# Research Papers — 2026-09 · bundle page 224 of 266 > Full-text markdown of papers #11151–11200 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/224 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/223.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/225.md) ### MARBO: Relational Belief Grounding for LLM Agents in Social Deduction Games Authors: Yechan Hwang, Sangjun Bae, Jeongmo Kim, Sangwoo Bang, Seungyul Han Published: 2026-09-06 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.06563v2 Social deduction games (SDGs) require agents to reason under partial observability by maintaining relational beliefs about hidden roles and team alignments. While recent LLM-agent approaches improve gameplay through prompting and preference optimization, they often optimize actions and in-game speech without explicitly grounding them in such beliefs. This frequently leads to strategically inconsistent behavior, especially for compact LLM agents. We introduce Multi-Agent Relational Belief Optimization (MARBO), a belief-grounded preference optimization framework that leverages relational beliefs to guide strategic decisions and in-game speech. MARBO provides preference feedback only when behaviors are supported by reliable relational beliefs and lead to strategically favorable social outcomes, encouraging more consistent learning under uncertainty. Experiments on representative SDGs show that MARBO enables compact LLM agents to consistently outperform existing baselines. The Code is available on https://github.com/PleaseTakemeAway/MARBO. --- ### Hidden in Plain Sight: The Overlooked Significance of Canonical Elements for Extreme LLM Sparsity Authors: Hyeondo Jang, Kwanhee Lee, Dongyeop Lee, Namhoon Lee Published: 2026-09-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06557v1 Large language models (LLMs) are often considered fragile under aggressive sparsification, and maintaining reliable performance typically requires sticking to moderate sparsity levels. However, recent studies suggest that LLMs are more resilient to high sparsity than previously thought, reframing the problem as a design challenge rather than a fundamental limitation. In this work, we challenge the perceived limits of unstructured post-training LLM pruning by revisiting elementary pruning strategies that have remained relatively underexplored at this scale. Through a progressive sparsification framework with second-order saliency and continued training coordinated with sparsity progression, we show that pretrained LLMs can retain strong performance far beyond commonly studied sparsity regimes. Across LLaMA-2 and Qwen-3 model families, our approach improves perplexity and downstream accuracy up to 99\% sparsity, surpassing both the current state-of-the-art and representative baselines. Precisely, on LLaMA-2-7B, our approach achieves WikiText-2 perplexities of 13.48 and 19.67 at 95\% and 99\% sparsity, respectively, while delivering 3.23$\times$ decoding speedup and 6.21$\times$ memory savings at 95\% sparsity. Taken together, our results show that LLMs can be pushed into extreme sparsity while retaining strong performance, providing a foundation for further improving sparse models in this regime. --- ### EStream: Fast and Memory-Efficient MoE Prefill through Expert Virtualization on Mobile NPUs Authors: Junming Zhang, Zhenzhe Zheng, Fan Wu, Xiaoyao Huang, Jie Wu Published: 2026-09-06 Categories: cs.DC, cs.AR, cs.LG arXiv: https://arxiv.org/abs/2609.06551v1 Mobile vendors and application developers increasingly deploy LLMs on smartphones for diverse prefill-only services. Yet current systems rely mainly on dense models whose regular computation maps efficiently to mobile NPUs, leaving more capable MoEs underused. MoE prefill does not fit mobile NPUs: NPU graphs are fixed at compile time, yet MoE picks experts at runtime; and one request touches most experts, more than a phone can hold in memory. We present EStream, which resolves both by separating what the NPU must fix from what MoE decides at runtime. A single compiled expert graph serves every expert, with each expert's routed tokens and weight address bound at call time, so dynamic MoE execution runs entirely on the NPU without padding or CPU/GPU fallback. Expert virtualization keeps the expert pool in UFS flash storage and pages it through a fixed-size NPU-addressable arena, group by group, with loading hidden behind computation, so memory is bounded by the arena rather than by the model. It further introduces a hardware-aware configuration algorithm that automatically configures the UFS--NPU pipeline and maximizes loading--computation overlap. Across 18 comparative settings covering three 7B--16B MoEs and 256--4,096-token prompts, we evaluate EStream on a commercial Snapdragon smartphone. Compared to the fastest baseline at each setting, EStream achieves a 2.25--27.57X pure-prefill TTFT speedup and reduces peak physical memory by 1.19--12.29X. EStream further scales to MoE models with up to 46.7B parameters. --- ### Introductory Notes on Learning$^2$ Authors: Sai Siddharth, Maniarasu Ravi Published: 2026-09-06 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2609.06546v1 Although machine learning can be used to predict the evolution of physical systems from data, a formulation that learns only the system state at each time leaves the temporal and dynamical structure of the solution to be resolved within a broad hypothesis space. We introduce Learning$^2$, a representation-level framework that structures this space by coupling a primary representation to a second representation through a known physical transformation. The resulting cross-representation constraint restricts the effective hypothesis space and provides an ante-hoc, physically interpretable criterion for excluding solutions that satisfy the primary representation alone. We instantiate Learning$^2$ through EuLaNet, an Eulerian--Lagrangian representation for fluid dynamics. Given the velocity state $u(\mathbf{x},t)$, EuLaNet constructs its induced Lagrangian flow map $X(\mathbf{a},t)$ through $\dot{X}(\mathbf{a},t)=u(X(\mathbf{a},t),t)$, from which material transport and finite-time deformation are derived. The resulting representation couples the predicted state to the dynamical consequences it induces, providing a second consistency criterion beyond state-level agreement. We formalize this construction through an effective hypothesis space $\mathcal{H}_{L^2}\subseteq\mathcal{H}$ and define the conditions under which a consequence representation provides discriminative constraints on candidate solutions. EuLaNet is implemented as a model-independent representation module, separating the physical constraint from the downstream learning architecture. This construction provides an ante-hoc mechanism for physically interpretable constraint in scientific learning and offers a basis for developing and evaluating broader classes of Learning$^2$ architectures. The implementation is open-sourced to support the development and extension of the architecture across scientific domains. --- ### LLMs Mirror Country-Specific Gender Patterns If Asked, but Skew Male When Generating Media in Local Languages Authors: Sharif Kazemi, Tanya Popli, Neil K. R. Sehgal, Sunny Rai, Niyati Malhotra, Victor Orozco-Olvera, Ana María Muñoz Boudet, Samuel P. Fraiberger, Sharath Chandra Guntuku, Manuel Tonneau Published: 2026-09-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.06545v1 Large language models (LLMs) are increasingly used to generate media, but whether their content perpetuates gender stereotypes is unknown: standard benchmarks rely on selection-based formats rather than long-form generation, and surveyed baselines for local gender associations are scarce outside the West. We collect gender associations for 22 occupational and domestic roles from 695 respondents across the United States, India, Kenya, and Nigeria, and evaluate eight LLMs under two regimes: direct questioning and media generation. Models track the surveyed associations under direct questioning but skew substantially more male under media generation in major local-language cells, consistent with the male bias documented in human-produced media. Outside the US, the shift is much smaller and non-significant under English prompting, so English-only or country-agnostic evaluation would miss this bias in the languages where these models are most deployed. Instruction prompting reduces the shift directionally, but trades off against alignment with the surveyed associations. Evaluating LLM gender bias for global deployment therefore requires generation-format testing, local-language prompting, and locally-collected human baselines. --- ### A Unified Policy Architecture (UPA): The Governance Kernel for Enterprise AI Operating Systems Authors: Prabhu Raghav, Balamurugan Pandi, Arul Vivek, Shek Mohammed, Sridhar S Published: 2026-09-06 Categories: cs.AI, cs.CL, cs.SE arXiv: https://arxiv.org/abs/2609.06543v1 Enterprise AI is evolving into an Enterprise Operating System where autonomous AI agents can plan, reason, use memory, invoke tools, execute workflows, and collaborate with other agents. This shift creates a new governance challenge: existing authorization, security, guardrails, and compliance mechanisms are fragmented and are not designed to govern autonomous AI as a unified system. This paper introduces the Unified Policy Architecture (UPA), a governance architecture for Enterprise AI Operating Systems. UPA provides a unified policy model for governing AI and agents, tools, workflows, memory, enterprise resources, and agent-to-agent interactions and enterprise business rules. It extends policy control beyond authorisation to include runtime obligations, human approvals, compliance, audit evidence, and governance evaluation. We present UPA's governance model, declarative policy language foundations, policy evaluation semantics, extensible plugins, industry policy packs, and an evaluation framework for enterprise governance. We also identify extensions for multi-agent coordination, provenance-aware policies, and stateful runtime governance. UPA provides a foundation for building secure, accountable, and governable Enterprise Operating Systems for autonomous AI. --- ### Recovering topological information of light by topological learning Authors: Benquan Wang, Trishita Das, Yuhan Peng, Tatjana Kleine, Shanshan Chang, Jinhui Chen, Nilo Mata-Cervera, Chunyu Li, Kelin Xia, Andrew Forbes, Yijie Shen Published: 2026-09-06 Categories: physics.optics, cs.AI arXiv: https://arxiv.org/abs/2609.06542v1 The evolution of modern-day communication networks towards optical solutions with enhanced capacity and robustness is driving interest in topological light waves, exploiting their stability against perturbations through a topological invariant, e.g., the skyrmion number. However, detecting the underlying topology remains a computationally intense process even under ideal conditions, becoming intractable after passing through strongly disordered channels, where the degradation into unrecognisable speckle appears to destroy the topology. Here, we propose and demonstrate a topology-enhanced artificial intelligence (AI) approach to recover and classify such apparently lost topological information by computationally leveraging topological invariants in the data across many length scales. By aligning the topological classification of information with the topology of light, our topology-enhanced learning protocol, termed TOPO$^{2}$, achieves highly efficient recognition of the topological states of light, even from speckle, without the need for any prior learning. Our approach outperforms benchmark tests against standard computational algorithms and has the benefit of requiring just a single intensity pattern as the input, facilitating single-shot operation. To demonstrate this, we leverage the skyrmion number as a robust data carrier of images through a disordered channel, using TOPO$^{2}$ to accurately reconstruct the transmitted images. This work synergises topological photonics and topological AI for unravelling hidden topological signatures in light, opening a pathway towards robust communications even in extreme disordered environments. --- ### SRD-GUARD: A Defense Framework of LLMs via Semantic Rewriting and Joint Multi-Model Scoring for Latent Intent Exposure Authors: Qi Wang, Chengcheng Wan, Jiangtao Wang Published: 2026-09-06 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.06540v1 Large language models (LLMs) are increasingly deployed in safety-critical applications, yet jailbreak attacks can conceal harmful intent through role-playing, fictional scenarios, or seemingly benign motivations. Existing inference-time defenses may miss disguised attacks or excessively refuse legitimate requests. We propose SRD-GUARD, a parameter-free, black-box defense framework that exposes concealed intent through semantic rewriting and consensus-based risk assessment. Given an input prompt, SRD-GUARD generates five semantically related rewrites that preserve the underlying objective while removing unnecessary contextual packaging. The original prompt and rewrites are jointly evaluated by multiple independent LLM-based safety scorers on a continuous risk scale. A decision module combines absolute risk thresholds with relative risk changes between the original and rewritten prompts to adaptively intercept, preserve, or warn on requests. We evaluate SRD-GUARD against UNIATTACK, CIPHER, and DeepInception on Llama-3-8B-Uncensored and DeepSeek-V4-Flash using AdvBench and OR-Bench-Hard. SRD-GUARD achieves average DSRs of 91.44% and 100%, with ORRs of 8.00% and 12.00%, respectively. Compared with evaluated baselines, it provides a more favorable DSR--ORR trade-off. Ablation studies show that rewriting exposes concealed harmful intent, joint scoring improves robustness to individual evaluator behavior, and risk-adaptive decision making enables selective handling of ambiguous inputs. These results demonstrate that semantic intent exposure, consensus-based risk assessment, and relative-risk-aware routing provide an effective and selective approach to black-box jailbreak defense. The artifact is available at https://anonymous.4open.science/status/CICD-Guard-D648. --- ### 3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models Authors: Ling Liu, Bingchen Gong, Amal Dev Parakkat, Maks Ovsjanikov Published: 2026-09-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06535v1 We introduce 3DHarnessBench, a benchmark that evaluates the agentic ability of frontier vision-language models (VLMs) to recover 3D geometry as Blender Python code from a variety of inputs. Unlike previous frameworks that prompt the VLMs with a fixed input (e.g., a single rendering or a text description), 3DHarnessBench evaluates four separate harness settings that progressively enable active agentic exploration, facilitated by recent Blender MCP functionality. Our hierarchy from Single-view, Multi-view, Active Visual (arbitrary viewpoint access), and Full 3D Interaction (complete access to the target object through Blender function calls) probes the models' abilities in both visual perception and active inference, tool calling, and self-correction. We observe that the ability of all frontier models to recover 3D geometry improves significantly with richer function call access, although the improvements are strongly model-dependent, revealing highly uneven agentic 3D-to-code capabilities. We will release the benchmark, code, outputs, and agent trajectories for reproducible 3D evaluation. --- ### Selective Knowledge Control for Continual GUI Agent Learning over Application Streams Authors: Zirui Shang, Xin Shu, Yang Liu, Zhi Gao, Xinxiao Wu, Lifeng Fan Published: 2026-09-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06530v1 Continual learning is a crucial capability for Graphical User Interface (GUI) agents to adapt to evolving applications while retaining knowledge acquired from previous applications. Such application streams pose a challenging knowledge modeling problem: new applications often share underlying knowledge with past ones, yet also introduce specific knowledge that must not interfere with historical knowledge. In this paper, we propose activation-conditioned selective knowledge control, a lightweight method that achieves selective knowledge retention via neuron-level gradient manipulation. Our method maintains a compact historical knowledge state to protect highly activated MLP neurons that preserve previous knowledge. When a new application arrives, it performs real-time gradient surgery conditioned on forward activation. Concretely, the protected neurons are categorized into two types: unactivated neurons holding specific knowledge, whose gradients are truncated to prevent interference; and activated neurons holding shared knowledge, whose gradients are orthogonally projected to preserve stability while enabling adaptation. After each application stage, newly identified critical neurons are merged into the historical state for future learning. Empirical evaluations on multi-app sequential benchmark demonstrate that our method effectively mitigates catastrophic forgetting on prior applications while sustaining robust adaptation to new ones. --- ### ProcArena: A Multi-Scenario Benchmark for LLMs on Direct and Interactive PL/SQL Development from Natural Language Authors: Hang Zhang, Chaokun Wang, Yuzhi Pan, Ziyao Zhong, Shuo Cao, Yue Xue, Zeyu Huang, Xingwei Zhou, Fang Niu, Bofan Xie, Guanchen Ge, Leqi Zheng et al. Published: 2026-09-06 Categories: cs.CL, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2609.06527v1 Large language models (LLMs) have shown strong potential for translating natural-language (NL) requirements into PL/SQL programs, attracting increasing attention from the database community. However, existing NL-to-PL/SQL efforts primarily focus on directly generating PL/SQL from complete NL requirements. In practice, PL/SQL development involves diverse scenarios, such as from-scratch development, code modification, debugging, and optimization, and may require either direct generation or multi-turn interaction. Yet, no comprehensive benchmark evaluates multi-scenario, direct and interactive, and multi-dialect NL-to-PL/SQL development. In this paper, we present ProcArena, an execution-based benchmark covering both Direct and Interactive modes. ProcArena comprises 3,998 executable tasks over 157 databases, spanning nine development subscenarios in PostgreSQL and Oracle. We construct challenging Direct tasks through Iterative Logic Enhancement and scenario-specific adapters, and derive paired Interactive tasks through Knowledge Integration and Requirement Perturbation while preserving executable targets. We further design a controlled Solver-User Simulator protocol that allows models to clarify user intent and inspect the database environment without exposing hidden execution feedback. Evaluating seven language models, we find that the best average scores are only 62.2% and 57.8% in Direct and Interactive, respectively, demonstrating that realistic NL-to-PL/SQL development remains challenging, particularly in interactive settings. --- ### Not Just Oversmoothing: Detecting the Echo Chamber Effect in Graph Neural Networks Authors: Asela Hevapathige, Ahad N. Zehmakan, Asiri Wijesinghe, Saman Halgamuge Published: 2026-09-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06521v1 Oversmoothing is a well-known failure mode of Graph Neural Networks (GNNs). However, most existing diagnostics rely on global aggregation measures that fail to capture the heterogeneous dynamics of message passing. Real-world graphs exhibit pronounced community structure, and message passing operates on two timescales, with representations collapsing rapidly within communities and slowly across them. This creates a critical gap in which intra-community representations can become indistinguishable while inter community separation persists, a failure mode that we refer to as the Echo Chamber Effect. To quantify this effect, we introduce the Echo Chamber Index (ECI), which stratifies pairwise distances by community membership and reveals when global energy diminishes while inter-community separation persists. ECI further shows that feature retention mechanisms can preserve the echo chamber under the conditions of our theoretical analysis. The consequences depend on label structure: when communities align with classes, the echo chamber can sharpen node classification, whereas when they do not, the same collapse makes classification provably harder. Motivated by this analysis, we propose Community-Aware Split Propagation (CASP), a lightweight plugin that decouples intra- and inter-community aggregation and learns their balance from label structure. CASP improves diverse backbone GNNs across most evaluated homophilic and heterophilic settings. --- ### Role-Specific Predictive Geometries for Nonstationary Multivariate Graph-Signal Forecasting Authors: Yanbo Chen, Anamitra Makur Published: 2026-09-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06519v1 Forecasting multivariate graph signals is challenging when node-level trajectories are nonstationary but stable relations persist across nodes and features. In an error-correction representation, long-run equilibrium restoration and short-run transient propagation represent different predictive roles and need not share a common cross-feature geometry. We introduce role-specific predictive geometries in which directed Long relations act on estimated equilibrium coordinates, whereas directed Short relations act on lagged differences. Matrix-valued Long responses mix equilibrium coordinates before graph propagation, while Short responses use graph-filtered transient designs; a direct multi-horizon estimator couples forecast corrections across adjacent horizons. Temporal cross-fitting and Frisch-Waugh-Lovell partialling-out give selected edges a conditional predictive interpretation relative to a graph-temporal backbone. The Long operator remains right-factorized through the equilibrium subspace and therefore annihilates source common-trend directions. Controlled experiments recover all planted Long relations (20/20), all planted Short relations (20/20), and both role families in every Dual realization (10/10). Across four real-world benchmarks, the proposed predictor improves on the G-VARMA backbone in three datasets, with all 25 fold-horizon comparisons favorable on the five-fold financial benchmark. --- ### Model-Adaptive and Risk-Constrained Frequency Hopping Against Predictive Jammers Authors: Yanbo Chen, Xinjing Zhou Published: 2026-09-06 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2609.06514v1 Adaptive frequency hopping against predictive jamming must address both model uncertainty and policy exposure: the context-loss relationship may vary across operating regimes, while persistent hopping patterns may expose high-probability channels to attack. We propose D-PACT-AFH, a model-adaptive and risk-constrained adversarial contextual-bandit framework in which a Tsallis-FTRL master combines a global linear learner with a partitioned local learner and selects the model class online. D-PACT-Hit incorporates channel-wise marginal hit risk into model selection, while D-PACT-Safe applies a minimum-Kullback-Leibler projection to enforce a per-slot risk budget. We establish estimator validity under non-anticipating attacks, an oracle decomposition relative to the better fixed base, and an exact conditional-risk guarantee for the Safe projection. Experiments across diverse channel regimes and jammer types demonstrate effective model adaptation and a controllable goodput-risk tradeoff: D-PACT-AFH recovers 95.5% of the local learner's gain under observable switching while avoiding 77.7% of its degradation in a negative-control regime. --- ### Bi-HYCO: Bi-Objective Cooperative Learning for PDE Parameter Identification under Fragmented Observations Authors: Umberto Biccari, Jun Chen, Roberto Morales, Enrique Zuazua Published: 2026-09-06 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.06511v1 Physical and synthetic models may describe complementary aspects of the same PDE-governed system while receiving different, possibly fragmented, observations. We propose Bi-Objective HYCO (Bi-HYCO), a cooperative framework that retains both representations and their local observational objectives while coupling their predicted states at unlabeled interaction points. These points contain no measurements and do not augment the data; they provide a communication mechanism in the common state space. The two criteria form a vector-valued objective, and weighted scalarizations provide computational realizations. For the deterministic shared-observation algorithm with fixed interaction points, we prove sufficient decrease and finite length of the whole alternating sequence, which converges to a mixed critical point under the stated Kurdyka-Lojasiewicz-type assumptions. Elliptic transmission and two-dimensional Navier-Stokes experiments assess parameter and state reconstruction, noise and scalarization effects, and PINN/XPINN references. Ablations show that removing state interaction while retaining aggregation deteriorates parameter recovery in the tested configurations, particularly for Navier-Stokes. --- ### A Cloud-Based Hybrid Model for Real-Time Detection of BRTA-Approved Licence Plates Using YOLO Tiny and Haar Cascade Authors: Debashis Kar Suvra, Tahsina Farah Sanam Published: 2026-09-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06507v1 Accurate vehicle license plate detection is essential for applications such as intelligent transportation systems, toll collection, parking management, and law enforcement. In Bangladesh, this task presents distinct challenges due to the complexity of localized license plates and environmental factors like lighting, occlusion, motion blur, and obstructions such as dirt or mud. These challenges often render conventional methods ineffective. This paper introduces a novel hybrid approach, combining the YOLO Tiny deep learning model with the Haar-Cascade classifier, for enhanced detection and localization of Bengali license plates. A key innovation of our system is the integration of a dynamic retraining pipeline, which allows the model to adapt to evolving real-world conditions. This retraining mechanism significantly boosts performance in low-confidence scenarios by continuously improving the model's accuracy as new data is encountered. Additionally, a publicly accessible dataset of BRTA-compliant license plates, captured under diverse and challenging conditions, has been developed to support this approach. Experimental results demonstrate that our approach not only achieves superior detection accuracy and computational efficiency over conventional models but also ensures consistent performance in resource-constrained environments, particularly in Bangladesh. --- ### CAM: Question Answering on Entity-Centric Videos with Continuous Extraction and Adaptive Querying Authors: Yizhou Tian, Zizhe Chen, Shiyuan Deng, Garry Yang, Zijie Dai, Luohao Pan, Hao Lin, Peiqi Yin, Xiao Yan, James Cheng Published: 2026-09-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06504v1 Memory facilitates question answering over long videos by extracting and retrieving facts to fit within the limited context windows of multimodal LLMs (MLLMs). Existing solutions typically extract independent memory entries from fixed-length video clips and thus cannot capture high-level semantics that need to be summarized over extended time periods, such as character traits and relations. Moreover, they rely solely on similarity-based retrieval and may fail to retrieve the fine-grained details required for question answering. To tackle these problems, we propose CAM, featuring continuous extraction for high-level semantics and adaptive querying for fine-grained details. In particular, CAM stores the entities and relations extracted from video clips in a knowledge graph. To capture the high-level semantics of each entity or relation, CAM summarizes the local subgraph of the target entity or relation once the subgraph reaches a predefined size. To retrieve the fine-grained details required for question answering, CAM supports multiple search methods, including knowledge graph traversal, video re-watching, and audio listening. It utilizes a planner-executor-verifier pipeline to adaptively compose these search methods according to question intent. Evaluations on three benchmarks show that CAM outperforms SOTA baselines and improves their accuracy by up to 23 percentage points. Code is available at https://github.com/Jake-Tian/CAM. --- ### Structural Entropy-Driven Graph Diffusion Generation for One-Shot Federated Graph Learning Authors: Shutong Zheng, Lele Fu, Sheng Huang, Wei Yang Bryan Lim, Chuan Chen Published: 2026-09-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06499v1 One-shot federated graph learning (FGL) requires the server to estimate client contributions from highly compressed information, yet conventional volume-based weighting captures the amount of client data while overlooking how its connectivity is organized. In this paper, we propose SPIRE, a Structural Entropy-Driven Graph Diffusion Generation method that introduces topology-aware client differentiation into one-shot FGL. Specifically, we employ first-order degree-distribution structural entropy as a compact descriptor of degree-mass dispersion and use it to derive structural client weights, providing an inductive bias that accounts for differences in graph topology beyond data volume. On the generation side, a graph diffusion model on the server synthesizes pseudographs conditioned on the weighted client prototypes, capturing both semantic and structural information without requiring additional client-side training. The generated pseudographs are then assembled via disjoint union fusion to train a global graph neural network. Extensive experiments on seven real-world graph datasets demonstrate that SPIRE consistently outperforms conventional and one-shot FGL methods, with particularly strong gains under highly heterogeneous (non-IID) and graph-perturbed settings. --- ### DFlow: Enabling Verifier Information Flow in Block Diffusion Speculative Decoding Authors: Yaojie Zhang, Linfeng Zhang, Bin Cui, Xupeng Miao Published: 2026-09-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.06498v1 Block diffusion speculative decoding improves LLM inference efficiency by proposing a block of future tokens in parallel and verifying them with a single forward pass through the target model. However, existing methods retain only the accepted prefix and discard the rejected suffix, preventing the computation spent on these positions from benefiting subsequent drafting rounds and forcing the drafter to repeatedly reconstruct representations for future tokens from scratch. We observe that rejection only determines whether a proposed token can be committed, while the verifier representations at rejected positions can still provide useful information for subsequent predictions. Based on this observation, we propose DFlow, a simple yet effective framework that enables verifier information to flow across drafting rounds. DFlow reuses the hidden states produced by the target verifier for the rejected suffix to guide subsequent drafting without additional target computation. To effectively learn this information flow across drafting rounds, we introduce a self-condition train strategy that feeds verifier representations from earlier predictions back into subsequent predictions. Experiments on Qwen3 models across diverse benchmarks demonstrate that DFlow consistently improves draft quality and acceptance length over DFlash. --- ### Vision-Guided Text Prompt Tuning for Multimodal Sentiment Analysis Authors: Xiaoran Kou, Jingyi Wu, Peng Sun, Yang Liu, Hong Chen Published: 2026-09-06 Categories: cs.MM, cs.CV arXiv: https://arxiv.org/abs/2609.06497v1 Multimodal sentiment analysis requires effective modeling of both verbal semantics and non-verbal affective cues. A central challenge is to calibrate text-centered sentiment understanding with visual facial evidence in a controlled, adaptive, and parameter-efficient manner. Text usually serves as the semantic anchor, whereas visual cues provide complementary evidence for ambiguous or implicit expressions; however, indiscriminate fusion may introduce visual noise and distort textual semantics. Moreover, fully fine-tuning large visual and textual encoders is costly and prone to overfitting on limited and scenario-dependent MSA benchmarks. To address these issues, we propose Vision-Guided Text Prompt Tuning (VG-TPT), which formulates visual-text sentiment modeling as controllable visual calibration of frozen text representations. VG-TPT injects visual affective cues into a frozen BERT encoder through layer-wise adaptive prompts, rather than relying on late-stage feature fusion or full backbone tuning. A co-guided router composes prompts from a trainable prompt bank according to both the evolving text state and the visual guidance feature, enabling sample-specific and layer-specific modulation. Experiments on CMU-MOSEI and CMU-MOSI show that VG-TPT consistently improves over text-only baselines and achieves competitive or superior performance compared with several full-modality methods, while updating only 2.4M trainable parameters. The code is available at https://github.com/ma-tubu/VG-TPT. --- ### Diffuse2Seg: Diffusion Models Can Segment Anything Without Supervision Authors: Christoph Hümmer, Joachim Sicking, Fabian Hüger, Hanno Gottschalk Published: 2026-09-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06491v1 Open-world entity segmentation aims to predict masks for arbitrary objects across domains and at multiple granularities, from parts to whole objects. In this setting, SAM sets a strong standard: trained on SA-1B, comprising 11M images and over 1B carefully annotated masks, it achieves remarkable zero-shot performance. Collecting such labels is expensive and time-consuming, however, which limits how far this recipe can scale. Text-to-image diffusion models offer a way around this. Their intermediate features transfer well across perception tasks, and since object structure emerges as the model denoises a noise sample into an image conditioned on a text prompt, that structure is already encoded in these representations. They can therefore be exploited for open-world entity segmentation without retraining or supervision. Building on this observation, we introduce Diffuse2Seg, which repurposes generative diffusion models for automatic mask generation by propagating a grid of point prompts through their self-attention representations in an edge-preserving manner. Diffuse2Seg produces multi-granular instance masks and outperforms prior state-of-the-art label generators by 4.3-7.1 p.p. in AR_1000 across five domains. Training an instance segmentation model on these generated masks advances detector-free open-world segmentation by 7.4 and 7.7 p.p. on "things" and "stuff+things" datasets and surpasses the detector-based UnSAM on "stuff+things" by 2.1 p.p. in AR_1000. Finally, we show that a model trained on Diffuse2Seg labels provides a strong initialization for semi-supervised learning, outperforming its fully supervised counterpart with already 5k labeled images. --- ### OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution Authors: Shubhashis Roy Dipta, Sourajit Saha, Shaswati Saha, Nobin Sarwar Published: 2026-09-06 Categories: cs.CV, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.06490v1 Recursive Super-Resolution (SR) extends fixed-scale SR to extreme magnification by repeatedly feeding predictions back into the same model, analogous to zooming an image repeatedly. However, ground truth availability at every scale, especially at depth, remains challenging as the required source resolution grows geometrically, leaving deeper predictions unsupervised. We present OracleZoom, an on-policy distillation-inspired, reference-constrained framework that trains on its trajectory while carrying the last ground-truth evidence beyond the supervision boundary. Direct and cross-scale supervision constrain verifiable content, while a no-reference quality objective guides unresolved fine-scale detail. A KL-constrained pretrained latent prior limits quality-driven drift, while EMA consistency stabilizes the supervision boundary. Across seven datasets, OracleZoom achieves the state-of-the-art SR quality across zooming scales, averaging 0.713 CLIPIQA, with larger gains on deeper scales, while significantly reducing hallucinations. Code, data, and models are available at https://dipta007.github.io/OracleZoom/ . --- ### Power Mean Estimation in Stochastic Continuous Monte Carlo Tree Search Authors: Tuan Dam Published: 2026-09-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.06489v1 Monte Carlo Tree Search (MCTS) has demonstrated success in online planning for deterministic environments, yet significant challenges remain in adapting it to stochastic Markov Decision Processes (MDPs), particularly in continuous state-action spaces. Existing methods, such as HOOT, which combines MCTS with the Hierarchical Optimistic Optimization (HOO) bandit strategy, address continuous spaces but rely on a logarithmic exploration bonus that lacks theoretical guarantees in non-stationary, stochastic settings. Recent advancements, such as POLY-HOOT, introduced a polynomial bonus term to achieve convergence in deterministic MDPs, though a similar theory for stochastic MDPs remains undeveloped. In this paper, we propose a novel MCTS algorithm, \Algname, designed for continuous, stochastic MDPs. \Algname integrates a power mean as a value backup operator, alongside a polynomial exploration bonus to address the non-stationarity inherent in continuous action spaces. Our theoretical analysis establishes that \Algname converges at a polynomial rate of $\mathcal{O}(n^{-ζ})$, $ζ\in (0,1/2)$, where \( n \) is the number of visited trajectories, thereby extending the non-asymptotic convergence guarantees of POLY-HOOT to stochastic environments. Experimental results on stochastic tasks validate our theoretical findings, demonstrating the effectiveness of \Algname in continuous, stochastic domains. --- ### Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing Authors: Tuan Dam Published: 2026-09-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.06484v1 Planning with a generative model aims to estimate the value of a state using as few simulator calls as possible. SmoothCruiser achieves problem-independent complexity $\widetilde O(\varepsilon^{-4})$ by exploiting the smoothness of the entropy-regularized Bellman backup, but its estimator is only first-order. We show that the sample-complexity exponent of SmoothCruiser-type planners is governed by the order $β$ of the local Taylor remainder, giving oracle complexity $\widetilde O(\varepsilon^{-(2+2/(β-1))})$: the first-order case $β=2$ recovers SmoothCruiser, while a second-order/cubic remainder $β=3$ yields $\widetilde O(\varepsilon^{-3})$. We reach this regime with an optimal-transport-smoothed Bellman backup over action distributions, which has a closed form, a policy gradient, and a Lipschitz Hessian, and whose quadratic correction admits an unbiased cross-product estimator. The resulting SecondOrderSmoothCruiser achieves $\widetilde O(\varepsilon^{-3})$ oracle complexity for fixed OT parameters, and we relate the OT, entropy-regularized, and unregularized objectives through explicit regularization-bias bounds. --- ### How Does Parameter Pruning Reshape DNN Representations? An Interaction-Driven Exploration Authors: Fangbo Li, Junpeng Zhang, Qihan Ren, Quanshi Zhang Published: 2026-09-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06483v1 This study focuses on the scientific problem of understanding internal factors that govern the diverse performance degradation of deep neural networks (DNNs) when different parameters are pruned. In order to explain why pruning certain parameters leads to significant performance degradation but pruning other parameters does not, we examine how the pruning operation affects the interaction patterns encoded by the DNN. We find that when we progressively increase the pruning ratio, the interaction patterns encoded by DNNs exhibit a distinct three-phase dynamics, \emph{i.e.}, model performance is not largely affected until the pruning operation begins to remove low-order interactions, and low-order interactions exhibit strong generalizability. Moreover, we find that the high sensitivity of DNN performance to the pruning of certain modules is attributed to whether the pruning operation removes generalizable low-order interaction patterns. --- ### One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypoints Authors: Shiqi Pan, Qi Zheng, Hanqin Sun, Youjian Zhang, Daquan Feng, Xu Wang Published: 2026-09-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.06476v1 Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an embodied agent to navigate unseen environments by following natural language instructions. Current zero-shot VLN-CE methods either rely on pre-trained waypoint predictors or require multiple queries to large models per step. To address prohibitive inference latency and computational overhead, we propose O2C-Nav, an efficient zero-shot navigation framework that calls only a single large model once per decision step. Our approach introduces a training-free structured waypoint generator and a novel abstract representation that projects sparse, history-aware candidate waypoints directly onto RGB images as visual markers. The MLLM selects a waypoint or generates a fallback target bounding box at each step, while a low-level Fast Marching Method (FMM) planner converts the selected target into an executable collision-free path. This paradigm provides the model with concrete spatial perception and explicit memory while significantly reducing the visual processing load. Extensive evaluations on the R2R-CE and RxR-CE benchmarks demonstrate that O2C-Nav outperforms current state-of-the-art zero-shot methods, highlighting its great potential for real-time robotic deployment. Code is available at https://github.com/kkpsq/O2C-Nav-Code. --- ### Thinking with Cameras: Active Visual Reasoning via Dynamic Viewpoint Control for Surveillance Video Understanding Authors: Xiao Zhang, Wang Zeng, Sheng Jin, Wentao Liu, Chen Qian, Shichao Kan Published: 2026-09-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06475v2 Large vision-language models (LVLMs) have recently achieved remarkable progress in general-purpose video understanding. However, their application to real-world surveillance remains challenging due to the lack of large-scale domain-specific datasets and the limitation of passive observation from fixed viewpoints. In surveillance scenarios, critical visual evidence can be easily missed when targets are distant, small, occluded, or move beyond the current camera view. In this work, we introduce CamVLM, a new framework for Thinking with Cameras, which enables LVLMs to actively acquire visual evidence in real-world surveillance by continuously controlling camera viewpoints. We first construct CCTV-Anomaly, a large-scale surveillance video understanding dataset containing 14,133 videos across 10 anomaly categories, with detailed captions and event annotations. We further formulate viewpoint control as an active visual perception problem and build CamTrack-53K, an object-centric viewpoint trajectory dataset for learning camera actions. Moreover, we propose a reinforcement learning based viewpoint policy optimization framework, which models camera control as a sequential decision-making process and learns long-horizon observation strategies beyond supervised trajectory imitation. Extensive experiments demonstrate that CamVLM achieves state-of-the-art performance under both passive observation and dynamic viewpoint settings, validating the effectiveness of active camera-based reasoning for surveillance video understanding. Our datasets, model, and code will be available at https://github.com/xiaozhang79/CamVLM. --- ### Learning Kernels by Alignment for Multiclass Bayes Classification Authors: Hollan Haule, Javier Escudero Published: 2026-09-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06474v2 Kernel methods separate data representation from decision-making, but typically require the kernel to be chosen in advance. We show that this kernel can instead be learned by alignment, and develop the resulting framework through the recently introduced Collaborative Learning and Inference (CLaI). We show that Collaborative Learning can be viewed as a kernel alignment process, in which an embedding is trained so that its induced similarity matches a label-derived target kernel. We also prove that Collaborative Inference is equivalent to kernel Bayes classification with Parzen-window density estimation. Motivated by these perspectives, we generalise CLaI by replacing cosine similarity with a learned Mahalanobis distance and extend it to multiclass classification. On CIFAR-10, PathMNIST, and SleepEDF, the Mahalanobis formulation improves accuracy, converges faster, and yields lower calibration error than the cosine-based variant. Auxiliary experiments further support these connections, showing that CLaI produces latent signals of the same form as a Gaussian process, while achieving competitive calibration on sepsis prediction. Together, these results establish a principled learned-kernel framework that unifies representation learning, kernel alignment, and Bayesian classification, and extends naturally to the multiclass setting. --- ### Steering Under Compression: Dose-Response, Capability Cost, and Failure Asymmetry in Quantized LLMs Authors: Saurav Bhandari, Benjamin Wade Published: 2026-09-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06473v1 Inference-time activation steering enables behavioral control of large language models without parameter modification, while post-training quantization reduces memory and compute costs for deployment. Despite their growing convergence in practice, the interaction between these two techniques remains uncharacterized. We systematically study activation steering under weight-only quantization (INT8 and NF4) across four open-weight 7-9B models and two behavioral targets: judged sentiment and judge-free reasoning length. Using an iso-effect framework that compares capability costs at matched behavioral effect, we find that sentiment steering survives quantization intact. After correcting a GSM8K parser artifact with a uniform v2.3.1 rescore, the pooled INT8 contrast is -0.010 (90% CI (-0.026, +0.007)), descriptively Equivalent under the preregistered three-label rule, while NF4 remains Inconclusive at -0.017 ((-0.067, +0.033)). In contrast, reasoning length exhibits a surprising asymmetric dose-response: lengthening is graded but terminates in cap-runaway and collapse, while shortening is a step function with only 12-30% shortening (model-dependent) before discontinuous failure. We expose a methodological pitfall: the naive iso-effect ladder anchors on the collapse floor for floor-bounded targets, and we introduce a censored construction that restores interpretable crossings. We also quantify a substantial baseline capability shift for Mistral-NF4 (0.545 to 0.365 GSM8K at alpha=0), demonstrating that compression can dominate the steering intervention. Despite this, steering vectors remain highly collinear with their FP16 siblings (cosine similarity 0.989-0.998 for INT8, 0.945-0.990 for NF4), confirming that the behavioral direction survives quantization even when the cost structure does not. All code and data are released. --- ### A Group-Based Resource Allocation Model for the Fractional Knapsack Problem Authors: Abhinaba Chakraborty Published: 2026-09-06 Categories: cs.DS, cs.CL arXiv: https://arxiv.org/abs/2609.06470v3 To solve the fractional knapsack problem, Dantzig's greedy rule orders items according to their value-to-cost ratio. This ordering introduces priority issues. An arbitrarily small perturbation to the input can change the allocation if the budget is exhausted between two items with very similar ratios. To mitigate that problem, we introduce a two-stage rule. We group items sharing attributes within a radius $δ$. We then evaluate these groups in descending order of ratio and divide their group's budget share without further ranking. Consider a group featuring an aggregate capacity $U_G$, unit costs contained in $(w^-,w^+)$, and a representative value $\widehat{v}$. The group's loss relative to the exact optimum is bounded by $\widehat{v}\, U_G\frac{w^+-w^-}{w^++w^-}+\varepsilon_v U_G$, where $\varepsilon_v$ limits the group's internal value variation. Moreover, this harmonic factor remains tight for any group size. The overall loss becomes restricted to the single budget-binding group whenever the grouping remains order-compatible; thus, groups containing at most $K$ items suffer a per-item loss of $\mathcal{O}(\frac{K}{n})$. Should group ratio intervals exhibit an overlap of at most $ω$, an additive term $ωC$ degrades this bound. Within the separation margin between adjacent groups, the grouped allocation remains Lipschitz continuous with respect to cost data, exhibiting a modulus of $\frac{K}{w_{\min}}$. Computing this allocation takes $\mathcal{O}(n+m\log m+|Γ|\log|Γ|)$ time given $m$ groups and a boundary group $Γ$. Alternatively, the time complexity drops to $\mathcal{O}(n+m\log m)$ if a linear-time selection method identifies the boundary group's allocation. --- ### One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control Authors: Zihan Lin, Xiaohan Wang, Jie Cao, Jiajun Chai, Guojun Yin, Wei Lin, Ran He Published: 2026-09-06 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.06469v1 Reinforcement learning (RL) across multiple domains can broaden the reasoning capabilities of large language models (LLMs), yet joint training often degrades individual-domain performance and can destabilize optimization. Existing work typically diagnoses such interference from a single-step view using first-order gradient alignment or curvature-based proxies. We show that this view can miss a critical form of sequential interference: same-point domain gradients may remain nearly orthogonal even when consecutive realized updates partially reverse one another in output space. We further show that consecutive token log-probability footprints recover this interaction directly from adjacent checkpoints as a local second-order interaction in output space, without explicitly reconstructing same-step curvature. Building on this insight, we propose OSOL, which designates a focus domain at each iteration, uses the preceding checkpoint footprint to rank token-level rebound risk, and applies a drift-ranked, adaptively scaled correction within the standard GRPO update. Our analysis shows that this correction suppresses the targeted cross-step output backtracking component. Controlled studies further show that cross-step backtracking is more strongly associated with subsequent task damage than same-point gradient diagnostics, while the preceding footprint ranks future rebound risk more accurately than Hessian-based proxies. On Qwen3-30B-A3B, OSOL reaches a domain-macro average of 0.4822, improving by 5.7% over the strongest compared baseline, without explicit higher-order differentiation. --- ### Sector-Mean: Deterministic Initialization of K-Means Centroids via Angular Sector Partitioning Authors: Abhiyan Dhakal, Pranish Kafle, Rajani Chulyadyo Published: 2026-09-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06468v1 K-Means is one of the most widely used clustering algorithms, but its susceptibility to initial centroid selection remains a primary bottleneck for its convergence speed and clustering accuracy. This paper proposes Sector-Mean Initialization, a deterministic initialization strategy with O(N) time complexity that partitions the two-dimensional data space into angular sectors around the global centroid and initializes centroids using sector-wise means. We evaluate the method on established two-dimensional benchmarks (SIPU, Birch) and multiple real-world datasets, comparing against random, K-Means++, and Max-Min initialization under identical Lloyd iterations. The statistical analysis of Friedman's test (p<0.05) and Nemenyi post-hoc comparison indicates that, while delivering equivalent clustering quality as K-Means++ and Max-Min, Sector-Mean offers significant computational efficiency. Experimental results show that Sector-Mean reduces the initialization time by 74.9% and 59.8% in comparison to K-Means++ and max-min, respectively. And, it yields the lowest average number of iterations, achieving approximately 5% fewer iterations than K-Means++ and 16% fewer than max-min. These results highlight that Sector-Mean initialization offers a deterministic and computationally efficient initialization strategy while preserving cluster quality. --- ### Local and Global Stability in Performative Reinforcement Learning Authors: Debmalya Mandal Published: 2026-09-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06467v1 In performative reinforcement learning the deployed policy shapes the environment that generates the learner's future data, and the natural solution concept is a performatively stable policy that is optimal in the environment it induces. Existing convergence guarantees rely on Lipschitz sensitivity assumptions on the environment map $π\mapsto (P_π, r_π)$, which are hard to verify and fail in settings such as multi-agent best-response dynamics. We instead study stability for mixtures of policies, and show that the resulting picture is fundamentally different from performative prediction, where randomization removes the need for any sensitivity assumption. We distinguish local mixed stability, an occupancy-weighted first-order relaxation that we show is equivalent to stationarity, from global mixed stability, which certifies against arbitrary deviating policies. Our first result is that a weighted per-state Hedge dynamic drives the local stability gap to zero at an $O(1/\sqrt{T})$ rate for an arbitrary, possibly discontinuous, environment map, both with exact and with trajectory feedback. The two notions genuinely differ: we exhibit an instance where local stability is achieved exactly but every mixture has global stability gap bounded away from zero. For global stability we introduce a bounded transition range assumption, strictly weaker than Lipschitz sensitivity, under which unweighted per-state Hedge converges up to a floor of $O(γε_P/(1-γ)^3)$, and we prove a matching-in-$ε_P$ lower bound of $Ω(γε_P/(1-γ))$ under trajectory feedback, so this floor is unavoidable. Finally, we extend both notions to $n$-player performative Markov games, obtaining local stability with no assumption on the joint environment map or game structure, and global stability for performative Markov potential games. --- ### A Theoretical Framework for Masked Pretraining (MPT) Authors: Qi Zhang, Runyu Zhou, Yifei Wang, Yisen Wang Published: 2026-09-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06460v1 Recently, Masked Pretraining (MPT) based on reconstruction pretraining tasks has risen to a promising self-supervised learning paradigm across various domains and achieves remarkable performance in multiple downstream tasks. However, the theoretical understanding of the working mechanism behind MPT is still limited. In this paper, we introduce a new theoretical framework to analyze MPT and understand the crucial role of masking in extracting meaningful representations. We establish theoretical connections between MPT and another popular self-supervised paradigm: contrastive learning. We prove that the masking technique implicitly creates positive pairs that are semantically similar and the reconstruction loss pulls them together in the feature space. Besides, as a result of the implicit alignment, we point out the dimensional collapse issue of MPT and propose a Uniformity-enhanced MPT (U-MPT) loss that can effectively address this issue and bring significant improvements in downstream tasks including linear evaluation, cross-dataset fine-tuning and out-of-distribution generalization on real-world data sets. Furthermore, we establish downstream guarantees of U-MPT and theoretically analyze the influence of masking strategies. Based on the theoretical analysis, we propose a new masking strategy which enhances the downstream performance of MPT and explains current improvements of masking strategies with our theoretical perspective. --- ### Phase-cycled randomized benchmarking of quantum processors: recovering hidden classical noise correlations Authors: Mirza Samad Ahmed Baig, Syeda Anshrah Gillani, Abdul Akbar Khan, Muhammad Omer Khan Published: 2026-09-06 Categories: cs.ET, cs.CL, cs.DC arXiv: https://arxiv.org/abs/2609.06448v1 Randomized benchmarking can hide classical temporal correlations because its Clifford-twirled response is even in the noise phase. For a stationary symmetric telegraph fluctuator, we show that continuous evolution and independent stationary resets at slot boundaries yield identical mean responses for arbitrary fixed idle modulations. We construct an eight-setting phase-cycle measurement of the connected sine-phase covariance under ideal Clifford twirling and classical idle dephasing. This observable vanishes for independent slot noise and fixed detuning without a weak-phase or Gaussian approximation. A closed telegraph response, independent circuit calculations and 800 simulation trials validate the construction and quantify the empirical coverage of a paired bootstrap estimator. A separate conservative confidence set states its finite-sample assumptions. Two acquisitions on an IBM processor compare engineered shared-sign and independently reset phases with identical marginals. Their primary contrasts are 0.254 and 0.211, with empirical 95% intervals (0.177, 0.331) and (0.136, 0.285), respectively; all negative-control intervals include zero. At equal shot and sensingwindow budgets, an ideal Ramsey/echo estimator is more precise in every tested class. The result supplies an explicit connection between a benchmarking identifiability limitation and a controlled correlation measurement. No native or quantum-memory detection is claimed. --- ### Causal Attribution for Agentic Decisions: Estimators, Coupling, and a Traceability Specification Authors: Ajay Pravin Mahale Published: 2026-09-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.06445v1 A provider of a high-risk AI system must keep records that make a decision traceable, and for agentic systems it has not been established what those records must contain for post-hoc causal attribution to be possible. We give the estimator framework and then the conditions under which it fails. We separate the marginal total effect that prior work measures from a common-random-numbers total effect that isolates a step's own contribution, add the natural direct effect under a pinned downstream, and check the estimators against hand derivations. Both estimands then fail, in the same direction. Under the marginal estimand a causally inert step has the identical total effect to the decisive one on every run of our planted chain, an algebraic identity and not a coincidence at one draw. Under common random numbers the decisive step returns exactly zero on the runs where the executing step flips, about one in ten, while its direct effect there is 0.25 and it demonstrably acts; an exact zero does not certify that a step did nothing, and we put that here rather than in the limitations. We derive the coupling that keeps the direct effect estimable once contexts diverge, with a closed form for its degradation, and show that the mediated share on which a natural ranking is built is not a share under suppression: where the direct and mediated paths oppose, it exceeds one and ranks a suppressed component above a pure mediator. We publish the discrepancy experiment's pre-registration rather than a result, because the live pipeline it requires was not available in the study window. We contribute the traceability specification such a filing would need, against a gap the Act's calendar opens: Article 86's right to an explanation has applied since 2 August 2026, while the Article 12 logging and Annex IV documentation that could evidence one were deferred to 2 December 2027 by Regulation (EU) 2026/1744. --- ### Decomposing LLM-Judge Uncertainty to Target Expert Labels Authors: Ryan Lail Published: 2026-09-06 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.06444v3 An LLM judge evaluates outputs at scale. Experts should label only where it is least sure. Its natural escalation signal conflates two uncertainties: aleatoric, real disagreement in the expert pool, which labels cannot reduce, and epistemic, the judge's ignorance, which labels do reduce. A small Bayesian model separates them: a regression on labels already collected learns how far to trust a black-box judge's prediction. Both components follow as simple formulas, with no sampling or further judge calls. The components isolate on a real LLM judge against exactly known truth, and stated confidence is no guide to its actual error. On real human disagreement (ChaosNLI) the epistemic ranking removes 83% more error than total uncertainty for the same expert labels, though simply escalating the least-labelled items does as well there. We demonstrate we can estimate where a judge is ignorant rather than where experts genuinely disagree, and propose using this to direct expert labelling. Code and data are available at https://github.com/composo-ai/judge-uncertainty-decomposition. --- ### InsightChain: Optimized Chain-of-Insight Analytics for LLM-driven Data Visualization Authors: Hanya Sun, Chen Zhang, Sheng Liang, Yongyue Zhang, Yong Liu Published: 2026-09-06 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2609.06438v1 Large language models (LLMs) are increasingly used for automated data visualization, yet existing approaches often frame visualization generation as a single-step mapping from user query to figure or code, overlooking the iterative analytical reasoning process of expert analysts. We present InsightChain, a four-stage visualization prompting pipeline (Explore--Focus--Test--Present) that emulates expert analytical workflows, together with VG-COPRO, a vision-guided automatic prompt optimization (APO) method adapted to jointly optimize such multi-stage, executable pipelines. To address the evaluation gap for complex data visualization, we introduce the Insight Progression Metric (IPM), a rubric combining four text-based dimensions with a vision-based dimension. We assess IPM through a 100-chain human pilot and an expanded 300-chain agent-based evaluation spanning all ten domains. Experiments on public datasets show that InsightChain consistently outperforms competing prompting baselines. Existing APO methods fail to yield consistent gains on this multi-stage task, whereas VG-COPRO improves performance in both in-domain and cross-domain settings. --- ### Large-Scale Pretraining for Improving Deep Learning-Based Geometric Distortion Correction of Diffusion-Weighted Imaging Authors: Saroj Khanal, Yashawant Kumar Yadav, Kritam Bhattarai, Jeevan Neupane, Shristi Subedi, Saship Gwachha, Manish Kumar Tiwari, Dong Zhang, Confidence Raymond, Aondona Moses Iorumbur, Udunna Anazodo, Surendra Maharjan et al. Published: 2026-09-06 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.06437v1 Diffusion-weighted imaging (DWI) is widely used in clinical settings but remains vulnerable to geometric distortion. Conventional correction methods often require additional acquisitions or vendor-specific solutions, limiting their feasibility in high-throughput, resource-constrained settings. This study investigates whether large-scale pretraining strategies can improve deep learning-based distortion correction for single-phase-encoding DWI. We formulate the task as image reconstruction, and compare a non-pretrained baseline against a self-supervised and a generative pretrained model, evaluated using both quantitative image-similarity metrics and qualitative expert assessment. The best-performing model was further tested for transferability on data collected in an LMIC setting with acquisition shift. Pretrained models outperformed the non-pretrained baseline, with cWDM achieving the strongest results across both quantitative and qualitative evaluation. However, application to LMIC data revealed transferability challenges, including contrast alteration and over-reliance on T1-weighted anatomical structure. Registering images to a common standard space improved predictions, suggesting that harmonized preprocessing may enhance cross-domain deployment. --- ### PLSR: Progressive and Localized Super-Resolution of 3D Objects via Localized Latent Voxel Diffusion Authors: Yuxin Liu, Minshan Xie, Jiawen Liang, Runsong Zhu, Chi-Wing Fu, Tien-Tsin Wong Published: 2026-09-06 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.06436v2 High-resolution 3D asset generation is vital in various 3D applications. Existing state-of-the-art diffusion-based models remain constrained by fixed resolutions, limiting their ability to produce details. In this paper, we tackle the challenge of generating more detailed, higher-resolution 3D objects by introducing a 3D super-resolution (SR) framework built on existing 3D generative foundation models. To this end, we design PLSR, a progressive and localized super-resolution solution to achieve this goal effectively and memory efficiently. Technically, given a coarse geometry from a pretrained 3D generator, we decompose the global SR task into localized sub-tasks via an associative input decomposition scheme, adapt a flow-based 3D generator into a localized super-resolution model through low-cost finetuning, and unify them in an iterative patch-wise denoising pipeline for seamless high-resolution output. Experiments on challenging objects show that our approach is able to generate 3D details with new strong fine-detail fidelity while significantly reducing the computational cost, offering a new and practical solution for high-resolution 3D asset generation. --- ### Collision Snapshot Guided Time-Reversed Safety-Critical Scenario Generation Authors: Taehyung Kim, Jongeun Choi Published: 2026-09-06 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.06433v1 The generation of safety-critical traffic scenarios is essential for training and evaluating autonomous vehicles. Prior approaches typically perturb the trajectories of existing agents in a traffic scenario using simplified adversarial objectives to induce safety-critical interactions, which can limit the plausibility and diversity of the generated scenarios. Although inserting new adversarial vehicles can alleviate this limitation, determining when and where to introduce them in a scenario-specific manner remains challenging. In this work, we introduce \underline{CO}llision \underline{S}napshot guided \underline{T}im\underline{E}-\underline{R}eversed safety-critical scenario generation (COSTER), a framework that leverages learned traffic priors to determine plausible collision times and locations. COSTER first constructs a collision snapshot by inserting a new vehicle in contact with the target vehicle at the identified collision state within a traffic scenario. Starting from this collision snapshot, a conditional variational autoencoder is used to perform a time-reversed rollout, reconstructing the trajectory of the inserted vehicle backward toward earlier timesteps. Experiments show that COSTER outperforms existing methods in plausibility, diversity, and data efficiency. Moreover, agents trained on COSTER-generated scenarios reduce collision rates by 31\% on safety-critical scenarios from the Waymo Open Motion Dataset while also improving ego task completion. The project website is available at https://anonym-121.github.io/COSTER/. --- ### Stability and Generalization of Straight-Through Estimators for Training Two-Layer Quantized Neural Networks Authors: Yiming Ying Published: 2026-09-06 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.06430v1 We study the identity straight-through estimator (STE) for training a two-layer binary-activation network with hinge loss from the perspective of Statistical Learning Theory (SLT). Our central question is whether algorithmic stability can explain the statistical generalization of the estimator produced by the discontinuous STE training rule. In the saturated-output regime, the zero-initialized samplewise STE recursion is exactly the stochastic subgradient descent on the convex latent loss $(-yu^\top x)_+$. This representation makes a stability analysis possible. We derive an exact distance identity for two coupled updates and prove approximate non-expansiveness of the common-example map, with a quadratic defect only when the two latent margins straddle zero. We then obtain explicit $\ell_2$ on-average model-stability and generalization bounds, transferring stability isometrically from the latent vector to the full first-layer matrix. Combining stability with a standard optimization bound yields an explicit excess induced-risk guarantee and the rate $O(n^{-1/2})$ when $T=n^2$. Under margin separability, a complementary argument gives the optimal-order $O(R^2/(γ^2n))$ expected excess misclassification error for a randomized one-pass STE iterate and a corresponding majority-vote bound. --- ### Sparse Oblique Rule Boosting for Simpler Additive Rule Ensembles Authors: Shahrzad Behzadimanesh, Pierre Le Bodic, Geoffrey I. Webb, Mario Boley Published: 2026-09-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06426v1 Small additive ensembles of symbolic rules offer interpretable prediction models. Traditionally, these ensembles use rule conditions based on conjunctions of simple threshold propositions $x \geq t$ on a single input variable $x$ and threshold $t$, resulting geometrically in axis-parallel polytopes as decision regions. While this form ensures a high degree of interpretability for individual rules and can be learned efficiently using the gradient boosting approach, it relies on having access to a curated set of expressive input features so that a small ensemble of axis-parallel regions can describe the target variable well. Absent such features, reaching sufficient accuracy requires increasing the number and complexity of individual rules, which diminishes the interpretability of the model. Here, we extend classical rule ensembles by introducing logical propositions with learnable sparse linear transformations of input variables, i.e., propositions of the form $\mathbf{x}^T\mathbf{w} \geq t$, where $\mathbf{w}$ is a learnable sparse weight vector, enabling decision regions as general polyhedrons with oblique faces. We propose a learning method using gradient boosting based on a weighted logistic regression. Empirical results across 14 regression and classification tasks demonstrate that the proposed method achieves lower model complexity than competitive baselines while maintaining similar or better predictive accuracy. Hence, the approach provides a favorable trade-off between interpretability and accuracy and reduces the reliance on manual feature engineering. --- ### On BatchNorm Forward Modes in Value-Based Reinforcement Learning Authors: Daniel Palenicek, Mikael Henaff, Scott Fujimoto, Koustuv Sinha Published: 2026-09-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.06421v1 Batch normalization (BN) substantially improves sample efficiency in continuous-control actor-critic methods such as CrossQ, yet recent studies report performance degradation in discrete-action value learning on Atari. These failures are surprising because discrete Q-networks lack the action-input distribution mismatch identified by CrossQ. We show for target-based C51 and target-free PQN that the simple choice between running and batch statistics at specific forward passes can reverse this degradation. In C51, switching the BN bootstrap forward to batch-statistic mode significantly improves performance over unnormalized and LayerNorm baselines and scales stably with update-to-data ratios up to 12. In PQN, using batch-statistics for both action selection and bootstrapping recovers performance from the failing running-statistic configuration. Across 26 Atari games at 400M frames, this configuration achieves a higher final aggregate score than PQN with LayerNorm. Our results show that carefully configured BN can substantially improve discrete-action value learning, and that its forward protocols are an essential part of the algorithm specification. --- ### Separating Capability from Confidence: Grounded Dual-State Calibration for GRPO-Trained Medical Vision-Language Models Authors: Yangyang Xie, Ke Hao, Jiaqi Liu, Yun Gu, Xinglin Zhang Published: 2026-09-06 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.06419v1 Medical vision-language models (VLMs) require confidence that reflects both answer correctness and patient-specific visual evidence. Recent GRPO-based methods optimize verbalized confidence together with answer generation. However, this joint optimization may interfere with answer learning and drive confidence toward near-binary values. Verbalized confidence also provides no explicit assessment of visual support. We therefore separate capability learning from confidence estimation and propose \textbf{DualRead}. DualRead builds on the insight that reliability can be read from the actor's internal states at critical moments in the answering process. It freezes the GRPO-trained actor and combines pre-answer solvability with a post-answer assessment of the generated answer and its visual support. To further assess whether confidence reflects visual grounding, we introduce \textbf{Counterfactual Confidence Grounding AUC} (CCG-AUC). It measures whether confidence decreases when real-image substitution changes the actor from correct to incorrect. Across two VLM backbones and both in- and out-of-distribution medical VQA benchmarks, DualRead improves correctness discrimination and calibration over verbalized confidence while preserving answer accuracy. CCG-AUC reveals whether confidence responds to answer-relevant visual evidence rather than primarily to non-visual cues. --- ### Visual Search Augmented Chain-of-Thought Reasoning for Attribute Value Extraction from Product Videos Authors: Tong Wu, Ming Cheng, Jiazhen Hu, Jiaying Gong, Hoda Eldardiry Published: 2026-09-06 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2609.06410v1 Existing approaches to visual attribute value extraction (AVE) primarily rely on static product images, failing to capture temporal cues, multi-angle views and fine-grained visual details. Directly applying video vision-language models (VLMs) to product AVE results in limited performance due to the lack of domain knowledge, and fine-tuning them requires extensive high-quality data and substantial computational resources. Thus, we propose visual search augmented chain-of-thought reasoning (ViS-CoT), a training-free, plug-and-play pipeline that can be easily applied to any open-source video VLM for video-to-text AVE in e-Commerce. Specifically, ViS-CoT employs visual clustering to identify representative frames, followed by visual search to retrieve semantically similar product knowledge that can enrich attribute cues. Next, an interleaved CoT reasoning module iteratively refines reasoning through visually-aligned auxiliary texts derived from captioning and automatic speech recognition. Finally, the integrated information guides the model toward accurate and fine-grained attribute predictions. Extensive experiments across 14 product categories on the VideoAVE dataset show that ViS-CoT consistently enhances multiple state-of-the-art video VLMs, achieving an average improvement of 17.91 percentage points in micro-F1. --- ### Hierarchical Wasserstein Merging for Multi-Domain Multi-Task Learning: From Specialists to a Generalist Authors: Ming Cheng, Jiaying Gong, Hoda Eldardiry Published: 2026-09-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.06406v1 Multi-domain multi-task learning (MD-MTL) aims to build a single generalist model that performs well across heterogeneous domains and tasks. However, joint training often suffers from interference under distribution shifts. Existing model merging methods mostly operate on model parameters while overlooking the geometric structure of latent representation distributions across domains and tasks. To address these limitations, we propose Hierarchical Wasserstein Merging (HWM), a representation-level framework that models each domain-task specialist as a distribution of hidden representations on a shared support. HWM constructs task-level and global Wasserstein barycenters to capture within-task domain variation and cross-task structure, enabling either training-free specialist aggregation by Wasserstein-derived weights or training-based generalist learning through a hybrid Wasserstein alignment loss. Experiments on four NLP tasks across four domains per task show that HWM achieves superior effectiveness and generalization capability in MD-MTL settings. --- ### From Concentration to Differentiation and Back: Routing Effective Rank in MoE Reasoning Cohorts Authors: Kang Chen, Sihan Zhao, Yixin Cao, Yu-Gang Jiang Published: 2026-09-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.06403v1 Test-time scaling produces cohorts of reasoning rollouts, yet there is no standard label-free account of how their internal computation reorganizes as inference unfolds. We introduce routing effective rank deff, the entropy-effective dimensionality of a cross-rollout graph built from MoE expert-routing similarity. Across ten MoE configurations and five math/science benchmarks, deff exhibits a reproducible low-high-low trajectory, with a prominent interior maximum in 98.5% of 3,105 model-question cohorts: routing similarity is concentrated early, maximally differentiated at intermediate budgets, and reconcentrated later, and the timing of this maximum varies systematically with architecture and reasoning effort. An exact decomposition separates cohort-wide common-mode mass from residual spectral dimensionality: common-mode reallocation accounts for about two thirds of the trajectory, while the residual spectrum contributes about one quarter and retains substantial variation beyond the common mode. The decomposition further localizes behavior: among non-unanimous cohorts, increases in common-mode concentration strongly predict same-answer recoverability, and higher reasoning effort delays the maximum by 2.59 octaves (doublings of the token budget) and consistently expands the high-rank period across all four tested architectures, locating the effort effect in timing and duration rather than peak amplitude. Correctness comparisons separate structural monitoring from answer selection, positioning routing effective rank as a decomposable, label-free diagnostic of cohort organization - a principled spectral lens on how MoE reasoning cohorts differentiate and reconcentrate over inference time. --- ### MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves Authors: Zihan Tan, Leixin Sun, Zitong Shi, Yitao Liu, Jiajun Wu, Nathaniel Brooks, Jiaru Qian, Xiaoran Shang, Suyuan Huang, Yi Ding, Yangxu Liao, Mukai Li et al. Published: 2026-09-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06396v2 Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet RSI has been validated almost exclusively on coding and formal benchmarks such as science QA and mathematics. This format bound limits RSI to improvement within a machine-checkable slice, not general capability where questions are open and correctness is settled by argument, replication, or measurement. We argue RSI must next operate across real, diverse scientific, engineering, and meta-scientific domains, not where formal evaluation is merely tractable. To that end we present MetaRSI-v1, where improvement is the scheduled composition of three typed operators over one unified paradigm. Data-RSI amplifies existing competence and marks its boundary; Harness-RSI edits a five-slot scaffold without touching weights; Model-RSI internalizes capability into parameters through bounded training. Sharing one loop kernel and artifact vocabulary, they make data, scaffold, and model changes composable rather than exclusive. A two-axis optimizer jointly decides operator order and each operator's proposal policy, while a meta-level policy revises the schedule across terms. We validate MetaRSI-v1 under the field's standard evaluations, on code and closed-form science, with no external teacher: the target model plays every role in its own loop. MetaRSI-v1 reframes self-improvement from a single-surface edit to a composition across the full model-production pipeline, opening two paths: a model route internalizing capability through training, and a harness route leaving weights untouched and thus extending self-improvement to any model reachable through an interface, with Data-RSI redefined as the shared substrate feeding both. The framework further yields refutable laws on where loops exist, how operators compose, and what supervision buys. --- ### Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling Authors: Diptarka Chakraborty, Satyaki Mukherjee, Gaurav Vallabhdas Revankar, Hoang-Son Tran Published: 2026-09-06 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2609.06394v1 Massive datasets in modern machine learning have made data reduction a central challenge, particularly for clustering tasks where memory and computational constraints demand compact yet faithful summaries. A standard approach is to construct an \textit{$ε$-coreset}: a small weighted subset that approximately preserves the clustering cost for every plausible choice of centers. For the \textit{$(k,z)$-clustering problem}, existing worst-case bounds on coreset size are essentially tight, ruling out substantially smaller coresets in general. However, such worst-case instances are often unrepresentative of real-world data. In this work, we show that significantly smaller coresets are possible under mild and natural assumptions on the underlying data distribution. We introduce a new correlated sampling framework, called \textit{determinantal sampling}, based on a novel application of determinantal point processes. Using this framework, we obtain an efficiently constructible $\varepsilon$-coreset for $(k,z)$-clustering in $\mathbb R^d$ whose dependence on $1/\varepsilon$ has exponent strictly smaller than $2$ when $d$ is fixed. This improves over the worst-case $\varepsilon^{-2}$ barrier under our beyond-worst-case assumptions. To the best of our knowledge, this is the first result that provably surpasses these lower bounds through beyond-worst-case assumptions. Finally, we validate our approach on synthetic and real-world benchmark datasets, where it consistently achieves smaller coresets than existing state-of-the-art methods, even without explicitly enforcing the assumptions used in the analysis. ---