# Research Papers — 2026-06 · bundle page 190 of 260 > Full-text markdown of papers #9451–9500 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/190 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/189.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/191.md) ### RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language Models Authors: Jing Wang, Shang Liu, Wenji Fang, Yuchao Wu, Yugao Zhu, Zhiyao Xie Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.08976v1 LLM-based RTL generation and reasoning is a promising direction for hardware design automation. High-quality benchmarks are critical infrastructure for tracking progress in this direction. However, existing RTL benchmarks face inherent limitations in both scale and task scope. The designs they cover are typically small and simple, and the tasks focus almost entirely on specification-to-RTL generation. Frontier models' performance already saturates on the existing benchmarks. Scaling these benchmarks up is fundamentally difficult because aligned labels are required for benchmarking, such as specifications and testbenches. Such aligned high-quality data are rarely available for real-world designs. We introduce RTL-BenchLS, a large-scale benchmark addressing both limitations above. It contains over 10,000 formally verified Verilog designs, covering substantially larger and more complex designs than existing benchmarks. Beyond specification-to-RTL generation, we propose three novel tasks that jointly evaluate reasoning and generation: round-trip reasoning, masked-content reasoning, and repository-issue reasoning. The first two are self-supervised, which directly resolves the scaling bottleneck. All tasks are verified through formal equivalence checking without any manual testbenches. We evaluate eight LLMs on RTL-BenchLS. Even the best model reaches only 23% on natural-language round-trip reasoning, 28% on masked-content reasoning, and 12% on repository-issue fixing. RTL-BenchLS is substantially more challenging than existing benchmarks. It leaves ample room for future improvement and offers guidance for developing LLM-based methods for hardware design. --- ### Diverse Thinking Schemata Elicit Better Reasoning in Large Language Models Authors: Xinyue Liang, Yizhe Yang, Yu Bai, Bin Xu, Jiawei Li, Yang Gao Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.08974v1 Large reasoning models (LRMs) have attracted increasing attention for their ability to solve complex mathematical problems by generating extended reasoning chains. In this work, we focus on two critical yet underexplored aspects of the reasoning process: reasoning transitions capturing the distinct transitions between reasoning steps and answer candidates reflecting the variety of solution paths produced by the model. We collectively define these two aspects as thinking schemata. We observe a correlation between the diversity of thinking schemata and model performance, which motivates us to enhance diversity as a means to further improve reasoning potential. To this end, we propose Diverse Schemata Policy Optimization (DiScO), a framework that first endows the model with schemata awareness, then encourages diversity through reinforcement learning, and further promotes diverse reasoning at inference time. Experiments on multiple mathematical reasoning benchmarks demonstrate that DiScO consistently outperforms standard group relative policy optimization. Beyond accuracy, human-annotated analyses show that DiScO substantially improves the model's ability to recover from erroneous initial attempts. Overall, our work suggests the important role that diversity of the thinking schemata plays and points to scaling along the diversity dimension as a promising research direction. --- ### A systematic investigation of molecular encoding methods for drug property predictions across neural network and Transformer encoder-based model Authors: Sheng-Ya Chen, Shan-Ju Yeh Published: 2026-06-08 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2606.08973v1 Fundamental investigations into how different molecular encoding methods affect molecular property prediction remain relatively limited. In this study, we extensively examined the optimal molecular encoding methods for molecular properties prediction using two prevalent structure designs: a classical neural network model (MLP) and a Transformer encoder-based model (MLP+TL). For molecular encoding methods, we investigated several types of fingerprints, including traditional topological fingerprints, substructure-based fingerprints, and string-based representations. These two models were trained on seven well-known molecular datasets to evaluate different input molecular encoding methods based on evaluation metrics. On several biologically relevant classification tasks, including toxicity, mutagenicity, and side-effect prediction, our models consistently achieved average AUC values above 0.9. Rather than relying on external post-hoc explanation methods such as the local interpretable model-agnostic explanation (LIME) or the Deep SHapley Additive exPlanations (SHAP), we leveraged the model's intrinsic attention weights as an internal interpretability signal for identifying potentially important feature. The MLP+TL model using MACCS and PubChem as input can capture chemically interpretable groups that determined the major blood-brain barrier (BBB) permeability and mutagenicity in Salmonella typhimurium. In particular, a comparison between Morphine and Heroin highlighted the role of hydroxyl-related substructures in BBB permeability prediction, which was consistently reflected in the attention weights. Overall, our findings provide practical guidance for selecting effective molecular encoding methods and contribute to the development of interpretable molecular informatics approaches for drug discovery. --- ### An Effective Router for Vision-Language Model Selection Authors: Can Wang, Shengwei Wang, Bolin Zhang, Zhiying Tu, Dianhui Chu Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.08970v1 Vision-language models (VLMs) with varying performance and resource requirements are widely deployed, making it difficult for users to select the most appropriate one among numerous VLM candidates. Existing work reveals the performance paradox phenomenon in language models and focuses on routing methods to solve it. However, developing a router for VLM selection is still a critical yet challenging problem, which primarily faces: 1) lack of specialized data, 2) ineffective feature representation, and 3) rigid model space and costly adaptation. In this paper, we construct a multimodal dataset for VLM selection, containing the outputs of seven mainstream VLMs on 32,626 unique image-text queries. We then propose ARMS, a router for VLM selection. ARMS enhances input signals with VLM profiles, employs a simple but effective architecture to improve representations of queries and VLM capabilities. To improve ARMS' adaptation to new VLMs, we propose two extension training strategies: incremental training and independent training. Experimental results on both in-distribution and out-of-distribution test sets demonstrate the effectiveness of ARMS. In particular, using our training strategy, ARMs (only 800M in size) can adapt to a broader VLM space and defeat commercial models like GPT-4o that are hundreds of times larger in scale. Our code, models, and datasets are available in the anonymous repository. --- ### CARE: A Conformal Safety Layer for Medical Summarization Authors: Suhana Bedi, Bridget Lin, Anson Y. Zhou, Chloe O. Stanwyck, Jenelle A. Jindal, Sanmi Koyejo, David Stutz, Nigam H. Shah Published: 2026-06-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.08969v1 Large language models (LLMs) are increasingly used for medical summarization, but their outputs can omit medically important information and introduce unsupported claims. Existing error-detection methods produce heuristic or uncalibrated scores, providing no formal control over missed errors and no principled way to trade off safety against clinician review burden. We introduce Conformal Assessment for Risk Evaluation (CARE), a post-hoc, model-agnostic safety layer that uses conformal risk control to overlay calibrated omission and hallucination flags onto summaries from any LLM without retraining. CARE provides finite-sample, distribution-free guarantees through two controllers: a hallucination controller that bounds the probability of a document containing any unflagged hallucinated sentence, and an omission controller that bounds the expected fraction of important omissions not surfaced for review. Unlike hallucination detection, omissions depend jointly on whether a source sentence is important and whether it is covered by the summary. We show that calibrating only one dimension can violate the target risk bound, while marginal decompositions remain valid but overly conservative. By jointly calibrating over the full $(τ,γ)$ threshold space, CARE preserves formal guarantees while surfacing up to 5$\times$ fewer sentences than alternative calibrated baselines. Across five medical summarization tasks, CARE satisfies the target risk bound at $α= 0.15$ with 95% confidence across 100 calibration/test resplits, using only ~100 labeled documents per domain. In a preliminary clinician study (75 document reviews), calibrated flags improved omission detection by 28.6 percentage points on average. These results show that sentence-level safety guarantees are feasible for LLM-assisted medical summarization and offer a tunable mechanism for balancing residual risk and review effort. --- ### C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache Authors: Weisen Zhao, Lam Nguyen, Zhicong Lu, Yuzhang Shang Published: 2026-06-08 Categories: cs.LG, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2606.08962v1 World Action Models (WAMs) generalize better than standard Vision-Language-Action (VLA) policies to novel motions and environments, because a video-modeling objective lets them learn from abundant unlabeled video rather than scarce labeled robot demonstrations. This generalization is computationally expensive. To complete a task, a WAM runs over multiple inference chunks, and each chunk requires a costly denoising process. Existing acceleration methods reduce this cost by caching and reusing computation within a single chunk's denoising trajectory. Our empirical analysis reveals a substantial source of redundancy they overlook: redundancy across chunks. When a robot executes a smooth behavior, the residuals computed at a given denoising step are strongly correlated from one chunk to the next. We introduce C$^3$ache, a training-free method that caches and reuses these residuals across inference chunks at the same denoising step. Experiments on benchmarks with a Fast-WAM backbone show that C$^3$ache achieves up to a $2.5\times$ speedup in total wall-clock inference time, with negligible degradation in task success rate. --- ### Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops Authors: Ziqian Zhong, Ivgeni Segal, Ivan Bercovich, Shashwat Saxena, Kexun Zhang, Aditi Raghunathan Published: 2026-06-08 Categories: cs.CR, cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2606.08960v1 Agent benchmarks score submissions with outcome verifiers that are typically hand-written and brittle, leaving them open to reward hacking. We audit 1,968 tasks across five terminal-agent benchmarks and find 323 (16%) hackable by frontier models given only the task description. This corrupts both leaderboard rankings and RL training signal, yet the standard response is manual and reactive. We introduce the hacker-fixer loop, a method for building exploit-resistant verifiers without per-task manual patching. The loop alternates three LLM agents: a hacker tries to pass the verifier without solving the task, a fixer patches the verifier to reject each discovered exploit, and a solver confirms the patched verifier still admits legitimate solutions. The loop iterates: each patch reshapes what the verifier rewards, surfacing the next exploit. We further add verifier access, and let patches transfer across tasks, to broaden the exploits the loop discovers. On KernelBench, the loop drives the attack success rate from 62% to 0% on a held-out corpus of publicly reported exploits. We also find that weaker agents in the loop can defend against much stronger hackers: Gemini 3 Flash's loop drives the stronger Gemini 3.1 Pro and Claude Opus 4.7's attack success rate from 76% and 61% to 0% on KernelBench, and Gemini 3.1 Pro's from 39% to 17% on Terminal Bench across 77 tasks. We release Terminal Wrench (323 hackable environments, 3,632 hack trajectories) as a snapshot of the current attack surface, our patched verifiers, the exploits the loop discovered, and our implementation as a basis for future work. --- ### ChinaHeritaQA: A Culturally-Grounded Visual Question Answering Dataset for World Heritage Sites in China Authors: Yi Zhang, Bolei Ma, Yong Cao, Chengyan Wu, Daniel Hershcovich, Anna-Carolina Haensch Published: 2026-06-08 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2606.08959v1 We introduce ChinaHeritaQA, a multimodal benchmark dataset for evaluating the cultural reasoning abilities of vision-language models (VLMs) on UNESCO World Heritage sites in China. The dataset comprises 2,279 in-the-wild images paired with 14,133 bilingual (Chinese/English) multiple-choice QA pairs spanning seven cognitive dimensions, from basic identity recognition to historical periodization and architectural analysis. Guided by a UNESCO-aligned heritage ontology and verified through rigorous human annotation, the dataset ensures linguistic quality and factual consistency. Evaluations of state-of-the-art VLMs reveal that while top models exceed human performance on average, substantial task-level variation emerges: models excel at visual recognition but struggle with culturally grounded reasoning. Performance also varies by dynasty and region. ChinaHeritaQA reveals that strong visual retrieval does not extend to cultural and historical understanding. We release the dataset to support future research on culturally aware multimodal learning. --- ### Rethinking 3D Shape Generation: Diffusion over Superquadrics Authors: Zhiyang Liu, Wanze Li, Yuwei Wu, Chengran Yuan, Jiawei Sun, Rui Zheng, Marcelo H Ang Published: 2026-06-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.08957v1 Diffusion models have advanced 3D shape generation, yet most methods still denoise in high-cardinality spaces (e.g., voxel/SDF grids, meshes, or point clouds), which is computationally and memory intensive and makes it difficult to scale in terms of both higher resolution and stronger controllability. We rethink the diffusion representation and propose to move diffusion from dense geometry to compact geometric primitives, representing each shape as a small set of superquadrics. Instead of operating on thousands to millions of geometric representation values, we leverage 7KB superquadric parameters (pose, size, and shape), drastically reducing diffusion-state dimensionality and per-step compute/memory. Our diffusion-over-superquadrics improves scalability by supporting broader capabilities (e.g., resolution-free point-cloud decoding, part-level editing, and constraint-based design) and achieving competitive surface-fidelity and distributional performance on standard benchmarks after point-cloud decoding, while enabling efficient generation within 0.6s per shape for most conditions. --- ### From inverse problems to neural operators: prediction, mechanism, and generalization of data-driven models Authors: Conor Rowan Published: 2026-06-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.08956v3 Scientists have historically relied on mathematical models based on differential equations to relate system inputs -- forces, fluxes, or heat sources -- to outputs, such as displacement, velocity, concentration, and temperature. These models rely on deep domain knowledge to determine the form of the governing differential equation, which is then calibrated with data by solving an inverse problem. In recent years, the field of Scientific Machine Learning has introduced a variety of alternative modeling strategies for physical systems. A method called Sparse Identification of Nonlinear Dynamics learns the governing equation as a sparse linear combination of terms in a user-defined library. Neural Ordinary Differential Equations construct the governing equation by taking in the state and its derivatives at the input layer of a neural network. Entirely foregoing the modeling framework of differential equations, neural operators directly learn a non-linear mapping between the system inputs and outputs. From inverse problems to neural operators, all of these modeling strategies can be conceptualized as data-driven machinery to predict a system's response over a range of inputs. It is then natural to wonder how exactly these various strategies relate to each other, and whether they can be neatly taxonomized. Drawing from the philosophical literature on scientific models, we argue that many model types have a common structure, differing only in the assumed model class of the input-output relation they define. Connecting to philosophical ideas on mechanism, and arguing that data from physical systems arises from solutions to parsimonious differential equations, we propose that only certain models are capable of mechanism discovery, and thus generalization. Our analysis is intended to unite apparently disparate modeling strategies and provide insight into their appropriate use cases. --- ### Self-Consistent Generative Paths via Admissible Random Variational Transport Authors: Lei Luo, Yingzhen Zhang, Jian Yang Published: 2026-06-08 Categories: cs.LG, math.FA arXiv: https://arxiv.org/abs/2606.08953v1 Modern generative models often define an entire probability path from a simple prior to the data law, rather than only an endpoint map. Diffusion models follow stochastic denoising paths, flow matching learns transport fields, consistency and distillation methods compress paths into one or a few steps, adversarial models match terminal distributions, and VAEs generate through latent kernels. Existing unifying views mainly describe how such paths are constructed. We study a complementary question: when is a generated probability path self-consistent? We define a self-consistent generative path as a random fixed point of admissible local variational transport corrections. In this framework, a local correction is specified by a random variational transport operator combining a divergence or geometry term, an energy term, and a structural constraint. The framework contains random regularized optimal-transport proximal steps as a structured instance, while also allowing non-OT divergences, latent kernels, adversarial constraints, causal discrete kernels, and terminal one-step maps. The theory yields a random fixed-point path residual (R-FPR), which measures the gap between the actual generated path and an admissible local correction. We prove well-posedness, random fixed-point existence and attraction, non-contractive existence, residual-to-generation error bounds, empirical residual concentration, proxy perturbation bounds, continuous-time limits, and operator-level generalization with model-specific corollaries. The resulting theory turns endpoint matching into path self-consistency testing and provides a residual-control principle for diagnosing failures, regularizing training, and guiding adaptive sampling across diffusion, flow, one-step, VAE, GAN/WGAN, and autoregressive generators. --- ### AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models Authors: Shouwei Ruan, Bin Wang, Zhenyu Wu, Qihui Zhu, Yuxiang Zhang, Jingzhi Li, Yubin Wang, Xingxing Wei Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.08952v1 Multimodal Foundation Models (MFMs) have made substantial progress, yet remain fragile in spatial reasoning over the physical world. A key bottleneck lies in their inability to transform local egocentric observations into a global allocentric spatial representation. To address this, we propose AlloSpatial, an agentic framework for allocentric spatial cognition in foundation models. AlloSpatial introduces World2Mind, a plug-and-play cognitive mapping sandbox that converts egocentric observations into structured allocentric priors, including Allocentric-Spatial Trees and route maps that support querying object topology, geometric relations, passability, and trajectories. To utilize these priors reliably under noisy reconstruction and ambiguous visual evidence, AlloSpatial introduces a Spatial Reasoning Harness for tool-use judgment, modality-decoupled cue collection, and geometry-semantic arbitration. We further internalize this process in Qwen3-VL through cold-start reinforcement learning with a harness-gated trajectory-level reward. Experiments on VSI-Bench and MindCube show that AlloSpatial improves proprietary models by 5%-18% in a training-free setting, while ASTs alone support strong spatial reasoning even when visual inputs are removed. The trained AlloSpatial agents further outperform larger general-purpose models and competitive spatial baselines, suggesting that structured allocentric representations, active tool use, and verifiable reasoning offer a promising route toward spatially capable foundation models. --- ### NutriMLLM: Multimodal Large Language Models for Dietary Micronutrient Analysis Authors: Runze Yan, Minxiao Wang, Jiaying Lu, Darren Liu, Xiao Hu, Hanqi Luo Published: 2026-06-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.08948v1 Comprehensive estimation of dietary micronutrients from food images could improve clinical nutrition care, but training such models requires large multimodal datasets linking diverse foods to complete nutrient profiles. We first show that existing multimodal large language models (MLLMs), including leading proprietary models, are unreliable for this task. Across five model families and four independent evaluation benchmarks (ASA24, SNAPMe, FNDDS, and NutriBench), models frequently abstained or returned statistically implausible values. To address this gap without costly expert annotation, we repurposed a decade of population-scale 24-hour dietary recalls as structured prompts for text-to-image generation. This pipeline produced a synthetic corpus of about 1.1 million image-description-nutrient triplets, each pairing a generated food image with a complete 65-nutrient label. To our knowledge, this is the largest synthetic food-image corpus with comprehensive micronutrient annotation planned for public release upon publication. Fine-tuning Qwen3-VL (2B/4B/8B/30B) and GLM-4.6V-Flash on this corpus yielded NutriMLLM, the first family of vision-language models specialized for comprehensive dietary micronutrient estimation. We evaluate these models with a four-component framework that separately measures abstention, hallucination, overall usability, and per-nutrient numerical accuracy. On real food images, every NutriMLLM variant achieved near-complete coverage across all 65 nutrients, and the largest variant matched or exceeded proprietary baselines (GPT-5, Gemini 3, and Claude Sonnet 4.5) in accuracy on most nutrients. These results show that recall-driven synthetic supervision can make image-based comprehensive micronutrient estimation a tractable engineering problem and support dietary assessment, personalized nutrition guidance, and population-scale micronutrient surveillance. --- ### From Hazard Functions to Language Space: Cox-Supervised Distillation of Survival Risk into a Large Language Model Authors: Nicholas I-Hsien Kuo, Blanca Gallego, Louisa Jorm Published: 2026-06-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.08945v1 We investigate whether information about time-to-event risk estimated by a Cox proportional hazards model can be transferred into a generative large language model. We propose a text-based survival modelling pipeline in which structured clinical covariates are converted into text prompts and a Qwen-based large language model is fine-tuned to generate patient-specific survival risk using Cox model predictions as a training target. Across GBSG2, ACTG320, and WHAS500, the model achieves competitive held-out discrimination and calibration despite being trained as a text-generation task rather than with a conventional survival-analysis loss. We further analyse the geometry of the model's hidden states, where t-SNE visualisations reveal smooth risk gradients in latent space, suggesting that the model represents survival risk as a continuous structure rather than isolated risk categories. Together, these findings suggest that large language models can internalise survival-risk structure while supporting calibrated prediction, providing a route towards time-to-event reasoning in language models. --- ### Estimate Collapsibility of Causal Effects in Completed Partial DAGs via Strong d-Convex Hulls Authors: Yuxin Deng, Yi Sun, Zhiming Li, Huaxiong Liu Published: 2026-06-08 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2606.08941v1 This paper proposes a collapsible method for estimating causal effects that maintains the estimator's consistency before and after marginalization over some variables in completed partially directed acyclic graphs (CPDAGs). We first introduce the estimate collapsibility for CPDAGs and characterize the minimal collapsible sets as strong d-convex hulls. An efficient algorithm is devised to obtain such sets in DAGs and is generalized to CPDAGs. Then, we combine the graph reduction procedure with the IDA framework. Finally, experiments and empirical analysis show the effectiveness of the collapsibility for causal estimations in CPDAGs. Code is available at https://github.com/Jamyang-D/strongly-convex. --- ### Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance Authors: Mikhail Krasitskii, Alexander Gelbukh, Olga Kolesnikova, Grigori Sidorov Published: 2026-06-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.08940v1 Reinforcement Learning from Human Feedback (RLHF) has significantly improved the quality and fluency of large language models in text summarization. However, its impact on affective properties remains insufficiently understood. In this work, we study sentiment drift, a systematic shift toward neutral sentiment in RLHF-based summarization outputs compared to source texts. We conduct extensive experiments across multiple datasets, model architectures, and eight languages to analyze how alignment objectives influence sentiment preservation. Our results show that sentiment drift is a consistent phenomenon that becomes stronger with increased KL regularization strength, indicating a trade-off between alignment stability and affective fidelity. To explain this behavior, we introduce a Policy Attribution framework that decomposes the RLHF objective and quantifies the contribution of its components. Our analysis reveals that KL regularization is the primary driver of sentiment suppression across all settings. Based on these findings, we propose a sentiment-aware modification of the KL regularization term, which selectively reduces constraints on sentiment-bearing tokens. Empirical results demonstrate that this approach mitigates sentiment drift while maintaining summarization quality. Overall, our findings highlight a fundamental limitation of current alignment methods: while they improve factual consistency and safety, they may unintentionally suppress emotional expressiveness. This motivates the development of alignment strategies that explicitly account for affective preservation. --- ### PACT: Learning Diverse Diagnostic Strategies via Privileged Synthesis and Branch Consensus Authors: Gen Li, Yuanze Hu, Zhichao Yang, Qingchen Yu, Jianwei Lv, Yue Guo, Yujing Liu, Faguo Wu, Hongwei Zheng, Xiandong Li, Bo Yuan, Yifan Sun et al. Published: 2026-06-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.08938v1 Clinical diagnosis requires flexible use of multiple reasoning paradigms under incomplete patient information. Existing LLM-based medical agents show strong medical reasoning ability, but single-paradigm or naively mixed dialogue supervision makes these paradigms difficult to learn without interference. We propose \textbf{PACT} (Periodic Anchor Consensus Training), a framework that couples supervised multi-paradigm dialogue synthesis with consensus-based Branch training. At the data level, \textbf{DPS} (Doctor-Patient-Supervisor) uses complete electronic medical records (EMRs) for quality control while keeping the doctor agent restricted to patient-visible information. This produces validated dialogues under four diagnostic reasoning paradigms without leaking hidden clinical answers. At the training level, PACT trains one paradigm-specific LoRA Branch per paradigm and periodically aggregates Branches into a shared Anchor through sign consensus. We further construct a dynamic multi-turn Chinese medical diagnosis benchmark for interactive consultation. Experiments show that PACT achieves state-of-the-art performance among compared proprietary, medical-specialized, and task-adapted baselines on diagnostic outcome and consultation-process metrics. --- ### Report on CHIIR 2026 Workshop on Generative AI and Academic Search (GAI&AS) Authors: Yifan Liu, Jaime Arguello, Orland Hoeber, Chang Liu, Soo Young Rieh, Luanne Sinnamon, Dean Alvarez, Susan Archambault, Rob Capra, Henson Chen, Charles Costa, Anita Crescenzi et al. Published: 2026-06-08 Categories: cs.IR, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2606.08936v1 This report summarizes the CHIIR 2026 Workshop on Generative AI and Academic Search (GAI\&AS), which examined how GenAI is reshaping academic search systems and research practices. The workshop brought together researchers in human information interaction and information retrieval to explore key challenges and opportunities in designing and evaluating future academic search systems that integrate GenAI, moving beyond traditional document retrieval to support summarization, recommendation, synthesis, and conversational interaction. Participants' interests and discussions focused on three thematic clusters: foundations and principles, applications and opportunities, and search-as-learning. Across these themes, the workshop highlighted the importance of academic search systems in supporting transparency, credibility, research integrity, and long-term scholarly needs, as well as in fostering higher-order cognitive processes. Participants discussed guiding theories, design principles, methodological approaches, partnerships, and community-building efforts aimed at advancing human-centered GenAI-enhanced academic search systems. Overall, the workshop demonstrated strong community interest and a diverse range of ongoing and emerging research initiatives at the intersection of GenAI and academic search. --- ### PAI: Preserving Amplitude Information in Representation-Based Time-Series Anomaly Detection Authors: Kang Zhang, Wei Jian Lau, Shoushou Ren, Dong Lin, Joon Son Chung, Chuanhao Sun Published: 2026-06-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.08935v1 Representation-based time-series anomaly detection algorithms significantly outperform other methods on diverse anomaly detection tasks. However, we notice that they suffer from a major limitation in our evaluation - their learned embeddings are often amplitude-agnostic. Losing amplitude information can degrade performance on amplitude related anomalies, and this failure is prevalent across all existing representation-based methods. To address aforementioned issues, we propose a new anomaly scoring scheme named PAI. PAI consists of two complementary modules, a diagnostic module and a final score augmentation function. The diagnostic module compares cosine and Euclidean scoring on the same representation bank to test whether amplitude information is already captured in the learned representation. Then in final score augmentation function, PAI computes a point-wise median and MAD deviation score and a local mean-shift score-which are fused with the representation score to produce the final anomaly score. On the TSB-AD-U-Eva and TAB UV datasets, PAI improves all four evaluated representation-based methods across every reported metric, achieving average VUS-PR gains of 98.4% and 36.8%, respectively. Among all evaluated combinations, PaAno + PAI achieves the best performance, outperforming the state-of-the-art method by 15%. Further evaluation on bootstrap confidence intervals, anomaly-type breakdowns, and a TS2Vec input-normalization ablation further support the proposed scheme. These results suggest that explicitly retaining amplitude information is important for representation-based time-series anomaly detection, which has been underemphasized in existing scoring schemes. Code is available at: https://github.com/pantheon5100/PAI --- ### Backward Coherence and Hidden-State Stability in Recurrent Neural Networks: A Quasi-Reverse-Martingale Theory Authors: Yuan-chin Ivan Chang Published: 2026-06-08 Categories: cs.LG, stat.AP, stat.CO, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2606.08934v1 Recurrent neural networks maintain a hidden state $h_t$, but its probabilistic meaning is often unclear. We study hidden-state stability through \emph{backward coherence}: the extent to which $h_t$ can be reconstructed from $h_{t+1}$ by a learned backward projector $g_φ$. Under contraction and summable backward drift, the hidden-state sequence forms a quasi-reverse-martingale. This yields almost-sure convergence, rates under mixing, an interpretable limiting representation, finite pathwise stopping times, and a theoretical framework for time-uniform confidence sequences. Simulations support the theory. Backward-coherence regularisation reduces the empirical quasi-martingale total $\hat Q$ by $43$--$58%$, reaches stability $28$--$44%$ earlier than an unregularised RNN, and gives tracking-error recovery consistent with geometric bounds. Additional tests confirm echo-state forgetting rates bounded by $ρ$ and verify the increment-sum tube $R_t$ with $100%$ simultaneous coverage, although $R_t$ is conservative; in practice, the defect-tail proxy $\hat Q_t$ is the more useful monitor. The backward-coherence loss is also equivalent to minimising a Kullback--Leibler divergence in a Gaussian backward model, linking the method to variational inference. Extensions cover $φ$-mixing inputs, change-point tracking, and finite-sample concentration. Three real-data studies further validate the approach. On PhysioNet 2012 ICU data, the Reverse Martingale RNN (RMRNN) matches RNN mortality-prediction AUC while reaching stable representations 13 hours earlier. On FRED-MD, it reduces one-month-ahead forecast error by about fourfold under concept drift. On UCI Human Activity Recognition, it maintains lower post-transition tracking error with geometric decay. The guarantees apply under the stated assumptions; universality is not claimed. --- ### From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing Authors: Jian Chen, Siyuan Li, Chucheng Wan, Zixuan Yuan Published: 2026-06-08 Categories: cs.CL, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2606.08932v1 Rule-following agents tasked with executing policies and regulations often fail via Silent Scope Omission (SSO): a model applies a general rule but silently drops nested exceptions or counter-exceptions, producing outputs that appear compliant yet break on important edge cases. Although such failures are often framed as an agentic-systems problem, the underlying bottleneck is statutory and policy understanding, a capability typically studied in legal NLP. However, most existing legal NLP benchmarks emphasize end-task outcomes, which can overlook the structural omissions that cause SSO. To diagnose and mitigate SSO, we introduce NormBench, a benchmark of 2,290 provisions spanning Chinese (laws and local policies), English (U.S. tax law, GDPR, and corporate policies), and cross-lingual settings, designed for defeasible scope parsing: identifying precisely which clause overrides which. NormBench uses Span-Grounded Deontic Trees (SG-DT), a compiler-style intermediate representation that anchors every logical branch to source spans and requires explicit exclusion guards, enabling deterministic compilation and audit. Evaluations of frontier LLMs reveal two recurring pathologies: (1) Recursion Decay, where performance drops sharply as defeater depth increases, and (2) an Auditability Trap, where models retrieve relevant spans but fail to assemble correct control flow. Using SG-DT as a constrained intermediate output improves whole-tree fidelity and defeater recovery, and downstream experiments show that its utility is mechanism-specific: gains concentrate on exception-active, SSO-prone cases, while aggregate accuracy can be mixed when the added structure is unnecessary or parser fidelity is low. --- ### PROBE-Web: An Interactive System for Probing Evaluation Landscapes of Knowledge Graph Completion Models Authors: Sooho Moon, Yunyong Ko Published: 2026-06-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.08926v3 Knowledge graph completion (KGC) models are commonly evaluated using rank-based metrics such as MRR and Hits@K, despite different users often requiring different evaluation perspectives. In this demo, we present PROBE-Web, an interactive system for probing diverse evaluation landscapes for KGC models. PROBE-Web enables users to flexibly evaluate KGC models by adjusting two critical perspectives: (P1) predictive sharpness and (P2) popularity-bias robustness. Through a user-friendly GUI, users easily evaluate multiple KGC models and analyze their strengths and weaknesses. PROBE-Web provides four key functionalities: (1) conventional evaluation toolkit, (2) flexible perspective-aware evaluation, (3) explainable case studies, and (4) evaluation landscape exploration. We believe that PROBE-Web can help users better understand KGC models aligning with their objectives. --- ### PROBE-Web: An Interactive System for Probing Evaluation Landscapes of Knowledge Graph Completion Models Authors: Sooho Moon, Yunyong Ko Published: 2026-06-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.08926v1 Knowledge graph completion (KGC) models are commonly evaluated using rank-based metrics such as MRR and Hits@K, despite different users often requiring different evaluation perspectives. In this demo, we present PROBE-Web, an interactive system for probing diverse evaluation landscapes for KGC models. PROBE-Web enables users to flexibly evaluate KGC models by adjusting two critical perspectives: (P1) predictive sharpness and (P2) popularity-bias robustness. Through a user-friendly GUI, users easily evaluate multiple KGC models and analyze their strengths and weaknesses. PROBE-Web provides four key functionalities: (1) conventional evaluation toolkit, (2) flexible perspective-aware evaluation, (3) explainable case studies, and (4) evaluation landscape exploration. We believe that PROBE-Web can help users better understand KGC models aligning with their objectives. --- ### Generalized Rank-based Evaluation for Knowledge Graph Completion: Perspectives, Framework, and Analyses Authors: Sooho Moon, Jian Kang, Yunyong Ko Published: 2026-06-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.08921v1 Knowledge graph completion (KGC) aims to predict missing facts from an observed knowledge graph (KG), playing a crucial role in a wide range of real-world applications such as drug discovery, recommender systems, and retrieval-augmented generation (RAG). Although numerous KGC models have been proposed, the evaluation of KGC remains underexplored, despite its critical role in reliably assessing model performance and selecting appropriate models for real-world applications. In this paper, we introduce two important perspectives for KGC evaluation that are overlooked by existing evaluation metrics, (P1) predictive sharpness and (P2) popularity-bias robustness. To address both perspectives, we propose a generalized evaluation framework, PROBE, which consists of a rank transformer (RT) that estimates the score of each prediction based on a desired level of predictive sharpness and a rank aggregator (RA) that determines the final evaluation score by aggregating all prediction scores according to a desired level of popularity-bias robustness. We theoretically analyze PROBE by defining six key properties for reliable KGC evaluation and prove that PROBE satisfies all the properties, while existing metrics fail to satisfy some. In particular, due to the open-world nature of KGs, an evaluation metric should preserve the relative performance of KGC models even when only incomplete facts are observed. We show that PROBE better maintains such consistency, providing a more reliable estimate of intrinsic model performance than existing metrics. Extensive experiments with six KGC models on six real-world KGs reveal that existing metrics may over- or under-estimate model performance depending on different evaluation perspectives, whereas PROBE enables a more comprehensive, flexible, and consistent evaluation of KGC models. --- ### PolyBuild: An End-to-End Method for Polygonal Building Contour Extraction from High-Resolution Remote Sensing Images Authors: Yaoteng Zhang, Julin Zhang, Guangshuai Wang, Jiwei Deng, Hui Sheng, Yasir Muhammad, Shiqing Wei Published: 2026-06-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.08920v1 Extracting building polygon contours from high-resolution remote sensing images is a fundamental task for various mapping applications. However, the presence of varying imaging conditions and complex building structures, makes automatic contour extraction extremely challenging. Mainstream approaches for building extraction often rely on pixel-level segmentation followed by multiple post-processing steps to produce building contour, which can be computationally intensive and prone to errors. In this paper, we propose an end-to-end method named PolyBuild, which can directly extract building vector polygons from high-resolution remote sensing images without the need for any post-processing operations. The proposed method leverages two primary modules: an Initial Contour Generation Module (ICGM) and a Contour Optimization Module (COM). The ICGM is designed to generate an initial building contour by utilizing concatenated sub-region center features for each building instance. It performs simultaneous object detection and initial contour extraction by generating bounding boxes and using the center features of four sub-regions to represent each building. The Contour Optimization Module (COM) further refines the generated building contours by iteratively integrating Convolutional Neural Network (CNN) features and contour positional information in a Transformer-based decoder. The hybrid CNN-Transformer architecture effectively captures both local and global spatial relationships within the building contour, ensuring high-quality boundary delineation. Extensive experiments are conducted on three building datasets to evaluate the performance of PolyBuild. The results demonstrate that PolyBuild significantly outperforms state-of-the-art methods, including mask-based and contour-based approaches. --- ### Oversight Has a Capacity: Calibrating Agent Guards to a Subjective, Fatiguing Human Authors: Emre Turan Published: 2026-06-08 Categories: cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2606.08919v1 As LLM agents begin to take real, irreversible actions (shell commands, file edits, deploys), the standard safety pattern is a human-in-the-loop approval gate: risky actions pause and wait for a person. We argue the gate is the easy part; the hard part is the judgment - which actions to stop - which the field evaluates against two false assumptions: that there is a ground-truth notion of "risky," and that the human reviewer is a perfect, infinitely-available oracle. On a hand-labeled set of 125 adversarially-weighted agent actions we show that (i) reviewers only moderately agree on what is risky (Fleiss' kappa = 0.52), so there is no single correct label; (ii) framing the guard as selective classification under asymmetric cost makes its operating limits measurable, and on hard inputs the guard cannot safely auto-decide; and (iii) when the reviewer is modeled as endogenous (fatiguing as escalation load grows), realized safety becomes an inverted-U in the escalation rate: more human oversight can make a system less safe, and the safety-optimal guard escalates below full escalation - a setting a load-aware policy also uses to resist a flooding attack that slips a malicious action past a fatigued reviewer. Agent oversight, framed this way, is not only a classification problem but a resource-allocation one: human attention is finite, and the guard's escalation policy spends it. We claim none of these mechanisms as novel - fatigue-aware learning-to-defer (FALCON), cost-sensitive deferral under workload constraints (DeCCaF), trajectory-level guarding, and reviewer-fatigue/flooding attacks are all prior art we cite. Our contribution is an open-source agent-oversight system that operationalizes and measures them in the LLM-agent action-gating setting, turning "is my guard good?" from a guess into a curve. The inverted-U and the flooding attack are modeling results that motivate a human study. --- ### GeoMetric: Injecting Metric Geographic Structure into Worldwide Image Geo-Localization Authors: Junchao Cui, Xuanzi Ma, Wenqi Shi, Nan Wu, Biru Zhu, Xiangyang Luo Published: 2026-06-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.08918v3 Worldwide image geo-localization aims to determine where on Earth a single image was captured. However, visually similar scenes may lie thousands of kilometers apart, so methods that localize primarily by appearance often mistake a distant look-alike for the true location. We attribute this failure to a structural cause: in existing methods, GPS coordinates serve only as training supervision, and the distance relationships among locations never enter the learned representation. To address this, we propose GeoMetric, a retrieval-based framework that encodes GPS coordinates relationally rather than in isolation, injecting the distance structure among locations into both representation learning and inference. GeoMetric comprises three components: (1) a Transformer-based GPS encoder with distance-aware location attention that modulates inter-sample aggregation by great-circle proximity; (2) a trimodal contrastive objective that aligns images, geo-textual descriptions, and GPS embeddings in a unified space; and (3) a retrieval-augmented inference stage that supplies large multimodal models (LMMs) with contrastive candidate context for grounded coordinate reasoning. Extensive experiments on IM2GPS, IM2GPS3k, YFCC4k, and YFCC26k demonstrate that GeoMetric consistently outperforms state-of-the-art methods, improving street-level accuracy (within 1 km) by 1.5%, 0.9%, 6.9%, and 2.5%, respectively. Controlled ablations confirm that the gains originate from the proposed geographic encoding rather than any specific LMM. --- ### When Vision Misleads, Let Location Speak: A Worldwide Image Geo-Localization Method via Location Attention Mechanism and Large Multimodal Models Authors: Junchao Cui, Wenqi Shi, Xuanzi Ma, Nan Wu, Shaoyong Du, Xiangyang Luo Published: 2026-06-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.08918v1 Worldwide image geo-localization aims to determine the capture location of an image on a global scale. Existing methods often mislocalize images by matching them to visually similar scenes from different geographic regions, which limits reliability in practical applications. To address this issue, we propose TransGeoCLIP, a novel retrieval-based framework that integrates a location attention mechanism and large multimodal models (LMMs). Using the Transformer encoder with location attention to encode GPS coordinates, TransGeoCLIP can effectively distinguish geographic features among visually similar images. The framework consists of two stages: 1) Retrieval database construction, which employs Transformers equipped with location attention mechanisms to encode labeled GPS coordinates and enhance location semantics, subsequently enables joint image-text-GPS embedding through CLIP; 2) Retrieval-augmented inference, which leverages LMMs to infer the final image location prediction from retrieved database results. Extensive experimental results on diverse datasets, including IM2GPS, IM2GPS3k, YFCC4k, and YFCC26k, demonstrate that TransGeoCLIP significantly enhances localization performance for visually similar images. Particularly, street-level localization accuracy (within 1 km error) is substantially improved, surpassing state-of-the-art methods by 1.5%, 1.07%, 7.18%, and 9.75% on these benchmarks, respectively. --- ### Failure-Aware Refinement of Vision-Language Model for Lithography Defect Detection Authors: Pangyun Jeong, Jiyeong Kong, Yuehua Hu, Dohee Jeong, Kyung-Tae Kang Published: 2026-06-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.08908v1 Semiconductor lithography inspection requires reliable detection of small pattern defects such as bridge, burr, pinch, and contamination. In this study, we propose a two-stage vision-language framework that combines initial defect detection with prediction refinement. In the first stage, Qwen3-VL is fine-tuned with LoRA as a vision-language adapter to predict defect counts, defect categories, and normalized bounding boxes from lithography images. However, direct fine-tuning may still produce common test-time errors, including false positives, missed defects, and incorrect defect types. To address this limitation, the second stage trains a refinement module using first-stage prediction failures and their corrected labels, allowing the model to review and revise initial outputs. By learning from cases where the initial adapter fails, the refinement process improves defect inference beyond single-stage fine-tuning. --- ### DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance Authors: Qiangqiang Zhou, Jiawei Xu, Yong Chen, Dandan Zhu, Yugen Yi, Xiaoqi Zhao Published: 2026-06-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.08906v2 In many binary segmentation tasks, most multimodal methods rely on fixed feature concatenation for cross-modal interaction and straightforward decoder designs dominated by low-frequency semantics. However, they ignore two key challenges: one is the lack of an adaptive mechanism to handle modality discrepancies and complementarity, and the other is the absence of an efficient decoding strategy to balance both high- and low-frequency representations. In this work, we propose a simple yet general multimodal binary segmentation framework, termed DifferSeg, to address both problems simultaneously. With the help of the differential perception fusion (DPF) module, DifferSeg employs learnable differential operators to adaptively align multimodal features and enhance their complementarity through residual fusion, effectively mitigating modality mismatch and fusion redundancy. In addition, we design a frequency-guided decoder (FGD) that builds cross-frequency interactions and multi-path upsampling to maintain consistency between detailed high-frequency structures and semantic low-frequency representations, ensuring fine-grained boundary recovery and noise suppression. % Benefiting from these designs, DifferSeg can be easily generalized to diverse binary segmentation tasks, including both natural and medical modalities. Without bells and whistles, it consistently surpasses 67 state-of-the-art methods across 29 public datasets involving 18 downstream tasks, demonstrating superior generalization and segmentation accuracy.Code and pretrained models will be available at the Link. --- ### DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance Authors: Qiangqiang Zhou, Jiawei Xu, Yong Chen, Dandan Zhu, Yugen Yi, Xiaoqi Zhao Published: 2026-06-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.08906v1 In many binary segmentation tasks, most multimodal methods rely on fixed feature concatenation for cross-modal interaction and straightforward decoder designs dominated by low-frequency semantics. %ToDO: % However, they ignore two key challenges: one is the lack of an adaptive mechanism to handle modality discrepancies and complementarity, and the other is the absence of an efficient decoding strategy to balance both high- and low-frequency representations. % In this work, we propose a simple yet general multimodal binary segmentation framework, termed DifferSeg, to address both problems simultaneously. With the help of the differential perception fusion (DPF) module, DifferSeg employs learnable differential operators to adaptively align multimodal features and enhance their complementarity through residual fusion, effectively mitigating modality mismatch and fusion redundancy. % In addition, we design a frequency-guided decoder (FGD) that builds cross-frequency interactions and multi-path upsampling to maintain consistency between detailed high-frequency structures and semantic low-frequency representations, ensuring fine-grained boundary recovery and noise suppression. % Benefiting from these designs, DifferSeg can be easily generalized to diverse binary segmentation tasks, including both natural and medical modalities. Without bells and whistles, it consistently surpasses 67 state-of-the-art methods across 29 public datasets involving 18 downstream tasks, demonstrating superior generalization and segmentation accuracy.Code and pretrained models will be available at the Link. --- ### Order Matters: Unveiling the Hidden Impact of Macro Placement Sequences via Proxy-Guided LLM Evolution Authors: Shibing Mo, Jing Liu, Jianchu Xu, Ruilin Wu Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.08904v1 Macro placement is a fundamental step in modern chip physical design, playing a crucial role in determining the solution quality of high-dimensional combinatorial optimization problems. Despite recent advancements in machine learning for spatial coordinate determination, the temporal dimension of placement sequencing remains largely governed by static heuristics. In this work, we demonstrate that the placement sequence is not merely a preprocessing step but a decisive factor in optimization, where suboptimal early decisions trigger irreversible domino effects that constrain the solution space. To harness this unexplored dimension, we propose \textbf{OrderPlace}, a proxy-guided LLM evolution framework for automatically discovering macro placement order strategies. Instead of relying on manually crafted heuristics such as area- or connectivity-based ordering, OrderPlace explores a broader space of code-level policies, ranging from static scoring metrics to dynamic physics-inspired mechanisms. To mitigate the prohibitive cost of evaluating sequences, we introduce a lightweight proxy evaluation mechanism that efficiently filters candidates using a deterministic greedy probe. Experimental results on the standard ISPD 2005 benchmarks demonstrate that OrderPlace discovers novel ordering strategies. Compared with WireMask-EA and the state-of-the-art method EGPlace, OrderPlace reduces wirelength by 34.04\% and 14.08\%, respectively. --- ### Synthetic but Not Realistic: The Evaluation Challenge in Generative Modelling for Structured Electronic Medical Records Authors: Nicholas I-Hsien Kuo, Blanca Gallego, Louisa Jorm Published: 2026-06-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.08903v1 Synthetic healthcare data are widely proposed as privacy-preserving substitutes for real patient data, yet their evaluation remains dominated by statistical similarity and predictive performance that do not reflect clinical validity. We introduce a multi-dimensional evaluation framework grounded in epidemiology, assessing descriptive fidelity, clinical utility, and structural validity, corresponding to descriptive, predictive, and causal questions. We evaluate four representative generative paradigms - GAN-based, VAE-boosted, diffusion-based, and masked modelling - using PRIME-CVD, a 50,000-person cohort with known ground-truth structure. While all models reproduce marginal distributions, none simultaneously preserve subgroup structure, effect estimates, and dependency structure. Notably, models with strong distributional fidelity can exhibit poor calibration and distorted relationships, leading to unreliable inference. These results show that current evaluation practices can overestimate synthetic data quality and motivate domain-informed assessment based on the ability to support valid clinical and scientific conclusions. --- ### Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training Authors: Yanxiong Li, Guoqing Chen, Qianqian Li, Sen Huang Published: 2026-06-08 Categories: eess.AS, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.08898v2 In the task of few-shot class-incremental audio classification, the number of classes is assumed to always increase without considering the possibility of decrease. However, the number of classes generally increases or decreases in practice. In this paper, we investigate a problem of Few-shot Class-variable Incremental Audio Classification (FCIAC), in which the number of classes increases or decreases. We propose a FCIAC method using prototype adaptation and pseudo class-variable training. The model in our method consists of an encoder and a classifier. The classifier is initialized by a class-variable prototype adaptation network, whose structure dynamically changes with the change of classes. In addition, we design a pseudo class-variable training strategy to enhance the model's adaptability to changing classes. Experiments on three public datasets show that our method exceeds previous methods in average accuracy. The code is at: https://github.com/cgq2971-afk/FCIAC. --- ### A multi-agent system for spine MRI report generation from multi-sequence imaging Authors: Zhiping Xiao, Junwei Yang, Gongbo Sun, Han Zhang, Hanwen Xu, Yi Yao, Zachary D. Miller, William E. King, Mohammed M. Kanani, Jalal B. Andre, Sammy Chu, Ming Zhang et al. Published: 2026-06-08 Categories: cs.CV, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2606.08897v1 Spinal pathology is a leading cause of pain and disability worldwide. Spine MRI is central to clinical evaluation, yet its interpretation remains complex and time-consuming, requiring integration of information across multiple imaging sequences and anatomical regions. Despite recent advances in automated MRI analysis, effectively combining multi-sequence data while preserving sequence-specific diagnostic information remains an open challenge. Here we present SpineAgent, a multi-agent framework for spine MRI report generation built upon a multi-sequence foundation model trained on routine clinical data from 32,047 patients and 453,683 MRI series, comprising a total of 13,441,191 MRI slices. To accommodate diverse modalities of sequences, we first pre-train two DINOv3-based encoders separately on T1- and T2-weighted sequences. We then introduce a continual training strategy that learns a synthesizer to embed images of other sequences using the T1 and T2 encoders, producing patient-level embedding that integrates various signals across MRI sequences. Using these embeddings, SpineAgent achieves state-of-the-art performance, and demonstrates strong generalizability under cross-manufacturer and cross-cohort evaluation. Beyond classification, SpineAgent enables pathology localization by identifying findings-relevant slices and segmenting pathological regions. It also supports multimodal image-report retrieval, providing a solid foundation for scalable and explainable MRI report generation. We further integrate these validated capabilities of SpineAgent into 37 specialized agents. Finally, we incorporate their outputs as structured tokens within a Medical Report Agent trained end-to-end for report generation. Through both automated metrics and expert evaluation by five radiologists, SpineAgent achieves leading performance in spine MRI report generation. --- ### FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting Authors: Qianyang Li, Xingjun Zhang, Shaoxun Wang, Tao Peng, Jia Wei Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.08896v1 Large-scale retail and industrial forecasting systems contain many heterogeneous time series whose lifecycle, sparsity, volatility, seasonality, spectral patterns, and contextual sensitivity differ substantially. A single forecasting model rarely performs well across all regimes, while dense ensembles increase inference cost and provide limited insight into expert suitability. This paper studies forecastability-aware expert routing: learning how data characteristics determine the suitability of forecasting experts. We propose \method{}, a sparse mixture-of-experts framework that represents each series with a multidimensional forecastability fingerprint, mines expert-suitability targets from validation performance, and trains a cost-aware sparse router to activate a small budgeted set of experts for each series. Using a production-scale vending-machine sales dataset from Shandong New Beiyang (SNBC), where the forecasting component has been integrated into the replenishment-planning pipeline, together with public retail benchmarks, we show that expert suitability varies systematically across data regimes. On the industrial dataset with 5,000+ machines and 60M+ transactions, \method{} Top-2 reduces MSE by 12.4\% over the strongest single expert, LightGBM, while executing 1.92 experts per series on average. The deployed component produces demand forecasts, while inventory-oriented gains are estimated by an offline replay simulator under a fixed replenishment policy rather than by online intervention. The framework turns heterogeneous sales forecasting from heuristic model selection into data mining of forecastability patterns and expert specialization. Code is available at https://github.com/hit636/FAME --- ### Are Reasoning Vision-Language Models Robust to Semantic Visual Distractions? Authors: Yizheng Sun, Mochuan Zhan, Yanan Ma, Jia Tong See, Yifan Wang, Ziyi Wang, Hao Li, Yang Cui, Wenhao Cai, Jingyu Sun, Chenghua Lin, Riza Batista-Navarro et al. Published: 2026-06-08 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2606.08894v1 Reasoning Vision-Language Models (VLMs) achieve strong performance on complex multimodal tasks, but reliable real-world application requires handling visual inputs that are messier than clean, curated benchmarks. Existing works mainly evaluate such reliability of VLMs through input corruptions, such as noise, blur and weather effects, which make visual evidence harder to perceive. This leaves a critical reliability failure mode underexplored: a model may perceive the evidence correctly, yet reason from plausible but irrelevant and distracting evidence and propagate this mistake to its final answer. To address this gap, we introduce \textbf{Distract-Bench}, a benchmark for evaluating VLM robustness to \textbf{semantic visual distractions}, defined as meaningful but task-irrelevant visual cues added to inputs while preserving the ground-truth answer. We comprehensively evaluate eight leading open-source and two closed-source VLMs across conventional vision corruptions and Distract-Bench. Our results show that Distract-Bench exposes a robustness failure distinct from vision corruptions: reasoning VLMs largely track their non-reasoning base models under perceptual degradation, but show consistently lower robustness to semantic distractions. Further analysis shows that these distractions often enter the reasoning process of VLMs, are treated as evidence, and lead to incorrect answers. Together, these findings reframe robustness evaluation for reasoning VLMs, shifting the focus from degraded perception to distractions for reliable real-world visual reasoning. Our data and code are available at https://github.com/Yizheng-Sun/Distract-Bench. --- ### Cheap Reward Hacking Detection Authors: Iván Belenky, Joaquín Itria, Steven Johns Published: 2026-06-08 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2606.08893v1 A small transformer encoder is trained to map Terminal-Wrench trajectories onto a unit sphere where embedding distance approximates the $L_1$ distance between reward and metadata signals. A linear probe on top of that embedding detects reward hacking on the cleaned test split with AUC $0.9467$ and TPR@5%FPR $0.8296$, matching the TW sanitized LLM-as-judge AUC ($0.9510$ on the cleaned split) and exceeding its TPR@5%FPR ($0.7130$ vs $0.8296$) on the same information condition, at roughly four orders of magnitude lower per-trajectory cost. The encoder is not a pure behavior reader: stripping natural-language reasoning from its input at probe time drops AUC to $0.6213$. --- ### Diffuse AI Control on Fuzzy Tasks Authors: Mikhail Terekhov, Caglar Gulcehre, Vivek Hebbar, Joe Benton Published: 2026-06-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.08892v2 AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts due to misalignment. Diffuse AI Control is a subfield of AI safety concerned with mitigating risks from AI sabotage distributed over long deployment horizons (diffuse threats). These risks are particularly pernicious on fuzzy tasks, i.e. tasks which are hard to grade or require intuition. To understand diffuse threats on fuzzy tasks, we introduce a framework that considers AI control as an adversarial game between a blue team and a red team. The blue team uses a weak trusted model to construct a weak score against which they would train a strong, potentially subversive model to remove the subversion propensity if it were present. The red team then tries to find model behaviors that are rated highly by the weak score, and thus might not be trained out, but actually correspond to poor performance. We test our framework on the task of writing experimental proposals for research questions from recent ML papers. We use a language model with access to the original paper as a proxy "ground-truth" scorer. Our red team discovers subversive behaviors using multi-objective evolutionary prompt optimization. We show that Opus~4.6 can write proposals that are worse according to the ground truth proxy than those of GPT-OSS-20B, while the weak scorer rates them as highly as the best proposals from Opus 4.6. We then propose an adversarial optimization algorithm for the blue team that discovers more robust prompts for the weak model. This algorithm produces a blue team prompt that our red team optimization fails to exploit. --- ### NE-BERT: A Multilingual Language Model for Nine Northeast Indian Languages Authors: Badal Nyalang Published: 2026-06-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.18094v1 Large pretrained language models have demonstrated remarkable capabilities across diverse languages, yet critically underrepresented low-resource languages remain marginalized. We present NE-BERT, a domain-specific multilingual encoder model trained on approximately 8.3 million sentences spanning 9 Northeast Indian languages and 2 anchor languages (Hindi, English), a linguistically diverse region with minimal representation in existing multilingual models. By employing weighted data sampling and a custom SentencePiece Unigram tokenizer, NE-BERT outperforms IndicBERT-V2 and MuRIL across all 9 Northeast Indian languages, achieving 15.97X and 7.64X lower average perplexity respectively, with 1.50X better tokenization fertility than mBERT. We address critical vocabulary fragmentation issues in extremely low-resource languages such as Pnar (1,002 sentences) and Kokborok (2,463 sentences) through aggressive upsampling strategies. Downstream evaluation on part-of-speech tagging validates practical utility on three Northeast Indian languages. We release NE-BERT, test sets, and training corpus under CC-BY-4.0 to support NLP research and digital inclusion for Northeast Indian communities. --- ### Abliteration Mitigation via Refusal Aliases Authors: Nathan Truong Published: 2026-06-07 Categories: cs.CL, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2608.18093v1 Abliteration, the removal of refusal capabilities from large language models by projecting weight matrices orthogonal to an extracted refusal direction, has emerged as a prominent safety concern through its ability to bypass post-training alignment using only a small set of contrastive prompts. We find that existing defenses commonly overlook the cause of abliteration; that is, how easily the refusal direction can be extracted. To hinder this process, we introduce a weight-editing method that obscures the refusal signal by applying rank-$k$ updates to residual stream writer matrices while replacing refusal-inducing activations with random aliases and correcting downstream reader matrices to preserve the model's original behavior. On Llama-3-8B, AMRA improves post-abliteration refusal scores by $2.16$ points over the undefended baseline with less than $0.5$ percentage points of MMLU degradation. On Gemma-2-9B, it improves the post-abliteration refusal by $14.70$ points over the baseline while keeping harmful output rates similar to the baseline, albeit at a greater utility cost. --- ### WARA: Toward Automated Wireless Optimization Research with Closed-Loop LLM Agents Authors: Yuan Guo, Yilong Chen, Chao Hu, Xianghao Yu, Liang Hong, Jie Xu Published: 2026-06-07 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2608.14573v1 Large language model (LLM) agents are increasingly capable of tool use, code execution, artifact inspection, and iterative revision, creating new opportunities for automating scientific and engineering research. To the best of our knowledge, this paper presents the first end-to-end autoresearch framework for the wireless domain, with a focus on wireless resource allocation optimization. We propose the Wireless AutoResearch Agent (WARA), a closed-loop multi-agent system for automated wireless optimization research. Given only an initial topic, WARA decomposes the workflow into three phases: research gap identification and problem proposal, wireless optimization modeling, algorithm design and experimentation, and research deliverable construction. Across these phases, WARA uses artifact-mediated control: upstream artifacts are consumed as inputs, structured outputs are stored for downstream use, and controller-managed gates validate consistency among models, algorithms, experiments, and claims. When validation fails, WARA repairs only the responsible artifact instead of restarting the whole workflow. We present a representative wireless resource allocation case study showing how WARA converts an initial topic into a complete research package with executable evidence and a synthesized technical manuscript. We further design a structured LLM-based ScoringAgent to evaluate manuscript-level research validity and optimization research maturity. Comparative results show that WARA substantially outperforms one-shot LLM generation and approaches the quality profile of recently accepted peer-reviewed technical papers. These results indicate that closed-loop artifact control is a promising path toward end-to-end LLM-assisted wireless optimization research. The source code is available at https://github.com/guoyuan-dotcom/WARA_CUHKSZ. --- ### Measuring Cognitive Engagement in Collaborative Discourse with an Extended ICAP Framework: Comparing Human Annotation, In-Context Learning, and Reflective LLM Agents Authors: Lan Anh Do, Hanling Jiang, Shuchin Aeron, Ayanna K. Thomas Published: 2026-06-07 Categories: cs.HC, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2607.28651v1 Collaboration supports learning and problem-solving, but its effectiveness depends on cognitive engagement during discourse. This study applies an extended 7-point ICAP framework based on the Interactive, Constructive, Active, and Passive modes to characterize variation in cognitive engagement during collaborative dialogue. Engagement was coded by trained human annotators and compared with large language model (LLM)-based labeling approaches, including in-context learning (ICL), zero-shot prompting, and self-reflective agents. Interrater reliability among human annotators was robust across framework refinement stages (kappa = 0.906-0.998), higher than the moderate agreement observed for ICL-based annotation (kappa = 0.541-0.609). The human-refined framework improved agreement among human annotators (Delta kappa = 0.10), but produced only modest gains for ICL-based LLMs (Delta kappa less than 0.04). Agent-refined frameworks improved cross-model agreement but remained below the human-refined framework. These findings highlight the promise of agent-based approaches and the importance of continued interaction between theory-guided human annotation and LLM-based methods in future work. --- ### Crystalis: Progressive Nucleation and Semantic Annealing for Coordinated Multi-View Visualization Generation Authors: Dazhen Deng, Zhaoping He, Xin Qian, Xiaotong Wang, Zi Ying, Yingcai Wu Published: 2026-06-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.24766v1 Large language models (LLMs) can generate individual charts, but coordinated multi-view visualizations (CMVs), where views share data flows and cross-view interactions, remain out of reach. Tight field-level coupling among data transformations, visual encodings, and interaction coordinations causes errors in one component to silently invalidate others. Rather than pursuing end-to-end analytical quality, which depends on model capability, domain knowledge, and user expertise, we target a foundational question: can LLMs reliably produce structurally correct CMVs, and what abstractions make this possible? We present Crystalis, a framework built on query-centric CMV modeling that decomposes a CMV into structured queries over a dependency graph spanning three component types (Data, Visualization, Interaction) and three abstraction levels (requirement, specification, executable object). Two complementary mechanisms operate over this structure: progressive nucleation crystallizes each query vertically from requirement to object along the dependency order, while semantic annealing enforces horizontal consistency across queries at each level through layered logical checks. On a 12-task benchmark across five frontier LLMs, Crystalis achieves up to 75% end-to-end success, substantially outperforming an agentic coding baseline (8.3% E2E with the same foundation model), and a user study with 12 practitioners confirms the usability of the decomposition and iterative refinement workflow. --- ### HeraSys: Collaborative Serving of Multiple LLM Workflows via Fine-Grained End-to-End Optimization Authors: Size Li, Zhiqing Tang, Hongrui Liang, Jianxiong Guo, Jiong Lou, Tian Wang, Weijia Jia Published: 2026-06-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22578v1 The proliferation of Large Language Models (LLMs) has shifted serving systems from processing isolated requests to orchestrating high-concurrency, multi-tenant agentic workflows. However, existing solutions typically prioritize intra-workflow optimization, largely neglecting the significant potential for inter-workflow optimization. In this paper, we propose HeraSys, an LLM serving system designed to optimize the end-to-end performance of concurrent workflows. Through fine-grained orchestration, HeraSys eliminates cross-workflow computational redundancy via structural node merging and reuse. Furthermore, HeraSys introduces a load-aware joint scheduling policy that dynamically manages execution order by evaluating both inter- and intra-query priorities. By integrating a resource skewing mechanism with adaptive batching and pipeline decomposition, HeraSys effectively mitigates tail latency while maintaining low average latency, thereby substantially improving system throughput. Extensive experiments demonstrate that HeraSys reduces P99 latency by up to 2.17$\times$ and increases serving throughput by up to 1.85$\times$ under strict latency guarantees. --- ### Platooning Connected, Autonomous, and Human-Driven Vehicles: A Deep Reinforcement Learning-based Approach Authors: Zhen Qina, Dong-Fan Xie, Heng Ma, Xiaomei Zhao, Zhengbing He Published: 2026-06-07 Categories: eess.SY, cs.AI, cs.HC, cs.LG, cs.MA, cs.RO, physics.soc-ph arXiv: https://arxiv.org/abs/2606.20648v1 Conventionally, existing vehicle platooning approaches are designed for connected vehicles, typically including connected autonomous vehicles and connected human-driven vehicles. Non-connected vehicles, such as non-connected autonomous or human-driven vehicles, are not incorporated. As a result, these platooning approaches may not properly reflect real-world mixed traffic conditions at the current stage. To address this limitation, this study proposes a hybrid platooning pattern that conditionally permits non-connected vehicles to join platoons, thereby enhancing platooning diversity and flexibility. However, it was found that the unregulated integration of non-connected vehicles can trigger rapid platoon expansion, significantly amplifying the risk of disturbance propagation in traffic flow. This, in turn, exacerbates the inherent conflict between traffic throughput and stability. To mitigate these challenges, this paper further develops a hybrid platooning control strategy based on deep reinforcement learning (DRL). This strategy integrates vehicle dynamics, platoon topology, and traffic flow states through a multi-level state representation network, enabling a dynamic trade-off between traffic capacity and stability. Numerical simulations demonstrate that the proposed strategy effectively suppresses velocity disturbance propagation by dynamically optimizing platoon structures, thereby significantly enhancing the stability and safety of mixed traffic while reducing fuel consumption and emissions. --- ### IOAH3: Importance-Driven Adaptive Spatial Partitioning Authors: Ehsaneddin Jalilian Published: 2026-06-07 Categories: stat.AP, cs.AI arXiv: https://arxiv.org/abs/2606.18280v1 We present IOAH3 (Importance-Oriented Adaptive H3 partitioning), a computational method for constructing data-driven spatial partitions of geo-referenced observation domains. Standard approaches to spatial aggregation adopt fixed areal units, such as administrative boundaries or uniform hexagonal grids at a single resolution, without regard to the informational content of the underlying observations in each region. This leads to the well-known modifiable areal unit problem: statistical and inferential results depend on the arbitrary choice of partition, and spatially concentrated phenomena are averaged out in coarse cells that obscure fine-scale structure. IOAH3 addresses this by constructing an adaptive partition in three stages: multi-source feature extraction and importance scoring via principal component analysis over road density, POI density, building density, and terrain roughness signals, with population and flood-hazard data entering as auxiliary inputs to cell filtering and spatial smoothness; spatial cell selection via Markov Random Field graph-cut optimisation, which jointly maximises per-cell importance while enforcing spatial contiguity; and data-driven hierarchical refinement of high-importance regions to finer H3 resolution levels, with neighbour-propagated support to avoid isolated fine-resolution islands. The resulting partitions serve as input to spatial inference pipelines and provide a principled resolution of the partition-sensitivity problem prior to any modelling step. --- ### Where Does Texture Evidence Live in SAM? Features, Proposal Masks, and Texture Segmentation Authors: Nadav Orenstein, Aviad Cohen Zada, Shai Avidan, Gal Oren Published: 2026-06-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.14755v1 Texture segmentation stresses foundation segmentation because meaningful regions are defined by material or repeated appearance rather than object identity. Segment Anything Models (SAMs) often fail by default on such texture-defined partitions, but this failure is ambiguous: the texture evidence may be absent, missing from the proposal bank, or present but selected or assembled incorrectly by an object-centric readout. We ask what texture-relevant evidence is already preserved in frozen SAM before adaptation. We study two frozen evidence spaces: multiscale features, probed with a minimal clustering readout, and the automatic proposal bank, treated as evidence for a supervised consolidation readout. SAM is frozen throughout; we do not fine-tune the backbone or retrain the proposal generator. Across RWTD, STLD, an ADE20K-selected refined-crop complement, and a ControlNet-stitched PTD bridge archive, frozen SAM is not a texture segmenter by default, but its failures are not simple texture blindness. Coarse frozen features preserve texture organization, and proposal banks often contain texture-aligned masks or fragments. Natural scenes more often require assembly and commitment over fragments, while cleaner synthetic cases more often reduce to selecting an already coherent proposal. Default mask failure should therefore be decomposed into representation evidence, proposal-bank support, readout mismatch, and commitment failure. --- ### Sub-Semantic Image Segmentation Authors: Aviad Cohen Zada, Nadav Orenstein, Shai Avidan, Gal Oren Published: 2026-06-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.14754v1 Images can be segmented based on visual cues (i.e., texture segmentation) or into objects (i.e., semantic segmentation). We propose a new category of sub-semantic image segmentation that blurs the line between the two. In sub-semantic image segmentation, language is not used to name whole objects. Instead, it is used to partition an image into stable appearance patterns that can be described by language. To do that, we couple a general-purpose vision-language model to SAM 3, a promptable segmentation backbone whose native text pathway can ground rich descriptions into masks. Simple coupling fails for a number of reasons that we identify in the paper, and we overcome them by introducing DETECTURE that resolves three concrete failure modes -- language leakage between texture regions, prompt competition inside the segmentation backbone, and semantic distortion at the language-to-mask interface. Since there is no dataset of sub-semantic image segmentation, we introduce one, termed TextureADE. The new dataset is derived from the ADE20K dataset using a system we designed. We compare DETECTURE to a number of baselines and find that it achieves the strongest performance on several datasets using different metrics. Code is available at https://github.com/Scientific-Computing-Lab/TextureDetecture. --- ### Beyond Self-Attention: Sub-Quadratic Vision Transformers for Fast Image Captioning Authors: Chiradeep Ghosh, Dakshina Ranjan Kisku Published: 2026-06-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.14753v1 Image captioning is a challenging and significant task that aims to generate coherent and semantically meaningful textual descriptions for given images. To accomplish this task, it requires a deep understanding of visual content along with the ability to express that understanding in natural language. Despite remarkable progress with transformer-based architectures, existing approaches often suffer from limitations, such as a lack of rich local feature representations and the high computational cost of quadratic self-attention. The proposed model focuses on improving computational efficiency by restructuring the vision transformer architecture. In designing this approach, the standard self-attention mechanism in Vision Transformers is replaced with a probabilistic transformer approach based on a Gaussian Mixture Model (GMM), a soft-clustering technique. Instead of computing pairwise attention among all image patches, the model groups similar patches into a fixed number of clusters using an Expectation-Maximization (EM) algorithm. This clustering-based mechanism reduces the computational complexity from quadratic O(n^2) to linear O(nK), where K << n. The autoregressive GPT-based decoder is used for caption generation. The model is evaluated on the Flickr 30K dataset, demonstrating competitive and significant improvement over existing works. ---