol and an LLM-powered reasoner to suggest the most proper response. To support evaluation, we introduce Accident Dispatch Dataset, a comprehensive dataset of accident assessment and emergency response according to Japanese accident response protocols adapted from the MM-AU dataset. We validate our framework on the Accident Dispatch Dataset, showing strong performance across various accident scenarios compared to the baseline VLM, pointing toward integration in autonomous vehicles that can automatically report both their own and nearby accidents.

---

### Identification and Honest Recovery from Semantic Observation Kernels: Operator Error, Coarsening, and Stability

Authors: Matthew Francis Dixon
Published: 2026-07-25
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2607.23130v2

Probabilistic text generators, such as large language models, assign probabilities to phrases, but consequential decisions require posterior uncertainty over meaningful states. These are not interchangeable: language probabilities depend on the prompt, may be incomplete and need not reliably identify state uncertainty. Without a statistical bridge, fluent responses and numerical confidence are insufficient for inference or governance. We formulate recovery of the target posterior as a semiparametric inverse problem and develop honest recovery guarantees that account jointly for calibration error, measurement noise, incomplete probabilities and weak identification. Simulations demonstrate the predicted coverage and stability behaviour, while two frozen language-model studies demonstrate held-out recovery. The resulting method determines when a semantic measurement can be trusted for inference and when use, review, recalibration or abstention is warranted, providing a statistical foundation for runtime AI governance.

---

### Identification and Learning of Semantic Observation Kernels: Partial Observation, Uniform Recovery, & Minimax Limits

Authors: Matthew Francis Dixon
Published: 2026-07-25
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2607.23130v1

Probabilistic text generators supply conditional distributions over tokens and complete verbal continuations, whereas scientific use often requires a posterior over a finite state. Large language models are the leading example: phrase probabilities depend on prompt wording, and model-printed percentages are generated text rather than state posteriors. More generally, we ask when an observable language law can support a reproducible posterior over declared states. A semantic map groups meaning-equivalent continuations; held-out cases with reference posteriors identify a semiparametric inverse from grouped language probabilities to state probabilities. The language law remains nonparametric and no hidden model quantity is used. This is principally a theory and methods paper and makes several contributions. On the theoretical side, we derive conditions for existence, identification, stable recovery, and sequential updating; concentration, asymptotic, and nonparametric rates; identified sets under truncated probabilities; and a minimax boundary for uniform stability. On the empirical side, theorem- directed simulations verify recovery rates, compatible-set coverage, and stability gates, while two frozen language-model studies illustrate held-out recovery and conformal coverage. The results specify when observable language probabilities can provide an auditable state measurement without being interpreted as internal belief.

---

### Vibe to Code: Elucidating Strategic Oscillation of Tacit Knowledge in Generative AI Design Workflows -- An Exploratory Qualitative Study

Authors: Daisaku Sato
Published: 2026-07-25
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2607.23126v2

The rapid adoption of generative AI tools has created new literacy demands for designers who must verbalize tacit knowledge through natural language prompts. Yet the micro-level cognitive processes by which designers externalize implicit intentions during iterative AI dialogue remain underexplored. This exploratory qualitative study examined five expert designers (11-20 years UI/UX experience, M = 15.4 years) using think-aloud protocols. We identified "Strategic Oscillation" -- experts' intentional return to vague language (Vibe) after progressing toward operational specifications (Code), leveraging AI's probabilistic nature for creative exploration. We observed shifts from "instruction" to "consultation" mode, deep reflection triggered by semantic collisions, and one participant's disengagement revealing conceptual alignment as a tentative boundary condition. We propose the ECRT cycle (Expectation-Collision-Reflection-Transformation) operationalizing the SECI model's "externalization" phase for human-AI collaboration. These findings yield three design patterns for metacognitive support and position AI as a "probabilistic mirror" catalyzing tacit knowledge externalization.

---

### From Vibe to Code -- and Back: Lexical Oscillation in the Formation of Design Intent with Generative AI

Authors: Daisaku Sato
Published: 2026-07-25
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2607.23126v1

Generative AI design tools make natural-language prompts a starting point for design, placing new articulation demands on designers. Rather than treating prompts as the transmission of pre-existing design intent, we ask how design intent is formed through situated interaction with AI. Five expert UI/UX designers (11-20 years' experience, M = 15.4) designed landing-page hero sections with a generative AI tool, recorded through think-aloud and retrospective interviews. Using reflexive thematic analysis, we used lexical granularity (L1 vibe, L2 design-domain, L3 operational language) as a sensitizing lens. Rather than moving from vibe to code unidirectionally, designers showed lexical oscillation, including returns from operational specificity to ambiguity. Mismatches with AI outputs were taken up as occasions for designers to reconsider what they meant, and engagement shifted from instruction to consultation. One non-oscillating trajectory -- a negative case -- suggested conceptual misalignment as a tentative boundary for future examination. We position AI as a non-neutral generative interlocutor and ambiguity as a resource for design judgment.

---

### Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation

Authors: Shuai Wang, Daoan Zhang, Zhe Tang, Hao Cheng, Jiaheng Wei
Published: 2026-07-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2607.23125v2

Post-training enables vision-language models (VLMs) to understand human instructions and perform various downstream tasks. Current post-training methods usually rely on human-annotated data, distillation from external models, reinforcement learning with human feedback, or verifiable answers. This limits their ability to improve without external supervision. To tackle this, we propose NOPD (Noisy Student On-Policy Self-Distillation), a simple yet effective self-distillation approach that improves VLMs without any external models or ground-truth answers. Our key insight is that prediction discrepancies between clean and corrupted inputs naturally induce a self-supervision signal. In NOPD, the model learns from corrupted inputs while using its own predictions under clean inputs as token-level supervision. We show the effectiveness of NOPD on five visual reasoning tasks; it can match and even outperform reinforcement learning approaches or distillation from external models. Notably, when trained with 2.1K samples from Geometry3K, NOPD improves Qwen2.5-VL-7B by 20 points on its validation set. It also shows generalization on out-of-distribution test sets and achieves 7.4 point gains on MathVista. Furthermore, we demonstrate that NOPD is a general approach to enhance VLMs, achieving improvements across three models on 12 benchmarks.

---

### AgentOmnia: Scaling Agentic Models for Full-Scenario Applications

Authors: Hao Jiang, Gangtao Xin, Yingdi Huang, Guojie Zhu, Jiangshan Zhang, Xinyuan Lin, Yunkun Xu, Chengyu Shen, Wenlong Fei, Jiawei Li, Yujie Fu, Sichen Kang et al.
Published: 2026-07-25
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2607.23124v1

Large language model agents have advanced rapidly, yet progress remains fragmented across domains, capabilities, task difficulty, and interaction settings. We frame this as full-scenario agentic scaling and present AgentOmnia, a framework coordinating task-space definition, data synthesis, post-training, evaluation, and improvement across To-Consumer (ToC), To-Business (ToB), and To-Employee (ToE) applications. An extensible Domain x Capability x Atomic Difficulty taxonomy aligns these stages and enables fine-grained diagnosis with OmniaBench. AgentOmnia combines bidirectional environment-task synthesis with tool-dependency, program-structured, and solver-based pipelines, constructing 5,018 stateful environments with 255,375 tools and 52,361 tasks. Programs, solvers, and verifiers provide correctness signals, while supervised fine-tuning, online agentic reinforcement learning, and a rollback curriculum support post-training. Evaluation failures translate into Product Requirement Documents (PRDs) for targeted self-evolution. Starting from Qwen3-30B-A3B-Thinking-2507, AgentOmnia raises the pass rate on the OmniaBench challenging subset from 9.16% to 37.11% and the macro-average across OmniaBench, $τ^2$-Bench, DeepPlanning, and VitaBench from 22.86% to 41.69%. Under a unified protocol,it leads the evaluated agentic post-trained baselines on OmniaBench and retains the highest four-benchmark macro-average. It also surpasses Qwen3-235B-A22B-Thinking-2507 on all four benchmarks and exceeds Qwen3.5-35B-A3B on the macro-average. Gains span three application splits, ten capability dimensions, eight atomic-difficulty factors, and 76 of 90 level-1 domains, indicating broad rather than category-specific improvement. A one-round study provides initial evidence for PRD-guided self-evolution, motivating validation at larger scales and in industrial settings.

---

### SQBench: A Benchmark for Evaluating Task Delivery by Language-Model Agents in Production-Oriented Workflows

Authors: Summer Sun
Published: 2026-07-25
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.23123v1

Existing evaluations of large language models cover knowledge, reasoning, coding, and tool use, but they rarely treat a verifiable deliverable produced within a constrained workflow as the unit of evaluation. We introduce SQBench, a benchmark for evaluating production-oriented task delivery by language-model agents. SQBench v1.0 contains 220 standardized tasks organized into L1 atomic capabilities, L2 composite skills, and L3 business scenarios. Each task requires an agent to process input assets, use available tools, and produce an explicitly specified deliverable. The evaluation first computes functional Completion and then derives Risk Penalty and Performance from independently evidenced triggers in a 10D Risk Matrix. A Strict Pass requires Completion = 1 and Risk Penalty = 0. We evaluate 27 model configurations under a common protocol, with one run per configuration-task pair. The highest prespecified Weighted Pass@1 is 60.5%. Mean Strict Pass@1 on L3 is 18.5%, and every configuration performs worse on L3 than on both L1 and L2, indicating that delivery under domain constraints is a shared weakness within the current task set. Of 2,348 results with Completion = 1, 113 (4.8%) fail the Strict Pass criterion because of risks such as unverifiable citations, inappropriate resource use, or format violations. These results show that functional completion alone does not fully characterize delivery quality and that risk determinations should be reported separately.

---

### Occlusion-Point Reuse for Ray-Traced Ambient Occlusion and Shadow

Authors: Haojie Jin, Fujia Su, Zehui Lin, Chenxiao Hu, Jierui Ren, Yuqing Yuan, Yanchen Zhang, Zhongtao Wang, Yisong Chen, Kangying Cai, Guoping Wang, Sheng Li
Published: 2026-07-25
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2607.23122v1

Ambient occlusion (AO) and soft shadows are critical visibility cues for spatial perception in real-time rendering. Hardware ray tracing provides a direct way to evaluate these effects, enabling ray-traced AO and area-light shadows that avoid many limitations of screen-space AO and shadow mapping. However, real-time budgets allow only a few rays per pixel, leaving raw ray-traced estimates noisy and expensive. We present an occlusion-point reuse framework that reuses traced samples in the domain of first-hit occlusion points instead of directly reusing final shading values or light samples. This provides a ray-reuse formulation for AO, rather than merely filtering or reusing completed AO values. The key idea is to transform AO and area-light shadow estimators into occluder-domain integrals, then combine neighboring occluder samples with a multiple-importance-sampling (MIS) formulation. For both AO and shadows, we derive unbiased estimators that validate convergence to the transformed integrals, as well as biased estimators designed for practical real-time execution. The biased variants assume local first-hit occluder consistency; for shadows, this occluder-based assumption better matches local visibility geometry than the visibility-consistency assumption commonly used when reusing light samples. Experiments show higher AO and shadow quality than non-reuse ray-traced baselines, and better shadow quality than light-sample reuse at comparable cost.

---

### SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads

Authors: Congfei Zhang, Jingxiao Ma, Xiaodong Liu, Hsiang-wei Chao, Siman Wang, Ge Liu, Shantanu Aggarwal, Vincent Zhang, Meghana Missula, Rachel Liao, Zichu Li, Xiao Bai et al.
Published: 2026-07-25
Categories: cs.IR, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2607.23121v1

Dynamic Product Ads (DPA) require retrieving relevant items from multi-million product catalogs, balancing two competing objectives: retargeting (re-surfacing known interests) and prospecting (discovering new categories). While Large Language Models (LLMs) capture semantic intent better than traditional embedding models, deploying them at scale introduces prohibitive inference costs and lexical mismatch issues. Through controlled experiments on millions of users, we demonstrate a critical retrieval decomposition: rule-generated queries excel at retargeting on a lexical BM25 index, while LLM-generated queries excel at prospecting on a dense ANN index. Building on this, we propose SMART (SeMantic-aware Adaptive ReTrieval). To manage costs, a lightweight quality gate identifies coverage gaps in initial keyword results, adaptively routing only the ~10% of users who benefit from semantic prospecting to the LLM path. Offline evaluation demonstrates that this gated approach captures the bulk of semantic prospecting gains in Relevance Score while maintaining competitive re-targeting performance at a 90% reduction in LLM costs. Finally, in a 2-week online A/B test at Snap, SMART improved the ad conversion rate by +27.6% over a strong embedding-based baseline.

---

### A scalable online machine learning approach for Stock Recommendation

Authors: Harsh Nagarkar
Published: 2026-07-25
Categories: cs.CE, cs.AI, cs.DC, cs.GT
arXiv: https://arxiv.org/abs/2607.23120v1

Stock recommendation systems face the dual challenge of adapting to rapidly changing market conditions while maintaining low-latency predictions for end users. Traditional batch-trained models fail to capture concept drift, and monolithic architectures struggle to provide fault tolerance under load. This paper presents a scalable online deep learning-based stock recommendation system built on a distributed microservices architecture using Kubernetes, Docker, and RabbitMQ. The system employs a hybrid leader-follower architecture where a primary model continuously trains on streaming financial data, including EPS, MACD, and price, from the Alpha Vantage API while multiple replica models serve user-facing recommendations in parallel. A multilayer perceptron implemented with TensorFlow Recommenders generates content-based recommendations using explicit user ratings (1-5) and transfer learning. The architecture ensures high availability. The leader persists model weights to Google Cloud Object Storage, allowing replicas to recover seamlessly upon failure, while RabbitMQ provides message durability and replay. Results demonstrate that the system serves stock recommendations in 23 seconds per request and processes up to 500 portfolio addition requests per second per follower. Key limitations include data staleness (up to 150 minutes due to API rate limits) and the absence of a service mesh for inter-cluster security. This work contributes a production-ready reference architecture for online recommender systems that balances consistency, availability, and scalability in a financial domain context

---

### KAYROS: An Anytime and Exact Open-Source Solver for Duration-Minimization Time-Dependent Vehicle Routing. A Technical Report and a Case Study in Human-AI Engineering

Authors: Florian Rascoussier
Published: 2026-07-25
Categories: math.OC, cs.AI, cs.MS
arXiv: https://arxiv.org/abs/2607.23116v2

Time-dependent routing recognizes that the same journey can take a different time depending on when it begins. Under duration minimization, even the departure time of each vehicle becomes a decision. Exact methods for this setting exist in the literature, but researchers and practitioners have lacked a ready-to-use open solver that combines rich piecewise-linear travel times, early feasible solutions and optimality claims. KAYROS fills this gap with two modes on one checker-consistent engine: an Iterated Local Search that streams improving solutions and a Branch-Price-and-Cut method that can issue computational optimality certificates under explicit arithmetic and search assumptions. It installs with one command and has no proprietary dependency. The public MAMUT-routing store currently contains 704 KAYROS certificates under a four-solve publication protocol, which has also led to the retraction and repair of invalid earlier claims. The report presents two complementary benchmark contributions to MAMUT-routing. The first integrates Blauth2024, a benchmark from the literature whose travel times derive from measured Uber speeds, for which KAYROS provides new best-known solutions on all 40 instances. The second proposes Poryos2026, a new benchmark of 1,080 paired static and time-dependent instances built from OpenStreetMap road networks and controlled synthetic traffic. Finally, the report describes the intensive human-AI collaboration behind this work and the verification practices that kept its outputs independently verifiable.

---

### KAYROS: An Anytime and Exact Open-Source Solver for Duration-Minimization Time-Dependent Vehicle Routing. A Technical Report and a Case Study in Human-AI Engineering

Authors: Florian Rascoussier
Published: 2026-07-25
Categories: math.OC, cs.AI, cs.MS
arXiv: https://arxiv.org/abs/2607.23116v1

KAYROS is an open-source solver for duration-minimization time-dependent vehicle routing problems, with or without time windows (TDVRPTW, TDVRP). In these variants, travel times change with departure time, and each route's dispatch time is a decision. To the best of the author's knowledge, it is the first openly available solver that is both anytime, streaming improving solutions from the first seconds, and exact, proving optimality with publicly verifiable certificates, for these problems over rich piecewise-linear travel- time functions rather than a time discretization. It has no proprietary dependency and installs with one command. It builds on the state of the art for time-dependent function composition and exact solving, extending the open-source branch-price-and-cut solver of Lera-Romero, Miranda Bront and Soulignac (2020) with an open LP backend, anytime and warm- start behavior, checker-exact pricing, and exact treatment of stepwise travel times. On the MAMUT-routing benchmark collection, KAYROS stands behind 468 published optimality certificates, each requiring agreement among four independent solves, and five certificates strictly improve published reference values. The report also introduces Poryos2026, a benchmark family designed and generated by the author from real OpenStreetMap city road networks. Its 1,080 paired CVRP, VRPTW, TDVRP and TDVRPTW instances combine real road geometries with controlled synthetic demands, time windows and congestion. Every instance carries a checker-validated best-known solution. This report presents the solver, its certification protocol, the benchmark's generation and feasibility guarantees, and their experimental connection for a broad technical audience. It is also a case study in the intensive human-AI collaboration that made this body of work feasible while keeping its claims independently verifiable.

---

### Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs

Authors: Zhihao Xu, Hao Zhong, Zeting Zhou, Yuhang Xu, Haoyu Tong, Wei Wang, Jinshan Chen, Keqiang He, Chong Zhu, Shengzhong Liu, Fan Wu, Guihai Chen
Published: 2026-07-25
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2607.23115v1

This paper aims to enable computation- and communication-efficient GPU sharing across devices within local area networks (LANs), facilitating ubiquitous AI inference on heterogeneous personal devices. We achieve distributed task offloading via CUDA API remoting. However, beyond raw computation, network constraints emerge as the primary bottleneck: limited bandwidth, high-frequency API invocations, and cross-task contention significantly hinder performance. To address these challenges, we propose Gleam, a novel and network-efficient framework for task-generic GPU sharing across local-area CUDA devices, with three key contributions. First, we reduce bandwidth overhead in CUDA API remoting through automatic model weight caching, and mitigate accumulated latency from frequent API calls by asynchronous execution. Second, we design a runtime task scheduler that dynamically determines API remoting pairs between LAN clients and servers, explicitly accounting for both network conditions and GPU resource contention under parallel workloads. Finally, we introduce dedicated mechanisms to ensure CUDA context consistency across distributed executions. Extensive experiments on heterogeneous NVIDIA GPUs and diverse AI workloads show Gleam consistently outperforms state-of-the-art baselines, achieving 1.4-24.2 times improvements in API remoting efficiency and up to 1.79 times higher system throughput.

---

### Operator Neural Jump ODEs: $L^2$-optimal prediction in function spaces

Authors: Florian Krach, Oliver Löthgren, Josef Teichmann
Published: 2026-07-25
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2607.23110v1

In this paper, we study the extension of Neural Jump ODEs to infinite-dimensional function spaces. In particular, the underlying process $X$ now takes values in $L^2(Ξ, \mathbb{R}^{d_X})$ instead of $\mathbb{R}^{d_X}$ and the Operator NJ-ODE approximates the optimal predictor of this process by producing a representative of the conditional expectation. The NJ-ODE model is a framework for online learning the optimal prediction of continuous-time stochastic processes, given discrete, possibly irregular and incomplete past observations. In a series of works, this model has been extended to deal with generic path-dependent processes, with observation noise and dependent observations, with long-term predictions, and with input-output systems. However, throughout all of these works, the underlying processes were restricted to be finite-dimensional. In particular, function-valued problems, like yield curve or volatility surface predictions, could only be handled through discretization, which inherently leads to a loss of information. In this work, we build on ideas from Neural Operator methods that allow us to extend the NJ-ODE framework to an infinite-dimensional output process. To prove convergence of the NJ-ODE to the optimal prediction process, we develop a new approximation strategy that also generalizes previous works in the finite-dimensional setting by considerably weakening the assumptions.

---

### SHReg: Strictly Rotation-Equivariant Point Cloud Registration via Spherical Harmonics

Authors: Chongjian Wang, Junjie Gao
Published: 2026-07-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2607.23096v1

Point cloud registration critically depends on local features that are both distinctive and robust to arbitrary 3D rotations. Existing learning-based methods typically approximate rotation invariance via fragile local reference frames or extensive data augmentation, providing only empirical invariance and often degrading under unseen rotational transformations. In this paper, we propose SHReg, a strictly rotation-equivariant point cloud registration framework grounded in the representation theory of $SO(3)$. By representing local geometric features as irreducible representations of $SO(3)$, SHReg guarantees exact equivariance under arbitrary rotations without relying on local reference frames. Built upon a spherical-harmonics-based equivariant backbone, SHReg jointly learns rotation-invariant descriptors for robust correspondence matching and rotation-equivariant features that preserve fine-grained orientation information. The preserved equivariant structure enables each correspondence to directly hypothesize a rigid transformation, reducing reliance on large-scale hypothesis sampling in conventional RANSAC-based pipelines and leading to improved robustness under challenging rotational variations. Extensive experiments on 3DMatch, 3DLoMatch, and KITTI demonstrate that SHReg consistently outperforms state-of-the-art methods in registration accuracy, particularly under large rotational perturbations.

---

### Compiler-Grounded Hierarchical Diagnosis for LLM-Based Triton Kernel Optimization

Authors: Dongjie Chen, Ping Zhao, Bohua Zhan, Yulong Wang, Shushu Chen, Liangjun Feng, Hao Zhou, Min Shen, Linmu Wang, Weijia Sheng, Xiangyu Wei, Weijie Ding et al.
Published: 2026-07-25
Categories: cs.AI, cs.PL
arXiv: https://arxiv.org/abs/2607.23089v1

Recent advances in large language models (LLMs) have enabled automated kernel generation and optimization, but most existing approaches rely on surface signals such as compilation feedback and profiling metrics. These signals reveal that a kernel is slow, but not why the backend compiler fails to realize a profitable optimization, especially on emerging accelerators such as NPUs. We therefore formulate kernel optimization as a progressive cross-layer diagnosis problem that links runtime symptoms to IR structure and compiler behavior before rewriting source. Based on this insight, we present our system, a compiler-grounded and hierarchical optimization framework for Triton kernels. the system escalates from lightweight pattern triage and profiling diagnosis to IR attribution and compiler-grounded analysis only when deeper evidence is needed, then proposes evidence-backed source-level rewrites. We implement the system on Triton for Ascend NPUs and evaluate it on 37 successfully converted entries from a standardized NPUKernelBench-derived Ascend 950 benchmark. Across these entries, the system attains a geometric-mean speedup of 4.35$\times$ and a median speedup of 2.73$\times$ from the initial to optimized Triton kernel; 22/37 exceed 2$\times$ and 13/37 exceed 5$\times$. The complete distribution ranges from near-baseline entries to large wins, motivating transparent reporting of the current system's scope and limitations.

---

### Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios

Authors: Lixun Ma, Ruolong Ma, Bei Wang, Feng Wei, Zhenguang Liu, Lorenzo Cavallaro, Wentao Chen
Published: 2026-07-25
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2607.23088v1

Large Language Models (LLMs) are widely used for code generation, yet their security behavior in realistic development workflows remains underexplored. Existing benchmarks often rely on explicitly specified security requirements, failing to capture real-world scenarios where prompts are frequently ambiguous or incomplete. In this paper, we adopt a developer-centric perspective and identify three representative risk scenarios that commonly lead to security vulnerabilities in LLM-generated code: Ambiguous Requirements, Under-Specified Operational Context, and Security--Functionality Conflict. Based on these scenarios, we construct a large-scale benchmark comprising 2,700 test cases, enabling fine-grained evaluation of LLM security under realistic conditions. Extensive evaluation of eight state-of-the-art LLMs reveals that all models exhibit average vulnerability rates exceeding 56\% across risk scenarios. We further demonstrate that security-aware prompting can substantially mitigate these risks, achieving up to 45\% improvement.

---

### LoRA for Gender-Inclusive Rewriting and Activation Steering for Counter-Narrative Generation

Authors: Akhil Rajeev P, Manoj Balaji J
Published: 2026-07-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2607.23083v1

Gender-inclusive language generation seeks to transform biased text into inclusive alternatives while preserving semantic meaning and contextual coherence. This paper presents the IHLC system for the LT-EDI 2026 Shared Task, addressing both gender-inclusive rewriting and counter-narrative generation. For gender-inclusive rewriting, we employ parameter-efficient Low-Rank Adaptation (LoRA) fine-tuning, achieving an official score of 80.00%. Our primary contribution is a compute-efficient inference-time representation engineering approach for counter-narrative generation. We derive a principal steering direction from contrastive hidden-state activations using principal component analysis (PCA) and inject it into the intermediate representations of Gemma-3-4B-it during inference, enabling behavioral steering toward inclusive responses without modifying model weights. Combined with constrained prompting, this approach produces polite and contextually appropriate counter-narratives, achieving an official score of 78.12%. We further present a manual analysis of steering behavior, identifying key failure modes including semantic drift, residual bias leakage, layer sensitivity, over-steering, and text degeneration. Our findings highlight both the practical potential and current limitations of activation steering as a lightweight alternative to parameter updates for controllable and socially aligned language generation.

---

### Scoping Review of AI, Metrology, and ESG in the Semiconductor Sector: Implications for Safe and Sustainable by Design (SSbD)

Authors: Karen Ang, Han-Teng Liao
Published: 2026-07-25
Categories: cs.SI, cs.AI, cs.CY, eess.SY
arXiv: https://arxiv.org/abs/2607.23082v1

The semiconductor sector faces a dual transition: scaling manufacturing execution through Artificial Intelligence (AI) while satisfying stringent sustainability mandates, such as the EU Carbon Border Adjustment Mechanism (CBAM). This paper presents a scoping review of 1,465 documents indexed in Web of Science and Scopus, spanning AI-integrated metrology, supply chain ESG, and federated industrial data spaces. Network analysis reveals a highly fragmented "core-periphery" knowledge structure, emphasizing a critical structural hole between AI-driven process optimization and downstream sustainability governance. To close these gaps, this study proposes a 6-layer Safe and Sustainable by Design (SSbD) architecture grounded in a System of Systems (SoS) paradigm. By establishing distinct "grid-to-core" and "standards-through-supply-chain" integration pathways, the proposed framework demonstrates how virtual metrology (VM), localized federated learning, and defensive RegTech mechanisms can build provenance-aware data fabrics. Ultimately, this architecture positions regulatory compliance as a driver for innovation, enabling secure, climate-neutral, and circular value chains in semiconductor manufacturing.

---

### Inverse Bayesian Inference for Extracting Lesion Dynamics from Longitudinal Spectral CT

Authors: Lukas Förner, Melina Wördehoff, Julian Steffens, Maximilian Schmutz, Rainer Claus, Josua Decker, Thomas Kröncke, Kartikay Tehlan, Thomas Wendler
Published: 2026-07-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2607.23078v1

Longitudinal medical imaging captures temporal evolution of lesions, yet extracting the underlying dynamical parameters governing this evolution remains challenging. We propose an inverse Bayesian framework for inferring lesion dynamics from longitudinal spectral CT. We decompose spectral feature ($x$) evolution into three components: \begin{equation*} \frac{dx_i}{dt} = A_i x_i + B \cdot n + C \cdot Δx_{\text{sat}} \end{equation*} where $A_i$ captures intrinsic dynamics (lesion-autonomous evolution), $B$ captures local environment tumour burden (organ tumour burden through satellite count coupling), and $C$ captures environment/satellite state change (i.e., whether surrounding lesions move similarly or not). We demonstrate the framework on photon-counting NSCLC CT data from metastases, recovering distinct dynamical regimes: lung lesions exhibit significant satellite count coupling ($B=-0.34$, $p<0.05$) suggesting competitive dynamics, while liver lesions show synergistic satellite behaviour coupling ($C\approx+1.0$, $p<0.05$). Synthetic validation confirms parameter recovery, and cross-coupling analysis validates that our method detects non-zero coupling when present. This work establishes inverse dynamical inference as a principled methodology for extracting interpretable parameters from longitudinal imaging, moving beyond static feature extraction toward mechanistic characterisation of lesion behaviour. The code and data are available at: https://github.com/lukasf98/inverse-bayesian-inference

---

### Structure over Depth: A Single-Block Spatio-Temporal Transformer for Multi-Entity Reasoning

Authors: Narthana Sivalingam, Santhirarajah Sivasthigan, Buddhi Wijenayake, Roshan Godaliyadda, Vijitha Herath, Parakrama Ekanayake
Published: 2026-07-25
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.23077v1

Modeling multi-entity temporal data requires capturing dependencies across entities, time, and their interactions. Transformer-based approaches perform well but often rely on deep stacks of layers to learn these heterogeneous dependencies implicitly, increasing computational cost. We revisit this problem from a structural perspective and decompose multi-entity temporal dynamics into three interaction types: spatial interactions among entities, temporal interactions across time, and cross interactions coupling the two domains. We propose a structured spatio-temporal transformer block that explicitly models all three within a single stage. It uses parallel spatial and temporal self-attention, followed by bidirectional cross-attention, and combines the outputs through learnable gated fusion. By directly encoding these complementary views, the model reduces the need for deep stacking. We evaluate the approach on video-based group activity recognition, skeleton-based human interaction analysis, and wearable sensor-based activity recognition. Despite its simplicity, the single structured Transformer block matches or outperforms deeper architectures with only 1.76M parameters. The results suggest that depth in prior models partly compensates for implicit and entangled interaction modeling, whereas explicit factorization offers a more efficient and transparent alternative. More broadly, this work supports a structure-first design principle: expressive multi-entity temporal reasoning can emerge by exposing interaction structure rather than relying on depth.

---

### Traceable LLM Reasoning for Fake-Order Fraud Detection

Authors: Siqi You, Bingsong Xu, Zhixian Zheng, Xinjian Peng, Yang Xie, Ying Wang, Jiarong Xu
Published: 2026-07-25
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2607.23075v1

Detecting fake-order fraud at scale remains a critical challenge for large online-to-offline (O2O) service platforms, as existing approaches often rely on expert-designed features, produce black-box decisions, and provide limited interpretability. To address these limitations, we propose DeepScrub, a reinforcement learning framework built upon large language models (LLMs) for fake-order fraud detection with traceable reasoning. DeepScrub introduces three innovations. First, a semantic unification module converts heterogeneous risk signals into textual descriptions that LLMs can understand. Second, continued pre-training on risk-control corpora injects domain knowledge, and task rewards jointly evaluate prediction correctness and reasoning quality. Third, the SUggest-REflect (SURE) mechanism incorporates expert feedback and model self-checking to iteratively refine reasoning paths. On a real-world fake-order fraud detection dataset, DeepScrub achieves a macro-F1 score of 85.3%, outperforming the best baseline by 2.7 percentage points. Our task-optimized 8B model further surpasses a 32B model, showing that domain adaptation can matter more than model scale in this setting. In a four-week live pilot, DeepScrub achieved 91.8% precision and 88.5% recall, improving over first-stage human reviewers by 16.6 and 38.8 percentage points. It reduced first-stage manual review workload by 94% and saved nearly one million RMB annually. These results show that DeepScrub improves fraud review accuracy, reduces first-stage review workload, and provides traceable evidence for production risk-review workflows.

---

### DishSeg24k: A Large-Scale Benchmark for Food Segmentation with Stochastic Expert Decoding

Authors: Yilin Wang, Haochen Shi, Guanyu Chen, Weiqing Min, Jinkai Zheng, Chenggang Yan, Shuqiang Jiang
Published: 2026-07-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2607.23070v2

Food segmentation is essential for applications such as intelligent catering, dietary assessment, and recommendation. However, existing benchmarks fail to capture the complexity of real-world dining scenes. The challenges of dense inter-dish overlap, fine-grained class similarity, and extreme long-tail class distributions exceed the fidelity of current datasets. To fill this gap, we introduce \textbf{DishSeg24k}, a large-scale dish-level segmentation benchmark with 24,096 images, 112,281 instances, and 278 fine-grained categories in real-world dining environments. Based on DishSeg24k, we further propose \textbf{Food Expert-Adaptive Segmentation Transformers (FEAST)} to address these challenges. FEAST models query-based decoding as a Markov Decision Process (MDP), where each decoder layer update is treated as a sequential decision step that explores uncertainty along dish boundaries. We further redesign the decoder with a reinforcement learning (RL)-guided Mixture-of-Experts (MoE) module, in which a dual-critic decoupled optimization scheme separates task-oriented query refinement from structure-aware expert routing. This design promotes expert specialization and prevents expert collapse under long-tail category distributions. Finally, extensive experiments on DishSeg24k demonstrate the state-of-the-art performance of FEAST, which outperforms previous methods by {+3.21\%} mIoU, {+3.68\%} mDice, and {+4.00\%} mAcc, respectively. We further validate the effectiveness of FEAST on FoodSeg103. The dataset and code will be publicly released.

---

### Neural Network-Driven Volatility Drag Mitigation under Aggressive Leverage

Authors: Christian Bongiorno, Efstratios Manolakis, Rosario Nunzio Mantegna
Published: 2026-07-25
Categories: q-fin.PM, cs.LG
arXiv: https://arxiv.org/abs/2607.23068v1

This paper introduces a compact reformulation of a modular end-to-end neural network for global minimum-variance portfolio optimization that decouples model complexity from both look-back window length and universe size. A five-parameter hyperbolic weighted moving average combined with a saturating exponential replaces the original 2,400-parameter lag-transformation layer, and a bidirectional gated-recurrent-unit eigencleaning module together with a streamlined marginal-volatility network reduce total learnable parameters from 39,586 to just 2,175. In out-of-sample tests against state-of-the-art nonlinear-shrinkage and risk-parity benchmarks, the compact network attains the lowest realized portfolio variance without compromising expected return. Under long-only constraints, the variance reduction supports substantially higher leverage while maintaining comparable drawdown control. Validation in a high-fidelity trading simulator that incorporates realistic margin-call dynamics confirms enhanced over-leverage resilience. These findings demonstrate that end-to-end variance-minimization architectures can achieve substantial parameter efficiency and robust capital-efficiency gains without sacrificing risk-adjusted performance.

---

### Attention-Guided Layer Selection for Contrastive Decoding in Large Language Models

Authors: Yusuke Sakai, Natthawut Kertkeidkachorn, Kiyoaki Shirai
Published: 2026-07-25
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2607.23067v1

Contrastive decoding methods such as DoLa improve the factuality of Large Language Models (LLMs) by contrasting the output distributions of mature and premature layers. However, DoLa's dynamic layer selection relies solely on divergences in output vocabulary distributions. In this work, we propose three attention-guided strategies: Attention-JSD, Attention-Entropy-Max, and Attention-Entropy-Min, which leverage structural information carried by internal self-attention mechanisms as a signal for layer selection. Experimental results on TruthfulQA demonstrate that our strategies, particularly Attention-JSD and Attention-Entropy-Min, consistently outperform the original DoLa. We observe significant gains on multi-answer metrics (MC2 and MC3), suggesting that attention distributions can provide a more sensitive signal for resolving factual knowledge than output vocabulary distributions.

---

### ADAGE: A Language-Agnostic Pipeline for Analogical Reasoning Evaluation

Authors: Ahmed Haj Ahmed, Alvin Grissom
Published: 2026-07-25
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2607.23058v1

Multilingual reasoning evaluation overwhelmingly relies on translating English benchmarks, a practice that introduces linguistic artifacts and fails to test culturally-grounded reasoning. We introduce ADAGE (Analogical Difficulty-by-design Assessment for Grounded Evaluation), a language-agnostic pipeline that combines native-speaker curation with LLM-assisted generation to construct challenging, translation-free benchmarks for abstract analogical reasoning. We validate ADAGE by constructing benchmarks for Arabic, Amharic, and Japanese. Evaluating 14 open-weight models, we find a consistent cultural reasoning gap: models that perform well on English proverb reasoning struggle substantially on all three native benchmarks, with accuracy dropping by 12--52 percentage points relative to English. We release the pipeline, all three benchmarks, and the full evaluation suite.

---

### SymStep: Symbolic Step Verification for Logical Reasoning

Authors: Aida Usmanova, Rui Gao, Dilshod Azizov, Ricardo Usbeck, Zangir Iklassov
Published: 2026-07-25
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.23055v1

Chain-of-thought (CoT) prompting can fail severely on constraint-dense logical reasoning tasks, where unverified errors accumulate silently across steps. We introduce SymStep: an LLM makes one atomic claim at a time (DEDUCE: Alice, pet, Cat), then a lightweight constraint propagator checks the claim for consistency with prior accepted deductions, rejects contradictions, and cascades implied facts automatically. SymStep+G additionally provides MRV guidance after each accepted step, directing the LLM toward the most constrained unresolved variable. On a 35-puzzle retained subset of ZebraLogicBench, a benchmark of 1,000 Einstein-style logic puzzles, Direct and CoT both achieve 0%, while SymStep+G reaches 97%. On AR-LSAT analytical reasoning problems, SymStep achieves 100% vs. CoT's 87%. On LGP-14, SymStep+G achieves 100% vs. 0% for CoT and Logic-LM, the strongest prior symbolic+LLM baseline we compare against. Ablation studies reveal that MRV guidance is a key mechanism for reducing directionless cycling, while consistency checking provides a safety net against explicit contradictions. Across six benchmarks spanning five task domains, SymStep variants match or exceed every baseline on constraint-dense and arithmetic tasks. Experiments on AQUA-RAT algebra confirm the advantage is constraint-density-specific.

---

### Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models

Authors: Dhruvil S, Fenil Sojitra, Ravirajsinh Chauhan
Published: 2026-07-25
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2607.23054v1

Multi-head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value pairs through a shared low-rank bottleneck (cKV), achieving 81% KV-cache reduction during inference. Despite its adoption in massive production models, no prior work has studied what information this bottleneck preserves or discards, nor how it reshapes internal transformer circuits. We present the first comprehensive mechanistic interpretability study of MLA, training a 114M-parameter transformer (pretrained on a web/code/math mixture, fine-tuned on TinyStories) and analyzing its representations through SVD, attention head taxonomy, linear probing, and a disruption-attribution analysis. Our key findings are: (1) the cKV bottleneck learns a pure content representation, preserving entity identity (98% retention) while discarding positional information, validating MLA's separation of content from position via RoPE; (2) induction heads co-locate at a single layer (Layer 12), unlike their distributed formation in standard MHA; (3) a single "semantic hub" layer (Layer 15) simultaneously exhibits the highest SVD effective rank and strongest disruption-attribution score; and (4) the bottleneck is globally over-provisioned, using only 46% of its capacity on average. These findings suggest MLA does not merely compress attention passively, but reshapes how the model organizes content, position, and circuit structure. We view this as an initial data point and detail scope limitations in Section 5.

---

### Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models

Authors: Sultan Alshehri, Zhantao Yang, Han Zhang, Marios Savvides
Published: 2026-07-25
Categories: cs.CV, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2607.23052v1

Dual-encoder vision-language models (VLMs) expose a similarity interface that enables zero-shot retrieval but fails compositional constraints: queries like "umbrella and no person" retrieve images containing both, even when concept detection is reliable. We trace this to an interface-level Bag-of-Concepts effect, where similarity scores approximate mean pooling of concept evidence regardless of operators. Although operator-dependent signals exist in text embeddings, they are too weak or misaligned to affect rankings. Fine-tuning does not reliably resolve this failure because the dominant bottleneck is how similarity aggregates evidence rather than what encoders represent. We propose factored inference, which separates evidence extraction from constraint execution, and introduce LCSE (Logic-Constrained Score Editing), a training-free method that executes constraints externally using concept scores from frozen encoders. We also introduce FACTOR-Bench, where LCSE achieves 85.5% accuracy versus 73.2% for the best fine-tuned baseline, 90.7% when applied to SigLIP 2, and improves NegBench COCO MCQ accuracy from 27.2% to 65.2% while preserving retrieval performance.

---

### The Entropic Bound for Transformers: Why Static Rank Fails and Attention-Native Rank Recovers

Authors: Byeong Hoon Yoon
Published: 2026-07-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2607.23050v1

Neural scaling laws describe how loss decreases as models, data, and compute grow, but they do not answer a prior question: for a fixed task, what is the minimum model capacity required to solve it? We study this through the Entropic Bound, a spectral notion of task-intrinsic capacity for Transformers. We first prove that, in a linear attention surrogate, the intrinsic rank $r^*$ of the token-mixing operator is a tight lower bound: any rank-deficient model incurs unavoidable excess risk, and the bound is achievable at $r^*$. We further show that gradient descent recovers this rank under standard low-rank implicit-bias assumptions, confirm all three properties empirically, and show $r^*$ is recoverable from data before training. We then ask whether this transfers to real attention. A naive transfer fails, and a controlled interpolation ladder localizes the cause precisely: it is not softmax and not a rank constraint, but the input-conditioned nature of attention's mixing operator, which a static weight kernel cannot summarize. Motivated by this, we introduce an attention-native intrinsic rank -- the minimum query-key kernel rank realizing the task within the attention class -- and show that under this definition the full Entropic Bound structure (deficiency, achievability, recovery) is restored for both linear and softmax attention, with the energy effective rank as the estimator robust to softmax distortion. Finally, we map the boundary of data-only predictability: $r^*$ is exactly recoverable for linear QK attention, even without the value map at scale, while softmax attention admits only partial pre-training recovery due to nonlinear inversion and kernel-value identifiability effects. Our results reframe the Entropic Bound from a post-hoc descriptor into an attention-native capacity measure with a precisely characterized predictability frontier.

---

### MixQuant: Adaptive Mixed-Precision Quantization for Large Language Models

Authors: Ashitabh Misra, Madhav Agrawal, Arham Jain, Tarek Abdelzaher
Published: 2026-07-25
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2607.23047v1

Mixed-precision quantization improves the accuracy of post-training quantization by allocating higher bitwidths to sensitive layers, but existing methods solve the allocation for a single fixed memory budget. In practice the budget varies across deployments and is unknown at calibration time. Adaptive quantization addresses this with one offline calibration that serves any budget, yet current methods score layer sensitivity in a manner that does not consider its dependency on quantization levels of other layers. We show that a layer's sensitivity depends strongly on the bitwidths of its upstream layers and that this dependence shifts the resulting preferred bit allocation. We propose MixQuant, a technique-agnostic adaptive framework that wraps any base quantizer. MixQuant marginalizes each layer's distortion over random quantized upstream configurations to obtain budget-agnostic scores, calibrates the quantizer's parameters on plans the allocator itself produces, and penalizes allocations that leave layers at the lowest bitwidths. A single greedy pass then serves any budget at deployment. Across Llama-3.2-3B, Llama-2-7B, and Mistral-7B under AWQ and GPTQ, MixQuant outperforms adaptive and mixed-precision baselines in every setting, improving average accuracy by up to 8 points and reducing perplexity from 12.43 to 10.70 at the tightest budget, while matching an ILP solver at negligible deployment cost.

---

### Structured Redundancy Modeling for Efficient Visual Token Pruning in High-Resolution MLLMs

Authors: Jouwon Song, Woohyeong Kim, Kyeongbo Kong
Published: 2026-07-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2607.23046v1

Recent high-resolution Multimodal Large Language Models (MLLMs) generate thousands of visual tokens per input, leading to a visual token explosion that introduces severe latency bottlenecks. While token pruning mitigates this issue, state-of-the-art subset-optimization methods typically rely on iterative subset construction to jointly capture visual diversity and instruction relevance. As visual token counts scale, this sequential dependency introduces significant selection overhead, severely limiting the translation of theoretical FLOPs reductions into actual wall-clock speedups. To address this limitation, we propose Single-Forward Pruner (SFPruner), a structural reformulation of visual token pruning that embeds redundancy control directly into the scoring space, bypassing the need for iterative combinatorial optimization. Our non-iterative framework achieves redundancy-aware importance selection in a single forward pass through two complementary mechanisms. First, to attenuate redundancy at the covariance level, we introduce a semantics-guided ridge leverage scheme. By integrating instruction relevance and visual saliency, this mechanism suppresses dominant covariance directions and mitigates representation bias. Second, ranking-based directional masking resolves residual overlap through asymmetric similarity competition, where higher-scoring tokens explicitly suppress redundant lower-scoring alternatives via parallel tensor operations. Extensive evaluations demonstrate that our approach maintains stable selection costs, reducing the token selection process by up to 110 ms, from 112.4 ms to just 2.5 ms at 512 tokens in Qwen2.5-VL. This structural efficiency successfully translates theoretical token reductions into tangible inference speedups while preserving highly competitive performance against state-of-the-art techniques under aggressive compression.

---

### Stress-testing large language model agents in a robotic chemistry laboratory

Authors: Lulu Guo, Yingkai Sun, Xiaobo Li, Luyao Ge, Ziming Wang, Haitao Zheng, Jingyu Li, Huijuan Zhang, Bingxu Chen, Daobin Liu, Yuebo Liu, Jie Li et al.
Published: 2026-07-25
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2607.23045v1

AI is evaluated through knowledge, reasoning and plan generation, yet scientific agency requires reliable physical action and adaptation to evidence. Here, we use a robotic chemistry laboratory as a physical-world testbed to make scientific agency measurable. Its 45 modular workstations exposed as machine-readable skills enabled 4,608 trials. Only 3.3% of trials produced expert-assessed executable workflows under laboratory constraints; even the best system achieved 28.1%. Long-horizon planning remained a challenge: only three executable workflows exceeded 30 operations, although the longest contained 44. Across five rounds, experimental feedback prompted local adjustments but no workflow-level replanning or analytical-method redesign. By making physical executability and evidence-driven replanning measurable, our study provides an evidence-based assessment of deployment readiness and a diagnostic framework to guide closed-loop improvements towards physically grounded autonomous research.

---

### Characterizing Arbitrary Lindbladian Dynamics with a Few Pauli Measurements

Authors: Taiqi Zhou, Weiyuan Gong
Published: 2026-07-25
Categories: quant-ph, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2607.23044v1

Quantum devices are open systems whose dynamics interleave coherent evolution with dissipation, and benchmarking, error mitigation, and error correction all rest on a faithful model of both. Existing characterization protocols either assume prior knowledge of the interaction and noise structure, or demand ancillas, entangled probes, or mid-circuit control, or capture only the Pauli-diagonal part of the noise. Here, we present a protocol that reconstructs an arbitrary sparse Markovian generator, including every Hamiltonian together with the jump operator coefficients, using only product Pauli state preparation, single uninterrupted forward evolutions, and product Pauli measurements. Given a sparsity budget $M_0$ and a strength bound $Γ$ of the Lindbladian, every coefficient is learned to precision $ε$ from $\widetilde{O}(Γ^2M_0^2/ε^4)$ experiments and $\widetilde{O}(ΓM_0^2/ε^2)$ total evolution time, with both supports identified from data without locality assumptions. The protocol runs at a logarithmic number of positive evolution times on a hardware clock lattice and is provably robust to calibrated state-preparation and measurement errors.

---

### Speech Signals Complement LLMs for Predicting Interpersonal Attraction in Speed Dating

Authors: Yuriko Kikuchi, Takato Hayashi, Ryusei Kimura, Naoya Inoue, Ryo Ishii, Shogo Okada
Published: 2026-07-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2607.23037v1

Large language models (LLMs) can predict interpersonal attraction from conversation transcripts, but it remains unclear what a speech predictor can add beyond transcript-only LLM prediction. Using Japanese speed-dating conversations, we combine predictions from a transcript-only LLM and a supervised speech predictor to estimate participants' reported liking of their partners. We show that speech can complement transcript-only LLM prediction, but that this complementarity is conditional rather than universal. Combining the two predictions significantly improves pairwise ranking accuracy over the transcript-only LLM alone in all evaluated conditions. By contrast, gains in per-participant Pearson $r$ vary across conversation rounds and rating directions, with none significant after correction. Retrospectively, these $r$ gains are concentrated among participants for whom the speech predictor is more accurate. Speech can therefore retain predictive value even when an LLM predicts attraction from transcripts. The relevant question is not simply whether speech helps, but where its complementarity emerges.

---

### Online Policy Evaluation for MDPs with Dynamic UBSR Measures

Authors: Weikai Wang, Erick Delage
Published: 2026-07-25
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2607.23030v1

Developing efficient function-approximation methods for policy evaluation is a fundamental challenge in risk-aware reinforcement learning. Existing approaches either focus on restrictive classes of risk measures or rely on access to a simulator, limiting their applicability in fully online settings. In this work, we propose computationally efficient online learning algorithms for policy evaluation in Markov decision processes (MDPs) with dynamic utility-based shortfall risk (UBSR) measures under linear function approximation. Specifically, we introduce the UBSR-TD algorithm, establish conditions under which it converges almost surely, and develop several variants designed to accelerate convergence. Our formulation shows that existing policy evaluation algorithms for risk-neutral MDPs can be readily adapted to dynamic UBSR settings by incorporating a loss function into the temporal-difference error. Numerical experiments support our theoretical findings, and an application to a perishable inventory management problem with shelf-life uncertainty demonstrates the practical effectiveness of the proposed methods.

---

### Multi-Agent Privacy Game in Federated Learning: A Unified Mean-Field View

Authors: Kun Zhao, Xu Chen
Published: 2026-07-25
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2607.23029v1

Federated learning enables collaborative model training across distributed clients without centralising their data, yet privacy remains a persistent concern because the shared model updates can leak information about local datasets. Existing privacy-preserving methods either inject calibrated noise into client updates, limiting their composition guarantees, or formulate client privacy choices as a multi-agent game whose Nash equilibrium becomes intractable as the number of clients grows. We bridge these two lines of work by formulating privacy-preserving federated learning as a mean-field privacy game: each client strategically chooses its own privacy budget while interacting with the population only through a single mean-field statistic. The mean-field limit yields a tractable equilibrium for arbitrarily many clients, accommodates heterogeneous client preferences, and inherits an exponentially decaying privacy guarantee through a log-Sobolev contraction. The framework recovers the entropic privacy baseline as the homogeneous special case and the multi-agent privacy game as the finite-population case. Experiments on quadratic regression, logistic regression, and MNIST demonstrate that the proposed framework attains the privacy-utility trade-off of the entropic baseline while delivering a personalized privacy guarantee that the homogeneous baseline cannot express.

---

### All in One: Generative Modeling as Mean-Field Game Design

Authors: Kun Zhao, Xu Chen
Published: 2026-07-25
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2607.23026v1

Mean-field games (MFGs) offer a unifying lens on continuous-time generative modeling: a cost tuple recovering twelve prominent models---Continuous Normalizing Flows, OT-Flow, Score-based Models, Schrödinger Bridges, and more---as special cases of one variational problem. Yet two dimensions of this space remain entirely unexplored: the interaction term $\mathcal{I}$ is set to zero in many existing models, and the rich family of MFG solvers has never been applied to generative modeling. We address both gaps with MFGLab an open-source PyTorch library whose primary API is the cost tuple: all twelve models are specified by four composable cost functions, and the training loop, log-Jacobian, and reverse-ODE sampler are shared automatically. We additionally propose DI-Flow, a novel cost design that uses a differentiable entropy functional to encourage mode coverage, and provide learning-based MFG solvers that substantially outperform neural training on stochastic-dynamics rows. Experiments on two 2-D benchmarks confirm that the unified API is lossless relative to hand-coded implementations.

---

### When Less Is More: A Controlled Benchmark of Lightweight CNNs for Satellite Land-Cover Segmentation on DeepGlobe

Authors: Atiq Ur Rehman, Joseph Michael Donovan
Published: 2026-07-25
Categories: cs.CV, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2607.23024v1

High-resolution satellite imagery is the backbone of good land-cover classification, and without that, environmental monitoring, urban planning, and sustainable resource management all fall short. Deep learning architectures perform well in semantic segmentation, but the efficiency-accuracy trade-off across classical convolutional encoders is not well quantified under controlled, reproducible conditions. This study compares five architectures VGG16, MobileNetV2, InceptionV3, AlexNet, and CNN on the DeepGlobe Land Cover Classification dataset using three progressively optimized iterations to isolate regularisation, transfer learning, and architectural depth. To ensure performance differentials reflect architectural properties, all experiments used identical preprocessing, hyperparameter, and training protocols without data augmentation or class-imbalance correction. At 24.98 MB, MobileNetV2_v1 had the highest overall accuracy (0.7906) and mean Intersection over Union (0.4625), outperforming deeper alternatives like InceptionV3_v2 (125.17 MB, accuracy 0.7610) and VGG16_v2 (71.13 MB, accuracy 0.7653). Class-wise analysis showed strength in urban, agricultural, and water categories, but rangeland-barren confusion showed that architectural optimization alone cannot optimize spectrally similar minority classes. Strong spatial generalization and crisp boundary delineation were confirmed on held-out test imagery, validating operational applicability. These results show that lightweight, transfer-learned models can match or outperform deeper models in resource-constrained remote-sensing environments, enabling scalable land-cover mapping.

---

### OmniMate: Open-Ended Real-Time Streaming Audio-Visual Generation for Interactive Avatars

Authors: Quanyue Song, Yishan He, Yanbo Ding, Zhixiang He, Yongxiang Li, Caigui Jiang, Zhi Zhi Guo
Published: 2026-07-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2607.23023v2

Recent advances in diffusion-based generative models have enabled real-time audio-driven avatar generation and unified audio-visual synthesis, providing a promising foundation for interactive avatar systems. However, extending unified audio-visual synthesis to real-time interactive streaming remains challenging, as the generation horizon is unknown in advance and the generated identity may drift over long-term generation. To address these challenges, we propose OmniMate, a unified framework for open-ended real-time interactive audio-visual avatar generation. OmniMate jointly synthesizes visual content, speech, and sound effects in real time, enabling natural and immersive multi-turn interactions. To achieve adaptive response progression, we introduce a Generation Progress Controller (GPC) that explicitly models the generation progress of each streaming chunk, allowing the model to complete responses according to the desired progress and achieve seamless transitions between execution and listening states. To preserve long-term cross-modal identity consistency, we propose a Multi-Reference Conditioning Module (MRCM), which leverages multiple reference images and a reference speech segment to provide persistent visual and speaker identity cues throughout long-duration streaming interactions. Extensive experiments on an interaction-oriented adaptation of VerseBench demonstrate that OmniMate achieves high-quality, low-latency streaming generation while maintaining strong long-term audio-visual consistency. The results further show that OmniMate supports realistic, coherent, and responsive interactive avatar experiences over extended multi-turn conversations.

---

### Reason Popper-ly: Patching In-Context Reasoning with Inductive Logic Programming

Authors: Zirong Chen, Meiyi Ma
Published: 2026-07-25
Categories: cs.AI, cs.LO, cs.SC
arXiv: https://arxiv.org/abs/2607.23019v1

Chain-of-thought (CoT) prompting enables large language models (LLMs) to tackle multi-step reasoning tasks, yet the generated intermediate steps are not guaranteed to be logically sound. We present Reason Popper-ly, a neurosymbolic framework that uses inductive logic programming (ILP) to learn relation composition rules from reasoning traces and deploys them as an online verifier for step-level correction. Given an LLM-generated trace, the method checks each inferred step against the learned rule table, diagnoses the violation type, rewrites incorrect steps with symbolically derived repairs, and regenerates the remaining suffix so that the model can produce its final answer conditioned on a verified trace. We evaluate on CLUTRR, a multi-hop kinship reasoning benchmark, using five language models over reasoning chains of 2 to 10 hops. Across all models, Reason Popper-ly consistently improves terminal accuracy over standard CoT, with gains of up to 48 percentage points for small models and 15 points for frontier models on the longest chains. Compared with a fully exogenous symbolic pipeline, our method performs better on harder instances by preserving the model's successful grounding while correcting only verifiable reasoning failures. In addition, step-level ILP verification yields a fine-grained error taxonomy that provides diagnostic insight beyond final-answer accuracy.

---

### Covariance-Boosted Gaussian Processes for Spatiotemporal Irregularities

Authors: Jeremy Ovadia
Published: 2026-07-25
Categories: stat.ML, cs.LG, physics.space-ph, stat.ME
arXiv: https://arxiv.org/abs/2607.23018v2

Nonstationary Gaussian process (GP) models are powerful tools for capturing input-dependent variability by adapting to observed data. However, with limited sampling and highly parameterized covariance structure, they are often prone to overfitting and overconfident uncertainty estimates, potentially leading to misleading predictions in safety-critical applications. Motivated by ionospheric modeling for satellite-based augmentation systems (SBAS), this paper proposes a Covariance-Boosted Gaussian Process (CBGP) framework centered upon boosting covariance priors to discover nonstationary latent functions for signal and observation variation that capture irregularities in the input domain. An additional layer of GP modeling of "partially-whitened" observations guides latent function relative error estimation that is used to iteratively update weak priors in a gradient descent-like procedure. Following boosting, restrictions are imposed upon prior covariances to prevent overfitting while posterior uncertainties are inflated to prevent model overconfidence. CBGP model efficacy and robustness are demonstrated through out-of-sample testing of both simulated and real-world applications that meet a three-nines integrity standard. The modeling of an extensive ionospheric storm dataset over South America suggests accurate and reliable means to compute SBAS ionospheric corrections in the most challenging space weather environment using regional models that are more informed and responsive than local fitting performed by currently-operating SBAS.

---

### Covariance-Boosted Gaussian Processes for Spatiotemporal Irregularities

Authors: Jeremy Ovadia
Published: 2026-07-25
Categories: stat.ML, cs.LG, physics.space-ph, stat.ME
arXiv: https://arxiv.org/abs/2607.23018v1

Nonstationary Gaussian process (GP) models are powerful tools for capturing input-dependent variability by adapting to observed data. However, with limited sampling and highly parameterized covariance structure, they are often prone to overfitting and overconfident uncertainty estimates, potentially leading to misleading predictions in safety-critical applications. Motivated by ionospheric modeling for satellite-based augmentation systems (SBAS), this paper proposes a Covariance-Boosted Gaussian Process (CBGP) framework centered upon boosting covariance priors to discover nonstationary latent functions for signal and observation variation that capture irregularities in the input domain. An additional layer of GP modeling of "partially-whitened" observations guides latent function relative error estimation that is used to iteratively update weak priors in a gradient descent-like procedure. Following boosting, restrictions are imposed upon prior covariances to prevent overfitting while posterior uncertainties are inflated to prevent model overconfidence. CBGP model efficacy and robustness are demonstrated through out-of-sample testing of both simulated and real-world applications that meet a three-nines integrity standard. The modeling of an extensive ionospheric storm dataset over South America suggests accurate and reliable means to compute SBAS ionospheric corrections in the most challenging space weather environment using regional models that are more informed and responsive than local fitting performed by currently-operating SBAS.

---

### Mini-batch Noise Lowers Sharpness via Dominant-Subspace Fluctuations

Authors: Junho So, Dongwook Shin
Published: 2026-07-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2607.23012v1

During SGD training, the gradients often align strongly with the dominant subspace spanned by the top-$k$ eigenvectors of the Hessian of the loss. While this seems to naturally imply that loss reduction mainly occurs within this space, prior work has shown that updates within this dominant subspace make no meaningful progress in reducing the loss. In this work, we argue that the dominant subspace is better understood not as the main space for loss reduction, but as a key subspace for explaining the sharpness dynamics of mini-batch SGD. To explain the role of the dominant subspace in reducing top-$k$ sharpness, we show how the averaged gradient over fluctuations in the dominant directions produces a sharpness correction term, and derive a sharpness correction term induced by mini-batch noise in the dominant directions. Experimental results show that adding the derived correction term to GD brings the sharpness evolution of GD closer to that of SGD.

---