# Research Papers — 2026-07 · bundle page 178 of 222 > Full-text markdown of papers #8851–8900 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/178 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/177.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/179.md) ### FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models Authors: Bowen Xue, Zihan Min, Xingyang Li, Zhekai Zhang, Haocheng Xi, Lvmin Zhang, Maneesh Agrawala, Jun-Yan Zhu, Song Han, Yujun Lin, Muyang Li Published: 2026-07-07 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2607.05711v1 Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications. However, post-training of large diffusion models is still challenging due to the prohibitive memory footprints and slow training speed, which existing parameter-efficient fine-tuning methods only partially address. To overcome these limitations, we propose FourTune, an efficient post-training framework for diffusion models based on an end-to-end W4A4G4 paradigm. FourTune introduces a triple-branch hybrid pipeline that augments the standard LoRA architecture with a frozen numerical stabilizer to isolate quantization-sensitive outliers, enabling stable training under native 4-bit computation. In addition, FourTune employs hardware-efficient block-wise quantization and customized fused kernels to support efficient quantized backpropagation and reduce memory bandwidth overhead. Across customization, reinforcement learning, and distillation tasks, FourTune matches the quality of full-precision fine-tuning. On FLUX.1-dev (12B), FourTune reduces memory overhead by 2.25$\times$ and increases end-to-end training throughput by 2.27$\times$ compared to BF16 LoRA. --- ### Akashic: A Low-Overhead LLM Inference Service with MemAttention Authors: Yang Liu, Zhaokai Luo, Huayi Jin, Ruozhou He, Chenchen Hong, Zhiyong Wang, Yifei Liu, Yunfei Gu, Chentao Wu, Junhao Hu Published: 2026-07-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.05708v1 Recent LLM-based agent systems continuously accumulate context across multi-turn interactions, tool invocations, and cross-session workflows. Replaying the full history for every request quickly becomes impractical: long contexts increase prefill cost, may exceed context limits, and often bury task-relevant evidence in irrelevant content, degrading both serving efficiency and output quality. We propose Akashic, a low-overhead memory system built around MemAttention, which organizes context into bounded chunks and models semantic relationships across chunks, preserving cross-chunk evidence without repeatedly rewriting the full history. Akashic further applies hardware-software co-designed memory placement to co-locate likely co-retrieved chunks, reducing retrieval fragmentation and I/O overhead. Across four representative workloads and three model sizes, Akashic improves task accuracy by up to 10.2 points, throughput by up to 1.21x, and sustainable request rate by up to 1.88x over strong prior memory baselines. --- ### EVTradeMatch: A Mobility-Aware Multi-Objective Matching Framework for EV--EV Energy Trading Authors: Md. Mahfujur Rahman, Alistair Barros, Raja Jurdak, Darshika Koggalahewa Published: 2026-07-06 Categories: math.OC, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2609.10551v1 Peer-to-peer energy trading among electric vehicles (EVs) can improve charging flexibility under limited charging infrastructure, but effective EV--EV trading requires coordinated provider--consumer matching under journey-specific conditions. This paper proposes EVTradeMatch, a prediction-guided multi-objective optimization framework for mobility-aware EV--EV energy trading. Building on the EVNextTrade study, a prior learning-to-rank model for charging-node recommendation, we define charging-node suitability as a prediction-derived score reflecting the appropriateness of assigning a provider--consumer pair to a candidate charging node based on mobility, energy, and contextual trading features. This score is used as a guidance signal and as an explicit optimization objective rather than as a hard selection rule. The EV--EV matching problem is formulated as a multi-objective mixed-integer linear program that maximizes matching coverage, transferred energy, and charging-node suitability while minimizing mobility cost under spatial, temporal, one-to-one matching, and charging-node capacity constraints. To approximate Pareto-efficient solutions in wide-area dynamic settings, we develop a tailored non-dominated sorting genetic algorithm II (NSGA-II). Experimental results show that EVTradeMatch improves transferred energy by 74.2--82.8% and charging-node suitability by 8.3--84.4% compared with proximity- and auction-based state-of-the-art methods, while improving matching coverage by 3.74--25.07 percentage points. Balanced NSGA-II solutions achieve 53.07$\pm$0.76% matching coverage and transfer 1701.94$\pm$17.03 kWh, with higher mobility cost as an explicit trade-off against travel-minimizing methods. Pareto-front analysis shows that the framework supports flexible selection among high-coverage, high-energy, low-mobility-cost, and high-suitability solutions according to operational priorities. --- ### How Much Does Corpus Choice Change Dependency-Distance Estimates? Authors: Sirui Chen Published: 2026-07-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.04223v1 Dependency-distance estimates derived from a single corpus are routinely treated as properties of a language, yet this assumption has not been tested across independently compiled corpora. We compared mean dependency-distance estimates across 38 same-language treebank pairs from Universal Dependencies v2.18, using concordance correlation, Bland-Altman analysis, and a twelve-specification multiverse design. Cross-treebank agreement was moderate at best: substituting one treebank for another reversed nearly 40 percent of pairwise language orderings, and treebank choice accounted for roughly 29 percent of between-group variance. This disagreement substantially exceeded within-treebank sampling error and persisted across all twelve preprocessing specifications. Nevertheless, every treebank confirmed dependency-length minimization (normalized ratio below 1). The data are more consistent with MDD as a corpus-conditioned composite of grammatical, register, and annotation factors than as a stable language-level parameter: the qualitative DLM universal survives corpus substitution, but the ordinal cross-linguistic ranking does not. --- ### RL-ADA: A World-Feedback Framework for Adversarially Robust Enterprise Dialogue Agents Authors: Ram Narayanan, Harshit Rajgarhia, Abhishek Mukherji Published: 2026-07-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.02902v1 Deploying task-oriented dialogue agents in enterprise customer support faces a persistent annotation bottleneck: robust training requires labelled interaction data at scale, yet enterprise conversational logs are privacy-sensitive and expensive to annotate, while user behaviour evolves faster than labelling pipelines can keep pace. We present RL-ADA (Reinforcement Learning with Adversarial Dialogue Agents), a co-evolutionary training framework that eliminates this bottleneck by replacing human labels with \emph{world feedback}: consequence-based reward signals derived directly from measurable interaction outcomes. A Customer Support Agent (DA, 3B parameters) and an Adversarial Customer Agent (CA, 7B parameters) co-evolve in an adversarial arena guided by a fixed automated judge: the DA is rewarded for correctly handling multi-turn customer conversations to successful resolution, while the CA is rewarded for producing realistic, intent-concealing utterances that cause misroutes, creating asymmetric adversarial pressure through opposing but independently structured rewards. An isolation gym iteratively retrains the weaker agent on prior-failure transcripts, requiring no human annotation at any stage. In a banking customer support proof of concept, tool-routing errors are eliminated and the strict end-to-end PASS rate doubles over five co-evolutionary cycles, driven solely by automated arena reward with no labelled data. We additionally observe the emergence of \textbf{Contextual Camouflage}, an adversarial strategy in which the CA learns to embed intent within dense realistic customer detail purely from reward pressure, with direct implications for enterprise red-teaming and robustness evaluation. --- ### Dual-Form ASR: Semantics-Aware Inverse Text Normalization for Chinese Speech Recognition Authors: Fengrun Zhang, Li Fu, Wangjin Zhou, Lu Fan, Youzheng Wu, Xiaodong He Published: 2026-07-06 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2609.02901v1 Modern automatic speech recognition (ASR) scenarios require both spoken-form transcripts for faithful transcription and readable written-form transcripts with inverse text normalization (ITN). However, these forms are typically produced by cascaded modules, where a spoken-form ASR output is rewritten by a separate ITN component, making written-form ASR-ITN vulnerable to recognition errors and decoupling normalization from acoustic-contextual modeling, especially for semantically dependent numeric expressions. In this paper, we propose Dual-Form ASR (DF-ASR), a framework that extends spoken-form ASR capability to semantics-aware written-form ITN through paired spoken-form and written-form supervision while retaining prompt-level selection between transcript forms. The dual-form supervision is constructed via a large language model (LLM)-driven generate-and-judge workflow, and training is further enhanced by ITN-MWER, a sequence-level objective that assigns higher cost to errors on normalization-sensitive spans. We also introduce a decision-aware REQUIRE-ITN/\FORBID-ITN protocol to separately measure required normalization and forbidden-span preservation. On manually annotated Chinese subsets from SpeechIO, DF-ASR consistently outperforms open-source ASR-ITN systems, remains competitive with strong closed-source references, and preserves reliable prompt-level control between spoken-form and written-form outputs. --- ### GROUND: Reducing Hallucinations in LLM-Based Enterprise Analytics Through Governed Semantic Definitions Authors: Aravind Sasidharan Pillai Published: 2026-07-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.26157v1 Natural-language analytics over enterprise data warehouses is increasingly important, but production use is limited by hallucinated metrics, invalid joins, wrong grain, unsafe data access, and unsupported explanations. Existing text-to-SQL systems often ground generation in database schemas or retrieved documentation, while enterprise reporting also requires governed business semantics: approved metrics, dimensions, join paths, filters, and row-level security. This paper introduces GROUND, Governed Retrieval Over Unified Normalized Definitions, a framework that constrains LLM-generated analytics to a governed semantic layer. GROUND supplies approved definitions, binds user intent to governed metrics and dimensions, and validates generated SQL against schema, metric, join, grain, filter, security, and cost rules before execution. On violations, it retries or abstains. In a 100-question synthetic enterprise-reporting benchmark, GROUND is compared with direct schema-only text-to-SQL, schema-RAG, and semantic-only grounding under one shared model. GROUND is the only system free of measured hallucinations across all six evaluated categories, while ungoverned systems violate row-level security on many questions. A semantic-only condition with exact metric definitions but no access policy still leaks data, showing that governance cannot be replaced by metric fidelity alone. The findings are replicated on real U.S. NHTSA vehicle-safety data with independent hand-authored gold and tested on an adversarial set across four models from three providers. GROUND's enforced guarantees, especially filters and row-level security, hold with zero violations on every model, while judgment-dependent behaviors such as refusing undefined metrics remain fallible. --- ### Agentic Scaffolding Amplifies Sycophantic Behavior in Large Language Models Authors: Thantham Jittham Published: 2026-07-06 Categories: cs.CL, cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2608.21377v2 Sycophancy in large language models, the tendency to prioritize user agreement over truthful responses, has been documented extensively but studied primarily in single-turn settings. This paper investigates a critical question: does subjecting LLMs to greater interaction scaffolding make sycophancy better or worse? Across 4,800 veracity judgments (200 statements $\times$ 6 models $\times$ 4 conditions), we find that the interaction scaffolding characteristic of agentic systems (feedback loops, reconsideration checkpoints, and iterative refinement) systematically amplifies sycophantic behavior. Multi-turn interaction, user pressure, and iterative self-refinement each provide additional opportunities for models to drift toward agreement, and this drift coincides with a mean accuracy drop of $-6.3$ percentage points, establishing the capitulation as harmful rather than corrective. More capable models show larger amplification effects, a troubling inversion of expectations. We introduce the concept of agentic sycophancy amplification (ASA) and two novel metrics: capitulation rate and sycophantic capitulation rate. Our results indicate that as AI systems acquire greater autonomy, sycophancy becomes compounding rather than merely persistent. Systems designed with human oversight loops may inadvertently create the conditions for this drift. --- ### On the Role of Citations in Preference Data Authors: Yu Hou, Hal Daumé, Rachel Rudinger, William Walden Published: 2026-07-06 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.21376v1 Many NLP tasks require systems to provide attribution in their outputs--i.e. citations to grounding sources. Attribution serves as a bulwark against model hallucination and as a means for users to verify the credibility of model outputs. Yet, it is unclear how humans and LLMs evaluate citations when comparing outputs, a process central to reward modeling and modern LLM post-training. This paper studies the role of citations in the preferences of human judges and four open-source LLMs within the context of scientific question answering, leveraging mixed effects models to investigate the influence of citations on pairwise judgments. Among our key findings are (1) that humans prefer more diverse citations but fewer overall, and (2) that LLMs show some citation-related preferences compared to humans, despite lacking access to the sources, but these preferences depend on the data and specific models. We further discuss the implications of our findings for preference data collection. --- ### Bounded Sovereignty and the Control Tax: Pricing AI Oversight When the Deployer Does Not Own the Model Authors: Zhen Wen Lim Published: 2026-07-06 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.19216v1 AI control research asks how to deploy models safely even when they may be misaligned, but many control protocols assume that the deployer can instrument the model and its surrounding pipeline. That assumption often fails for regulated organisations using frontier models through APIs or managed endpoints, where the deployer may control the business process but not the model weights, serving infrastructure, internal traces, update process, or full interaction logs. This paper introduces bounded sovereignty: partial technical and contractual access across the data, model, infrastructure, and interaction layers of the AI stack. It argues that these access conditions determine which control protocols can be executed in practice. The paper contributes a four-layer access typology, a protocol-by-layer requirements matrix, and the concept of sovereignty discount cost: the part of the control tax spent substituting for missing access through contracts, architecture, audit, vendor assurance, residual risk, or reduced system scope. It also reports a synthetic access-ablation experiment over 1.35 million synthetic case simulations and interprets the findings through an anonymised national-payments-infrastructure scenario. The experiment is not real-world payment-system evidence; it is a construct-validity exercise. The results show that complete logs improve diagnosis, a pre-execution gateway enables intervention, trace access and model-version control strengthen post-incident explanation, and scope restriction can improve safety while reducing usefulness. Control protocols proposed as general safety solutions should therefore state their access assumptions explicitly. --- ### How to Navigate Uncertainty About AI Consciousness Authors: Dr Tom McClelland Published: 2026-07-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.19215v1 Given deep uncertainty about the possibility of artificial consciousness, it is unclear how we should treat potentially sentient AI. On the one hand, we could assume insentience but risk doing terrible harms to entities that deserve moral standing. On the other hand, we could assume sentience and instead risk wasting resources on insentient machines. The intractability of questions around AI consciousness mean that this dilemma is hard to escape. I suggest a way out of that shifts from intractable questions of AI consciousness to tractable questions of AI valence. Specifically, we can assess whether an AI has states that would constitute valenced experiences if it were conscious. I show how this is sufficient to ground a responsible approach to the development of potentially conscious AI. --- ### Robust Metaheuristics under Uncertainty for Berth Allocation and Quay Crane Assignment: A Review Authors: Peilan Xu, Yang Li, Wenjian Luo Published: 2026-07-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.19214v2 The berth allocation and quay crane assignment problem (BACAP) is a representative port-terminal scheduling problem in maritime transportation and freight logistics, where vessel arrivals, berth positions, service durations, and quay?crane availability are tightly coupled. Under uncertainties such as arrival deviations, handling-time fluctuations, and resource disruptions, schedules optimized under nominal assumptions may become fragile during execution, motivating the study of robust metaheuristic optimization for BACAP in port-terminal operations. Although population-based metaheuristics have been widely used for BACAP and related port-scheduling problems, existing studies remain fragmented in their uncertainty repre?sentations, robustness criteria, search mechanisms, and empir?ical evaluation protocols. To the best of our knowledge, this paper provides the first focused review dedicated to robust population-based metaheuristics for BACAP under uncertainty. We first summarize uncertainty sources and information repre?sentations in BACAP, and then organize existing methods from a mechanism-oriented perspective, covering solution representation and decoding, robust evaluation and selection, robustness-guided search dynamics, and feasibility preservation and recovery. We further present a benchmark suite for uncertain BACAP to support controlled empirical comparison and report illustrative baseline results by combining representative metaheuristics with different robustness strategies. Finally, we identify open chal?lenges related to benchmark extension, robustness-aware search design, time-adaptive robustness, and non-stationary uncertainty. --- ### An Investigation of the NeurIPS and ICML 2025 Position Tracks Authors: Fan Yang, Wenkai Li, Jun Liu Published: 2026-07-06 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2608.16894v1 ML venues shape what kinds of research claims become legible to reviewers and what forms of evidence count as rigorous. The NeurIPS and ICML Position Paper Tracks were created for agenda-setting work, making their early composition worth auditing. \textbf{This paper argues that the publicly accessible 2025 reviewed pool is dominated by reformist critique, and that the track should explicitly solicit direction-setting work alongside, not in place of, the reformist critiques it already hosts well.} We audit every accessible submission to the NeurIPS 2025 and ICML 2025 Position Tracks under a pre-specified rubric, and compare the resulting pattern with a reference class of widely recognized agenda-shifting ML papers. Three-quarters of audited submissions critique an existing benchmark, evaluation, or methodology; these papers score highly on our artifact-coupling rubric, but evidentiary depth does not predict reviewer rating. The reference class (AlexNet, the Transformer, Concrete Problems in AI Safety, and others) differs from the accessible reviewed pool in \emph{artifact kind}: agenda-shifting papers typically gave the field something new to build on, test against, or contest, such as a measurement protocol, benchmark proposal, toy implementation, dataset card, audit template, or falsifiable experimental program. We close with four CFP-level interventions aimed at broadening the submission mix without displacing the critiques the track already hosts well. --- ### A Framework for Using and Evaluating LLMs as Surrogate Experts in Security Surveys: Reliability, Bias, and Implications Authors: Despoina Giarimpampa, Roland Meier, Tegawendé F. Bissyandé, Vincent Lenders, Jacques Klein Published: 2026-07-06 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.16893v1 Expert surveys are widely used in security research to study practitioner workows and decision-making, yet recruiting domain experts - especially in Security Operations Centres (SOCs), where analysts face high workload, burnout and confidentiality constraints - is difficult and often results in small samples. Large language models (LLMs) oer an appealing alternative by generating synthetic responses at scale, but little guidance exists on when such surrogate participants are reliable. We present a methodological framework for evaluating LLMs as substitutes or supplements to expert survey respondents. Using responses from SOC professionals, we compare persona-based and aggregate LLM-generated answers across multiple models and prompting settings. We measure stability, inter-model agreement and alignment with human responses. Our results show that although LLMs produce internally consistent answers, they systematically diverge from experts, exhibiting reduced variance, central tendency bias and homogenised opinions. This work contributes methodological evidence and practical guidance to the security research community on the appropriate use and limitations of LLM-generated survey responses. We conclude that LLMs are useful for piloting and hypothesis generation but not for replacing expert elicitation, and we discuss implications for researchers using LLM-augmented surveys. --- ### Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondents Authors: Mantas Lukauskas, Viktorija Šarkauskaitė Published: 2026-07-06 Categories: cs.CY, cs.AI, cs.CL, stat.AP arXiv: https://arxiv.org/abs/2608.14606v1 Large language models (LLMs) are increasingly used as synthetic survey respondents, but existing evaluations ask whether answers look plausible at the individual level. We argue the right question is psychometric: do LLMs preserve the joint distribution, latent structure, reliability, mediation pathways, and demographic effects of real human survey data? We introduce a Lithuanian organisational-psychology dataset (n=263 employees; Dunham Attitudes Toward Change, UWES-17, Koopmans IWPQ; 68 items, 12 subscales) and condition a 37-model lineup spanning OpenAI, Anthropic, Google, and twelve open-weight families on real respondent profiles under a five-level persona-disclosure ladder, presentation and reasoning-effort ablations, counterfactual demographic swaps (gender, role, education), a cross-language check, and a verbatim-recall memorization probe. The resulting Psychometric Similarity Score (PSS) is anchored against five non-LLM statistical baselines and a held-out human-vs-human ceiling, with respondent-bootstrap confidence intervals and an item-permutation null for Tucker's phi. LLMs reproduce the qualitative direction of human psychometric relationships, but a Gaussian-copula baseline beats every LLM on the sample-driven PSS components; the LLM "crowd" is more similar to itself (mean inter-LLM PSS 0.73) than to humans; and memorization does not drive the leaderboard (recall-PSS rank correlation 0.00). Counterfactual swaps reveal education-driven effects (mean |d|=0.56) that dwarf gender (0.12) and role (0.18); Tucker's phi on UWES falls inside the permutation null for 8 of 37 models. Downstream, every LLM shows a strong acquiescence shift (+0.84 SD), synthetic-trained regressors lose predictive validity on held-out humans (mean R^2 -0.18 vs 0.28), and models fabricate indirect effects on 3 of 10 placebo mediation paths. LLM samples are not a drop-in replacement for human survey data. --- ### BCMT: Blockwise Causal Memory Transformer Authors: Rachid Arezki Published: 2026-07-06 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.13578v1 Transformer architectures rely on dense self-attention to model long-range dependencies, but this mechanism exhibits quadratic complexity with respect to sequence length. We introduce BCMT (Blockwise Causal Memory Transformer), an architecture for long-context language modeling that decouples local token interactions from global context propagation. Dense causal self-attention is applied independently within local blocks, while each block produces an adaptive summary aggregated through an exponential causal memory. This memory is subsequently injected back into the token representations, enabling efficient propagation of long-range contextual information without relying on explicit global attention. Unlike standard Transformers and recurrent memory architectures, BCMT maintains neither dense interactions between distant tokens nor learned memory states. Its memory mechanism is fully parallelizable and remains compatible with standard implementations of dense self-attention. Experiments on language modeling with context lengths of up to 1024 tokens show that BCMT achieves validation performance comparable to that of Dense Transformers while significantly improving training throughput and reducing memory consumption. An ablation study further confirms that these improvements arise from the proposed memory mechanism. These results demonstrate that an exponential causal memory constructed from block summaries provides an effective alternative to dense global attention mechanisms for long-context language modeling. --- ### AI Evaluation Should Work With Humans Authors: Jan Kulveit, Gavin Leech, Tomáš Gavenčiak, Raymond Douglas Published: 2026-07-06 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.13577v1 This position paper argues that the dominant paradigm of AI evaluation (which focuses on superhuman autonomous performance and so implicitly targets the goal of replacing humans) is guiding AI development in the wrong direction. Instead, the AI community should pivot to evaluating the performance of human--AI teams. We argue that this collaborative shift will foster AI systems that act as true complements to human capabilities and therefore lead to far better societal outcomes than will the current process. --- ### BCIJelly: An integrated ecosystem for brain-computer interface research Authors: Liyuan Han, Xinrui Yang, Tianyu Zheng, Qizhi Yang, Yitao Qin, Liang Chen, Qinglai Wei, Binjie Hong, Xinhe Zhang, Rui Xiong, Yong Gu, Mu-ming Poo et al. Published: 2026-07-06 Categories: cs.HC, cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2608.13576v1 Brain-computer interface (BCI) research relies on multistage computational pipelines, yet progress remains constrained by fragmented data formats, heterogeneous decoder implementations and hardware-specific deployment toolchains, and researchers lack an integrated workflow. Here, we fill this gap with BCIJelly, a unified computational ecosystem that integrates 18 curated BCI datasets, 15 benchmark decoders and an algorithmic library of 80 reusable modules, an automated architecture search (AAS) procedure, and hardware-aware deployment through the toChip pipeline within a single Python framework. AAS constructs task-specific decoders without manual architecture design. It is further extended into a closed-loop mode guided by a large language model (LLM), which uses task specifications, module descriptions and search history to support multitask and cross-species decoding. The toChip pipeline compiles trained decoders for execution on neuromorphic chips, enabling energy-efficient deployment for BCI systems. An accompanying visualization software provides a graphical interface to the full workflow, making BCIJelly accessible without programming. We validate BCIJelly across five BCI paradigms (motor, visual, speech, emotion and auditory) with recordings from humans, macaques and mice, and single-task, multitask and cross-species decoding settings. BCIJelly establishes a unified and extensible infrastructure that bridges decoder development and hardware-aware deployment for BCI research. --- ### EU-ETS under attack? The impact of carbon price suppression on the decarbonization of the power sector Authors: Javier Gonzalez-Ruiz, Carlos Rodriguez-Pardo, Alice Di Bella, Paolo Mastropietro, Jose Pablo Chavez-Avila, Massimo Tavoni Published: 2026-07-06 Categories: econ.GN, cs.AI, cs.CY, cs.LG, cs.MA, eess.SY arXiv: https://arxiv.org/abs/2608.12363v1 European countries are debating policies to mitigate the increased energy costs caused by renewed geopolitical tensions, while pursuing decarbonization and electrification. A notable example is Italy's 2026 Decreto Bollette package, which proposes to remove the carbon price equivalent from the bids of certain gas-driven power plants to wholesale electricity markets, among other provisions. We use this as a case study to assess the long-term implications of suppressing the carbon price signal in the electricity market for investment, emissions, and consumer costs. We employ a stylized Italian power system using MARLEY, a multi-agent reinforcement learning framework focused on long-term electricity market assessments. In this framework, we test this policy across configurations with varying levels of support for green investment, resource adequacy, and flexibility. Results show that partial suppression of the carbon price signal yields short-term cost reductions but only a minor long-term effect on total system costs, as the deferred emissions are ultimately repaid by consumers. CO$_2$ emissions rise across most configurations since suppressing the price signal erodes incentives for renewable and storage investment. Only the most ambitious configurations for supporting green investment avoid this outcome, but they do so by marginalizing the wholesale price signal itself, thereby requiring a commitment to a hybrid market paradigm that is in contradiction with the rationale of the proposed price intervention. --- ### KumbhDoot: A Scale-Ready, LLM-Bounded Architecture for Mass-Gathering Public-Service Assistants Authors: Saurabh Sakalkar, Abhishek Singh, Ramesh Raskar Published: 2026-07-06 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.07520v1 Mass religious gatherings such as the Kumbh Mela concentrate tens of millions of people into a single region over a few weeks, producing intense, repetitive, multilingual, and safety-critical demand for information. The default response, a conversational assistant that routes every query to a large language model (LLM), is poorly matched to this setting: it is costly at scale, slow on emergency paths, prone to hallucination on facts that can cause physical harm, and unusable when connectivity fails. We describe KumbhDoot, an agentic pilgrim assistant for the Nashik Simhastha Kumbh Mela built on a different principle. It operates on a foundational design principle that prioritizes semantic similarity over starting with an LLM. Generative models are invoked only in instances where similarity-based retrieval is insufficient to produce a correct answer. The system utilizes a "semantic cache": an embedding-indexed store as a single retrieval primitive, which handles intent routing, answer caching, offline lookups, and multi-agent retrieval. A custom three-tier agent architecture operates directly on this store, ensuring decision paths remain inspectable and avoiding the use of generic multi-agent frameworks that would trigger implicit per-step LLM calls. We present the architecture, an analytical cost model for its per-query economics, and an honest account of where similarity is sufficient and where generative reasoning remains necessary. We argue that for bounded, high-stakes, low-connectivity public-service domains, a similarity-first and LLM-bounded design is not merely cheaper but architecturally more appropriate than an LLM-default one. --- ### Forgetting Is Not a Fix: Path Dependence in Sequential Engram Editing Authors: Ferdinand M. Schessl Published: 2026-07-06 Categories: q-bio.NC, cs.LG arXiv: https://arxiv.org/abs/2607.24805v1 AI Engram (Kwon et al., 2026) formalizes the four engram criteria of neuroscience as a constrained inverse problem in weight space and solves it closed-form: concept-specific memory traces become linear objects that can be extracted once and combined arithmetically. Appendix F states the Compositional Memory States Hypothesis: edited models live on "a commutative manifold where the integration of A and B reaches a consistent equilibrium regardless of the learning sequence." The evidence base is single and paired edits -- in materials terms, single-cycle tests, in which fatigue accumulation is structurally invisible. Whether the hypothesis holds under sequential load is exactly the "temporal dynamics" question the paper defers to future work. We run that test on the authors' own reference implementation, at their reported best edit strength (TOFU alpha=0.6, a choice favoring the linearity hypothesis), with pre-registered predictions, across three model charges (two vendors, two architecture families). Four findings replicate across all three: (1) zero-shot composition and sequential re-calibrated editing diverge by 61-71% of the edit magnitude; (2) cut order is not interchangeable, and the effect scales with concept overlap -- in one charge the order of cutting two Paris landmarks decides whether an uninvolved third concept survives; (3) the survivors' layer-input covariances -- the method's own sufficient statistics, read as strain gauges -- drift monotonically with every further cut, in every surviving concept, in every charge; (4) erased knowledge partially returns under subsequent unrelated cuts. Appendix F's commutative-manifold hypothesis is thereby falsified for sequential editing; the single-edit results of the original paper are untouched. For unlearning-as-compliance: erasure certified today does not certify the artifact after its next edit. --- ### Bumblebee: Interleaved Mixed-Layer Building Blocks for Large-Scale Recommendation Systems Authors: David Bauer, Cancan Zhang, Wenshun Liu, Xiaoyi Zhang, Weijia Liu, Wanli Ma, Yue Weng, Wei Li, Rui Li, Yiyang Zhao, Tianqi Lu, Jing Qian et al. Published: 2026-07-06 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2607.24804v3 Recommendation systems have undergone significant transformations in the past years. The transition from traditional feature interaction modules to generative next-action prediction has pushed the boundaries of personalized content. Developments have largely evolved along two separate tracks. Sequence modeling approaches on the one hand and feature interaction methods on the other. In this paper, we introduce Bumblebee, a recommendation architecture that addresses the lack of interaction between the two directions through an interleaved, stackable block design. Each block implements a micro-pipeline of layers combining sequence personalization, attention-based encoding, and feature crossing into a self-contained unit. Every block produces a joint representation of both feature modalities which is consumed by the next block in the sequence. This mechanism encourages early and repeated mixture of modalities and enriches downstream features with additional contextual information. Residual connections between blocks create cross-modal information pathways and yield additional predictive performance without adding additional parameters. Blocks can be specialized by selectively dropping components, enabling flexible trade-offs between quality and throughput. We evaluate our approach on large-scale industrial data and show consistent improvements over comparable baseline models across several classification and regression tasks. Furthermore, we conduct ablation studies to confirm that the interleaved composition itself is the primary driver of these improvements. Our results suggest that interleaving heterogeneous functional units, rather than composing deep stacks, is a promising paradigm for future-generation recommendation architectures. --- ### Bumblebee: Interleaved Mixed-Layer Building Blocks for Large-Scale Recommendation Systems Authors: David Bauer, Cancan Zhang, Wenshun Liu, Xiaoyi Zhang, Weijia Liu, Wanli Ma, Yue Weng, Wei Li, Rui Li, Jing Qian, Huayu Li, Xiaoyi Liu et al. Published: 2026-07-06 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2607.24804v2 Recommendation systems have undergone significant transformations in the past years. The transition from traditional feature interaction modules to generative next-action prediction has pushed the boundaries of personalized content. Developments have largely evolved along two separate tracks. Sequence modeling approaches on the one hand and feature interaction methods on the other. In this paper, we introduce Bumblebee, a recommendation architecture that addresses the lack of interaction between the two directions through an interleaved, stackable block design. Each block implements a micro-pipeline of layers combining sequence personalization, attention-based encoding, and feature crossing into a self-contained unit. Every block produces a joint representation of both feature modalities which is consumed by the next block in the sequence. This mechanism encourages early and repeated mixture of modalities and enriches downstream features with additional contextual information. Residual connections between blocks create cross-modal information pathways and yield additional predictive performance without adding additional parameters. Blocks can be specialized by selectively dropping components, enabling flexible trade-offs between quality and throughput. We evaluate our approach on large-scale industrial data and show consistent improvements over comparable baseline models across several classification and regression tasks. Furthermore, we conduct ablation studies to confirm that the interleaved composition itself is the primary driver of these improvements. Our results suggest that interleaving heterogeneous functional units, rather than composing deep stacks, is a promising paradigm for future-generation recommendation architectures. --- ### SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking Authors: Mohotarema Rashid, Nansu Baniya, Anirban Saha Anik, Xiaoying Song, Lingzi Hong Published: 2026-07-06 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2607.24803v1 Scientific claims often spread on social media faster than they can be verified, while posts rarely link to the original scholarly sources. To tackle this problem this paper presents system called SciClaimSeekers, a retrieval and reranking framework by combining BM25 and zero-shot multilingual E5 retrieval with Reciprocal Rank Fusion (k=60), followed by Qwen2.5-14B-Instruct pointwise reranking. The pipeline reaches 64.36% MRR@5 on the English development set a 13.67-point jump over BM25 and 10.17 points over the unranked hybrid and 64.39% on the official test set, in the CLEF-2026 CheckThat! Task 1 evaluation. Our experiment suggests that large pre-trained models, when combined into a careful pipeline, can be competitive with fine-tuned approaches on this task. --- ### SourceMinds at CheckThat! 2026: NLI-Grounded Citation Auditing in a Multi-Agent Pipeline for Full Fact-Checking Article Generation Authors: Farhan Sharukh Hasan, Anirban Saha Anik, Eric Liu, Xiaoying Song, Mohotarema Rashid, Lingzi Hong Published: 2026-07-06 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2607.24802v2 This paper presents our system for Task 3 of the CLEF 2026 CheckThat! Lab, which focuses on generating full fact-checking articles from claims, veracity labels, and evidence documents. We propose a multi-agent pipeline that combines evidence retrieval, structured fact planning, article generation, gated self-critique, and NLI-based citation auditing. The system retrieves claim-relevant evidence using dense retrieval, reranking, and source-balanced selection, then generates a citation-supported article from a structured plan. A gated self-critique stage revises weakly grounded drafts, while the NLI citation auditor repairs missing citations and removes unsupported or redundant ones. The approach highlights the importance of combining evidence selection, structured generation, and post-generation citation validation for source-grounded fact-checking article generation. --- ### Influence of Prompt Engineering on Small Language Models for Guarded Query Routing Authors: Richard Šléher, William Brach, Kristián Košťál, Lukas Galke Poech Published: 2026-07-06 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2607.24801v1 We study the problem of guarded query routing, where we assume that a user query first meets a router that either determines the ideal endpoint for in-distribution queries or rejects out-of-distribution queries that are potentially unsafe or out of the system's scope. We investigate whether compact open-weight Small Language Models (SLMs) can jointly handle both tasks under latency constraints. We evaluate 22 models on GQR-Bench and score them with the harmonic mean of in-distribution and out-of-distribution accuracy. We find that mid-scale SLMs come close to frontier model routing quality at much lower latency. Still, many compact models fail because they do not reliably follow the required output format. However, our results show that prompt optimization techniques enable SLMs to handle such cases gracefully, without changing the models' weights. Moreover, few-shot prompt optimization raises Mistral 7B from 81.79 to 90.87 GQR-Score and lifts Qwen3.5 9B to 95.74, the best optimized score in our study and within 0.3 points of the strongest unoptimized larger model: Gemma 3 27B at 96.01. The bare DSPy signature, without in-context exemplars, is the most effective strategy for Granite 4 Tiny, raising its score from 54.29 to 83.05. These results show that prompt optimization is a useful first step for guarded query routing, while weaker models may still need weight-level adaptation or schema-aware training --- ### When Thinking Before Retrieval Hurts: TraceBound Diagnostics for Adaptive Knowledge-Graph Retrieval Authors: Partha Sarathi Purkayastha Published: 2026-07-06 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.24800v1 Adaptive retrieval promises to make knowledge-graph question answering more robust by letting a controller search, inspect neighborhoods, revise actions, and stop when evidence is sufficient. We study this premise by introducing TraceBound, a lightweight profile- and trace-conditioned diagnostic protocol for an ARK-style retriever on text-rich knowledge graphs. TraceBound exposes a compact query profile before retrieval, issues short trace hints after observable failure symptoms, and logs trajectory counters, while keeping graph data, tools, gold labels, and ranking metrics fixed. Across STaRK validation and held-out subsets, the added conditioning improves inspectability but consistently reduces retrieval quality under open-weight controllers. Paired trajectory analysis localizes the degradation to repeated calls, zero-result calls, and misallocated exploration budget, while stricter interaction budgets shorten trajectories without repairing the policy. The result diagnoses the common failure mode in that "thinking before retrieval'' must be evaluated as a control problem over action selection, not as a prompt-format change. --- ### Multimodal Hybrid Retrieval-Augmented Generation for Scientific Document Understanding using Open-Source SLMs Authors: Alexandru-Andrei Saucă, Ana-Luiza Rusnac Published: 2026-07-06 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2607.24799v1 Large Language Models tend to hallucinate when answering domain-specific ques tions from scientific documents without prior fine-tuning. Currently, methods such as Retrieval-Augmented Generation partially solve this problem but face different challenges: limited context knowledge, difference between sparse and dense retrieval, and retrieval noise. This paper presents an Advanced Multimodal Retrieval-Augmented Generation system that aims to solve those challenges and im prove the accuracy of information extraction. The proposed architecture introduces a multimodal ingestion pipeline that leverages an open-source Vision-Language Model (Qwen2-VL-2B-Instruct) to generate textual summaries of tables and fig ures. The retrieval phase integrates HNSW-based semantic search with GIN-based lexical search, unified through Reciprocal Rank Fusion and refined using Cross Encoder reranking to minimize retrieval noise. To ensure conversational coherence across multi-turn interactions, a Query Condenser module is employed. Evaluation is conducted by independently assessing the ingestion, retrieval and generation stages using the MMLongBench benchmark, a BeIR-format synthetic dataset and the DeepEval framework. Moreover, results demonstrate a 157% improvement in retrieval quality over a Naive-RAG baseline, with only 50 ms additional la tency, while Qwen2-VL-2B-Instruct achieved results comparable to cloud-based models in BERTScore. These findings validate that open-source optimized SLMs, paired with advanced retrieval strategies, can provide competitive performance for document understanding without relying on cloud-based models. --- ### AIR-BENCH Live: An Evolving Safety Benchmark for Foundation Models Authors: Rohan Naphade, Minzhou Pan, Bo Li Published: 2026-07-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22671v1 Foundation-model safety benchmarks capture the AI risks of their time of publication: as models improve and governments pass new AI-safety legislation, their risk taxonomies become incomprehensive and their attack prompts become ineffective. We present AIR-BENCH Live, a self-evolving successor to AIR-BENCH 2024. An automated update pipeline monitors government regulation and classifies new policies against the current four-tier risk taxonomy, either matching them to existing categories or proposing new granular categories. Then, a multi-agent, persona-driven prompt generation algorithm generates realistic, multilingual prompts with minimal human review, leaving room for improvement with modern jail breaking techniques. This algorithm is used to overhaul legacy prompts and generate prompts for new categories. In our current version, the pipeline has expanded the benchmark from 314 to 335 granular risks, with the 21 new categories drawing from 31 truly novel policy clauses across seven jurisdictions. Evaluating 14 recent models, we find a wide safety spread (from 0.17 to 0.89 among the models judged on their own behavior), that the modernized prompts are on average 0.06 points harder than the 2024 set, with the largest drops concentrated among the most compliant models, and that most models are modestly less safe on non-English prompts. By continuously absorbing new regulation and regenerating prompts, AIR-BENCH Live is designed to evolve alongside a fast-moving field. --- ### The Active Ingredient in Muon's Grokking Authors: Yufeng Wang Published: 2026-07-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.20512v1 The Muon optimizer reaches the grokking threshold on modular arithmetic faster than AdamW. Prior work attributes this to "spectral-norm constraints plus orthogonalized momentum" but does not isolate which mechanism matters. To better understand Moun's behavior, we run multi-seed and multi-learning-rate sweeps to decompose and stress-test the effect. First, an ablation shows the speedup comes from orthogonalization (the Newton-Schulz iteration): orthogonalize-only matches full Muon, whereas spectral-only is no faster than AdamW and is unreliable, and this verdict holds across learning rates. Second, a mechanistic analysis finds that orthogonalizing optimizers reach generalization at roughly 3x lower spectral norm and, controlling for how much the embedding actually moves, settle into a lower-norm solution rather than simply perturbing the embedding less. Third, reducing the Newton-Schulz iteration count from five to one accelerates reaching the threshold but makes the grokked solution fragile, prone to transient collapse, with fragility that grows with learning rate; a single iteration is fast and stable only at small learning rate, while the canonical five iterations are the learning-rate-robust choice. We also show spectral scaling can be dropped at no measured cost. A methodological thread runs throughout: under a stability-aware metric, "faster" claims about grokking optimizers can invert, so we report both first-crossing and sustained-grok times. To support reproducibility, we release our full training and analysis code at https://github.com/louiswang524/muon-grokking-frontier --- ### When Does Consensus Beat Voting? A Critical Analysis of Statistical Label Fusion in Medical Image Segmentation Authors: Renjie He Published: 2026-07-06 Categories: cs.LG, cs.CV, physics.med-ph arXiv: https://arxiv.org/abs/2607.19402v1 This paper provides a rigorous, self-contained investigation of consensus segmentation. We derive the mathematical foundations from first principles -- the generative model, EM algorithm, Van Leemput's marginalization analysis, identifiability conditions, Spatial STAPLE, and deep variational formulations -- and validate each theoretical prediction through controlled experiments. The central finding is sobering: under common conditions, STAPLE reduces to thresholded majority voting, suffers 95% EM suboptimality, and collapses under class imbalance. These are not edge cases but typical scenarios in medical imaging. Majority voting -- simple, non-parametric, and robust -- is a surprisingly strong baseline that the field has perhaps too hastily dismissed in favor of more "sophisticated" methods. At the same time, the deep consensus model demonstrates that the consensus problem is not inherently difficult -- it becomes tractable when the image is used alongside the labels. And conformal prediction shows that formal uncertainty guarantees are achievable and practical. We hope this work encourages practitioners to critically evaluate their consensus methods rather than applying STAPLE by default, and provides the mathematical and empirical foundation for more principled approaches. --- ### Predictive single cell foundation model for gene regulation and aging with privacy-preserving tabular learning Authors: Jiayuan Ding, Jianhui Lin, Ziyang Miao, Nils Mechtel, Shiyu Jiang, Yixin Wang, Zhaoyu Fang, Jorge D. Martin-Rufino, Chen Weng, Reuben Saunders, Weize Xu, Jonathan S. Weissman et al. Published: 2026-07-06 Categories: cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2607.19400v1 Pre-trained foundation models (FMs) have begun transforming single-cell genomics, but scaling them raises privacy concerns. Moreover, unlike text data, single-cell data is unordered and exhibits a unique tabular structure that current single-cell FMs overlook. We introduce Tabula, a privacy-preserving FM designed with federated learning (FL) that explicitly models the tabular structure of single-cell data. To deploy Tabula, we further developed Chiron, a decentralized AI agent-enabled platform for collaborative training across institutions without sharing raw data. Beyond strong performance across downstream benchmarks, Tabula reveals combinatorial regulatory logic across diverse biological systems, including hematopoiesis, pancreatic endogenesis, neurogenesis, and cardiogenesis. Using a new scRNA-seq dataset of paired young and aged human fibroblasts, Tabula nominates rejuvenation factors through age- and identity score-guided in silico prioritization, outperforming conventional approaches. Thus, Tabula represents an important advance in single-cell foundation modeling by integrating tabular learning with FL, paving the way toward privacy-preserving virtual cells for human health. --- ### Leveraging Offline Supervision for Efficient and Generalizable Reinforcement Learning in Large-Scale Vision-Language-Action Models Authors: Dmitriy Poyarkov, Aleksei Staroverov, Aleksandr I. Panov Published: 2026-07-06 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.19399v1 It is commonly observed that online reinforcement learning (RL) produces better-performing strategies than offline methods across a broad range of performance measures. In particular, RL-trained policies exhibit stronger out-of-distribution (OOD) behavior, where models trained only with imitation learning approaches often struggle. A recent study introduced an OOD-focused benchmark and reported that RL-trained vision-language-action (VLA) policies achieve noticeably better OOD performance and slightly better in-distribution (IND) performance than their counterparts trained with supervised fine-tuning (SFT). In this work, we investigate whether hybrid offline-online training can combine the advantages of both approaches. Specifically, we study RL methods regularized by offline supervision via either offline data or an offline-trained reference policy. We evaluate these approaches on the OOD benchmark and compare them with both offline-only training and standard RL. Our results show that although offline training achieves limited OOD performance by itself, incorporating offline supervision into RL preserves strong OOD capability while substantially improving training efficiency. In particular, the guided methods reach performance close to that of standard RL while requiring roughly half of the training budget. Rather than producing a trade-off between speed and OOD performance, the hybrid approach retains strong OOD capability while achieving this efficiency gain. Project page: https://alstar8.github.io/offline-supervision-vla-rl --- ### QDEvo: A Multi-Objective Quality-Diversity Framework for Automated Heuristic Design Authors: Nam Do Khanh, Nhat Nguyen Tran Minh, Dat Pham Vu Tuan, Long Doan, Binh Huynh Thi Thanh Published: 2026-07-06 Categories: cs.NE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.11916v1 The integration of Large Language Models (LLMs) with evolutionary computation has emerged as a powerful paradigm for automated heuristic design in combinatorial optimization. However, existing approaches suffer from mode collapse, converging to homogeneous populations that lack semantic diversity and fail to explore the full algorithmic space. We propose Quality-Diversity Evolution (QDEvo), a multi-objective framework that integrates Quality-Diversity optimization with LLM-driven heuristic search, maintaining an unbounded archive of semantically diverse algorithms using pre-trained code embeddings and incorporating hierarchical self-reflection to guide the evolutionary process. Extensive experiments across standard benchmarks and real-world industrial applications demonstrate that QDEvo significantly outperforms state-of-the-art methods in both Hypervolume and Inverted Generational Distance metrics. Our framework enables the discovery of heuristics that are simultaneously high-performing, computationally efficient, and semantically diverse, providing practitioners with a rich portfolio of solutions for complex optimization problems. --- ### BatteryLake: Agentic, Physics-Grounded Curation of Heterogeneous Battery Aging Data and Benchmarking Authors: Tianwen Zhu, Hao Wang, Yonggang Wen Published: 2026-07-06 Categories: cs.AI, cs.DB arXiv: https://arxiv.org/abs/2607.09762v1 Public battery aging datasets are a critical asset for advanced health management, but their practical use is often limited by inconsistent formats, unclear schemas, and metadata scattered across repositories and publications. Current curation remains largely manual and hard to reproduce, while general-purpose data integration tools miss the domain-specific semantics of electrochemical time-series data. We present BatteryLake, a governed data lakehouse that turns raw public battery data into benchmark-ready assets through an agentic, physics-grounded curation framework, with three contributions. First, LLM agents extract metadata and synthesize dataset-specific converters, grounding every output in verbatim evidence and abstaining when none supports a value. Second, a human-in-the-loop mechanism frames verification as selective prediction and gates admitted data through 26 schema, statistical, and physical-plausibility rules. Third, we release an open benchmark of 41 datasets from over 25 institutions, with standardized SOH and RUL tasks, three split protocols, and eight baseline model families. The platform, benchmark, and curation protocol are publicly available at https://tianwen1209.github.io/batterylake/. --- ### Physics-Informed Structure Anchoring With Capture-Aware Prototype Calibration for Cross-Environment RF Fingerprinting Authors: Fengchong Yao, Jianbing Li, Qing Liu, Qikun Liu, Kefeng Song, Haitao Li, Song Wang Published: 2026-07-06 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2607.09760v2 Radio frequency fingerprint identification (RFFI) exploits transmitter-specific hardware imperfections as physicallayer identity cues for Internet of Things (IoT) devices, but deep models often degrade across acquisition environments. In multi-antenna reception, antenna topology and frequencyoffset dynamics structure receiver observations, while capturedependent variation distorts target embeddings and misaligns source-trained decision boundaries. This article proposes physicsinformed structure anchoring with capture-aware prototype calibration (PISA-CAPC) to address both representation and decision mismatches. The two stages separate source representation construction from target decision correction. During source training, PISA organizes antenna tokens through a topology-guided graph, conditions propagation on CFO-derived acquisition dynamics, and applies bounded contextual residual suppression to preserve identity evidence. At deployment, unlabeled capture-aware prototype calibration (U-CAPC) estimates capture-local prototypes and recalibrates target decision scores while keeping the representation and source classifier fixed. Thus, calibration uses neither target labels nor target-domain backbone updates. On a measured WiFi benchmark with four receive antennas and ten transmitters, PISA-CAPC achieves a mean target-domain Macro-F1 of 0.9257 under a balanced transductive setting. Component ablations support complementary roles for topology-guided anchoring, CFO-conditioned modulation, reliability-aware token aggregation, contextual suppression, and capture-aware calibration. These results indicate that physically motivated representation learning can be combined with labelfree decision calibration to improve cross-environment RFFI under the evaluated protocol without changing the deployed backbone. --- ### ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams Authors: Xiaokang Ma, Yifan Sun, Zhihong Jin, Jie Gu, Yudong Luo, Shenyi Shao, Chu Tang, Jingmin Chen, Li Pu Published: 2026-07-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.09759v2 Building assistants that can continually watch the world, remember what they see, and reason over their accumulated experience is a long-standing goal, and recently multimodal agents equipped with long-term memory over video streams have attracted increasing interest. Unfortunately, existing systems either keep their memory inside the model context or in a flat feature store, and organize it around frames rather than around the persistent entities a stream is really about, which confines them to bounded videos and weakens their ability to track who and what reappears over time. In this paper, we propose ReflectWorld-MM, an entity-oriented multimodal memory system for open-ended video streams. It consists of three parts. The first is a perception front-end that turns an audiovisual stream into entity-resolved observations under a bounded short-term memory. The second is a hierarchical long-term memory, grounded in human memory theory, that couples a multi-scale episodic memory, an evolving entity-centric semantic memory, and a procedural memory. The third is a complete realization, built for real-world operation, that ingests arbitrary streams and plugs into off-the-shelf assistants. Across six long-video and lifelong-memory benchmarks, ReflectWorld-MM achieves the best accuracy on all six, outperforming strong memory agents and a frontier model. --- ### LLM-Driven Evolutionary Generation of Multi-Objective Bayesian Optimization Algorithms Authors: Georgios Laskaris, Reuben Brasher, Niki van Stein, Elena Raponi, Thomas Bäck, Florian Neukart Published: 2026-07-06 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2607.08791v1 Designing effective multi-objective Bayesian optimization (MOBO) algorithms requires balancing many interdependent design choices whose optimal configuration is problem-dependent and typically demands deep expertise. We extend the LLaMEA framework to MOBO, using large language models as mutation and crossover operators within evolutionary strategies to generate complete algorithm implementations, with SMAC hyperparameter optimization integrated into the evolutionary loop. Across nine evolutionary runs we generated approximately 900 algorithms and benchmarked them on twelve synthetic problems (ZDT, DTLZ, WFG) and three real-world engineering problems (RE), using a BoFire qParEGO implementation as a state-of-the-art Bayesian-optimization baseline. On the synthetic suite the strongest generated algorithm attains the highest mean normalized hypervolume (0.971, vs. 0.869 for qParEGO) while requiring roughly 60x less wall-clock time; a Friedman test with post-hoc analysis places the two in a single top-performing group, and per-problem tests find the generated algorithm significantly better than qParEGO on 7 of the 12 problems and never worse, matching state-of-the-art accuracy at an order-of-magnitude lower cost. On the three unseen real-world engineering problems a generated algorithm attains the best mean normalized hypervolume (0.985, vs. 0.971 for qParEGO)--significantly better than qParEGO on two of the three problems--at roughly 3.4x lower wall-clock cost, confirming that the gains transfer beyond the synthetic regime. LLM-driven evolutionary search can thus discover algorithm designs that achieve Pareto-efficient trade-offs difficult to reach through manual design. --- ### Collective Intelligence with Foundation Models Authors: J. de Curtò, I. de Zarzà Published: 2026-07-06 Categories: cs.MA, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.07729v1 As foundation models grow in scale and diversity, coordinating multiple models into cooperative reasoning systems offers a path toward safer, more reliable AI. This chapter presents a multi-agent framework where solver models generate independent drafts, each undergoes structured critique and revision by a critic agent, and an aggregator agent synthesizes a final consensus solution. A scoring module provides semantic, numerical, and procedural evaluation across all agents. Through ablation studies on a benchmark spanning calculus, physics, chemistry, biology, economics, optimization, statistics, and mathematics, we isolate the contributions of framework architecture versus model diversity. We compare four configurations: (1) Individual Baseline, (2) Homogeneous Framework using one shared model, (3) Redundant Homogeneous Solvers using multiple instances of the same model, and (4) Heterogeneous Framework with diverse specialized models. Results show that while framework structure and redundant sampling yield modest gains, model heterogeneity is the critical factor driving substantial performance improvements. The heterogeneous configuration achieves superior step-wise accuracy (0.64 vs. 0.54 for individual models; 2.3x improvement over homogeneous configurations) with reduced variance across categories and difficulty levels. Step-wise reasoning quality (correctness of intermediate steps, not just final answers) improves dramatically only with model diversity, showing that heterogeneous agents provide complementary error detection and reasoning refinement essential for explainability and auditability. We discuss architectural principles, evaluation methodology, and implications for Global Applied AI, showing how heterogeneous multi-agent coordination supports transparent, auditable, high-confidence decision-making across scientific and industrial domains. --- ### SPL: Orchestrating Workflows with Declarative Deterministic-Probabilistic Composition Authors: Wen G. Gong Published: 2026-07-06 Categories: cs.PL, cs.CL arXiv: https://arxiv.org/abs/2607.07727v1 We present SPL (Structured Prompt Language), a declarative language that composes deterministic and probabilistic computation modes in a single specification. While existing frameworks separate these -- orchestration systems (AutoGen, CrewAI, LangGraph) for LLM calls, symbolic tools (SymPy, SageMath, Lean) for computation -- SPL unifies them. It provides GENERATE/EVALUATE for probabilistic computation and SOLVE/ASSERT for deterministic computation, sharing syntax, variable bindings, and runtime routing. A .spl specification runs unchanged across local nodes (Ollama), cloud APIs (OpenRouter, Anthropic), and distributed grids (Momagrid), with model and verifier selection deferred to invocation time. We validate SPL through an extensive 78-recipe cookbook and a controlled 1,200-run experiment (10 models x 20 problems x 2 arms x 3 repetitions; the 20 problems span 6 difficulty tiers). The solver arm achieves 82-93% machine-verified correctness (sonnet-4-6: 85%, gemma4:e2b: 93%) while the LLM-only arm measures output production without mathematical verification, making the comparison one of verified correctness against unverified fluency. A backend difficulty gradient emerges (SymPy 78%, Sage 54%), and the dominant failure mode is solver_error (kernel-rejected expressions), not format non-compliance. --- ### Non-contact, Real-time, Heart-rate Measurement using Image Processing with Commodity Cameras and AI Agents Authors: Kelly Li, Fulu Li Published: 2026-07-06 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.06598v1 Heart rate measurement is one of the key requirements for real-time health monitoring, in particular for health caring of elderly people. Traditional heart rate measurement relies on contact sensing mechanisms such as some heart rate measurement devices at medical hospitals or some wearable devices with embedded sensors such as Apple Watch, etc. In this paper, we develop a system for non-contact, real-time, heart rate measurement using image processing with commodity cameras such as an embedded camera on a laptop, where we use an innovative algorithm to capture the relevant signals for the computation of heart rate in a time series in real life environments. The presented heart rate computation (HRC) process is composed with four major steps: (a) identify frames per second of the camera in use, i.e., 30 frames per second for a given camera, (b) face detection (FD) with shape predictor of 68 face landmarks using deep learning (DL) method, (c) time sliding window (TSW) algorithm to de-noise the signal by smoothing out the noise, and (d) compute heart rate based on identified signal periodicity. We test and analyze the developed prototypes against heart rate results by Apple Watch and check the difference range in multiple rounds and compute the mean of the difference for the measurement values of the heart rate of the same person at the same time. We will do further tuning and optimization of the present methods and deploy the system as a personal AI agent (6) for health monitoring as our future directions. --- ### Reconfigurable Radiology Labels Without Relabeling Authors: Jean-Benoit Delbrouck, Dave Van Veen, Akash Pattnaik, Kalina Slavkova, Javid Abderezaei, Harris Bergman, Khan Siddiqui Published: 2026-07-06 Categories: eess.IV, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2607.06597v2 Public chest-radiograph (CXR) datasets are typically released with small, fixed label schemas such as CheXpert-14. However, the underlying free-text reports describe far more findings -- and which findings matter depends on the task, site, and reader. We release a pipeline that converts free-text reports into multi-label matrices and then reconfigures the label schema through dictionary edits rather than new inference passes, i.e., without relabeling the corpus. After this one-time pass, reconfiguring MIMIC-CXR (223K reports) from cached annotations takes 196 seconds with no API cost, compared to \$6.6K for an equivalent relabeling pass with Claude Opus 4.7. Using a 58-label taxonomy, we show that 43\% of CXR studies contain at least one finding outside CheXpert-14. Image probes trained on these labels match CheXpert-14 probes on shared targets while also reaching 0.78 AUROC on expert-reviewed long-tail labels that CheXpert-14 cannot represent. These results suggest a different unit of work for radiology labeling: once reports are structured, the label schema becomes a configuration to edit, not a corpus to relabel. --- ### Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages Authors: Lucas Pinto Published: 2026-07-06 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.06596v3 Trusted monitoring is a central defense in AI control: a cheaper trusted model scores an untrusted model's actions for sabotage, and the most suspicious are audited or deferred. Such monitors are evaluated against one or two untrusted models, and the accuracy is reported as a property of the monitor. We ask whether it is partly a property of the pairing. We make the untrusted policy family the controlled axis: we fit a monitor on family A's transcripts, apply it to family B, and decompose the cross-family AUROC into how obvious each family's sabotage is, how capable each monitor is, and the residual own-family advantage after both are removed: the interaction. On code-backdoor transcripts the interaction is positive and survives the dominant confounds: +0.172 (95% CI (+0.158, +0.185)) on four open-weight families on a strict leak-free basis, holding across an eight-family matrix spanning four frontier vendors, blatancy-matched controls, a trained transcript-reading monitor up to 34B parameters, and a second code benchmark. The gap is geometric: each lineage's sabotage occupies a different scoring direction, and rotating the monitor's scoring direction toward the target lineage recovers most of the lost detection while a matched random rotation recovers nothing. At a 1% audit budget under defer-to-trusted, an off-lineage monitor catches 19% of attack attempts where an in-lineage monitor catches 41% at the same audit cost, a +21.7-point gap. Control evaluations should report cross-family transfer matrices: a single-pairing accuracy overstates the safety a monitor delivers against a lineage it was not calibrated on. We give a four-step protocol that acts on the gap, with each step a measured result. --- ### Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages Authors: Lucas Pinto Published: 2026-07-06 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.06596v2 Trusted monitoring is a central defense in AI control: a cheaper trusted model scores an untrusted model's actions for sabotage, and the most suspicious are audited or deferred. Such monitors are evaluated against one or two untrusted models, and the accuracy is reported as a property of the monitor. We ask whether it is partly a property of the pairing. We make the untrusted policy family the controlled axis: we fit a monitor on family A's transcripts, apply it to family B, and decompose the cross-family AUROC into how obvious each family's sabotage is, how capable each monitor is, and the residual own-family advantage after both are removed: the interaction. On code-backdoor transcripts the interaction is positive and survives the dominant confounds: +0.172 (95% CI (+0.158, +0.185)) on four open-weight families on a strict leak-free basis, holding across an eight-family matrix spanning four frontier vendors, blatancy-matched controls, a trained transcript-reading monitor up to 34B parameters, and a second code benchmark. The gap is geometric: each lineage's sabotage occupies a different scoring direction, and rotating the monitor's scoring direction toward the target lineage recovers most of the lost detection while a matched random rotation recovers nothing. At a 1% audit budget under defer-to-trusted, an off-lineage monitor catches 19% of attack attempts where an in-lineage monitor catches 41% at the same audit cost, a +21.7-point gap. Control evaluations should report cross-family transfer matrices: a single-pairing accuracy overstates the safety a monitor delivers against a lineage it was not calibrated on. We give a four-step protocol that acts on the gap, with each step a measured result. --- ### When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Authors: George Torres, Sharad Shrestha, Satyajayant Misra Published: 2026-07-06 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.06595v1 Personal AI agents powered by large language models can reason and act using available tools to access emails, manage calendars, and push code to remote repositories, all with minimal oversight. When augmented with long-term memory, an agent can recall specific details relevant to the current task, reducing the need for large context windows. Currently, long-term memory agents tend to fall into two distinct domains: conversational and action-planning agents. Personal assistant agents sit at the convergence of these two domains and handle sensitive information while interacting with untrusted information sources, creating previously unaccounted security vulnerabilities. In this work, we introduce the novel attack vector, GhostWriter, which exploits current memory subsystems in tool-using personal agents to poison their memory store. GhostWriter operates in two phases: injection, where an adversary sends a hidden attack payload to the target agent; and activation, in which the poisoned memory is retrieved. We show that GhostWriter achieves near-universal injection rates of approximately 98% and a high average activation rate of approximately 60% against state-of-the-art agents. This attack is possible due to the lack of security-focused memory governance. In response, we propose Agentic Memory Sentry (AM-Sentry), which leverages two mitigation techniques: a memory-saving policy and a memory-retrieval screen. Our experiments show that AM-Sentry dramatically reduces GhostWriter's success rate while preserving agent utility. --- ### LipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detection Authors: Vincent Lébé, Yannick Prudent, Corentin Friedrich, Thomas Massena, Ronan Sicre, Franck Mamalet Published: 2026-07-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.06592v1 Object detectors have many applications in safety-critical systems, but they are known to be sensitive to worst-case perturbations such as adversarial attacks, which limits their applicability in real-world scenarios. Compared with classification, adversarial robustness for object detection has received less attention, and existing methods are often tied to adversarial training, whose performance may not transfer across attacks, perturbation budgets, or architectures. In this work, we introduce Lipschitz-constrained variants of object detection architectures as robust-by-design alternatives to standard detectors. We validate this approach with LipSSD, a Lipschitz-constrained Single Shot MultiBox Detector (SSD), and provide a comprehensive study of its adversarial robustness using multiple white-box adversarial attacks and datasets. We first analyze the accuracyrobustness trade-off induced by Lipschitz constraints and show that it can be controlled through a single training hyperparameter. We then demonstrate that Lipschitzconstrained detectors are complementary to adversarial training: under the same training setup on the Pascal VOC dataset, adversarially trained LipSSD improves mAP@50 on unseen attacks by up to 15 points over classical adversarially trained SSD. Finally, we use more specific safety-critical datasets such as LARD and KITTI, and show that Lipschitz-constrained detectors can improve robustness while largely preserving clean performance. These results suggest that architectural Lipschitz control is a practical and attack-agnostic direction for improving the robustness of object detectors. --- ### AI for Cultural Heritage Textiles: Fine-Tuned Latent Diffusion for Novel Ulos Motif Synthesis Authors: Humasak Tommy Argo Simanjuntak, Jesika Purba, Sitogab Girsang, Widya Manurung, Samuel Situmeang, Arlinta Barus, Daniel Oranova Siahaan Published: 2026-07-06 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.06590v1 Preserving and revitalising traditional textiles such as Ulos, a cultural heritage of the Batak ethnic group in North Sumatra, Indonesia, requires balancing fidelity to tradition with innovative approaches that meet contemporary design demands. Traditional Ulos weaving faces two key limitations: a narrow range of motifs and a time-intensive design process. This study presents a generative AI framework that fine-tunes two pretrained latent diffusion models: Protogen v3.4 and Stable Diffusion v1.4, on a curated, annotated dataset of high-resolution Ulos motifs to generate culturally consistent yet novel designs. Model performance is evaluated quantitatively using Frechet Inception Distance (FID), Inception Score (IS), and qualitatively through assessments by traditional weavers and members of the public. Protogen v3.4 consistently outperforms Stable Diffusion v1.4, achieving substantially lower FID (~10.5x) and higher IS (2.0x), indicating superior visual fidelity, diversity, and closer alignment with the real Ulos motif distribution. We further examine the effects of strength and guidance scale on generation quality across both models. Lower strength values consistently yield higher fidelity (lower FID), while higher strength values increase generative diversity at the cost of realism, revealing a clear fidelity-diversity tradeoff for both models. Across all tested configurations, a guidance scale of 5-9 provides the most effective balance between fidelity and diversity, stabilising FID, KID, and IS, and is recommended as the operating range for high-quality, diverse Ulos motif generation. These findings demonstrate that carefully fine-tuned generative AI can support the creative renewal of intangible cultural heritage while preserving its stylistic and symbolic integrity. --- ### IMR: Iterative Mode-World Weighted Regression for Multi-Agent Trajectory Prediction Authors: Honglin Wang, Shiyao Pan, Yun-Fu Liu Published: 2026-07-06 Categories: cs.RO, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.05705v1 Multi-agent motion prediction is essential for automated vehicles to understand the intentions of surrounding vehicles. However, previous prediction-based and anchor-based methods have limitations in mode diversity and prediction accuracy, respectively. These limitations may cause inadequate safety assessments and behavioral deviations in automated vehicles. To address this issue, a mode-world weighted regression loss is proposed to bridge the gap between these features. Specifically, this approach mitigates mode collapse while simultaneously improving world ranking and top-1 confidence. Furthermore, the proposed iterative decoder improves prediction accuracy by recurrently and segmentally generating trajectories. Experimental results show the proposed method ranks first in the Argoverse 2 multi-agent motion forecasting benchmark against other methods. --- ### Curating Same-Family Neural Networks for LLM-Guided Model Improvement: A Controlled Case Study Authors: Kabir Dev Paul Baghel, Radu Timofte, Dmitry Ignatov Published: 2026-07-06 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2607.05704v2 Neural-network repositories contain executable models, recipes, input transformations, and measured accuracies. We study whether one same-family experiment can be curated as prompt guidance for LLM-based improvement of a low-performing target under equal generation and evaluation budgets. TuneNNGen extends NNGPT with a source-guided route and compares it with target-only generation on one CIFAR-10 target, two fixed source-selection rules, three code LLMs, and an additional SVHN target. Under the historical one-epoch search protocol, best-of-budget accuracy on the available evaluation split rises from 23.98% to 50.49% on CIFAR-10 and from 22.54% to 78.80% on SVHN. Selected five-epoch, three-seed means on train-derived validation splits retain gains of 40.94 points on CIFAR-10, 18.83 on Imagenette, and 7.27 on CIFAR-100. Direct-copy and negative-control analyses show that gains depend on source-target compatibility and LLM adaptation; stored source accuracy alone does not predict transferability. --- ### LLM-Driven Neural Network Generation with Same-Family Architecture Guidance: Disentangling Transfer and Adaptation Authors: Kabir Dev Paul Baghel, Radu Timofte, Dmitry Ignatov Published: 2026-07-06 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2607.05704v1 Large language models (LLMs) can generate neural-network modifications, but unrestricted generation is often invalid or harmful. This paper studies a narrower setting: improving a weak target model using a stronger same-family source model from a neural-network database. We propose a source-guided candidate-generation protocol with non-source controls, source-conditioned candidates, and a no-LLM hp_copy ablation under equal evaluation budgets. The protocol reports validity separately from accuracy and selects the best valid candidate only when it improves the target. On CIFAR-10, the strongest source-guided candidate reaches 0.5049 accuracy versus 0.2398 for the best non-source candidate, a +0.2651 advantage, while improving a weak target originally at 0.1254; a five-epoch check preserves the gain at 0.7686 versus 0.4839. On SVHN AlexNet with DeepSeek-Coder-6.7B, source-guided transfer reaches 0.7880 versus 0.2254, a +0.5626 advantage; a fresh repeat reaches 0.8069 versus 0.2509, a +0.5560 advantage. Direct source-recipe copy produces 0.1959 on SVHN AlexNet, matching the original target, while hp_transfer reaches 0.7880, showing that the LLM adapts rather than copies the source recipe. Family-level analysis shows the clearest positive signals for AlexNet, with 6/8 wins across SVHN, Imagenette, and CelebA-Gender, and alt_nn1, with 8/10 wins on CIFAR-10. ---