# Research Papers — 2026-07 · bundle page 149 of 222 > Full-text markdown of papers #7401–7450 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/149 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/148.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/150.md) ### CLOE: Christoffel Loss Autoencoder for Anomaly Detection Authors: Léa Billet, Louise Travé-Massuyès, Elodie Chanthery, Alexandre Gaffet Published: 2026-07-10 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2607.20530v1 Semi-supervised anomaly detection plays a key role in diverse fields such as process monitoring, healthcare, and finance. However, lightweight methods often struggle with high-dimensional data and typically require careful tuning of multiple hyperparameters. Among existing approaches, Christoffel Function--based methods are attractive due to their simplicity, requiring at most a single hyperparameter. They also benefit from a well-established theoretical foundation that yields several interesting results for data science. However, their main limitation is poor scalability to high-dimensional settings. In this paper, we introduce CLOE, a new method that combines an autoencoder for dimensionality reduction with a Christoffel Function--based detector applied in the latent space. To better align representation learning with anomaly detection, we design a novel loss function that leverages the Christoffel Function to guide the autoencoder toward representations that better capture the support of the normal data distribution. We further propose a principled procedure to set the detection threshold and an efficient strategy to tune the single remaining hyperparameter. Experiments on multiple high-dimensional tabular anomaly detection benchmarks demonstrate that CLOE achieves superior performance compared to existing methods, while preserving the lightweight and low-tuning advantages of Christoffel Function--based approaches. --- ### Uncertainty-Aware Trust Estimation for Multi-LLM Systems via Structured Expert Judgement Authors: Jiawei Zheng, Jiazhen Zhang Published: 2026-07-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.20529v1 Large Language Model (LLM) ensembles are increasingly used to improve reliability by combining predictions from multiple LLMs. However, existing aggregation methods typically assume that all models are equally trustworthy, overlooking differences in uncertainty quality. This assumption is poorly suited to heterogeneous LLMs, whose reliability and capability vary significantly, making naive aggregation vulnerable to unreliable or adversarial experts. In this work, we formulate multi-LLM aggregation as a problem of uncertainty-aware trust estimation. We adapt structured expert judgment from decision theory, using context-aware calibration questions to estimate expert reliability based on the quality of its probabilistic predictions. Specifically, we employ Cooke-style log weighting, which penalises overconfident incorrect predictions and favours well-calibrated experts. We evaluate our approach on MMLU and MMLU-Pro across homogeneous, heterogeneous, and contaminated expert panels. Results show that while aggregation methods perform similarly in homogeneous settings, Cooke weighting becomes critical under heterogeneity and contamination. It achieves a superior accuracy-reliability balance and remains robust when unreliable experts are introduced. These findings suggest that Multi-LLM aggregation requires not just combining predictions, but calibrating trust under uncertainty. --- ### PromptPack: Scaling LLM Annotation Agents for Online Recommendation Authors: Sebastian Koralewski, Merwan Barlier, Yulia Stolin, Blaž Škrlj Published: 2026-07-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.20528v1 Online recommendation platforms increasingly use Large Language Models (LLMs) to extract structured features from ad creatives. While deploying a single-call LLM annotation agent yields significant Click-Through Rate (CTR) improvements in our live production environment, per-creative prompting is prohibitively expensive to scale. The redundant system instructions sent in every request account for 94% of billed input tokens. To break this cost bottleneck, we introduce PromptPack, a scalable, high-throughput LLM annotation agent. PromptPack achieves this scale via in-context batching, combining a shared system prompt, a strict XML structural envelope, and an output correction layer to ensure deterministic, pipeline-ready feature extraction across multiple creatives simultaneously. We evaluate PromptPack via an offline retrieval benchmark using a downstream logistic-regression ranker. To deeply profile the agent's behavior, we measure AUC and introduce Volume-Weighted Absolute Lift (VWAL), a novel metric capturing the signal quality of the generated features. Compared to our live, unbatched production baseline, PromptPack at batch size 20 cuts our LLM costs by 89% and accelerates throughput by 2.5x while fully preserving AUC. --- ### Evaluating and Guarding Citation Faithfulness in Agentic Scientific Synthesis Authors: Taewan Goo, Junsik Kim, Kyulhee Han, GwonYul Jo, Jong-Soo Kim, Tae-Hyung Kim Published: 2026-07-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.20527v1 Agentic LLM systems such as OpenScholar and PaperQA2 read the scientific literature and return cited answers, and both they and their benchmarks already check whether those citations hold, with a fixed attribution model or human graders. Neither audits the reliability of that check itself. We show it is not reliable, and that this matters. On identical agent outputs the measured unsupported-citation rate ranges from about 3% to about 18% depending only on the verifier's strictness, and although verifiers agree on which citations are supported, they disagree on which to flag (negative-specific agreement 0.27 to 0.30), so no single flag set is trustworthy and cross-paper comparison is invalid without a named verifier and protocol. We present a gold-anchored evaluation protocol and a deployable guard that make this behavior measurable and bounded. The protocol validates the verifier, measures re-attribution, and calibrates a guarantee against human gold rather than another model's verdict; the verifier is a swappable instrument chosen on cost (recall 0.94 on the supported class, held out), and re-attribution is a commodity step where a deterministic BM25 matches the best open generator. The guard adds a split-conformal layer placing a distribution-free, finite-sample bound on truly unsupported citations that slip past a chosen flagging rule, a guarantee on catch rate rather than conclusion correctness. The bound holds on held-out gold, and we identify and quantify the condition governing its transfer to deployment, calibration-negative difficulty, with a concrete recalibration recipe, left untested by prior conformal-factuality work. Validated across four open 27-35B models and three agentic pipelines on public benchmarks (SciFact, QASA, PubMedQA), with confidence intervals on every headline number, the protocol and guard ship as an open single-GPU kit. --- ### ConfidenceBench: Evaluating Confidence Calibration in Large Language Models Authors: Matthew ffrench-Constant, Daniel Yang, Xinmeng Huang, Sanyam Kapoor Published: 2026-07-10 Categories: cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.20526v1 Large language models (LLMs) are increasingly deployed in settings where fluent but incorrect answers can be costly. In these settings, accuracy alone is insufficient: models must also know when they are likely to be wrong. We present ConfidenceBench, a calibration benchmark that evaluates verbalized confidence estimates in 15 frontier LLMs using the Brier score, a proper scoring rule that incentivises truthful probability reporting. Confidence is elicited via prompting, requiring no access to model logits and making the framework applicable to both closed-source and open-source systems. The benchmark comprises 200 private multiple-choice questions across four categories: spatial reasoning, high-precision mathematics, word lookup, and unknowable questions. Across three independent runs, Claude Opus 4.6 and Gemini 3.1 Pro Preview achieve the lowest Brier scores, both reported as 0.103. Both substantially outperform the calibrated-random baseline of 0.1875, while Gemini 3.1 Flash-Lite scores 0.367, indicating severe miscalibration. Accuracy and calibration diverge substantially across model families: the most accurate model is not the best-calibrated, and several models perform worse than the calibrated-random Brier baseline despite reasonable accuracy. These results show that verbalized confidence calibration is a distinct and practically important axis of LLM reliability, complementary to standard accuracy-based evaluation. --- ### MAC 2026: Advancing Micro-Action Analysis Towards Fine-Grained Understanding Authors: Kun Li, Dan Guo, Jihao Gu, Pengyu Liu, Xiaobai Li, Haoyu Chen, Yanbin Hao, Guoying Zhao, Meng Wang Published: 2026-07-10 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2607.16284v2 Micro-Actions (MAs) are subtle and spontaneous human behaviors that provide important non-verbal cues in social interaction and affective communication. However, their short duration, weak motion patterns, and fine-grained semantic differences make them difficult to annotate, model, and evaluate in a standardized manner. To promote academic research on micro-action analysis, we proposed and have annually organized the Micro-Action Analysis Grand Challenge (MAC) as a public benchmark platform for this emerging field. The first two editions of MAC established standardized evaluation settings for micro-action recognition and detection, providing publicly accessible datasets and protocols. Building upon these editions, this paper presents the 3rd MAC, held in conjunction with ACM Multimedia 2026. Under the theme of moving from recognition to fine-grained micro-action understanding, this edition further expands the scope of the challenge beyond conventional recognition and detection. In particular, we introduce a new task named fine-grained micro-action understanding, evaluated with the assistance of multimodal large language models, aiming to assess models' ability to capture fine-grained semantic cues and interpret subtle human micro-actions at a deeper level. We summarize the datasets, task settings, evaluation protocols, competition results, and representative solutions from top-performing teams. Finally, we discuss future directions for micro-action analysis and its broader role in human-centric video understanding. --- ### GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification Authors: Md Faraz Kabir Khan, Saeed Anwar, Ghulam Mubashar Hassan Published: 2026-07-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.16283v1 The rapid advancement of generative AI has outpaced our ability to reliably detect its outputs, particularly when detectors encounter generators they have not seen before. We introduce GenSyn10, a CIFAR-10-aligned synthetic image dataset of 60,000 images (10 classes, 32$\times$32, 50k/10k split) generated using three architecturally diverse state-of-the-art models: FLUX.2-dev (Rectified Flow Transformer), HunyuanImage-3.0 (MoE Transformer), and Qwen-Image-2512 (Multimodal Diffusion Transformer), to advance research in AI-generated image detection. A central challenge in this domain is that detectors perform well on known generators but degrade on unseen ones. GenSyn10 addresses this limitation by curating data from multiple contemporary architectures under a standardized generation protocol, enabling controlled and systematic evaluation of out-of-distribution (OOD) generalization to novel generators. Images are generated using a template-based prompt engine and downsampled to ensure consistency. We evaluate 17 image classification models under a four-stage protocol: real-data baseline, zero-shot transfer, fine-tuning, and retention. Despite a measurable domain gap, CIFAR-10-trained models achieve up to 96.86\% zero-shot accuracy on GenSyn10, increasing to 99.88\% after fine-tuning. In binary real-vs-synthetic classification, fine-tuned models achieve 97-99.9\% accuracy on seen generators but drop to 79-96\% on images from an unseen generator, highlighting persistent limitations in OOD generalization. These results establish GenSyn10 as a controlled benchmark for studying synthetic image detection beyond single-generator settings, supporting research on robustness, domain adaptation, and cross-generator generalization. --- ### Volition Elicitation: Operational Semantics for People and Their Machines Authors: Ehud Shapiro Published: 2026-07-10 Categories: cs.PL, cs.AI, cs.DC, cs.HC, cs.MA arXiv: https://arxiv.org/abs/2607.14138v1 The most prevalent distributed systems today include people and their personal machines (smartphones). In such systems, computations are driven by people's volitions: a payment when a person wishes to pay someone, befriending when two people wish to become friends, etc. Volition-Guarded Multiagent Atomic Transactions were proposed as an abstract specification language for such systems, in which each agent consists of a person and their machine, and a transaction can be guarded by both the machine states and the personal volitions of its participating agents. Here, we define the programming language volition-guarded GLP (vGLP), which extends GLP with volition-guarded clauses, and define its operational semantics as an instance of Communicating Volitional Agents. As the semantics requires the person to will a volition-guarded clause reduction, a correct implementation must elicit the person's volitions: finding out ``what's in the person's head'' is the sole rationale for the UI, which is realised accordingly by standard constructs. We demonstrate the approach on the grassroots social graph, social network, and currencies: each platform is a vGLP program, generated by AI from volition-guarded multiagent atomic transactions; the implementation of vGLP, also created by AI, then maps its volition-guarded clauses into the user-interface constructs, resulting in a single working app deployed on a physical smartphone. --- ### Untrusted Authors, Trusted Answers: A Calculus of Fidelity-Graded Translations Authors: Christoph Kirsch Published: 2026-07-10 Categories: cs.PL, cs.AI, cs.LO, cs.SE arXiv: https://arxiv.org/abs/2607.14137v2 To answer a question about a program, move the program to where the question is decidable. Every such move is a translation, and every translation is a place to be wrong. We study translation as a graph -- many languages, a few reasoning targets, independently built routes of honestly different trustworthiness -- and give it a calculus: pairs of languages close commuting squares that are directional (exactness is the identity-embedding special case of over-approximation), checkable per program, and composable, a route's contract being the componentwise meet of its hops' contracts -- assurance class, direction, kept observables, measured cost. One asymmetry organizes trust: witness-carrying answers are self-certifying by replay at the source; universal answers are where grades, independent branches, and re-checked certificates earn their cost. The compositional core, lax telescope included, is mechanized in Lean 4. hurdy-gurdy implements the calculus as two planes meeting in one registry. The use plane reads declarations and produces evidence-carrying answers; its builders and its intended player are both LLMs, untrusted by construction. The evolution plane grows the graph: unmet questions are recorded as demand, pairs are recommended by evidence and registered by humans, and a ratchet keeps every prior verdict standing. Answers never write; growth never answers. Run indefinitely, the loop converges on every reducibly decidable question, at fidelity that only rises. We measure the July 2026 snapshot -- per-construct conjoined coverage, dual-route branch agreement for two ISAs, source-level witness replay, certified unreachability re-validated by a formally verified checker, escape rates for the gate itself -- and report the defects the architecture caught in its own authors' work. --- ### Repairing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry Authors: Adam Haroon, Cody Fleming, Beiwen Li Published: 2026-07-10 Categories: cs.LG, eess.IV arXiv: https://arxiv.org/abs/2607.11928v1 Single-shot fringe projection profilometry (FPP) networks that regress depth directly can exploit a shape-prior shortcut, recovering depth from object boundaries rather than from fringe phase. On a photorealistic synthetic benchmark (15,600 fringe images, 50 objects at 1.5-2.1 m standoff), the best such UNet baseline plateaus at 14.54 mm object mean absolute error (MAE), and neither more data nor more capacity removes the shortcut, because neither changes the hypothesis space the optimizer searches. We introduce PhiCalNet, which outputs a wrapped-phase representation $(\sinφ, \cosφ)$ and maps it to depth through a fixed differentiable calibration layer, removing the shape-prior solution architecturally rather than by a loss penalty. Because the single-shot mapping is non-injective without fringe order, PhiCalNet takes the fringe order as auxiliary input, an assumption a sensitivity analysis shows tolerates realistic decoding error; a physics-informed (PINN) baseline with the same physics as a soft penalty yields no gain, isolating the architectural choice as the operative factor. PhiCalNet reduces object MAE 3.3x to 4.46 mm, its residual confined to 0.103% of pixels at the $\pmπ$ wrap discontinuity, and a three-frame extension reaches 1.16 mm. Two checks agree: interpretability makes phase the most decodable internal feature, and pixel-wise conformal uncertainty quantification, to our knowledge the first for FPP, localizes error at the same discontinuity, where rejecting the top 5% of pixels by snapshot disagreement cuts root-mean-square error by 64% versus 3.5% for the baseline. --- ### FlashTrie: A GPU-Accelerated Constrained Beam Search for Generative Retrieval Authors: Dakshitha Anandakumar, Anurag Mukkara, Wenxiang Hu, Jiusheng Chen, M Akash Kumar, Ting Ye, Qiang Lou, Jian Jiao Published: 2026-07-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.10044v1 Constrained decoding is essential in generative retrieval, where document identifiers generated directly from a query must exactly match a predefined library of valid IDs. At scale, decoding is often constrained using a trie with beam search but most implementations run on CPU. Limited parallelism then makes trie traversal and candidate validation a serving bottleneck as beam width grows. We present FlashTrie, which addresses this limitation by optimizing constrained beam search on GPUs. It introduces an integer-aware succinct trie layout that uses bit compression to reduce memory footprint while keeping the full index in GPU high-bandwidth memory reducing memory stalls, and a cooperative CUDA kernel that performs beam expansion, validation, and pruning entirely on-device without per-step host orchestration. It further replaces CPU-style irregular lookup and heap maintenance with GPU-aware parallel primitives, improving warp utilization and reducing divergence. Together, these designs significantly reduce decoding latency and increase throughput while preserving retrieval quality. On a library of 800M keywords with beam widths up to 1000, FlashTrie reduces trie-search latency to under 3 ms, achieving up to 24x speedup over a highly optimized multi-threaded CPU baseline. These improvements enable FlashTrie to scale beam sizes by up to 5x in latency-critical applications such as sponsored search. In a large-scale online A/B experiment on a popular commercial search engine, it delivers a statistically significant +0.71% revenue lift, enabling real-time constrained decoding at a scale previously feasible only offline. The FlashTrie code will be publicly released after the review process. --- ### Adaptive Search in Collatz Exponent-Code Space via 2-adic and 3-adic Constraints Authors: Oliver Kramer Published: 2026-07-10 Categories: cs.NE, cs.IT arXiv: https://arxiv.org/abs/2607.10041v1 We study a symbolic search space for the Collatz conjecture based on finite exponent codes of the accelerated map. Each code records the number of divisions by two after every 3n + 1 step and determines three quantities: real drift, a 2-adic start representative, and a 3-adic endpoint representative. Their combination defines the 2-3-infinity diagnostic. Counterexample-like codes should exhibit near-critical drift, small 2-adic start representatives, and endpoints compatible with growth on the scale of (3/2)^k. We prove that every infinite code generated by a fixed positive integer has asymptotically vanishing 2-adic and 3-adic residue rates. Experiments with random critical codes, mechanical critical codes, and adaptive evolutionary search at lengths 100, 200, and 400 show that adaptive search improves finite-length trade-offs, while all methods retain clearly positive residue rates. The proposed framework is not a verification method for the Collatz conjecture, but a symbolic diagnostic approach for investigating obstruction structures in exponent-code space. --- ### Are We Ready for AI-Driven Discovery? AI Verification Before the Next Fundamental Physics Breakthrough Authors: Gaia Grosso, Vinicius Mikuni, Lukas Heinrich Published: 2026-07-10 Categories: physics.data-an, cs.LG, hep-ph arXiv: https://arxiv.org/abs/2607.10039v1 Machine learning (ML) has become integral to fundamental physics, accelerating statistical workflows from data acquisition through inference and hypothesis testing. As ML systems grow increasingly autonomous, ensuring their reliability for discovery claims becomes critical. This review synthesizes the VERaiPHY (Validation & Evaluation for Robust AI in PHYsics) initiative's frameworks for rigorous ML assessment across particle physics, astrophysics, and cosmology. We establish when verification is essential by contextualizing ML within the statistical discovery workflow. We emphasize fundamental limitations: inductive bias is unavoidable, sample complexity bounds learning, and experimental constraints limit discovery. We reflect on physicists' evolving role as both experimental designers and evaluators whose judgments encode scientific rigor into AI systems. Responsible integration requires understanding ML's transformative potential alongside its intrinsic boundaries. --- ### Geometric mean-based pairwise comparison method with the reference values -- statistical approach Authors: Konrad Kułakowski, Kamil Pustelnik, Jacek Szybowski Published: 2026-07-10 Categories: stat.ME, cs.AI, math.ST arXiv: https://arxiv.org/abs/2607.10038v3 For many years, pairwise comparison methods have been widely used for eliciting preferences and ranking alternatives in decision-making problems. These methods estimate priority weights from a pairwise comparison matrix and are now standard tools in multi-criteria decision analysis. In this paper, we present a statistical view of the pairwise comparison method using reference values and the geometric mean to calculate alternative priorities. Thanks to this approach, we can simultaneously capture the phenomenon of inconsistency in pairwise comparisons and the preference distance between different alternatives. In this paper, we define indicators that measure the quality of the obtained weight vector, which, thanks to the statistical approach, have an understandable interpretation. --- ### MLPs are Hebbians: Constructing Efficient Fact-Storing MLPs for Transformers Authors: Roberto Garcia, Jerry Liu, Ronny Junkins, Sabri Eyuboglu, Atri Rudra, Christopher Ré Published: 2026-07-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.10034v1 Large language models (LLMs) store factual knowledge in their parameters. While recent work has shown that this knowledge resides in MLP layers, existing constructive and mechanistic interpretability models of fact-storage in LLMs fail to explain the surprising empirical phenomenon that they store facts at an information-theoretically optimal rate. In this work, we develop a theoretical account of this phenomenon. We develop the first Transformer-compatible fact-storing MLP closed-form construction that satisfies the following three properties empirically observed in LLMs: it (i) attains optimal fact storage scaling, (ii) handles arbitrary input/output geometries, and (iii) works inside Transformers. Key to our work is to analyze the decoding margin of MLPs, whereas prior work only studies MLP fact storage. Under isotropic embeddings, our construction achieves information-theoretically optimal storage capacity scaling and requires $10$-$104\times$ fewer parameters at matched fact count than prior constructions. For arbitrary key and value embeddings, we show that our construction attains the same storage capacity scaling, up to penalization factors depending on the embedding geometries. Moreover, we demonstrate that our constructed MLPs can be used within Transformer blocks for factual recall tasks at optimal capacity scaling, requiring $15$-$63\times$ fewer parameters at matched fact count than prior constructions. Finally, as a proof-of-concept, we show that fact-storing MLPs enable modular fact editing by swapping a Transformer's MLP with a new one. --- ### Robustly Invertible Nonlinear Dynamics and the BiLipREN: From Inversion-Based Control to Generative Trajectory Modelling Authors: Yurui Zhang, Ruigang Wang, Ian R. Manchester Published: 2026-07-10 Categories: eess.SY, cs.LG, math.OC arXiv: https://arxiv.org/abs/2607.10026v1 This paper proposes a new notion of robust invertibility for nonlinear dynamical systems, and introduces constructive parameterizations of recurrent neural network which are robustly invertible by design. We define robust invertibility as the existence of a causal inverse system such that both the forward and inverse systems are contracting and have bounded incremental input-output gains (the system is bi-Lipschitz), implying that both forward prediction and input reconstruction are robust to signal perturbations and initial-state mismatch. We construct robustly invertible recurrent models via series composition of static orthogonal layers and dynamic layers satisfying a strong input-output monotonicity property, and provide a differentiable neural network parameterizations in the form of the bi-Lipschitz recurrent equilibrium network (BiLipREN). Additionally, composition with dynamic orthogonal layers yields a nonlinear minimum-phase/all-pass (a.k.a. inner--outer) factorization. We illustrate the utility of the framework through a series of application examples in data-driven internal model control, dynamic surrogate loss learning, and signal-space normalizing flows, illustrating its utility for robust control, trajectory optimization, and generative modeling of complex trajectory distributions. --- ### Local Multimodal Music Alignment from Global Supervision Authors: Irmak Bukey, Zachary Novack, Jongmin Jung, Dasaem Jeong, Chris Donahue Published: 2026-07-10 Categories: cs.SD, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2607.10023v2 Understanding music requires understanding localized relationships across data modalities, e.g., how time in performance audio maps onto position in a score image. Yet supervision for such local correspondences is difficult to obtain-in practice, we often only have access to coarser global supervision like paired segments of audio and images. To address this gap, we propose FuSiLi (Fused Sinkhorn-Localized Similarity), a similarity score for multimodal contrastive learning operating directly on local image patch and audio frame features via Sinkhorn-based soft alignment. We show that FuSiLi (i) effectively learns local relationships, (ii) requires only global supervision, and (iii) retains the global alignment capabilities of conventional contrastive approaches. We fine-tune pretrained CLIP and CLAP encoders on pairs of raw sheet music images and audio using a hybrid contrastive objective combining FuSiLi with conventional global similarity. We evaluate on cross-modal retrieval and frame-level alignment tasks against a range of global and local baselines, showing that our approach outperforms them on local alignment while remaining competitive on retrieval. --- ### A Symbolic Neural CPU for Quantization-Simulated Writeback and Interpretable Program Execution Authors: Jose Luis Lima de Jesus Silva Published: 2026-07-10 Categories: cs.AI, cs.AR, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2607.10021v1 Neural networks can learn algorithmic input-output mappings, but trusting a learned executor requires more than a correct final answer because the state transitions that produce it are usually hidden. To make those transitions visible, we introduce a trace-supervised symbolic neural CPU, a factorized learned execution architecture that combines recurrent control, an explicit operation router over a fixed differentiable arithmetic-logic unit bank, destination-masked register writeback, complete trajectory supervision and matched fixed-point replay. The model exposes the selected operation, source and destination registers, register trajectory, memory signals and writeback semantics at every step. On the principal 16-wide benchmark, the non-quantized executor reproduces reference execution exactly, while the eight-bit quantization-simulated executor preserves the symbolic operation path through programs of 1,000 instructions. When the same execution is evaluated against a matched fixed-point replay, the residual numerical drift disappears, showing that it comes from a mismatch between continuous and low-precision reference semantics rather than from execution failure. We compare recurrent, Transformer, temporal-convolution, temporal graph-inspired and state-space controllers, and the ablations show that operation-gate supervision is necessary for an inspectable execution path. Hidden-opcode memory-pressure tasks expose the remaining limits in delayed state use and temporal binding. We also extend the interface with ValueMemory, hybrid adaptive leaky integrate-and-fire controllers, candidate-constrained symbolic control trained through behaviour cloning and actor-critic reinforcement learning, and an RV32I base-integer semantic bridge. Together, these results establish a trace-verifiable framework for interpretable, low-precision and controllable neural execution. --- ### FindMyText: Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora Authors: Lars Henry Berge Olsen, Pierre Lison, Martin Jullum, Mark Anderson Published: 2026-07-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.10020v2 We present FindMyText, an open-source Python package designed to efficiently assess whether a given text appears, in part or in full, within a text corpus. The tool builds on prior techniques for document fingerprinting, but extends them with a novel mechanism to explicitly capture sequences of matching fingerprints. By identifying such chains, the tool can more reliably detect near-verbatim copies of a given text rather than mere textual similarities. This makes FindMyText particularly suited for verifying the presence of copyrighted material in a corpus. Leveraging a distributed, disk-based indexing framework, the system scales to large web-crawled datasets. Using a new benchmark for evaluating text containment methods, we show that FindMyText outperforms alternative approaches across three datasets (ArXiv papers, Wikipedia, and generic web content). --- ### Tokenizing Numerical and Embedding Features for LLM RecSys Authors: Zhe Xu, Ankit Peshin, Chiyu Zhang, Feng Qi, Johnson Lui, Anil Ramakrishna, Justin Johnson, Carl Hu, Kaushik Rangadurai, Luke Simon Published: 2026-07-10 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2607.10016v3 Large language models (LLMs) are increasingly used as backbone architectures for recommender systems because of their strong sequence modeling and representation learning capabilities. However, most LLM-based recommenders operate primarily on discrete textual tokens, whereas practical recommendation pipelines also rely on continuous numerical features and dense embedding features produced by upstream feature engineering or pretrained encoders. This mismatch limits the ability of LLM-based models to exploit fine-grained non-textual signals. We propose a soft-token fusion framework that maps numerical and embedding features into the LLM embedding space, allowing heterogeneous recommendation signals to be consumed through the standard token interface. We instantiate the framework in a shared-parameter LLM-based two-tower retrieval model and introduce an interaction-based fusion module that refines embedding and numerical soft tokens before they are inserted into the final LLM input. Experiments on three Amazon recommendation benchmarks show that soft-token fusion improves retrieval performance over LLM-based baselines, and that interaction-based fusion is more effective than direct concatenation of heterogeneous soft tokens. --- ### Runtime Safety Filtering for Learned Small UAS Separation Policies under GNSS Degradation Authors: Alex Zongo, Peng Wei Published: 2026-07-10 Categories: cs.RO, cs.LG, cs.MA, eess.SY arXiv: https://arxiv.org/abs/2607.10014v2 Learning-based separation assurance for small Unmanned Aircraft Systems (sUAS) achieves near-zero collision rates in simulation, but assumes accurate position and velocity information from Global Navigation Satellite Systems (GNSS). This assumption fails in urban environments, where multipath propagation, signal blockage, and intentional interference degrade navigation integrity. This raises a fundamental architectural question for deploying learned separation policies under GNSS degradation: should runtime safety mechanisms filter the policy's actions or its observations? This work evaluates both approaches for multi-agent sUAS separation under adversarial GNSS degradation. Both architectures first estimate a worst-case traffic state consistent with bounded observation uncertainty, then diverge: action filtering constrains policy outputs via discrete-time control barrier functions evaluated at the worst-case state, while observation filtering presents the worst-case state directly to the policy as corrected input. Experimental results show that action filtering provides negligible safety improvement, while observation filtering reduces near mid-air collisions by 90% and remains robust to the barrier function's tradeoff between separation distance and closing rate. These results suggest that, for policies with learned safety behaviors, preserving the policy's decision authority outperforms overriding its actions with hand-designed constraints. --- ### Runtime Safety Filtering for Learned Small UAS Separation Policies under GNSS Degradation Authors: Alex Zongo, Peng Wei Published: 2026-07-10 Categories: cs.RO, cs.LG, cs.MA, eess.SY arXiv: https://arxiv.org/abs/2607.10014v1 Learning-based separation assurance for small Unmanned Aircraft Systems (sUAS) achieves near-zero collision rates in simulation, but assumes accurate position and velocity information from Global Navigation Satellite Systems (GNSS). This assumption fails in urban environments, where multipath propagation, signal blockage, and intentional interference degrade navigation integrity. This raises a fundamental architectural question for deploying learned separation policies under GNSS degradation: should runtime safety mechanisms filter the policy's actions or its observations? This work evaluates both approaches for multi-agent sUAS separation under adversarial GNSS degradation. Both architectures first estimate a worst-case traffic state consistent with bounded observation uncertainty, then diverge: action filtering constrains policy outputs via discrete-time control barrier functions evaluated at the worst-case state, while observation filtering presents the worst-case state directly to the policy as corrected input. Experimental results show that action filtering provides negligible safety improvement, while observation filtering reduces near mid-air collisions by 90% and remains robust to the barrier function's tradeoff between separation distance and closing rate. These results suggest that, for policies with learned safety behaviors, preserving the policy's decision authority outperforms overriding its actions with hand-designed constraints. --- ### Manifold Constrained Conformal Prediction for Spatial Events Authors: Collin Nill, Trevor Harris, Jason Adams Published: 2026-07-10 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2607.10008v1 We introduce a new conformal prediction method that constructs calibrated prediction sets over collections of spatial events, such as tropical cyclone genesis and earthquake locations. Forecasting natural hazards has become increasingly important, due to their significant economic impact, and quantifying the uncertainty of predictions is critical for accurate risk assessment. Our approach works by representing spatial point clouds as empirical measures so that we can score them using (sliced) Wasserstein distance, then constraining the resulting distribution-valued prediction set to be supported only near the training data manifold. We derive a coverage lower bound for the intersected sets and show that, in practice, this gap can be made small through a simple data-adaptive selection criterion. Because the resulting set is not analytically tractable, we introduce a modified flow-based sampling procedure, which allows us to represent and apply these prediction sets in practice as ensembles. Numerical experiments on synthetic data, tropical cyclone genesis, and earthquake occurrences show that our method achieves near-nominal coverage, with significantly lower energy distance and manifold distance than highest predictive density region (HDR) baselines along with generative model baselines. --- ### Model Guides You How to Draw: Adaptive Visual Gating for Unified Multimodal Reasoning Authors: Wenxi Gao, Guanxi Lu, Didi Zhu, Hao Mark Chen, Quan Deng, Zhican Wang, Jiankang Deng, Hongxiang Fan Published: 2026-07-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.10004v1 Unified multimodal models (UMMs) with interleaved reasoning, which generate both textual and visual steps as part of intermediate reasoning traces, have demonstrated great potential for visual mathematical reasoning tasks. However, we identify a key insight in this paradigm: generating intermediate visual reasoning steps is not always beneficial and can even be harmful, as self-generated visual steps may introduce erroneous visual evidence that misleads subsequent reasoning. Moreover, frequently triggering visual steps during reasoning incurs substantial computational and memory overhead, degrading inference efficiency. To address these accuracy and efficiency challenges, we observe that the model's internal signals can indicate whether a visual step will benefit reasoning before the entire visual generation is completed. Specifically, this work identifies two internal signals: 1) Generation Intent, which reflects whether the model has a concrete textual plan for what to draw, and 2) Visual Fidelity, which measures whether the visual generation remains grounded in the original input image. Leveraging these internal signals, we propose AdaViG, a training-free adaptive visual gating method for unified multimodal reasoning. AdaViG dynamically evaluates each triggered visual step at an early visual generation stage and aborts it when both signals are weak, thereby preventing misleading visual evidence from entering the reasoning trace while avoiding unnecessary computation. Comprehensive experiments demonstrate that AdaViG improves accuracy by up to 5.7% while reducing visual generation FLOPs by 25.0%-91.0% and wall-clock latency by 15.4%-45.6%. --- ### Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts Authors: Renuka Oladri, Mohan Vamsi Varadaraju Priya, Jerry Wu Published: 2026-07-10 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.09999v2 We show that post-training quantization can silently alter how large language models reason even when task accuracy is preserved. Using a six-category failure taxonomy validated by two independent human annotators (Cohen's $κ$ = 0.906), we classify 30,000 chain-of-thought outputs from five instruction-tuned LLMs (3B--14B parameters) across three quantization precisions (FP32, FP16, NF4) and four reasoning benchmarks. We find that while accuracy is robust across precisions (maximum 3.1 pp drop), Hollow Convergence (correct answers reached through incomplete or unverifiable reasoning) shows a significant size-dependent shift under NF4, dropping sharply for the two smallest models tested but remaining invariant for models at 12B parameters and above. This effect is also benchmark-specific: GSM8K is categorically immune while LogiQA and ARC-Challenge show the largest shifts. Furthermore, under NF4, Shortcut Collapse rises from 44% to 78% of wrong-answer failures in LLaMA 3.2-3B while Confidence Snowballing collapses from 15.8% to near zero, a qualitative shift invisible to accuracy metrics. Finally, we show Hollow Convergence cannot be reliably detected from surface-level text features (best F1 = 0.53), establishing it as a deployment-relevant failure mode that standard evaluation pipelines cannot catch. --- ### Vilya-1: An all-atom foundation model for macrocycle structure prediction and design Authors: Vilya Research, :, Pascal Sturmfels, Milad Salem, Naozumi Hiranuma, Stephen Rettie, Xiaoliang Pan, Benjamin D. Sellers, Adam P. Moyer, Patrick J. Salveson, Ivan Anishchanka Published: 2026-07-10 Categories: cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2607.09998v1 Macrocyclic peptides are an increasingly important therapeutic modality, but existing computational methods for modeling their structures and properties are limited in scope and do not generalize well across the synthetically accessible chemical space. In this work, we introduce Vilya-1, a deep learning model that addresses two central challenges in macrocycle design: sampling biologically relevant conformations across arbitrary chemistries and predicting key developability properties such as membrane permeability. Vilya-1 operates on a uniform all-atom representation and is trained on heterogeneous structural datasets spanning diverse topologies and chemical classes. Across a broad set of macrocycles composed of canonical and non-canonical residues, Vilya-1 substantially improves geometric accuracy relative to physics-based methods, co-folding networks, and deep-learning conformer generators, while maintaining broad chemical coverage that extends to small molecules. Vilya-1 also supports generative applications, enabling the design of novel macrocycles with tailored chemical, structural, and property profiles. Together, these capabilities establish Vilya-1 as a foundation model for accelerating the development of next-generation macrocycle therapeutics. --- ### Who&When Pro: Can LLMs Really Attribute Failures in AI Agents? Authors: Jiale Liu, Huajun Xi, Shaokun Zhang, Yifan Zeng, Tianwei Yue, Chi Wang, Jian Kang, Qingyun Wu, Huazheng Wang Published: 2026-07-10 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2607.09996v1 Automated failure attribution uses LLMs to identify where and why agentic systems fail. As agents become more capable, their failures become subtler, making automated attribution increasingly important. We introduce Who&When Pro, a large-scale benchmark for automated failure attribution in agentic systems. Using a strictly controlled pipeline that injects a failure only after exactly replaying a successful prefix, we construct 12,326 failed trajectories with golden labels across 3 modalities and 26 benchmarks covering various scenarios. Beyond benchmarking, we conduct extensive experiments and analyses, revealing systematic patterns in how models attribute failures across modalities, protocols, and model families, and providing empirical guidance for future automated failure attribution systems. --- ### Beyond Bayesian Nash: Learning Minimax-Regret Equilibria for Adversarial Team Games under Asymmetric Information Authors: Naman Aggarwal, Jonathan P. How Published: 2026-07-10 Categories: cs.GT, cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2607.09993v1 Adversarial team games (ATGs) with asymmetric information, such as adversarial path-finding, goal search, and reachability games on graphs, require strategies that are robust to hidden opponent types, such as a hidden goal flag, and to deception. Under asymmetric information, deception is seen as strategic shifts in the type distribution such that the omniscient opponent can collude with Nature and condition its play on the observed type. Existing risk-neutral solution concepts, such as Bayesian Nash equilibrium (BNE), are sensitive to distribution shifts, while distributionally robust approaches provide guarantees only within a prescribed ambiguity set. To address these limitations, we introduce Probabilistically Robust Minimax-Regret Equilibrium (PR-MRE), a novel equilibrium concept that combines the distribution-free robustness of minimax-regret reasoning with probabilistic information from a nominal type distribution. PR-MRE minimizes worst-case regret over a high-confidence subset of the type space, providing protection against strategic redistribution of probability mass while avoiding the conservatism of fully distribution-free approaches. We show that, for normal-form Bayesian games, PR-MRE can be formulated as a robust bilinear program and derive a tractable semidefinite relaxation. We then adapt this relaxation into a novel meta-solver within a robust double-oracle framework, PRMRE-PSRO, enabling population-based learning of approximate PR-MRE strategies via deep reinforcement learning best responses. Experiments on graph-structured adversarial team games demonstrate that PR-MRE discovers strategies with substantially improved worst-case performance across hidden types compared to risk-neutral equilibrium solutions, resulting in more robust behavior under strategic distribution shifts. --- ### An LLM-powered Agentic Recommendation System for Connected TV Content Discovery Authors: Lei Shi, Di Wang, Harry Tran, Helsing Xu, Yuchen Lu, Dhara Ghodasara, Wilson Chaney, Xueting Liao, Jerry Yu, Huayu Ding, Reza Mirghaderi, David Fan et al. Published: 2026-07-10 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2607.09988v3 Recommendation systems, from traditional multi-stage to recent unified generative architectures, face challenges in incorporating diverse contextual signals, such as trending topics, breaking news, cultural events, and cross-surface user activities, into their ranking pipelines. These systems are designed to consume structured behavioral signals with consistent schemas, and lack the reasoning capability to naturally process unstructured or heterogeneously formatted contextual information. Incorporating such signals typically requires feature engineering, bespoke data pipelines, and carefully tuned heuristics. In this paper, we present an LLM-powered agentic recommendation system designed for Connected TV (CTV) content discovery that addresses these limitations. Our system leverages the reasoning capabilities of large language models to naturally process and synthesize diverse signals across varying schemas and structures, eliminating much of the manual integration inherent in traditional ranking and retrieval systems. Recognizing that current LLM-based solutions still fall short of traditional machine learning models in several recommendation tasks, including retrieval efficiency, personalization precision, and scalability, we adopt an agentic architecture that orchestrates specialized components, allowing each sub-task to be handled by the most suitable method, whether LLM-based or traditional ML. The main contribution of this work is our engineering approach to successfully overcoming the practical limitations of enabling LLM for recommendation, particularly inference latency. We share insights from our work and discuss the trade-offs and lessons learned in building a hybrid system that combines the flexibility of LLMs with the performance of established recommendation techniques. --- ### UniPose9D: Universal Category-Agnostic Object Pose Estimation Authors: Yang You, Yi Du, Cole Harrison, Leonidas Guibas Published: 2026-07-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.09985v1 Object pose estimation is a fundamental problem in 3D vision. Although recent state-of-the-art approaches achieve strong performance, they often overfit to existing benchmarks and exhibit limited generalization to novel categories and unseen scenes. We propose UniPose9D, a category-agnostic foundation model for 9D object pose estimation: given an instance mask/ROI and either an RGB-D observation or an RGB image with predicted depth, the model estimates rotation, translation, and metric size without category labels, CAD models, mean-shape priors, or reference views. Specifically, UniPose9D samples point pairs from the observed object geometry and uses DINOv2 and PointNet features to predict NOCS coordinates for each pair. To improve accuracy, we introduce a point-pair-based RANSAC N-hop Kabsch--Umeyama algorithm with an adaptive threshold. We further employ flow matching to address symmetric ambiguities and construct a large-scale training set by curating and aligning pose annotations from existing public datasets. Experiments across six datasets show that a single unified model can match or surpass specialist methods while generalizing to unseen objects and in-the-wild scenarios. Our code and model are available on https://github.com/qq456cvb/UniPose9D. --- ### Multimodal Routing for Interpretable, Robust, and Auditable Clinical Prediction Authors: Nikkie Hooman, Zhongjie Wu, Eric C. Larson, Mehak Gupta Published: 2026-07-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.09982v1 Electronic health record (EHR) data are inherently multimodal, and leveraging multiple modalities can improve predictive performance. However, most existing approaches rely on deep fusion, which obscures how individual modalities contribute to predictions and limits the interpretability of multimodal reasoning. We propose an explicit multimodal routing framework for clinical prediction that enables interpretable, robust, and auditable reasoning across three EHR modalities: structured longitudinal variables (L), clinical notes (N), and chest X-rays (I). Our model constructs discrete unimodal, directional bimodal, and trimodal routes to capture both individual modality signals and asymmetric cross-modal interactions. To audit multimodal reasoning and assess robustness, we introduce inference-time route masking, which simulates missing modalities and reweights the remaining routes without retraining. We analyze changes in performance and routing weights under these scenarios to understand model decision-making. We evaluate our framework on multi-label phenotype prediction (K = 25) and binary ICU mortality prediction using trimodal patient stays from MIMIC-IV, revealing systematic differences in modality reliance across clinical condition groups. Overall, our framework offers a transparent, auditable, and practical approach to multimodal clinical prediction, providing interpretability, robustness, and insights into how different data sources drive model decisions. --- ### Inverse-IMPRESSION: A Graph-based Platform for Molecular Structure Elucidation from Experimental NMR Spectroscopic Properties Authors: Zheqi Jin, Grace Armitage, Richard Cox, Ben Honoré, Mohammad Golbabaee, Craig Butts Published: 2026-07-10 Categories: physics.chem-ph, cs.LG arXiv: https://arxiv.org/abs/2607.09978v1 Here, we present a platform built on our inverted Graph Transformer Network, IMPRESSION-G2, which can accurately and rapidly reconstruct molecular bonding directly from experimental nuclear magnetic resonance (NMR) spectroscopic information. It comprises three interconnected stages: a one-shot model that predicts bond connectivity between atoms; a structure-correction stage that corrects the predicted structures by removing uncertain bonds and iteratively reassigning them; noise-augmented multi-shot prediction, generating an ensemble of candidate structures, which are ranked to identify the best-fit structure. By integrating a range of $^{1}$H and $^{13}$C NMR data, including two-dimensional (2D) experiments such as COSY, HSQC, and HMBC, the inverse-IMPRESSION platform correctly identifies the structures of 77.8% of molecules with up to 30 heavy atoms (H, C, N, O and F) using simulated NMR data, and 10 of 19 (53%) molecules using experimental NMR data. The experimental structures solved have molecular weights of up to 480 Da and are representative of the complex structures in synthetic and natural products that routinely challenge chemists. The inverse-IMPRESSION framework thus provides the first effective approach for automated molecular structure elucidation using graph-based machine learning on experimental data. --- ### A Production-Oriented Framework for Evaluation of SFX Generation Authors: Mélodie Desbos, Yara Bahram, Eric Granger, Mohammadhadi Shateri Published: 2026-07-10 Categories: cs.SD, cs.AI, eess.AS, eess.SP, eess.SY arXiv: https://arxiv.org/abs/2607.09973v1 Industrial sound design requires audio generation systems that not only produce realistic audio, but also preserve the perceptual identity of a reference, support controllable variation, and remain efficient for practical workflows. Existing evaluations are usually tied to text-to-audio (TTA), unconditional, or task-specific settings, limiting assessment for reference-guided sound effects (SFX) variation. To address this gap, we present a production-oriented evaluation framework for structured comparison of heterogeneous audio generation and editing methods. Our framework identifies nine production requirements and explicitly accounts for differences in model capabilities, enabling comparison under a common production objective. A two-stage protocol is introduced: (1) a reference-guided audio-to-audio (ATA) variation task, in which all methods are evaluated under the same ESC-50 SFX adaptation setup, and (2) capability-specific analyses of native operations such as SFX morphing, temporal and energy alignment, inpainting, and targeted editing. This framework combines objective metrics (including FAD, ImageBind-based reference alignment, and diversity across generated variants), together with a human study of perceptual identity preservation and transient diagnosis. Our study reveals complementary strengths and trade-offs across baselines for different production needs. Among the full-generation baselines evaluated under a shared ATA setting, AudioX provides the strongest overall trade-off between reference alignment and diversity while still supporting SFX morphing. Other baselines remain most suitable for specific editing operations. Our framework establishes a structured evaluation and decision protocol for reference-guided SFX variation and provides a practical basis for designing future unified industrial audio generation pipelines. Audio demos are on the accompanying web page. --- ### TopoExplore: Homology as an Exploration Signal Authors: Jason Carlson Published: 2026-07-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.09971v2 Exploration signals in reinforcement learning are currently computed from what an agent has seen: visitation counts, density estimates, or a model's prediction error at individual states. None of these report the holes in the visitation space. To capture them, we compute the persistent homology of the agent's own archive of visited states during exploration and turn each detected class (an enclosed region the archive surrounds but has not entered) into a selection bonus concentrated on the archived states from which entry is possible, gated by an attempt counter that retires candidate entrances and prunes sealed structures. The method, TopoExplore, is Go-Explore plus one additive term, so the comparison with Go-Explore isolates that term. On the 189 held-out worlds of the open-source TopoGym benchmark of topologically varied hard-exploration environments, TopoExplore finds the goal in 167 worlds against 152 for Go-Explore and, where both find it, with a median 126k steps against 186k. On an environment that stress-tests far-apart chambers that create holes in the archive space, TopoExplore enters all six or eight chambers across 5 seeds, against 1 and 2 of 5 seeds for Go-Explore. On Montezuma's Revenge, built over the room graph, the term helps whenever the archive surrounds a room it has not entered, puts 33-45% of the selections on the surrounding rooms while it is active, and enters the room sooner in five of six cases; such enclosures are rare on this game, so the score is unchanged. Beyond discrete, restorable state spaces, the same signal drives an embodied explorer that walks to every target it selects and explores from depth alone; a vision-language-action navigation policy fine-tuned on its trajectories succeeds 58% more often on unseen scenes than one fine-tuned on shortest-path oracle demonstrations. --- ### TopoExplore: Topological Discrimination for Archive-Based Exploration Authors: Jason Carlson Published: 2026-07-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.09971v1 Archive-based exploration methods such as Go-Explore select which visited state to return to using visitation rarity, and frontier methods return to the boundary of the unknown; neither asks whether the unexplored region behind a boundary is enterable at all. Exploration is not just about finding reward - it is about collecting a structurally complete experience for downstream learning and planning. We introduce TopoExplore, which augments Go-Explore cell selection with a periodic topological pass: enclosed unexplored regions (voids) of the visited-set occupancy grid are detected by flood fill (the H1 classes of its cubical complex), and a decaying selection bonus is placed only on their strict entrances (gap or door cells), so sealed regions are never targeted and entered regions retire. On a controlled 18-environment MiniGrid suite (15 seeds, frozen hyperparameters) TopoExplore attains a 1.52x geometric-mean speedup in median steps-to-first-entry over its exact Go-Explore ablation, versus 1.37x for a frontier baseline; frontier exploration degrades when sealed decoy structure appears (0.83-1.48x on decoy environments vs. 1.65-2.11x for TopoExplore), while TopoExplore holds its largest win on hard multi-interaction doors (10.9x). We report an honest negative on Montezuma's Revenge - without wall knowledge, unreachable occupancy artifacts capture the bonus and performance degrades as it grows, isolating the wall-aware entrance test as the load-bearing component - and a preliminary positive on HM3D scanned buildings, where the speedup over Go-Explore tracks scene difficulty (r=0.69) even as frontier selection dominates blanket coverage. The evidence supports a deliberately scoped claim: topology-aware selection pays off where enclosed structure must be discriminated, and remains competitive at open coverage, where frontier methods are strongest, despite not being tuned for that regime. --- ### Learning in Curved Weight Space:Exponential-Linear Weight Reparameterization for Improved Optimization Authors: Ethan Smith Published: 2026-07-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.09967v3 Many neural networks operations have a multiplicative nature rather than additive: halving or doubling a norm are analogous relatively but require unequal optimization distances when taking linear steps. Adaptive optimizers such as Adam normalize updates per coordinate, but update steps remain additive; weights with very different magnitudes receive similarly sized absolute changes, producing very different relative perturbations. We introduce \textbf{\method} (\textbf{\methodshort}), a weight reparameterization for neural networks that combines a sign-aware symmetric-exponential pathway with an identity-like linear pathway. The symmetric-exponential pathway is near-linear for small raw weights but increasingly curved at larger magnitudes. Additive updates in logarithmic space map to magnitude-proportional changes in effective weight space. The linear pathway provides a direct route through the transform that we hypothesize stabilizes optimization, while learnable scale, curvature, and offset parameters control balance between pathways and the curvature of the exponential pathway. These components create a curved parameter-space geometry that empirically improves speed of loss descent over standard linear parameterization. We also identify a useful \emph{mismatched initialization}: raw weights are chosen so a symmetric version of the transform matches Xavier statistics, but training uses an asymmetric forward transform that leaves positive weights at full strength while making negative weights smaller in magnitude; in small-model ablations, this improves early optimization and may act as a form of symmetry breaking. We train transformers on OpenWebText over nine width$\times$depth configurations, \methodshort reaches matched validation loss in 1.32--1.49$\times$ fewer training steps, with the largest widths seeing the biggest gains. --- ### Learning in Curved Weight Space:Exponential-Linear Weight Reparameterization for Improved Optimization Authors: Ethan Smith Published: 2026-07-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.09967v2 Many neural networks operations have a multiplicative nature rather than additive: halving or doubling a norm are analogous relatively but require unequal optimization distances when taking linear steps. Adaptive optimizers such as Adam normalize updates per coordinate, but update steps remain additive; weights with very different magnitudes receive similarly sized absolute changes, producing very different relative perturbations. We introduce \textbf{\method} (\textbf{\methodshort}), a weight reparameterization for neural networks that combines a sign-aware symmetric-exponential pathway with an identity-like linear pathway. The symmetric-exponential pathway is near-linear for small raw weights but increasingly curved at larger magnitudes. Additive updates in logarithmic space map to magnitude-proportional changes in effective weight space. The linear pathway provides a direct route through the transform that we hypothesize stabilizes optimization, while learnable scale, curvature, and offset parameters control balance between pathways and the curvature of the exponential pathway. These components create a curved parameter-space geometry that empirically improves speed of loss descent over standard linear parameterization. We also identify a useful \emph{mismatched initialization}: raw weights are chosen so a symmetric version of the transform matches Xavier statistics, but training uses an asymmetric forward transform that leaves positive weights at full strength while making negative weights smaller in magnitude; in small-model ablations, this improves early optimization and may act as a form of symmetry breaking. We train transformers on OpenWebText over nine width$\times$depth configurations, \methodshort reaches matched validation loss in 1.32--1.49$\times$ fewer training steps, with the largest widths seeing the biggest gains. --- ### Workload-Driven Optimization for On-Device Real-Time Subtitle Translation Authors: Tsz-To Wong Published: 2026-07-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.09957v2 This report studies on-device English-to-Traditional-Chinese subtitle translation for Taiwan under short inputs, short outputs, batch-size-one inference, low latency, and privacy constraints. These conditions limit the value of optimizations designed for long-context or high-throughput language-model serving. Starting from LMT-60-0.6B, preliminary profiling suggests that vocabulary projection becomes a more important decode-time cost after GGUF quantization reduces the relative cost of Transformer blocks. We replace the original 151k-token vocabulary with a 64k-token subtitle-domain tokenizer, migrate the embedding space, and adapt the model through embedding calibration followed by full supervised fine-tuning. On an OpenSubtitles2024 test set, LocalSubs achieves a 59.2% tie-excluded win rate against Google Translate under GPT-4o pairwise judging. Performance is strongest on short cues and declines as cue length increases. In a separate preliminary Apple M2 Metal profiling run, LocalSubs shows a 1.63x speedup over a 151k-vocabulary baseline. The code is available on https://github.com/aiden1020/localsubs . --- ### Optimizing ARDL Models for Retail Sales Forecasting and Fair Pricing Authors: Sujay Uday Rittikar Published: 2026-07-10 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2607.09956v1 Pricing food products to balance profitability with consumer welfare is a central challenge for retailers. Dynamic pricing is widely used to maximize revenue, yet most pricing models optimize business objectives while overlooking consumer fairness. This paper studies the risk of consumer exploitation under dynamic food pricing in Canada and proposes a methodology that embeds fairness constraints directly into retail sales forecasting. We model total retail trade sales with a log--log Autoregressive Distributed Lag (ARDL) specification, in which the coefficient on a product price is a sales elasticity, and pose the pricing problem as maximizing forecast sales subject to price bounds anchored to the Consumer Price Index (CPI). We solve this problem with both Linear Programming (LP) and Simulated Annealing (SA), under single-product and multi-product configurations. A key finding is that the fitted nominal elasticities are positive. As a result, an unconstrained sales-maximizer would push every price to its upper bound, and the CPI ceiling is the safeguard that prevents this. Simulated Annealing instead settles on conservative, interior prices that lower consumer cost while still meeting the sales target. We benchmark forecast accuracy against naive, seasonal-naive, ARIMA, and SARIMA baselines, and a CPI-deflated re-specification shows that the positive nominal elasticities are largely an inflation-driven artifact. The result is a transparent, fairness-aware pricing framework. --- ### A Foundation Model for Multimodal Event Sequences in Financial Applications Authors: Nikita Rusakov, Vladislav Meshkov, Konstantin Zorin, Gleb Zaripov, Alexander Uglov, Alexey Vasilev, Anton Klenitskiy Published: 2026-07-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.09955v1 Predictive modeling is a core component of modern financial services, where a wide range of tasks are traditionally addressed using separate models trained on manually engineered tabular features. This task-specific approach limits reuse and makes it difficult to fully exploit heterogeneous data sources such as transaction histories and digital interaction signals. In this paper, we present an approach based on pretraining a foundation transformer model on multimodal sequences of user events. Events from multiple data sources are unified into a single chronological sequence, enabling early fusion of heterogeneous modalities and learning of general-purpose representations via a next-event prediction objective. These representations are combined with existing engineered user features, on top of which lightweight neural models are trained for multiple downstream tasks. The proposed system outperforms traditional task-specific models while reducing development overhead. The approach was deployed in production at one of the biggest banks in Eastern Europe, resulting in measurable improvements in business metrics. --- ### A Knowledge-Based Multi-Agent Framework for Security Control Recommendation Authors: Carolina Fernández-Martínez, Shuaib Siddiqui, Vanesa Daza Published: 2026-07-10 Categories: cs.GT, cs.AI, cs.CR, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2607.09954v1 Hardening IT on-premises environments can be a daunting task for teams without access to adequate cybersecurity expertise. In this regard, Decision Support Systems (DSS) with embedded expert knowledge can assist users by guiding them with security recommendations to meet their objectives. This work proposes a Security DSS that recommends security control sub-families given minimal user requirements indicating coverage of different security dimensions. It leverages a curated, unified dataset from both well-known Information Security (InfoSec) and academic sources. This DSS is defined as a non-zero-sum, simultaneous game that is grounded in a Multi-Agent Influence Diagram (MAID) model and explores the decision space over 7 security dimensions or agents, using no-regret online learning to ultimately find the security control sub-families that best fit the requirements while incurring minimal under- and over-provisioning of security resources. This work was validated in terms of performance and accuracy, among others, for varying dataset sizes. It shows exceptional satisfaction coverage results of 99% when using as little as ~65% of the SW-implementable security controls, running in 1.2-35.7 seconds; and more moderate coverage results of 73%-77% when using ~29% of the controls, resolving in 0.8-13.8 seconds. --- ### Artificial Intelligence Across the Cardiac Amyloidosis Diagnostic and Management Pathway: From Single-Modality Detection to Multimodal Clinical Integration Authors: Diana Shadibaeva, Rochak Dhakal, Kui Zhang, Diana Paez, Xiaofeng Yang, Saurabh Malhotra, Weihua Zhou Published: 2026-07-10 Categories: physics.med-ph, cs.LG arXiv: https://arxiv.org/abs/2607.09948v2 Cardiac amyloidosis (CA) is increasingly recognized but remains substantially underdiagnosed because its clinical and imaging phenotype overlaps with more common cardiomyopathies. Definitive subtype assignment and management further require integration of multimodal evidence to distinguish transthyretin from light-chain disease. Machine learning and deep learning have been applied across the diagnostic and management pathway. These applications span electrocardiography (ECG), echocardiography, and health record-based case finding, as well as cardiac magnetic resonance (CMR) and nuclear interpretation, including single-photon emission computed tomography/computed tomography (SPECT/CT) biomarker quantification, prognostic modeling, and treatment response assessment. This narrative review synthesizes these studies by clinical tasks, namely screening, detection, quantification, prognosis, and longitudinal assessment after treatment initiation, rather than by input modality. This task-based organization clarifies why apparently similar AI models require different cohorts, reference standards, evaluation metrics, and implementation thresholds. The evidence reveals a maturity gradient. Binary detection and AI-assisted interpretation of cardiac scintigraphy with bone-avid tracers and SPECT/CT currently represent one of the more mature AI applications in cardiac amyloidosis, supporting standardized image interpretation and quantitative biomarker extraction. However, patient-level diagnosis still requires integration with monoclonal protein testing, SPECT/CT localization, clinical context, and biopsy or tissue typing when indicated. --- ### Artificial Intelligence Across the Cardiac Amyloidosis Diagnostic Pathway: From Single-Modality Detection to Multimodal Clinical Integration Authors: Diana Shadibaeva, Rochak Dhakal, Kui Zhang, Xiaofeng Yang, Saurabh Malhotra, Weihua Zhou Published: 2026-07-10 Categories: physics.med-ph, cs.LG arXiv: https://arxiv.org/abs/2607.09948v1 Cardiac amyloidosis (CA) is increasingly recognized but remains substantially underdiagnosed, because its clinical and imaging phenotype overlaps with more common cardiomyopathies. Definitive subtype assignment and management further require integration of multimodal evidence to distinguish transthyretin from light chain disease. Machine learning and deep learning have been applied across the diagnostic and management pathway. These applications span ECG, echocardiography, and health record-based case finding, as well as CMR and nuclear interpretation, including SPECT/CT biomarker quantification, prognostic modeling, and treatment response assessment. This narrative review synthesizes these studies by clinical tasks, namely screening, detection, quantification, prognosis, and treatment response monitoring, rather than by input modality. This task-based organization clarifies why apparently similar AI models require different cohorts, reference standards, evaluation metrics, and implementation thresholds. The evidence reveals a maturity gradient. Binary detection and AI assisted quantification on bone scintigraphy and SPECT/CT are closest to clinical translation. Detection is supported by large externally validated cohorts, and quantification by interpretable, outcome linked measurement of myocardial tracer burden. By contrast, subtype aware classification, prognostic risk stratification, and treatment response monitoring remain at an early stage. These tasks are limited by small cohorts, enriched retrospective designs, heterogeneous labels, incomplete external validation, and uncertain calibration in realistic prevalence settings. Across tasks, high discrimination alone is insufficient. --- ### SMETA-ZSL:Semantic Meta-Alignment for Zero-Shot Threat Classification Authors: Ivan Alejandro Montoya Sanchez, Anantaa Kotal, Aritran Piplai Published: 2026-07-10 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2607.09936v1 Cybersecurity systems must adapt rapidly to emerging threats. However, labeled data for new threat categories is unavailable when those threats first appear. Generalized zero-shot learning offers a natural solution by enabling recognition of unseen classes through auxiliary semantic knowledge rather than labeled examples. Large language models are particularly promising in this setting because they can convert unstructured CTI reports into semantic prototypes for emerging threats. However, applying language-driven zero-shot learning to cybersecurity is difficult due to strong semantic overlap between threat descriptions, heterogeneity between behavioral attributes and text, severe class imbalance, and open-set conditions where unseen threats are unknown during training. We propose SMETA-ZSL, that learns semantic prototypes from overlapping language descriptions through contrastive finetuning, aligns behavioral features through episodic meta-learning and knowledge distillation, and performs adaptive routing for generalization across seen-unseen classes. Across 7 benchmarks, SMETA-ZSL delivers the strongest overall generalized zero-shot performance under the strictest inductive setting, surpassing prior methods by 10.8 points on average, with gains up to 18.1 points. Github:https://github.com/Security-And-Intelligence-Lab-UTEP/SMETA-ZSL --- ### Faithful by Design: Evaluating and Improving LLM-Generated Clinical Trial Summaries for Multi-Stakeholder Audiences Authors: Robert Williams Published: 2026-07-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.09932v1 Large language models are increasingly used to summarize clinical trial results for healthcare providers, patients, and payers, but their tendency to hallucinate poses significant risks in this high-stakes context. This study introduces a benchmark evaluation framework for measuring the faithfulness of LLM-generated clinical trial summaries across three stakeholder audiences. The framework consists of 200 stratified trials drawn from the Aggregate Analysis of ClinicalTrials.gov database, evaluated using audience-specific prompt templates and a six-dimension faithfulness annotation schema. Baseline measurements were established for GPT-4o, Claude Sonnet 4.6, and Gemini 2.5 Flash across 1,800 generated summaries scored using a cross-encoder natural language inference (NLI) model. Unsupported Claims was identified as the dominant failure mode across all three models, with a mean annotation score of 1.55 out of three. A knowledge-graph-augmented retrieval system was developed and evaluated against the baseline, producing statistically significant improvements in NLI-based faithfulness scores (entailment +0.0125, faithfulness +0.0130, p < 0.0001). Improvement pathways were model-dependent, with GPT-4o improving primarily through contradiction reduction while Claude Sonnet 4.6 and Gemini 2.5 Flash improved through increased entailment. --- ### Banshee: Target Switch Attacks on Gimbal-Stabilized Visual Tracking Systems via Acoustic Injection Authors: Jiarui Li, Joseph Brewington, Qingzhao Zhang, Z. Morley Mao Published: 2026-07-10 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2607.09930v1 Gimbal-stabilized visual tracking is critical for modern autonomous systems such as Unmanned Aerial Vehicles (UAVs). While prior work shows acoustic signals can disturb gimbal internals, the impact of such attacks on real-world applications like UAV tracking and following remains underexplored. Existing demonstrations largely overlook practical challenges for real-world attacks, such as object-motion uncertainty and runtime latency. To bridge this gap, we present Banshee, the first physically realizable attack that induces target switching in UAV visual tracking systems by exploiting acoustic vulnerabilities in gimbal-camera systems. Banshee generates carefully crafted acoustic waveforms that induce optimized adversarial gimbal oscillations, causing directionally biased camera-view drifts that break inter-frame target associations. Consequently, the onboard tracker is driven to switch from the original target to an attacker-selected object with high probability, with occasional target loss. Banshee achieves a 93.6% success rate in simulation across two commercial gimbal systems and five trackers. Real-world benchtop and in-flight black-box attacks against a commercial drone across varied scenarios show an overall 95.5% attack success rate. Our results reveal a practical cross-domain vulnerability between acoustics and vision, highlighting the need for robust designs of gimbal systems and applications. Our code is available at: https://github.com/U1ltra/Banshee. --- ### Global Merger-Arbitrage Forecasting with Language Models Authors: Hinal Jajal, Michal Mucha, Charles Sweat, Chris Pulman, Charlie Flanagan, Peter Anderson Published: 2026-07-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.09921v1 We present a language-model forecasting system for merger arbitrage, a specialized high-stakes financial setting in which the task is to predict the outcome of announced M\&A deals. Unlike prior work on judgmental forecasting with LLMs, which has focused on broad mixed-topic benchmarks and short context such as news snippets, we study a setting that requires long-context reasoning over hundreds of pages of technical documents. Our system combines expert-guided context engineering with finetuning on hindsight-guided reasoning traces derived from historical deals. Given an announced deal, it outputs a probability distribution over three mutually exclusive outcomes: closing at announced terms, a higher bid, or deal termination. On an out-of-sample set of more than 400 large deals spanning 42 countries, our finetuned system achieves the best performance of any method we evaluate, reducing class-balanced Brier score to 0.151. This is 24\% below calibrated market-implied probabilities, 19\% below XGBoost, and 25-42\% below frontier language models. These results, together with ablation studies, show that LLM-based forecasting can succeed in specialized, long-context financial workflows, with hindsight-based supervision and expert-designed context playing a critical role. --- ### Learning Partition Trees for Nearest Neighbor Search Authors: Sanjeev Khanna, Ashwin Padaki, Erik Waingarten Published: 2026-07-10 Categories: cs.DS, cs.LG arXiv: https://arxiv.org/abs/2607.09909v1 We study nearest neighbor search from the perspective of data-driven algorithm design: given a dataset $P \subset \mathbb{R}^d$ of size $n$ and sample access to a query distribution over $\mathbb{R}^d$, the goal is to learn a data structure optimized for queries drawn from that specific distribution. We focus on the class of balanced halfspace trees, which naturally abstracts space-partitioning frameworks like locality-sensitive hashing. Assuming Gaussian-like marginal conditions on the dataset and query distribution, we give an efficient algorithm that learns a tree achieving $o(nd)$ query time, provided that a perfect tree exists. At the core of our algorithmic approach is the balanced halfspace cut problem, where we are given a distribution over $\mathbb{R}^d \times \mathbb{R}^d$ and must find a balanced halfspace that minimizes the fraction of cut pairs. We prove that without distributional assumptions, finding the optimal balanced halfspace is NP-hard. To circumvent this computational barrier, we design an efficient improper learning algorithm: if the optimal halfspace cuts an $α$ fraction of pairs, our algorithm outputs a balanced polynomial threshold function of degree $\tilde{O}(1/\varepsilon^2)$ that cuts at most an $O(\sqrt{α+\varepsilon})$ fraction. --- ### RouteRec: Strict Evaluation of Recommender-Agent Selection and Aggregation Authors: Kaiji Zhou, Vladimir Kalmykov, Yue Feng Published: 2026-07-10 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2607.09908v1 Recommender systems increasingly face a choice among heterogeneous agents -- collaborative filters, sequential models, content-based retrievers, and LLM-based rerankers -- yet no single agent is uniformly best. We study this choice as task-aware agent ranking under cost constraints using RouteRec, a framework that compares request-level hard selection with item-level learned aggregation over four traditional recommender agents and one LLM reranker agent. On MovieLens-1M, the full quality oracle has substantial headroom (HR@10 = 0.584), confirming that useful cross-agent signal exists. Under a leakage-free 5-fold out-of-fold protocol, however, hard selection remains below BM25 (0.223 vs. 0.254), and selective LLM escalation does not improve it. The same protocol yields a different outcome for learned aggregation: its cheap-only variant matches BM25 in HR and has a higher NDCG point estimate (0.123 vs. 0.114), while gated all-agent aggregation reaches HR@10 = 0.295 with 70.2\% LLM calls. The resulting lesson is not that routing is solved, but that request-level selection of one complete agent list is too coarse for this sparse fixed-candidate setting; item-level aggregation is the more promising action space. --- ### Depth-Efficient Quantum Topological Data Analysis for Regime-Specific Detection of Financial Stress Authors: Arul Rhik Mazumder, Shreyan Ronit Mazumder Published: 2026-07-10 Categories: quant-ph, cs.LG, q-fin.ST arXiv: https://arxiv.org/abs/2607.09906v1 We present, to our knowledge, the first adaptation of Pauli Correlation Encoding (PCE) to quantum topological data analysis, reformulating Betti number estimation as a depth-efficient variational optimization over a compressed qubit register. From a Takens embedding and Vietoris--Rips filtration of S&P~500 returns, we extract combinatorial Laplacians and recast null-space counting as a continuous-PCE Rayleigh-quotient minimization with variational deflation, encoding $n_k$ simplex indices into $O(n_k^{1/κ})$ qubits with shallow, ancilla-free circuits. Because the resulting loss is rational rather than bilinear in the correlators, the barren-plateau bound of~\cite{Sciorilli25} does not transfer; empirically the gradient variance decays only polynomially, with no exponential barren plateau, over $n=4$--$12$ qubits. The classical stage matches ripser~\cite{bauer2021ripser} on all 190 sliding windows (2007-2009). On the real market Laplacians ($β_1=1$--$22$), warm-starting from a classical null-space surrogate allows PCE-VQE to recover $β_1$ exactly at every scale, placing the obstacle in the optimisation landscape rather than the encoding. Chronologically split classification gives in-regime ROC AUC $0.818$, but out-of-distribution evaluation on the 2020 COVID shock and 2022 rate cycle (AUC $0.009$, $0.515$) shows the calibration does not generalize across crisis regimes. ---