# Research Papers — 2026-08 · bundle page 134 of 240 > Full-text markdown of papers #6651–6700 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/134 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/133.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/135.md) ### Algebraic Decomposition Theory for Transformer Length Generalization Authors: Andy Yang, Blerta Veseli, Corentin Barloy, Michaël Cadilhac, Andreas Krebs, Charles Paperman, Howard Straubing, Michael Hahn Published: 2026-08-13 Categories: cs.FL, cs.AI arXiv: https://arxiv.org/abs/2608.13433v1 Transformer-based language models are known to sometimes generalize to sequences longer than seen during training, but we lack a precise characterization of which tasks admit length generalization. It is not even known which regular languages transformers length-generalize on -- and this is a foundational class of languages. Our contributions are to establish the first complete characterization of which regular languages transformers length-generalize on and provide a decision algorithm running in polynomial time in the size of the language's syntactic monoid. These results rely on an effective characterization of the regular languages in C-RASP, a recently-established formalism that expresses which languages transformers length-generalize on. This characterization is challenging because classical tools like Krohn-Rhodes decomposition theory for finite semigroups are insufficient for C-RASP. Firstly, the basic building blocks of Krohn-Rhodes theory -- flip-flop and simple groups -- are not expressible in C-RASP. Secondly, the basic building block of C-RASP (unbounded counting) is not expressible by the finite semigroups of Krohn-Rhodes theory. Thus, length generalization on regular languages is controlled by an algebraic property that is invisible to classical finite decomposition theory. We generalize classical decomposition theory from finite semigroups to the infinite additive group on the integers, allowing us to characterize C-RASP in terms of iterated wreath products of the integers and derive a provable polynomial-time decision algorithm for regular language membership. Experiments across a broad test suite of regular languages confirm that our theory captures transformers' length-generalization behavior more accurately than existing classifications. --- ### Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity Authors: Irina Proskurina, Mayank Kumar, Oyindolapo O. Komolafe Published: 2026-08-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.13430v2 Instruction-tuned language models achieve strong performance across a range of generation tasks but have recently been shown to exhibit verbalized overconfidence, which may manifest in less diverse supporting rationales for incorrect answers. However, whether such overconfidence is associated with rationale consistency remains an open question. In this paper, we study whether changes in the lexical diversity of generated answer rationales accompany changes in model confidence induced by instruction tuning. We evaluate three matched base and instruction-tuned models across question-answering benchmarks and find that instruction tuning consistently increases answer confidence, despite limited changes in predictive accuracy, while degrading likelihood-based calibration. Secondly, we observe a non-uniform effect of instruction tuning on rationale diversity: cross-rationale diversity consistently decreases, whereas surface-level lexical diversity varies in both direction and magnitude across models and benchmarks. Finally, we find that these differences persist after controlling for answer selection and rationale length, confirming that confidence and rationale diversity capture distinct effects of instruction tuning. --- ### Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity Authors: Irina Proskurina, Mayank Kumar, Oyindolapo O. Komolafe Published: 2026-08-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.13430v1 Instruction-tuned language models achieve strong performance across a range of generation tasks, but have also recently been shown to exhibit verbalized overconfidence. In question answering, verbalized model overconfidence may be associated with the consistency of the generated supporting rationales. In this paper, we study whether corresponding changes in the lexical diversity of generated answer rationales accompany changes in model confidence induced by instruction tuning. We evaluate three matched base and instruction-tuned models across question-answering benchmarks and find that instruction tuning consistently alters answer confidence, despite limited changes in predictive accuracy and decreases in likelihood-based calibration. Secondly, we observe a non-uniform effect of instruction tuning on rationale diversity: cross-rationale diversity consistently decreases, whereas surface-level lexical diversity varies in both direction and magnitude across models and benchmarks. Finally, we find that these differences persist after controlling for answer selection and rationale length, confirming that confidence and rationale diversity capture distinct effects of instruction tuning. --- ### RAIL: An Automatic Classifier of the Artificial Intelligence Readiness Level Authors: Juan Irving Vasquez, Juan Terven, Laura-Ivoone Garay-Jimenez Published: 2026-08-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.13428v1 Assessing the maturity of artificial intelligence technologies is essential for investment decisions, project management, and policy monitoring, yet the available readiness frameworks are heterogeneous and difficult to apply automatically: the adaptation of Technology Readiness Levels to AI lacks AI-specific gating criteria, the Machine Learning Technology Readiness Levels presuppose access to internal process artifacts, and AI/data readiness dimension models employ scales that resist direct comparison. This paper makes two contributions. First, we unify these three frameworks into the Unified AI Readiness Level (AIRL), a nine-level ordinal scale built on an environmental evidence ladder and complemented by dimensional caps (covering specification, data existence, data quality, data legality, expert knowledge, and algorithmic maturity) together with a generality-anchoring rule and explicit assignment disciplines, so that a readiness level becomes decidable from a natural-language description of the work alone. Second, we propose RAIL (Readiness Assessment via Independent LLM-experts), a panel-of-experts classifier that operationalizes the scale: one evidence agent and six independent dimension agents, each a large language model with a narrowly scoped mandate, deliver verdicts that a deterministic minimum rule aggregates and a chief expert reviews under asymmetric authority, confirming or lowering the panel's recommendation but never raising it above the caps. The method was tested in the analysis of several research works showing consistency and avoiding overestimation from monolithic LLM classifiers. --- ### Reduced Matrix Multiplication: Input-Adaptive Matrix-Product Reduction for LLM Inference Authors: Zixuan Lan, Yanhong Li, Jiawei Zhou Published: 2026-08-13 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.13426v2 Transformer-based language models achieve strong performance but incur substantial inference cost due to repeated high-dimensional matrix multiplications. We propose Reduced Matrix Multiplication (RMM), a training-free, input-adaptive inference method that reduces Transformer matrix products by selecting informative slices along their contraction dimensions, without modifying model weights. Under a simple retention-ratio control, RMM provides a smooth and predictable accuracy-efficiency trade-off. Across language models ranging from 1B to 70B parameters, we find that reduction tolerance depends on the model family, task, component, and retention ratio, although it often improves with model scale. Under moderate reduction, RMM remains robust across the evaluated discriminative, autoregressive generation, and long-context settings. We further show that the same principle extends to multimodal vision-language inference. Mechanistic ablations reveal a structural asymmetry within Transformers: attention-side computations are substantially more reducible than MLP components. Finally, wall-clock benchmarks with custom kernels on an NVIDIA A100 show that these computational savings can translate into practical runtime gains, especially at longer sequence lengths. Together, these results position RMM as a scalable direction for input-adaptive inference-time optimization. --- ### Reduced Matrix Multiplication: Input-Adaptive Matrix-Product Reduction for LLM Inference Authors: Zixuan Lan, Yanhong Li, Jiawei Zhou Published: 2026-08-13 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.13426v1 Transformer-based language models achieve strong performance but incur substantial inference cost due to repeated high-dimensional matrix multiplications. We propose Reduced Matrix Multiplication (RMM), a training-free, input-adaptive inference method that reduces Transformer matrix products by selecting informative slices along their contraction dimensions, without modifying model weights. Under a simple retention-ratio control, RMM provides a smooth and predictable accuracy-efficiency trade-off. Across language models ranging from 1B to 70B parameters, we find that reduction tolerance depends on the model family, task, component, and retention ratio, although it often improves with model scale. Under moderate reduction, RMM remains robust across the evaluated discriminative, autoregressive generation, and long-context settings. We further show that the same principle extends to multimodal vision-language inference. Mechanistic ablations reveal a structural asymmetry within Transformers: attention-side computations are substantially more reducible than MLP components. Finally, wall-clock benchmarks with custom kernels on an NVIDIA A100 show that these computational savings can translate into practical runtime gains, especially at longer sequence lengths. Together, these results position RMM as a scalable direction for input-adaptive inference-time optimization. --- ### Motor, Cognitive, or Corpus? What Survives Cross-Lingual Transfer in Speech-Based Parkinsons Disease Detection Authors: Serli Kopar, Sam Gijsen, Abner Hernandez, Paula Andrea Perez-Toro, Kerstin Ritter Published: 2026-08-13 Categories: cs.CL, eess.AS, eess.SP arXiv: https://arxiv.org/abs/2608.13425v1 Self-supervised learning (SSL) speech representations achieve strong performance for Parkinson's disease (PD) detection within individual corpora. However, it remains unclear whether these models capture disease-related characteristics or exploit dataset-specific confounds, particularly since most SSL backbones are pretrained exclusively on healthy speech. To investigate this question, we perform a layer-wise analysis of nine SSL speech backbones using a low-capacity logistic regression probe across three languages. We structure the evaluation as multiple scenarios that progressively introduce distribution shifts in participant identity, recording conditions, language, and pathology. Our results reveal two key findings. First, layer selection is highly corpus-dependent: the optimal representation layer is determined primarily by the source dataset rather than by the SSL architecture itself. Second, the transferred discriminative signal lacks pathological specificity: classifiers trained to detect PD assign similarly high probabilities to both PD and dementia speech in the target corpus. These results highlight critical limitations that must be addressed before speech-based pathology recognition models can be reliably deployed in clinical settings. --- ### Enhancing Virtual Agents through SLMs and Edge-Computing: An Exploratory Evaluation of Think and Memory Processes Authors: Aimilios Hadjiliasi, Louis Nisiotis Published: 2026-08-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.13420v1 Embodied intelligent virtual agents are expected to operate as persistent, adaptive, and context-aware entities within complex virtual and Metaverse worlds. However, implementing cognitively capable agents in such environments is conceptually and technologically challenging. Among a range of blueprints and development approaches, the Cognitive Embodied Agent Architecture (CEAA) has been developed as an implementation-oriented framework for architecting components of perception, memory, reasoning, planning, and embodied action. Considering the recent advances in edge computing and generative AI language models, this paper explores the use of Small Language Models (SLMs) to support edge-based operation of selected CEAA components, focusing on "Think" and "Memory" as processes central to cognitive orchestration and persistence of virtual agents in interactive virtual worlds. An edge-based virtual agent gateway system was developed and evaluated on an NVIDIA Jetson Orin NX using Qwen2.5 models of different sizes, exploring the system's capability to process service requests and handle memory-driven conversations. A series of simulation experiments evaluated routing accuracy, memory-read performance, and latency, demonstrating an SLM-driven prototype agent system that partially implements selected CEAA processes to support the development of embodied agents whose cognitive "brain" can operate efficiently and contextually for interactive experiences in immersive virtual worlds. --- ### Wasserstein Filtering: A Sample Selection Method for Robust Distribution Learning Authors: Yikai Xu, Zhao Chen, Jian Huang Published: 2026-08-13 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.13418v1 Given a dataset where a portion of the samples are contaminated, our goal is to recover the underlying clean population distribution. To this end, we propose Wasserstein Filtering (WF), a novel sample selection framework that discards a fraction of suspicious samples and estimates the target distribution using the empirical measure of the remaining data. The core insight is to select a subset of samples whose empirical distribution maximizes its Wasserstein distance to the fully contaminated empirical distribution, thereby preferentially isolating and removing geometrically influential outliers. To render this optimization computationally tractable, we introduce three algorithms: a marginal screening scheme, SinkMarg, and two joint optimization algorithms, SinkWF and SlicedWF, leveraging entropic optimal transport and sliced Wasserstein approximations, respectively. On the theoretical front, we introduce the Far Exclusion and Local Projection (FELP) contamination model, which characterizes corruptions consisting of well-separated outliers and locally indistinguishable perturbations. Under this model, we prove that the WF estimator achieves minimax optimality over distribution families with bounded covariance. Extensive numerical experiments on synthetic datasets, benchmark anomaly detection suites, and robust generative learning with diffusion models demonstrate that WF serves as a highly practical, model-agnostic preprocessing tool. It delivers competitive outlier detection performance and provides substantial downstream benefits for generative modeling under heavy contamination. --- ### Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development Authors: Yiwei Li, Wanli Yang, Hexiang Tan, Xiangzhou Huang, Zhengyu Chen, Ziran Li, Borun Chen, Shanglin Lei, Huaisheng Zhu, Hao Tian, Fei Sun, Xunliang Cai et al. Published: 2026-08-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.13417v1 Autonomous agents are increasingly capable of improving models, systems, and other technical artifacts through long-horizon experimentation. To understand the current state of this capability, however, evaluation must go beyond final scores, which neither reveal where progress is gained or lost nor indicate whether accumulated experience improves later decisions. We therefore present a systematic evaluation of seven frontier models on 36 long-horizon tasks based on a new framework that uses rule-based metrics to characterize within-run behavior through Solution Framing, Execution, and Feedback Control and controlled comparisons to assess experience reuse within and across tasks. The results show that current agents operate more like engineering optimizers than fully autonomous researchers: they can formulate and implement practical solutions, but their performance varies substantially across runs, their strongest solutions mainly adapt or combine established techniques, and genuine methodological novelty remains rare. Detailed analysis reveals that observed performance is shaped by multiple factors, including distinct process bottlenecks behind similar final outcomes, experience reuse that can help or mislead subsequent decisions, and harness designs that affect performance stability. These findings suggest concrete directions for improving model training, inference-time strategies, experience management, and harness design. --- ### StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs Authors: Joya Chen, Zeyun Zhong, Mike Zheng Shou Published: 2026-08-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.13416v4 Humans effortlessly perceive the present while remembering the past, yet streaming VLMs often trade off real-time perception against long-term memory. Prior work shows that shortening the context can sharpen current-scene perception at the expense of long-range recall. To reconcile these abilities, we introduce StreamTTT, which writes long-range history into online-updated fast weights outside the attention context. This leaves a short sliding key-value cache dedicated to recent evidence, mitigating attention dilution. We train StreamTTT jointly on offline long-video QA and a newly constructed real-time QA corpus. On OVO-Bench, under each model's reported input protocol, StreamTTT-4B outperforms the same-scale SimpleStream-4B by 0.6 points in real-time perception and 5.3 points in backward tracing. It also surpasses the larger SimpleStream-8B by 0.73 points on StreamingBench's Real-Time Visual Understanding (RTVU) subset. Our code is publicly available at https://github.com/zeyun-zhong/StreamTTT. --- ### StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs Authors: Joya Chen, Zeyun Zhong, Mike Zheng Shou Published: 2026-08-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.13416v1 Humans effortlessly perceive the present while remembering the past, yet streaming VLMs often trade off real-time perception against long-term memory. Prior work shows that shortening the context can sharpen current-scene perception at the expense of long-range recall. To reconcile these abilities, we introduce StreamTTT, which writes long-range history into online-updated fast weights outside the attention context. This leaves a short sliding key-value cache dedicated to recent evidence, mitigating attention dilution. We train StreamTTT jointly on offline long-video QA and a newly constructed real-time QA corpus. On OVO-Bench, StreamTTT-4B outperforms SimpleStream-4B by 1.4 points in real-time perception and 3.7 points in backward tracing. It also remains competitive with the larger SimpleStream-8B on the Real-Time Visual Understanding (RTVU) subset of StreamingBench. Our code will be released. --- ### Deliberate Practice: Learning Robot Skills under a Budget Authors: Shivam Vats, Sudarshan Harithas, Mete Tuluhan Akbulut, Arvind Raghunathan, George Konidaris Published: 2026-08-13 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.13415v1 We consider the problem of autonomously learning robot skills under a limited practice budget for sequential tasks. We propose an active skill learning algorithm, \emph{Deliberate Practice (DP)}, that computes a provably \emph{budget-optimal} allocation---practicing skills that maximize expected cumulative reward while being learnable within the budget. DP estimates both the time needed to master skills and the cumulative reward of the task plans that the skills unlock. Computing a budget-optimal allocation is challenging as it requires reasoning about combinatorially many skill plans over a large practice budget. Our key contribution is a bilinear program that can compute this exactly using off-the-shelf solvers. Through simulated and real-world experiments on long-horizon manipulation tasks, we show that our approach allows robots to optimally use limited practice time to acquire useful policies and improve long-horizon planning. --- ### Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings Authors: Mirko Tritella, Riccardo Pozzi, Matteo Palmonari Published: 2026-08-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.13410v1 Parliamentary proceedings are a primary record of democratic deliberation, yet their volume and fragmentation make multi-perspective access difficult for citizens, journalists, and researchers. Applying Retrieval-Augmented Generation (RAG) to parliamentary transcripts introduces three specific risks: dominance of the most frequent speakers, inability to weight speakers according to topical expertise, and citation misattribution in politically sensitive text. We present ParliamentRAG, a RAG system for the Italian Chamber of Deputies that addresses these risks jointly. Its core contribution is a topic-dependent authority model that estimates each speaker's authority as a function of the current query, combining interpretable components such as profession, education, and previous interventions. Given a user query, the system retrieves relevant speech chunks, identifies topic-relevant experts across parliamentary groups, and generates a summary synthesizing their perspectives, accompanied by supporting quotations. ParliamentRAG is evaluated against Google NotebookLM on 15 policy topics via a two-level protocol combining automated metrics and blind A/B human evaluation by six domain experts. The system achieves higher coverage across political groups (0.97 vs. 0.95), perfect quotation faithfulness (1.00 vs. 0.95), and stronger expert preferences on source-related dimensions, while NotebookLM remains stronger on prose-oriented dimensions. --- ### Jointly Predicting Courses and Grades Using a Transformer-Based Model Authors: Paul Savala Published: 2026-08-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.13409v1 Existing predictive models in learning analytics often treat student academic history as a simple sequence, overlooking the concurrent nature of courses taken within a semester. This simplification can lead to inaccurate performance predictions, particularly for students with heavy or challenging course loads. This paper introduces a TRansformer for Academic Course-grade Estimation (TRACE) that addresses this limitation by jointly predicting both the set of courses a student will take and their corresponding grades for an upcoming semester. Our approach encodes courses on a per-semester basis to capture the effects of course concurrency and utilizes a novel loss function combining course-set prediction with grade prediction. We demonstrate that predicting courses taken in addition to the grades in those courses leads to significant improvements in prediction quality. Trained on ten years of institutional data, our joint prediction model reduces mean absolute error by nearly 50% compared to an identical architecture that predicts grades alone. The model also outperforms traditional LSTM-based sequential models, as well as graph neural network-based approaches, and offers natural ways to incorporate student attribute data. This work demonstrates the utility of modern neural architectures for creating interpretable models that can be adapted to new institutions via retraining and recalibration, as well as the importance of key techniques, such as predicting courses taken during training. We discuss how this model could be incorporated into early detection systems at institutions of higher education. --- ### Heterogeneity-Aware Belief Synchronization for Semantic Communication in AI-Native 6G Networks Authors: Muhammad Hannan Akram, Muhammad Abubakar Rashid, Wassi Haider Kabir, Haejoon Jung, Kapal Dev, Syed Ali Hassan Published: 2026-08-13 Categories: eess.SP, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.13394v1 6G networks will not be serving as communication infrastructures only; rather, they are expected to evolve into intelligent systems, where thousands of autonomous artificial intelligence (AI) agents are interconnected. The agents are deployed across a wide range of platforms including low Earth orbit (LEO) satellites, high-altitude platforms (HAPs), unmanned aerial vehicles (UAVs), edge servers, and terrestrial devices. These agents continuously observe their environment and exchange information. Semantic communication provides an efficient mechanism for exchanging meaningful information instead of raw data. However, its effectiveness depends on the communicating agents having sufficiently aligned beliefs to correctly interpret and decode the transmitted messages. This assumption becomes difficult to satisfy in the 6G network where heterogeneous AI models operate under diverse computational constraints and continuously acquire different knowledge from their local environments. This article presents a heterogeneity-aware belief synchronization framework for 6G AI-native networks. It uses latent translation models deployed on multi-access edge computing (MEC) servers. These models translate belief updates from one agent to agent-specific knowledge without requiring joint training and a homogeneous architecture of models. By exchanging compact belief updates through a latent translation model only when necessary, the framework preserves privacy, reduces synchronization cost, and minimizes local knowledge drift. We validate the framework through a case study on a multi-layered terrestrial/non-terrestrial network. Results demonstrate that it maintains low synchronization cost, measured by the number of parameters transmitted, and low belief alignment error across the heterogeneous agents in the case study. --- ### Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation Authors: Hmrishav Bandyopadhyay, Xuanchi Ren, Zijian Huang, Jay Zhangjie Wu, Tianshi Cao, Ruilong Li, Bryan Chu, Sanja Fidler, Yi-Zhe Song, Zian Wang Published: 2026-08-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.13391v1 Interactive autoregressive video generation demands both low-latency rollouts and precise online control. Few-step distillation accelerates generation by reducing denoising steps, while online control imposes a causal constraint: frames and blocks should depend on history and controls available during generation. Existing video distribution matching distillation (DMD) pipelines, however, often supervise causal few-step students using bidirectional teachers that score complete clips. The score for a target can therefore depend on future frames and controls that were unavailable when the student generated it, misaligning teacher supervision with the student's causal information set. We introduce Context-Matched Distillation (CMD), a causal DMD framework that aligns teacher supervision with the information available when each target is generated. CMD replaces bidirectional full-clip scoring with a causal teacher that evaluates each target without access to future frames or controls. The same causal teacher initializes the few-step student, establishing a consistent causal formulation across teacher training, student distillation, and inference. Beyond aligning the temporal information boundary, Prefix Scoring matches supervision to the student's realized rollout context by evaluating each target under the cached student-generated prefix that produced it. Prefix Corruption further stabilizes training by perturbing unreliable prefixes produced early in training while preserving this target-context alignment. With a simple causal formulation, CMD naturally extends to frame-wise and chunk-wise generation, long video distillation, and camera-conditioned distillation. Experiments demonstrate state-of-the-art aggregate performance among autoregressive methods on both short- and long-video benchmarks, together with substantially improved adherence to time-varying camera controls. --- ### TopoIntent: Compiling Security Intent into Executable, Compliance-Checked Network Topologies Authors: Xiaokang Qu, Jianliang Ma, Zao Fan, Tianshu Chu, Tianlong Fan, Linyuan Lü Published: 2026-08-13 Categories: cs.AI, cs.CR, cs.NI arXiv: https://arxiv.org/abs/2608.13389v1 Enterprise security topology design requires translating business intent, regulatory requirements, and risk assumptions into zones, boundary devices, inter-zone paths, and access-control policies. Existing NetOps automation tools mainly operate after this design is fixed, providing limited support for generating structured security topologies from underspecified natural-language requirements. We present TopoIntent, a system that compiles security intent into executable, compliance-checked network topologies. It uses a schema contract to constrain generation, retrieves reference architectures from a curated template library via dense-vector search, and applies staged fusion for intent-template alignment and security completion. The generated topology is checked against CIS Controls v8.1.2 safeguards visible at the topology layer, while unresolved cases are marked for manual review. Structural gaps are repaired through additive schema-preserving edits. The final topology is exported to Mininet scripts with kernel-level iptables ACLs, enabling executable reachability and allow/deny tests. Because no public benchmark exists for this requirement-to-topology task, we construct an evaluation set from reference security architecture diagrams. The retrieval set contains 22 templates and 44 synthetic intents across five scenarios, while the held-out set contains 7 templates and 14 intents from finance and government scenarios excluded from retrieval. On the held-out set, additive repair improves topology-visible CIS satisfaction from 0.78 to 1.00 in fewer than 1.5 rounds on average, and one feedback round raises the post-ACL policy pass rate from 0.78 to 0.88. --- ### CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation Authors: Enhan Li, Junhao He, Hongyang Du Published: 2026-08-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.13387v4 On-policy distillation (OPD) supervises a student language model on trajectories sampled from its current policy, but assigns equal credit to response tokens with unequal supervision value. Selective OPD addresses this limitation by allocating supervision non-uniformly across response tokens according to their estimated training value. Most existing criteria, however, focus primarily on optimization need, such as uncertainty or teacher-student disagreement, while task relevance, namely whether the supervision is tied to the semantic content of the current input, remains less directly characterized as a complementary dimension. To address this gap, we introduce Counterfactual Relevance for On-Policy Distillation (CROP), which operationalizes task relevance through a paraphrase-calibrated counterfactual sensitivity margin. For each source prompt, CROP constructs a validated original-paraphrase-counterfactual triplet, holds the student rollout fixed, and measures each response position by its sensitivity to a task-relevant condition change calibrated by its sensitivity to a meaning-preserving rewrite. Matched selection controls show that CROP identifies more useful supervision positions than random or lowest-relevance selection, while component comparisons confirm the value of both counterfactual sensitivity and paraphrase calibration. Across two teacher-student settings, CROP improves aggregate performance by 1.92 and 2.96 points over the strongest non-CROP selector. These results support task relevance as a complementary criterion for selective OPD and establish CROP as a model-internal, contrast-specific method for allocating token-level supervision. --- ### CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation Authors: Enhan Li, Junhao He, Hongyang Du Published: 2026-08-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.13387v1 On-policy distillation (OPD) supervises a student language model on trajectories sampled from its current policy, but assigns equal credit to response tokens with unequal supervision value. Selective OPD addresses this limitation by allocating supervision non-uniformly across response tokens according to their estimated training value. Most existing criteria, however, focus primarily on optimization need, such as uncertainty or teacher-student disagreement, while task relevance, namely whether the supervision is tied to the semantic content of the current input, remains less directly characterized as a complementary dimension. To address this gap, we introduce Counterfactual Relevance for On-Policy Distillation (CROP), which operationalizes task relevance through a paraphrase-calibrated counterfactual sensitivity margin. For each source prompt, CROP constructs a validated original-paraphrase-counterfactual triplet, holds the student rollout fixed, and measures each response position by its sensitivity to a task-relevant condition change calibrated by its sensitivity to a meaning-preserving rewrite. Matched selection controls show that CROP identifies more useful supervision positions than random or lowest-relevance selection, while component comparisons confirm the value of both counterfactual sensitivity and paraphrase calibration. Across two teacher-student settings, CROP improves aggregate performance by 1.92 and 2.96 points over the strongest non-CROP selector. These results support task relevance as a complementary criterion for selective OPD and establish CROP as a model-internal, contrast-specific method for allocating token-level supervision. --- ### When Is a Task Vector Enough? An Empirical Theory of Implicit Multimodal ICL Authors: Jiaqian Li Published: 2026-08-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.13385v1 Implicit multimodal in-context learning compresses demonstrations into internal interventions, ranging from static task vectors to query-conditioned transformations and attention routing. Despite their common goal, these methods differ substantially in how the intervention depends on the query and where it modifies the model, leaving unclear which additional complexity is necessary for a given task. We propose the Selection--Realization Hypothesis. It views demonstrations as inducing a compact family of internal changes from which the query selects, while the model's computation constrains how the selected change can be implemented. We evaluate this account using controlled multimodal tasks in which query dependence varies without changing the underlying task primitives or prompt format. By contrasting correct demonstrations with matched counterfactuals, we measure the structure of explicit M-ICL and test whether it predicts intervention behavior. We find that the success of a static task vector is closely tied to how much of the demonstration-induced change is shared across queries. Additional intervention complexity becomes useful when explicit M-ICL contains query-specific or distributed structure that a local additive shift cannot recover. These relationships extend to natural VQA benchmarks and support cost-aware method selection without access to test performance. Our results provide a unified empirical theory of when demonstrations can be compressed into a task vector and when a more expressive intervention is warranted. --- ### Reconstructing Historical Manuscripts through MSI: The Potential of Contrast in Assessing Image Quality and Legibility Authors: Anna Breger Published: 2026-08-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.13381v1 Digital restoration of historical manuscript images aims to improve readability while preserving the authenticity of cultural heritage documents. However, evaluating quality of restored manuscripts remains challenging, where readability is often subjective and expert annotations are scarce. This study investigates the suitability of contrast-based image quality measures to assess quality and legibility of reconstructed manuscript images from multi-spectral imaging. Two experiments were conducted with publicly-available data sets, facilitating manual quality scores by experts and full-reference image quality measures as reference evaluations. The results show that potential contrast achieves the highest correlation with expert ratings, while contrast-to-noise ratio demonstrates the strongest agreement with full-reference quality measures. Overall, contrast-based measures consistently outperform general image quality measures, demonstrating their potential as objective indicators of manuscript legibility and reconstruction quality. --- ### Sign Language Video Synthesis via Loss-Guided Multi-Expert GANs Authors: Dingzhan Nong, Zhihao Ren, Ziqi Li, Tim Lo Published: 2026-08-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.13368v2 This preliminary technical report presents a framework for sign language video synthesis using a loss-guided multi-expert Generative Adversarial Network (GAN) to enhance communication for individuals with hearing impairments. Three specialized discriminators -- global, hand, and head -- each guide a corresponding expert branch in the generator toward a distinct visual region, enabling implicit feature specialization without explicit diversity losses. To stabilize this multi-discriminator system, whose early-phase training otherwise exhibits chaotic dynamics, we introduce a United Loss consensus mechanism that regularizes each discriminator toward the ensemble average at a 10% weight. Each branch further adopts a dual-pathway convolutional-transformer design with learnable AdaptiveFeatureFusion, balancing the stability of convolutions against the detail of windowed self-attention. The generator is trained using an alternating three-mode schedule (discriminator, holistic generation, branch-specialized generation). On a custom 156GB dataset with a filtered test set that removes easy and repetitive samples, our 0.2B-parameter variant achieves 29.8 PSNR (0.959 SSIM) and the 1.3B-parameter variant achieves 30.7 PSNR (0.965 SSIM), with inference VRAM footprints of 1.5 GB and 8 GB respectively, enabling deployment on consumer-grade hardware. Full ablation studies remain ongoing due to the 2-3 month training cycle on a single GPU. The system was showcased at the 2025 Hong Kong Frontier Technology Summit. --- ### Sign Language Video Synthesis via Loss-Guided Multi-Expert GANs Authors: Dingzhan Nong, Zhihao Ren, Ziqi Li, Tim Lo Published: 2026-08-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.13368v1 This preliminary technical report presents a framework for sign language video synthesis using a loss-guided multi-expert Generative Adversarial Network (GAN) to enhance communication for individuals with hearing impairments. Three specialized discriminators -- global, hand, and head -- each guide a corresponding expert branch in the generator toward a distinct visual region, enabling implicit feature specialization without explicit diversity losses. To stabilize this multi-discriminator system, whose early-phase training otherwise exhibits chaotic dynamics, we introduce a United Loss consensus mechanism that regularizes each discriminator toward the ensemble average at a 10% weight. Each branch further adopts a dual-pathway convolutional-transformer design with learnable AdaptiveFeatureFusion, balancing the stability of convolutions against the detail of windowed self-attention. The generator is trained using an alternating three-mode schedule (discriminator, holistic generation, branch-specialized generation). On a custom 156GB dataset with a filtered test set that removes easy and repetitive samples, our 0.2B-parameter variant achieves 29.8 PSNR and the 1.3B-parameter variant achieves 30.7 PSNR, with inference VRAM footprints of 1.5 GB and 8 GB respectively, enabling deployment on consumer-grade hardware. Full ablation studies remain ongoing due to the 2-3 month training cycle on a single GPU. The system was showcased at the 2025 Hong Kong Frontier Technology Summit. --- ### When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Authors: Shuhan Wang, Yilin Luo, Nan Xu, Chi Wang Cheung Published: 2026-08-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.13365v1 Rotation-based post-training quantisation commonly applies an orthogonal transform across an entire attention head to reduce outlier-induced error. RoPE instead partitions each head into two-dimensional frequency pairs, raising the question of whether a transform respecting this decomposition can improve on full-head mixing. Prior work has established the per-pair rotations that commute with RoPE. We state the converse result that, for distinct frequencies, no other single-head orthogonal map commutes with RoPE. For the head-shared parameterisation used in our experiments, we then derive the rotation angle that minimises the larger channel variance under a pooled-covariance, position-averaged surrogate and verify that the implementation attains its analytic minimum. The evaluated head-shared pairwise configuration does not improve accuracy in the tested dynamic W4A4KV4 setting. Across four checkpoints, replacing the full-head Hadamard with this configuration increases perplexity at both short and long context lengths. Composing the pairwise rotation with the Hadamard satisfies the selected $\pm0.05$-PPL interval criterion under the default estimator. Estimating the shared angle from K alone improves pairwise-only on every checkpoint but does not close its gap to full-head mixing. The analytic objective controls a position-averaged second moment of a pooled calibration covariance, whereas the dynamic quantiser sets its step from a tokenwise group range. The pairwise transform also has only two-channel mixing support. Along a controlled interpolation from two-channel to full-head mixing, K range, relative quantisation error, and perplexity degradation decrease as support increases. These results show that optimality for a structured surrogate need not reduce quantisation error when the surrogate and mixing support are misaligned with the quantiser's scale-setting statistic. --- ### Rules or Character? Scaling Laws for AI Safety Design Authors: Satoshi Takahashi, Nobuji Kouno, Masaaki Komatsu, Ryuji Hamamoto Published: 2026-08-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.13345v1 Artificial Intelligence (AI) safety systems combine character shaping (e.g., Reinforcement Learning from Human Feedback (RLHF), Constitutional AI), which modifies behavioral distributions at training time, with rule enforcement (e.g., output filters, safety classifiers), which blocks harmful outputs at inference time, yet little formal analysis exists on how their optimal balance should change as deployment scales increase. We introduce a stylized comparative-statics model that parameterizes safety design as a resource allocation alpha in (0,1) between these two approaches, incorporating scale-dependent filter degradation, common-mode failures, and character fragility -- the risk that shaped behavior degrades or collapses under novel conditions. Under a multiplicative Pareto damage model, we derive closed-form expected harm and supplement it with tail-risk (CVaR) analysis via Monte Carlo simulation. Across three scenarios (optimistic, moderate, pessimistic), the optimal alpha* is interior or at the rules-only boundary and shifts weakly toward character shaping as deployment scale T grows, from negligible (Delta alpha* = +0.01) to pronounced (Delta alpha* = +0.21) depending on scenario. The dominant parameter is the baseline character fragility rate p^(0)_frag, which shifts alpha* by 0.50 across its range -- far exceeding the effect of tail severity, filter quality, or common-mode failure probability. CVaR and expected-harm optima converge at large T. These results suggest that safety architecture decisions depend less on deployment scale per se than on the reliability of character shaping under distributional shift. --- ### LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning Authors: Yupan Ding, Jing Xiao, Zhenyuan Zhang, Chaofeng Chen, Liang Liao, Gui-Song Xia, Mi Wang Published: 2026-08-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.13344v1 Long-horizon Earth observation reasoning requires models to organize multi-stage geographic evolution, localize spatial changes, detect temporal anomalies, and infer future from extended image sequences. However, existing remote sensing vision-language models mainly focus on isolated images, image pairs, or short sequences, limiting reliable grounding in the relevant frames and regions. We introduce LongEarth-Bench, a benchmark containing approximately 120k question-answering samples derived from 117k unique images. Its sequences average 15.14 frames and extend to 30 frames, covering 12 tasks across evolution summarization, spatial reasoning, anomaly identification, and logical prediction. A 30k-sample subset further provides structured reasoning traces linking key frames and changed regions to final answers. We develop LongEarth through supervised fine-tuning with explicit sequence identifiers and structured chain-of-thought supervision. Building on LongEarth, LongEarth-R1 applies group relative policy optimization with format, temporal, and spatial rewards. LongEarth-R1 achieves the best results on all 12 long-sequence tasks while remaining competitive on standard remote sensing benchmarks. --- ### AmalthAI: An Open-Source Computer Vision Platform for Cultural Heritage Authors: Christos Chatzisavvas, Stelios Alvanos, Efstratios Politis, Panagiotis Rigas, Thomas Pappas, Ioannis Giannoukos, Nikolaos Mitianoudis, Agata Ulanowska, Katarzyna Żebrowska, Nazarij Buławka, Christina Margariti, George Pavlidis et al. Published: 2026-08-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.13343v1 Computer vision (CV) and machine learning (ML) offer new tools for cultural heritage (CH) artifact analysis, but the CV/ML pipeline remains largely inaccessible to CH domain experts, who lack the background to configure, train, or assess models. We present AmalthAI, an open-source CV platform that bridges this gap, enabling non-ML CH experts to independently produce and validate archaeologically meaningful findings. The interface covers dataset management, training, and inference for classification, segmentation, and object detection, with Kubeflow and Katib handling scalable training and hyperparameter search. Grad-CAM localizes the image region behind a prediction, and a vision-language model (VLM) adds a text description of it for expert review. Since archaeological data is often state-owned or rights-encumbered and cannot leave institutional custody, AmalthAI's self-hostable deployment ensures sensitive data is kept within premises. We test the platform on an archaeological use case built on a custom dataset of clay textile imprints, where CH experts trained and validated segmentation, and classification models for hypothesis testing. We provide the implementation code at https://github.com/TEXTaiLES/AmalthAI. --- ### Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and analysis from molecules to complex samples Authors: Yusen Tan, Yixuan Chen, Zheng Fang, Pan Liu, Yifan Li, Qinyu Guo, Zhedong Lin, Yuqiang Li, Xiangxiang Zeng, Tong Wang, Jun Xia Published: 2026-08-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.13341v2 Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Conventional interpretation is labor-intensive, relies on prior knowledge and reference spectra, and is difficult to scale, whereas most machine-learning methods are tailored to individual tasks or datasets, require large labeled training sets, and transfer poorly across analytical objectives and experimental datasets. Here we introduce UltraIR, a foundation model for IR spectroscopy with more than 100 million parameters that enables simulation-to-real transfer learning for chemical sensing and analysis from molecules to complex samples. UltraIR is pretrained on approximately 60 million simulated IR spectra using spectral reconstruction, molecular fingerprint similarity alignment, and functional-group prediction, then adapted to downstream objectives with task-specific labels or targets. Across functional-group prediction, molecular structure elucidation, physicochemical property prediction, mixture-component identification and quantification, bacterial classification, medicinal-herb geographic origin traceability and constituent quantification, microplastics classification, and soil property prediction, UltraIR outperforms conventional machine-learning and task-specific deep-learning baselines. It performs strongly with limited labeled experimental spectra and in zero-shot inference for the same analytical task across Fourier-transform infrared spectrometers and laboratories, providing a route to adaptable, data-efficient chemical sensing from complex real-world samples. --- ### Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and analysis from molecules to complex samples Authors: Yusen Tan, Yixuan Chen, Zheng Fang, Pan Liu, Yifan Li, Qinyu Guo, Zhedong Lin, Yuqiang Li, Xiangxiang Zeng, Tong Wang, Jun Xia Published: 2026-08-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.13341v1 Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Conventional interpretation is labor-intensive, relies on prior knowledge and reference spectra, and is difficult to scale, whereas most machine-learning methods are tailored to individual tasks or datasets, require large labeled training sets, and transfer poorly across analytical objectives and experimental datasets. Here we introduce UltraIR, a foundation model for IR spectroscopy with more than 100 million parameters that enables simulation-to-real transfer learning for chemical sensing and analysis from molecules to complex samples. UltraIR is pretrained on approximately 60 million simulated IR spectra using spectral reconstruction, molecular fingerprint similarity alignment, and functional-group prediction, then adapted to downstream objectives with task-specific labels or targets. Across functional-group prediction, molecular structure elucidation, physicochemical property prediction, mixture-component identification and quantification, bacterial classification, medicinal-herb geographic origin traceability and constituent quantification, microplastics classification, and soil property prediction, UltraIR outperforms conventional machine-learning and task-specific deep-learning baselines. It performs strongly with limited labeled experimental spectra and in zero-shot inference for the same analytical task across Fourier-transform infrared spectrometers and laboratories, providing a route to adaptable, data-efficient chemical sensing from complex real-world samples. --- ### Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation Authors: Valentin Noël Published: 2026-08-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.13337v1 Sparse autoencoders are meant to name the things a language model computes, and the usual way to check that a latent matters is to switch it off and see what changes. But a latent fires at many tokens, and the effect has to be measured at one of them. The convention is to measure where the latent fires hardest. That choice is almost never reported, and it is not made by the experimenter: it is made by the dictionary under evaluation. Change the dictionary and the measurement moves to a different token. We show this is not a detail. Take two sparse autoencoders released by Google for the same model and match their latents by decoder similarity: even among the pairs the two dictionaries encode almost identically, they pick different tokens for a large share of them. Two dictionaries compared under the usual protocol are therefore very often compared at different places. To separate the convention from the dictionaries we train six autoencoders from one initialisation, differing only in fitting choices, so that a latent means the same thing in each. Most of the variance such a comparison reads as "these dictionaries disagree about this latent" turns out to be the position instead: it falls from 7.6% and 11.9% of variance to near zero once every dictionary is measured at the same token. More evaluation data does not rescue it. Across a sixteenfold range of corpus sizes the dictionaries agree less about where to measure, not more, so the problem grows with scale. The correction is one line of evaluation code. We give the protocol an ablation-based causal number must report to be comparable across papers, and an audit of five published papers against it. In short: a causal number reported without its position describes the token it was taken at as much as the latent it was taken from. --- ### Neural Quadratic Forms: A Unified Minimal Model for Sudden Learning and Scaling Laws Authors: Liu Ziyin, Yizhou Xu, Tomaso Poggio, Isaac Chuang Published: 2026-08-13 Categories: cs.LG, cond-mat.dis-nn, cond-mat.stat-mech arXiv: https://arxiv.org/abs/2608.13335v1 Neural networks trained by gradient descent on a smooth cost function can nevertheless learn in steps: the cost holds on long plateaus and then drops abruptly. Meanwhile, training losses instead follow smooth power laws. Variants of both behaviors occur in architectures with very different microscopic structures, which is the signature of a few relevant collective variables. We show that a symmetry fixes what those variables are: a network layer is a sum over interchangeable units, so relabeling the units leaves it unchanged; given smoothness and the condition that a unit's gradient vanish at the origin, symmetry then enforces a universal leading form for the expansion about the near-zero weights present at the start of training, the quadratic $\Tr(WW^{\top}A(x))$, in which every architectural detail is confined to a single ``structure matrix" $A(x)$ that we compute for each architecture. Perceptrons, attention layers, mixtures of experts, and convolutions become one model at different $A$. Its training dynamics then close on the ``order parameter" $M=WW^{\top}$ and, whenever the data matrices share an eigenbasis, reduce to a Lotka--Volterra equation whose modes switch on one after another. The smaller the initial weights, the further apart the switch-on times, and the plateaus appear as a singular limit of a smooth flow; when many modes are unresolved the same events merge into a power law in training time whose exponent the theory predicts. We confirm both numerically across training methods and architectures. --- ### RippleMem: From Isolated Retrieval to Associative Recollection for Long-Term Agent Memory Authors: Jingbo Ji, Lingyi Li, Xilong Cheng, Yuhao Zhou, Wenji Zhang, Yuting Tan, Yunxiao Qin Published: 2026-08-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.13334v1 LLM-based agents increasingly rely on external memory to support long-horizon reasoning and interaction. However, the main bottleneck is not simply storing past experience, but recovering the right set of evidence when relevant information is distributed across many interactions. Existing approaches struggle with this access problem. Full-context methods require noisy long-context search, flat retrieval often returns isolated and incomplete records, and graph-based memory systems can be expensive to construct while compressing rich event context. We introduce RippleMem, a long-term memory system that replaces one-shot retrieval with adaptive associative recollection. Inspired by cue-dependent episodic retrieval and associative completion, RippleMem stores interaction history as cue-rich episodic memory units and organizes them in an event-centric memory graph. Given a query, it first recalls relevant memory anchors through hybrid cues, then expands from these anchors along semantic and structural associations to recover missing supporting evidence. In this way, initially recalled memories serve not only as answer context, but also as cues for completing the evidence needed to answer. Experiments on LoCoMo and LongMemEval-S show that RippleMem achieves the best overall performance across evaluated settings, improving LLM-as-a-Judge accuracy by 3.95% on LoCoMo and up to 11.87% on LongMemEval-S, while reducing graph construction cost by about 30x. --- ### LLM-Guided Graph Generation for Structure-Based Local Improvement Methods Authors: Hai Xia, Vaidyanathan Peruvemba Ramaswamy, Stefan Szeider Published: 2026-08-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.13333v3 Large neighborhood search normally selects a random subset of decision variables for iterative optimization. To efficiently solve various problems, researchers tend to design variable selection strategies that take into account structural features across different domains. In this paper, we build an automatic pipeline that is problem-agnostic to all problems in the MiniZinc format. By prompting an LLM with our semantic guidelines, we guide the LLM to produce a graph generator that maps any instance of a problem type to a uniform weighted graph, where nodes represent decision variables and edges represent constraint relationships. These problem-agnostic graphs guide our structure-based local improvement (SLIM) framework for variable selection. Meanwhile, the weighted graph enables all problem instances to share the same generic graph representation, from which the same graph features can be extracted and used for configuration selection. We evaluated our pipeline on instances across 20 MiniZinc competition problems, finding that algorithm selection achieves a 39.6% average problem-weighted win rate against a one-shot Gurobi baseline, more than doubling the best single configuration (19.3%). A post-hoc configuration and a feature ablation indicate a headroom of up to 44.0%, demonstrating that LLM-based semantic generation enables effective automated structure and feature extraction for constraint optimization. --- ### LLM-Guided Graph Generation for Structure-Based Local Improvement Methods Authors: Hai Xia, Vaidyanathan Peruvemba Ramaswamy, Stefan Szeider Published: 2026-08-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.13333v1 Large neighborhood search normally selects a random subset of decision variables for iterative optimization. For efficiently solving different problems, researchers tend to design variable selection strategies by taking into account structural features from different domains. In this paper, we build an automatic pipeline that is problem-agnostic to all problems in the MiniZinc format. By prompting an LLM with our semantic guidelines, we guide the LLM to produce a graph generator that maps any instance of a problem type to a uniform weighted graph, where nodes represent decision variables and edges represent constraint relationships. These problem-agnostic graphs guide our structure-based local improvement framework (SLIM) in variable selection. Meanwhile, the weighted graph enables all problem instances to share the same generic graph representation, from which the same graph features can be extracted and used for configuration selection. We evaluated our pipeline on instances across 20 MiniZinc competition problems, finding that algorithm selection achieves a 39.5% average problem-weighted win rate against a one-shot Gurobi baseline, more than doubling the best single configuration (19.3%). Configuration and feature ablation boost the performance further to 44.0%, demonstrating that LLM-based semantic generation enables effective automated structure extraction and feature extraction for constraint optimization. --- ### Training AI Scientists to Replicate Research Authors: Damon Falck, Samer Sabri, Anja Surina, Thom Foster, Anya Sims, Sam Devlin, Dylan Rogers, Tantum Collins, Kaloyan Aleksiev, Louis Kirsch, Edward Hughes Published: 2026-08-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.13331v1 The replicability of papers is a cornerstone of scientific knowledge, ensuring the reliability of existing results and providing a base for further experiments. The act of replication typically illuminates details that were previously underspecified, and thus requires similar hypothesis-driven exploration to open-ended research. In this work, we develop Replica, a scalable task space for paper replication. To provide reward signal, we introduce an auto-generated rubric-based judge that has low noise and agrees with human assessment of replication quality. We post-train Faraday, a 27B-parameter "AI Scientist" agent that leverages coding agents as tools, surpassing the performance of Claude Opus 4.8 and GPT-5.5 on held-out replication tasks. Qualitative analysis of individual rollouts reveals that Faraday adopts a more scientifically-principled approach. We believe that our results provide a stepping stone towards AI agents capable of long-horizon scientific innovation without requiring complex harnesses. --- ### A Probe Direction Is a Property of Its Prompt Authors: Valentin Noël Published: 2026-08-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.13329v1 A model that behaves differently when it senses it is being tested would undermine the evaluations we rely on, so recent work has sought to read that sense directly from a model's activations. The standard instrument contrasts activations on prompts that announce an evaluation against prompts that do not, and reports how well the resulting direction separates held-out cases. That number is then compared across models and correlated with scale. We observe that the instrument has a free parameter its readings do not disclose: "a prompt that announces an evaluation" is not a prompt but a choice among many, and nothing in the method fixes which. Holding the task text fixed and varying only that choice, we find that the reported score, and even the direction in which it trends with model size, follows the prompt rather than the model; two published studies that disagree about the sign of that trend are both reproducible from a single design, by choice of prompt alone. Treating the prompt as a facet of a measurement design rather than an implementation detail, we find the model under study accounts for a small share of the variance in the number reported about it, and most of the rest lies in how each model responds to each prompt: collecting more evaluation items cannot repair the measurement, while varying prompts can. A further check finds that the split these probes are scored on is largely separable from surface form alone, so a direction carrying no information about evaluation at all still reproduces a substantial fraction of each published score. We conclude that a single-prompt design cannot support comparison between models, and we give the number of prompts a defensible comparison requires. --- ### It's How You Ask: Gender-Associated Linguistic Bias in LLMs Authors: Katherine Van Koevering, Anjalie Field Published: 2026-08-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.13328v1 Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguistic features more commonly used by women (hedges, tag questions, collective reference), they systematically elicit shorter, less sophisticated, and less formal responses across three document types and four models. These effects persist after controlling for prompt complexity and feature carry-over. Explicit gender cues like sign-off names are encoded in the same representational space as linguistic dialect - suggesting shared underlying mechanisms - yet linguistic register is far more influential, producing large, consistent effects where names produce none. Our results further reveal that post-hoc mitigation is challenging: because these patterns are culturally embedded and outside conscious control, users cannot easily avoid them through strategic self-presentation, and mechanistic analysis reveals that linguistic features are encoded in early transformer layers and entangled with other features. Our work calls for upstream consideration of the influences of linguistic variation to mitigate disparate impacts of LLM-mediated workplace communication. --- ### Beyond Local Accuracy: A Protocol-Level Identifiability Audit for Controlled LLM Reasoning Evaluation Authors: Junhao Luo, Ning Huang, Ziqi Sha, Wenxuan Tang, Wei Deng Published: 2026-08-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.13326v1 LLM benchmark scores can be precise even when the observation protocol does not identify the behavioral property they are intended to measure. In a controlled, solver-grounded setting, we formalize a protocol-level identifiability audit over a finite behavioral policy class: given policies H, observation support O, and estimand $τ$, we test whether O separates every pair with different $τ$. The audit requires zero model calls and resolves our diagnostic case: base-only observation collapses seven frozen deterministic policies into one equivalence class; full support yields seven classes and no cross-estimand collisions; every leave-one-out support retains a constructive collision witness. Empirically, both constrained-generation variants have pair-validity 1.0, yet base accuracy and selective-response fidelity diverge - 0.620 versus 0.324 across six balanced oracle-transition directions (cluster-bootstrap 95% CI (0.600, 0.642) vs. (0.304, 0.345)) - and the gap recurs on a second deterministic source (0.646 vs. 0.331). The audit also synthesizes a minimum identifying support $O^*$ for the frozen policy class: two cells instead of the full 36-cell tensor. This case shows how evaluation-design validity can be checked structurally before model inference and why base correctness does not determine intervention-response fidelity. --- ### StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems Authors: Yanwen Peng, Delvin Ce Zhang, Xi Wang, Nikolaos Aletras Published: 2026-08-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.13317v1 Large language model based multi-agent systems usually communicate in text, i.e., using discrete tokens. However, text introduces a discrete bottleneck. Converting the sender's continuous hidden states into discrete tokens discards information that token identities alone cannot capture. Recent work proposes latent communication as an alternative, where agents transmit hidden representations directly without converting them to text. However, existing latent methods either inject working memory layer by layer across the transformers, or require trained projectors that limit portability. We propose StateBridge, a training-free latent communication approach that aligns the sender's final-layer hidden states to the receiver's input space via a closed-form orthogonal transformation. Lightweight norm calibration and vocabulary anchoring ensure compatibility with the pretrained input distribution. The aligned states are prepended to the input of the receiver agent as a continuous prefix. We evaluate StateBridge on math reasoning, code generation, and question answering with four models from two families. StateBridge achieves the best or tied-best score on 22 out of 26 model-task pairs, consistently outperforming the strongest baseline. --- ### Foundation models for movement data: Are they ready for prime-time? Authors: Alexander Bräuer, Benjamin Cauchi, Nils Strodthoff Published: 2026-08-13 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2608.13316v1 Foundation models (FMs) trained on large-scale accelerometer data have been proposed as general-purpose feature extractors for health monitoring, but systematic evidence of their advantages is lacking. We present the first comprehensive evaluation of four open-source accelerometer FMs against supervised baselines covering 19 tasks across the domains of activity recognition including activities of daily living, clinical monitoring, and physiological inference. We find task-dependent performance results: supervised models remain competitive with FMs on human action recognition (HAR), with no consistent advantage for either, while selected FMs lead on fall and stress detection and are the most robust to sensor-placement variation. As frozen feature extractors, FMs are strongest for demographic inference, whereas sleep staging performance remains near chance level for all models. The internal FM representations show strong similarity across layers, highlighting potential for future FM improvements. Linear and frozen probing reveals that UniMTS provides the strongest representations and is the only FM that surpasses the supervised baselines without finetuning. Concept discovery analysis shows all models capture high-intensity activities clearly but struggle with sedentary, complex or ambiguous activities. We provide scenario-based deployment recommendations. Furthermore, we identify FM-derived activity profile inference-moving beyond fixed category classification-as a promising research direction. --- ### Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services Authors: Ahmet Bugra Gundogan, Yigit Turkmen, Melih Bastopcu Published: 2026-08-13 Categories: cs.GT, cs.AI, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2608.13315v1 We study a large language model (LLM) service in which a provider chooses a per-token price and a default reasoning-token allocation, while a user may accept the default, customize the allocation, or exit. Larger allocations can improve accuracy but increase token cost and latency. We model this interaction as a Stackelberg game and derive the user's unique optimal customized allocation in closed form. For any price, the acceptable defaults form either an empty set or a compact interval. We characterize the provider's optimal default through a three-regime rule, reduce equilibrium computation to a one-dimensional price optimization, and prove the existence of the equilibrium. We further show that defaults affect the implemented reasoning allocation only when users value the convenience of avoiding customization; otherwise, every service-providing outcome implements the user's optimal customized allocation. Experiments with two compact open-weight reasoning models on five mathematics and science benchmarks support the accuracy-token model and show how model and task characteristics determine equilibrium prices, defaults, and reasoning allocations. --- ### How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning? Authors: Wafa Al Ghallabi, Ritesh Thawkar, Sara Ghaboura, Omkar Thawakar, Numan Saeed, Dana Al Nuaimi, Ajnas Alkatheeri, Salman Khan, Fahad Shahbaz Khan Published: 2026-08-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.13309v1 Magnetic Resonance Imaging (MRI) interpretation is fundamental to clinical decision-making, requiring radiologists to integrate multi-view anatomical planes across sequential timepoints while precisely localizing interval changes. However, existing vision-language benchmarks remain confined to single-timepoint, single-view interpretation, failing to capture the temporal-spatial reasoning essential to radiologic practice. We introduce the Time-Aware Multi-View MRI Benchmark, an evaluation framework unifying multi-view anatomical input, temporal reasoning across longitudinal scans, and structured localization guidance. The benchmark comprises 3,920 expert-verified question-answer pairs derived from 890 patients across over 3,200 longitudinal MRI timepoints, drawn from seven clinical cohorts covering glioblastoma, neurodegeneration, vestibular schwannoma, and brain metastases, in open-ended, multiple-choice, and binary formats, requiring models to identify anatomical regions of maximal change, characterize progression across sequences and views, and provide structured guidance specifying boundaries, imaging features, and confounders. Experiments across 16 vision-language models reveal moderate temporal alignment but systematic failure on change direction recognition and volumetric quantification, while multi-view inputs improve spatial localization yet degrade temporal reasoning in compact architectures. Our benchmark provides a systematic framework for evaluating progression tracking, interval change localization, and temporal ordering, which are essential for clinical deployment. Code, evaluation splits, and the dataset are available at: https://github.com/wafaAlghallabi/Time-Aware-MRI. --- ### Physics-informed distribution of relaxation times estimation and latent-space condition monitoring of solid oxide fuel and electrolysis cells from electrochemical impedance spectroscopy Authors: Žan Gorenc, Žiga Gradišar, Felix Mütter, Vanja Subotić, Pavle Boškoski Published: 2026-08-13 Categories: stat.AP, cs.AI arXiv: https://arxiv.org/abs/2608.13305v1 Estimating the distribution of relaxation times (DRT) fromelectrochemical impedance spectroscopy (EIS) is an ill-posed inverse problem that is highly sensitive to regularisation choices. We propose a physics-informed convolutional autoencoder that estimates DRT directly from EIS data without spectrum-specific tuning. A discretised relation between impedance and the DRT is embedded in the training process, constraining the network to produce impedance-consistent distributions. The model resolves overlapping relaxation processes in synthetic two-ZARC spectra and accurately reconstructs measurements from three independent solid oxide fuel and electrolysis cell datasets, with range-normalised errors below 1.1%. Decoder-probe analysis shows that the learned latent representation is organised according to relaxation timescale. Distances in this latent space capture operating changes, hydrogen-shortage events, and long-term degradation. The same lightweight architecture is applied across all datasets without modification, providing consistent DRT estimation and an interpretable basis for condition monitoring. --- ### Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety Authors: Ping Wu, Haibo Tong, Feifei Zhao, Han Shen, Yu Shi, Yilin Zhao, Sicheng Shen, Guobin Shen, Yun Luo, Yi Zeng Published: 2026-08-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.13304v1 Safety tuning can improve harmful refusal, but models may learn surface-form shortcuts: wrapped harmful prompts bypass safety, while similarly wrapped benign prompts are over-refused. We propose Wrapper-Based Intent-Form Augmentation (WIFA), an automatic intent-group augmentation method that pairs wrapped harmful examples with structurally matched wrapped benign counterexamples, requiring no external teacher or manual per-wrapper intent labels. We use WIFA as a common data layer for two complementary fine-tuning routes: WIFA-Boost, a two-stage high-safety recipe, and Anchored Group-Consistent Refusal Training (A-GCRT), which regularizes refusal/compliance decision scores across same-intent wrappers and anchors harmful and benign groups on opposite sides of a margin. In the Qwen setting, WIFA-Boost reaches the strongest transformed-harmful refusal, while A-GCRT reduces OR-Bench over-refusal from 25.7\% for the base model to 17.4\%; reproduced baselines do not match these operating points. Llama results and ablations over data structure, two-stage order, and A-GCRT components support this intent-group interpretation without claiming universal below-base over-refusal. --- ### The Time Value of Evolution Authors: Matthew Siper, Ahmed Khalifa, Julian Togelius Published: 2026-08-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.13297v1 In evolutionary search, a weak child can be a valuable ancestor that makes high-fitness regions reachable. Immediate-return control is blind to this delayed utility, penalizing mutations through their immediate offspring even when they open productive future lineages. We formalize this hidden dynamic as the time value of evolution within a finite-horizon Markov decision process. To exploit it, we introduce Lineage-Value Policy Gradients (LVPG), a long-horizon actor-critic framework for automated trading policy discovery. Our architecture decouples search control into specialized policy heads over a shared generative backbone: a bootstrapped critic head estimates the value of finite-horizon lineage potential from multi-step mutation trees, while an actor head dynamically modulates mutation intensity over the remaining search budget. We isolate the impact of long-horizon credit assignment against immediate-return optimization across 90 paired runs under matched operators, lineage supervision, folds, seeds, and budgets. Path-based credit assignment substantially accelerates finite-budget search, increasing validation best-so-far AUC by 0.394 Sharpe units. LVPG also produces fewer temporary regressions than immediate-return optimization and recovers from them more often. Finite-horizon lineage value yields more selective non-monotonic search and stronger policies within identical resource constraints. --- ### Large-scale Testing Global Optimization Methods with Black-box Adversarial Attacks Authors: Wojciech Zarzecki, Jarosław Arabas Published: 2026-08-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.13296v1 Existing global optimization benchmark suites are of a moderate size and are based on a small number of analytical functions that date back even to the 1970s. This causes a risk of biasing the development of global optimization methods. We argue that the tasks related to the black-box adversarial attack (BBAA) can serve as valuable global optimization benchmark in many-dimensional space. We demonstrate the efficiency of several types of evolutionary algorithms and other metaheuristics in solving example BBAA problems. Thus, we take a step towards convergence of global optimization methods to the challenges and needs that arise in the modern machine learning field. --- ### NAS-Driven Hardware Accelerator Exploration for Edge AI and Quantization Effects on the Pareto Space Authors: Eleftherios Mylonas, Angelos Kouprizas, Michael Birbas, Alexios Birbas Published: 2026-08-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.13293v1 Edge AI deployment demands neural architectures that are simultaneously accurate, computationally efficient, and hardware-deployable - a challenge addressed by hardware-aware Neural Architecture Search (NAS). While recent works incorporate quantization directly into the NAS loop, these approaches expand search complexity and tightly couple architecture and quantization design. The simpler post-search quantization strategy has received little analytical attention: the effects of Post-Training Quantization (PTQ) on the NAS-discovered Pareto structure remain uncharacterised, and no framework combines quantized architecture mapping onto reconfigurable accelerators with automated hardware exploration. This paper addresses both gaps. First, a three-stage pipeline is proposed: a hardware-agnostic Pareto rank surrogate frontend on NAS-Bench-201, a quantization bridge with Pareto-aware filtering and feedback control, and an evolutionary Domain Space Exploration (DSE) backend on CGRA4ML for optimal hardware mapping. Second, an empirical study characterises how INT4 PTQ perturbs the NAS-Bench-201 Pareto space through formal stability metrics on ground-truth data for all 15,625 architectures, and demonstrates that an FP32 zero-shot surrogate outperforms a dedicated INT4-trained surrogate in Pareto space coverage across two standard search strategies. --- ### EEG Decoding Using CNN and LSTM Network Authors: Athanasios Karagounis Published: 2026-08-13 Categories: cs.LG, cs.HC arXiv: https://arxiv.org/abs/2608.13285v1 Motor imagery (MI) brain--computer interfaces (BCIs) have emerged as a promising approach for establishing flexible communication pathways between the human brain and external devices , particularly for individuals affected by stroke or neurodegenerative disorders. Reliable decoding of motor-imagery electroencephalography (MI-EEG) remains challenging because EEG recordings contain substantial noise and exhibit complex, weakly informative relationships with the underlying brain activity. Although deep learning provides an effective means of learning representations directly from EEG signals, its application to MI-EEG feature learning remains comparatively limited. This study introduces a hybrid deep-learning architecture that integrates a convolutional neural network (CNN) with a bidirectional long short-term memory (bi-LSTM) network. The CNN is used to learn high-level spatial and temporal representations directly from raw MI-EEG recordings, whereas the bi-LSTM models temporal dependencies and relationships among the extracted features. The proposed approach is evaluated using both a publicly available dataset and a privately acquired dataset obtained with an EEG acquisition system. The experimental results indicate that the CNN\&bi-LSTM architecture provides robust performance for both two- and three-class motor-imagery classification and demonstrates promising subject-independent decoding capability across the evaluated methods. --- ### Towards Context-Aware Clinical Motion Understanding in Daily Living at Home: Freezing of Gait Detection with Egocentric Vision Authors: Vayalet Stefanova, Diwas Lamsal, Margot Genbrugge, Maxim Yudayev, Christian Schlenstedt, Moran Gilat, Bart Vanrumste, Benjamin Filtjens Published: 2026-08-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.13283v1 Understanding motion in daily living requires context beyond kinematics, because similar inertial patterns during activities of daily living (ADLs) can reflect intentional stopping, object interaction, or pathological movement impairment. Egocentric vision provides task-related context that may help disambiguate these cases. We investigate this challenge through freezing of gait (FOG) detection in Parkinson's disease (PD), a symptom strongly influenced by contextual factors during ADLs. Using synchronized egocentric video, wearable IMUs, and expert-annotated FOG labels collected from 13 PD participants in their homes, we evaluate frozen representations from pretrained ego-video and time-series foundation models, alongside an IMU-based TCN trained from scratch, under leave-one-subject-out evaluation. The IMU-based TCN achieved the strongest event-detection performance, reaching 42.3 F1 and 83.0 AUROC, compared with 32.6 F1 and 77.2 AUROC for V-JEPA2 ego-video features. Although ego-video alone did not outperform IMU-based sensing, it showed above-chance discrimination, and qualitative analyses suggest that egocentric vision may capture FOG-relevant information independent of IMUs. Together, these results support the use of pretrained ego-video representations to add contextual information to wearable-sensor-based clinical motion understanding in daily living. ---