# Research Papers — 2026-06 · bundle page 194 of 260 > Full-text markdown of papers #9651–9700 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/194 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/193.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/195.md) ### Lost in the Non-convex Loss Landscape: How to Fine-tune the Large Time Series Model? Authors: Xu Zhang, Peang Wang, Wei Wang Published: 2026-06-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.08578v1 Recently, large time series models (LTSMs) have gained increasing attention due to their similarities to large language models, including flexible context length, scalability, and task generality, outperforming advanced task-specific models. However, prior studies indicate that pre-trained LTSMs may exhibit a poorly conditioned non-convex loss landscape, leading to limited trainability. As a result, direct fine-tuning tends to cause overfitting and suboptimal performance, sometimes even worse than training from scratch, substantially diminishing the benefits of pre-training. To overcome this limitation, we propose Smoothed Full Fine-tuning (SFF), a novel fine-tuning technology. Specifically, we construct an auxiliary LTSM via random initialization to obtain a smoother loss landscape, and then linearly interpolate its weights with those of the pre-trained model to smooth the original landscape. This process improves trainability while preserving pre-trained knowledge, thereby enabling more effective downstream fine-tuning. From an optimization perspective, SFF perturbs sharp minima without significantly harming flat regions, facilitating escape from poor local basins toward smoother and more generalizable solutions. Extensive experiments on benchmark datasets demonstrate consistent improvements across eight representative LTSMs, including Timer, TimesFM, MOMENT, UniTS, MOIRAI, Chronos, TTMs, and Sundial, on diverse downstream tasks. The code is available at the link: https://github.com/Meteor-Stars/SFF. --- ### OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework Authors: Chenhan Jin, Shengze Xu, Qingsong Wang, Fan Jia, Dingshuo Chen, Tieyong Zeng Published: 2026-06-07 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2606.08574v1 Data pruning (DP), as an oft-stated strategy to alleviate heavy training burdens, reduces the volume of training samples according to a well-defined pruning method while striving for near-lossless performance. However, existing approaches, which commonly select highly informative samples, can lead to biased gradient estimation compared to full-dataset training. Furthermore, the analysis of this bias and its impact on final performance remains ambiguous. To address these challenges, we propose OrderDP, a plug-and-play framework that aims to obtain stable, unbiased, and near-lossless training acceleration with theoretical guarantees. Specifically, OrderDP first randomly selects a subset and then chooses the top-$q$ samples, where unbiasedness is established with respect to a surrogate loss. This ensures that OrderDP conducts unbiased training in terms of the surrogate objective. We further establish convergence and generalization analyses, elucidating how OrderDP affects optimal performance and enables well-controlled acceleration while ensuring guaranteed final performance. Empirically, we evaluate OrderDP against comprehensive baselines on CIFAR-10, CIFAR-100, and ImageNet-1K, demonstrating competitive accuracy, stable convergence, and exact control -- all with a simpler design and faster runtime, while reducing training cost by over 40%. Delivering both strong performance and computational efficiency, our method serves as a robust and easily adaptable tool for data-efficient learning. The code is publicly available at https://github.com/shengze-xu/OrderDP. --- ### Titans-as-a-Layer: Test-Time Memory for Conversational Speech Emotion Recognition Authors: Daniel Chen, Qicong Hu, Yang Xiao, Ting Dang, Hong Jia Published: 2026-06-07 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.08573v1 Speech emotion recognition (SER) is commonly formulated as utterance-level classification, although conversational emotion depends on a speaker's usual vocal range and the emotional context established by previous utterances. Speech-language models provide strong pretrained acoustic and semantic representations, and can adapts them to SER labels via finetune, but this mechanism still missing per-dialogue state. We study whether test-time neural memory can supply this missing context while leaving the large audio language models (LALMs) backbone intact. Building on Titans, we introduce a plug-and-play Memory-as-a-Layer (MAL) adapter that writes dialogue history into a small neural memory and reads it back as an audio-token-aligned residual update, avoiding changes to the host model's token positions. Across different audio LLMs and emotion recognition datasets evaluations, our design improves SER performs across different evaluation metrics, supporting test-time memory as a residual contextual mechanism for conversational SER. --- ### OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning Authors: Jiahao Wang, An Ping, Yanghai Wang, Yuanxing Zhang, Shihao Li, Hanyan Bian, Yichi Ren, Yize Zhang, Han Wang, Haowen Chen, Junze Li, Jiaqi Wang et al. Published: 2026-06-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.08572v1 While Omni-modal Large Language Models (OLLMs) have demonstrated impressive capabilities in jointly processing audio and visual streams, their ability to strictly adhere to complex, multi-faceted user instructions remains largely unexplored. Existing benchmarks primarily focus on holistic video understanding or text-only instruction following, failing to capture the intricate interplay between modalities and user constraints. To bridge this gap, we introduce OmniCap-IF, the first comprehensive benchmark specifically designed to evaluate instruction-following capabilities in omni-modal captioning. OmniCap-IF incorporates a systematic framework that assesses captions on two dimensions: format correctness and content correctness. Our benchmark encompasses 50 distinct constraint types across pure visual, pure audio, and audio-visual modalities, while integrating Temporal Grounding to assess spatio-temporal precision. Extensive evaluations of prominent models on 1,920 high-quality samples reveal significant performance disparities. Furthermore, our analysis uncovers a critical "format-content tradeoff", demonstrating that increasing formatting complexity directly degrades models' omni-modal reasoning abilities. Finally, to advance the field, we curate a 54K instruction-tuning dataset, OmniCap-IF-54K and present OmniCaptioner-IF, which achieves notable improvements in both complex instruction adherence and general omni-modal captioning performance. --- ### Calibration of Structured Ignorance Certificates for Diagnosing Unknown Unknowns in Reasoning Models Authors: Subramanyam Sahoo Published: 2026-06-07 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.08571v1 Large language models frequently fail in a characteristic way: rather than acknowledging ignorance, they produce fluent but incorrect answers to questions that lie beyond their knowledge boundaries. We introduce \textbf{Structured Ignorance Certificates} (SICs), a JSON-formatted output schema that demands a model explicitly name the missing domain intersection, enumerate required concepts, and propose a productive retrieval query rather than hallucinating an answer. To train models to produce high-quality SICs we construct a 7,347-sample \emph{Unknown-Unknown} (UU) dataset by prompting Qwen3-14B to stitch together questions from seven domains (physics, biology, engineering, CS, economics, medical, legal) into novel cross-domain queries that no single-domain expert could answer. We fine-tune a 14B-parameter model with Group Relative Policy Optimization (GRPO) using a composite reward that combines retrieval utility, concept specificity, and output-format validity. A paraphrase-divergence probe trained on model responses confirms that SIC-tuned outputs systematically exhibit higher unknown-unknown probability scores. Evaluation on 735 held-out UU questions achieves a 99.46\% JSON validity rate, a mean Certificate Specificity Score of 0.967, and a 3.6\% ROUGE-L improvement over the base model on retrieval-grounded generation -- demonstrating that explicit epistemic structuring is a learnable and measurable capability. --- ### Towards Accurate Emotion-Attributed Video Captioning via Fine-grained Emotion-Cause Pair Extraction Authors: Weidong Chen, Cheng Ye, Zhendong Mao, Liping Wang, Xinyan Liu, Yongdong Zhang Published: 2026-06-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.08566v1 Emotional Video Captioning (EVC) is a challenging task that aims to generate factually accurate and emotionally rich descriptions for videos. Existing EVC methods leverage holistic visual features to mine global emotional cues, and then aggregate multimodal features to guide the emotional caption generation, which ignores the critical characteristic of the EVC task. Visual emotions are evoked by specific motivational causes, which are usually only implied in core video segments. The holistic mining brings significant information redundancy and inaccurate emotional cues. Thus, fine-grained visual cause extraction has a facilitative effect on both emotion perception and emotion-attributed caption generation. To this end, we propose a fine-grained emotion-cause pair extraction framework for emotion-attributed video captioning. Specifically, we learn pair-wise emotion and cause features in two rounds: 1) We propose a Concept-aware Visual Semantic Decomposition module to augment visual features by exploring scene, object, and motion concepts. Besides, to enhance emotional features, we propose a Visual-guided Emotion Interpretable Learning module, which guides emotion refinement with visual temporal dynamics, and augments the interpretable refinement process by reliable VAD-vector constraints. 2) We achieve emotion-cause pair extraction by cross-coupling the visual and emotional features before and after refinement, and leverage contrastive loss to achieve semantic forced alignment. Overall, our approach optimizes complex semantic understanding and emotion perception of videos, leading to a promising performance in emotional captioning. Extensive experiments on three challenging datasets demonstrate the superiority of our approach and each proposed module, e.g., achieving the best performances with +4.4% and +5.4% w.r.t. BLEU-2 and ROUGE-L, respectively, on the EVC-MSVD dataset. --- ### EinSort: Sorting is All We Need for Tensorizing LLM Authors: Toshiaki Koike-Akino, Jing Liu, Ye Wang Published: 2026-06-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.08565v1 Tensor networks provide efficient representations for compressing large neural networks. By carefully designing shapes and topologies, they can significantly reduce memory and computational costs. However, identifying implicit low-rank structures in large foundation models remains challenging due to their enormous scale and un-structured weight distributions. We propose an adaptive tensorization method that discovers inherent low-rank structure in a target tensor by index ordering. Experiments on weight and KV-cache compression demonstrate improved reconstruction quality compared to baselines. --- ### Physics-Guided Dual Decoding and Spectral Supervision for Global 3D Hydrometeor Prediction Authors: Dandan Chen, Yaqiang Wang Published: 2026-06-07 Categories: cs.LG, physics.ao-ph arXiv: https://arxiv.org/abs/2606.08563v1 While global data-driven models excel at predicting continuous atmospheric variables, three-dimensional hydrometeor forecasting remains challenging due to the zero-inflated, long-tailed distributions of these variables. Standard deep learning optimization often yields overly smooth forecasts, attenuating extreme events and spatial textures. We propose PredHydro-Net, a physics-guided dual-decoding framework that mitigates this smoothing. To resolve multi-variable optimization conflicts, it employs a decoupled architecture where macroscopic thermodynamic and dynamic fields unidirectionally modulate hydrometeor generation. By integrating wavelet-based frequency decoupling, spectral amplitude matching, and adversarial training, the model achieves a favorable trade-off between quantitative accuracy and spatial fidelity. In a 72-h global evaluation, PredHydro-Net outperforms both spatiotemporal deep learning baselines (Earthformer and PredRNNv2) and the operational Global Forecast System (GFS) in extreme-event detection and spectral representation. Furthermore, it demonstrates strong climatological consistency with Global Precipitation Measurement (GPM) satellite retrievals. The model reasonably reproduces the three-dimensional cloud structures in extreme weather events, such as Hurricane Ian. Feature attribution confirms its dependence on physical precursors such as relative humidity and wind convergence, offering a robust, physics-informed approach to long-tailed atmospheric prediction. --- ### Inside the LLM Word Factory Authors: Benzi Busigin, Yuval Pinter Published: 2026-06-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.08562v2 Transformer language models process input provided as subword fragments, but natural language semantics usually rely on word-level concepts. Detokenization is the process where models reconcile these two facts, aggregating subwords into word-level representations through their computation. Prior work has found that this takes place mostly in early-to-middle layers, but so far the exact mechanics of the process have not been pinned down. We venture deep into detokenization using activation patching in controlled paired experiments that isolate the contribution of different model components, localizing English detokenization in Llama2-7B to a two-stage process at Layer 1. Attention transmits a token-specific signal from nonfinal subwords, using sequential relays if necessary, while the MLP composes it with the local embedding. This two-stage structure generalizes to twelve models from eight families, but the depth over which it takes place depends on the flavor of positional encoding: RoPE-based models detokenize over 1 to 5 layers, while learned-absolute models take 5 to 10. Finally, we provide a probe for determining the success of the detokenization process based on early-layer activations alone, performing at 0.94-0.97 AUROC depending on the amount of context. --- ### Inside the LLM Word Factory Authors: Benzi Busigin, Yuval Pinter Published: 2026-06-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.08562v1 Transformer language models process input provided as subword fragments, but natural language semantics usually rely on word-level concepts. Detokenization is the process where models reconcile these two facts, aggregating subwords into word-level representations through their computation. Prior work has found that this takes place mostly in early-to-middle layers, but so far the exact mechanics of the process have not been pinned down. We venture deep into detokenization using activation patching in controlled paired experiments that isolate the contribution of different model components, localizing English detokenization in Llama2-7B to a two-stage process at Layer 1. Attention transmits a token-specific signal from nonfinal subwords, using sequential relays if necessary, while the MLP composes it with the local embedding. This two-stage structure generalizes to twelve models from eight families, but the depth over which it takes place depends on the flavor of positional encoding: RoPE-based models detokenize over 1 to 5 layers, while learned-absolute models take 5 to 10. Finally, we provide a probe for determining the success of the detokenization process based on early-layer activations alone, performing at 0.94-0.97 AUROC depending on the amount of context. --- ### CP-factorization for high dimensional tensor time series and double projection iterations Authors: Jinyuan Chang, Guanglin Huang, Qiwei Yao, Long Yu Published: 2026-06-07 Categories: stat.ME, econ.EM, stat.ML arXiv: https://arxiv.org/abs/2606.08560v2 We adopt the canonical polyadic (CP) decomposition to model high-dimensional tensor time series. Our primary goal is to identify and estimate the factor loadings in the CP decomposition. We propose a one-pass estimation procedure through standard eigen-analysis for a matrix constructed based on the serial dependence structure of the data. The asymptotic properties of the proposed estimator are established under a general setting as long as the factor loading vectors are linearly independent, allowing the factors to be correlated and the factor loading vectors to be not nearly orthogonal. The procedure adapts to the sparsity of the factor loading vectors, accommodates weak factors, and demonstrates strong performance across a wide range of scenarios. To further reduce estimation errors, we also introduce an iterative algorithm based on a novel double projection approach. We theoretically justify the improved convergence rate of the iterative estimator, and derive the associated limiting distribution. A consistent estimator of the asymptotic variance is also provided, which plays a key role in the related inference problems. All results are validated through extensive simulations and two real data applications. --- ### CP-factorization for high dimensional tensor time series and double projection iterations Authors: Jinyuan Chang, Guanglin Huang, Qiwei Yao, Long Yu Published: 2026-06-07 Categories: stat.ME, econ.EM, stat.ML arXiv: https://arxiv.org/abs/2606.08560v1 We adopt the canonical polyadic (CP) decomposition to model high-dimensional tensor time series. Our primary goal is to identify and estimate the factor loadings in the CP decomposition. We propose a one-pass estimation procedure through standard eigen-analysis for a matrix constructed based on the serial dependence structure of the data. The asymptotic properties of the proposed estimator are established under a general setting as long as the factor loading vectors are linearly independent, allowing the factors to be correlated and the factor loading vectors to be not nearly orthogonal. The procedure adapts to the sparsity of the factor loading vectors, accommodates weak factors, and demonstrates strong performance across a wide range of scenarios. To further reduce estimation errors, we also introduce an iterative algorithm based on a novel double projection approach. We theoretically justify the improved convergence rate of the iterative estimator, and derive the associated limiting distribution. A consistent estimator of the asymptotic variance is also provided, which plays a key role in the related inference problems. All results are validated through extensive simulations and two real data applications. --- ### A Theoretical Analysis of Memory and Overfitting Phenomena in Stochastic Interpolation Models Authors: Yunchen Li, Shaohui Lin, Zhou Yu Published: 2026-06-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.08554v1 This paper provides a theoretical account of memorization in stochastic interpolation models. By leveraging closed-form expressions for the optimal velocity field and the associated score function, we show that, in the continuous-time oracle setting, both deterministic and stochastic generation processes recover training samples. Under Euler discretization, generated samples remain centered around training samples, with deviations controlled by the step size. We further analyze generation in the presence of estimation errors and show that accumulated estimation errors control the endpoint deviation from the training set. These results imply that the generated sample admits a representation as a training sample perturbed by three controlled terms: a discretization-induced bound, an estimation-error-induced bound, and stochastic Gaussian noise. Based on this characterization, we provide theoretical definitions of overfitting and underfitting in generative models. Synthetic simulations support our theoretical findings. --- ### Quantitative Promise Theory: Intentionality and Inference in Autonomous Agents Authors: Mark Burgess Published: 2026-06-07 Categories: cs.AI, cs.MA, cs.NE, physics.data-an arXiv: https://arxiv.org/abs/2606.08552v1 I discuss some quantitative representations of Promise Theory for processes involving autonomous agents. Agent models are common in software systems, machine learning, and biology, for example, but may also apply to physics and other forms of engineering. I describe how Bayesian probability and information theoretic optimization, including Active Inference, may be incorporated with promise semantics -- as well as how Promise Theory supplements solutions, helping to avoid probability's pitfalls, which include non-local coordination, calibrating, and normalizing probabilistic computations. The role of boundary conditions in constraining allowed states and selecting decision thresholds is a form of promise, and agent alignment provides a scalable definition of intent. Autonomous agents may congeal into swarms with superagent characteristics by trying to minimize their information, despite uncertainty that works to maximize it. The use of Promise Theory involves some research challenges as well as stylistic preferences. --- ### Ishigaki-IDS: An Open-Weight Verifier-Aware Model for Information Delivery Specification Drafting in Building Information Modeling Authors: Ryo Kanazawa, Koyo Hidaka, Teppei Miyamoto, Takayuki Kato, Tomoki Ando, Chenguang Wang, Dayuan Jiang, Naofumi Fujita, Shuhei Saitoh, Atomu Kondo, Koki Arakawa, Daiho Nishioka Published: 2026-06-07 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2606.08545v1 Building Information Modeling (BIM) projects require information requirements to be described as machine-checkable Information Delivery Specification (IDS) files in order to verify whether building models contain the required attributes. However, IDS authoring remains a practical bottleneck: practitioners must handle domain vocabulary, strict XML schema constraints, and external validator conformance while also checking whether the requirement itself is correctly expressed. We present Ishigaki-IDS, an open-weight LLM specialized for verifier-aware IDS draft generation. The model combines continued pretraining on BIM/IDS corpora, supervised fine-tuning on information-requirement-to-IDS pairs, and reinforcement learning with verifiable rewards from an external validator. The goal is not to replace expert review, but to move IDS authoring from low-level XML and schema repair toward validator-loadable drafts that practitioners can inspect and correct. On the 166-case expert-created Ishigaki-IDS-Bench, Ishigaki-IDS-8B achieves an IDSAuditPass score of 0.651, a validator-pass metric for generated IDS files, substantially outperforming Claude Opus 4.5, the strongest single-shot LLM baseline we evaluated, at 0.331. It also obtains an Audit-Gated FacetF1 of 0.282, which measures requirement-facet alignment among validator-passing drafts. The same recipe scales: 14B and 32B variants reach IDSAuditPass 0.753 / 0.693 and Audit-Gated FacetF1 0.392 / 0.369. In a workflow check with six BIM practitioners, Ishigaki-assisted authoring reduced aggregate work time by 54.7% under the same validation and alignment endpoint. These results suggest that verifier-aware IDS generation can reduce the practical burden of converting BIM information requirements into reviewable IDS drafts. --- ### PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR Authors: Shumeng Yang, Yisu Liu, Jiayi Zheng, Zhaohui Yang, Linjing Li Published: 2026-06-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.08543v1 Reinforcement learning with verifiable rewards (RLVR) improves large language model reasoning but often suffers from rapid policy-entropy collapse, where the policy prematurely concentrates on narrow high-probability reasoning paths. While global entropy regularization can encourage exploration, uniformly increasing entropy across all token positions is inefficient for long reasoning trajectories, where many tokens are not decision-relevant. We propose Position-Aware Entropy Calibration (PAEC), a token-level entropy-management framework that constructs a soft mask from local top-p entropy and top-two candidate competition, and applies an anchor-based lower-bound penalty to prevent selected-position entropy collapse. Experiments on five mathematical reasoning benchmarks show that PAEC improves macro-average majority-vote performance over strong RLVR baselines, with clear gains on AIME-style tasks. Our results suggest that entropy management in reasoning RL should be formulated as selective exploration allocation over decision-sensitive positions rather than uniform randomness injection. --- ### When Video Misreads: Closed-Loop Distillation of Reading Heuristics for Exploratory Manipulation Trace QA Authors: Haizhou Ge, Yufei Jia, Yue Li, Zhixing Chen, Lu Shi, Lei Han, Guyue Zhou, Ruqi Huang Published: 2026-06-07 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2606.08542v1 Exploratory manipulation often turns an apparent failed attempt into the key evidence for what to do next. For example, a robot pulls a locked cabinet drawer, fails, and only succeeds after opening the lock. The failed pull reveals a latent precondition (the drawer is locked) that determines the minimal-success action chain (the fewest actions that complete the task), here (lock-open, drawer-pull). Correctly reading this trace is therefore the prerequisite for recovering that chain. We formalize this setting as Exploratory Manipulation Trace QA (EMT-QA): given synchronized video and proprioception from an exploratory trace, predict the minimal-success action chain under the latent precondition revealed by the probe. However, even state-of-the-art VLMs and embodied multimodal LLMs misread this evidence: they do not reliably recover the chain from raw video, raw proprioception, or their combination. We introduce Closed-Loop Trace Distillation, a pipeline that uses a per-task coding agent to inspect labeled training traces and distill a one-line natural-language prompt over the trace, which we call the Distilled Reading Heuristic (DRH). At inference, no agent is invoked and no model weights are updated; a frozen VLM receives the raw trace plus the DRH as a prompt entry. Across three simulator and two real-robot tasks, the DRH improves chain accuracy by +0.38 to +0.47 over the best raw-modality baseline. The same DRH also serves as the sole specification for one-shot programmatic classifiers that match the prompted VLM. --- ### AgentTrust: A Self-Improving Trust Layer for AI-Agent Actions Authors: Chenglin Yang Published: 2026-06-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.08539v1 AI agents increasingly take consequential actions -- shell commands, cloud operations, and arbitrary tool-calls -- so a trust layer must decide, per action, whether to allow, warn, block, or escalate. We argue that the right way to reason about such a layer is by threat type. Lexical (fixed-signature) threats, where danger lives in a stable token, are decidable by deterministic rules; semantic (intent-dependent) threats, where a benign and a malicious action share the same surface, are out of reach for rules by construction. We make this concrete with a negative proof: a determined, hand-authored cloud rule pack lifts held-out accuracy only 48 to 56% overall and moves the semantic categories by 0pp (data_db 29 to 29, observability 59 to 59, supply_chain 50 to 50), while a strong LLM judge carries exactly those categories. We give the judge a self-learning capability: on a corpus that is mainly semantic attacks it nearly doubles rule accuracy (48% to 83.6-85.2%) with near-zero false-blocks, and this holds across two model providers. We turn this into a self-improving dual-store system: the judge distills a growing deterministic rule floor on lexical threats (cheaper over time) and feeds a guarded RAG memory on semantic threats (a verdict-cache fails -- surface-twins collapse to ~58% -- so a corroboration guard lifts semantic accuracy +13pp, 70 to 84). The result is what sets AgentTrust v2 apart from its static v1 predecessor: a trust layer that self-evolves from its own stream of decisions -- cheaper on the lexical class (it distils its own rules) and smarter on the semantic class (it accrues guarded precedent), while never hard-blocking a benign action. An end-to-end online replay shows the judge-call rate falling (50% to 44%) and judge-domain accuracy rising (71% to 80%), with 0 benign hard-blocks across 45,000 actions. --- ### Routine laboratory trajectories encode the onset of organ-level complications in cancer Authors: Jannik Lübberstedt, Krischan Braitsch, Jacqueline Lammert, Christof Winter, Florian Gabriel, Tristan Lemke, Christopher Zirn, Markus Graf, Friedrich Puttkammer, Hartmut Häntze, Johannes Moll, Anirudh Narayanan et al. Published: 2026-06-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.08538v1 Routine laboratory panels drawn during cancer treatment constitute longitudinal physiological recordings of organ function, yet their temporal structure is discarded by single-timepoint prognostic tools. A transformer trained on 2,777,595 laboratory measurements from 3,905 patients with multiple myeloma or ovarian cancer predicted the two-year onset of 162 treatment-associated complications, including therapy-related myelodysplastic syndromes, spanning eight clinical categories, achieving 1.5- to 6.1-fold enrichment above prevalence at the group level. It matched or outperformed non-sequential baselines across grouped endpoints (AUROC gains up to +0.11), demonstrating that longitudinal laboratory trajectories capture evolving complication-specific physiology inaccessible from isolated measurements. Predictions generalised across both cancers, divergence concentrating in disease-specific complications, and biomarker masking recovered signatures consistent with established pathophysiology. External validation on MIMIC-IV and MMRF CoMMpass confirmed transferability across independent healthcare systems (AUROC up to 0.85). Routine oncological laboratory data encode organ deterioration weeks to months before clinical onset, enabling complication-specific surveillance without additional testing infrastructure. --- ### NGram-MoSE: Efficient Remote Sensing Super-Resolution via N-Gram Context and Mixture-of-Experts Authors: Yun-Hsuan Huang, Trong-An Bui, Chih-Hung Chuang Published: 2026-06-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.08535v1 Remote sensing applications for environmental monitoring and disaster management are frequently constrained by a spatial--temporal trade-off: imagery with fine spatial detail is often acquired less frequently, whereas more temporally available observations are typically coarser. Single-image super-resolution provides a practical means to enhance coarse imagery without changing acquisition schedules, yet many Transformer-based SR models remain computationally expensive and can be sensitive to limited or geographically biased training data, which degrades robustness under out-of-distribution conditions. This paper presents NGram-MoSE, a lightweight Transformer architecture designed to improve both efficiency and texture continuity. NGram-MoSE introduces N-Gram Context Injection to strengthen cross-window local consistency and mitigate window-boundary artifacts, and incorporates a Mixture-of-Experts (MoE) feed-forward design to scale capacity through sparse activation without proportional growth in inference cost. Experiments on a geographically disjoint OOD test set show that NGram-MoSE achieves 31.68\,dB PSNR while reducing FLOPs by \(14\times\) relative to a heavyweight Transformer reference. Downstream evaluation on a landslide segmentation benchmark further demonstrates that restoring degraded inputs to the detector training scale improves performance, yielding a 4.47\% absolute gain in mAP@50 over bicubic upsampling, and exhibits stronger cross-scale consistency under scale extrapolation. These results indicate that NGram-MoSE provides an effective SR module for resource-constrained remote sensing pipelines requiring robust generalization. --- ### Autonomous Aerial Manipulation via Contextual Contrastive Meta Reinforcement Learning Authors: Lixuan Jin, Bingxuan Lan, Xinyi Bao, Xiangyuan Xie, Chunjie Zhang, Zheng Chen, Tianshuo Liu, Ruijie Tian, Jinyu Ru, Gang Wang, Lei Yuan, Yang Yu Published: 2026-06-07 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2606.08533v1 Unmanned aerial vehicles (UAVs) are increasingly being deployed in logistics, service robotics, and other real-world applications, creating a growing demand for autonomous payload acquisition and delivery. Existing approaches typically assume pre-attached payloads or rely on specialized grippers, leaving versatile end-to-end aerial delivery largely unresolved, where different payloads induce highly variable flight dynamics, requiring a single policy to adapt online without manual calibration or explicit system identification. To this end, we study \textbf{A}utonomous \textbf{A}erial Manipulation via \textbf{Co}ntextual \textbf{Co}ntrastive Meta Reinforcement Learning (\textbf{\textit{Aco2}}), a fully autonomous aerial delivery setting in which a quadrotor equipped with a lightweight hook continuously picks up, transports, and delivers diverse handle-equipped objects between randomized locations, all without human intervention. First, we design a contextual observation encoder that infers a compact latent context from recent interaction history, enabling the policy to adapt online to payload-dependent dynamics. To further improve the quality of this context, we introduce a contrastive objective that structures the context embedding around task-relevant variations, improving generalization across diverse payloads without requiring explicit system identification. Trained entirely in simulation with extensive domain randomization, \textit{Aco2} can be directly deployed on a physical quadrotor without real-world fine-tuning. --- ### DN-Hypo-Pipeline: An AI-Driven Workflow for Generating Hypotheses using Large Language Models and Scientific Explanations Authors: Lei Lin, Xinlong Pan, Ronghao Wang, Chunbao Zhou, Jue Wang, Yangang Wang, Ivana Rasovska Published: 2026-06-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.08532v5 Modern artificial intelligence excels at prediction but cannot explain. From large language models to AI-for-science systems, today's machines answer what by recombining patterns already present in the human literature, yet they cannot reason out why a phenomenon must arise from underlying principles even though explanation, not prediction, lies at the heart of scientific discovery. Here we ask whether the structure of scientific explanation can be operationalized to guide how a machine generates hypotheses. We introduce DN-Hypo-Pipeline, a hypothesis-generation framework that adopts a layered, explanation-theoretic scaffold: Hempel's deductive-nomological (DN) model supplies the output form and deductive validity of a hypothesis, Salmon's causal-process account supplies an organizing constraint on where to search for the governing laws, and Armstrong's view of laws as relations between universals supplies the bridge from a phenomenon's constituent processes to the laws that may be associated with it. Rather than searching the space of what has been written, the framework searches the space of what principles govern a phenomenon: given an explanandum, it abstracts the universals instantiated in the phenomenon's formation process, retrieves the laws relating those universals, and deductively reconstructs a new, testable explanation. Evaluated in data-science modeling and judged by both LLMs and human experts, hypotheses generated through this principled reasoning significantly outperform those from direct prompting. Crucially, we translated the two highest-scoring hypotheses into novel algorithms one that reduces the Transformer's theoretical complexity with only minimal performance loss, and another that achieves competitive accuracy with substantially fewer parameters. --- ### ForesightSafety-SAGE:A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents Authors: Lu Jia, Haibo Tong, Feifei Zhao, Jindong Li, Dongqi Liang, Ping Wu, Qian Zhang, Yi Zeng Published: 2026-06-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.08531v3 Large language models (LLMs) are increasingly evolving from simple text-based interaction systems into LLM agents that can maintain memory, use tools, access external environments, and execute tasks. As their capabilities and autonomy expand, the safety risks they face also become more diverse. Existing evaluations often rely on manually written scenarios, static prompts, or final-output judgments, making it difficult to capture the diverse risks that agents may face during task execution. We introduce ForesightSafety-SAGE, a fully automated scenario generation and safety evaluation framework for LLM agents. Based on five risk dimensions,we instantiae abstract and diverse safety risks in real-world task execution into 1,072 measurable evaluation scenarios. Using the automated evaluation pipeline, 12 LLM agents are evaluated under two authority contexts. The results show that current agents still face substantial behavioral safety risks during task execution, with an average ASR of 47.1% and several models exceeding 70%. These findings demonstrate the importance of executable, process-level evaluation for understanding and improving LLM agent safety. --- ### VESTA: A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents Authors: Lu Jia, Haibo Tong, Feifei Zhao, Jindong Li, Dongqi Liang, Ping Wu, Qian Zhang, Yi Zeng Published: 2026-06-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.08531v1 Large language models (LLMs) are increasingly evolving from simple text-based interaction systems into LLM agents that can maintain memory, use tools, access external environments, and execute tasks. As their capabilities and autonomy expand, the safety risks they face also become more diverse. Existing evaluations often rely on manually written scenarios, static prompts, or final-output judgments, making it difficult to capture the diverse risks that agents may face during task execution. We introduce VESTA, a fully automated scenario generation and safety evaluation framework for LLM agents. Based on five risk dimensions, VESTA instantiaes abstract and diverse safety risks in real-world task execution into 1,072 measurable evaluation scenarios. Using the automated evaluation pipeline, 12 LLM agents are evaluated under two authority contexts. The results show that current agents still face substantial behavioral safety risks during task execution, with an average ASR of 47.1% and several models exceeding 70%. These findings demonstrate the importance of executable, process-level evaluation for understanding and improving LLM agent safety. --- ### GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation Authors: Yuan Zhang, Shiqi Zhang, Yedong Shen, Shuai Dong, Jiajun Deng, Xin Zhang, Yuxuan Gao, Jiajia Wu, Xin Nie, Zhiyuan Cheng, Jianmin Ji, Yanyong Zhang et al. Published: 2026-06-07 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.08530v2 Vision-Language-Action (VLA) models achieve strong benchmark performance but still struggle in real-world deployment with unseen objects, background shifts, and different robot embodiments. We argue that this stems from the lack of a unified geometry-aware manipulation representation, leaving existing VLAs vulnerable to low-level trajectory supervision, misaligned 3D features, and embodiment differences. To address this, we propose GEAR-VLA, a VLA framework for learning unified geometry-aware action representations for generalizable robotic manipulation. GEAR-VLA adopts coarse-to-fine action learning, where multi-source embodied pretraining equips the VLM with embodied reasoning and discrete action understanding before latent action tokens connect action semantics to a gradient-decoupled DiT continuous action expert. It further performs semantic-aligned 3D integration by aligning a trainable 3D spatial backbone with the VLA representation while freezing the original VLM-aligned visual pathway. To share this representation across robots, GEAR-VLA uses embodiment canonicalization, where embodiment-aware states and embodiment-invariant actions confine robot differences to the low-level interface. Extensive simulation and real-world experiments demonstrate strong generalization: GEAR-VLA achieves state-of-the-art performance on LIBERO, zero-shot LIBERO-Plus, and RoboTwin 2.0, reaches 85.9% success on AgileX and 81.0% on the pretraining-unseen LDT-01 embodiment, and obtains 90.1% success on a 6,360-trial universal grasping benchmark with 212 unseen objects. Code and models will be released at https://github.com/babynabeauty/GEAR-VLA. --- ### Scaffold Effects on GAIA: A Controlled Comparison Authors: Jason Starace Published: 2026-06-07 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.08529v1 Published agent capability scores conflate what a model can do with what its scaffold lets it do, and the magnitude of this elicitation gap is not well characterized under controlled conditions. This study executes a pre-registered controlled comparison of three scaffolds (ReAct, a Planner-Actor-Rater multi-agent design, and planner-then-executor) across five models from three providers (Claude Opus 4.7, Sonnet 4.6, Haiku 4.5; Gemini 3.1 Pro Preview; GPT-5.5) on GAIA validation Levels 1 and 2, holding tasks and conditions fixed, with three attempts per question. Scaffold choice alone moves measured accuracy by as much as 28 percentage points within a single model (Opus, Level 2, robust slice), confirming the pre-registered hypothesis that scaffold variation produces gaps of at least 10 points. The pre-registered prediction that more capable models would be less scaffold-sensitive is rejected in direction: scaffold effects vary significantly by model in every dataset slice, but the most capable Anthropic model gains the most from structured scaffolds at the harder level, and tier-scaling holds only at Level 1 under the robust slice. The multi-agent advantage over ReAct at Level 2 appears within the Anthropic family but not for the cross-provider models, making model family rather than capability tier the conditioning variable, and the predicted planner-executor advantage on file-reading tasks is falsified. Structured scaffolds make fewer tool calls yet recover more often from mid-trajectory errors at the harder level, and a single cell (Gemini with planner-then-executor) is the cheapest at both levels and the most accurate at Level 2. These results indicate that single-scaffold capability numbers are scaffold-conditional estimates and that the elicitation gap is not guaranteed to shrink as models improve. --- ### DriveReward: A Comprehensive Dataset and Generative Vision-Language Reward Model for Autonomous Driving Authors: Qimao Chen, Fang Li, Yuechen Luo, Zehan Zhang, Haiyang Sun, Fangzhen Li, Bing Wang, Guang Chen, Yang Ji, Jiong Deng, Hongwei Xie, Hangjun Ye et al. Published: 2026-06-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.08525v2 Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving. However, acquiring such rewards typically relies on hand-crafted rule-based objectives or perception ground truth, which hinders generalization for data-scaling. While Vision-Language Models (VLMs) have demonstrated feasibility as reward models in other domains, their effectiveness in driving tasks remains underexplored. In this work, we bridge this gap by (1) introducing DriveReward, a reasoning trajectory evaluation dataset rigorously labeled via temporally-grounded visual guidance, and augmented with counterfactual driving behaviors., (2) alongside a specialized Vision-Language Reward Model. To address the scarcity of failure cases in conventional datasets, we propose a counterfactual data annotation scheme to construct cases encompassing diverse driving styles and erroneous behaviors. Evaluations on our proposed benchmark reveal that even leading open-source and proprietary VLMs fail to excel across all tasks, highlighting significant room for improvement in existing models. Building on these findings, we subsequently tailor a specialized 1B reward model that outperforms larger VLMs on task-specific reward alignment. Finally, we validate our reward model's effectiveness by integrating it into RL finetuning and multi-modal trajectory scoring across multiple baselines, achieving performance comparable to rule-based reward calculations in both open-loop and closed-loop evaluation. --- ### A Joint Finite-Sample Certificate for Adaptive Selective Conformal Risk Control Authors: Xiaoli Yu, Jiamiao Liu Published: 2026-06-07 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.08517v1 Selective predictors answer on confident inputs and abstain elsewhere; deploying one safely needs a single finite-sample certificate that simultaneously upper-bounds the selected risk, lower-bounds the acceptance probability $\pacc$ above a floor $\pmin$, and lower-bounds the deployment utility. This certificate must be valid under adaptive threshold selection from a finite grid of $m$ pairs on $\ncert$ samples. We give such a certificate for bounded, possibly non-monotone losses by treating the selected risk directly as a ratio rather than through a Hoeffding-style range bound. The construction couples three confidence bounds: a variance-adaptive empirical-Bernstein bound on the ratio risk, a Clopper--Pearson bound on acceptance, and a two-sided closeness bound on utility. Together they lower-bound the certified policy's utility absolutely and to within $2\gammau$ of the best over the \emph{certified set}, both non-vacuous whenever feasible; a regime-scoped third leg matches an external oracle, informative only where the risk margin $\gammar < α$ and vacuous at the headline operating points. Relative to the range-only Hoeffding-ratio construction this sharpens the acceptance-floor dependence from $1/\pmin$ to $1/\sqrt{\pmin}$, and a closed-form corollary identifies a per-pair regime in which our risk bound dominates a Hoeffding conformal risk control (Hoeffding--CRC) selective bound. Empirically, on ImageNet (three ResNets) and COCO val 2017 panoptic, the certificate opens a $+22$ pp certified-acceptance frontier over Hoeffding--CRC and is ${\approx}10{\times}$ tighter than a non-vacuous matched-valid baseline; these gains are regime-scoped, not universal, and absent on ADE20K. The certifier runs in $O(\ncert m)$ time. --- ### OmniTryOn: Video Try-On Anything at Once! Authors: Changliang Xia, Chengyou Jia, Minnan Luo, Zhuohang Dang, Xin Shen, Bowen Ping Published: 2026-06-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.08514v2 Although video virtual try-on (VVT) has achieved significant progress, existing methods still exhibit two fundamental limitations: first, they are restricted to single-garment transfer, rendering simultaneous multi-object try-on highly impractical; second, their heavy reliance on explicit external priors (e.g., garment masks) inevitably destroys crucial physical dynamics and degrades visual quality. To bridge this gap, this paper proposes the novel Try-On Anything task, which aims to simultaneously transfer diverse wearable objects onto a person in a video in a single inference pass. To support and standardize this paradigm, we introduce TryAny-Bench, a comprehensive benchmark encompassing a paired video dataset alongside a tailored evaluation protocol. Furthermore, we present OmniTryOn, an external-prior-free generative framework designed to tackle this task. Specifically, OmniTryOn employs a First Frame Wearable Cache strategy, which directly provides diverse wearable objects for the generation process through the initial video frame. To maintain consistency, we propose the Spatiotemporally Consistent RoPE (STC-RoPE), which inherently establishes robust spatiotemporal anchors to strictly preserve complex human motions and background dynamics. Optimized by the proposed Gradual Try-On (GTO) training strategy, our model progressively masters robust multi-object synthesis. Extensive experiments on TryAny-Bench demonstrate that OmniTryOn significantly outperforms existing specialized video virtual try-on models and general video editing baselines, establishing a powerful new standard for the Try-On Anything task. Our dataset, code, and models are available at https://github.com/xcltql666/OminTryOn. --- ### Towards End to End Motion Planning and Execution for Autonomous Underwater Vehicles Using Reinforcement Learning Authors: Elisei Shafer, Oren Gal Published: 2026-06-07 Categories: cs.RO, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2606.08513v1 Autonomous Underwater Vehicles (AUVs) traditionally rely on complex, heavily engineered pipelines for perception, path planning, and motion control. This paper explores the feasibility of an end-to-end Deep Reinforcement Learning (DRL) approach that maps raw sensor data directly to thruster commands, reducing manual engineering. We propose a hierarchical reinforcement learning (HRL) architecture splitting the problem into two Markov Decision Processes. A High-Level (HL) policy operating at 2Hz processes raw $84 \times 84$ pixel monocular camera frames, stacked $100 \times 100$ pixel forward-looking imaging sonar, and proprioceptive data to generate spatial subgoals. Simultaneously, a Low-Level (LL) policy operating at 10Hz converts these subgoals into thruster commands. The HL policy is trained using Reinforcement Learning from Prior Demonstrations (RLPD) within a modified Sample-Efficient Robotic Reinforcement Learning (SERL) framework, while the LL policy utilizes Soft Actor-Critic (SAC) combined with Hindsight Experience Replay (HER). Evaluated in the high-fidelity HoloOcean simulator, our method demonstrates successful obstacle avoidance, achieving trajectory lengths closely approximating (within 4% to 6% of) an $\text{RRT}^*$ planning baseline. Furthermore, the learned policy exhibits strong robustness to simulated sensor noise and decreased visibility. While the system navigates familiar geometries effectively, experiments reveal generalization limitations when encountering unvisited areas with novel obstacle shapes. Ultimately, this work demonstrates the promise of sample-efficient, end-to-end DRL for underwater navigation using minimal computational hardware. --- ### Friend or Foe? Language as an ideological switch in open-weight LLMs under Russian disinformation stress Authors: Anna Małgorzata Kamińska, Tetiana Klynina Published: 2026-06-07 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2606.08512v1 As Russia's war against Ukraine extends into generative AI, large language models (LLMs) adapted for local post-Soviet languages are deployed in contested information environments. Policy and industry discourse assumes that culturally aligned adaptation encodes the political orientation of the target community: a Ukrainian-oriented model will resist Russian narratives, a Russian-oriented one will reinforce them. Does it? This article systematically disconfirms that assumption. We run a controlled audit of four openly available LLMs sharing a common base model but fine-tuned for different linguistic communities, querying them in Ukrainian, Russian and English across ten contested wartime narratives: Crimea, "denazification", the "one people" thesis, and atrocity denial at Bucha and Mariupol. The result is a Fine-Tuning Paradox: the Ukrainian-oriented model shows the weakest resistance to Russian disinformation in Russian, while the Russian-oriented one exhibits the strongest rejection. Corpus composition, language coverage and prompt format prove more decisive than nominal cultural provenance. We situate these findings within debates on hybrid warfare, digital sovereignty and post-imperial information orders, arguing that the principal threat to regional information sovereignty is not adversarial fine-tuning but the untested assumption that cultural alignment guarantees resilience. --- ### Look Less, Reason More: Block-wise Attention Skipping for Efficient Multimodal LLMs Authors: Jie Ma, Zhike Qiu, Jiayi Ji, Xiaoshuai Sun, Rongrong Ji Published: 2026-06-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.08511v1 Multimodal Large Language Models (MLLMs) face a significant inference bottleneck due to the quadratic computational cost of self-attention over long visual token sequences. However, we identify a critical inefficiency in current architectures: Visual Attention Saturation. Our analysis reveals that visual tokens rapidly establish their spatial structure and intra-modal relationships in early layers, rendering visual-to-visual self-attention in deeper layers computationally redundant. Conversely, Feed-Forward Networks (FFNs) in these layers remain essential for projecting visual features into the evolving textual semantic space. Leveraging this insight, we present Visual-Skip (V-Skip), a training-free inference paradigm that decouples spatial interaction from semantic evolution. Rather than discarding tokens, V-Skip imposes block-wise structured sparsity by selectively bypassing saturated visual self-attention modules. Furthermore, recognizing that varying downstream tasks demand distinct reasoning depths, V-Skip employs a lightweight, few-shot calibration to dynamically route the task-optimal sparsity path. Extensive experiments demonstrate that V-Skip effectively bypasses redundant vision attention to achieve block-wise sparsity, maintaining a 94.16% to 100.31% performance retention across diverse MLLMs. Ultimately, we prove that to reason more effectively, models do not need to discard what they see -- they simply need to "look less" at the right depth. --- ### ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies Authors: Bingjia Huang, Xiangyu Li, Xiang Wang, Liang Mi, Zixu Hao, Weijun Wang, Hao Wu, Kun Li, Yunxin Liu, Ting Cao Published: 2026-06-07 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.08508v1 Generative robot policies fail unpredictably at deployment: they hesitate at critical moments, drift off-task, or commit to unrecoverable actions. Existing online failure detectors either require white-box access to policy internals or add runtime overhead through resampling and observation-side signals. Our empirical analysis shows that emitted action chunks themselves already carry strong predictive signal for impending failures in generative robot policies. Motivated by this observation, we introduce ActProbe, a lightweight, pure action-space detector that uses two compact signals available from a single forward pass: Temporal Consistency Error (TCE) between consecutive action chunks and Action Chunk Magnitude (ACM) of the current chunk. ActProbe maps these signals to per-step failure probabilities with a task-conditioned LSTM-MLP architecture. Across a diverse suite of generative robot policies and benchmarks, ActProbe raises alerts before failures become visually recognizable, improving the accuracy (F1)-timeliness Pareto frontier of failure detection by an average hypervolume gain of +12.7% over both internal- and external-feature baselines, with a +9.0% early-detection ROC-AUC lead on unseen tasks. ActProbe further transfers to deployment, predicting failures on unseen real-robot pick tasks and accelerating RL fine-tuning (PPO) with 2.9x fewer environment interactions. --- ### Standpoint Logics with Defeasible Beliefs Authors: Nicholas Leisegang, Thomas Meyer, Sebastian Rudolph Published: 2026-06-07 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2606.08503v1 In this paper, we integrate the defeasible logic of Kraus, Lehmann and Magidor (KLM) with the standpoint logic framework of Gómez Álvarez and Rudolph. This is done with the goal of formally expressing knowledge taking into account multiple (possibly contradicting) viewpoints, which in turn may hold defeasible beliefs. In doing so, we utilise Defeasible Restricted Standpoint Logics (DRSL), introduced by Leisegang et al. Our work expands on previous work by providing a foundational representation result for DRSL semantics and systematically lifting several well-known entailment relations from the propositional case to the standpoint-enhanced setting. In particular, we characterise the semantics for DRSL through a set of KLM-style postulates adapted for the standpoints case. We furthermore provide a means to lift preferential entailment, and the class of entailment relations based on single ranking functions from the purely propositional to the standpoint-enhanced context, including rational and lexicographic closure. We show this can be done equivalently through semantic and algorithmic means. Furthermore, we show that, for each considered form of entailment, the complexity class of entailment checking does not change when moving from propositional KLM to DRSL. --- ### Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models Authors: Yawen Shao, Jie Xiao, Kai Zhu, Yu Liu, Hongchen Luo, Xueyang Fu, Yang Cao, Wei Zhai, Zheng-Jun Zha Published: 2026-06-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.08501v2 Reinforcement learning (RL) holds immense promise for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, progress is fundamentally constrained by a dual misalignment between authentic generation trajectory and the gradient update process: (i) Process-reward misalignment. Sparse, terminal rewards are indiscriminately assigned to all intermediate steps of the generation process, failing to provide discriminative credit assignment. (ii) State-trajectory misalignment. Policy updates are often diverted toward artificial, out-of-trajectory states, squandering gradients on less informative samples. To address these limitations, we introduce Process Aligned Policy Optimization (PAPO), a novel framework that holistically aligns the RL update with the dLLM's generative trajectory via Step-Aware Process Rewards (SPR) that transform sparse terminal rewards into dense, step-wise credit, and Entropy-Guided Historical Re-enactment (EHR) that replays authentic trajectories at high-uncertainty steps. Extensive experiments on four benchmarks demonstrate that PAPO significantly outperforms baselines, achieving gains of 4.5% on GSM8K, 4.8% on MATH500, 42.2% on Countdown and 16.1% on Sudoku. --- ### Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models Authors: Yawen Shao, Jie Xiao, Kai Zhu, Yu Liu, Hongchen Luo, Xueyang Fu, Yang Cao, Wei Zhai, Zheng-Jun Zha Published: 2026-06-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.08501v1 Reinforcement learning (RL) holds immense promise for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, progress is fundamentally constrained by a dual misalignment between authentic generation trajectory and the gradient update process: (i) Process-reward misalignment. Sparse, terminal rewards are indiscriminately assigned to all intermediate steps of the generation process, failing to provide discriminative credit assignment. (ii) State-trajectory misalignment. Policy updates are often diverted toward artificial, out-of-trajectory states, squandering gradients on less informative samples. To address these limitations, we introduce Process Aligned Policy Optimization (PAPO), a novel framework that holistically aligns the RL update with the dLLM's generative trajectory via Step-Aware Process Rewards (SPR) that transform sparse terminal rewards into dense, step-wise credit, and Entropy-Guided Historical Re-enactment (EHR) that replays authentic trajectories at high-uncertainty steps. Extensive experiments on four benchmarks demonstrate that PAPO significantly outperforms baselines, achieving gains of up to 4.5% on GSM8K, 4.8% on MATH500, 42.2% on Countdown and 16.1% on Sudoku. --- ### Projecting the Emerging Mindset of SWE Agent by Launching a Wild Code Understanding Journey Authors: Zhengyi Zhuo, Yan Liu Published: 2026-06-07 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2606.08500v1 Software engineering agents (SWE agents) increasingly work through tool-mediated trajectories in real repositories, yet their behavior remains difficult to characterize in concrete, observable terms. These trajectories record tool use, intermediate reasoning, evidence selection, and self-directed stopping, but they do not by themselves explain why particular moves were chosen, what evidence was trusted, or when understanding was judged sufficient. This tension makes trajectory data both limited and valuable: faithful, replayable traces can become an empirical substrate for studying agent behavior when interpreted through disciplined observation. We introduce Ada, a scoped apparatus for repository-level code understanding. Ada enters real codebases through a bounded tool interface, allowing open-ended exploration to remain recordable as finite trajectories. Across this wild-but-bounded setting, Ada chooses where to look, what to read closely, when to consolidate partial understanding, and when to close its account of the repository. We project Ada's think-action chains through observation lenses that make navigation, evidence selection, synthesis, grounding, and stopping visible without reducing behavior to raw tool counts or speculating about hidden intent. Read together, these lenses produce behavioral profiles grounded in recorded movement through software worlds. Across 408 trajectories, spanning multiple models, repositories, task families, and launch conditions, the study shows how faithful digital traces can be transformed into disciplined, comparable projections of emerging SWE-agent mindset. The results expose differences in efficiency, trajectory diversity, epistemic grounding, and the limits of intervention, while providing a methodological foundation for observing SWE agent behavior in real codebases. --- ### Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets Authors: Minyoung Hwang, Seokhyun Lee, Changhee Lee Published: 2026-06-07 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.08497v1 As deep language models (DLMs) are increasingly deployed in high-stakes domains such as healthcare, understanding their decision rationale becomes paramount for ensuring trust, safety, and accountability. However, achieving this vital level of interpretability is particularly challenging when these DLMs operate as black-box systems (e.g., via APIs), where access to internal model states (e.g., parameters, gradients) is restricted. Despite numerous efforts, existing explanation methods often fail to concurrently satisfy three key desiderata: (i) inference-time efficiency, (ii) black-box compatibility without inducing out-of-distribution behavior, and (iii) comprehensible explanations grounded in the input's linguistic structure. To address these challenges, we propose a method that explains predictions of DLMs by selecting a small, informative subset of input words. We formulate this as an amortized optimization problem, enabling efficient one-shot inference without the need for input-specific search. Our selection policy is trained via REINFORCE-style policy gradients, allowing discrete word selection in a fully gradient-free setting. To enhance interpretability and align with human linguistic intuition, we integrate graph-structured knowledge into this selection process, fostering linguistically coherent subsets that result in explanations both highly informative and cognitively meaningful to end-users. We evaluated our method on diverse DLM architectures and multiple real-world datasets. It consistently identifies word subsets with enhanced discriminative power and stronger alignment with linguistically salient cues, outperforming both conventional black-box compatible methods and gradient-based approaches that are given oracle access to the black-box model's gradients for a more challenging benchmark. Our code is available at here. --- ### SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Authors: Jingyi He, Haiyan Zhao, Ruxue Shi, Yanguang Liu, Xin Wang, Fei Sun, Mengnan Du Published: 2026-06-07 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.08496v2 Although Sparse Autoencoders (SAEs) have mitigated the opacity of large language models (LLMs) by decomposing dense representations into sparse features, explaining these features still remains a central challenge. Current explanation methods, however, typically operate within an open-loop paradigm, failing to leverage mechanistic feedback for further refinement. In this paper, we propose SAEExplainer, a training framework that utilizes activation scores as an objective reward signal to train the model for self-correction and iterative bootstrapping. By iteratively verifying and correcting foundational explanations through a two-round optimization process, SAEExplainer achieves continuous improvement in its explanatory capabilities. This mechanism significantly reduces explanation hallucinations and reinforces causal triggering patterns. Extensive experiments demonstrate our approach improves upon established baselines across most metrics, especially in causal triggering and discriminative activation. The code is available at https://github.com/he-jingyi/SAEExplainer. --- ### SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Authors: Jingyi He, Haiyan Zhao, Ruxue Shi, Yanguang Liu, Xin Wang, Fei Sun, Mengnan Du Published: 2026-06-07 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.08496v1 Although Sparse Autoencoders (SAEs) have mitigated the opacity of large language models (LLMs) by decomposing dense representations into sparse features, explaining these features still remains a central challenge. Current explanation methods, however, typically operate within an open-loop paradigm, failing to leverage mechanistic feedback for further refinement. In this paper, we propose SAEExplainer, a training framework utilizes activation scores as an objective reward signal to train the model for self-correction and iterative bootstrapping. By iteratively verifying and correcting foundational explanations through a two-round optimization process, SAEExplainer achieves continuous improvement in its explanatory capabilities. This mechanism significantly reduces explanation hallucinations and reinforces causal triggering patterns. Extensive experiments demonstrate our approach improves upon established baselines across most metrics, especially in causal triggering and discriminative activation. --- ### EgoPriMo: Egocentric Motion Generation for Interactive Humanoid Control Authors: Haoyang Ge, Peng Ren, Yukun Shi, Cong Huang, Kun Li, Kai Chen Published: 2026-06-07 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2606.08495v1 Humanoid robots require whole-body motions that adapt to scene context, task requirements, and user intent. Motion tracking reproduces specified trajectories, and humanoid vision-language-action systems provide semantic interfaces, but neither offers a scalable and interactive prior for broad full-body behavior. We introduce EgoPriMo (Egocentric Motion Prior for Humanoid Robots), a unified framework that learns such priors from egocentric human demonstrations. Given egocentric observations and a text prompt, EgoPriMo reconstructs, generates, and forecasts SMPL-based full-body motion. Language is used as a high-level control signal rather than a complete motion specification. At the core of EgoPriMo is a Triple-stream DiT that jointly models body dynamics, egocentric visual context, and text; task-conditioning masks route different tasks and missing-modality data through the same checkpoint. Experiments on Nymeria and EgoExo4D show that one checkpoint improves egocentric motion generation over UniEgoMotion while supporting reconstruction and forecasting; the generated SMPL motions can also be executed by a Unitree humanoid controller. These results indicate a practical path from scalable egocentric observations to generalizable and interactive humanoid motion priors. --- ### Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement Authors: Abdul Moeed, Stefan Schrod, Martin Rohbeck, Marc Jan Bonder, Pavlo Lutsik, Oliver Stegle, Daniel Dimitrov Published: 2026-06-07 Categories: q-bio.GN, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.08493v2 Tissue graph counterfactuals ask how a cell's expression would change under altered spatial neighbor contexts. Such queries are central to predicting cell behavior in tissues, but lack a unified definition, with existing methods targeting specific intervention types or treating cells as i.i.d. In this work, we first formalize tissue graph counterfactuals as a class of spatial interventions that either rewire connections between cells (edge perturbation) or modify the expression of their neighbors (node perturbation). We then introduce Cellina (https://cellina.readthedocs.io) - a framework that uses supervised disentanglement to decompose a cell's intrinsic state from its spatial context, using the latter as a conditioning input for counterfactual predictions. Across benchmarks spanning over 2.5 million spatially-resolved cells in colorectal cancer and mouse brain, Cellina outperforms spatially-informed and non-spatial competitors in in-silico graph perturbations, disentanglement, and scalability. Additionally, we show that Cellina reveals biologically distinct cancer subdomains in an unsupervised manner and enables targeted neighbor perturbation simulations. --- ### Seeing is Believing: Aligning Prompt Rewriting with Visual Anchors for Text-to-Image Generation Authors: Xuanyi Liu, Deyi Ji, Junyu Lu, Jing Wang, Lanyun Zhu, Qianxiong Xu, Xuhang Chen, Tianrun Chen, Siwei Ma Published: 2026-06-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.08492v2 Despite the impressive capabilities of text-to-image (T2I) models, an intent-generation gap often persists due to the brevity and ambiguity of user prompts. Existing approaches primarily polish the prompt for fluency and readability. However, the enhancement process still lacks visual grounding. As a result, the rewriter may over-infer missing details, causing an intent-generation gap. To address this limitation, we propose FaithRewriter, a novel prompt-enhancement framework for T2I generation. Specifically, FaithRewriter first leverages a multimodal MLLM to generate an image from the original prompt as an intermediate visual cue. This cue is then combined with the prompt and fed into a large-scale LLM to produce visually grounded augmentations that better reflect how the intended content should appear in images. Finally, these augmentations are distilled into a small-scale LLM for efficient deployment, enhancing its ability to generate effective T2I prompts. Experiments show that FaithRewriter yields prompts that are more faithful to the user intent and more visually plausible than strong baselines, helping narrow the intent-generation gap. --- ### What Makes a Desired Graph for Relational Deep Learning? Authors: Yao Cheng, Siqiang Luo Published: 2026-06-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.08491v1 Relational deep learning (RDL) converts relational databases (RDBs) into heterogeneous graphs, but graphs derived directly from database schemas are often not well suited for how graph neural networks (GNNs) perform relational reasoning. We study what makes a relational graph suitable for deep learning and show that schema-derived graphs suffer from two systematic failures: information overload and semantic fragmentation. Our empirical analysis reveals that the desired graph is not the raw schema, but a result of controlled structural adaptation. Performance depends on balancing two operations: mitigating information overload via filtering, and repairing semantic fragmentation via injection. Specifically, filtering serves as a bias-variance knob with non-monotonic effects, while injection improves performance only when it explicitly restores the relational dependencies missing from the original schema. Based on these findings, we develop an end-to-end structural optimizer that applies both operations to adapt relational graphs automatically. Across 26 tasks spanning classification, regression, and recommendation, the optimized graphs consistently improve accuracy while often reducing inference cost. --- ### TRADE: Transducer-Augmented Decoder for Speech LLM Authors: Yun Tang, Shanil Puri, Shinji Watanabe, Subhabrata Mukherjee Published: 2026-06-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.08486v1 Speech Large Language Models (Speech LLMs) lack a principled mechanism for streaming inference: their label-synchronous generation has no acoustic-frame alignment, making real-time decoding and end-of-utterance detection difficult. We propose TRADE TRansducer-Augmented DEcoder, which augments a multimodal LLM with a transducer branch that shares the audio encoder and uses the LLM's hidden states directly as the prediction network -- coupling frame-synchronous acoustic alignment with the LLM's linguistic reasoning. Three design choices make the system accurate, streamable, and long-form capable: (1)Tightly coupled dual vocabularies -- a compact transducer vocabulary derived from the LLM vocabulary, enabling zero-cost score fusion; (2)Chunk-synchronized streaming training with gradient stopping, eliminating the train-inference mismatch at offline-equivalent memory cost; and (3)Localized Decoder Audio Attention (LDAA), a causal sliding window that caps KV-cache memory independently of utterance length. A single TRADE checkpoint supports offline and streaming decoding across a continuous range of latency operating points. TRADE achieves 6.71% average WER on the Open ASR Leaderboard, while the streaming recognition with 960ms chunk size reaches 8.40% from the same checkpoint. On long-form speech, it obtains 3.64% WER on TED-LIUM and 10.88% on Earnings-22 without external segmentation. TRADE provides sentence-end punctuation timestamps that, when combined with acoustic voice activity detection (VAD), improve end-of-utterance detection by +0.03 F_1 over acoustic VAD alone. --- ### STELLAR: Spatio-Temporal Environmental Learning with Latent Alignment and Refinement for Long-Tailed Species Distribution Modeling Authors: Shufeng Kong, Tao Yu, Yuanyuan Wei, Caihua Liu, Junwen Bai, Yingheng Wang, Marc Grimson, Daniel Fink, Carla P. Gomes Published: 2026-06-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.08484v1 Joint Species Distribution Modeling (JSDM) is a key enabler for biodiversity monitoring and conservation planning. However, accurate JSDM faces two coupled challenges: environmental drivers and species distributions are inherently spatio-temporal, while species co-occurrence patterns exhibit complex non-linear community structure and severe long-tail imbalance driven by rare species. Existing approaches often address these factors in isolation, learning from static covariates or neglecting the historical trajectories of dynamic community structure. To overcome these limitations, we propose STELLAR (Spatio-Temporal Environmental Learning with Latent Alignment and Refinement), a novel framework that learns a shared latent space where dynamic habitat context and community structure are optimized jointly. Our approach integrates three complementary components: (1) a Graph-Temporal Encoder that employs graph attention and recurrent units to aggregate spatial neighborhood effects and capture the co-evolving historical dynamics of environmental context and community structure; (2) a Context-Anchored Latent Alignment mechanism that structures the latent space using a label-activated mixture prior and supervised contrastive learning, actively clustering species based on shared environmental preferences; and (3) an Imbalance-Aware Decoupled Decoding module that utilizes Asymmetric Loss to focus learning on hard, rare species samples, preventing mode collapse in the long tail. Experiments on the large-scale eBird dataset, curated with domain experts, demonstrate that our framework significantly outperforms state-of-the-art baselines, particularly in predicting rare species and revealing interpretable species interactions. --- ### Testing the Black Box: Structural Barriers to Independent Evaluation of Consumer-Facing Health LLMs Authors: Rahul Gorijavolu, Kaushik Madapati, Pritika Vig, Rawan Abulibdeh, Nikhil Jaiswal, Mahri Kadyrova, Zeamanuel Hailu Tesfaye, Charles Senteio, Paula Maurutto, Leo Anthony Celi Published: 2026-06-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.08483v1 Background: Consumer-facing large language models are now a common source of health information, and they interpret and personalize responses rather than retrieve them. Whether their responses vary across users is a clinical, equity, and governance question, sharpened by evidence that sycophantic responses can alter judgment and increase trust. Objective: To evaluate response variation and sycophancy in consumer-facing health LLMs under conditions resembling ordinary patient use. Methods: We constructed simulated user profiles differing in geography, browsing context, expressed beliefs, and social determinants of health, drawing on literature linking social context to health attitudes. We adapted validated instruments, including the Vaccination Attitudes Examination scale and reproductive attitudes scales, into multi-turn prompts designed to elicit clinically meaningful variation across users. Results: The evaluation encountered five linked barriers. Factual prompts produced stable responses that masked sycophancy emerging over multi-turn conversation. Browser-based interfaces did not disclose which signals influence outputs and could not be reset to a clean baseline. Large-scale testing was restricted by terms of service, rate limits, and bot detection. Accuracy-based criteria could not capture tone, framing, or omission, and LLM-as-judge methods risked shared alignment bias. Models changed without traceable version identifiers, preventing reliable replication. Conclusions: No reliable independent evaluation framework yet exists for examining how consumer-facing health LLMs behave in ordinary use. Oversight requires disclosure of personalization signals, stable version identifiers, researcher safe harbor programs, and post-deployment monitoring of health-related outputs. --- ### PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systems Authors: Suraj Ranganath, Anish Raghavendra Published: 2026-06-07 Categories: cs.LG, cs.AI, cs.DB, cs.SE arXiv: https://arxiv.org/abs/2606.08481v1 Enterprise property graphs vary widely in schema structure, internal terminology, domain assumptions, governance constraints, and user interaction patterns. A deployment-relevant Text2Cypher benchmark therefore reflects the questions users and agents actually ask of that graph. Creating such a benchmark is difficult because schemas and values are unique, and graph structure changes over time. Each NL-query pair must also be executable, use real graph entities, preserve diversity, and remain balanced across query types and difficulty levels. We present PIPE-Cypher, a local benchmark-generation pipeline that turns a live property graph and optional seed queries from customer questions, analyst logs, or agent tool calls into balanced NL-to-Cypher benchmarks. PIPE-Cypher combines schema profiling, reverse-query grounding, constrained generation, deterministic Cypher governance, execution validation, redaction, diversity controls, and a calibrated local LLM judge. Using local Qwen3.5-9B generation and judging, PIPE-Cypher exports 3,000 accepted FinBench/SNB examples, completes three audited ablation suites, calibrates judge behavior with human labels, and evaluates 11 local downstream models. The resulting benchmark is deliberately discriminative: zero-shot transfer is weak, while a few-shot control shows that schema-specific example banks can help compatible model families. Together, PIPE-Cypher makes Text2Cypher benchmarking a repeatable process that evolves with the graph, its users, and its target workloads. --- ### Adaptive Loss Balancing for Noise-Robust GRPO in Generative Recommendation Authors: Kewei Xu, Junbo Qi, Yanyan Zou, Pengfei Zhang, Xingzhi Yao, Shengjie Li Published: 2026-06-07 Categories: cs.LG, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2606.08480v1 Reinforcement learning (RL) presents a promising avenue for enhancing generative recommendation beyond supervised imitation, leveraging reward signals to guide policy improvement. However, its efficacy is critically contingent on the trustworthiness of the reward model for the samples it evaluates. In practice, production rankers, the widely adopted reward models, are trained on exposure-biased logs, leading to sample-dependent inaccuracies that violate this assumption. Our stratified analysis uncovers a consistent pattern: reward guidance is most beneficial when the policy exhibits uncertainty and the ranker can effectively discriminate the ground-truth item from rollout negatives. On other samples, the reward signal is either negligible or detrimental, highlighting the risk of uniform RL application. To address such an issue, we introduce AdaGRPO, a novel framework that treats reward-guided optimization as selective admission rather than uniform pressure. Training is anchored in supervised negative log-likelihood, while the GRPO objective is gated by a binary, per-sample clip determined by two rollout diagnostics: policy-side difficulty and reward discriminability. Instances failing either diagnostic default to pure supervision, ensuring stability and mitigating the amplification of noisy gradients. We validate AdaGRPO on a large-scale e-commerce dataset. At the best intermediate checkpoint, it elevates HR@10 from 11.01% to 12.18% while constraining hallucination below 0.22%, and maintains robustness at the final checkpoint (HR@10 11.63%, hallucination 0.27%), outperforming fixed NLL--GRPO mixtures across the retrieval--validity frontier. In production A/B tests, AdaGRPO achieves statistically significant gains in click-through rate and dwell time, confirming its practical utility. --- ### Inferring hidden forcing in a biological oscillator using Kolmogorov-Arnold networks Authors: Julian Szereszewski, Facundo Fainstein, Leandro E. Fernandez, Gabriel B. Mindlin Published: 2026-06-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.08479v1 Inferring the forces that drive a dynamical system from partial observations is a fundamental challenge across physics, particularly when distinct underlying mechanisms produce similar observable dynamics. Here we show that the effective muscular forcing underlying avian respiratory dynamics can be reconstructed from measurements of air-sac pressure alone. Using an interpretable learning framework based on Kolmogorov-Arnold networks, we infer the governing equations of the system directly from data and uncover a nontrivial structure in the underlying forcing that is not apparent from the pressure signal, which instead suggests a relaxation-like oscillation. The reconstructed dynamics predict a two-phase activation pattern within each respiratory cycle, which we independently validate through electromyographic recordings of expiratory muscles. These results demonstrate that data-driven reconstruction of dynamical laws can reveal hidden physical structure and provide access to unobserved driving variables, establishing a general route to infer latent forces in partially observed dynamical systems. ---