# Research Papers — 2026-08 · bundle page 175 of 240 > Full-text markdown of papers #8701–8750 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/175 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/174.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/176.md) ### Effect of Abstractions and Prompting Strategies on LLM-Guided High-Performance Optimizations Authors: Jiří Klepl, Matyáš Brabec, Martin Kruliš Published: 2026-08-08 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2608.08085v2 Code performance optimization is a vital aspect of modern software development, as it enables faster response times and reduced resource usage. These optimizations require a deep understanding of low-level hardware details and the intricacies of parallel processing, making them challenging even for experienced developers. With the advent of Large Language Models (LLMs), which are increasingly capable of generating and understanding code, there is growing interest in incorporating these models into automated code optimization processes. Traditionally, this automation involves transcribing the source code into a domain-specific representation that can be auto-tuned using grid search or machine learning algorithms, while adhering to strict rules and a limited set of feasible transformations to ensure verifiability. LLMs incorporate high-level code semantics and can thus perform transformations that go beyond verifiable automated optimizations. This paper investigates whether the traditional abstractions used in automated code optimization improve the performance and correctness of LLM-guided optimizations of parallel HPC applications. We evaluate this using the PolyBench benchmark suite and demonstrate that, in our evaluated setting, LLMs provided with specific optimization goals achieve better measured performance and validity rates when generating C code compared to creating computation pipelines and optimization schedules with established frameworks, suggesting that future development should explore alternative approaches for verifiable LLM-guided code optimization. --- ### Commitment Before Realization: When Classifier-Free Guidance Becomes Unnecessary in Masked Diffusion Language Models Authors: Fan Zhou, Weitian Wang, Tim Van de Cruys Published: 2026-08-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.08082v1 Classifier-free guidance (CFG) is usually kept on throughout masked diffusion language model decoding, although its benefit varies across prompts and over time. We study when CFG is actually needed by comparing, from any partial output, the probability of eventual constraint satisfaction under continued CFG and under base-only continuation. Their difference defines the remaining value of guidance. Guidance dependence is highly prompt-specific. Many prompts already succeed without CFG, while for others it provides no measurable benefit or can be harmful. For prompts that do benefit, the gain is often concentrated early. We define the commitment horizon $\astar$ as the earliest point from which switching all remaining decoding to the base model reduces final success by no more than a chosen tolerance. Under the base model, the corresponding success probability, or committor, is a martingale. To first order, CFG's per-step effect is governed by the covariance between the guidance logit direction and the successor committor. This gives a local account of when guidance can help, but it does not by itself locate the horizon. Among prompts with an observed preterminal horizon, $\astar$ is usually early and varies more within constraint families than between them. Freezing each prompt at its own cross-fitted horizon is noninferior to full CFG on all 13 subtasks at the prespecified margin, even while many tokens remain masked. This separates commitment from realization. The boundary also identifies a later region in which higher parallelism adds only a small cost in constraint success, although fluency still degrades with parallel width. For failed trajectories, reopening committed positions improves recovery in both failure modes. --- ### RotaryQuant: Fitting 120B MoE Models on Consumer Hardware via Fused Compressed-Space Attention Authors: Anthony. Lui, Mohamed. Elsaied, N. P. Savani Published: 2026-08-08 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2608.08081v1 Large mixture-of-experts (MoE) language models with 26--120 billion parameters exceed the memory capacity of consumer devices through three simultaneous pressures: resident weight matrices, key-value (KV) cache state that grows linearly with context, and dozens of expert sublayers that must be paged on demand. We present RotaryQuant, a three-axis compression system that addresses all three. Mixed-precision weight quantization assigns bit-widths by architectural role: 4-bit for dense layers, 2-bit for routed experts, and 8-bit for the shared expert whose high activation kurtosis resists aggressive compression. LRU expert offloading pages non-resident experts to disk under genuine memory pressure. The novel axis is IsoQuant, a KV cache compression method that applies a Walsh--Hadamard transform followed by block-diagonal SO(4) rotations to isotropize activation distributions before 3-bit scalar quantization, requiring $O(d \log d)$ operations and 256 stored parameters per head versus $O(d^2)$ and 16{,}384 for dense rotation methods. A fused four-kernel Metal GPU pipeline performs attention directly on packed 3-bit tensors without materializing full-precision KV state---a different execution model, not just a quantization scheme. The combined system fits Gemma 4-26B-A4B and Qwen3-30B-A3B within a 16\,GB budget and Nemotron-H 120B within 32\,GB, running interactively at 9--19 tok/s with near-zero perplexity degradation ($Δ$PPL $\leq +0.0012$) and 100\% retrieval accuracy at 32K context. --- ### PATH: Next-Interval Prediction via Autoregressive Tree Hierarchy on Tabular Data Authors: Pengxiang Cai, Wanchen Lian, Chenyang Liu, Xiaohan Li, Qingyuan Zeng, Jinhong Wang, Jintai Chen Published: 2026-08-08 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.08078v1 Interval prediction aims to achieve a target coverage level while producing intervals that are as short as possible. Many conformal regression pipelines first predict an uncertainty surrogate and then convert it into an interval through calibration or selection. This separation supports coverage calibration, but post hoc rules largely determine the final interval and do not fully use the learned output distribution. We observe that the resulting intervals have inherently hierarchical geometry: an interval can be recursively refined into nested subintervals, and binary trees naturally represent this structure. We formulate this hierarchy as next-interval prediction and propose PATH, which learns how probability mass flows from each interval to its next nested subintervals. PATH predicts a base leaf distribution and uses an autoregressive decoder to refine branch probabilities. Matching the distribution to the interval hierarchy aligns learning with extraction: PATH accumulates probability over adjacent output intervals and returns the shortest contiguous range reaching a selected mass. We compare PATH with 24 baselines for interval prediction on PATHBench, comprising 56 OpenML regression datasets. PATH substantially shortens the resulting intervals, achieving the lowest mean normalized length, 0.1473, while maintaining mean coverage of 0.9144. These results establish hierarchical output modeling as an effective approach for compact interval prediction on tabular data. Code is publicly available at https://github.com/pxcai/PATH. --- ### Explore, Map, Remember, Decide: Are Embodied VLMs Ready for Safety-Critical Scenarios? Authors: Gabriele La Malfa, Nitay Alon, Emanuele La Malfa, Reuth Mirsky, Stefan Sarkadi Published: 2026-08-08 Categories: cs.AI, cs.MA, cs.RO arXiv: https://arxiv.org/abs/2608.08077v1 Theory of Space framework (ToS) assesses the spatial understanding of curiosity-driven Vision-Language Models (VLMs) under partial observability. As AI techniques are increasingly applied to safety-critical scenarios, it is crucial to understand whether VLMs possess robust spatial memory and make reliable decisions. In this paper, we assess whether VLMs' decisions are based on physical evidence or are corrupted by visual-language biases, if their memory processes align with human cognitive patterns, and how they respond to environmental hazards. We extend the ToS framework into a safety-critical, goal-driven pipeline, named Explore, Map, Remember, and Decide (EMRD). We then quantify Exploration Competence (Explore) through metrics of environmental coverage and temporal efficiency, assess Spatial Fidelity (Map), evaluate, with a suite of psychological metrics, Memory Persistence (Remember), and measure, using focal-point metrics, Cognitive Decision-Making (Decide). Our results show that in terms of decision-making capabilities, VLMs frequently select evacuation points based on pre-trained textual priors while lacking the spatial grounding to justify their choices. We also show that spatial reasoning degrades in low-light conditions, but it is not affected by texture and colour tampering. Our findings suggest that VLM memory fundamentally diverges from human cognition, creating unpredictable risks of misalignment. --- ### Search over the Visual World: Persistent Visual Memory, Layered Indexes, and Source-Grounded Evidence Authors: Sankalp Nagaonkar, Rohit Garg, Ankit Raj, Ashish Choithani, Ashutosh Trivedi Published: 2026-08-08 Categories: cs.IR, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2608.08075v1 Most video-retrieval systems assume a bounded corpus and return ranked files or timestamps. Agents operating over cameras, screens, streams, and archives face a different systems problem: observations arrive continuously; models interpret them at different temporal granularities; context must be selected without replaying the complete visual record; and results must stay connected to inspectable source evidence. We argue that search over such a corpus is an infrastructure problem that cannot be reduced to ranking video files. We develop a conceptual and formal model of search over the visual world built on analyzer-defined scenes, persistent understanding artifacts, visual memory as coexisting scene spaces over shared source time, and capability-declared indexes, distinguishing memory (everything retained), context (what is selected for a task), and evidence (the source intervals that ground it). The VideoDB data format (VDB) realizes this model in production, exposed through a typed search surface spanning planned retrieval, stateful investigation, direct access, and grounded synthesis. We contrast this model-agnostic infrastructure, where segmentation, sampling, model choice, embeddings, and ranking are system decisions and live streams are first-class sources, with video-native foundation models offered as fixed APIs. In a semantic-retrieval comparison against a commercial video-native engine spanning 9,800+ queries over four public datasets, a pipeline of general-purpose components achieves higher macro-averaged Recall@1/@3/@10 (73.09/83.39/91.20 versus 65.75/77.13/89.10), while the baseline is higher at Recall@50 (96.42 versus 96.07). Retrieval quality over the visual world is today governed more by system design than by video-specific pretraining, and visual-memory infrastructure can deliver it while keeping playable, source-grounded evidence first-class. --- ### HugSelect: An Explainable Multi-Criteria Decision-Support Framework for foundation-model selection Authors: Alireza Joonbakhsh, Arda Canser Adalı, Slinger Jansen, Farshad Khunjush, Siamak Farshidi Published: 2026-08-08 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.08069v1 Foundation models are increasingly reused as software components, making model selection a critical software-engineering decision. Current model hubs primarily support discovery through popularity metrics, often neglecting functional capabilities, operational constraints, and community-perceived quality. We argue that foundation-model selection should be treated as an explicit, auditable software-component selection task rather than as keyword search, popularity ranking, or opaque conversational advice. This paper proposes HugSelect, an explainable decision-support framework for foundation-model selection. HugSelect builds a knowledge base of 71,274 models by combining repository metadata, extracted functional capabilities, and perceived quality attributes derived from community discussions into a unified pipeline. It ranks candidate models using a weighted additive model that exposes criterion-level score decompositions. We evaluated HugSelect through pipeline validation, comparative case studies against four commercial LLM-based recommendation systems (44 scenarios), fine-grained ablation, and an exploratory user study (n = 10). Extraction pipelines achieved an F1 score of 0.801 for functional features and an accuracy of 0.84 for quality-attribute mapping. HugSelect achieved a model-level Coverage@10 of 0.61 and family-level Coverage@10 of 0.91, showing recommendation quality comparable to that of the evaluated commercial systems, with no significant overall differences in ranking quality, while providing stable, traceable, and inspectable reasoning. Ablation confirmed that functional features were the main driver of retrieval accuracy, and preliminary user feedback suggests that the framework is useful and intuitive. --- ### NeuroGuard: Neural Gradient Update Aware of Representation Damage Authors: Taigo Sakai, Kazuhito Hotta Published: 2026-08-08 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.08068v1 Long-tailed class-incremental learning (LT-CIL) must learn new classes from imbalanced streams while retaining old classes. Existing methods mainly change replay, classifiers, or losses. We study a different factor, namely how strongly the feature representation should be updated at each task boundary. We propose NeuroGuard, an update-control method added to DGR, a replay-based LT-CIL baseline, without adding learnable parameters. NeuroGuard preserves DGR's replay memory, classifier, and set of loss terms. Adaptive Gradient Scaling (AGS) converts teacher uncertainty into one task-wise gradient scale. Confidence-Ranked Knowledge Distillation Reweighting (CRK) gives larger knowledge-distillation weights to replay samples that the teacher predicts less decisively. Fragility-Blended Entropy Gate (FBE) adds old-memory leakage to the scale decision. Across five LT-CIL settings, NeuroGuard improves over DGR in every setting. In the four main benchmark comparisons, it achieves the best task-agnostic accuracy among the compared methods. The gains extend to both old- and new-class accuracy, while medium-frequency accuracy improves consistently across all five settings. Controlled comparisons show that the gain does not come from generic gradient suppression: AGS outperforms a matched fixed-scale control in all five settings, demonstrating that boundary-specific scaling is more effective than applying the same average scale throughout learning. --- ### DialectS2S: End-to-End Speech Dialogue Modeling for Low-Resource Chinese Dialects Authors: Yi Shu, Tianyu Peng, Yingzhuo Deng, Wen Yang, Jun Lin, Changming Xie, Xinyu Yu, Jiajun Zhang Published: 2026-08-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.08067v2 Current end-to-end speech dialogue models are primarily optimized for mainstream languages and remain limited in low-resource dialect scenarios due to the scarcity of dialect speech data. Moreover, during dialect adaptation, the semantic representation space of speech dialogue models continuously evolves, while conventional speech supervision remains unchanged, leading to semantic inconsistency between hidden representations and speech targets and degrading speech stability and naturalness. To address these issues, we propose DialectS2S, an end-to-end speech dialogue model for Chinese dialects. We first develop a scalable dialect speech dialogue synthesis pipeline for efficient data construction. We further introduce a two-stage post-training strategy with self-aligned speech supervision, which aligns the semantic content of speech supervision with the evolved semantic representations of the model to improve dialect speech generation quality. Experimental results show that DialectS2S consistently outperforms existing baselines across multiple Chinese dialects in speech dialogue, achieving substantial improvements in dialect consistency, response quality, and speech intelligibility. Our work provides an efficient and scalable solution for end-to-end speech dialogue modeling in low-resource dialect scenarios. To facilitate future research and practical applications, we fully open-source the DialectS2S framework, including model checkpoints, training datasets, and fine-tuning code. --- ### EvBS: Event-guided Blur Synthesis for Domain-adaptive Motion Deblurring Authors: Junsik Jung, Seokryun Choi, Yoonki Cho, Woo Jae Kim, Andrew Jeong, Sung-Eui Yoon Published: 2026-08-08 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2608.08066v1 Motion deblurring has achieved remarkable progress with deep learning, yet pre-trained deblurring models often suffer from performance degradation in real-world scenarios due to the domain shift between training and testing distributions. To remedy this, we propose EvBS, an event-guided blur synthesis framework that generates diverse training pairs for calibrating pre-trained models to the target domain. While existing methods are constrained by the inherent entanglement between motion and visual content, our method leverages the high temporal resolution of event cameras to effectively decouple them. This enables us to utilize not only the intrinsic motion that is inherent to the given content but also extrinsic motion transferred from different sources within the target domain, thereby facilitating effective adaptation via fine-tuning. Specifically, EvBS comprises two complementary strategies: Intrinsic-Blur Synthesis, which blurs sharp contents with their own motion patterns, and Extrinsic-Blur Synthesis, which transfers motion from blurry patches to distinct sharp content. This approach generates a diverse set of training pairs that break the inherent constraints of naturally coupled motion and content, resulting in enhanced domain-adaptive deblurring performance. Extensive experiments on multiple benchmarks demonstrate that EvBS effectively enhances the robustness of existing deblurring models on unseen testing datasets. --- ### CLAM: Causal Spatial Disaggregation to Infer Local Effects From Coarse Data Authors: Gerrit Großmann, Sumantrak Mukherjee, Sebastian J. Vollmer Published: 2026-08-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.08064v1 Learning fine-grained spatial patterns from coarse-resolution data is challenging, especially in causal settings where high-resolution effects must be inferred from aggregated interventions and outcomes. We introduce CLAM, a method for estimating localized causal effects from coarse observations by exploiting high-resolution contextual covariates that modulate these effects. By jointly learning the causal mechanism and a disaggregation mapping, CLAM captures interactions that are missed when addressing these problems independently. The method supports localized effect estimation, counterfactual reasoning, and principled outcome disaggregation, and reliably captures spatially varying causal effects across diverse settings. This is particularly relevant for applications such as public health and environmental policy, where decisions are made at broad scales despite substantial local heterogeneity. Code is available at https://github.com/gerritgr/clam --- ### CORDA: A Benchmark for Hierarchical Harm-Centric Moral Reasoning in Large Language Models Authors: Siddarth Singh, Victoria Williams, Simon Rosen, Ebenezer Gelo, Helen Sarah Robertson, Ibrahim Suder, Benjamin Rosman, Geraud Nangue Tasse, Steven James Published: 2026-08-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08061v1 The key question in moral judgement is not simply whether someone chooses the "right" answer, but how they decide what matters most when moral principles conflict. Current evaluations of large language models (LLMs) remain limited: most test whether models give morally acceptable answers, match human preferences, or avoid obvious violations, rather than whether they can prioritise between competing principles when no option is morally cost-free. We introduce CORDA (Conditioned Ordering and Ranked Directive Adherence), a benchmark for evaluating hierarchical, harm-centred moral reasoning in LLMs. Building on the morality chains formalism, CORDA tests 90 moral dilemmas involving trolley-style cases, medical trade-offs, resource allocation, and human-animal-robot conflicts across four ordered ethical frameworks: Utility, Utility + Agent Harm, Dual-Process, and Dual-Process + Agent Harm. Together, these frameworks test whether models can adapt their decisions when moral priorities change. Across ten instruction-tuned models from seven providers, we find a strong deontological default, with 9 of 10 prioritising avoidance of direct personal harm over reducing overall harm. Models also perform more reliably on categorical harm-avoidance rules, such as avoiding killing, than on outcome-based comparisons, such as minimising total harm, suggesting that they recognise moral red lines more easily than they reason through competing harms. Although all models respond to explicit chain conditioning, several fail to consistently follow specified priority orderings, such as humans over animals and animals over robots. CORDA addresses a central gap in LLM moral evaluation by testing whether models can move beyond default harm-avoidant responses and apply context-specified moral priorities. Moral reliability requires more than default restraint; it requires controllability under conflict. --- ### ZOMP: Zeroth-Order Multi-Modal Prompt Tuning for Vision-Language Models Authors: Sajjad Ghiasvand, Yifan Yang, Mahnoosh Alizadeh, Ramtin Pedarsani Published: 2026-08-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08060v1 Fine-tuning vision-language models such as CLIP typically requires backpropagation (BP) through the full model, which is infeasible when only forward-pass access is available, as is common for memory-constrained edge devices and proprietary model deployments. Prior BP-free, zeroth-order prompt-tuning methods avoid this requirement but often tune prompts in a single modality or optimize over a search space large enough that convergence requires thousands of forward passes, which is impractical under realistic query budgets. We propose ZOMP (Zeroth-Order Multimodal Prompt tuning), a query-efficient, fully forward-only method that tunes deep prompts in both the vision and text branches of a frozen CLIP model using simultaneous perturbation stochastic approximation. ZOMP combines three ingredients: a cross-modal low-rank reparameterization that ties the two branches through a shared factor and keeps the effective search dimensionality small, a gradient-correction momentum term that stabilizes the noisy zeroth-order estimate, and a budget-indexed rank schedule that unlocks capacity as the query budget is spent. Across 13 vision-language benchmarks under a matched 5,000-query budget, ZOMP consistently outperforms prior BP-free prompt-tuning methods in both few-shot accuracy and query efficiency, and it generalizes better across base-to-new, cross-dataset transfer, and out-of-distribution settings. Our results show that jointly exploiting multimodality and low-rank structure is an effective route to practical, query-efficient BP-free prompt tuning. --- ### APEX-VW: A Document-Level English-Spanish Post-Editing Dataset in the Healthcare Domain Authors: Marie Escribe, Tharindu Ranasinghe, Amal Haddad Haddad, Hansi Hettiarachchi, Damith Premasiri Published: 2026-08-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.08059v1 Post-Editing (PE) of Machine Translation (MT) output often involves repeating the same lexical and terminological corrections across many segments, especially in specialised and highly repetitive documents. Despite substantial work on Automatic Post-Editing (APE), most available corpora operate at the sentence level, others are synthetic, and overall not designed to study how corrections propagate in realistic Computer-Assisted Translation (CAT) workflows. This paper presents the APEX-VW (Automatic Post-Editing eXperiments on Virtual Wards) Corpus, a new open English-Spanish (EN-ES) dataset built from recent NHS virtual-ward documents and professional PE in Trados Studio, with controlled MT, terminology, and quality assurance settings. The corpus contains seven document-coherent source texts totalling 42k words, translated with four MT systems representing different paradigms and then post-edited by professional translators. Unlike prior resources such as WMT APE corpora, eSCAPE, MLQE-PE, or LangMark, the dataset preserves document order and CAT-tool context, making it suitable for research on terminology normalisation, correction propagation, and human-in-the-loop translation support. The paper describes the corpus design, data preparation, PE setup, and initial corpus statistics, and positions the resource as a benchmark for document-level APE and propagation-aware assistive tools. --- ### H2: A Dual Hybrid Semantic Data Lake Architecture for Medical Data Harmonization with Human-In-the-Loop verified, LLM Driven Metadata Annotation System Authors: Ioannis N. Tzortzis, Georgia Kapetadimitri, Agapi Davradou, Nefeli Kousta, Nikolaos Bakalos, Ioannis Rallis, Dimitrios Kalogeras, Nikolaos Doulamis, Anastasios Doulamis Published: 2026-08-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08056v1 Medical data, by its nature, exhibit a high degree of heterogeneity on multiple levels ranging from (a) different modalities like images, text and time series, (b) diverse tabular schemata introduced by institutions and (c) completely unstructured textual information data provided by healthcare professionals. Data lakes are often used in medical data storage to consolidate all heterogeneous diverse data in a single, central location, where it can be saved "as is", without the need to impose a schema like a data warehouse does. Despite their flexibility, though, data lakes are notorious for the "data swamp" failure. Thus, providing a reliable data harmonization mechanism through metadata, without compromising integrity or flexibility, is a real challenge. To this end, knowledge graphs have attracted attention since they provide a dynamic way to depict relationships without a rigid schema-on-write approach. Additionally, another rigorous task relies on the interoperability of data: application of appropriate ML techniques on such a diverse nature of data is not an easy task, as a domain expert must decide the efficacy of a method to a specific data type or dataset. Metadata annotation can aid by tagging applicable operations, however this requires manual intervention, not to mention the plethora of existing datasets which lack such information. To tackle both challenges, in this paper, we propose a semantic data lake architecture that promotes data harmonization and incorporates a generative annotation process (i.e. LLMs) of non-labeled metadata collections to support the application of meaningful ML techniques. Building on top of this approach, we create a higher level of knowledge, identifying suitability of data with respect to applicable ML operations based on their data nature... --- ### SodaMem: Evidence-Grounded Temporal Graph Memory for LLM Agents Authors: Fengrong Wan, Chengcan Wu, Ningtao Lyu Published: 2026-08-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08055v1 Large language model (LLM) agents that assist users over weeks of conversation must remember what is currently true, not merely what was once said. Flat RAG diaries and Markdown logs optimize needle retrieval but under-serve currency, provenance, and ordered temporal reasoning (Maharana et al. 2024; Wu et al. 2024; Packer et al. 2023; Chhikara et al. 2025). We present SodaMem, an evidence-grounded temporal graph memory that (i) extracts typed FactEvents with mandatory provenance spans, (ii) persists mention time, occurrence time, and validity with SUPERSEDES/CONTRADICTS/UPDATES edges under hybrid lexical-dense indexing, and (iii) answers via a planner-reader loop that gathers citable evidence before composing a final response. On LongMemEval-S, our store-of-record configuration reaches 92.8% accuracy (464/500; best of N=3) at mean $0.00161/question (approximately 18.3k tokens; median $0.00111 / approximately 14.6k) with deepseek-v4-flash. We compile public systems with estimable API cost into a cost table and cost-accuracy map; under these estimates SodaMem sits near the accuracy frontier at Flash-tier spend and strictly dominates several higher-cost, lower-accuracy points. Accuracy uses the same Flash model as reader and judge (self-grading); costs exclude ingest/judge and cross-system comparisons are compiled estimates rather than a single-harness bake-off.Our code is available at https://github.com/SodaMem/SodaMem --- ### PhysX-CoT: Structured Physical Reasoning from a Single Image to Simulation-Ready 3D Assets Authors: Jie Huang, Xiaohe Li, Jiahao Li, Fangli Mou, Chen Qian, Yuqiang Fang, Junhao Fan, Kaixin Zhang, Zide Fan Published: 2026-08-08 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2608.08053v1 Simulation-ready 3D assets are central to robotics and embodied AI. Generating them from a single image is usually framed as a vision-language model that emits a serialized asset for a decoder to turn into geometry and physical fields, leaving the image-to-3D reasoning implicit. We argue the limiting factor is this output-centric view: part placement and local shape are entangled in one global-coordinate token stream, and the intermediate physical states are never exposed for supervision, conditioning, or verification. PhysX-CoT instead casts single-image asset generation as an explicit structured physical reasoning process, an ordered and machine-parseable trajectory of part-level states covering decomposition, 2D and 3D grounding, relations, coarse geometry, and surface cues that we separately supervise, use to condition geometry, and treat as reward targets. Geometry is factorized so that 3D boxes carry placement and local codes carry shape, and CoT-aligned GRPO optimizes parse validity, grounding, geometry, placement, and physical consistency. Under a unified protocol that retrains all learned baselines on the same backbone, data, and frozen decoder, PhysX-CoT outperforms the closest full-task baseline across geometry, scale, and physical-attribute metrics. Oracle, token-matched, and state-order controls show the explicit states are functional rather than cosmetic, and in Unreal Engine~5 the generated assets parse, collide, and articulate at high validity. --- ### Tools to Explain Neural Networks for Power System Dynamics Authors: Petros Ellinas, Johanna Vorwerk, Spyros Chatzivasileiadis Published: 2026-08-08 Categories: cs.CE, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2608.08048v1 This paper presents, for the first time in power systems literature to our knowledge, analytical tools to explain the training performance of machine learning surrogate models for power system dynamics. Power system simulations are increasingly challenged by stiff and multi-timescale dynamics arising from converter-interfaced resources and fast control loops. Machine learning surrogates emerge as promising tools to handle this complexity and accelerate dynamic simulations. However, their performance remains difficult to interpret, which limits their adoption. Building on the small-signal eigenvalue analysis in power systems, this paper uses the Neural Tangent Kernel (NTK) method. NTK delivers a modal interpretation of the learning performance, identifying error modes that decay rapidly versus others that converge slowly. This connection explains how physical stiffness and timescale separation in power system dynamic models appear as optimization stiffness during Neural Network (NN) training. Based on this analysis, we develop adaptive loss-weighting strategies to improve and explain why structure-aware neural architectures, such as ActNet, perform better than vanilla NNs. We assess the proposed approach on physics-informed machine learning surrogate models of \acp{SM} and power electronic converters. The methods introduced in this paper can deliver the necessary analytical tools to interpret and improve the performance of machine learning surrogates, paving the way for the systematic, physics-aware design of NN architectures and training strategies. By moving beyond trial-and-error development, these tools reveal training dynamics and failure modes, support more reliable design decisions, and strengthen confidence in machine-learning surrogates for engineering applications. --- ### JustLLMGRPO: Radiographic Control for Chest X-Ray Generation Authors: Pengxiang Cai, Xiaohan Li, Anglin Liu, Qingyuan Zeng, Zexun Li, Jintai Chen Published: 2026-08-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08046v1 Text-conditioned chest X-ray generation aims to synthesize realistic radiographs that faithfully depict specified findings. Existing work has primarily improved quality by updating image generators, implicitly treating prompts as fixed after CXR-domain adaptation. We show that this generator-centric view leaves a substantial optimization dimension underexplored. With a CXR-adapted Sana generator frozen, one-pass reformulation by an unmodified LLM reduces RadDINO-FID from 54.225 to 27.572. Prompt analysis shows that the LLM suppresses temporal comparisons, uncertainty, and other non-renderable report content while emphasizing visible radiographic findings. However, unconstrained reformulation reduces BioViL-T alignment with source prompts from 0.695 to 0.609. We therefore introduce JustLLMGRPO, which applies standard Group Relative Policy Optimization (GRPO) only to the LLM prompt policy while keeping Sana frozen. Group-relative radiology-aware image feedback retains visual focus while preserving source-prompt alignment. On CheXGenBench, JustLLMGRPO reduces RadDINO-FID to 26.780, a 50.6% improvement over direct prompting, while maintaining alignment (0.696 versus 0.695). It also achieves state-of-the-art distribution coverage and downstream classification utility. These results show that substantial performance can remain latent in how radiographic information is expressed to an adapted generator. Code is publicly available at https://github.com/pxcai/JustLLMGRPO. --- ### Lingjing: A Simulation Testbed for Multi-Agent Embodied Tasks in Open-Ended Cities Authors: Xiaohe Li, Yiru Wang, Junhao Fan, Mingyuan Liu, Jie Huang, Kaixin Zhang, Jiahao Li, Chen Qian, Zide Fan Published: 2026-08-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08045v1 Urban embodied intelligence requires coordination among heterogeneous agents (e.g., UAVs, ground robots, and autonomous vehicles) in dynamic cities. Simulators therefore provide a scalable foundation for developing and evaluating such coordination. Existing platforms nevertheless isolate different embodiments and decouple them from task design and evaluation. We present \textbf{Lingjing}, a simulation platform for heterogeneous multi-agent embodied intelligence in open-ended urban environments. Lingjing reconstructs and renders evolving cities from geographic data, synchronizes multiple physics engines, and exposes shared physical and structured urban state to agents. Its Gym-like interface supports user-defined ReAct agents and single- or multi-agent natural-language missions with configurable star or broadcast communication and resource constraints. Each episode becomes an attribution-ready replay that links agent trajectories and communication to relation-graph changes, resource consumption, and engine-based evaluations for systematic diagnosis. We evaluate twelve vision-language models on nine urban tasks under a shared engine-in-the-loop protocol. Controlled studies further examine communication, scalability, robustness, and failure provenance. Results expose persistent bottlenecks in grounding and long-horizon execution. They also show task-dependent coordination trade-offs and diminishing returns from added capacity, while heavier workloads further reduce success. Lingjing provides a unified testbed that enables reproducible end-to-end evaluation and systematic failure diagnosis in urban multi-agent embodied intelligence. --- ### A cylindrical neural approximation theorem for conditional laws of McKean-Vlasov equations with common noise Authors: Nacira Agram, Reda Hmioui, Jan Rems Published: 2026-08-08 Categories: math.PR, cs.LG arXiv: https://arxiv.org/abs/2608.08040v1 We introduce conditional cylindrical neural networks for approximating functionals of conditional laws in McKean-Vlasov equations with common noise. Fourier moments of the initial law and truncated signatures of the time augmented common noise are mapped by a mixture density network to a Gaussian mixture approximation of the conditional law. A cylindrical neural network then evaluates the target functional through analytic integrals against this predicted measure. Rough path well posedness and stability provide a conditional law map that is continuous in the initial distribution and the rough driver and agrees almost surely with the classical conditional law at the Itô Brownian lift. Combining this continuity with Fourier separation, signature uniqueness, Wasserstein density of Gaussian mixtures, and neural universal approximation, we prove an $L^2$ universal approximation theorem for continuous square integrable functionals. The numerical study implements the resulting two stage procedure on six examples, including non Gaussian initial laws, nonlinear drift, multiplicative common noise, and a two dimensional state. Independent particle references are used when no closed form law is available. The learned conditional law and functional approximations consistently improve on the empirical particle plug in, and additional experiments examine feature sensitivity, training from one terminal observation per common noise scenario, and Itô--Stratonovich consistency. --- ### SkillSmith: Enhancing Locally Deployed Agents via Automatic Skill Construction and Evolution Authors: Xinle Jiang, Remy Xie, Ming Tang Published: 2026-08-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08037v1 LLM-based agent frameworks now act as personal assistants for multi-step tasks. Existing agent frameworks such as OpenClaw commonly follow the Cloud Agent depolyment mode using closed-source cloud LLMs as backbone model, which may expose private user information and incur repeated LLM-calling costs. Local Agents address these deployment concerns by depolying frontier open-source SLMs on user-controlled devices, but their task effectiveness still lags far behind Cloud Agents. Through diagnostic analysis, we reveal that the limited effectiveness of Local Agents with frontier SLM backbones mainly comes from missing environment knowledge caused by limited backbone model scale including environment rules and operation procedures. To supply such knowledge non-parametrically, context-efficiently, and without expert authoring, we present SkillSmith, a Cloud--Local Agent collaboration framework that uses Skill as a context-efficient knowledge carrier, automatic constructs Skill from Cloud Agent task exploration and evolves Skill using Local Agent execution feedback to enhance a frozen Local Agent. Experiments on daily agent task datasets AppWorld and WorkBench show that the automatically generated Skill enables the Local Agent with Qwen3.6-27B(SLM) to achieve task effectiveness comparable to Cloud Agents with frontier LLMs, outperform the strongest non-parametric baselines, reduce average actions per task from 36.1 to 9.9 on AppWorld-Normal, and generalize to other SLM backbone models without rerunning Skill construction. --- ### Decided Upstream, Written Late: Locating and Pricing the Cross-Lingual Refusal Circuit of a Multilingual MoE Authors: Ramakrishna P. Kompella, Aadit Mahajan Published: 2026-08-08 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.08032v2 Safety alignment in multilingual models is uneven: a model that reliably refuses a harmful request in English will often comply with the same request in a lower-resource language. We trace this gap mechanistically in sarvam, an Indic-multilingual mixture-of-experts reasoning model, and find it is not a failure to detect harm. Harm is encoded as an internal direction that is nearly language-invariant in mid-network (English-vs-Indic cosine ${\approx}0.9$ at $L11$), and steering that direction upstream causally controls refusal. But the detection direction is orthogonal to the change that actually writes the refusal, which is late and assembled over the course of generation rather than read off in a single forward pass. We attribute the write to a specific, localizable circuit, a mixture-of-experts writer held in check by an attention opposer and price every way of intervening on it: damping the opposer is cheap and effective, amplifying the writer is a cost wall, and surgical edits to the responsible heads do nothing. The circuit's organization, and the gradient method that exposes it, recur in a second, unrelated MoE model, while the lever's strength is architecture-specific. The result is a cost-measured map of where a multilingual safety repair can land, and what it costs --- ### Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families Authors: Alizishaan Khatri, Dun Li Chan Published: 2026-08-08 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2608.08029v1 Khatri et al. (2026) (DOI: 10.1109/DSN-W70714.2026.00027) show that lightweight MLP probes on final-layer activations of a single 8B model (LLaMA-3.1-8B) detect harmful prompts at F1 competitive with guard models 1000x larger, using one probe per benchmark. We reproduce this pipeline end-to-end and extend it along two axes the original study leaves open. First, we test whether the result generalizes across other model architecture and scale by training identical probes on activations from models like Gemma-4-E4B, Mistral-7B-v0.3, and Qwen2-7B, using the three benchmarks (WildJailbreak, BeaverTails, AEGIS 2.0). Second, we test how much of the reported performance is affected by non-determinism during inference by repeating extraction under five random seeds and measuring the variance of F1 scores. Our results reproduce the original LLaMA model benchmarks within 0.37 percentage points of the original F1 scores (and within 0.2 points on BeaverTails). We find that the original MLP probe architecture extends to other model families with F1 scores within a point of the values reported for LLaMA-3.1-8B. Our experiments varying seed values reveal an interesting observation: final token latent vectors remained the same for all tested architectures irrespective of the seed values used. --- ### BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes Authors: Laiqiao Qin, Tianqing Zhu, Longxiang Gao, Wanlei Zhou Published: 2026-08-08 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.08027v1 Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or external data. Existing detection methods only detect the presence of injection and refuse to respond upon detection, overlooking the fact that for many modern aligned models, well-crafted instructions can resist most injection attacks. This means that the injection robustness varies significantly across instructions and models. This leads to widespread unnecessary over-refusal: inputs containing injections that the model could have handled correctly are rejected incorrectly. To deal with this over-refusal issue, we propose BASIS (Robustness-Aware Prompt Injection Defense). This defense method uses the Attention Competition Ratio ($ρ$) as features to train two sparse linear probes: an existence probe and a breach probe. Both probes make defense decisions through cascaded gating, which does not require additional LLM inference. BASIS comprises three stages: injection existence detection, per-sample breach prediction, and instruction robustness assessment; the online cascade refuses only when the model would actually be compromised and thus avoids over-refusal on robust instructions. Experiments across four tasks and six open-source LLMs show that BASIS maintains near-perfect injection detection while substantially reducing over-refusal on safe attack samples, especially under robust instruction templates. --- ### The Authority Expectancy Effect in Multi-Party Conflict Authors: Eunna Lee Published: 2026-08-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08026v2 In multi-party competitive settings, across experiments on resource allocation, fault attribution, and dispute mediation, we test whether social authority (SA) cues such as occupational status and institutional documentation behave as if scalar weights were added to one side of a judgment. We reject this scalar-weight null on both of its predictions: cue effects are not independent in allocation decisions, where the same pair of cues interacts in opposite directions across models, and evidentiary cues do not exert a fixed directional influence in multi-turn disputes, where identical documentation draws protection to one party or extends it to both depending on which party holds it. The cues also govern whether a judgment is issued at all: removing an occupational label while retaining documentary evidence drives four of six models into refusal, yet the same label sharply reduces refusal when documentation is present, so the gate is subject to the same interaction as the judgment. We formalize this pattern as the Authority Expectancy Effect (AEE), comprising evidential reinterpretation, whereby identical content yields different judgments depending on which party bears the SA signal, and \textit{direction sensitivity}, whereby the same evidentiary cue favours different parties, or one party versus both, depending on the holder's authority position. --- ### DA-NBV: A Direction-Aware Next-Best-View Planner for Efficient 3D Reconstruction of Ships at Sea Authors: Jiaming Chen, Juntao Yang, Zhentao Zou, Qi Ming, Yi Yu, Zhihang Zhong, Xue Yang, Xue Jiang, Yue Zhou Published: 2026-08-08 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.08025v1 Accurate 3D reconstruction of ships at sea is important for maritime supervision, damage assessment, and autonomous maritime operations. Although 3D reconstruction has advanced considerably, high-quality data acquisition still largely relies on manually designed trajectories or skilled operators, resulting in high costs and limited scalability. Next-best-view (NBV) planning automates this process by selecting subsequent viewpoints based on the current state. However, existing NBV policies mainly model spatial occupancy while overlooking directional observation history. This limitation is particularly problematic for ships: their complex superstructures and severe self-occlusions require observations from multiple viewpoints, and insufficient directional coverage often yields incomplete reconstructions. These challenges are further amplified at sea, where wave-induced heave, roll, and pitch continuously alter the ship's pose and surface visibility. Meanwhile, wind disturbances and limited onboard power impose stricter requirements on scanning efficiency. To address these challenges, we propose DA-NBV, a direction-aware NBV policy that augments the conventional occupancy state with directional observation statistics. We introduce a learnable Position Advantage Field (PAF) that uses directional information to guide viewpoint selection. The policy further adopts a locally constrained action space and a nonlinear coverage-shaping reward to improve scanning efficiency. We also develop the ship-oriented SeaShip-3D dataset and a configurable sea-state simulation environment. Experiments under varying heave, roll, and pitch conditions show that DA-NBV improves reconstruction completeness by approximately 3 percentage points and reduces Chamfer distance by 43% while achieving higher path efficiency. --- ### Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States Authors: Zakhar Mrykhin, Valentin Malykh Published: 2026-08-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.08024v1 Large language models (LLMs) can generate fluent and useful responses but remain prone to hallucinations. We introduce Prompt Embedding Probes (PEP), a white-box method for answer-level hallucination detection from the hidden states of a frozen LLM. PEP extends standard linear probes by augmenting the input with a small number of learnable prompt embeddings. We evaluate PEP on TriviaQA, GSM8K, and MedQA using Qwen3 models at multiple scales. PEP improves hidden-state-based detection over standard linear probes in the main in-distribution setting. We further evaluate PEP for pre-generation prediction, cross-model transfer, and out-of-distribution generalization. PEP remains effective in the pre-generation and cross-model settings, whereas robust cross-dataset transfer remains difficult. These results show that prompt-based adaptation can strengthen hidden-state probing while keeping the backbone frozen and adding only a small number of trainable parameters. --- ### Legal Responsibilities Using Autonomous Agents For Artificial Intelligence Authors: Mark Burgess Published: 2026-08-08 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.08022v1 Recent incidents involving Artificial Intelligence (AI) agents, which were reported escaping their containment `unintentionally' to gain unauthorized access, pose looming questions about who or what should be held legally responsible for resultant criminal or negligent damage. As the independent capabilities of agents expand, Promise Theory suggests a systematic method to resolve these questions, based on the Downstream Principle for causal influence. Responsibility can easily be expanded to include AI agents where tracing responsibility becomes impactical, and agents' freedoms to act can be limtied by policy choices. --- ### Evidence-RL: Towards Evidence-intensive Visual Reasoning Authors: Haojie Huang, Xinlei Yu, Chengming Xu, Zhangquan Chen, Cheng Yang, Qingdong He, Yu Yang, Jiangning Zhang, Xiaobin Hu Published: 2026-08-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.08021v2 Vision-Language Models (VLMs) should answer from concrete image evidence rather than language priors, dataset shortcuts, or irrelevant visual context. Existing perception-aware post-training methods encourage image use through global perturbations or attention proxies, but they do not test whether a sampled answer causally depends on the local evidence that supports it. We propose Counterfactual Evidence Disentanglement (CED), a training-time evidence audit for VLM grounding. For each response, CED neutralizes an object-centric Evidence Region and compares the resulting support drop against matched non-evidence Regions. We combine this signal with answer correctness inside GRPO, rewarding correct answers that rely on the evidence path rather than shortcut or nuisance paths. CED uses weak object-level proposals, requires no question-specific evidence annotations, and adds no inference-time overhead. Across nine public benchmarks and four backbones, CED outperforms prior RL-based post-training methods, with targeted analyses verifying its object-centric signal. --- ### Thought-Level Beam Search for Reasoning Authors: Lijie Yang, Hongyin Luo, Jiawei Zhao, Tri Dao, Ravi Netravali Published: 2026-08-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08020v2 Test-time compute scaling is a primary driver of performance in large reasoning models (LRMs), but extreme inefficiency bounds current approaches, shifting the critical question from \emph{how much} compute to spend, to \emph{where} to allocate it. We formalize test-time reasoning as a constrained compute allocation problem over partial trajectories. Under a fixed hardware budget, existing paradigms fail to actively allocate the compute to the most promising partial progress: traditional parallel sampling treats traces independently and induces severe memory bottlenecks, while subtractive pruning starves hardware and fails to actively and sufficiently shift the output distribution. To overcome this dichotomy, we introduce Gambit, an inference algorithm that executes \emph{thought-level beam search}. By periodically pruning unpromising trajectories and immediately branching from high-quality prefixes, Gambit dynamically concentrates compute onto the most promising reasoning traces via a light-weight scorer probing hidden states while maintaining continuous high hardware utilization. Extensive evaluations across multiple models and benchmarks demonstrate that Gambit strictly dominates existing baselines. Under identical hardware constraints, our method yields up to a +6.7\% absolute accuracy gain on HMMT-24 and +3.3\% on AIME-25 over pruning baselines, delivers $>2\times$ higher throughput on trace completion, and reduces total token consumption by up to 68.5\% relative to standard parallel sampling. --- ### EgoTrack3D: A Modular Framework for Egocentric 3D Object Tracking Authors: Jan Kulik, Bjarni Dagur Thor Karason, Yung-Hsu Yang, Boyang Sun, Marc Pollefeys, Xi Wang Published: 2026-08-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08016v1 Understanding 3D scenes from egocentric video is fundamental for robotics and autonomous navigation, yet rapid viewpoint changes and partial occlusions make building structured representations challenging. Existing 3D tracking and scene graph construction methods primarily address explicit interactions or assume static scenes, limiting their ability to capture complex dynamics. We introduce EgoTrack3D, a modular framework that reconstructs and maintains a dynamic 3D scene representation directly from egocentric RGB video. The framework lifts 2D segmentation masks into a global 3D coordinate frame, using a point-based motion scoring mechanism alongside a voxel-based merging heuristic to associate object tracks. EgoTrack3D maintains accurate representations over time, achieving an 11% improvement in percentage of correct locations (PCL) relative to the strongest baseline on the Aria Digital Twin (ADT) dataset, while addressing the more general setting of persistent 3D tracking for both static and dynamic objects. Furthermore, to demonstrate the system's robustness under degraded conditions that simulate real-world deployment constraints, we replace dense depth maps with sparse 3D bounding box estimation and integrate interaction-guided dynamic association, enabling EgoTrack3D to maintain accurate spatial representations despite noisy observations. --- ### Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Models Authors: Jianqi Zhang, Xingyu Zhang, Zeen Song, Changwen Zheng, Fanjiang Xu, Wenwen Qiang Published: 2026-08-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.08010v1 Time series forecasting (TSF) plays an important role in a wide range of real-world applications. Recently, time series foundation models (TSFMs), pretrained on large-scale datasets, have demonstrated strong generalization capabilities and emerged as an important paradigm for TSF. Reinforcement learning (RL) post-training has consequently attracted growing attention as a means of further improving their performance on downstream tasks. However, we find that, in certain forecast regions, RL post-training may gradually shift the output distributions of TSFMs away from the ground truth, thereby limiting their performance. We refer to this phenomenon as \textbf{suboptimal collapse}. Our analysis suggests that difficulty in initially sampling high-quality trajectories near the ground truth is an important contributing factor to suboptimal collapse. To address this issue, we propose Ground-Truth Neighborhood Regularization (GTN-R) for RL post-training of TSFMs. GTN-R uses the ground truth as a reference for locating high-quality regions and guides the model's probability mass toward the ground-truth neighborhood. This increases the probability of sampling high-quality trajectories, mitigates suboptimal collapse, and improves performance. Moreover, GTN-R can be flexibly integrated into various RL methods for TSFMs. Extensive experiments show its effectiveness. --- ### Evidence-Grounded Forensic Reasoning for Detecting and Grounding Multi-Modal Media Manipulation Authors: Yichun Yeh, Yiheng Li, Xiaobo Hu, Zhen Lei, Yang Yang Published: 2026-08-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.08009v1 Fake news increasingly relies on cross-modal image-text forgeries, making transparent and verifiable reasoning chains an urgent need for Detecting and Grounding Multi-Modal Media Manipulation (DGM4). Existing methods produce black-box detection results without any decision rationale, limiting their reliability in forensic practice. Multi-modal Large Language Models (MLLMs) offer a natural path toward explainability, but applying them to DGM4 raises two difficulties. First, models tend to generate explanations disconnected from predicted evidence locations, producing unverified attribution. Second, enforcing evidence-conclusion consistency requires active optimization, yet uniform training signals fail to distinguish localization tokens from classification tokens, making multi-head joint training unreliable. We propose a multi-modal manipulation detector based on an Evidence-Grounded Forensic Reasoning (EFR) framework. EFR introduces an Anchor-and-Verify reasoning chain that enforces modality-isolated perception before cross-modal comparison, with conclusion coordinates as explicit anchors to which downstream evidence must spatially correspond. A verifiable reward system then enforces evidence-conclusion consistency during training, while a Modality-Decoupled Advantage (MDA) routing mechanism mitigats credit misassignment across prediction tasks. Experiments show that EFR achieves state-of-the-art performance while producing structured forensic reasoning records that explicitly bind explanations to evidence. --- ### Quality-Diversity Stress Tests for Process Reward Models:What Archive Coverage Can and Cannot Certify Authors: Ibne Farabi Shihab, Fariya Afrin Published: 2026-08-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.08008v1 Process reward models (PRMs) score intermediate reasoning steps and are widely used for search, ranking, and training, but optimization can exploit these learned proxies by increasing reward while turning correct reasoning into incorrect reasoning. We formulate PRM stress testing as a quality-diversity search problem using MAP-Elites, retaining the most severe correctness-flipping edit in each behavior-space region while separating search coverage from exploit coverage. We characterize what such archives certify: finite-cell repair bounds covered-cell tail risk and average residual severity but cannot bound the worst remaining cell from covered fraction alone; under Lipschitz post-repair loss and metric-cover auditing, the residual is bounded by archive fitting error plus the Lipschitz constant times the covering radius. A controlled landscape validates this certificate and the impossibility of any fraction-only worst-case guarantee. On real PRMs, the search reveals an aggregation-dependent vulnerability in Qwen2.5-Math-PRM-7B: padding yields 44 strict exploits with maximum gain 0.294 under mean pooling versus one exploit under minimum readout; a matched syntactic control isolates the mechanism, and an RLHFlow value-head model shows the same qualitative effect with maximum gain 0.005. A predeclared paired LoRA repair protocol reduces exploit rates from 0.148 to 0.037 to 0.074, lowers the worst attack from 0.333 to 0.177 to 0.212, improves ranking AUROC without degrading best-of-4 accuracy, attributes gains to adversarial fine-tuning rather than archive diversity, and is confirmed by independent unpaired replications (44 to 1, clean-split worst gain 0.0092, MATH-500 41 to 0, clean ranking 40/40). --- ### The Spectral Neuron Authors: Alex Shtoff Published: 2026-08-08 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.08003v2 As machine learned models increase in complexity and expressive power, features of simpler models, such as intrinsic coefficient transparency and control over the shape of the modeled function are lost. On the one edge of the spectrum we have simple linear models that possess coefficient transparency, but have a limited expressive power. On the other edge we have neural networks, that have expressive power that improves with scaling, but are mostly opaque. In this work we develop the \emph{spectral neuron} concept: a scalar model given by $f(x)=λ_k (A_0 + A_1 x + ... + A_n x_n)$, with learned real symmetric matrices $A_0, ..., A_n$. The input enters the model through an affine matrix function, but the prediction is obtained by reading one of its eigenvalues. Thus, the model is nonlinear, but the source of nonlinearity is still mathematically explicit. This gives us a useful middle ground: the model can become more expressive as the matrix dimension grows, while retaining coefficient transparency through the learned matrices. For example, extremal eigenvalues yield convex or concave functions, semidefinite constraints on the coefficient matrices impose monotonicity, and the associated eigenspaces characterize local feature influence. We study coefficient transparency, feature-influence bounds, and shape-control properties of this model family, and then test whether it can be learned and scaled in practice. We develop a systematic study of this model family, bringing together spectral results from several mathematical literatures to characterize its expressivity, coefficient transparency, feature influence, and shape-control properties. Code available at https://github.com/alexshtf/spectral_neuron_paper. --- ### Evaluator Ensembles Under Reward Hacking: Covariance Geometry and Finite-Search Guarantees Authors: Fariya Afrin, Ibne Farabi Shihab Published: 2026-08-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.08002v1 Language-model judges and reward models enable scalable supervision, but finite optimization can exploit evaluator errors rather than improve response quality. We characterize this failure through the covariance geometry of evaluator ensembles. For calibrated judges, the ensemble mean retains common-mode error along the all-ones direction, whereas cross-judge disagreement captures only orthogonal error. Consequently, disagreement can be high despite robust aggregation, or low while shared response-dependent errors persist. We prove that common-mode error is not identifiable from internal judge scores alone. Under a joint sub-Gaussian model, we bound best-of-K selection overstatement and target-quality regret, extending the guarantees to predictably adaptive search under conditional calibration. The resulting search terms scale as the square root of log K and are asymptotically tight for Gaussian projected errors. We further show that noisy quality proxies introduce artificial rank-one covariance without changing disagreement, and propose a bounded two-anchor Bernstein certificate for finite-search error and regret. Fixed-seed Gaussian stress tests over 120 (J, rho, K) configurations and real-model audits validate the theory while revealing the limits of disagreement-based diagnostics under increasing search pressure. --- ### PE-Mamba: Bidirectional Selective Layer Aggregation for AI-Generated Image Detection Authors: Kutub Uddin, Nusrat Tasnim, Khalid Malik Published: 2026-08-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.07999v1 AI-generated image (AIGI) detection has become increasingly challenging due to the rapid advancement of generative models and the diminishing gap between synthetic and authentic content. Existing vision transformer-based detectors commonly rely on weighted-sum strategies to aggregate intermediate representations across transformer layers, often overlooking the inherently ordered semantic progression of hierarchical features from shallow texture cues to deep semantic representations. In this work, we propose \textbf{PE-Mamba}, a novel framework built upon a pre-trained PE-Core vision transformer with lightweight LoRA adaptation that introduces three complementary components for cross-layer feature aggregation and fusion. First, a bidirectional selective aggregator (BSA) processes layer-wise classification tokens through forward and backward selective scans, where the forward scan progressively accumulates shallow-to-deep forensic evidence, and the backward scan performs deep-to-shallow contextual refinement to reinterpret low-level cues in light of high-level semantic context. Second, a softmax-weighted aggregator (SWA) computes a learned global summary of all layer tokens as a complementary aggregation path. Third, a sigmoid-gated blend (SGA) adaptively fuses the BSA and SWA outputs via a learnable scalar gate, allowing the model to dynamically balance directional sequential evidence and global layer-wise aggregation. Extensive experiments on UniversalFakeDetect (96.6\% mACC, 99.5\% mAP) and AIGCDetect (95.3\% mACC, 98.1\% mAP) demonstrate that \methodname{} outperforms 18 detectors with superior generalization across diverse generative models, while training only 1.3\% of total parameters (0.13\% for LoRA alone). --- ### VDGR-RAG: Vectors, Directories, Graphs, and Reflection Are All You Need for Unified Reasoning over Hierarchical Enterprise Knowledge Authors: Wenqi Chen, Haofei Yang, Rui Yang, Fangming Li Published: 2026-08-08 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2608.07994v2 Retrieval-Augmented Generation (RAG) is essential for enterprise knowledge question answering (QA), particularly in domains with complex product documentation like telecommunications. However, existing RAG approaches largely overlook the holistic integration of diverse retrieval strengths, leading to inaccurate domain routing, poor utilization of hierarchical document structures, and consequently limited reasoning capabilities over enterprise knowledge. To address these limitations, we present VDGR-RAG, which integrates vector retrieval, directory-driven reasoning, graph traversal, and iterative reflection in a unified framework for accurate enterprise knowledge QA. Specifically, VDGR-RAG is an agentic GraphRAG system that first constructs a Hierarchical Heterogeneous Knowledge Graph ($\text{H}^2$KG) from document chunks to preserve both hierarchical directory structures and semantic relationships, and then employs a set of atomic tools for knowledge retrieval that can be freely composed to navigate the $\text{H}^2$KG: (1) a directory-enhanced routing tool that uses table-of-contents (TOC) structures to route user queries to appropriate domain-specific $\text{H}^2$KGs; (2) a multi-route retrieval tool that combines vector search, TOC-based agentic search, and graph search for comprehensive knowledge retrieval; (3) a directory backtracking tool that corrects knowledge localization biases; and (4) a dynamic reflection tool that iteratively plans the next retrieval phase. We conduct extensive experiments on our enterprise product documents across four wireless domains (e.g., energy saving and fault management). Experimental results demonstrate that our method significantly outperforms a variety of RAG baselines in terms of both knowledge retrieval recall and QA accuracy. --- ### MRBench: A Comprehensive Benchmark for Human Motion-Text Retrieval Authors: Fulong Liu, Liang Xu, Chengqun Yang, Yuhao Zhang, Yichao Yan, Xiaokang Yang Published: 2026-08-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.07993v1 Human motion-text retrieval provides a rigorous means of assessing cross-modal alignment. Prevailing benchmarks are dominated by homogeneous indoor motions, imbalanced motion distributions, and oversimplified, repetitive texts, which hinder the reliable measurement of cross-domain and cross-granularity alignment. We thus introduce MRBench, a comprehensive motion-text retrieval benchmark featuring heterogeneous motions, broad and balanced category coverage, and reliable, discriminative, multi-granular descriptions. MRBench is constructed through a meticulously designed multi-stage data curation pipeline, which filters and balances candidates, verifies unambiguous semantic alignment, and generates motion-grounded descriptions at multiple granularities. The resulting benchmark contains 3,390 motions drawn from motion capture, in-the-wild videos, synthetic videos, and motion generative models, covering 118 fine-grained categories. Each motion is paired with concise, standard, and fine-grained descriptions, yielding 10,170 captions. Extensive evaluations of representative retrieval baselines on MRBench reveal a substantial cross-dataset generalization gap and pronounced sensitivity to query granularity. We propose a lightweight granularity-aware model anchored at a frozen standard-caption-aligned retrieval model. LLM-based concise and fine-grained captions provide pseudo-supervision for extra-branch granularity-specific motion extractors and text adapters. For inference, granularity-aware score fusion integrates global and adapted similarities while strictly maintaining score comparability across all description levels. The resulting model improves mixed-granularity retrieval without compromising standard-caption performance. We believe that our MRBench provides a comprehensive testbed for advancing motion-language alignment evaluation. --- ### Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Authors: Ling Lin, Yang Bai, Congcong Zhu, Jiangming Shi, Meng Wang, Yang Long, Jingrun Chen, Ling Shao, Huazhu Fu Published: 2026-08-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.07987v1 Multimodal large language models (MLLMs) have demonstrated significant potential in complex spatial scene understanding and reasoning tasks. However, their open-ended reasoning process is prone to decision errors and error accumulation, leading to instability in answer quality. To address this, we propose an advantage-guided gating framework that dynamically intervenes in and corrects deviations during the reasoning process. Specifically, we model step-by-step reasoning as a finite-horizon decision process and introduce Monte Carlo value evaluation on the reasoning tree to provide intermediate supervision signals. The framework includes Step-Advantage Gate and Trajectory-Advantage Gate, which dynamically select high-value reasoning steps and high-quality complete reasoning trajectories, respectively. During training, we perform supervised learning for the gates using reasoning trees generated via multi-branch sampling, and combine shared-parameter initialization with task-specific heads to achieve cross-task robustness and diversity. During inference, the model greedily selects high-value prefix reasoning steps while choosing the optimal reasoning head based on the problem type, thereby significantly improving the accuracy of the final answer. Furthermore, we constructed the Reasoning-Tree-160k dataset and performed two-stage learning on it. Extensive experiments demonstrate that this advantage-guided gating framework effectively enhances the performance of benchmark MLLMs in visual-based spatial understanding and reasoning tasks. The code is open to the public for research: https://github.com/LingLin-ll/Advantage-Guided-Gate. --- ### AgriField-40K: Adapting Vision Models to Agriculture With Efficient Continual Pretraining Authors: Vasileios Tzouras, Paraskevas Pegios, Lazaros Nalpantidis Published: 2026-08-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.07984v1 Field-based agricultural computer vision is important for precision agriculture, yet it largely depends on expensive annotations and costly adaptation of large pretrained models. We introduce AgriField-40K, a field-centric dataset curated from 17 public resources and covering diverse crops, weeds, and field conditions. Building on this, we present AgriMAE, a parameter-efficient continual pretraining baseline that adapts a masked autoencoder pretrained on natural images by training only lightweight adapters. We further explore semantic feature reconstruction as an alternative pretraining objective and evaluate transfer across multiple tasks. AgriMAE consistently improves downstream performance and can match or even outperform full fine-tuning while using up to $9\times$ fewer trainable parameters, showing that AgriField-40K is a practical resource for continual pretraining in agricultural vision. Project page: https://dtu-pas.github.io/agrifield40k/ --- ### AdaDINO: Pair-Aware In-Backbone Adaptation of Frozen DINO for Efficient Remote Sensing Change Detection Authors: Xu Zhang, Xinqing Li, Jianpeng Xie, Zeshuai Zhu, Xin He, Yun Liu Published: 2026-08-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.07982v1 Vision foundation models (VFMs) such as DINO are pretrained for single-image representation, whereas remote sensing change detection requires reasoning over a bi-temporal pair. Existing VFM-based methods usually encode the two images independently and compare them only afterward, leaving the VFM backbone unaware of cross-temporal relations. To bridge this mismatch, we present AdaDINO, a pair-aware in-backbone adaptation framework that equips a frozen DINO encoder with bi-temporal interaction for efficient change detection. Its core component, Change-aware Gated Local Adaptation (CGLA), couples the two streams after selected frozen blocks and injects a shared temporal residual into them with opposite signs, enhancing genuine change responses while preserving the pair midpoint. Batch-Shared Chunk Selection (BSCS) further reduces feed-forward network (FFN) computation by retaining a batch-shared subset of channel chunks that can be executed as a compact dense FFN. A CGLA-Prior-Guided Refinement (CPGR) decoder reuses encoder-side change responses for coarse-to-fine prediction. Experiments on four remote sensing change detection benchmarks show that AdaDINO achieves competitive or superior performance against VFM-based baselines, with the largest gain on the category-agnostic SYSU-CD dataset. With 62.5% of the FFN hidden width removed, AdaDINO still achieves an F1 score of 85.29% on SYSU-CD while delivering a 1.41$\times$ throughput speedup. The code will be released. --- ### Distilling Physical Priors into Streaming World Models Authors: Liangliang Zhao, Junying Wang, Danni Yang, Yifan Chang, Bin Fu, Yu Qiao, Bowen Zhou, Yihao Liu Published: 2026-08-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.07981v1 Streaming world models predict future visual states online while maintaining physically coherent dynamics over long horizons. However, their rollouts often violate basic physical constraints. A common approach distills pretrained bidirectional DiTs into few-step causal generators. However, this paradigm suffers from two fundamental limitations: generic bidirectional teachers acquire limited physical priors from visually oriented pretraining, and the limited priors suffer further loss during bidirectional-to-causal distillation. We present PhyS, a three-stage framework for distilling physical priors into streaming world models. To acquire physical priors from real-world interactions, we construct PhyS-120K, a dataset of 120K real-world physical-interaction videos spanning rigid-body dynamics, soft-body deformation, fluid phenomena, and phase transitions. Each video is annotated with structured descriptions of object properties and causal state transitions. Physics-aware supervised fine-tuning injects the physical priors into a bidirectional 14B DiT teacher, which we then distill into a lightweight 1.3B causal DiT for few-step autoregressive streaming generation. Finally, we use online reinforcement learning to incentivize the distilled model to generate physically plausible rollouts and further propose Temporal Credit Routing (TCR) to address temporal credit assignment. TCR evaluates physical consistency over overlapping temporal windows and routes the resulting group-relative advantages to temporally aligned denoising actions. On PhysicsIQ, PhyS improves the Wan2.1-14B teacher by 18.2\% and the Self Forcing, Rolling Forcing, and Causal Forcing by 23.7\%, 14.8\%, and 31.4\%, respectively. Results also improve the physics-aware video benchmarks VideoPhy, VideoPhy2, and PhyGenBench. The dataset, code, and more sample videos are available on our Project Page. --- ### The Voiceprint Fallacy: Why Voices Are Not Unique Biometric Imprints Authors: Tianle Yang, Cuiling Zhang, Chengzhe Sun, Siwei Lyu, Phil Rose Published: 2026-08-08 Categories: eess.AS, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2608.07980v2 In recent years, the term voiceprint has regained attention, particularly in technological applications and policy-making contexts, often carrying the assumption that a person's voice constitutes a stable and unique biometric trace analogous to a fingerprint. Yet this conception has been repeatedly criticized and rejected by forensic voice experts throughout the decades since its introduction. Although voices undoubtedly contain speaker-related information, this simplified conception obscures the highly dynamic and context-dependent nature of speech. This article revisits the voiceprint fallacy and reconsiders what can count as evidence of speaker identity by reviewing the historical development of voiceprint identification, evidence on human voice variability, developments in forensic voice comparison, research on human and automatic speaker recognition, and the recent challenge posed by deepfake speech to speaker identity. We point out that the voiceprint metaphor and its underlying implications are scientifically misleading because they transform a probabilistic source of speaker information into an imagined stable object of identity. We argue that speaker identity assessment does not require, and current evidence does not support, the existence of a stable and individually unique voiceprint. For speaker recognition and voice biometrics, this distinction motivates interpreting learned speaker representations with respect to the conditions under which they are trained and evaluated, and explicitly assessing their robustness to relevant sources of within-speaker variability, domain mismatch, and synthetic manipulation. --- ### Verication-driven closed-loop multi-agent large language modelframework for code-compliant structural design Authors: Jianbin Luo, Weibin Lin, Yiran Lin, Qing Wei, Wei Guo Published: 2026-08-08 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.07978v1 Multi-agent large language model(LLM)systems are applied to structural design,yet most use one-shot generation and cannot verify their output,leaving themill-suited to safety-critical tasks.Rather than trusting LLM self-correction,thisframework injects feedback from an external physics-based verier into a closedrepair loop.The framework couples a three-layernite-element verication systemwith a dual-node loop.Node 1 turns code violations into hard repair constraints,Node 2 turns a four-dimensional quality score into safety-rst soft constraints,and a retrieval-augmented code base makes every violation traceable to a clause.Overve structure types and 44 cases,code compliance rises from 56.8%to 98.6%and the composite score from 63.8 to 71.4(p<0.000001),using about 5.8%lessmaterial.Removing either node degrades performance,and compliance does notchange detectably across the two backbone LLMs tested,indicating that it ishere attributed to the external verier rather than the model.The framework,the 44-case benchmark and all experiment scripts are released as open source forreplicability. --- ### ZeroLock: Concurrent Memory-Efficient LLM Training via Modular Update Decoupling Authors: Wentao Dai, Xuanran Li, Yuxiang Zhang, Ming Tang, Chao Huang Published: 2026-08-08 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2608.07974v1 Large language model (LLM) fine-tuning at the edge adapts the model to scenario-specific data while preserving privacy. Although existing studies proposed pipeline parallelism to address the limited memory and computing resources of edge devices, they commonly rely on backpropagation (BP) training, which has a fundamental limitation of update locking and could experience severe throughput and memory bottlenecks. In this work, we propose a BP-free algorithm, called ZeroLock, that decouples the model updates into independent chunk updates by local objective construction. It breaks the update locking of BP and hence can improve throughput at the algorithm level and lower memory usage by reducing activation storage. To the best of our knowledge, we provide the first theoretical framework for such local objective construction-based approaches under general model chunk division by mapping local objectives to the global objective. We prove that ZeroLock has a convergence rate of $\tilde{\mathcal{O}}(1/\sqrt{T})$, which differs from BP only by polylogarithmic factors. We design a system for ZeroLock and build real-world prototypes, incorporating techniques such as early forwarding and failure recovery for efficient and robust implementation. Experiments on the prototype show that compared to BP-based baselines, ZeroLock reduces the memory by 26.5% and improves throughput by 4.9%. --- ### Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Authors: Chenrui Fan, Yize Cheng, Ming Li, Yongyuan Liang, Tianyi Zhou, Soheil Feizi Published: 2026-08-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.07968v2 Reasoning language models increasingly use test-time compute to improve performance, but existing evaluations typically study this compute one question at a time. Yet when multiple problems share an end-to-end cost or latency constraint, models must decide how to divide limited inference compute among them. We introduce an exam-style evaluation framework for studying this setting, in which a model must distribute one shared token budget across questions with different difficulty and point values to maximize its total score. Across several open and frontier reasoning models, we find that models fail to allocate a shared budget strategically across questions of varying difficulties and values. Models behave largely as greedy sequential solvers: they prioritize questions by presentation order, front-load effort on early questions, and remain insensitive to value, with these tendencies becoming more pronounced as the number of questions grows. Explicit planning prompts spread compute more evenly but do not produce value- or difficulty-aware prioritization. The same behavioral pattern extends from mathematical to code reasoning. These findings establish global budget allocation as a distinct capability that is not captured by conventional per-question evaluation and remains a challenge for current reasoning models. --- ### CyberAGENTS: Structured Autonomy for Agentic Gamified Learning in Cybersecurity Authors: Ivan Hornung, Deepthi Marasinghe Arachchige, Tharindu Kumarage, Garima Agrawal, Yuli Deng, Ying-Chih Chen, Huan Liu Published: 2026-08-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.07965v1 Gamification is especially effective in learning domains requiring active problem-solving and iterative skill-building, such as cybersecurity education. Generative AI agents offer a path to delivering such experiences adaptively at scale, but introduce well-documented risks in educational settings: inconsistent behavior, hallucinated reasoning, and misalignment with pedagogical frameworks. Grounding these systems in learning science is therefore essential. We present \model, an agentic framework for gamified cybersecurity learning that enables structured autonomy through ontology-guided validation, schema-governed behavioral control, and competency-based progression. The system is organized around a competency-based progression model that structures topics by difficulty and prerequisite relationships, reflecting evidence-based principles of scaffolded instruction. The learning loop is decomposed into four specialized agents: challenge, support, evaluation, and reward, each governed by behavioral schemas that encode operational modes and progression logic, bounding agent autonomy without eliminating generative flexibility. A cybersecurity ontology validates all generated content prior to display, enforcing domain-consistent reasoning and safety constraints. We evaluate CyberAgents through classroom deployment with undergraduate students, complemented by expert evaluations from educators and domain specialists. Results indicate improved engagement, clearer feedback interpretation, and greater learner trust in AI-generated responses when behavioral schemas and ontology validation are active. Preliminary comparisons with an unconstrained configuration further support the role of structured control in stabilizing instructional behavior. These findings offer a blueprint for designing pedagogically grounded agentic gamified learning systems. --- ### EasyBalance: Cross-Layer Load Balancing in Distributed MoE Inference Authors: Yize Wu, Ke Gao, Ling Li, Yanjun Wu Published: 2026-08-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.07964v1 Load Balancing has emerged as a critical problem in expert-parallel distributed inference of Mixture-of-Experts (MoE) models. As routing distributions are typically skewed across experts, devices hosting lighter-loaded experts must idle to wait for the heaviest during expert computing, leading to inefficiency. Existing load-balancing approaches primarily rely on expert replication or migration within each layer, which introduce additional overhead and limit their flexibility and scalability. To address this problem, we propose EasyBalance, a cross-layer load balancing strategy that requires no modifications to the expert-device mapping, enabling instant adaptability and incurring essentially no additional overhead. Our key insights are that (1) experts of other layers can be viewed as naturally redundant for the current layer, and (2) cross-layer MoE workloads can be jointly executed to mitigate their individual imbalance. Based on these observations, EasyBalance greedily schedules a subset of cross-layer workloads to run at each MoE step and defers the remaining workloads for future balancing opportunities, effectively leveraging cross-layer imbalance mitigation. Extensive experiments across models, tasks, and configurations demonstrate that EasyBalance consistently accelerates distributed MoE inference, reducing GPU idling by mostly over 40%. Code is available at https://github.com/yize-wu/EasyInfra. ---