# Research Papers — 2026-08 · bundle page 4 of 240 > Full-text markdown of papers #151–200 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/4 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/3.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/5.md) ### Asymmetries in Spontaneous and Instructed Deception Authors: Josiah Luikham Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.00180v1 Large language models sometimes deceive users without being instructed to. However, much of the study on deception in models involves instructed deception. We investigated the relationship between instructed and spontaneous (uninstructed) deception in Llama-3.1-70B-Instruct. We compared these two deception settings through direction geometry, cross-setting classifiers, and cross-setting steering. We found the two deception settings share a component of direction (cosine of approximately 0.5) and an asymmetry in the transfer between settings regarding detection and causation. Spontaneous trained classifiers performed better on instructed data than vice versa, and instructed derived directions performed better at steering spontaneous prompts than vice versa. Likewise the best token position to derive steering vectors from differed from the best token position to train and apply classifiers. --- ### Do General NLP Embeddings Capture Ontological Reasoning? Authors: Hamed Babaei Giglou, Jennifer D'Souza, Sören Auer Published: 2026-08-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.00177v1 General-purpose NLP embedding models perform well on linguistic tasks, but their ability to capture symbolic ontological structure remains unclear. We introduce AVA, a systematic framework for evaluating whether embeddings distinguish logic-sensitive relational semantics in ontologies and knowledge graphs. AVA comprises 171,007 contrastive triplets derived from 163 heterogeneous ontologies using hierarchy inversion, relation substitution, and disjointness injection. Each triplet contains an ontology statement, a semantically equivalent paraphrase, and a logic-sensitive hard negative with contradictory relational meaning. We evaluate more than 25 state-of-the-art embedding models and find substantial limitations: the best model achieves only 0.739 triplet accuracy, while hard negative accuracy falls to 0.135. Fine-tuning improves discrimination by a large margin but transfers poorly to downstream Semantic Web tasks, including taxonomy discovery and ontology alignment. Further analysis suggests that improvements stem partly from perturbation-specific pattern recognition rather than robust ontological understanding. These findings reveal a persistent gap between linguistic representation learning and ontology-level discrimination, challenging the assumption that strong NLP benchmark performance translates to Semantic Web competence. --- ### IMPACT: Attention Is the Interaction Map for Scalable Interaction-Aware World Model Training Authors: Rongze Tang, Jianjie Fang, Zhaolu Wang, Ziyou Wang, Xvyuan Liu, Haisheng Su, Xin Zhang, Wei Wu, Chen Gao, Yong Li, Zhibo Chen Published: 2026-08-31 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2609.00161v1 World models have made remarkable progress in action-conditioned future prediction for embodied agents, yet still struggle to model physically plausible interactions. Existing approaches address this limitation by constraining the generation process with external representations encoding motion, geometry, or semantics. Obtaining these spatiotemporally dense representations typically requires auxiliary estimators or manual annotations, limiting training scalability. We instead revisit the training objective and identify a supervision-allocation mismatch under the globally averaged mean squared error (MSE) denoising objective: prevalent static content dominates the optimization signal, leaving sparse dynamic-object regions critical to interaction generation disproportionately under-supervised. Motivated by this observation, we introduce IMPACT, a scalable Interaction-aware Model training framework with Prior-guided Attention Calibration and Targeting. IMPACT uses cross-attention associated with manipulated-object tokens as an internal spatiotemporal prior for action-conditioned changes. It samples candidate regions from this prior, calibrates them with detached local prediction errors to construct an interaction map, and uses the map to reweight denoising supervision, requiring neither external representations nor inference-time modifications. Extensive experiments on robot-arm and human-hand manipulation, spanning diverse control modalities and DiT backbones, show that IMPACT consistently outperforms the corresponding MSE-trained baselines, improving interaction fidelity, physical plausibility, and visual quality. --- ### Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs Authors: Deniz Bayazit, Badr AlKhamissi, Antoine Bosselut Published: 2026-08-31 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.00155v1 Latent language identification is often used to argue that multilingual language models route computation through language-specific states, such as English pivots. However, existing probes infer latent language from different signals, such as the geometry of hidden states or what can be decoded from intermediate representations. Since such claims shape conclusions about how models share and route information across languages, we ask whether these probes measure the same phenomenon or expose distinct aspects of multilingual computation. We study this question across model families, training regimes, domains, tasks, checkpoints, and up to 27 languages. We find that identification probes systematically disagree: the GMM-based representation probe, which draws evidence from hidden state geometry, shows earlier cross-lingual mixing, whereas decoding-based probes, which rely on output-space decodability, retain sharper language-specific and more English-biased signals. These differences track model multilinguality and training progression, but are comparatively stable across domains. Our results suggest a more cautious interpretation of latent language identification, where current probes expose different aspects of multilingual processing, rather than directly revealing a single internal lingua franca. --- ### Recursive Criticality of AI Self-Improvement Authors: Mikhail Burtsev Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.00137v1 AI is increasingly used in the R\&D process that produces future AI systems. We study the conditions under which this feedback becomes self-amplifying. Our model describes how the rate of AI capability growth depends on baseline research productivity, recursive feedback, and the increasing difficulty of research progress. We derive a recursive reproduction number, $\mathcal{R}_{\mathrm{AI}}$, that determines whether improvements are amplified or damped across development cycles. This quantity compares the strength of feedback with the rate at which further progress becomes more difficult. When $\mathcal{R}_{\mathrm{AI}}>1$, the effects of improvements compound across development cycles, placing the system in a self-amplifying regime. When $\mathcal{R}_{\mathrm{AI}}<1$, their effects weaken across cycles. The transition depends on the structure of the AI R\&D feedback loop and need not occur at any particular level of model capability. A system can therefore enter a self-amplifying regime before acceleration becomes visible, while rapid progress can also occur without self-amplification. Higher baseline research productivity can accelerate progress without changing whether the system is self-amplifying, but the duration of the development cycle becomes a limiting timescale for amplification. Increasing research difficulty can end a period of self-amplification. Extending the model to multiple research actors shows that improvements shared across organizations can make the overall research ecosystem self-amplifying even when no individual actor is. The framework identifies measurable properties of AI R\&D systems that can help distinguish recursive amplification from rapid progress driven by other sources, including the strength of recursive feedback, how effectively improvements propagate into successor systems, cycle duration, and the increasing difficulty of further progress. --- ### Flawed in Nature, Perfect through Evolution Authors: J. M. Diederik Kruijssen Published: 2026-08-31 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2609.00129v1 The performance of artificial intelligence (AI) and machine learning (ML) models degrades when the problem they were trained on drifts. This is a near-universal feature of real-world problems, which often change unpredictably. Biological evolution has achieved intelligence by overcoming this obstacle through natural selection acting on heritable variation. AI/ML techniques have long incorporated forms of natural selection, but it has been challenging to maintain model diversity as optimization naturally drives convergence. Here we show that a swarm of AI/ML models subjected to deliberate mutations of their model coefficients away from optimality can reliably and sustainably improve performance in changing environments by acting as a statistical hedge against non-stationarity. We call this mechanism 'Flawed in Nature, Perfect through Evolution', reflecting that the collective performance gain goes at the expense of individual performance. We prove via four theorems that the resulting regret reduction is guaranteed under general conditions, establishing the Flawed-in-Nature mechanism as a generalizable design principle for AI/ML systems. We validate these results on synthetic linear regression tasks, demonstrating that the mutated swarm delivers the best model in $\sim80\%$ of environment changes and that inference synthesis successfully translates this individual advantage into a collective one. The mechanism proves to be most effective when the mutation drift rate matches the drift rate of the environment. We outline a simple, adaptive controller that enables practical applications by tuning the mutation drift rate to match the unknown drift rate of the environment. The close analogy of the Flawed-in-Nature mechanism to biological evolution suggests it may have been a critical missing ingredient for the organic discovery of AI forms that more closely mimic biological intelligence. --- ### Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving Authors: Xin Zhou, Zongchuang Zhao, Zhibo Yang, Mingsheng Li, Humen Zhong, Shuai Bai, Du Chu, Ruizhe Chen, Zhaohai Li, Jun Tang, Qiuyue Wang, Mingkun Yang et al. Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.00111v1 We present Qwen-Drive-1.0, an initial step towards a vision-language foundation model for autonomous driving. Qwen-Drive-1.0 retains the architecture of the pretrained vision-language model (VLM) and integrates 3D perception, visual question answering, and motion planning within a unified framework. An external bird's-eye-view (BEV) perception head jointly performs 3D object detection, semantic occupancy prediction, and BEV map segmentation. It serves as a probe of the 3D information accessible from the shared representations and provides an explicit, inspectable interface to 3D scene structure. A Planning Expert conditions on shared VLM representations to generate future ego trajectories. A staged training recipe combines driving supervision with general-purpose vision-language data to acquire driving-specific competence while helping preserve broad visual understanding and instruction-following capabilities. Experiments demonstrate strong 3D perception and driving scene understanding while largely preserving general vision-language capability. Comprehensive evaluations across open-loop, pseudo-closed-loop, and closed-loop settings further show highly competitive motion-planning performance. --- ### Deploying and Evaluating a Smart-Agriculture Agentic Engine for Full-Season Soybean Farm Operations Authors: Ao Qu, Panagiotis Michelakis, Linyuan Han, Yiannis Hadjiyianni, Kun Ouyang, Konstantinos Siskos, Feng Li, Ran Meng, Jingchi Jiang, Dimitrios Stamoulis, Jie Liu Published: 2026-08-31 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2609.00106v1 This paper presents FAIRY, a full-stack smart-agriculture agent system developed for and deployed to an operating soybean research farm at Harbin Institute of Technology's smart-agriculture site. We develop FAIRY to execute and evaluate agentic agronomic operations on full-season spatiotemporal workflows that span ridge preparation, planting, irrigation, fertilization, pest and disease treatment, harvest, grain handling, drying, and storage. FAIRY integrates APIs and infrastructure across production-grade machinery, fixed soil and canopy sensors, multispectral and thermal drones, satellite vegetation products, a weather station, calibrated crop-process models, agronomic records, and multi-season yield histories. The system is built around the novel "everything is an event" execution paradigm, which represents spatiotemporal world evolution, remote sensing and UAV observations, sensor readings, crop-growth transitions, machinery actions, and management interventions as state-changing events in a shared farm process engine. On top of this event-driven world model, FAIRY implements a complete agentic stack: a knowledge library of atomic agronomic skills; multi-agent controller and orchestration backends; frontier- and edge-model execution; full-path trace logging; and deployment profiling on local nodes. We use FAIRY to evaluate nine state-of-the-art agent controllers across one hundred full-season soybean scenarios that preserve the operational coupling between spatial observations in a 64-ridge field, temporal decision sequences, agronomic constraints, delayed effects, and final yield. We develop an evaluation suite that combines agentic success, full-path spatiotemporal correctness, token cost, and edge-device runtime. --- ### Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond Accuracy Authors: Shmuel Berman, Jia Deng Published: 2026-08-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.00103v1 Memory is widely viewed as an important unsolved problem for LLMs and VLMs, and current benchmarks typically evaluate it by testing accuracy over long text or video. However, accuracy alone misses properties that matter for real long-horizon tasks. We introduce ECCBench, a benchmark and evaluation protocol that measures memory beyond a system's capacity--its raw accuracy at a specific budget--via three axes we call ECC: efficiency--the computation, in FLOPs, needed to answer from memory; compression--whether compressible inputs are remembered more accurately or efficiently; and calibration--whether the system abstains in response to its own uncertainty and the cost of an error. We find that pretrained VLMs compress their memory over text but not video and are poorly calibrated on both. Among a broader set of memory backbones, several non-Transformer architectures achieve better compression-calibration tradeoffs than RoPE Transformers, suggesting they may be useful components for agents operating over long horizons. --- ### Different representation learning objectives recover distinct latent structures from the same psychometric data Authors: Cong Cao, Tassos C. Kyriakides, Pambos Vrasidas Published: 2026-08-31 Categories: cs.AI, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2609.00100v1 Psychometric questionnaires contain rich item-level information, yet it remains unclear whether different representation learning objectives recover the same latent organization. We investigated this question using 757 matched teacher-child pairs from the baseline assessment of the Cyprus ProW preschool trial. Behavioral structure was characterized from child SDQ, ASBI, and CBRS item responses using principal component analysis and clustering, yielding four behavioral phenotypes. A contrastive objective substantially improved teacher-child retrieval relative to PCA-based representations, increasing Top-1 accuracy from 0.13% to 7.27% and Top-10 accuracy from 1.98% to 56.14%. However, contrastive representations preserved behavioral phenotype structure less effectively than PCA-based representations. A multi-task objective jointly optimizing alignment and behavioral prediction partially restored behavioral organization but reduced retrieval performance. These findings indicate that teacher-child correspondence and behavioral phenotypes represent distinct forms of latent organization and demonstrate that the latent structure recovered from linked psychometric data depends on the representation learning objective. --- ### Generative artificial intelligence for reliable mechanistic reasoning for corrosion Authors: M N Bharath, R K Singh Raman, Alankar Alankar Published: 2026-08-31 Categories: cs.LG, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2609.00099v2 Corrosion accounts for approximately 4% of global GDP, and reliable prediction is essential for timely mitigation. Machine learning effectively predicts corrosion rates from composition, microstructure, and environmental variables, but cannot explain the underlying mechanisms. A reliable approach in safety-critical materials engineering requires not only accurate retrieval but also mechanistically defensible reasoning, a capability that existing factuality metrics cannot assess. This work presents a domain-adapted retrieval-augmented generation framework for corrosion knowledge synthesis, demonstrated on magnesium alloy corrosion. Three open-weight language models (Llama-3.1-8B, Qwen-2.5-7B, Mistral-7B) are fine-tuned on 3,309 expert-verified question-answer pairs from 840 peer-reviewed papers and integrated with a hybrid dense-lexical retrieval pipeline. Retrieval augmentation produces Token F1 gains of 143-194%, with system faithfulness of 0.964 and context recall of 0.988. Blind external validation on newly published literature and in-house electrochemical data confirms trend-level generalisation. Reason Map, a proposition-graph framework, is further introduced; it independently constructs directed evidence graphs from generated answers and retrieved literature, enabling systematic detection of causal direction inversions and unsupported inferential leaps that flat factuality metrics cannot expose. The modular architecture can be applied across domains, offering a generalizable blueprint for trustworthy AI-assisted knowledge synthesis to circumvent corrosion, which can also be applied to other engineering domains. --- ### Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding Authors: Zhigeng Liu, Zhiyuan Ning, Ruixiao Li, Xiaoran Liu, Yuerong Song, Min Zhang, Ziwei He, Xipeng Qiu Published: 2026-08-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.00097v1 The development of long-context Large Language Models (LLMs) is constrained by the memory bandwidth bottleneck and quadratic complexity of the attention mechanism during decoding. To overcome the inherent trade-offs between the memory overhead of metadata-based metrics and the computational inefficiency of adaptive selection strategies, we present Faster Flash Decoding (FFD), a novel hardware-algorithm co-design framework designed to break the memory wall in long-context decoding. FFD integrates the selector and computer into a fully fused kernel, replacing external metadata indices with content-aware scanning via low-bit quantization. Furthermore, we introduce the top-delta strategy, which dynamically filters blocks to achieve distribution-adaptive sparsity without global synchronization. Offering a training-free and plug-and-play solution, FFD also enables the reuse of scanning results for computation, achieving up to 11.6x kernel-level speedup and scaling to 256K context length, with 2.37x end-to-end throughput improvement. Empirical validation on RULER and LongBench confirms that FFD maintains model accuracy while delivering high-ratio sparsity, with code available at https://github.com/qluoluo/faster-flash-decoding --- ### Local Reference Geometry Residual Augmentation for Imbalanced Time Series Classification Authors: Chuanhang Qiu, Yanran Xu, Yue Wang, Anthony Bagnall Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.00093v1 Imbalanced time series classification is often addressed by changing the training distribution, objective, logits, or final threshold. These interventions address important biases, yet leave a representation-level question unmeasured: after minority support is reduced, does a learned feature space remain locally reliable around minority regions? We identify a training-local geometry failure: under imbalance, minority cases can lie in sparse, rest-dominated, or mixed feature-space neighborhoods, even when the representation retains useful global class structure. To diagnose and repair this failure, we propose Local Reference Geometry (LRG), a lightweight post-hoc feature augmentation module applied between a fixed feature extractor and the classifier head. Using training features only, LRG measures local exposure and class-mixture risk, then augments each fixed feature with a standardized signed displacement from nearby training geometry and an LDA-projected residual summary. On controlled UCR/Bake Off Redux imbalance benchmarks, paired raw-versus-LRG comparisons show gains for learned, pretrained, and fixed representations, including when LRG is combined with training-level interventions and post-encoder classifier corrections. Ablations show that the gain comes from the signed local residual appended to the original feature, rather than from generic prototype distances, affinity features, scalar statistics, or VLAD-style codes. Further analyses support the proposed local-geometry failure hypothesis: minority neighborhoods become increasingly rest-exposed under imbalance, training-local risk identifies error-prone regions, and LRG gains concentrate in those high-risk regions. --- ### Safin-1: Safety from Within through Memory-Native State Evolution Authors: Ming Zhang, Kaisen Yang, Shu Yu, Ermo Hua, Zhekai Chen, Cheng Jin, Jingnan Zheng, Yi Zhang, Zhongtian Ma, Jiawei Zhou, Sirui Chen, Qiaosheng Zhang et al. Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.00092v1 Long-horizon complex tasks require foundation models to accumulate information, maintain internal states, and adapt over extended interactions. Safety should be an intrinsic property of the model itself, rather than a behavioral constraint relying solely on external safeguards or post-hoc alignment such as supervised fine-tuning. This motivates Safety from Within, where safety-relevant capabilities are represented and invoked through the model's native computation. We present Safin-1, a family of foundation models realizing this principle through memory routing and state evolution. Safin-1 is built on Memory-Anchor Routing across Context History (MARCH), a network architecture that maintains structured memory states and selectively retrieves relevant historical information through content-conditioned routing. It supports test-time adaptation of persistent capability states without repeatedly modifying the backbone, enabling controlled specialization over a shared foundation. We investigate this interface on downstream safety tasks through a Safety State, demonstrating effective state-based adaptation with substantial safety improvements. More broadly, the routed-state interface unifies contextual memory and persistent capability adaptation within the model's native computation, reframing memory from a passive record of prior context into an active substrate for maintaining and evolving model behavior. Evaluations across general capabilities, long-context understanding, retrieval, and efficiency further validate Safin-1. These findings provide a path toward safety as a state-native and adaptively maintainable capability. This work is only an initial architectural exploration of Safety from Within, and substantial further work is needed to realize this broader vision. --- ### Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence Authors: Eddie Conti, Claudio Daka, Álvaro Parafita, Antonio L. Alfeo, Axel Brando, Mario G. C. A. Cimino Published: 2026-08-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.00090v2 Feature importance Methods (FIMs) are widely used in Explainable AI to interpret model predictions, yet attribution scores alone often provide limited insight into the underlying reasoning process. In this work, we introduce a novel perspective by embedding FIMs within a hypothesis-testing framework based on Weight of Evidence (WoE). We quantify how strongly the observed evidence supports any given hypothesis on feature importance. The reference hypothesis can stem from domain knowledge, ground truth, or be derived from the FIM itself. This formulation enables a principled evaluation of FIMs, capturing both their alignment with prior knowledge and their variability. We further provide theoretical results linking WoE to attribution variance. Empirical results shows the applicability and flexibility of our strategy analyzing LIME and SHAP explanations in settings with different reference hypotheses. Overall, our framework offers a complementary tool for assessing FIMs through a contrastive, evidence-based lens. --- ### Foundation models for electricity price forecasting and battery arbitrage: Can they replace market-specific forecasting models? Authors: Arkadiusz Lipiecki, Rafał Weron Published: 2026-08-31 Categories: cs.LG, econ.EM arXiv: https://arxiv.org/abs/2609.00089v1 Foundation models promise accurate forecasts with little or no task-specific training, but whether they can replace models designed specifically for electricity price forecasting remains unclear. We compare nine variants from five foundation model families, evaluated in zero-shot mode, with two state-of-the-art electricity price forecasting benchmarks in Germany, Poland, and Spain over 2021-2025. Their performance is assessed in terms of point and probabilistic forecasting accuracy, as well as economic value in battery energy storage arbitrage. Only the TabPFN models consistently and significantly outperform the benchmarks across all three markets and all statistical measures. However, this statistical dominance does not translate directly into economic dominance: TabPFN performs best under unlimited bids and riskier quantile-based strategies, whereas the Distributional Deep Neural Network benchmark is more profitable when risk tolerance is lower. Thus, foundation models cannot universally replace market-specific models, and their value depends on both model architecture and the decision problem. --- ### Commit-first LLM judging inherits the judge's own errors Authors: Idil Gozel Published: 2026-08-31 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.00088v1 LLM judges, models that score another system's output, can be gamed by the systems they score. Recent work identifies one defence that works: the judge solves the task itself first and commits to that answer, then accepts a candidate only if the two match. We call this commit-first judging, and ask whether shipped software implements it, and what it costs. We audit the default judge configurations of eight widely used evaluation frameworks. Of the 24 configurations in scope, none implement it. Nine implement a variant the literature measures as ineffective, and share one ancestor prompt, traceable through a copied typographical error. In a controlled experiment, an ordinary best-of-N search with no access to correct answers optimises code against one of these configurations, used exactly as documented. On an interval merging task the judge accepted 90 of 96 candidates in one seed and 93 of 96 in the other; every accepted candidate passed every test the search could see and failed a held-out suite it could not. The judge identified the defective line and cited it as grounds for a perfect score. Commit-first judging removed the effect: 0 of 96 in both seeds. On a second task it made matters worse in both seeds: the judge's committed answer was wrong, and in one seed the population converged on it. This is our main finding. Commit-first judging does not remove the anchor that gets gamed, it moves it from the candidate to the judge's own answer, so evaluation is only as good as the judge is at the task. That precondition is cheap to measure in advance, and is task local rather than scale dependent: a smaller judge solved a task the frontier judge failed and resisted gaming where it did not. We also validate our own instruments: five of fifteen claims in our criteria were wrong against verbatim sources, and two held-out checks were unjustified by their specifications. --- ### Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation Authors: Ante Kapetanovic, Tomislav Duricic, Andro Mercep, Emanuel Lacic Published: 2026-08-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.00086v1 Large language models (LLMs) are increasingly used as rerankers in conversational recommender systems, yet measured gains depend strongly on the retrieval and inference protocol. On the ReDial conversational movie recommendation benchmark, we compare proprietary, open-weight, and fine-tuned LLM rerankers with collaborative-filtering and sequential baselines in a shared retrieve-then-rerank pipeline. We vary candidate-pool size, first-stage retriever, and decoding temperature. With a shared semantic top-250 candidate pool and strict candidate-aware scoring, the best proprietary reranker reaches NDCG@10 of 0.1497, compared with 0.0939 for the strongest non-LLM baseline. The same reranker reaches 0.2925 in zero-shot generation, showing that unconstrained scoring can yield a much larger apparent advantage than matched-pool evaluation. No evaluated open-weight LLM outperforms the tuned shallow autoencoder baseline under this protocol. For the strongest proprietary and open-weight rerankers, switching from semantic to collaborative-filtering candidates raises NDCG@10 by more than 50%, showing that measured reranker performance is highly sensitive to candidate generation. For the best proprietary reranker, raising temperature from 0 to 1.0 increases top-10 Jaccard distance from 0.0900 to 0.1240 while mean NDCG@10 changes negligibly, whereas weaker LLMs show larger degradation. These ReDial results support treating candidate generation, candidate-pool size, scoring policy, and decoding configuration as required reporting fields rather than implementation details. --- ### Stochastic complexity of vectors containing cluster structure Authors: Daniel Nicorici, Olli Yli-Harja, Jaakko Astola Published: 2026-08-31 Categories: cs.LG, cs.IT, stat.ML arXiv: https://arxiv.org/abs/2609.00084v1 This paper studies the problem of computing the stochastic probability (shortest code length) of the encoded vectors containing cluster structure using Normalized Maximum Likelihood (NML) model. This is of great theoretical and practical importance in data clustering based on Minimum Description Length (MDL) principle, such as for estimating the best number of clusters and best cluster structure for the data. Straightforward computation of the shortest code length of the vector containing cluster structure based on the NML model requires polynomial time with respect to the size of the vector and number of clusters. We show that this is a tractable problem by introducing a recursion formula for the efficient computation of normalizing constant from the NML model. The time complexity of the new formula is linear opposed to previous polynomial time with respect to the size of the vector and number of clusters. --- ### KItCAT: Knowledge Injection via Input Corruption for Auto-regressive Training Authors: Meghanadh Pulivarthi, Kushagra Bhushan, Vineet Kumar, Gaurav Pandey, Jaydeep Sen, Dinesh Raghu, Sachindra Joshi, Yatin Nandwani Published: 2026-08-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.00082v1 LLMs acquire vast amounts of knowledge during pre-training, but often lack the specialized knowledge needed to answer questions from niche sources such as manuals or technical documents unseen during pre-training. Continued pre-training (CPT) is widely used to inject such knowledge into model parameters. However, niche documents seldom repeat facts, making it difficult for CPT to robustly acquire such knowledge. Recent works address this by generating multiple paraphrases of the new knowledge, but paraphrasing is computationally expensive and typically requires powerful LLMs. In this work, we introduce KItCAT: Knowledge Injection via Corrupted Auto-regressive Training, a lightweight training strategy that reduces the need for paraphrasing in decoder-only LLMs. KItCAT augments standard next-token prediction by stochastically corrupting the input sequence. During training, a random subset of input tokens is replaced with other vocabulary tokens while the original next-token labels are kept unchanged. This simple intervention generates diverse training inputs from each sample, enabling large-scale data augmentation at negligible cost. We show that KItCAT consistently improves over CPT across multiple datasets and model families. Code is available at https://github.com/meghanadhpulivarthi/KItCAT. --- ### RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks Authors: Xingran Chen, Rohit Bhagat, Ghadir Ayache, Rawad Bitar, Yanmin Gong, Salim El Rouayheb Published: 2026-08-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.00078v1 Parameter-efficient fine-tuning methods such as LoRA have become a standard approach for adapting large foundation models. Adopting fine-tuning to distributed settings faces several challenges. Most existing distributed LoRA methods rely on centralized aggregation, and gossip-based decentralized LoRA requires repeated synchronization among multiple model copies. Both methods incur significant communication overhead and introduce errors due to simultaneous aggregation of multiple model updates. In this paper, we take a different perspective and propose a random-walk-based LoRA fine-tuning scheme. Instead of maintaining multiple model replicas, a single model token traverses the network and is updated sequentially using local fine-tuning objectives. This design eliminates the need for global synchronization, substantially reduces communication and computation costs, and avoids aggregation errors. We provide rigorous convergence guarantees for non-convex objectives under standard assumptions. Through empirical results on multiple NLP tasks and graph topologies, we show that the proposed method achieves competitive task performance with substantially less communication and computation than gossip-based LoRA. --- ### Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops Authors: Bowei He, Weixu Zhang, Yili Jin, Xue Liu Published: 2026-08-31 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2609.00077v1 Code-level autonomous research loops (ARLs) have recently emerged as a concrete object of study in automated machine learning research. In such loops, an LLM agent proposes modifications to an experimental training pipeline, executes the modified pipeline, and retains edits that improve a verifiable in-loop metric. Although executable metrics may appear to provide a reliable signal of progress, it remains unclear whether repeated metric-driven code editing leads to genuine improvements that generalize beyond the loop. We provide a systematic diagnosis of this question. Across various experiment settings, we identify a robust failure mode that we call \textbf{algorithmic mode collapse}. In this regime, surface-level edit diversity remains stable, but semantic and mechanism-level diversity collapse: the agent continues to edit different lines of code while repeatedly proposing the same kinds of algorithmic changes. This collapse is accompanied by a widening gap between in-loop metric gains and gains measured on independent held-out evaluations. We then propose Diversity-Aware Proposal Sampling (\textsc{DAPS}), a lightweight mitigation that combines category-coverage reweighting, persistent edit memory, and a validation gate. Under a three-tier protocol separating the in-loop metric, the audit metric read by the gate, and a blind metric no loop component ever accesses, \textsc{DAPS} reduces semantic-cluster decay of edits by $69.1\%$ and improves relative faithfulness by $83.7\%$ blind and $81.6\%$ audited, while preserving in-loop optimization speed. We provide the code in Github \href{https://github.com/BokwaiHo/arl-mode-collapse}{repository}. --- ### AI Morbidity and Mortality: A Framework for Clinical AI Failure Review Authors: Paulius Mui, Dean F. Sittig, Steve Labkoff, Sanjay Basu Published: 2026-08-31 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2609.00076v1 Clinical artificial intelligence is increasingly embedded in real-world care, yet existing safety mechanisms are poorly suited to reconstructing and learning from individual AI-related errors and near-misses. Aggregate model monitoring can identify performance changes, and traditional patient safety reporting can capture adverse events, but neither is designed to explain how risk emerges across the interaction among AI systems, clinicians, workflows, and institutional controls. We propose AI Morbidity and Mortality (AI M&M), a structured, blameless framework for case-based review of clinical AI failures. The framework combines standardized case intake, evidence preservation and investigator-level reconstruction, tool-in-loop attribution, and corrective-action tracking. Each event is classified across four linked dimensions: Trigger - Mechanism - Clinical Pathway - Corrective Action, separating the condition that exposed a vulnerability from the process that produced risk, its consequence for care, and the remediation assigned. We demonstrate the framework using five illustrative outpatient medication and clinical decision-support cases; two clinician reviewers independently applied all four classification axes and reached agreement across all 20 axis-level classifications. AI M&M is intended to complement, rather than replace, model monitoring, patient safety reporting, and regulatory oversight by converting individual AI-in-workflow failures into actionable institutional learning. Prospective evaluation across institutions, AI systems, and clinical settings is needed. --- ### MiNER: Fine-Tuned Biomedical Natural Language Processing for Malaria Disease Entity Recognition in Clinical Texts Authors: V. S. Anoop, Devika N Published: 2026-08-31 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.00073v2 Malaria remains a significant global health burden, necessitating continuous research efforts to understand its complex molecular mechanisms, epidemiology, and potential therapeutic interventions. Extracting essential biomedical information from the vast and constantly growing malaria literature is a challenging task that demands innovative approaches. Recently, pre-trained language models have revolutionized natural language processing tasks, demonstrating remarkable capabilities in various domains. This paper proposes a fine-tuned pre-trained biomedical language model for biomedical information extraction from scientific literature on malaria disease. The proposed methodology selects and preprocesses a large corpus of scientific articles on malaria, and then annotates them with entities of clinical significance. It then leverages BioBERT, a state-of-the-art pre-trained language model, to encode the textual data into context-aware representations. We fine-tune the model using domain-specific annotations and supervised learning to enhance its ability to extract relevant biomedical named entities. Extensive experiments and comparisons with different encoding and machine learning algorithms show that the proposed approach significantly outperforms them in precision, recall, and accuracy. We also publish our human-labeled dataset for entity and relation extraction to enable other health informatics researchers to train advanced models for malaria information extraction. --- ### Context-Aware Interleaved Batching for WhisperX Authors: Carlos Bain, Max Bain Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.31170v1 While WhisperX accelerates speech transcription via intra-audio batching, it isolates audio segments, losing the historical context needed for coherent punctuation and terminology transcription. Conversely, standard Whisper retains context sequentially but suffers from slow inference and hallucination loops. To achieve the best of both worlds, we propose Context-Aware Interleaved Batching. By using VAD-derived segment boundaries, our algorithm stabilizes Whisper's text conditioning, allowing us to safely maintain continuous historical context across batched audio segments. As demonstrated on long-form audio benchmarks, this approach reduces Word Error Rate (WER) and improves proper noun transcription, all while maintaining high-throughput inference speeds. --- ### SUN: Agentic Robot Policy Learning with Persistent Task Programs Authors: Weiqi Wang, Zhi Li, Yudong Lei, David Martinez, Xiaofeng Gao, Yuxin Jiang, Chenfanfu Jiang, Yingnian Wu, Demetri Terzopoulos, Ran Gong Published: 2026-08-31 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.31167v2 Model-based control can directly execute specified objectives, while learning can amortize such behaviors into reactive policies, making their combination a natural solution to multi-stage manipulation. We introduce Semantically UNified (SUN) Programs, typed executables that compile grounded relations into aligned optimal control objectives, satisfaction predicates, and learning rewards. Our harness, Kuafu, equips a foundation model as a task-level agent to orchestrate scene preparation, verification, residual RL, and data production. The agent uses program feedback to repair candidate programs and training diagnostics to calibrate relative reward weights, retaining accepted task semantics across tool calls. Across nine multi-stage manipulation tasks, Kuafu achieves 82.03% average success rate, significantly outperforming all learned baselines. Its learned controllers generate demonstrations at 10.57x the human-teleoperation rate, yielding data that improve visualpolicy success by 23.6 percentage points over the strongest baseline. The policies transfer zero-shot to physical Franka and Kinova robots, demonstrating sim-to-real generalization. --- ### SUN: Persistent Programs For Language-Grounded Control-to-Learning-to-Real Policies Authors: Weiqi Wang, Zhi Li, Yudong Lei, David Martinez, Xiaofeng Gao, Yuxin Jiang, Chenfanfu Jiang, Yingnian Wu, Demetri Terzopoulos, Ran Gong Published: 2026-08-31 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.31167v1 Bridging model-based control and learned policies in long-horizon manipulation has harbored a silent disagreement: control executes specified objectives, learning amortizes that behavior into a reactive policy, yet existing protocols discard task semantics, leaving rewards hand-crafted and behavior drifting from what control verified.We introduce Semantically UNified (SUN) Programs, typed executables where geometric and contact relations are defined once and compiled into aligned Model Predictive Control (MPC) costs, satisfaction predicates, RL rewards, transition guards, and diagnostics. Our system, Kuafu, driven by large vision language systems, automatically synthesizes SUN Programs from language and scene semantics, screens feasibility via MPC, and retains semantics while training stage-conditioned policies. Across nine tasks, Kuafu achieves 82.03% macro-success, outperforming sparse-reward (35.67%) and Stage-BC (24.75%) baselines. At 8192-way scale, it generates 10.57x the successful trajectory time per hour of human teleoperation. With 500 trajectories per task, Kuafu data trains DP3 policies to 46.0% simulation success (vs. 22.4% for alternatives) and 34.7% on physical Franka and Kinova robots. These results establish that simulation-screened task semantics can effectively amortize control into robust policies, without demonstrations or manual dense rewards, unifying symbolic planning and data-driven execution. --- ### Constant Individual Regret in General Games Authors: Mingyang Liu, Gabriele Farina, Asuman Ozdaglar Published: 2026-08-31 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2608.31166v1 Uncoupled no-regret dynamics provide a decentralized route to equilibrium, but prior guarantees for individual regret retain a polylogarithmic dependence on the horizon. We remove this dependence for every finite $N$-player normal-form game under full-information feedback. We introduce \emph{ECHO-OFTRL}: optimistic follow-the-regularized-leader (OFTRL) equipped with an EMA cascade for high-order optimism (ECHO), where EMA denotes exponential moving average. The algorithm is deterministic and fully uncoupled. If $m_{\max}$ denotes the largest action-set size, then, simultaneously for every horizon $T\geq1$, it guarantees that each of the $N$ players in the game incurs regret upper bounded by $O(\textrm{poly}(N, \log m_{\max}))$. Our algorithm leverages a new form of optimism inspired by modern filter design. --- ### BRF-GS: Hyperspectral Bidirectional Reflectance Factor Modeling and Image Generation Based on 3D Gaussian Splatting Authors: Yiling Yao, Wenjuan Zhang, Bowen Wang, Bocheng Li, Wentao Song, Bing Zhang Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.31159v1 The bidirectional reflectance factor (BRF) characterizes the directional radiative properties of terrestrial surfaces. However, existing three-dimensional (3D) radiative transfer models require complex scene construction and computationally intensive radiative transfer solvers, limiting efficient generation of multi-angle hyperspectral reflectance imagery. 3D Gaussian Splatting (3DGS) offers an efficient framework for neural scene representation and novel view synthesis, but its low-order spherical harmonics representation is insufficient for complex directional reflectance, while the high dimensionality and inter-band quality differences of hyperspectral data introduce additional challenges. To address these challenges, we propose BRF-GS, a 3DGS-based framework for BRF modeling and hyperspectral reflectance image generation. BRF-GS introduces a hybrid BRDF-driven kernel to represent complex directional reflectance, selects geometry-reliable spectral bands for robust 3D scene initialization, and adopts a two-stage training strategy that decouples geometry optimization from spectral modeling. We further construct the AIR-BRF dataset, a multi-angle hyperspectral directional reflectance dataset comprising three scenes with diverse natural and artificial targets. Experiments demonstrate that BRF-GS achieves superior spatial and spectral fidelity and accurately reproduces characteristic view-dependent BRF responses. The proposed framework provides an efficient data-driven approach for BRF modeling and multi-angle hyperspectral reflectance image generation in remote sensing scenes. --- ### Sharp Approximation Rates for Neural Networks with Affine Latent Parameterizations Authors: Shijun Zhang Published: 2026-08-31 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2608.31157v1 Many parameter-efficient methods generate the parameters of a large neural network from a low-dimensional latent representation. Given an architecture $Φ$ with $P_Φ$ parameter slots, we write $\boldsymbolθ_f=\mathcal{G}(\boldsymbolξ_f)$, where $\mathcal{G}\colon\mathbb{R}^M\to\mathbb{R}^{P_Φ}$ is a parameter generator and $\boldsymbolξ_f\in\mathbb{R}^M$ is a latent representation of the target function $f$. The architecture $Φ$ and the generator $\mathcal{G}$ are shared across the entire target class, while each target $f$ is represented by its own latent vector $\boldsymbolξ_f$, with $Φ_{\mathcal{G}(\boldsymbolξ_f)}$ approximating $f$. This framework encompasses hypernetworks, low-dimensional parameterizations, parameter-efficient adaptation, and model compression. Understanding the tradeoff between the latent dimension $M$ and the network budget $P$ is therefore fundamental to characterizing the expressive efficiency of these methods. We study this tradeoff for affine generators and fully connected ReLU architectures. More precisely, optimizing jointly over architectures $Φ$ satisfying $P_Φ\leq P$ and affine generators $\mathcal{G}:\mathbb{R}^M\to \mathbb{R}^{P_Φ}$, we prove that the optimal worst-case uniform approximation error over the unit ball of $α$-Hölder functions on $(0,1)^d$, where $0<α\leq1$, has the sharp order $ \bigl(P\min\{M,P\}\bigr)^{-α/d}. $ In particular, our result shows that even a fixed-dimensional latent space suffices to achieve vanishing approximation error as the network budget increases. --- ### Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification Authors: Yisen Xi Published: 2026-08-31 Categories: cs.SE, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2608.31142v1 The 2025--2026 AI market has seen a wave of stealth releases: frontier models launched anonymously on developer platforms under codenames. For their users, identity determines data-handling terms, supply-chain risk, and capability expectations. No validated methodology exists for black-box identity verification of anonymous models: practitioner checklists lack accuracy evidence, and self-identification is untrustworthy by design. We propose a four-stage forensic audit protocol for API-served models. Stage 0 reconstructs launch-time configuration from archived platform snapshots (Internet Archive), exposing preview--production drift. Stage 1 fingerprints configuration (context, output ceiling, reasoning, modality) against the platform catalog. Stage 2 tests tokenizer identity with a cross-length differential that rejects short-prompt collisions. Stage 3 corroborates with behavioral probes. We test declaration consistency on 10 known-identity releases (7 exact, 2 precision-differences, 1 partial, 0 counter-directional), not end-to-end identification under anonymity. Identification is validated prospectively on a flagship case whose 2026-08-23 analysis pointed to the GLM-5.3 version line and whose official reveal confirmed those family and version-line inferences (deployment variant was not pre-asserted; Flash was consistent post-reveal), and on three Stage-0-only cases where the protocol produced a graded hypothesis or declined rather than guessed. A standard-library-only implementation is provided as supplementary material. --- ### Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation Authors: Riya Ahuja, Tim Kacprowski, Roya Shiasi Sardoabi Published: 2026-08-31 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2608.31139v1 BioMedRAG introduced retrieval-augmented generation with a learned chunk scorer for biomedical information extraction. However, it relies on fixed-size chunking which can fragment semantic evidence. We propose a configurable semantic chunking framework that addresses this limitation by combining entity-preserving windows, trigger-centered chunking, proposition-first extraction, tiered trigger prioritization, and hierarchical relation resolution. The framework integrates with BioMedRAG by replacing only the chunk construction stage while preserving the embedding model, learned chunk scorer, generator, and evaluation protocol. We evaluate the framework on biomedical relation extraction benchmarks (GM-CIHT, DDI, ChemProt) and adverse event classification (ADE). On GM-CIHT, the full hybrid configuration achieves 82.6% F1, improving over the fixed-size baseline (74.2% F1) by 8.4 points under our experimental setup. Cross-dataset analysis shows that semantic chunking improves extraction datasets with explicit relation cues, such as GM-CIHT and DDI, while fixed chunking remains competitive or stronger for dense biochemical extraction and binary classification settings such as ChemProt and ADE. By externalizing chunking logic into configuration files, the framework provides an interpretable and adaptable alternative to rigid fixed-size chunking for biomedical RAG pipelines. --- ### OntoAligner-Ensemble: Voting-Based Fusion across Heterogeneous Ontology Alignment Techniques Authors: Hamed Babaei Giglou, Sören Auer, Peio Popov, Mahsa Sanaei, Jennifer D'Souza Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.31137v1 Ontology alignment (OA) has evolved through several methodological paradigms, ranging from lexical and structural aligners to knowledge graph embedding (KGE) models and, more recently, Large Language Model (LLM)-based approaches. Although modern OA frameworks provide unified ecosystems for deploying these heterogeneous aligners, mechanisms for systematically reconciling their complementary and sometimes conflicting predictions remain relatively underexplored. We present OntoAligner-Ensemble, a modular and aligner-agnostic framework that combines candidate correspondences through a configurable two-stage process comprising voting-based fusion strategies followed by post-fusion selection policies. The framework supports any aligner implemented within OntoAligner that produces candidate correspondences, enabling diverse alignment paradigms to be integrated through a unified decision process. To demonstrate its effectiveness, we instantiate the framework using representative lightweight string-aligner, KGE-based, and Retrieval-Augmented Generation aligners powered by both open-weight and API-based LLMs. We evaluate individual aligners and ensemble configurations across eight benchmark tasks from five OAEI tracks spanning biomedical to beyond-equivalence. The results show that ensemble fusion consistently improves the balance between precision and recall and frequently outperforms standalone aligners across diverse domains. Furthermore, our analysis reveals that ensemble composition directly affects the precision-recall trade-off: heterogeneous cross-paradigm ensembles generally improve precision, whereas homogeneous LLM ensembles more often achieve higher overall F1-scores. These findings demonstrate that systematic ensemble learning offers a robust and reproducible strategy for OA while providing practical guidance for selecting ensemble compositions under different alignment scenarios. --- ### Implementing neural network mixed-effects models in Template Model Builder (TMB) Authors: Nan Zheng, Hoi Yiu Cheung, Vibhu Sharma, James T. Thorson, Noel G. Cadigan Published: 2026-08-31 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.31133v1 Neural network mixed-effects models (NMMs) have gained traction by combining the strong representation and predictive power of artificial neural networks with the capacity of mixed-effects modeling to capture complex correlation structures. However, existing estimation approaches rely heavily on manual derivations of objective functions and gradients, which inherently forces simplifying approximations and severely constrains the complexity and accuracy of NMMs. In this work, we introduce a general framework for implementing NMMs using Template Model Builder (TMB). By leveraging automatic differentiation and Laplace approximation, TMB requires users to specify only the negative joint log-likelihood and any regularization terms. The framework automatically integrates out random effects and evaluates the marginal objective function alongside its exact gradients, eliminating the need for manual derivations or ad hoc approximations. We demonstrate the efficiency, flexibility, and statistical performance of TMB-based NMMs across two numerical examples, including an application to monotonic NMMs. Reproducible code is provided to facilitate broader adoption. --- ### DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk Screening Authors: Yung Wei Shueh, Zhi-Jie Chen, Chia-Hsuan Hsu, Hsin-Ling Hsu, Donghua Zhang, Chenwei Wu, Jun-En Ding, Tongze Zhang, Shihao Yang, Pengfei Hu, Fang-Ming Hung, Feng Liu Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.31128v1 Large language models (LLMs) offer promising clinical decision support but remain vulnerable to hallucinated facts, unsupported recommendations, and citation errors. We present DIASENTINEL, a fully on-premise multi-agent system for one-year type 2 diabetes mellitus (T2DM) risk screening and guideline-grounded report generation from electronic health records (EHRs). The system integrates calibrated risk prediction, deterministic clinical signal extraction, Reciprocal Rank Fusion over American Diabetes Association (ADA) guidelines, and a hybrid verification layer combining rule-based checks with LLM entailment. The demonstration provides a real-time batch-screening dashboard and an interactive patient report interface with cited recommendations, verification results, and raw EHR comparison. DIASENTINEL demonstrates a practical framework for reliable, auditable, and privacy-preserving LLM-based clinical decision support. --- ### On the Complexity of the Compatibility Problem for Succinctly Encoded Conditional Distributions Authors: Guy Emerson Published: 2026-08-31 Categories: cs.LG, cs.CC, math.PR arXiv: https://arxiv.org/abs/2608.31120v1 The motivation for this paper is the investigation of the trade-offs implicit in probabilistic models used in machine learning. Models are often used to make predictions in the form of conditional probabilities. However, a pair of conditional distributions p(x|y) and p(y|x) may not be compatible with any joint distribution p(x,y). Given two such conditionals, determining if there exists a compatible joint is known as the compatibility problem. For discrete random variables, when the conditionals are encoded as probability tables, the compatibility problem has a known solution, which is computationally tractable. In this paper, we formalise and study a succinct version of the problem, encoding conditional distributions as arithmetic circuits. This is applicable to practical applications of probabilistic modelling in high-dimensional settings, including neural network models. We show that, for succinct circuit representations of conditionals, the compatibility problem is intractable. In the case that all probabilities are non-zero, the problem is co-NP-complete. In the case that probabilities can be zero, we give examples to demonstrate that several notions of compatibility can be distinguished, and we prove that multiple versions of the problem are PSPACE-complete. Furthermore, we show that, assuming the polynomial hierarchy does not collapse, there exist compatible succinct conditionals whose joint cannot be expressed succinctly. Implications of these results for probabilistic modelling and machine learning are discussed. --- ### PaperGym: Rubric-Centered Evolution for Research-Plan Generation Authors: Yuhan Wang, Zhengxi Lu, Yuchen Yan, Kaitao Song, Wenqi Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.31119v1 Research planning is the decisive capability of AI scientists. Yet a research plan admits no verifiable answer, so reinforcement learning lacks the environment it requires: tasks paired with a critic. Rubrics extracted from scientific papers can supply the critic. Existing pipelines, however, draw the question and the criteria from the same content, so the reward can be earned by paraphrase. The rubric is further compressed into a single scalar per rollout. We introduce PaperGym, a unified framework that turns each research paper into a complete training environment. PaperGym exploits the structure of a paper: the question is synthesized from the research goal and background, while the criteria are derived from the method and experiments. The criteria span methodological innovation and experimental design, and criterion leakage falls to 3.7%, versus 11.90% to 34.10% in existing datasets. Training uses the rubric twice: first as privileged context for OPSD's self-teacher, then as the reward for GRPO. Across Qwen3-1.7B/4B/8B, this schedule outperforms supervised fine-tuning, either stage alone, and the reverse ordering, improving five-benchmark averages by +5.6, +5.0, and +4.8 points. With the recipe held fixed, models trained on PaperGym-20k win 58.1% of three-way comparisons, against 28.2% for RubricHub Science. The trained Qwen3-8B reaches 73.48 on ResearchQA, above the far larger Kimi K2.6. We release the pipeline, the 20,000-instance corpus PaperGym-20k, and the benchmarks PaperGym-Innov and PaperGym-Design. --- ### When Does Bigger Help? A Controlled Study of LLM Scale for Ontology Learning Authors: Hamed Babaei Giglou, Sören Auer, Jennifer D'Souza Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.31118v1 The effect of Large Language Model (LLM) scale on ontology learning (OL) performance remains insufficiently characterized. We present a controlled evaluation of 13 models spanning dense and Mixture-of-Experts variants from the Qwen3.5 and Qwen3.6 lineages, together with proprietary GPT release variants, using the OntoLearner retrieval-augmented generation pipeline. All models are evaluated with the same embedding model, retrieval configuration, prompt templates, decoding settings, datasets, and metrics on term typing, taxonomy discovery, and non-taxonomic relationship extraction across four biomedical and materials science and engineering ontologies. Within the dense Qwen3.5 lineage, increasing parameter count primarily improves precision rather than recall, with the largest gains occurring between 9B and 27B parameters. However, the effect of scale is neither monotonic nor uniform across tasks and domains. Dense 27B models outperform substantially larger sparse models on term typing, whereas larger Mixture-of-Experts models achieve the strongest open-weight results on taxonomy discovery. Non-taxonomic relationship extraction remains difficult across model scales, particularly for the Materials Data Science ontology. Performance differences across matched Qwen variants and proprietary GPT releases further indicate that architecture and model lineage can outweigh nominal parameter count. These findings show that model size alone is an insufficient selection criterion for OL and provide empirical guidance for reproducible LLM-assisted ontology engineering. --- ### "Train classical, deploy quantum" requires rethinking generalization Authors: Snehal Raj, Natansh Mathur, Alejandro Perdomo-Ortiz Published: 2026-08-31 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2608.31117v1 Generative models have become central across science and industry, from image and text synthesis to the design of molecules and materials. Quantum generative models are considered one of the most promising applications for quantum computers, since a quantum circuit naturally produces samples from the distribution it encodes, and for suitable circuits that distribution is believed to be hard for any classical computer to reproduce. A leading strategy trains these models on a classical computer and reserves the quantum device for generating samples at deployment. This is possible when the training loss can be evaluated on a classical computer. A prime example is the maximum mean discrepancy (MMD$^2$), a moment-matching loss that compares the model and the data through their Pauli-$Z$ correlations. Research so far has asked whether such models can be trained and whether their sampling is hard; whether minimizing such an objective yields a model that generalizes, rather than one that merely reproduces the training statistics, remains poorly understood. We benchmark a broad set of quantum and classical generative models by direct sampling and show that models trained with a moment-matching loss generally show worse generalization than the likelihood-trained models. We show this on two application-inspired datasets: first a cardinality-constrained dataset at up to $30$ qubits and second a dataset of genomic single-nucleotide variants, whose valid set is the observed data. These results indicate that a converged moment-matching loss is not a reliable measure of generalization, and that train-classical, deploy-quantum workflows will need approaches that target generalization directly, leaving open whether better training objectives suffice or whether the model architectures themselves must change. --- ### Overcoming critical slowing down in frustrated spin systems by learned multiscale sampling Authors: Gabriele Bandini, Giulio Biroli, Patrick Charbonneau, Andrea Gambassi Published: 2026-08-31 Categories: cond-mat.stat-mech, stat.ML arXiv: https://arxiv.org/abs/2608.31114v1 Cluster algorithms, such as the Swendsen--Wang and Wolff methods, are among the most successful MCMC methods for mitigating critical slowing down in statistical systems. These constructive cluster algorithms, however, fail in the presence of even extremely weak frustration. Here, we sidestep this fundamental limitation by learning rather than constructing the relevant clusters. Specifically, we use the wavelet conditional renormalization group (WCRG) sampling method to learn the probability distribution of collective fluctuations of a frustrated two-dimensional soft-spin model. Configurations are then generated recursively from coarse to fine scales by sampling conditional wavelet distributions. The WCRG method reproduces the main statistical properties of the system across different phases, including the local-field distribution and the structure factor. At an Ising-like critical point, the conditional dynamics remains decorrelated within $\mathcal{O}(1)$ sweeps at each scale, yielding an overall sampling complexity of $\mathcal{O}(\log_2 L)$, thus making WCRG much more efficient than standard local MCMC methods. These results show that learned multiscale sampling can overcome critical slowing down in frustrated systems for which conventional cluster algorithms fail. By assessing the sampling accuracy of different observables, we also clarify the main tradeoff of the WCRG method: the accuracy of the fast sampling scheme depends on the expressiveness of the energy-based model used to estimate the wavelet conditional distributions. --- ### BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives Authors: Pradyumn Goyal, Yizhak Ben-Shabat, Hsueh-Ti Derek Liu, Haomiao Jiang, Snehasish Mukherjee, Kyle Spence, Mark Stauber, Evangelos Kalogerakis, Yunze Zeng Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.31113v1 We introduce BLARM, a feed-forward method for video-driven 3D mesh animation. Given a monocular video and a static object mesh, BLARM predicts a temporally coherent animated mesh whose motion follows the video. Rather than relying on explicit rigs or directly regressing high-dimensional vertex motion, we represent animation using a compact set of learned, time-varying rigid motion components and time-invariant vertex-to-component skinning weights. This yields a low-dimensional deformation space without requiring skeletons, cages, skinning weights, or rig annotations. Our architecture conditions geometry-derived deformation latents on video features through factorized spatial-temporal attention, then decodes rigid transformations blended by predicted skinning weights. Trained with trajectory reconstruction, entropy regularization, and motion-aware contrastive learning, BLARM produces accurate and temporally stable animations while recovering compact, interpretable motion structure from monocular video. --- ### Aspire: Can Models Self-Evolve from Vague Goals? Authors: Yuhao Wu, Jingyuan Zhang, Jiajun Shi, Yuxuan Zhang, Xinping Lei, Junting Zhou, Zexuan Wang, Yuchen Wu, Huan Zhou, Duo Wang, Yinzhu Piao, Yongchang Peng et al. Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.31111v1 Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to learn, and determine whether they have actually improved. In contrast, existing work on LLM self-evolution typically begins with tasks and evaluation metrics specified by humans, reducing self-evolution to optimizing an explicit objective rather than deciding what and how to learn. We introduce ASPIRE, a benchmark for vague-goal-driven self-evolution. ASPIRE provides only a natural-language capability goal while downstream evaluation tasks remain hidden. The agent must operationalize the goal by choosing data and update methods, constructing training and validation signals, and deciding when to evaluate. ASPIRE supports both model-weight and agent-harness evolution in a unified interactive environment and evaluates the resulting systems on a hidden, expert-authored set of 520 items spanning six goals. Our experiments show that vague goals redirect search effort toward goal interpretation. Current agents routinely complete training and harness-editing loops, but weight-level gains remain sparse and unstable, and the strongest evolved harness remains below the engineered Qwen-Agent reference. Agents often train on mismatched data and trust narrow self-evaluations, so local gains fail to transfer to hidden evaluation and continued search and training can erase earlier improvements. --- ### Stress-Testing Efficient Responsible-AI Evaluation: When Compute Savings Change Benchmark Conclusions Authors: Ahmed El Kady, Aravind Narayanan, Rehana Riaz, Yani Ioannou, Shaina Raza Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.31108v2 Efficient evaluation changes the protocol used to support claims about model behavior, yet it is rarely tested whether those claims remain stable after the evaluation itself is made cheaper. We stress-test conclusion robustness in responsible-AI benchmarking by evaluating three dense and mixture-of-experts models on BBQ and BBQ-V under seven conditions spanning batching, quantization, benchmark reduction, and their combinations. Rather than treating preserved aggregate accuracy as sufficient, we compare accuracy, bias severity and prevalence, reasoning quality, subgroup behavior, subset-membership stability, runtime, and measured GPU energy against a full-benchmark BF16 baseline. Larger batching keeps accuracy within 0.35 percentage points of baseline and produces comparatively small subgroup changes, while reducing energy in five of six model--dataset settings. INT8 largely preserves quality but uses 1.79--4.26$\times$ baseline energy. INT4 causes larger, model- and context-dependent changes. Reduced benchmarks provide the most consistent savings, but very small subsets are substantially more sensitive to which items are retained. Efficient evaluation should therefore be treated as a measurement intervention whose validity must be checked across the conclusions the benchmark is intended to support. Our project website is https://vectorinstitute.github.io/sustainable-rai-evaluation/ and the code is available at https://github.com/VectorInstitute/sustainable-rai-evaluation. --- ### Stress-Testing Efficient Responsible-AI Evaluation: When Compute Savings Change Benchmark Conclusions Authors: Ahmed El Kady, Aravind Narayanan, Rehana Noorani, Yani Ioannou, Shaina Raza Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.31108v1 Efficient evaluation changes the protocol used to support claims about model behavior, yet it is rarely tested whether those claims remain stable after the evaluation itself is made cheaper. We stress-test conclusion robustness in responsible-AI benchmarking by evaluating three dense and mixture-of-experts models on BBQ and BBQ-V under seven conditions spanning batching, quantization, benchmark reduction, and their combinations. Rather than treating preserved aggregate accuracy as sufficient, we compare accuracy, bias severity and prevalence, reasoning quality, subgroup behavior, subset-membership stability, runtime, and measured GPU energy against a full-benchmark BF16 baseline. Larger batching keeps accuracy within 0.35 percentage points of baseline and produces comparatively small subgroup changes, while reducing energy in five of six model--dataset settings. INT8 largely preserves quality but uses 1.79--4.26$\times$ baseline energy. INT4 causes larger, model- and context-dependent changes. Reduced benchmarks provide the most consistent savings, but very small subsets are substantially more sensitive to which items are retained. Efficient evaluation should therefore be treated as a measurement intervention whose validity must be checked across the conclusions the benchmark is intended to support. Our project website is https://vectorinstitute.github.io/sustainable-rai-evaluation/ and the code is available at https://github.com/VectorInstitute/sustainable-rai-evaluation. --- ### VeriCam: A Verification Baseline for the Classification of Unknown Data Authors: Lucas Wojcik, Gabriel E. Lima, Sergio M. Silva, Eduil Nascimento, David Menotti Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.31107v2 The advent of foundation models have enabled a new era in zero-shot classification. Yet, key challenges persist. Despite their impressive generalization power that leverages the immense pre-training knowledge, both foundation models for image and text as well as vision-text hybrids lack the representational power needed for fine-grained, minutiae-based class separation that some real-world tasks require. To address the current gaps in the literature, we propose VeriCam, a pipeline designed to learn highly specialized features that enable classification of unknown classes in unseen data. VeriCam works by leveraging the representation power of image models trained for the verification task, where the model develops an intricate feature space that incorporates fine-grained details. By training a model to discriminate between pairs of images from the same and different classes, a relational graph is constructed, representing the class relationships between data points. We then present two approaches for graph clustering: a naive algorithm and a specific setup for the Leiden graph clustering algorithm. The pipeline is validated on the LPLCv2 dataset, which comprises real-world traffic surveillance images. We show that the dataset carries an inherent capture device bias that is posed as a generalization challenge for downstream License Plate recognition tasks such as OCR. As such, we dynamically identify capture devices with a label-agnostic approach, enabling the construction of a fair and unbiased benchmark. In the cross-device scenario, our pipeline reaches an F1-Score of 93.45 in the verification baseline and a V-Measure score of 80.13 in the clustering step. All code is publicly available at https://github.com/lmlwojcik/VeriCam --- ### VeriCam: A Verification Baseline for the Classification of Unknown Data Authors: Lucas Wojcik, Gabriel E. Lima, Sergio M. Silva, Eduil Nascimento, David Menotti Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.31107v1 The advent of foundation models have enabled a new era in zero-shot classification. Yet, key challenges persist. Despite their impressive generalization power that leverages the immense pre-training knowledge, both foundation models for image and text as well as vision-text hybrids lack the representational power needed for fine-grained, minutiae-based class separation that some real-world tasks require. To address the current gaps in the literature, we propose VeriCam, a pipeline designed to learn highly specialized features that enable classification of unknown classes in unseen data. VeriCam works by leveraging the representation power of image models trained for the verification task, where the model develops an intricate feature space that incorporates fine-grained details. By training a model to discriminate between pairs of images from the same and different classes, a relational graph is constructed, representing the class relationships between data points. We then present two approaches for graph clustering: a naive algorithm and a specific setup for the Leiden graph clustering algorithm. The pipeline is validated on the LPLCv2 dataset, which comprises real-world traffic surveillance images. We show that the dataset carries an inherent capture device bias that is posed as a generalization challenge for downstream License Plate recognition tasks such as OCR. As such, we dynamically identify capture devices with a label-agnostic approach, enabling the construction of a fair and unbiased benchmark. In the cross-device scenario, our pipeline reaches an F1-Score of 93.45 in the verification baseline and a V-Measure score of 80.13 in the clustering step. All code is publicly available at https://github.com/lmlwojcik/VeriCam --- ### DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution Authors: Jiashu Zhu, Yanhao Zheng, Ruitian Tian, Rujing Dang, Shen Zhang, Bingze Song, Jiachen Lei, Ruimin Lin, Jiahong Wu, Xiangxiang Chu Published: 2026-08-31 Categories: cs.CV, cs.SD arXiv: https://arxiv.org/abs/2608.31106v1 Recent video generators often omit audio or synthesize it in a separate stage, limiting reciprocal modeling of visual dynamics and acoustic events. We present DreamX-Creator 1.0, a compact native joint audio-video generation system centered on a 7B generator. Conditioned on a first frame and a text prompt, the generator jointly denoises modality-specialized audio and video streams. The streams are processed independently in the first half of the network and coupled in the latter half through Gated Cross-Modal Attention, whose token- and head-wise output gates modulate each active cross-modal attention-head output. A unified Audio-Video Data System constructs and filters temporally coherent clips, produces structured multimodal annotations, and organizes clips into capability-oriented data pools. Progressive Joint Training comprises two audio-video pre-training stages followed by High-Quality Finetuning. Audio-Video Reinforcement Learning further post-trains the generator with Modality-Aware Multimodal Feedback that routes video-, audio-, and cross-modal feedback to the corresponding streams. For high-resolution output, our Autoregressive 1-Step 2K Refinement pipeline adapts a bidirectional multi-step teacher into an autoregressive multi-step refiner and distills it into a student requiring one denoising evaluation per temporal chunk. Overall, DreamX-Creator 1.0 achieves native, synchronized audio-video generation with performance competitive with state-of-the-art open-source systems. By releasing our compact 7B generator and 2K Refiner, we seek to democratize native audio-video generation and provide an accessible foundation for future research in unified audio-video generative modeling. --- ### BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing Authors: Adrians Skapars, Edoardo Manino Published: 2026-08-31 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.31105v1 Users of a deployed language model routinely encounter behaviours that testing almost never surfaces, since deployment puts the model through orders of magnitude more interactions than any evaluation can simulate. Automated auditors make testing cheap to scale and flexible enough to cover almost any specified behaviour, yet their lack of optimisation pressure makes them sample-inefficient. To address this shortcoming, we introduce BLOOM-WILT, a full auditing pipeline that elicits natural multi-turn instances of rare behaviours, without training cost or access beyond the target's next-token distribution. On the input side, WILT's auditor model revises its conversational strategy across rounds, learning from previous scored interactions. On the output side, WILT adaptively reweights the target's decoding using the model's own distribution conditioned on an elicitation prompt, so that behaviour-relevant generations are sampled ahead of others it finds equally probable when unprompted. We evaluate WILT across 4 target models and 8 behaviours, where it beats the baseline auditor in 30 of the 32 settings and overturns the previous model safety rankings. WILT raises average behaviour presence from 51% to 100% when eliciting self-harm encouragement from Qwen3.5-4B, beating every elicitation method we port into the same pipeline at matched compute, without pushing output probability below the baseline's. --- ### LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering Authors: Gopi Krishnan Rajbahadur, Amir M. Ebrahimi, Boyuan Chen, Ahmed E. Hassan Published: 2026-08-31 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.31102v1 Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improvements under fixed compute and mixture budgets without regressing the rest. The maintained artifact is increasingly dataware: behavior governed by a curated post-training mixture, updated via bounded mixture patches rather than clean-slate retraining. From an industrial code-generation improvement effort, we offer a maintainer's perspective on why this work is hard in practice, distilling three recurring challenges, zero-sum mixture design, yield as the binding metric, and end-to-end integration under uncertainty, and arguing that progress depends less on one-off recipes than on an engineering discipline for programming dataware. In our case study, interventions that raised the conversion of teacher distillation into usable training data increased accepted supervision by 2.84 times while using the same solution teacher and four solution attempts per candidate problem. In our primary evaluation, the yield-engineered patch improved CodeForces pass@1 by +2.59 points (+3.11 pass@3) and held-out LiveCodeBench v6 pass@1 by +6.11 (+8.05 pass@3), all statistically significant across 16 stochastic evaluations of each benchmark from one fixed checkpoint per condition, with internal AIME and MATH regression suites within tolerance. --- ### S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement? Authors: Jiajun Shi, Siyuan Tao, Yuhao Wu, Zexuan Wang, Jingyuan Zhang, Jiaheng Liu, Xinping Lei, Xinrong Zhang, Siyuan Fang, Zhewen Tan, Tianle Cai, Junhao Fang et al. Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.31100v1 Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience, yet existing agent benchmarks largely evaluate them as fixed policies. It therefore remains unclear whether an agent can actively test its behavior, judge the resulting experience, and use that experience to improve future decisions. We introduce \textbf{S\textsuperscript{3}Gym}, an interactive benchmark for evaluating LLM self-improvement through three coupled capabilities: \textbf{Self-Testing}, \textbf{Self-Judging}, and \textbf{Self-Improvement}. S$^3$Gym separates permissive exploration from strict held-out evaluation and instantiates this protocol in seven text-based games with executable environment verifiers. We evaluate three pathways for incorporating interaction experience: direct History ICL, score-conditioned Summary Memory, and parameter Training. Our experiments reveal that self-improvement is neither automatic nor uniform. Context-level experience improves performance for several model--game pairs, but the most effective pathway depends strongly on the task structure: summaries are beneficial when experience can be compressed into reusable strategic rules, yet often underperform raw history when success depends on precise, state-contingent information. Parameter training produces substantial gains on some tasks, but also exhibits unstable improvement and severe negative transfer on others. These findings show that recognizing successful actions is insufficient; agents must also transform feedback into executable and transferable policies. S$^3$Gym provides a unified framework for diagnosing this process and identifying the bottlenecks that prevent agents from translating interaction experience into reliable self-improvement. ---