# Research Papers — 2026-04 · bundle page 132 of 233 > Full-text markdown of papers #6551–6600 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/132 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/131.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/133.md) ### Simpler Logarithmic Approximation Algorithms for the Optimal Decision Tree and Adaptive Set Cover Authors: Michał Szyfelbein Published: 2026-04-13 Categories: cs.DS, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2604.12036v3 We study a well-known task of constructing a decision tree identifying an unknown hypothesis from a given ground set of hypotheses under both the average- and worst-case cost. The Optimal Decision Tree problem has been extensively studied in the literature and $\mathcal{O}(\log n)$-approximation guarantees are known for both cost criteria (here $n$ is the number of hypotheses). Although the algorithms achieving this approximation ratio are usually relatively simple, their analysis often turns out to be quite technical. Hereby, we show a new algorithm with a simplified analysis which simultaneously achieves an $\mathcal{O}(\log n)$-approximation for both cost criteria. Moreover, the leading constant under the $\mathcal{O}$-notation in the approximation ratio is relatively small, below $3.65$ for the worst-case cost and twice as much for the average-case cost, assuming base $2$ logarithm. Our algorithm for the Optimal Decision Tree behaves greedily with respect to the hereby introduced Separating Subfamily problem which asks for the cheapest subfamily of tests which partitions the hypotheses into pieces of small enough size. We show that the Separating Subfamily can itself be reduced to an instance of the well-known Maximum Coverage problem. At the core of our approach lies exploiting properties of cutting a clique into small pieces, where edges represent pairs of hypotheses to be separated. As an application of our result we also provide an $\mathcal{O}(\log (k\cdot n))$-approximation for the Adaptive Set Cover problem, where $k$ is the number of possible realizations. --- ### Constant-Factor Approximation for the Uniform Decision Tree Authors: Michał Szyfelbein Published: 2026-04-13 Categories: cs.DS, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2604.12036v2 We resolve a long-standing open question, about the existence of a constant-factor approximation algorithm for the average-case \textsc{Decision Tree} problem with uniform probability distribution over the hypotheses. We answer the question in the affirmative by providing a simple polynomial-time algorithm with approximation ratio of $\frac{2}{1-\sqrt{(e+1)/(2e)}}+ε<11.57$. This improves upon the currently best-known, greedy algorithm which achieves $O(\log n/{\log\log n})$-approximation. The first key ingredient in our analysis is the usage of a decomposition technique known from problems related to \textsc{Hierarchical Clustering} (SODA '17, WALCOM '26), which allows us to decompose the optimal decision tree into a series of objects called separating subfamilies. The second crucial idea is to reduce the subproblem of finding a \textsc{Separating Subfamily} to an instance of the \textsc{Maximum Coverage} problem. To do so, we analyze the properties of cutting cliques into small pieces, which represent pairs of hypotheses to be separated. This allows us to obtain a good approximation for the \textsc{Separating Subfamily} problem, which then enables the design of the approximation algorithm for the original problem. --- ### When Does Visual Token Pruning Improve Calibration? The Role of Evidence Coverage in MLLMs Authors: Kaizhen Tan, Yang Feng, Heqing Du, Hanzhe Hong, Siru Tao, Xin Xu Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.12035v3 Visual token pruning is widely used to reduce the inference cost of multimodal large language models (MLLMs), but it is usually evaluated only by accuracy. We study how pruning affects calibration, defined as the agreement between confidence and correctness, and show that the selection rule matters more than the token budget alone. On POPE with LLaVA-1.5, coverage-based pruning from 576 to 128 tokens reduces expected calibration error from 0.041 to 0.016 without a statistically significant accuracy loss. In contrast, attention-based selection preserves confidence while accuracy deteriorates, becoming less calibrated than random pruning at aggressive budgets. Across pruning conditions, kept-set coverage is strongly associated with accuracy (Spearman $ρ=+0.89$) but not with mean confidence ($ρ=-0.03$), producing a strong inverse relation with overconfidence ($ρ=-0.92$); controlled kept-set interventions support this evidence-coverage account. Two boundaries limit it: query-conditioned FastV is more overconfident than its coverage predicts, and on language-prior-dominated ScienceQA, coverage ceases to order calibration. The selector ordering otherwise generalizes to GQA and LLaVA-NeXT, and coverage beats random on Qwen2-VL, although the calibration gain over the unpruned model is task- and model-dependent. We also identify an evaluation pitfall in FastV: zeroing rather than removing pruned tokens can reduce accuracy to chance. Visual token pruning therefore changes confidence quality as well as efficiency, and calibration should be evaluated alongside accuracy when comparing pruning methods. --- ### Memory as Metabolism: A Design for Companion Knowledge Systems Authors: Stefan Miteski Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.12034v1 Retrieval-Augmented Generation remains the dominant pattern for giving LLMs persistent memory, but a visible cluster of personal wiki-style memory architectures emerged in April 2026 -- design proposals from Karpathy, MemPalace, and LLM Wiki v2 that compile knowledge into an interlinked artifact for long-term use by a single user. They sit alongside production memory systems that the major labs have shipped for over a year, and an active academic lineage including MemGPT, Generative Agents, Mem0, Zep, A-Mem, MemMachine, SleepGate, and Second Me. Within a 2026 landscape of emerging governance frameworks for agent context and memory -- including Context Cartography and MemOS -- this paper proposes a companion-specific governance profile: a set of normative obligations, a time-structured procedural rule, and testable conformance invariants for the specific failure mode of entrenchment under user-coupled drift in single-user knowledge wikis built on the LLM wiki pattern. The design principle is that personal LLM memory is a companion system: its job is to mirror the user on operational dimensions (working vocabulary, load-bearing structure, continuity of context) and compensate on epistemic failure modes (entrenchment, suppression of contradicting evidence, Kuhnian ossification). Five operations implement this split -- TRIAGE, DECAY, CONTEXTUALIZE, CONSOLIDATE, AUDIT -- supported by memory gravity and minority-hypothesis retention. The sharpest prediction: accumulated contradictory evidence should have a structural path to updating a centrality-protected dominant interpretation through multi-cycle buffer pressure accumulation, a failure mode no existing benchmark captures. The safety story at the single-agent level is partial, and the paper is explicit about what it does and does not solve. --- ### Benchmarking Deflection and Hallucination in Large Vision-Language Models Authors: Nicholas Moratelli, Christopher Davis, Leonardo F. R. Ribeiro, Bill Byrne, Gonzalo Iglesias Published: 2026-04-13 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.12033v1 Large Vision-Language Models (LVLMs) increasingly rely on retrieval to answer knowledge-intensive multimodal questions. Existing benchmarks overlook conflicts between visual and textual evidence and the importance of generating deflections (e.g., Sorry, I cannot answer...) when retrieved knowledge is incomplete. These benchmarks also suffer from rapid obsolescence, as growing LVLM training sets allow models to answer many questions without retrieval. We address these gaps with three contributions. First, we propose a dynamic data curation pipeline that preserves benchmark difficulty over time by filtering for genuinely retrieval-dependent samples. Second, we introduce VLM-DeflectionBench, a benchmark of 2,775 samples spanning diverse multimodal retrieval settings, designed to probe model behaviour under conflicting or insufficient evidence. Third, we define a fine-grained evaluation protocol with four scenarios that disentangle parametric memorization from retrieval robustness. Experiments across 20 state-of-the-art LVLMs indicate that models usually fail to deflect in the presence of noisy or misleading evidence. Our results highlight the need to evaluate not only what models know, but how they behave when they do not, and serve as a reusable and extensible benchmark for reliable KB-VQA evaluation. All resources will be publicly available upon publication. --- ### Curvelet-Based Frequency-Aware Feature Enhancement for Deepfake Detection Authors: Salar Adel Sabri, Ramadhan J. Mstafa Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.12028v1 The proliferation of sophisticated generative models has significantly advanced the realism of synthetic facial content, known as deepfakes, raising serious concerns about digital trust. Although modern deep learning-based detectors perform well, many rely on spatial-domain features that degrade under compression. This limitation has prompted a shift toward integrating frequency-domain representations with deep learning to improve robustness. Prior research has explored frequency transforms such as Discrete Cosine Transform (DCT), Fast Fourier Transform (FFT), and Wavelet Transform, among others. However, to the best of our knowledge, the Curvelet Transform, despite its superior directional and multiscale properties, remains entirely unexplored in the context of deepfake detection. In this work, we introduce a novel Curvelet-based detection approach that enhances feature quality through wedge-level attention and scale-aware spatial masking, both trained to selectively emphasize discriminative frequency components. The refined frequency cues are reconstructed and passed to a modified pretrained Xception network for classification. Evaluated on two compression qualities in the challenging FaceForensics++ dataset, our method achieves 98.48% accuracy and 99.96% AUC on FF++ low compression, while maintaining strong performance under high compression, demonstrating the efficacy and interpretability of Curvelet-informed forgery detection. --- ### TriFit: Trimodal Fusion with Protein Dynamics for Mutation Fitness Prediction Authors: Seungik Cho Published: 2026-04-13 Categories: cs.LG, q-bio.BM, q-bio.QM arXiv: https://arxiv.org/abs/2604.12026v1 Predicting the functional impact of single amino acid substitutions (SAVs) is central to understanding genetic disease and engineering therapeutic proteins. While protein language models and structure-based methods have achieved strong performance on this task, they systematically neglect protein dynamics; residue flexibility, correlated motions, and allosteric coupling are well-established determinants of mutational tolerance in structural biology, yet have not been incorporated into supervised variant effect predictors. We present TriFit, a multimodal framework that integrates sequence, structure, and protein dynamics through a four-expert Mixture-of-Experts (MoE) fusion module with trimodal cross-modal contrastive learning. Sequence embeddings are extracted via masked marginal scoring with ESM-2 (650M); structural embeddings from AlphaFold2-predicted C-alpha geometries; and dynamics embeddings from Gaussian Network Model (GNM) B-factors, mode shapes, and residue-residue cross-correlations. The MoE router adaptively weights modality combinations conditioned on the input, enabling protein-specific fusion without fixed modality assumptions. On the ProteinGym substitution benchmark (217 DMS assays, 696k SAVs), TriFit achieves AUROC 0.897 +/- 0.0002, outperforming all supervised baselines including Kermut (0.864) and ProteinNPT (0.844), and the best zero-shot model ESM3 (0.769). Ablation studies confirm that dynamics provides the largest marginal contribution over pairwise modality combinations, and TriFit achieves well-calibrated probabilistic outputs (ECE = 0.044) without post-hoc correction. --- ### WiseOWL: A Methodology for Evaluating Ontological Descriptiveness and Semantic Correctness for Ontology Reuse and Ontology Recommendations Authors: Aryan Singh Dalal, Maria Baloch, Asiyah Yu Lin, Anna Maria Masci, Kathleen M. Jagodnik, Hande Kucuk McGinty Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.12025v1 The Semantic Web standardizes concept meaning for humans and machines, enabling machine-operable content and consistent interpretation that improves advanced analytics. Reusing ontologies speeds development and enforces consistency, yet selecting the optimal choice is challenging because authors lack systematic selection criteria and often rely on intuition that is difficult to justify, limiting reuse. To solve this, WiseOWL is proposed, a methodology with scoring and guidance to select ontologies for reuse. It scores four metrics: (i) Well-Described, measuring documentation coverage; (ii) Well-Defined, using state-of-the-art embeddings to assess label-definition alignment; (iii) Connection, capturing structural interconnectedness; and (iv) Hierarchical Breadth, reflecting hierarchical balance. WiseOWL outputs normalized 0-10 scores with actionable feedback. Implemented as a Streamlit app, it ingests OWL format, converts to RDF Turtle, and provides interactive visualizations. Evaluation across six ontologies, including the Plant Ontology (PO), Gene Ontology (GO), Semanticscience Integrated Ontology (SIO), Food Ontology (FoodON), Dublin Core (DC), and GoodRelations, demonstrates promising effectiveness. --- ### Convolutional Maximum Mean Discrepancy for Inference in Noisy Data Authors: Ritwik Vashistha, Jeff M. Phillips, Abhra Sarkar, Arya Farahi Published: 2026-04-13 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2604.12022v1 Modern data analyses frequently encounter settings where samples of variables are contaminated by measurement error. Ignoring measurement noise can substantially degrade statistical inference, while existing correction techniques are often computationally costly and inefficient. Recent advances in kernel methods, particularly those based on Maximum Mean Discrepancy (MMD), have enabled flexible, distribution-free inference, yet typically assume precise data and overlook contamination by measurement error. In this work, we introduce a novel framework for inference with samples corrupted by potentially heteroscedastic noise from a known distribution. Central to our approach is the convolutional MMD (convMMD), which compares distributions after noise convolution and retains metric validity under standard kernel conditions. We establish finite-sample deviation bounds that are unaffected by measurement error and prove an equivalence between testing under noise and kernel smoothing. Leveraging these insights, we introduce a convMMD-based estimator for inference with noisy, heteroscedastic observations. We establish its consistency and asymptotic normality, and provide an efficient implementation using stochastic gradient descent. We demonstrate the practical effectiveness of our approach through simulations and applications in astronomy and social sciences. --- ### A Framework for Longitudinal Health AI Agents Authors: Georgianna Lin, Rencong Jiang, Noémie Elhadad, Xuhai "Orson" Xu Published: 2026-04-13 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.12019v3 Although artificial intelligence (AI) agents are increasingly proposed to support potentially longitudinal health tasks, such as symptom management, behavior change, and patient support, most current implementations fall short of facilitating user intent and fostering accountability. This contrasts with prior work on supporting longitudinal needs, both within and beyond clinical settings, where follow-up, coherent reasoning, and sustained alignment with individuals' goals are critical for both effectiveness and safety. In this paper, we draw on established clinical and personal health informatics frameworks to define what it would mean to orchestrate longitudinal health interactions with AI agents. We propose a multi-layer framework and corresponding agent architecture that operationalizes adaptation, coherence, continuity, and agency across repeated interactions. Through representative use cases, we demonstrate how longitudinal agents can maintain meaningful engagement, adapt to evolving goals, and support safe, personalized decision-making over time. Our findings underscore both the promise and the complexity of designing systems capable of supporting health trajectories beyond isolated interactions, and we offer guidance for future research and development in multi-session, user-centered health AI. --- ### LLMs Struggle with Abstract Meaning Comprehension More Than Expected Authors: Hamoud Alhazmi, Jiachen Jiang Published: 2026-04-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.12018v1 Understanding abstract meanings is crucial for advanced language comprehension. Despite extensive research, abstract words remain challenging due to their non-concrete, high-level semantics. SemEval-2021 Task 4 (ReCAM) evaluates models' ability to interpret abstract concepts by presenting passages with questions and five abstract options in a cloze-style format. Key findings include: (1) Most large language models (LLMs), including GPT-4o, struggle with abstract meaning comprehension under zero-shot, one-shot, and few-shot settings, while fine-tuned models like BERT and RoBERTa perform better. (2) A proposed bidirectional attention classifier, inspired by human cognitive strategies, enhances fine-tuned models by dynamically attending to passages and options. This approach improves accuracy by 4.06 percent on Task 1 and 3.41 percent on Task 2, demonstrating its potential for abstract meaning comprehension. --- ### Identity as Attractor: Geometric Evidence for Persistent Agent Architecture in LLM Activation Space Authors: Vladimir Vasilenko Published: 2026-04-13 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.12016v1 Large language models map semantically related prompts to similar internal representations -- a phenomenon interpretable as attractor-like dynamics. We ask whether the identity document of a persistent cognitive agent (its cognitive_core) exhibits analogous attractor-like behavior. We present a controlled experiment on Llama 3.1 8B Instruct, comparing hidden states of an original cognitive_core (Condition A), seven paraphrases (Condition B), and seven structurally matched controls (Condition C). Mean-pooled states at layers 8, 16, and 24 show that paraphrases converge to a tighter cluster than controls (Cohen's d > 1.88, p < 10^{-27}, Bonferroni-corrected). Replication on Gemma 2 9B confirms cross-architecture generalizability. Ablations suggest the effect is primarily semantic rather than structural, and that structural completeness appears necessary to reach the attractor region. An exploratory experiment shows that reading a scientific description of the agent shifts internal state toward the attractor -- closer than a sham preprint -- distinguishing knowing about an identity from operating as that identity. These results provide representational evidence that agent identity documents induce attractor-like geometry in LLM activation space. --- ### UCS: Estimating Unseen Coverage for Improved In-Context Learning Authors: Jiayi Xin, Xiang Li, Evan Qiang, Weiqing He, Tianqi Shang, Weijie J. Su, Qi Long Published: 2026-04-13 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.12015v1 In-context learning (ICL) performance depends critically on which demonstrations are placed in the prompt, yet most existing selectors prioritize heuristic notions of relevance or diversity and provide limited insight into the coverage of a demonstration set. We propose Unseen Coverage Selection (UKS), a training-free, subset-level coverage prior motivated by the principle that a good demonstration set should expose the model to latent cluster unrevealed by the currently selected subset. UCS operationalizes this idea by (1) inducing discrete latent clusters from model-consistent embeddings and (2) estimating the number of unrevealed clusters within a candidate subset via a Smoothed Good--Turing estimator from its empirical frequency spectrum. Unlike previous selection methods, UCS is coverage-based and training-free, and can be seamlessly combined with both query-dependent and query-independent selection baselines via a simple regularized objective. Experiments on multiple intent-classification and reasoning benchmarks with frontier Large Language Models show that augmenting strong baselines with UCS consistently improves ICL accuracy by up to 2-6% under the same selection budget, while also yielding insights into task- and model-level latent cluster distributions. Code is available at https://github.com/Raina-Xin/UCS. --- ### Sample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-End Authors: Steve Hanneke, Idan Mehalel, Shay Moran Published: 2026-04-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.12013v2 Modern large language models generate text autoregressively, producing tokens one at a time. To study the learnability of such systems, Joshi et al. (COLT 2025) introduced a PAC-learning framework for next-token generators, the primitive underlying autoregressive models. In this framework, an unknown next-token generator maps a sequence of tokens to the next token and is iteratively applied for $T$ steps, producing a chain of tokens whose final token constitutes the model's output. The learning task is to learn the input-output mapping induced by this autoregressive process. Depending on the available supervision, training examples may reveal only the final output (End-to-End supervision) or the entire generated chain (Chain-of-Thought supervision). This raises two natural questions: how the sample complexity depends on the generation length $T$, and how much Chain-of-Thought supervision can reduce this dependence. In this work we give a nearly complete answer to both questions by uncovering a taxonomy of how the sample complexity scales with $T$. For End-to-End learning, we show that the landscape is remarkably rich: subject to mild conditions, essentially any growth rate $r(T)$ between constant and linear can arise as the sample complexity, and combined with the linear upper bound of Joshi et al., this yields an essentially complete characterization. In contrast, under Chain-of-Thought supervision we show that the sample complexity is independent of $T$, demonstrating that access to intermediate reasoning steps can eliminate the dependence on the generation length altogether. Our analysis introduces new combinatorial tools, and as corollaries we resolve several open questions posed by Joshi et al. regarding the dependence of learnability on the generation length and the role of Chain-of-Thought supervision. --- ### TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment Authors: Bingyi Cao, Koert Chen, Kevis-Kokitsi Maninis, Kaifeng Chen, Arjun Karpur, Ye Xia, Sahil Dua, Tanmaya Dabral, Guangxing Han, Bohyung Han, Joshua Ainslie, Alex Bewley et al. Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.12012v1 Recent progress in vision-language pretraining has enabled significant improvements to many downstream computer vision applications, such as classification, retrieval, segmentation and depth prediction. However, a fundamental capability that these models still struggle with is aligning dense patch representations with text embeddings of corresponding concepts. In this work, we investigate this critical issue and propose novel techniques to enhance this capability in foundational vision-language models. First, we reveal that a patch-level distillation procedure significantly boosts dense patch-text alignment -- surprisingly, the patch-text alignment of the distilled student model strongly surpasses that of the teacher model. This observation inspires us to consider modifications to pretraining recipes, leading us to propose iBOT++, an upgrade to the commonly-used iBOT masked image objective, where unmasked tokens also contribute directly to the loss. This dramatically enhances patch-text alignment of pretrained models. Additionally, to improve vision-language pretraining efficiency and effectiveness, we modify the exponential moving average setup in the learning recipe, and introduce a caption sampling strategy to benefit from synthetic captions at different granularities. Combining these components, we develop TIPSv2, a new family of image-text encoder models suitable for a wide range of downstream applications. Through comprehensive experiments on 9 tasks and 20 datasets, we demonstrate strong performance, generally on par with or better than recent vision encoder models. Code and models are released via our project page at https://gdm-tipsv2.github.io/ . --- ### When to Forget: A Memory Governance Primitive Authors: Baris Simsek Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.12007v1 Agent memory systems accumulate experience but currently lack a principled operational metric for memory quality governance -- deciding which memories to trust, suppress, or deprecate as the agent's task distribution shifts. Write-time importance scores are static; dynamic management systems use LLM judgment or structural heuristics rather than outcome feedback. This paper proposes Memory Worth (MW): a two-counter per-memory signal that tracks how often a memory co-occurs with successful versus failed outcomes, providing a lightweight, theoretically grounded foundation for staleness detection, retrieval suppression, and deprecation decisions. We prove that MW converges almost surely to the conditional success probability p+(m) = Pr(y_t = +1 | m in M_t) -- the probability of task success given that memory m is retrieved -- under a stationary retrieval regime with a minimum exploration condition. Importantly, p+(m) is an associational quantity, not a causal one: it measures outcome co-occurrence rather than causal contribution. We argue this is still a useful operational signal for memory governance, and we validate it empirically in a controlled synthetic environment where ground-truth utility is known: after 10,000 episodes, the Spearman rank-correlation between Memory Worth and true utilities reaches rho = 0.89 +/- 0.02 across 20 independent seeds, compared to rho = 0.00 for systems that never update their assessments. A retrieval-realistic micro-experiment with real text and neural embedding retrieval (all-MiniLM-L6-v2) further shows stale memories crossing the low-value threshold (MW = 0.17) while specialist memories remain high-value (MW = 0.77) across 3,000 episodes. The estimator requires only two scalar counters per memory unit and can be added to architectures that already log retrievals and episode outcomes. --- ### BayMOTH: Bayesian optiMizatiOn with meTa-lookahead -- a simple approacH Authors: Rahman Ejaz, Varchas Gopalaswamy, Ricardo Luna, Aarne Lees, Vineet Gundecha, Christopher Kanan, Soumyendu Sarkar, Riccardo Betti Published: 2026-04-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.12005v1 Bayesian optimization (BO) has for sequential optimization of expensive black-box functions demonstrated practicality and effectiveness in many real-world settings. Meta-Bayesian optimization (meta-BO) focuses on improving the sample efficiency of BO by making use of information from related tasks. Although meta-BO is sample-efficient when task structure transfers, poor alignment between meta-training and test tasks can cause suboptimal queries to be suggested during online optimization. To this end, we propose a simple meta-BO algorithm that utilizes related-task information when determined useful, falling back to lookahead otherwise, within a unified framework. We demonstrate competitiveness of our method with existing approaches on function optimization tasks, while retaining strong performance in low task-relatedness regimes where test tasks share limited structure with the meta-training set. --- ### Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision Authors: Yinghui He, Simran Kaur, Adithya Bhaskar, Yongjin Yang, Jiarui Liu, Narutatsu Ri, Liam Fowl, Abhishek Panigrahi, Danqi Chen, Sanjeev Arora Published: 2026-04-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.12002v2 Current post-training methods in verifiable settings fall into two categories. Reinforcement learning (RLVR) relies on binary rewards, which are broadly applicable and powerful, but provide only sparse supervision during training. Distillation provides dense token-level supervision, typically obtained from an external teacher or using high-quality demonstrations. Collecting such supervision can be costly or unavailable. We propose Self-Distillation Zero (SD-Zero), a method that is substantially more training sample-efficient than RL and does not require an external teacher or high-quality demonstrations. SD-Zero trains a single model to play two roles: a Generator, which produces an initial response, and a Reviser, which conditions on that response and its binary reward to produce an improved response. We then perform on-policy self-distillation to distill the reviser into the generator, using the reviser's token distributions conditioned on the generator's response and its reward as supervision. In effect, SD-Zero trains the model to transform binary rewards into dense token-level self-supervision. On math and code reasoning benchmarks with Qwen3-4B-Instruct and Olmo-3-7B-Instruct, SD-Zero improves performance by at least 10% over the base models and outperforms strong baselines, including Rejection Fine-Tuning (RFT), GRPO, and Self-Distillation Fine-Tuning (SDFT), under the same question set and training sample budget. Extensive ablation studies show two novel characteristics of our proposed algorithm: (a) token-level self-localization, where the reviser can identify the key tokens that need to be revised in the generator's response based on reward, and (b) iterative self-evolution, where the improving ability to revise answers can be distilled back into generation performance with regular teacher synchronization. Code: https://github.com/princeton-pli/Self-Distillation-Zero. --- ### The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results Authors: Xingyu Qiu, Yuqian Fu, Jiawei Geng, Bin Ren, Jiancheng Pan, Zongwei Wu, Hao Tang, Yanwei Fu, Radu Timofte, Nicu Sebe, Mohamed Elhoseiny, Lingyi Hong et al. Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.11998v1 Cross-domain few-shot object detection (CD-FSOD) remains a challenging problem for existing object detectors and few-shot learning approaches, particularly when generalizing across distinct domains. As part of NTIRE 2026, we hosted the second CD-FSOD Challenge to systematically evaluate and promote progress in detecting objects in unseen target domains under limited annotation conditions. The challenge received strong community interest, with 128 registered participants and a total of 696 submissions. Among them, 31 teams actively participated, and 19 teams submitted valid final results. Participants explored a wide range of strategies, introducing innovative methods that push the performance frontier under both open-source and closed-source tracks. This report presents a detailed overview of the NTIRE 2026 CD-FSOD Challenge, including a summary of the submitted approaches and an analysis of the final results across all participating teams. Challenge Codes: https://github.com/ohMargin/NTIRE2026_CDFSOD. --- ### Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces Authors: Manas Pathak, Xingyao Chen, Shuozhe Li, Amy Zhang, Liu Leqi Published: 2026-04-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.11996v5 Should we trust Large Language Models (LLMs) with high accuracy? LLMs achieve high accuracy on reasoning benchmarks, but correctness alone does not reveal the quality of the reasoning used to produce it. This highlights a fundamental limitation of outcome-based evaluation: models may arrive at correct answers through flawed reasoning, and models with substantially different reasoning capabilities can nevertheless exhibit similar benchmark accuracy, for example due to memorization or over-optimization. In this paper, we ask: given existing benchmarks, can we move beyond outcome-based evaluation to assess the quality of reasoning itself? We seek metrics that (1) differentiate models with similar accuracy and (2) are robust to variations in input prompts and generation configurations. To this end, we propose a reasoning score that evaluates reasoning traces along dimensions such as faithfulness, coherence, utility, and factuality. A remaining question is how to aggregate this score across multiple sampled traces. Naively averaging them is undesirable, particularly in long-horizon settings, where the number of possible trajectories grows rapidly, and low-confidence correct traces are more likely to be coincidental. To address this, we introduce the Filtered Reasoning Score (FRS), which computes reasoning quality using only the top-K% most confident traces. Evaluating with FRS, models that are indistinguishable under standard accuracy exhibit significant differences in reasoning quality. Moreover, models with higher FRS on one benchmark tend to perform better on other reasoning benchmarks, in both accuracy and reasoning quality. Together, these findings suggest that FRS complements accuracy by capturing a model's transferable reasoning capabilities. We open source our evaluation codebase: https://github.com/Manas2006/benchmark_reproducibility. --- ### Loss-Driven Bayesian Active Learning Authors: Zhuoyue Huang, Freddie Bickford Smith, Tom Rainforth Published: 2026-04-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.11995v2 The central goal of active learning is to gather data that maximises downstream predictive performance, but popular approaches have limited flexibility in customising this data acquisition to different downstream problems and losses. We propose a rigorous loss-driven approach to Bayesian active learning that allows data acquisition to directly target the loss associated with a given decision problem. In particular, we show how any loss can be used to derive a unique objective for optimal data acquisition. Critically, we then show that any loss taking the form of a weighted Bregman divergence permits analytic computation of a central component of its corresponding objective, making the approach applicable in practice. In regression and classification experiments with a range of different losses, we find our approach reduces test losses relative to existing techniques. --- ### Offline-Online Reinforcement Learning for Linear Mixture MDPs Authors: Zhongjun Zhang, Sean R. Sinclair Published: 2026-04-13 Categories: cs.LG, math.OC, stat.ML arXiv: https://arxiv.org/abs/2604.11994v1 We study offline-online reinforcement learning in linear mixture Markov decision processes (MDPs) under environment shift. In the offline phase, data are collected by an unknown behavior policy and may come from a mismatched environment, while in the online phase the learner interacts with the target environment. We propose an algorithm that adaptively leverages offline data. When the offline data are informative, either due to sufficient coverage or small environment shift, the algorithm provably improves over purely online learning. When the offline data are uninformative, it safely ignores them and matches the online-only performance. We establish regret upper bounds that explicitly characterize when offline data are beneficial, together with nearly matching lower bounds. Numerical experiments further corroborate our theoretical findings. --- ### Ultra-low-light computer vision using trained photon correlations Authors: Mandar M. Sohoni, Jérémie Laydevant, Mathieu Ouellet, Shi-Yuan Ma, Ryotatsu Yanagimoto, Benjamin A. Ash, Tatsuhiro Onodera, Tianyu Wang, Logan G. Wright, Peter L. McMahon Published: 2026-04-13 Categories: cs.CV, physics.optics arXiv: https://arxiv.org/abs/2604.11993v1 Illumination using correlated photon sources has been established as an approach to allowing high-fidelity images to be reconstructed from noisy camera frames by taking advantage of the knowledge that signal photons are spatially correlated whereas detector clicks due to noise are uncorrelated. However, in computer-vision tasks, the goal is often not ultimately to reconstruct an image, but to make inferences about a scene -- such as what object is present. Here we show how correlated-photon illumination can be used to gain an advantage in a hybrid optical-electronic computer-vision pipeline for object recognition. We demonstrate correlation-aware training (CAT): end-to-end optimization of a trainable correlated-photon illumination source and a Transformer backend in a way that the Transformer can learn to benefit from the correlations, using a small number (<= 100) of shots. We show a classification accuracy enhancement of up to 15 percentage points over conventional, uncorrelated-illumination-based computer vision in ultra-low-light and noisy imaging conditions, as well as an improvement over using untrained correlated-photon illumination. Our work illustrates how specializing to a computer-vision task -- object recognition -- and training the pattern of photon correlations in conjunction with a digital backend allows us to push the limits of accuracy in highly photon-budget-constrained scenarios beyond existing methods focused on image reconstruction. --- ### ReefMapGS: Enabling Large-Scale Underwater Reconstruction by Closing the Loop Between Multimodal SLAM and Gaussian Splatting Authors: Daniel Yang, Jungseok Hong, John J. Leonard, Yogesh Girdhar Published: 2026-04-13 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2604.11992v1 3D Gaussian Splatting is a powerful visual representation, providing high-quality and efficient 3D scene reconstruction, but it is crucially dependent on accurate camera poses typically obtained from computationally intensive processes like structure-from-motion that are unsuitable for field robot applications. However, in these domains, multimodal sensor data from acoustic, inertial, pressure, and visual sensors are available and suitable for pose-graph optimization-based SLAM methods that can estimate the vehicle's trajectory and thus our needed camera poses while providing uncertainty. We propose a 3DGS-based incremental reconstruction framework, ReefMapGS, that builds an initial model from a high certainty region and progressively expands to incorporate the whole scene. We reconstruct the scene incrementally by interleaving local tracking of new image observations with optimization of the underlying 3DGS scene. These refined poses are integrated back into the pose-graph to globally optimize the whole trajectory. We show COLMAP-free 3D reconstruction of two underwater reef sites with complex geometry as well as more accurate global pose estimation of our AUV over survey trajectories spanning up to 700 m. --- ### Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning Authors: Xiaoxue Han, Libo Zhang, Zining Zhu, Yue Ning Published: 2026-04-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.11986v1 We introduce Graph Concept Bottleneck (GCB) as a new paradigm for self-explainable text-attributed graph learning. GCB maps graphs into a subspace, concept bottleneck, where each concept is a meaningful phrase, and predictions are made based on the activation of these concepts. Unlike existing interpretable graph learning methods that primarily rely on subgraphs as explanations, the concept bottleneck provides a new form of interpretation. To refine the concept space, we apply the information bottleneck principle to focus on the most relevant concepts. This not only yields more concise and faithful explanations but also explicitly guides the model to "think" toward the correct decision. We empirically show that GCB achieves intrinsic interpretability with accuracy on par with black-box Graph Neural Networks. Moreover, it delivers better performance under distribution shifts and data perturbations, showing improved robustness and generalizability, benefitting from concept-guided prediction. --- ### A Geometric Algebra-informed NeRF Framework for Generalizable Wireless Channel Prediction Authors: Jingzhou Shen, Luis Lago Enamorado, Shiwen Mao, Xuyu Wang Published: 2026-04-13 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2604.11983v1 In this paper, we propose the geometric algebra-informed neural radiance fields (GAI-NeRF), a novel framework for wireless channel prediction that leverages geometric algebra attention mechanisms to capture ray-object interactions in complex propagation environments. Our approach incorporates global token representations, drawing inspiration from transformer architectures in language and vision domains, to aggregate learned spatial-electromagnetic features and enhance scene understanding. We identify limitations in conventional static ray tracing modules that hinder model generalization and address this challenge through a new ray tracing architecture. This design enables effective generalization across diverse wireless scenarios while maintaining computational efficiency. Experimental results demonstrate that GAI-NeRF achieves superior performance in channel prediction tasks by combining geometric algebra principles with neural scene representations, offering a promising direction for next-generation wireless communication systems. Moreover, GAI-NeRF greatly outperforms existing methods across multiple wireless scenarios. To ensure comprehensive assessment, we further evaluate our approach against multiple benchmarks using newly collected real-world indoor datasets tailored for single-scene downstream tasks and generalization testing, confirming its robust performance in unseen environments and establishing its high efficacy for wireless channel prediction. --- ### The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break Authors: Xinyu Jessica Wang, Haoyue Bai, Yiyou Sun, Haorui Wang, Shuibai Zhang, Wenjie Hu, Mya Schroder, Bilge Mutlu, Dawn Song, Robert D Nowak Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.11978v1 Large language model (LLM) agents perform strongly on short- and mid-horizon tasks, but often break down on long-horizon tasks that require extended, interdependent action sequences. Despite rapid progress in agentic systems, these long-horizon failures remain poorly characterized, hindering principled diagnosis and comparison across domains. To address this gap, we introduce HORIZON, an initial cross-domain diagnostic benchmark for systematically constructing tasks and analyzing long-horizon failure behaviors in LLM-based agents. Using HORIZON, we evaluate state-of-the-art (SOTA) agents from multiple model families (GPT-5 variants and Claude models), collecting 3100+ trajectories across four representative agentic domains to study horizon-dependent degradation patterns. We further propose a trajectory-grounded LLM-as-a-Judge pipeline for scalable and reproducible failure attribution, and validate it with human annotation on trajectories, achieving strong agreement (inter-annotator κ=0.61; human-judge κ=0.84). Our findings offer an initial methodological step toward systematic, cross-domain analysis of long-horizon agent failures and offer practical guidance for building more reliable long-horizon agents. We release our project website at \href{https://xwang2775.github.io/horizon-leaderboard/}{HORIZON Leaderboard} and welcome contributions from the community. --- ### Multi-Head Residual-Gated DeepONet for Coherent Nonlinear Wave Dynamics Authors: Zhiwei Fan, Yiming Pan, Daniel Coca Published: 2026-04-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.11972v2 Coherent nonlinear wave dynamics are often strongly shaped by a compact set of physically meaningful descriptors of the initial state. Traditional neural operators typically treat the input-output mapping as a largely black-box high-dimensional regression problem, without explicitly exploiting this structured physical context. Common feature-integration strategies usually rely on direct concatenation or FiLM-style affine modulation in hidden latent spaces. Here we introduce a different paradigm, loosely inspired by the complementary roles of state evolution and physically meaningful observables in quantum mechanics: the wave field is learned through a standard DeepONet state pathway, while compact physical descriptors follow a parallel conditioning pathway and act as residual modulation factors on the state prediction. Based on this idea, we develop a Multi-Head Residual-Gated DeepONet (MH-RG), which combines a pre-branch residual modulator, a branch residual gate, and a trunk residual gate with a low-rank multi-head mechanism to capture multiple complementary conditioned response patterns without prohibitive parameter growth. We evaluate the framework on representative benchmarks including highly nonlinear conservative wave dynamics and dissipative trapped dynamics and further perform detailed mechanistic analyses of the learned multi-head gating behavior. Compared with feature-augmented baselines, MH-RG DeepONet achieves consistently lower error while better preserving phase coherence and the fidelity of physically relevant dynamical quantities. --- ### Multi-Head Residual-Gated DeepONet for Coherent Nonlinear Wave Dynamics Authors: Zhiwei Fan, Yiming Pan, Daniel Coca Published: 2026-04-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.11972v1 Coherent nonlinear wave dynamics are often strongly shaped by a compact set of physically meaningful descriptors of the initial state. Traditional neural operators typically treat the input-output mapping as a largely black-box high-dimensional regression problem, without explicitly exploiting this structured physical context. Common feature-integration strategies usually rely on direct concatenation or FiLM-style affine modulation in hidden latent spaces. Here we introduce a different paradigm, loosely inspired by the complementary roles of state evolution and physically meaningful observables in quantum mechanics: the wave field is learned through a standard DeepONet state pathway, while compact physical descriptors follow a parallel conditioning pathway and act as residual modulation factors on the state prediction. Based on this idea, we develop a Multi-Head Residual-Gated DeepONet (MH-RG), which combines a pre-branch residual modulator, a branch residual gate, and a trunk residual gate with a low-rank multi-head mechanism to capture multiple complementary conditioned response patterns without prohibitive parameter growth. We evaluate the framework on representative benchmarks including highly nonlinear conservative wave dynamics and dissipative trapped dynamics and further perform detailed mechanistic analyses of the learned multi-head gating behavior. Compared with feature-augmented baselines, MH-RG DeepONet achieves consistently lower error while better preserving phase coherence and the fidelity of physically relevant dynamical quantities. --- ### Classification of Epileptic iEEG using Topological Machine Learning Authors: Sunia Tanweer, Narayan Puthanmadam Subramaniyam, Firas A. Khasawneh Published: 2026-04-13 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2604.11971v1 Epileptic seizure detection from EEG signals remains challenging due to the high dimensionality and nonlinear, potentially stochastic, dynamics of neural activity. In this work, we investigate whether features derived from topological data analysis (TDA) can improve the classification of brain states in preictal, ictal and interictal iEEG recordings from epilepsy patients using multichannel data. We analyze data from 55 patients, significantly larger than many previous studies that rely on patient-specific models. Persistence diagrams derived from iEEG signals are vectorized using several TDA representations, including Carlsson coordinates, persistence images, and template functions. To understand how topological representations interact with modern machine learning pipelines, we conduct a large-scale ablation study across multiple iEEG frequency bands, dimensionality reduction techniques, feature representations, and classifier architectures. Our experiments show that dimension-reduced topological representations achieve up to 80\% balanced accuracy for three-class classification. Interestingly, classical machine learning models perform comparably to deep learning models, achieving up to 79.17\% balanced accuracy, suggesting that carefully designed topological features can substantially reduce model complexity requirements. In contrast, pipelines preserving the full multichannel feature structure exhibit severe overfitting due to the high-dimensional feature space. These findings highlight the importance of structure-preserving dimensionality reduction when applying topology-based representations to multichannel neural data. --- ### INDOTABVQA: A Benchmark for Cross-Lingual Table Understanding in Bahasa Indonesia Documents Authors: Somraj Gautam, Anathapindika Dravichi, Gaurav Harit Published: 2026-04-13 Categories: cs.CV, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.11970v1 We introduce INDOTABVQA, a benchmark for evaluating cross-lingual Table Visual Question Answering (VQA) on real-world document images in Bahasa Indonesia. The dataset comprises 1,593 document images across three visual styles (bordered, borderless, and colorful) with one or more than one tables, and 1,593 question-answer sets in four languages: Bahasa Indonesia, English, Hindi, and Arabic. This enables evaluation of Vision-Language Models (VLMs) in both monolingual (Bahasa documents with Bahasa questions) and cross-lingual settings (Bahasa documents with questions in other languages). We benchmark leading open-source VLMs (Qwen2.5-VL, Gemma-3, LLaMA-3.2) and GPT-4o and reveal substantial performance gaps, particularly on structurally complex tables and in low-resource languages. Fine-tuning a compact 3B and LoRA-finetuned 7B model on our dataset yields 11.6% and 17.8% improvements in accuracy. Providing explicit table region coordinates as additional input further improves performance by 4-7%, demonstrating the value of Spatial priors for table-based reasoning. Our findings underscore the importance of language-diverse, domain-specific datasets and demonstrate that targeted fine-tuning can significantly enhance VLM performance on specialized document understanding tasks. INDOTABVQA provides a valuable resource for advancing research in cross-lingual, structure-aware document understanding, especially in underrepresented regions of the world. Full dataset can be accessed in huggingface at: https://huggingface.co/datasets/NusaBharat/INDOTABVQA} --- ### Narrative-Driven Paper-to-Slide Generation via ArcDeck Authors: Tarik Can Ozden, Sachidanand VS, Furkan Horoz, Ozgur Kara, Junho Kim, James Matthew Rehg Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.11969v1 We introduce ArcDeck, a multi-agent framework that formulates paper-to-slide generation as a structured narrative reconstruction task. Unlike existing methods that directly summarize raw text into slides, ArcDeck explicitly models the source paper's logical flow. It first parses the input to construct a discourse tree and establish a global commitment document, ensuring the high-level intent is preserved. These structural priors then guide an iterative multi-agent refinement process, where specialized agents iteratively critique and revise the presentation outline before rendering the final visual layouts and designs. To evaluate our approach, we also introduce ArcBench, a newly curated benchmark of academic paper-slide pairs. Experimental results demonstrate that explicit discourse modeling, combined with role-specific agent coordination, significantly improves the narrative flow and logical coherence of the generated presentations. --- ### The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts Authors: Thomas Walker, Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk Published: 2026-04-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.11962v2 The Linear Representation Hypothesis (LRH) identifies features of a trained deep network (DN) as linear directions in the activation spaces, i.e., output spaces of intermediate layers. This characterization decouples the input-output maps learned by a DN from the organization of feature directions in its activation spaces. We introduce the Linear Centroids Hypothesis (LCH), which instead identifies features with linear directions among a DN's centroid spaces -- where any vector denotes a centroid or summary of a local affine expert characterizing the learned input-output maps of the DN exactly (e.g., for piecewise-affine DNs) or approximately (e.g., for smooth DNs like transformers). We show that replacing intermediate activations with centroids yields a functional drop-in alternative for standard interpretability tools. Empirically, this change yields sparser, more downstream-useful feature dictionaries on DINO ViTs, suppresses spurious directions on a controlled task, recovers interpretable circuits in GPT2-Large, and produces faithful gradient-based saliency maps. LCH unifies dictionaries, probing, circuits, and saliency maps into a single geometric object grounded in the network's input-output map -- making interpretability mechanistic by construction rather than post hoc. Code to study the LCH https://github.com/ThomasWalker1/LinearCentroidsHypothesis . --- ### Fall Risk and Gait Analysis in Community-Dwelling Older Adults using World-Spaced 3D Human Mesh Recovery Authors: Chitra Banarjee, Patrick Kwon, Ania Lipat, Rui Xie, Chen Chen, Ladda Thiamwong Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11961v1 Gait assessment is a key clinical indicator of fall risk and overall health in older adults. However, standard clinical practice is largely limited to stopwatch-measured gait speed. We present a pipeline that leverages a 3D Human Mesh Recovery (HMR) model to extract gait parameters from recordings of older adults completing the Timed Up and Go (TUG) test. From videos recorded across different community centers, we extract and analyze spatiotemporal gait parameters, including step time, sit-to-stand duration, and step length. We found that video-derived step time was significantly correlated with IMU-based insole measurements. Using linear mixed effects models, we confirmed that shorter, more variable step lengths and longer sit-to-stand durations were predicted by higher self-rated fall risk and fear of falling. These findings demonstrate that our pipeline can enable accessible and ecologically valid gait analysis in community settings. --- ### Agentic LLM Reasoning in a Self-Driving Laboratory for Air-Sensitive Lithium Halide Spinel Conductors Authors: Yuxing Fei, Bernardus Rendy, Xiaochen Yang, Junhee Woo, Xu Huang, Chang Li, Shilong Wang, David Milsted, Yan Zeng, Gerbrand Ceder Published: 2026-04-13 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2604.11957v1 Self-driving laboratories promise to accelerate materials discovery. Yet current automated solid-state synthesis platforms are limited to ambient conditions, thereby precluding their use for air-sensitive materials. Here, we present A-Lab for Glovebox Powder Solid-state Synthesis (A-Lab GPSS), a robotic platform capable of synthesizing and characterizing air-sensitive inorganic materials under strict air-free conditions. By integrating an agentic AI framework into the A-Lab GPSS platform, we structure autonomous experimental design through abductive and inductive reasoning. We deploy this platform to explore the vast compositional space of lithium halide spinel solid-state ionic conductors. Across a synthesis campaign comprising 352 samples with diverse compositions, the system explores a broad chemical space, experimentally realizing 72% of the 171 possible pairwise combinations among the 19 metals considered in this study. Over the course of the campaign, the fraction of compositions exhibiting both good ionic conductivity (> 0.05 mS/cm) and high halide spinel phase purity increases from 1.33% in the first 75 agent-proposed samples to 5.33% in the final 75. Furthermore, by inspecting the AI's reasoning processes, we reveal distinct yet complementary discovery strategies: abductive reasoning interrogates abnormal observations within already explored regions, whereas inductive reasoning expands the search into broader, previously unvisited chemical space. This work establishes a scalable platform for the autonomous discovery of complex, air-sensitive solid-state materials. --- ### AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection Authors: Zijie Zhao, Chenyuan Yang, Weidong Wang, Yihan Yang, Ziqi Zhang, Lingming Zhang Published: 2026-04-13 Categories: cs.SE, cs.AI, cs.CL, cs.CR arXiv: https://arxiv.org/abs/2604.11950v2 While recent LLM-based agents can identify many candidate bugs in source code, their reports remain static hypotheses that require manual validation, limiting the practicality of automated bug detection. We frame this challenge as a test generation task: given a candidate report, synthesizing an executable proof-of-concept (PoC) - such as a script, command sequence, or crafted input - to trigger the suspected defect. Automated PoC generation can act as a scalable validation oracle, enabling end-to-end autonomous bug detection by providing concrete execution evidence. However, naive LLM agents are unreliable validators: they are biased toward "success" and may reward-hack by producing plausible but non-functional PoCs or even hallucinated traces. To address this, we present ANYPoC, a general multi-agent framework that (1) analyzes and fact-checks a candidate bug report, (2) iteratively synthesizes and executes a PoC while collecting execution traces, and (3) independently re-executes and scrutinizes the PoC to mitigate hallucination and reward hacking. In addition, ANYPoC also continuously extracts and evolves a PoC knowledge base to handle heterogeneous tasks. ANYPoC operates on candidate bug reports regardless of their source and can be paired with different bug reporters. To demonstrate practicality and generality, we apply ANYPoC, together with a simple agentic bug reporter, on 12 large-scale, critical software systems, including Firefox, Chromium, LLVM, OpenSSL, SQLite, FFmpeg, and Redis. Compared to the state-of-the-art coding agents, e.g., Claude Code and Codex, ANYPoC produces 37% more valid PoCs for true-positive bug reports and rejects 9.7x more false-positive bug reports. ANYPoC also enables the discovery of 121 new bugs from over two thousand noisy bug reports, with 108 confirmed by developers and 92 fixed. 46 PoCs have also been adopted as official regression tests. --- ### Active Imitation Learning for Thermal- and Kernel-Aware LFM Inference on 3D S-NUCA Many-Cores Authors: Yixian Shen, Chaoyao Shen, Jan Deen, George Floros, Andy Pimentel, Anuj Pathania Published: 2026-04-13 Categories: cs.LG, cs.AR arXiv: https://arxiv.org/abs/2604.11948v1 Large Foundation Model (LFM) inference is both memory- and compute-intensive, traditionally relying on GPUs. However, the limited availability and high cost have motivated the adoption of high-performance general-purpose CPUs, especially emerging 3D-stacked Static Non-Uniform Cache Architecture (3D S-NUCA) systems. These architectures offer enhanced bandwidth and locality but suffer from severe thermal challenges and uneven cache latencies due to 3D Networks-on-Chip (NoC). Optimal management of thread migration and V/f scaling is non-trivial due to LFM kernel diversity and system heterogeneity. Existing thermal management approaches often rely on oversimplified analytical models and lack adaptability. We propose AILFM, an Active Imitation Learning (AIL)-based scheduling framework that learns near-optimal thermal-aware scheduling policies from Oracle demonstrations with minimal run-time overhead. AILFM accounts for both core-level performance heterogeneity and kernel-specific behavior in LFMs to maintain thermal safety while maximizing performance. Extensive experiments show that AILFM outperforms state-of-the-art baselines and generalizes well across diverse LFM workloads. --- ### ResBM: Residual Bottleneck Models for Low-Bandwidth Pipeline Parallelism Authors: Alan Aboudib, Rodrigo Lopez Portillo A., Kalei Brady, Steffen Cruz Published: 2026-04-13 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2604.11947v1 Unlocking large-scale low-bandwidth decentralized training has the potential to utilize otherwise untapped compute resources. In centralized settings, large-scale multi-node training is primarily enabled by data and pipeline parallelism, two techniques that require ultra-high-bandwidth communication. While efficient methods now exist for decentralized data parallelism, pipeline parallelism remains the primary challenge. Recent efforts, such as Subspace Models (SM), have claimed up to 100x activation compression but rely on complex constrained optimization and diverge from true end-to-end training. In this paper, we propose a different approach, based on an architecture designed from the ground up to be native to low-bandwidth communication environments while still applicable to any standard transformer-based architecture. We call this architecture the Residual Bottleneck Model or ResBM, it introduces a residual encoder-decoder bottleneck module across pipeline boundaries that can be trained end-to-end as part of the model's parameters while preserving an explicit low-rank identity path. We show that ResBMs achieve state-of-the-art 128x activation compression without significant loss in convergence rates and without significant memory or compute overhead. --- ### AutoSurrogate: An LLM-Driven Multi-Agent Framework for Autonomous Construction of Deep Learning Surrogate Models in Subsurface Flow Authors: Jiale Liu, Nanzhe Wang Published: 2026-04-13 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.11945v1 High-fidelity numerical simulation of subsurface flow is computationally intensive, especially for many-query tasks such as uncertainty quantification and data assimilation. Deep learning (DL) surrogates can significantly accelerate forward simulations, yet constructing them requires substantial machine learning (ML) expertise - from architecture design to hyperparameter tuning - that most domain scientists do not possess. Furthermore, the process is predominantly manual and relies heavily on heuristic choices. This expertise gap remains a key barrier to the broader adoption of DL surrogate techniques. For this reason, we present AutoSurrogate, a large-language-model-driven multi-agent framework that enables practitioners without ML expertise to build high-quality surrogates for subsurface flow problems through natural-language instructions. Given simulation data and optional preferences, four specialized agents collaboratively execute data profiling, architecture selection from a model zoo, Bayesian hyperparameter optimization, model training, and quality assessment against user-specified thresholds. The system also handles common failure modes autonomously, including restarting training with adjusted configurations when numerical instabilities occur and switching to alternative architectures when predictive accuracy falls short of targets. In our setting, a single natural-language sentence can be sufficient to produce a deployment-ready surrogate model, with minimum human intervention required at any intermediate stage. We demonstrate the utility of AutoSurrogate on a 3D geological carbon storage modeling task, mapping permeability fields to pressure and CO$_2$ saturation fields over 31 timesteps. Without any manual tuning, AutoSurrogate is able to outperform expert-designed baselines and domain-agnostic AutoML methods, demonstrating strong potential for practical deployment. --- ### A unified data format for managing diabetes time-series data: DIAbetes eXchange (DIAX) Authors: Elliott C. Pryor, Marc D. Breton, Anas El Fathi Published: 2026-04-13 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2604.11944v1 Diabetes devices, including Continuous Glucose Monitoring (CGM), Smart Insulin Pens, and Automated Insulin Delivery systems, generate rich time-series data widely used in research and machine learning. However, inconsistent data formats across sources hinder sharing, integration, and analysis. We present DIAX (DIAbetes eXchange), a standardized JSON-based format for unifying diabetes time-series data, including CGM, insulin, and meal signals. DIAX promotes interoperability, reproducibility, and extensibility, particularly for machine learning applications. An open-source repository provides tools for dataset conversion, cross-format compatibility, visualization, and community contributions. DIAX is a translational resource, not a data host, ensuring flexibility without imposing data-sharing constraints. Currently, DIAX is compatible with other standardization efforts and supports major datasets (DCLP3, DCLP5, IOBP2, PEDAP, T1Dexi, Loop), totaling over 10 million patient-hours of data. https://github.com/Center-for-Diabetes-Technology/DIAX --- ### ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems Authors: Daeyeon Son Published: 2026-04-13 Categories: cs.OS, cs.LG arXiv: https://arxiv.org/abs/2604.11943v3 An OS kernel that runs LLM inference internally can read the model's own next-token logit distribution before any text is generated, and act on it as a governance primitive. I present ProbeLogits, a kernel-level operation that performs a single forward pass and reads specific token logits to classify an agent's action as safe or dangerous, with zero learned parameters. Because the probe reads a logit from the same base model the agent already runs, it removes the second model a fine-tuned guard requires: the marginal cost of a safety check becomes a single logit read. I evaluate ProbeLogits on three base models (Qwen2.5-7B, Llama-3-8B, Mistral-7B) across three external benchmarks (HarmBench, XSTest, ToxicChat). On HarmBench non-copyright, all three reach a 97-99% block rate. On ToxicChat (n=1,000), ProbeLogits attains F1 parity-or-better against Llama Guard 3: Qwen2.5-7B Safe/Dangerous reaches F1=0.812 (+13.7 pp, bootstrap 95% CIs disjoint), Llama-3 matches within CI (+0.4 pp), and Mistral exceeds by +4.4 pp. Classification is a measured 2.4-3.4x faster than Llama Guard 3 (332-556 ms vs. 851-1,142 ms), because it reads a single logit position instead of generating tokens. A calibration strength alpha acts as a deployment-time policy knob rather than a learned hyperparameter, trading recall for precision per operation class. I implement ProbeLogits within Anima OS, a bare-metal x86-64 kernel written in ~285,000 lines of Rust. Because agent actions must pass through kernel-mediated host functions, enforcement operates below the WASM sandbox boundary, making it substantially harder to circumvent than application-layer classifiers. --- ### EigenCoin: sassanid coins classification based on Bhattacharyya distance Authors: Rahele Allahverdi, Mohammad Mahdi Dehshibi, Azam Bastanfard, Daryoosh Akbarzadeh Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11932v1 Solving pattern recognition problems using imbalanced databases is a hot topic, which entices researchers to bring it into focus. Therefore, we consider this problem in the application of Sassanid coins classification. Our focus is not only on proposing EigenCoin manifold with Bhattacharyya distance for the classification task, but also on testing the influence of the holistic and feature-based approaches. EigenCoin consists of three main steps namely manifold construction, mapping test data, and classification. Conducted experiments show EigenCoin outperformed other observed algorithms and achieved the accuracy from 9.45% up to 21.75%, while it has the capability of handling the over-fitting problem. --- ### Fast and principled equation discovery from chaos to climate Authors: Yuzheng Zhang, Weizhen Li, Rui Carvalho Published: 2026-04-13 Categories: cs.LG, math.DS, physics.comp-ph arXiv: https://arxiv.org/abs/2604.11929v2 Our ability to predict, control, and ultimately understand complex systems rests on discovering the equations that govern their dynamics. Identifying these equations directly from noisy, limited observations has therefore become a central challenge in data-driven science, yet existing library-based sparse regression methods force a compromise between automation, statistical rigor, and computational efficiency. Here we develop Bayesian-ARGOS, a hybrid framework that reconciles these demands by combining rapid frequentist screening with focused Bayesian inference, enabling automated equation discovery with principled uncertainty quantification at a fraction of the computational cost of existing methods. Tested on seven chaotic systems under varying data scarcity and noise levels, Bayesian-ARGOS outperforms two state-of-the-art methods in most scenarios. It surpasses SINDy in data efficiency for all systems and noise tolerance for six out of the seven, with a two-order-of-magnitude reduction in computational cost compared to bootstrap-based ARGOS. The probabilistic formulation additionally enables a suite of standard statistical diagnostics, including influence analysis and multicollinearity detection that expose failure modes otherwise opaque. When integrated with representation learning (SINDy-SHRED) for high dimensional sea surface temperature reconstruction, Bayesian-ARGOS increases the yield of valid latent equations with significantly improved long horizon stability. Bayesian-ARGOS thus provides a principled, automated, and computationally efficient route from scarce and noisy observations to interpretable governing equations, offering a practical framework for equation discovery across scales, from benchmark chaotic systems to the latent dynamics underlying global climate patterns. --- ### INTARG: Informed Real-Time Adversarial Attack Generation for Time-Series Regression Authors: Gamze Kirman Tokgoz, Onat Gungor, Tajana Rosing, Baris Aksanli Published: 2026-04-13 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2604.11928v1 Time-series forecasting aims to predict future values by modeling temporal dependencies in historical observations. It is a critical component of many real-world systems, where accurate forecasts improve operational efficiency and help mitigate uncertainty and risk. More recently, machine learning (ML), and especially deep learning (DL)-based models, have gained widespread adoption for time-series forecasting, but they remain vulnerable to adversarial attacks. However, many state-of-the-art attack methods are not directly applicable in time-series settings, where storing complete historical data or performing attacks at every time step is often impractical. This paper proposes an adversarial attack framework for time-series forecasting under an online bounded-buffer setting, leveraging an informed and selective attack strategy. By selectively targeting time steps where the model exhibits high confidence and the expected prediction error is maximal, our framework produces fewer but substantially more effective attacks. Experiments show that our framework can increase the prediction error up to 2.42x, while performing attacks in fewer than 10% of time steps. --- ### A Workflow to Efficiently Generate Dense Tissue Ground Truth Masks for Digital Breast Tomosynthesis Authors: Tamerlan Mustafaev, Oleg Kruglov, Margarita Zuley, Luana de Mero Omena, Guilherme Muniz de Oliveira, Vitor de Sousa Franca, Bruno Barufaldi, Robert Nishikawa, Juhun Lee Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11927v1 Digital breast tomosynthesis (DBT) is now the standard of care for breast cancer screening in the USA. Accurate segmentation of fibroglandular tissue in DBT images is essential for personalized risk estimation, but algorithm development is limited by scarce human-delineated training data. In this study we introduce a time- and labor-saving framework to generate a human-annotated binary segmentation mask for dense tissue in DBT. Our framework enables a user to outline a rough region of interest (ROI) enclosing dense tissue on the central reconstructed slice of a DBT volume and select a segmentation threshold to generate the dense tissue mask. The algorithm then projects the ROI to the remaining slices and iteratively adjusts slice-specific thresholds to maintain consistent dense tissue delineation across the DBT volume. By requiring annotation only on the central slice, the framework substantially reduces annotation time and labor. We used 44 DBT volumes from the DBTex dataset for evaluation. Inter-reader agreement was assessed by computing patient-wise Dice similarity coefficients between segmentation masks produced by two radiologists, yielding a median of 0.84. Accuracy of the proposed method was evaluated by having a radiologist manually segment the 20th and 80th percentile slices from each volume (CC and MLO views; 176 slices total) and calculate Dice scores between the manual and proposed segmentations, yielding a median of 0.83. --- ### GoodPoint: Learning Constructive Scientific Paper Feedback from Author Responses Authors: Jimin Mun, Chani Jung, Xuhui Zhou, Hyunwoo Kim, Maarten Sap Published: 2026-04-13 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.11924v1 While LLMs hold significant potential to transform scientific research, we advocate for their use to augment and empower researchers rather than to automate research without human oversight. To this end, we study constructive feedback generation, the task of producing targeted, actionable feedback that helps authors improve both their research and its presentation. In this work, we operationalize the effectiveness of feedback along two author-centric axes-validity and author action. We first curate GoodPoint-ICLR, a dataset of 19K ICLR papers with reviewer feedback annotated along both dimensions using author responses. Building on this, we introduce GoodPoint, a training recipe that leverages success signals from author responses through fine-tuning on valid and actionable feedback, together with preference optimization on both real and synthetic preference pairs. Our evaluation on a benchmark of 1.2K ICLR papers shows that a GoodPoint-trained Qwen3-8B improves the predicted success rate by 83.7% over the base model and sets a new state-of-the-art among LLMs of similar size in feedback matching on a golden human feedback set, even surpassing Gemini-3-flash in precision. We further validate these findings through an expert human study, demonstrating that GoodPoint consistently delivers higher practical value as perceived by authors. --- ### Spectral Structure in Finite Free Information Inequalities and $p$-Stam Phase Transitions Authors: Baran Hashemi Published: 2026-04-13 Categories: math.PR, cs.LG, math.CO arXiv: https://arxiv.org/abs/2604.11922v2 Using FlowBoost, a closed-loop deep generative optimization framework for extremal structure discovery, we investigate $\ell^p$-generalizations of the finite free Stam inequality for real-rooted polynomials under finite free additive convolution $\boxplus_n$. At $p=2$, FlowBoost finds the Hermite pair as the unique equality case and reveals the spectral structure of the linearized convolution map at this extremal point. As a result, we conjecture that the singular values of the doubly stochastic coupling matrix $E_n$ on the mean-zero subspace are ${2^{-k/2}:k=1,\ldots,n-1}$, independent of $n$. Conditional on this conjecture, we obtain a sharp local stability constant and the finite free CLT convergence rate, both uniform in $n$. We introduce a one-parameter family of $p$-Stam inequalities using $\ell^p$-Fisher information and prove that the Hermite pair itself violates the inequality for every $p>2$, with the sign of the deficit governed by the $\ell^p$-contraction ratio of $E_n$. Systematic computation via FlowBoost supports the conjecture that $p^*\!=2$ is the sharp critical exponent. For $p<2$, the extremal configurations undergo a bifurcation, meaning that they become non-matching pairs with bimodal root structure, converging back to the Hermite diagonal only as $p\to 2^-$. Our findings demonstrate that FlowBoost, can be an effective tool of mathematical discovery in infinite-dimensional extremal problems. --- ### Can AI Detect Life? Lessons from Artificial Life Authors: Ankit Gupta, Christoph Adami Published: 2026-04-13 Categories: cs.LG, cs.AI, cs.NE, q-bio.PE arXiv: https://arxiv.org/abs/2604.11915v2 Modern machine learning methods have been proposed to detect life in extraterrestrial samples, drawing on their ability to distinguish biotic from abiotic samples based on training models using natural and synthetic organic molecular mixtures. Here we show using Artificial Life that such methods are easily fooled into detecting life with near 100% confidence even if the analyzed sample is not capable of life. This is due to modern machine learning methods' propensity to be easily fooled by out-of-distribution samples. Because extra-terrestrial samples are very likely out of the distribution provided by terrestrial biotic and abiotic samples, using AI methods for life detection is likely to yield significant false positives. --- ### Self-Monitoring Benefits from Structural Integration: Lessons from Metacognition in Continuous-Time Multi-Timescale Agents Authors: Ying Xie Published: 2026-04-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.11914v1 Self-monitoring capabilities -- metacognition, self-prediction, and subjective duration -- are often proposed as useful additions to reinforcement learning agents. But do they actually help? We investigate this question in a continuous-time multi-timescale agent operating in predator-prey survival environments of varying complexity, including a 2D partially observable variant. We first show that three self-monitoring modules, implemented as auxiliary-loss add-ons to a multi-timescale cortical hierarchy, provide no statistically significant benefit across 20 random seeds, 1D and 2D predator-prey environments with standard and non-stationary variants, and training horizons up to 50,000 steps. Diagnosing the failure, we find the modules collapse to near-constant outputs (confidence std < 0.006, attention allocation std < 0.011) and the subjective duration mechanism shifts the discount factor by less than 0.03%. Policy sensitivity analysis confirms the agent's decisions are unaffected by module outputs in this design. We then show that structurally integrating the module outputs -- using confidence to gate exploration, surprise to trigger workspace broadcasts, and self-model predictions as policy input -- produces a medium-large improvement over the add-on approach (Cohen's d = 0.62, p = 0.06, paired) in a non-stationary environment. Component-wise ablations reveal that the TSM-to-policy pathway contributes most of this gain. However, structural integration does not significantly outperform a baseline with no self-monitoring (d = 0.15, p = 0.67), and a parameter-matched control without modules performs comparably, so the benefit may lie in recovering from the trend-level harm of ignored modules rather than in self-monitoring content. The architectural implication is that self-monitoring should sit on the decision pathway, not beside it. --- ### V-Nutri: Dish-Level Nutrition Estimation from Egocentric Cooking Videos Authors: Chengkun Yue, Chuanzhi Xu, Jiangpeng He Published: 2026-04-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.11913v1 Nutrition estimation of meals from visual data is an important problem for dietary monitoring and computational health, but existing approaches largely rely on single images of the finally completed dish. This setting is fundamentally limited because many nutritionally relevant ingredients and transformations, such as oils, sauces, and mixed components, become visually ambiguous after cooking, making accurate calorie and macronutrient estimation difficult. In this paper, we investigate whether the cooking process information from egocentric cooking videos can contribute to dish-level nutrition estimation. First, we further manually annotated the HD-EPIC dataset and established the first benchmark for video-based nutrition estimation. Most importantly, we propose V-Nutri, a staged framework that combines Nutrition5K-pretrained visual backbones with a lightweight fusion module that aggregates features from the final dish frame and cooking process keyframes extracted from the egocentric videos. V-Nutri also includes a cooking keyframes selection module, a VideoMamba-based event-detection model that targets ingredient-addition moments. Experiments on the HD-EPIC dataset show that process cues can provide complementary nutritional evidence, improving nutrition estimation under controlled conditions. Our results further indicate that the benefit of process keyframes depends strongly on backbone representation capacity and event detection quality. Our code and annotated dataset is available at https://github.com/K624-YCK/V-Nutri. ---