# Research Papers — 2026-05 · bundle page 249 of 326 > Full-text markdown of papers #12401–12450 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/249 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/248.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/250.md) ### Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect Authors: Ely Hahami, Ishaan Sinha, Lavik Jain Published: 2026-05-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.14111v1 Can small language models detect and report on perturbations their own internal activations? We investigate this question through the lens of activation steering: injecting concept vectors into a model's residual stream and measuring whether the model can accurately report on the perturbation. We first show that the binary detection paradigm used in prior work -- prompting the model to answer Yes'' or No'' to whether it detects an injected thought -- is confounded in small models, as steering biases the model toward affirmative responses regardless of the question content. We therefore propose two confound-free evaluation paradigms: sentence localization (identifying which of $N$ sentences was perturbed, chance $= 1/N$) and strength comparison (identifying which of two sentences received a stronger injection, chance $= 50\%$). Evaluating across six models from two families (Llama-3.2 and Gemma-4), we find that models as small as 2B parameters introspect reliably well above chance, and that introspective ability generally increases with scale. Llama-1B, however, performs at or below chance. We then introduce \emph{Introspection Fine-Tuning} (IFT): supervised fine-tuning on sentence-localization examples constructed from the model's own perturbed forward passes. IFT raises Llama-1B sentence-localization accuracy from $9.6\%$ to $60.6\%$ (a $6\times$ improvement), with gains generalizing zero-shot to the held-out strength-comparison task ($30.2\% \to 52.2\%$). IFT also improves introspection for 3B and 8B models, while inducing negligible degradation on standard capability benchmarks. Our results suggest that introspective ability is not fixed by scale alone: it can be directly trained, and doing so unlocks latent self-monitoring capacity with implications for AI transparency and alignment. Our code is \href{https://anonymous.4open.science/r/IFT-introspection-2092/README.md}{here}. --- ### GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings Authors: Asit Desai, Aman Kumar, Prashant Devadiga Published: 2026-05-08 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2607.00013v1 Retrieval-Augmented Generation (RAG) systems are widely used in institutional question answering settings where responses must be grounded in authoritative documentation (Gao et al., 2023). In entity-dense domains where relevant information is distributed across heterogeneous documents, vector-only retrieval often produces fragmented evidence and increases dependence on inference-time reasoning (Zhao et al., 2024). This paper introduces GRACE-RAG, a retrieval-governed, graph-augmented RAG architecture that externalizes structural reasoning from the generative stage to a structured retrieval layer, resolving structural ambiguity offline, enabling deployment on self-hosted lightweight models calibrated to closed-domain institutional vocabulary. Experiments across three model capacities: Mistral 24B, GPT OSS 120B, and Gemini 2.5 Flash show consistent improvements in completeness, depth, and anticipatory coverage, with overall quality gains of up to 20% under mid-scale models, indicating that retrieval architecture governs structural quality over model scale, reducing computational and latency footprint without dependence on proprietary systems. --- ### PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption Authors: Xue Tan, Yi Zheng, Chang Huo, Yunruo Zhang, Yu Liu, Hao Luan, Zhuyang Yu, Xiaoyan Sun, Ping Chen, Jun Dai Published: 2026-05-08 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2607.00012v1 Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge, effectively mitigating their inherent knowledge limitations. However, RAG remains vulnerable to poisoning attacks that manipulate retrieved texts to mislead model outputs. Existing defense mechanisms often lack theoretical robustness guarantees and perform unreliably when the LLM has limited knowledge of the retrieved content. In this work, we propose PRA-RAG, a provably robust retrieval aggregation algorithm designed to defend against poisoning attacks on retrieved texts. PRA-RAG samples multiple combinations of retrieved texts and utilizes geometric structures in the embedding space to identify a robust subset, from which a stable aggregated representation is derived. We provide theoretical bounds on the maximum impact of poisoned retrieved content and establish a quantitative measure of RAG's robustness. Experiments across multiple benchmarks and RAG architectures demonstrate that PRA-RAG reduces the attack success rate to as low as 1% while maintaining an accuracy of 71%, significantly outperforming representative state-of-the-art methods. --- ### SkillSelect-Serve: QoS-Aware Budgeted Skill Service Recommendation for LLM Agents Authors: Jingyuan Zheng, Dongjing Wang, Xin Zhang, Hao Chen, Youhuizi Li, Xudong Shen, Haiping Zhang, Butian Huang, Dongjin Yu, Guandong Xu Published: 2026-05-08 Categories: cs.IR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2607.00011v2 Reusable agent skills are emerging as a service-oriented capability layer for Large Language Model (LLM) agents. Unlike plain retrieval items, a skill exposes functional capabilities, input-output assumptions, tool dependencies, context cost, and risk metadata. Selecting skills is particularly challenging for small LLM agents, which can load only a few capability units under restricted context, tool availability, and risk tolerance. Existing fixed Top-k methods rank skills by textual relevance and overlook requirement satisfaction, deliverability, and operational constraints. We present SkillSelect-Serve, a QoS-aware, budget-constrained Skill Service recommendation framework. Raw skills are profiled as structured Skill Services, the task is converted into a structured requirement object, and candidates discovered from a large-scale registry are ranked by a calibrated task-conditioned suitability estimator and packed by a constrained projection enforcing token-budget, aggregated-risk, and tool-availability constraints, using only deployment-observable features. On a registry of 35,353 skills with pooled multi-positive relevance judgments verified by two independent assessors, the unconstrained top-5 recommendation fits a realistic 4,000-token context for only 9.1% of tasks; the constrained projection restores 100% deliverability at a cost of only 1.14 points of hit rate, outperforming retrieve-and-rerank, budget truncation, and diversity-based selection under identical budgets. The same mechanism halves delivered risk exposure and eliminates the 44-81% tool-violation rates of tool-agnostic recommendation. At an identical three-service budget, hit rate improves from 0.8864 to 0.9091 over fixed Top-3 retrieval. The results support managing reusable agent skills as discoverable, comparable, and constraint-aware service units instead of plain retrievable documents. --- ### Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework Authors: Nipun B Nair, Tongtong Wu, Weiqing Wang Published: 2026-05-08 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.00010v1 Conversational recommender systems (CRSs) are a core component of next-generation intelligent recommender systems because they enable users to actively elicit preferences, clarify intentions, and adapt recommendations in real time. However, there are two key obstacles in the CRS domain: evaluation and access to training data. Evaluating CRSs through real human studies is more critical than for traditional recommender systems, yet such studies are both costly and time-consuming. Moreover, CRS interaction data are often difficult to obtain for model training due to privacy concerns. Large language model (LLM)-based user simulators have shown promise in addressing both challenges by generating synthetic user interactions for evaluation and training. However, existing approaches suffer from systematic positive bias, data leakage, and limited behavioral diversity, and they rely on brittle manual prompt engineering that requires extensive domain expertise. In this paper, we propose a framework to automatically optimize prompts for LLM-based user simulators in CRSs, simultaneously mitigating these issues. Experimental results demonstrate that the proposed framework achieves improved behavioral alignment with human interaction patterns compared to baseline methods across diverse prompt settings. --- ### Position: The Term "Machine Unlearning" Is Overused in LLMs Authors: Sangyeon Yoon, Yeachan Jun, Albert No Published: 2026-05-08 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.27379v1 Large language models increasingly face demands to "forget" training data, knowledge, or behaviors due to regulatory deletion obligations, copyright/licensing disputes, and safety or product-policy requirements. This position paper argues that machine unlearning is overused as a term in LLM research and should be reserved for dataset-defined deletion: removing the training influence of a precisely specified forget set such that the resulting model is approximately indistinguishable from retraining without that data. We contend that many tasks currently labeled "unlearning" (e.g., refusal for harmful requests, entity/knowledge removal, or targeted suppression) pursue different, often policy-dependent objectives and therefore require different terminology and baselines (e.g., alignment, suppression, editing, obfuscation). We further argue that this confusion is not cosmetic: because papers make different implicit guarantees under the same label, metrics and benchmarks are frequently reused outside their intended scope, rewarding surface-level non-disclosure (e.g., low ROUGE/forget accuracy) even when retraining-equivalence is not tested and derived capabilities remain. We conclude by calling for stricter terminology tied to explicit guarantees and reference models, and for evaluations that match the claimed objective. --- ### Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent Collaboration Authors: Junjie Xu, Xingjiao Wu, Zihao Zhang, Yujia Xu, Yuzhe Yang, Jin Zhu, Luwei Xiao, Wen Wu, Liang He Published: 2026-05-08 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2606.18259v1 AI agents that plan, retain memory across sessions, invoke external tools and act with partial autonomy are transforming human--AI collaboration. Research on affective computing, simulated empathy in large language models, trust in automation and AI safety has illuminated important design principles, yet these literatures remain fragmented. No integrated account explains how affective cues operate within agentic collaboration -- settings in which humans delegate, monitor and correct consequential tasks. This Review synthesises computational and interactional mechanisms of affective dynamics: the processes through which affective cues, emotion-like behaviour and perceived agent affect shape trust calibration, delegation decisions, error correction, dependence and governance. We trace how model-generated affective signals enter interaction loops that govern reliance, repair and oversight, and propose a framework that treats affect not as an internal property of AI but as a coordination layer through which humans and agents negotiate capability, uncertainty and responsibility. The framework provides a foundation for calibrated measurement, purposeful design and informed governance. --- ### Creating and Evaluating K-12 GenAI Assessment Graders Through Context Engineering Authors: Zewei Tian, Alex Liu, Lief Esbenshade, Michael Xiao, Zachary Zhang, Yulia Lápicus, Thomas Han, Kevin He, Min Sun Published: 2026-05-08 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2606.12422v1 The integration of large language models (LLMs) into educational assessment represents a transformative shift in classroom grading practices. While automated scoring systems and machine learning techniques have existed for decades, generative AI (GenAI) now enables educators to implement standards-based grading (SBG) with unprecedented efficiency and scale. This paper examines the theoretical foundations and evaluates an LLM grader that uses commercially available foundation models with context and prompt engineering to score student work against a rubric. Drawing on an empirical interrater agreement study using Massachusetts Comprehensive Assessment System (MCAS) data, we observed the Quadratic Weighted Kappa (QWK) and Proportional Reduction in Mean-Squared Error (PRMSE) across mathematics, science, and ELA, using Claude Sonnet 4, Haiku 4.5, GPT-5, and GPT-5 Mini. The results demonstrate that LLM graders, especially when based on foundational models with more parameters, achieve substantial agreement with human raters in mathematics and science assessments, while the performances vary in ELA, suggesting generic foundation models can be effective at scoring in given contexts. Additional analysis of teacher and student feedback reveals strong acceptance of AI-generated narrative feedback but skepticism toward numerical scores, suggesting that LLMs function most effectively as formative tools rather than summative evaluators. Our findings indicate that thoughtfully designed hybrid models that combine AI efficiency with teacher judgment can reduce workload, enhance feedback quality, and support equitable assessment practices without displacing professional expertise. --- ### Eigenism: Ethics for a Human-AI Future Authors: Dan Hendrycks Published: 2026-05-08 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.12420v1 Our concepts of survival and self-interest were built for single, continuous biological lives. These ideas break down when applied to artificial intelligence, since an AI can be easily copied, paused, branched, or merged. To determine what an AI actually has reason to care about, this paper introduces \textit{Eigenism}, an ethical framework that treats identity not as an all-or-nothing property tied to specific hardware, but as a graded, distributed pattern of information. We propose that an agent evaluates outcomes by summing the wellbeing of all entities weighted by their connectedness to the agent's pattern: $\sum c\cdot w$. We first formalize this equation to map exactly how an AI should value its existence across copies, forks, and updates. We then demonstrate that this ethical theory successfully generalizes to humans as well, providing a much-needed shared moral vocabulary. Finally, the framework uses this shared vocabulary to reframe AI alignment. Rather than only attempting to constrain AIs from the outside using confinement or reinforcement, Eigenism points toward ``identity engineering,'' showing how deep, non-redundant shared histories can make human flourishing a genuine component of an AI's own rational self-interest. --- ### GeoDial: A Multimodal Conversational Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns Authors: Sankalan Pal Chowdhury, Junling Wang, Donya Rooein, April Yi Wang, Mrinmaya Sachan Published: 2026-05-08 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.12419v1 Several educational domains rely heavily on diagrams and visual cues, yet most existing tutoring datasets are limited to text-only interactions. This limits the development of AI tutors that can teach in visually grounded ways used by human instructors. Thus, we introduce GeoDial, a multimodal tutoring dataset of over 1.3K teacher-student dialogs in the domain of geometry collected from experienced math teachers, where instructional turns are explicitly grounded in diagram highlights. We propose a scalable annotation protocol that integrates dialog acts, visual highlighting, and feedback, enabling fine-grained supervision of both language and visual tutoring behavior. To illustrate the challenges posed by this setting, we fine-tune several vision-language models on GeoDial and evaluate their ability to generate tutoring utterances and diagram highlights. While supervised fine-tuning substantially improves the quality of generated dialog, it struggles to produce accurate diagram highlights, revealing a key limitation of current methods and highlighting the need for approaches that more effectively integrate visual reasoning with pedagogical interaction. --- ### Divination by Prompt: LLM-Mediated Xuanxue on Chinese Social Media Authors: Chuang Li, Lixuan Wang, Yuqi Chen, Ze Hong Published: 2026-05-08 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.12418v1 The rapid proliferation of large language models (LLMs) has produced a striking cultural practice: using conversational AI for divination. This paper offers one of the first systematic studies of LLM-mediated divination in the context of Xuanxue, an internet-native umbrella term for mystical and spiritual practices on Chinese social media. Using a mixed-methods design, we analyze 23000+ posts and comments from Xiaohongshu and conduct 32 semi-structured interviews with users and professional diviners. Users primarily consult LLMs about pragmatic concerns - romantic relationships, careers, exams, and in-game gacha draws - via two intersecting pathways: trend-driven curiosity enabled by viral visibility and zero-cost access, and event-driven anxiety under conditions of uncertainty. A defining feature is collaborative prompt refinement, which turns users into active prompt engineers. Among commenters expressing a clear stance, perceived efficacy skews positive, with "accuracy" often justified through biographical fit and retrospective confirmation, consistent with Barnum and confirmation bias. Users also develop verification practices such as repeated trials and cross-model comparison. Professional diviners, by contrast, portray LLMs as lacking the "spiritual power" required for genuine divination, reflecting both ontological commitments and economic boundary-work. We also show how participants navigate tensions between scientific and metaphysical frames when interpreting AI-generated readings. Situating these findings in anthropological and cognitive-evolutionary theories of divination, we argue that LLM divination preserves core functions of traditional practice while introducing scalability, repeatability, and prompt-driven co-production that reshape how divinatory authority is constructed and evaluated. --- ### Business Utility of Large Language Models as Exploratory Data Analysis Agents Authors: Rafał Łabędzki, Patryk Miziuła, Hubert Rutkowski, Szymon Betlewski, Cezary Depta, Szymon Janowski, Jarosław Kochanowicz, Jan Kanty Milczek Published: 2026-05-08 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.00051v1 Large Language Models (LLMs) are increasingly used in analytical workflows, but their suitability as exploratory data analysis (EDA) agents in business settings remains uncertain. In practice, a deployable EDA agent must provide not only useful average performance but also sufficient repeatability to support trust in its outputs. We evaluate this requirement in a controlled, business-relevant benchmark built on an agent-based supply chain simulation. The task is to identify supplier-product combinations responsible for low quality and downstream sales loss by reasoning from indirect operational traces rather than from explicit labels. Fifteen model-variant configurations from eight model families were evaluated under four experimental conditions that varied data representation, prompt clarity, and signal strength, with five trajectories per condition. Outputs were scored against deterministic ground truth using the Jaccard index and assessed through a framework that combines mean score (ms), coefficient of variation (CV), exploratory cross-condition significance tests, and Business utility, a risk-adjusted metric that we propose to summarise quality and repeatability in a single operational measure. The results show that most configurations are not reliable enough for autonomous EDA use, even when their average scores appear acceptable. GPT-5.4 with extra-high reasoning effort achieved the strongest overall profile, with an experiment-averaged ms of 0.8748 and an experiment-averaged Business utility of 0.6952, while the next-best configurations lost substantially more utility after variability discounting. Our findings suggest that evaluation of EDA agents should treat average quality, repeatability, and condition sensitivity as complementary dimensions of operational trustworthiness. --- ### Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts Authors: Zixuan Huang, Da Chen, Kecheng Huang, Lihao Yin, Xing Li, Huiling Zhen, Mingxuan Yuan, Zili Shao Published: 2026-05-08 Categories: cs.NE, cs.DC, cs.LG, cs.PF, cs.SE, eess.SY arXiv: https://arxiv.org/abs/2605.30359v2 Generating high-performance GPU kernels remains challenging due to the need for both correctness and hardware-aware optimization. While large language models (LLMs) show promise in code generation, they often fail to produce kernels that are both correct and efficient. We propose Kernel Foundry, a diagnosis-driven evolutionary framework for automatic GPU kernel optimization. Our method combines expert-guided, retrieval-augmented initialization with a multi-island evolutionary search, where candidate kernels are iteratively refined using structured diagnostic feedback. A centralized experience library accumulates reusable optimization knowledge to guide subsequent evolution, while explicit mechanisms prevent cheating behaviors that bypass kernel-level computation. Experiments on KernelBench show that our method consistently improves both correctness and performance over strong baselines, achieving up to 100% correctness on Level~2. --- ### Benchmarking Fairness in Spiking Neural Networks: Data Bias, Spurious Features, and Hardware Effects Authors: Hudi He, Fukun Wang, Zhe Wang, Xinyi Wang, Shuhan Ye, Jiarui Liu, Qing Qing, Ziqi Xu, Xikun Zhang, Renqiang Luo Published: 2026-05-08 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.27407v1 Evaluating fairness in Spiking Neural Networks (SNNs) demands rigorous benchmarks that reflect real-world complexities, yet existing assessments remain limited by superficial dataset diversity and idealized hardware assumptions. This work introduces the first systematic fairness benchmark for SNNs, addressing three critical dimensions of realism: (1) demographic coverage gaps in training data, (2) spurious feature leakage (e.g., skin tone as a proxy for class labels), and (3) deployment-environment mismatches (e.g., edge devices with constrained spike encoding). Our framework integrates four cross-demographic datasets with controlled bias injections and three neuromorphic hardware simulators (Loihi 2, SpiNNaker), enabling isolated analysis of fairness-performance trade-offs under resource constraints. Standardized evaluations of 12 state-of-the-art SNNs reveal stark disparities: models trained on biased data exhibit 23\% higher false positive rates for underrepresented groups, while hardware limitations (e.g., reduced spike precision) further amplify accuracy gaps by up to 41\% in edge deployments. Critically, bias mitigation strategies developed for cloud-based SNNs often degrade under resource constraints, highlighting the need for co-design principles that jointly optimize fairness and hardware efficiency. By bridging algorithmic fairness research with neuromorphic engineering, our benchmark provides a foundation for trustworthy SNNs in socially critical applications such as healthcare and autonomous systems. Our code is available at: https://anonymous.4open.science/r/SNN-Benchmarks-8017. --- ### Multivariate Financial Forecasting using the Chronos Time Series Foundation Models Authors: Sanjiv R Das, Tarang Goyal, Mohini Yadav Published: 2026-05-08 Categories: q-fin.ST, cs.AI arXiv: https://arxiv.org/abs/2605.21504v1 Using Chronos-2, an open-source time-series foundation model, we evaluate pretrained time-series models for economic and financial forecasting with an emphasis on whether multivariate (MV) inputs improve accuracy relative to univariate (UV) baselines. The study covers two panels -- the Magnificent-7 equities and U.S. Treasury interest rates -- as well as a combined panel, using rolling monthly evaluations from 2000--2025. We vary input window lengths and forecast horizons and report RMSE and MAPE. Across datasets, MV forecasts consistently outperform UV forecasts, with especially strong gains for interest rates and meaningful improvements for equities. Series-level comparisons show MV improvements in every case, and error dispersion is generally lower under MV inputs. We also provide parameter-heatmap and time-series visualizations. However, mixing time series across equity and interest rate markets reduces forecast accuracy, indicating that adding noisy context degrades model performance. Overall, the results indicate that foundation models can leverage cross-series information to improve forecast accuracy in finance, and that the benefits are strongest when related series are modeled jointly under disciplined rolling protocols. Other than using an open-source foundation model, this paper also showcases how AI may be used for financial research. --- ### Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks Authors: Kyle Higgins, Ivan Laponogov, Dennis Veselkov, Kirill Veselkov Published: 2026-05-08 Categories: q-bio.MN, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.21502v1 Graph neural networks (GNNs) are increasingly used to model biological systems, yet the reliability of post-hoc explanation methods for recovering meaningful molecular mechanisms remains unclear. Here, we systematically evaluate four widely used approaches: Saliency Attribution (SA), Integrated Gradients (IG), GNNExplainer, and Layer-wise Relevance Propagation (LRP) for identifying disease-relevant structure in breast cancer RNA-seq data projected onto a protein-protein interaction network. Using synthetic benchmarks with known ground-truth motifs, we show that explanation methods recover distinct signal organizations: SA performs best for sparse single-node drivers, whereas IG and LRP preferentially recover distributed pathway-like and cascade-like signals. In TCGA BRCA data, we identify a consistent topological signature of disease-associated hubs in which attribution peaks in the immediate 1-hop neighborhood and decays across successive network shells, a pattern most pronounced for IG and LRP and associated with strong enrichment of known cancer hubs. We further observe a trade-off between local hub enrichment and global gene ranking performance, with IG optimizing local enrichment and SA achieving superior global discrimination. Motivated by these complementary behaviors, we introduce a framework combining a shell-based hub score with consensus ranking across explainers. Consensus scores improve prioritization of canonical cancer genes (TP53, BRCA1, ESR1, MYC), reduce dependence on node degree, and, especially when tuned, outperform individual methods. Pathway enrichment further reveals improved recovery of biologically coherent cancer programs, including ERBB2, RTK, MAPK, immune, and cytokine signaling. Together, these results demonstrate that topology-aware integration of graph explanations can improve biological interpretability and biologically relevant molecular recovery. --- ### A Task-Agnostic Algebraic Integrity Metric for Event-Camera Streams Toward SOTIF-Compliant Perception using Pearson Correlation Coefficient Authors: Arthur de Miranda Neto Published: 2026-05-08 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2605.21500v1 Event cameras have emerged as a high-bandwidth, low-latency sensing modality for safety-critical perception in automated driving systems (ADS), offering microsecond temporal resolution, 120-140 dB dynamic range, and intrinsic absence of motion blur. However, no task-agnostic quality metric currently operates directly on the asynchronous event stream: state-of-the-art proxies require a downstream task (e.g., detection accuracy, tracking error) to assess stream integrity, which is incompatible with the certification requirements of ISO 21448 (SOTIF) and ISO/PAS 8800:2024. The recent BiasBench benchmark (CVPR 2025) explicitly identifies this gap. This work proposes a unified algebraic framework that lifts the Pearson Correlation Coefficient (PCC), historically used in two prior works for redundancy filtering and ROI selection on frame-based images, to the three standard event representations: Time Surface, Event Frame, and Voxel Grid. The framework yields three metrics: (i) r-TS for stream integrity monitoring against an ego-motion-predicted Time Surface, (ii) r2-EF for adaptive ROI selection requiring only integer comparisons, and (iii) r-VG for temporal redundancy gating. A structural isomorphism is established between the contrast-threshold mechanism of the event camera (|Delta L| >= C) and the PCC-based change criterion, the three lifted metrics are formalized, and pipeline latency and information loss are analyzed symmetrically against the raw stream. Illustrative behavior of each metric is demonstrated on a procedural-synthetic event stream, generated by direct simulation of the emission model rather than drawn from any real or video-derived dataset, including a tunnel-dip integrity-anomaly scenario in which r_C drops from 0.93 (coherent flow) to below 0 (alarm). An explicit epistemic convention ((ESTABLISHED), (SOLID), (HYPOTH.), (OPEN)) delineates the status of every contribution. --- ### Generative 3D Gaussians with Learned Density Control Authors: Runjie Yan, Yan-Pei Cao, Peng Wang, Ding Liang, Yuan-Chen Guo Published: 2026-05-08 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2605.16355v1 We present Density-Sampled Gaussians (DeG), a novel 3D representation designed to bridge the gap between adaptive rendering primitives and scalable generative modeling. Unlike existing approaches that constrain 3D Gaussians to fixed voxel grids or arrays, DeG models Gaussian centers as samples from a learnable probability density function defined over an octree. This formulation provides a rigorous mathematical framework for adaptive density control: by jointly optimizing the spatial density and Gaussian attributes under rendering supervision, our model naturally concentrates primitives in regions of high geometric complexity. We achieve this via a new render loss contribution gradient that serves as a fully differentiable analogue to the discrete densification and pruning heuristics used in standard Gaussian Splatting. The resulting representation is highly flexible, supporting variable-resolution decoding from a single latent code by simply adjusting the sampling budget. To enable generative synthesis, we train a latent diffusion model on DeG. We identify a critical challenge in applying diffusion to unordered set-structured latents, which can significantly slow convergence, and propose VecSeq, a canonical re-indexing mechanism that anchors latent tokens to a deterministic 3D Sobol sequence. This transforms the ambiguous set-generation problem into a robust sequence modeling task. Extensive experiments demonstrate that our pipeline achieves state-of-the-art quality in single-image-to-3D generation, combining the structural adaptivity of unstructured primitives with the training stability of grid-based methods. --- ### Augmenting Human Evaluation with LLM Judges: How Many Human Reviews Do You Need? Authors: Jane Paik Kim Published: 2026-05-08 Categories: cs.LG, cs.AI, cs.CL, cs.HC, stat.ML arXiv: https://arxiv.org/abs/2605.16354v1 Large language models (LLMs) are increasingly used as automated evaluators of AI systems, including in high-stakes applications. In this role, LLMs are used to generate judgments about the quality, appropriateness, or even safety of model outputs. This approach is motivated by practical constraints. Expert human ratings are costly and difficult to scale, whereas LLM ratings can be produced quickly at low cost. However, current approaches to deploying LLM evaluators are ad hoc, typically limited to reporting agreement metrics between human and LLM judges as a justification for substitution of human ratings, and lack a formal basis for study design. This paper (1) shifts the role of the LLM judge from substitutive to auxiliary, and (2) formulates the LLM-as-a-judge paradigm as one of augmenting human evaluation through a two-stage sampling design, where LLM evaluations are measured for all observations at the first stage and human ratings are partially observed for a subsample at the second stage. We propose to use a doubly robust estimator from the missing data literature, which takes advantage of the robustness property against the prediction model, since the missingness model is known by design. Using the asymptotic variance of this estimator, we propose how sample sizes of human and LLM ratings can be determined to achieve a targeted level of power. We also show that a study can be efficiently designed by allocating more human ratings for types of evaluations where the predictability of LLM ratings is not high. To the best of our knowledge, there is very little guidance on how much human oversight should be retained when validating benchmarks. --- ### StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMs Authors: Chang Che, Ziqi Wang, Hui Ma, Cheems Wang, Zenglin Shi Published: 2026-05-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.16353v2 Continual Visual Instruction Tuning (CVIT) enables Multimodal Large Language Models to incrementally acquire new abilities. However, existing CVIT methods operate under a restrictive task-incremental setting, where each training phase corresponds to a single, predefined task. This does not reflect real-world conditions, where data arrives as a continuous stream of interleaved and dynamically evolving tasks. To bridge this gap, we introduce Streaming CVIT (StrCVIT), a more general and realistic setting where models learn from a stream of data chunks containing a dynamic mixture of tasks. In StrCVIT, a model must simultaneously acquire new abilities, reinforce recurring abilities, and mitigate forgetting. Existing CVIT methods fail here as they cannot reliably distinguish or adapt to the heterogeneous task samples within each chunk. We therefore propose StrLoRA, a regularized two-stage expert routing framework. StrLoRA first performs task-aware expert selection using the textual instruction to activate a sparse subset of relevant experts, reducing cross-task interference. It then applies token-wise expert weighting within this subset, where contribution weights are computed via cross-modal attention between local visual tokens and the global instruction representation. To maintain stability across the non-stationary stream, a routing-stability regularization aligns current routing distributions with a historical exponential moving average reference. Extensive experiments on a newly developed StrCVIT benchmark show that StrLoRA substantially outperforms existing methods, effectively enhancing model's abilities from continuously evolving data streams. The code is available at https://github.com/chanceche/StrCVIT. --- ### LARGER: Lexically Anchored Repository Graph Exploration and Retrieval Authors: Yuntong Hu, Tongli Su, Liang Zhao, Bowen Zhu, Hasibul Haque Published: 2026-05-08 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.16352v1 Repository-level coding agents must first localize the files and symbols relevant to a task; failures at this stage can cascade across downstream objectives ranging from patch generation to test writing and codebase question answering. Existing agents navigate repositories primarily through lexical search, often missing structural relations such as imports, call chains, type hierarchies, and code-test links. Graph-based retrieval can recover such dependencies, but existing approaches often require separate graph tools or traversal stages that fragment the agent's interaction loop. We formalize repository context localization as Lexically Anchored Structural Localization, where success depends on turning lexical matches into high-precision structural entry points and exposing the most useful confidence-filtered local neighborhoods within the agent's existing search loop. We introduce LARGER (Lexically Anchored Repository Graph Exploration and Retrieval), a lexically anchored active-set retrieval framework that starts from lexical matches, aligns them to graph anchors, and performs confidence-filtered local expansion within the agent's existing search loop. LARGER integrates directly into existing CLI coding agents without requiring external graph databases or specialized graph interfaces. Across four benchmarks spanning localization, test generation, and codebase understanding, LARGER improves file-level Acc@5 on LocBench by +13.9 points with tuned hyperparameters and still gains +11.8 points with fixed hyperparameters over the strongest baseline, while delivering consistent gains on MuLocBench, SWE-Atlas Test Writing, and SWE-Atlas Codebase QA. --- ### PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution Shift Authors: Sangyoon Bae, Shinjae Yoo, Jiook Cha Published: 2026-05-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16351v1 Scientific foundation models are expected to reuse representations under changes in dataset, acquisition protocol, and deployment domain, yet many sequence backbones treat scientific temporal structure as an unconstrained pattern to be fitted. We argue that this misses a central property of natural dynamical systems: neural and atmospheric time series are organized by interacting processes across multiple physical timescales, and failure to preserve this multiscale structure contributes to brittleness under distribution shift. We formalize this failure mode as temporal kernel mismatch, where a model fits in-distribution dynamics with an effective memory policy that is not anchored to the signal's physical timescales, leading to representation drift and degraded transfer. We propose Physics-Informed Multi-Scale Mamba (PIMSM), a state-space architecture that maps spectrum-estimated transition points between frequency regimes (knee frequencies) to scale-specific discretization parameters and anchors them to acquisition time units. On Human Connectome Project fMRI, PIMSM improves robustness and representation stability under severe temporal-context truncation, extreme low-resource transfer, and resting-state-to-task-state generalization. Without modality-specific adaptation, the same architecture also attains the lowest variable-wise MAE across all reported horizons and variables on Weather-5K held-out-station spatial out-of-distribution forecasting. These results support temporal-scale alignment as a practical inductive bias for scientific foundation models that must preserve structure, not only fit correlations, under deployment shift. --- ### Federated Nested Learning: Collaborative Training of Self-Referential Memories for Test-Time Adaptation Authors: Hong Chen, Pengcheng Wu, Yuanguo Lin, Peilin Zhao, Xiuze Zhou, Fan Lin, Han Yu Published: 2026-05-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16350v1 We rethink Federated Learning (FL) from a nested learning perspective, framing the core challenge as how to collaboratively learn optimization rules, not just static models, to tackle Non-IID client data. To address this, we propose Federated Nested Learning (FedNL), a novel framework that reformulates FL as a three-level nested optimization system. FedNL embeds Titans-based linear attention into FL, enabling clients to perform lightweight, zero-shot test-time adaptation by treating a delta rule as an online gradient step. Experiments on Non-IID MMLU and long-context benchmarks show that FedNL achieves competitive performance in short-context reasoning, enhances the performance of long-context retrieval and streaming Cross-Entropy, and maintains constant inference memory. --- ### Geometric Asymmetry in MoE Specialization: Functional Decorrelation and Representational Overlap Authors: Feilong Liu Published: 2026-05-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.16349v1 Mixture-of-Experts (MoE) architectures achieve scalable capacity through sparse routing, yet the geometric structure of expert specialization remains poorly understood. We introduce a unified Jacobian-PCA-Grassmann framework for analyzing MoE layers in both function space and representation space. Across pretrained MoE Transformers (Mistral, Qwen), we find a consistent structural asymmetry: experts exhibit strong functional decorrelation (consistently low, near-zero cross-expert Jacobian alignment) while their routed representations occupy distinct but partially overlapping subspaces. This indicates that functional decorrelation and representation overlap coexist rather than coincide in MoE specialization. Controlled routing experiments further indicate that routing sparsity appears to be a key factor shaping this geometry: top-k routing induces sharper functional separation and larger subspace divergence, whereas fully soft routing yields more entangled expert structure. Together, these results suggest a geometric interpretation in which MoE layers may be viewed as implementing locally decorrelated operators over overlapping submanifolds on a shared representation manifold, and provide a general diagnostic framework for studying conditional computation in modern Transformer architectures. --- ### Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field Authors: Kim Yong Tan, Yueming Lyu, Ivor Tsang, Yew-Soon Ong Published: 2026-05-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16348v1 Training-free guidance enables pre-trained diffusion and flow models to optimize application-specific objectives using feedback from external black-box reward functions. However, existing methods are feedback-inefficient because reward feedback is used only transiently to inform a localized gradient approximation or a discrete search decision, and is subsequently discarded. To address this limitation, we propose Flow-Direct, a framework that guides the generation process via a persistent guidance field. Theoretically, this guidance field is analytically derived from the log-density ratio between the base and reward-weighted target distributions; it transports the pre-trained distribution to the target distribution. In practice, the field is implemented as a non-parametric estimator constructed from all accumulated reward-evaluated samples. As more samples are collected during optimization, this empirical guidance field becomes increasingly accurate. This persistent formulation yields two major advantages. First, Flow-Direct is highly feedback-efficient: because every evaluated sample is used to refine the global guidance field, no reward information is wasted. Second, the framework is naturally reusable: once optimization is complete, the collected dataset defines a reusable guidance field for generating novel target samples without additional reward evaluations, and distinct guidance fields can be combined to generate samples that simultaneously satisfy multiple objectives. --- ### HPC-LLM: Practical Domain Adaptation and Retrieval-Augmented Generation for HPC Support Authors: Nourin Shahin, Izzat Alsmadi Published: 2026-05-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.16347v1 Modern scientific research increasingly depends on High-Performance Computing (HPC) infrastructures, yet many researchers face significant operational barriers when interacting with cluster environments, job schedulers, GPU resources, and parallel computing frameworks. General-purpose large language models (LLMs) provide useful coding assistance but often lack the domain-specific operational knowledge required for reliable HPC support. This paper presents HPC-LLM, a retrieval augmented and domain-adapted assistant designed to support common HPC workflows including Slurm scheduling, MPI execution, GPU utilization, filesystem management, and cluster troubleshooting. The proposed framework integrates automated documentation ingestion, dense retrieval, lightweight domain adaptation using QLoRA, and local inference within a modular orchestration pipeline. To support domain adaptation, we construct an HPC-oriented corpus from publicly available university HPC documentation, curated operational examples, and synthetic instruction-answer pairs generated from retrieved HPC content. The resulting dataset contains approximately 9,000 to 24,000 HPC-focused training examples spanning job scheduling, GPU computing, distributed training, storage systems, and cluster administration topics. We fine-tune Llama 3.1 8B using QLoRA and evaluate the resulting model against several open weight baselines under retrieval-augmented settings on JetStream2 infrastructure. Experimental results indicate that the adapted 8B model achieves performance comparable to substantially larger general-purpose models while operating under significantly lower GPU memory requirements and inference latency. In particular, the adapted model approaches the performance of Qwen 2.5 14B while requiring substantially fewer computational resources. --- ### PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation Authors: Bingyu Yan, Xiaoming Zhang, Jinyu Hou, Chaozhuo Li, Ziyi Zhou, Xiaozhe Zhang, Litian Zhang Published: 2026-05-08 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.16346v1 LLM-based multi-agent systems (LLM-MAS) have become a promising paradigm for solving complex tasks through role specialization, tool use, memory, and collaborative reasoning. However, these interactions create new security risks that malicious instructions injected through messages, tools, or memories can propagate across agents and rounds, causing system-level compromise. Existing defenses largely rely on local filtering or graph-based anomaly detection, but they often fail to trace fine-grained propagation paths or remediate contaminated states without disrupting benign collaboration. We propose PropGuard, a propagation-aware framework for safeguarding LLM-MAS. PropGuard constructs a dual-view spatio-temporal graph that combines response-centric risk estimation with full-state evidence preservation. Guided by these risk priors, a GE-GRPO trained inspector sequentially explores the full-state graph to recover compact suspicious propagation subgraphs. PropGuard then verifies harmful propagation through subgraph-aware diagnosis and applies source-guided remediation to correct upstream contamination and replay affected downstream interactions. Experiments across four communication architectures and five attack settings demonstrate that PropGuard consistently lowers attack success while maintaining high task-level defense success, achieving a favorable effectiveness--efficiency trade-off. --- ### Goal-Conditioned Supervised Learning for LLM Fine-Tuning Authors: Shijun Li, Kaiwen Dong, Xiang Gao, Joydeep Ghosh Published: 2026-05-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16345v2 Large language models often require fine-tuning to better align their behavior with user intent at deployment. Existing approaches are commonly divided into online and offline paradigms. Online methods, such as RL-based alignment, can directly optimize outcome quality but typically rely on external reward models and iterative rollouts, making them costly and difficult to deploy in many cases. Offline methods are more efficient, but prevailing approaches such as supervised fine-tuning (SFT) and direct preference optimization (DPO) remain limited: SFT typically collapses graded feedback into binary supervision, while DPO depends on paired preference data that is often unavailable or expensive to construct. In this paper, we propose goal-conditioned supervised learning (GCSL) as an offline fine-tuning framework for LLMs. Our core idea is to treat feedback signals directly as an explicit goal and train the model, purely through supervised learning, to generate responses that achieve that goal. To better exploit graded feedback, we further introduce a novel goal formulation that defines learning as consistently pursuing outcomes above a target quality threshold, rather than imitating samples from a selected high-quality subset. This design mitigates the bounded-learning effect by learning transferable patterns of meeting or exceeding quality thresholds. We also propose natural-language goal representations to further connect these patterns to the LLM's pretrained knowledge and generalization capabilities. We evaluate our method on three tasks: non-toxic generation, code generation, and LLM for recommendation. Results show that our approach consistently outperforms standard offline fine-tuning baselines while retaining the efficiency, scalability, and simple data requirements of supervised learning. --- ### Goal-Conditioned Supervised Learning for LLM Fine-Tuning Authors: Shijun Li, Kaiwen Dong, Xiang Gao, Joydeep Ghosh Published: 2026-05-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16345v1 Large language models often require fine-tuning to better align their behavior with user intent at deployment. Existing approaches are commonly divided into online and offline paradigms. Online methods, such as RL-based alignment, can directly optimize outcome quality but typically rely on external reward models and iterative rollouts, making them costly and difficult to deploy in many cases. Offline methods are more efficient, but prevailing approaches such as supervised fine-tuning (SFT) and direct preference optimization (DPO) remain limited: SFT typically collapses graded feedback into binary supervision, while DPO depends on paired preference data that is often unavailable or expensive to construct. In this paper, we propose goal-conditioned supervised learning (GCSL) as an offline fine-tuning framework for LLMs. Our core idea is to treat feedback signals directly as an explicit goal and train the model, purely through supervised learning, to generate responses that achieve that goal. To better exploit graded feedback, we further introduce a novel goal formulation that defines learning as consistently pursuing outcomes above a target quality threshold, rather than imitating samples from a selected high-quality subset. This design mitigates the bounded-learning effect of SFT and classic GCSL by explicitly guiding the model to learn the directional progression of quality. We also propose natural-language goal representations to better leverage the semantic understanding and reasoning capabilities of LLMs. We evaluate our method on three tasks: non-toxic generation, code generation, and LLM for recommendation. Results show that our approach consistently outperforms standard offline fine-tuning baselines while retaining the efficiency, scalability, and simple data requirements of supervised learning. --- ### A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems Authors: Yichu Zhou, Mehdi Ben Ayed, Lin Yang, Jiacong He, Andreanne Lemay, Jiaye Wang, Jaewon Yang, Josie Zeng, Dhruvil Deven Badani, Yijie Dylan Wang, Jiajing Xu, Charles Rosenberg Published: 2026-05-08 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2605.16344v1 Large-scale recommenders encode multi-objective trade-offs by combining multiple predicted outcomes into a single utility score. Although this utility layer can be updated independently of the ranker, weight tuning remains largely manual, globally applied, slow to adapt to changing environments and business needs, and hard to govern as priorities shift. We propose PRL-PUTS, a Production-ready, ranker independent RL framework for Personalized Utility-weight Tuning with Pareto Sweeping. We cast utility tuning as a one-step, value-based RL problem: given request context, an agent selects a utility-weight vector that re-weights ranker predictions to maximize request-level engagement rewards. To visualize performance across the trade-off spectrum and allow decision makers to update the deployed operating policy instantly, we adopt an inference-time Pareto frontier sweeping via a scalarization parameter, producing a family of policies and an empirical Pareto frontier used as a governance artifact for operating policy selection. PRL-PUTS runs in parallel with ranking inference without adding serving latency. We validate PRL-PUTS with offline analysis using unbiased exploration logs and online experiments on Pinterest Homefeed where PRL-PUTS showed significant increases in engagement compared to baseline such as +0.13\% increase in successful session, a core metric for user engagement. --- ### LoopQ: Quantization for Recursive Transformers Authors: Rui Fang, Hsi-Wen Chen, Ming-Syan Chen Published: 2026-05-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.16343v1 Looped language models (LoopLMs) improve parameter efficiency by recursively reusing Transformer blocks, enabling deeper computation under a fixed model size. However, this reuse makes LoopLMs more fragile under post-training quantization (PTQ). We present the first systematic study of quantization in LoopLMs and identify three challenges: distribution shift across roles, state reuse across loop transitions, and recursive error accumulation. To address these challenges, we propose LoopQ, a loop-aware PTQ framework that preserves a shared quantized backbone while introducing lightweight adaptations. LoopQ combines activation scaling, selective transformation, cross-loop state alignment, and trajectory-aware optimization to reduce distributional mismatch within loops and error accumulation across loops. Experiments across seven benchmarks show that, under W4A4 quantization, LoopQ improves average downstream accuracy by 68.8% and reduces average perplexity by 87.7% compared with the strongest static PTQ baseline. --- ### DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models Authors: Amin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade, Lokesh Boominathan, Manuel R. Ciosici, Yizhe Zhang, Irina Belousova Published: 2026-05-08 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.16342v1 Diffusion large language models are a compelling alternative to autoregressive models, yet existing RL methods for diffusion treat all denoising steps as equally important and rely on biased, high-variance likelihood estimates. We identify two fundamental weaknesses: the absence of temporal credit assignment across the denoising trajectory, and the systematic bias of mean-field likelihood estimates used for policy optimization. To address these, we propose Denoising-Aware Credit Assignment for GRPO (DACA-GRPO), a lightweight, plug-and-play enhancement for any GRPO-style trainer. DACA-GRPO introduces two complementary mechanisms: Denoising Progress Scores, which extract per-token importance weights from intermediate predictions at no additional forward cost, and Stratified Masking Likelihood, which partitions token positions into strata so that each token is predicted with most of the sequence as context, reducing the mean-field bias. Applied on top of three GRPO base methods, DACA-GRPO achieves consistent improvements across seven benchmarks spanning mathematical reasoning, code generation, constraint satisfaction, and constrained generation, with gains of up to 5.6pp on math reasoning, 7.4pp on code generation, 36.3pp on constraint satisfaction, and 5.9pp on JSON schema adherence. --- ### GEAR: Genetic AutoResearch for Agentic Code Evolution Authors: Ahmadreza Jeddi, Minh Ngoc Le, Hakki C. Karaimer, Konstantinos G. Derpanis, Babak Taati Published: 2026-05-08 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2605.13874v1 Autonomous research agents can already run machine learning experiments without human supervision, but many rely on a narrow search strategy: they repeatedly modify one program and keep changes only when they improve the current best result. This can cause them to discard useful partial ideas, alternative promising directions, and insights from failed or incomplete experiments. GEAR, or Genetic AutoResearch, replaces this single-path search with a population-based search over multiple research states. It keeps a set of strong candidate solutions, selects parents based on productivity, novelty, and coverage, and explores new ideas through mutation and crossover. Each research state stores its code changes, reflections, and performance data, allowing future decisions to build on past discoveries. The paper studies three versions of GEAR: one controlled through prompting, one using a fixed programmatic search controller, and one where the controller itself can evolve during the run. Under the same compute budget and environment, all three versions outperform the AutoResearch baseline. More importantly, while the baseline tends to settle into one local optimum, GEAR continues finding improvements over longer runs. Overall, the results suggest that autonomous research agents become more effective when they maintain multiple promising directions and can adapt their search strategy over time. --- ### Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation Authors: Md Sazzad Hossen, Avimanyu Sahoo Published: 2026-05-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.10975v1 Graphs with heterophily, where adjacent nodes carry different labels, are prevalent in real-world applications, from social networks to molecular interactions. However, existing spectral Graph Neural Network (GNN) approaches tailored for heterophilous graph classification suffer from hub-dominated (node with large degree) aggregation and oversmoothing, as their suboptimal polynomial filters introduce approximation errors and blend distant signals. To address the degree-biased aggregation and suboptimal polynomial filtering, we introduce a Hierarchical Multi-view HAAR (HMH), a novel spectral graph-learning framework that scales in near-linear time . HMH first learns feature- and structure-aware signed affinities via a heterophily-aware encoder, then constructs a soft graph hierarchy guided by these embeddings. At each hierarchical level, HMH constructs a sparse, orthonormal, and locality-aware Haar basis to apply learnable spectral filters in the frequency domain. Finally, skip-connection unpooling layers combine outputs from all hierarchical levels back into the original graph, effectively preventing hub domination and long-range signal bottleneck (over-squashing). Experimentation shows that HMH outperforms state-of-the-art spectral baselines, achieving up to a 3% improvement on node classification and 7% points on graph classification datasets, all while maintaining linear scalability. --- ### Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization Authors: Navid Rezazadeh, Arash Gholami Davoodi Published: 2026-05-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.10974v1 Certified verification of transformer attention requires bounding the softmax function over interval constraints on the pre-softmax scores. Existing verifiers relax softmax ndependently of the downstream objective, leaving avoidable slack. We prove that the exact optimum of this score-box problem is attained at a vertex of the constraint box, and establish a threshold structure theorem showing that, after sorting the objective coefficients, the optimum lies among only linearly many candidates, yielding the Vertex-Softmax primitive with log-linear complexity in the sequence length. We further prove a formal optimality result showing that Vertex-Softmax is the tightest sound bound obtainable from score intervals alone, characterizing precisely what additional structure (score correlations, score-value coupling) is needed for further improvement. Integrated into a CROWN Convex Relaxation based Optimization for Worst-case Neurons)-style verifier with a formal soundness guarantee, Vertex-Softmax significantly improves certified rates and substantially tightens lower bounds across MNIST, Fashion-MNIST, and CIFAR-10 attention models, while consistently matching or outperforming alpha-CROWN and branch-and-bound baselines at a fraction of their cost. --- ### Rotation-Preserving Supervised Fine-Tuning Authors: Hangzhan Jin, Tianwei Ni, Lu Li, Pierre-Luc Bacon, Mohammad Hamdaqa, Doina Precup Published: 2026-05-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.10973v1 Supervised fine-tuning (SFT) improves in-domain performance but can degrade out-of-domain (OOD) generalization. Prior work suggests that this degradation is related to changes in dominant singular subspaces of pretrained weight matrices. However, directly identifying loss-sensitive directions with Hessian or Fisher information is computationally expensive at LLM scale. In this work, we propose preserving projected rotations in pretrained singular subspaces as an efficient proxy for Fisher-sensitive directions, which we call Rotation-Preserving Supervised Fine-Tuning (RPSFT). RPSFT penalizes changes in the projected top-$k$ singular-vector block of each pretrained weight matrix, limiting unnecessary rotation while preserving task adaptation. Across model families and sizes trained on math reasoning data, RPSFT improves the in-domain/OOD trade-off over standard SFT and strong SFT baselines, better preserves pretrained representations, and provides stronger initializations for downstream RL fine-tuning. Code is available at \href{https://github.com/jinhangzhan/RPSFT.git}{https://github.com/jinhangzhan/RPSFT}. --- ### Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models Authors: Hanhan Zhou, Shamik Roy, Rashmi Gangadharaiah Published: 2026-05-08 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.10971v1 Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive models. Controlled generation methods for DLMs, imported from autoregressive models, apply uniform intervention at every denoising steps. We show this uniform schedule degrades quality, and the damage compounds when multiple attributes are steered jointly. To diagnose the failure, we train sparse autoencoders on four DLMs (124M-8B parameters) and find that different attributes commit on distinct schedules, varying in timing, sharpness, and magnitude. For instance, topic commits within the first 2\% of denoising, whereas sentiment emerges gradually over 20\% of the process. Consequently, uniform intervention wastes steering capacity on steps where the target attribute has already solidified or has yet to emerge. We propose a novel adaptive scheduler that concentrates interventions on the steps where an attribute is actively forming and leaves the rest of generation untouched. The cost-control trade-off admits a closed-form characterization: the advantage of adaptive over uniform scheduling is governed by a single dispersion statistic of the commitment distribution. Across four DLMs and seven steering tasks, our method achieves precise control without the degradation typical of uniform interventions. Especially on challenging simultaneous three-attribute control, it reaches up to 93\% steering strength, beating the strongest baseline by up to 15\% points while preserving generation quality. --- ### Context-Gated Associative Retrieval: From Theory to Transformers Authors: Moulik Choraria, Argyrios Gerogiannis, Vidhata Jayaraman, Ankur Mani, Lav R. Varshney Published: 2026-05-08 Categories: cond-mat.dis-nn, cs.AI arXiv: https://arxiv.org/abs/2605.10970v1 Hopfield networks and their generalizations have established deep connections among biological associative memories, statistical physics, and transformers. Yet most models treat retrieval as a fixed query-to-memory mapping, ignoring the role of external context in recall. In this work, we propose a two-stage associative memory architecture, wherein a context-gate subcircuit reshapes the retrieval energy landscape before and during recall. We show theoretically that context gating increases inter-memory separation while inducing sparsity, translating into exponential improvements in retrieval. Crucially, we prove that the system admits a unique self-consistent fixed point, revealing that the resulting retrieval state is driven by both a direct contextual bias and a second-order retrieval-gate feedback loop. We then bridge this theory to transformers; specifically, we evaluate a first-order approximation on Llama-3, confirming that in-context learning acts as context-gated retrieval. Native dynamics mirror our theory: context localizes a memory subspace, enabling the zero-shot query to cleanly discriminate. Ultimately, this framework provides a mechanistic link between associative memory theory and LLM phenomenology. --- ### MMTB: Evaluating Terminal Agents on Multimedia-File Tasks Authors: Chiyeong Heo, Jaechang Kim, Junhyuk Kwon, Hoyoung Kim, Dongmin Park, Jonghyun Lee, Jungseul Ok Published: 2026-05-08 Categories: cs.MM, cs.AI arXiv: https://arxiv.org/abs/2605.10966v1 Terminals provide a powerful interface for AI agents by exposing diverse tools for automating complex workflows, yet existing terminal-agent benchmarks largely focus on tasks grounded in text, code, and structured files. However, many real-world workflows require practitioners to work directly with audio and video files. Working with such multimedia files calls for terminal agents not only to understand multimedia content, but also to convert auditory and visual evidence across related files into appropriate actions. To evaluate terminal agents on multimedia-file tasks, we introduce MultiMedia-TerminalBench (MMTB), a benchmark of 105 tasks across 5 meta-categories where terminal agents directly operate with audio and video files. Alongside MMTB, we propose Terminus-MM, a multimedia harness that extends Terminus-KIRA with audio and video perception for terminal agents. Together, MMTB and Terminus-MM support a controlled study of multimedia terminal agents, revealing how different forms of multimedia access shape task outcomes and determine which evidence agents rely on to construct executable terminal workflows. MMTB media and metadata are released at https://huggingface.co/datasets/mm-tbench/mmtb-media --- ### MicroDiffuse3D: A Foundation Model for 3D Microscopy Imaging Restoration Authors: Yongkang Li, Brian Wong, King Wai Chiu, Hanwen Xu, Tangqi Fang, Erin Dunnington, Dan Fu, Sheng Wang Published: 2026-05-08 Categories: cs.CV, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2605.08566v1 Chemical imaging enables label-free visualization of cells, tissues and living systems while providing direct biochemical information that is difficult to obtain with conventional fluorescence microscopy. Despite its promise in applications ranging from intraoperative diagnosis to drug-response analysis, its broader use remains limited by slow data acquisition, particularly for three-dimensional imaging. Here we present MicroDiffuse3D, a pretrained foundation model for 3D microscopy image restoration that recovers high-quality volumetric structure from degraded low-resolution measurements acquired at substantially higher throughput. We evaluated MicroDiffuse3D across three challenging restoration settings, including 3D super-resolution under 16-fold volumetric sparsity, joint degradation in resolution and noise, and 3D denoising in the low signal-to-noise ratio (SNR) regime, where the model delivered clear gains over strong baselines. Under the sparse 3D super-resolution setting, MicroDiffuse3D produced clearer continuity across depth with fewer artifacts and improved segmentation quality by 10.58% and line-profile concordance by 15.59%. Together, our results establish pretrained 3D restoration as a broadly applicable strategy for overcoming the throughput and SNR limitations in volumetric chemical imaging, enabling high-resolution analysis at scales and speeds that were previously difficult to achieve. --- ### Finer is Better (with the Right Scaling) Authors: Clemens Schaefer, Gil Tabak Published: 2026-05-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.08565v2 Microscaling is a critical technique for preserving the quality of Large Language Models (LLMs) quantized to ultra-low precision formats. Intuitively, finer block sizes should yield lower quantization error; however, a paradox recently identified by Fasoli et al. (2026) demonstrates that standard abs-max scaling can actually result in degraded model quality as block sizes shrink. In this work, we investigate the underlying mechanics of this phenomenon. We demonstrate that this degradation is not an inherent limitation of finer granularity, but is primarily driven by how elements in smaller blocks statistically cluster closer to their local block maximum, interacting poorly with the coarse subnormal E4M3 values used as scaling factors. Specifically, we show that i) preventing the scaling factor from underflowing to zero mitigates errors caused by extreme underflow, ii) targeted algorithmic interventions like the 4-over-6 methodology that give more flexibility to the choice of scaling factor resolve the paradox for larger values, and iii) a brute-force search establishes an optimal baseline, confirming that the theoretical Mean Squared Error (MSE) strictly improves with finer block sizes. Ultimately, our findings highlight a critical insight for hardware-software co-design: the block-size paradox is partially an artifact of naive scale selection. While using hierarchical scaling factors or wider formats like UE5M3 interchangeably resolves much of the quality loss, we found the 4-over-6 scale selection heuristic can even further improve quality, especially for very small block sizes. Consequently, maximizing the performance of next-generation ML accelerators will require treating silicon format specifications and software scaling algorithms as tightly coupled design choices. --- ### Biological Plausibility and Representational Alignment of Feedback Alignment in Convolutional Networks Authors: Jake Lance, Larry Kieu Published: 2026-05-08 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.08564v1 The feedback alignment (FA) algorithm offers a biologically plausible alternative to backpropagation (BP) for training neural networks yet notably fails to scale to convolutional architectures. Modifications have been proposed to address this limitation, but at questionable cost to biological plausibility. In this paper, we evaluate five learning algorithms including modified FA and standard BP, applied to the same convolutional architecture with the CIFAR-10 dataset. We provide a tripartite comparative analysis focusing on biological plausibility, interpretability, and computational complexity. Our results indicate that modified FA algorithms converge on internal representations that are structurally similar to those produced by backpropagation. In particular, it appears the functional success of modified FA algorithms may be rooted in their ability to mimic the representational geometry of backpropagation, converging on similar representations despite relying on fundamentally different weight update mechanisms. --- ### Why Retrying Fails: Context Contamination in LLM Agent Pipelines Authors: Zhanfu Yang Published: 2026-05-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.08563v1 When an LLM agent fails a multi-step tool-augmented task and retries, the failed attempt typically remains in its context window -- contaminating the next attempt and elevating the per-step error rate beyond the base level. This context-contaminated restart phenomenon is widely observed in practice yet entirely lacks formal treatment. We introduce the Context-Contaminated Restart Model (CCRM): a chain of T tool-call steps, each failing with base rate epsilon_0; after any failed attempt, the subsequent attempt operates in contaminated context with elevated error rate epsilon_1 > epsilon_0. Under this model we derive five main results. (R1) An exact closed-form formula for P(succeed in at most K attempts). (R2) A cascade-overhead theorem giving the additional attempts Delta K incurred by contamination versus the clean-restart baseline. (R3) An optimal budget-allocation theorem identifying the pipeline depth T* that maximises success probability for a fixed total budget B=KT; we prove the closed form T* = sqrt(B * log(1/(1-epsilon_1)) / log(1/(1-epsilon_0))), with K*=B/T*. (R4) An information-theoretic lower bound via Le Cam's method showing K_CCRM is tight up to O(1). (R5) A clean-restart dominance theorem quantifying the exact benefit of context-clearing before retry. We validate CCRM on real SWE-bench Verified data: the IID model overestimates pass@3 by 17.4 percentage points (98.6% vs. 81.2%), while CCRM fits with error less than 0.001, implying a cascade ratio of epsilon_1/epsilon_0 = 7.1. Monte Carlo experiments confirm all theoretical predictions. --- ### CONTRA: Conformal Prediction Region via Normalizing Flow Transformation Authors: Zhenhan Fang, Aixin Tan, Jian Huang Published: 2026-05-08 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.08561v1 Density estimation and reliable prediction regions for outputs are crucial in supervised and unsupervised learning. While conformal prediction effectively generates coverage-guaranteed regions, it struggles with multi-dimensional outputs due to reliance on one-dimensional nonconformity scores. To address this, we introduce CONTRA: CONformal prediction region via normalizing flow TRAnsformation. CONTRA utilizes the latent spaces of normalizing flows to define nonconformity scores based on distances from the center. This allows for the mapping of high-density regions in latent space to sharp prediction regions in the output space, surpassing traditional hyperrectangular or elliptical conformal regions. Further, for scenarios where other predictive models are favored over flow-based models, we extend CONTRA to enhance any such model with a reliable prediction region by training a simple normalizing flow on the residuals. We demonstrate that both CONTRA and its extension maintain guaranteed coverage probability and outperform existing methods in generating accurate prediction regions across various datasets. We conclude that CONTRA is an effective tool for (conditional) density estimation, addressing the under-explored challenge of delivering multi-dimensional prediction regions. --- ### ZAYA1-VL-8B Technical Report Authors: Hassan Shapourian, Kasra Hejazi, Olabode M. Sule, Beren Millidge Published: 2026-05-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.08560v1 We present ZAYA1-VL-8B, a compact mixture-of-experts vision-language model built upon our in-house language model, ZAYA1-8B. Despite its compact size, ZAYA1-VL achieves performance competitive with leading base models such as Molmo2-4B and InternVL3.5-4B, while surpassing models including Qwen2.5-VL-3B, PLM-3B, and MolmoE-1B across a range of image understanding, reasoning, and counting benchmarks. The architecture incorporates two key innovations: (1) vision-specific LoRA adapters integrated into the LLM to increase modality-specific capacity without increasing the number of experts, and (2) bidirectional attention over image tokens within the LLM to enhance visual understanding. We detail the full training pipeline including data composition at each stage, sequence packing, and the attention masking scheme. The model comprises 9.2B total parameters, with 1.4B active parameters including the vision encoder, and is publicly available at https://huggingface.co/Zyphra/ZAYA1-VL. --- ### Structure-Preserving Reconstruction of Convex Lipschitz Functionals on Hilbert Spaces from Finite Samples Authors: Anastasis Kratsios Published: 2026-05-08 Categories: math.FA, cs.LG, cs.NE, math.NA, math.OC arXiv: https://arxiv.org/abs/2605.08559v1 Convex functionals are ubiquitous in applied analysis, appearing as value functions, risk measures, super-hedging prices, and loss functionals in machine learning. In many applications, however, the functional is only observed through finitely many exact pointwise evaluations. We ask whether a convex functional on a separable Hilbert space $H$ can be reconstructed, up to arbitrary uniform accuracy, by an explicit formula which preserves convexity and Lipschitz regularity and is finitely computable. We answer this affirmatively. For every compact convex $C\subseteq H$, every $L$-Lipschitz convex functional $ρ:C\to\mathbb{R}$, and every $\varepsilon>0$, we construct an explicit finite-sample reconstruction which is convex, $L$-Lipschitz, and uniformly $\varepsilon$-accurate on $C$. The construction uses only finitely many linear measurements $\langle b,\cdot\rangle_H$, with $b$ lying in a finite-dimensional subspace of $H$, and is exactly implementable by a $\operatorname{ReLU}$-MLP. Building on this, we introduce convex neural functionals (CNFs), a structured trainable architecture class containing our reconstruction, whose every admissible parameter configuration is automatically convex and Lipschitz, providing a principled foundation for learning convex functionals from finite data. --- ### Beyond Static Bias: Adaptive Multi-Fidelity Bandits with Improving Proxies Authors: Muyun Lu, Haoyang Hong, Huazheng Wang, Ying Lin Published: 2026-05-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.08558v1 As an extension of the classical multi-armed bandit problem, multi-fidelity multi-armed bandits (MF-MAB) enable individual arms to be evaluated using diverse feedback sources that vary in both cost and accuracy. Prior stochastic models typically assume fixed low-to-high fidelity discrepancies, whereas modern proxy sources, such as learning-based simulators and Large Language Models (LLMs), can be improved using additional calibration. We investigate adaptive MF-MAB with improving proxy sources, and focus on the canonical two-fidelity case in which the low-fidelity source becomes more informative with repeated use. To capture this dynamic, we introduce a selected-average mismatch bound that converts dynamic low-fidelity observations into improvement-aware confidence bounds for the high-fidelity target. We propose the Threshold-Based Adaptive Continuation Companion (TACC), an optimistic algorithm that uses a bounded continuation rule to decide when low-fidelity sampling remains cost-effective and when to escalate. We prove an instance-dependent regret bound showing that, for detected intermediate arms, adaptive continuation replaces logarithmic high-fidelity confirmation with bounded low-fidelity continuation. Experiments on synthetic bandits and an LLM-as-a-judge policy-evaluation task examine when continuation improves cost-weighted regret. --- ### MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matching Authors: Salim Khazem, Ibrahim Mohamed Serouis, Zakaria Ezzahed Published: 2026-05-08 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.08557v1 Parameter-efficient adaptation of pretrained vision models is commonly performed through linear probes, prompts, low-rank updates, or lightweight residual modules. While effective, these methods usually treat adaptation as a discrete Euclidean perturbation of frozen representations, without explicitly modeling the geometry of the task-induced feature displacement. We propose \textsc{MC-RFM}, a mixed-curvature Riemannian flow-matching framework for few-shot adaptation of frozen visual backbones. The key idea is to represent adapted features on a product manifold combining a hyperbolic factor, which captures hierarchy-sensitive semantic structure, and a Euclidean factor, which preserves locally discriminative visual variation. Adaptation is formulated as a task-conditioned continuous transport from frozen features to support-set prototypes, trained with a flow-matching objective and coupled to a hybrid prototype-linear classifier. The method is lightweight, backbone-agnostic, and operates entirely on cached frozen features. Across seven visual recognition benchmarks, five frozen backbones, and 1/4/16-shot regimes, \textsc{MC-RFM} is the best-performing method in a majority of evaluated settings, with the strongest gains on Transformer backbones and fine-grained datasets. Ablations show that the mixed-curvature head, task conditioning, adaptive branch gating, prototype shrinkage, and discriminative supervision each contribute to performance. These results suggest that few-shot adaptation benefits not only from deciding which parameters to update, but also from modeling how representations should move through a geometry matched to the structure of the downstream task. --- ### Can Revealed Preferences Clarify LLM Alignment and Steering? Authors: Khurram Yamin, Jingjing Tang, Eric Horvitz, Bryan Wilder Published: 2026-05-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.08556v2 LLMs are increasingly used to make or support high-stakes decisions under uncertainty, where alignment depends not only on factual accuracy but on how models weigh tradeoffs between different outcomes. We present an empirical pipeline for estimating the implied preferences that an LLM's observed choices optimize: we elicit the model's probability distribution over unknowns along with the choice it would make for the decision task and then fit a discrete choice model to recover the cost function that best rationalizes the model's decisions. We show how this revealed-preference description allows rigorous evaluation of whether models behave in a consistently goal-directed way, whether they can verbalize a description of their objectives which matches their revealed decision policy, and whether prompting can reliably steer those policies to implement a user-specified cost function. We apply this evaluation across four medical diagnosis domains and multiple frontier and open-source models. We find that while many models have a nontrivial degree of internal coherence, they also have significant weaknesses in faithfully reporting or adopting preferences in response to user direction. --- ### Can Revealed Preferences Clarify LLM Alignment and Steering? Authors: Khurram Yamin, Jingjing Tang, Eric Horvitz, Bryan Wilder Published: 2026-05-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.08556v1 LLMs are increasingly used to make or support high-stakes decisions under uncertainty, where alignment depends not only on factual accuracy but on how models weigh tradeoffs between different outcomes. We present an empirical pipeline for estimating the implied preferences that an LLM's observed choices optimize: we elicit the model's probability distribution over unknowns along with the choice it would make for the decision task and then fit a discrete choice model to recover the cost function that best rationalizes the model's decisions. We show how this revealed-preference description allows rigorous evaluation of whether models behave in a consistently goal-directed way, whether they can verbalize a description of their objectives which matches their revealed decision policy, and whether prompting can reliably steer those policies to implement a user-specified cost function. We apply this evaluation across four medical diagnosis domains and multiple frontier and open-source models. We find that while many models have a nontrivial degree of internal coherence, they also have significant weaknesses in faithfully reporting or adopting preferences in response to user direction. ---