# Research Papers — 2026-05 · bundle page 54 of 326

> Full-text markdown of papers #2651–2700 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-05/page/54
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/53.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/55.md)

### When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR

Authors: Maike Züfle, Jan Niehues
Published: 2026-05-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.28211v2

SpeechLLMs are increasingly deployed in professional settings where domain customisation is standard practice: users supply context in prompts with sensitive information, fine-tune on proprietary recordings, or both. We identify and systematically investigate an overlooked privacy risk of such customisation: a model adapted to recognise domain-specific terminology can be nudged into transcribing a phonetically similar word from its context or training data, even when a different word is spoken, thereby leaking private information. To evaluate this risk, we propose a technique to automatically construct benchmarks of such attacks and apply it to measure leakage rates across two customisation mechanisms, prompting and fine-tuning. Both mechanisms cause measurable leakage, compounding when combined. We evaluate a prompt-level mitigation strategy and analyse the accuracy-leakage trade-off across customisation approaches, finding that fine-tuning without context prompts offers the best balance.

---

### When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR

Authors: Maike Züfle, Jan Niehues
Published: 2026-05-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.28211v1

SpeechLLMs are increasingly deployed in professional settings where domain customisation is standard practice: users supply context in prompts with sensitive information, fine-tune on proprietary recordings, or both. We identify and systematically investigate an overlooked privacy risk of such customisation: a model adapted to recognise domain-specific terminology can be nudged into transcribing a phonetically similar word from its context or training data, even when a different word is spoken, thereby leaking private information. To evaluate this risk, we construct a controlled dataset and measure leakage rates across two customisation mechanisms, prompting and fine-tuning. Both mechanisms cause measurable leakage, compounding when combined. We evaluate a prompt-level mitigation strategy and analyse the accuracy-leakage trade-off across customisation approaches, finding that fine-tuning without context prompts offers the best balance. We release our code and dataset publicly.

---

### The Illusion of Opting in AI-Mediated Consequential Decisions

Authors: Eugene Yu Ji
Published: 2026-05-27
Categories: cs.AI, cs.CY, cs.HC, q-bio.NC
arXiv: https://arxiv.org/abs/2605.28210v2

Drawing on Ullmann-Margalit's concept of opting (transformative, irrevocable, and shadowed by foreclosed alternatives), we show that current AI systems raise a profound ethical problem that existing AI ethics has not fully captured: the illusion of opting, in which persons and groups encounter the deceptive appearance of meaningful consequential choice while the agency needed to become genuinely capable of choosing is weakened. Against approaches that treat AI primarily as an optimizer of already given ends, we argue that AI systems should be evaluated by whether they protect and cultivate meta-capacity against the illusion of opting: the socially and institutionally scaffolded agentive capacity through which means and ends can be formed, contested, revised, and owned. This reframing is especially urgent for disadvantaged populations, who are least able to absorb the costs of the illusion of opting when AI-mediated pathways misdirect behavior and action. We propose three normative imperatives for AI-mediated consequential decisions: existential honesty, which acknowledges the limits of prediction; ecological rationality, which situates guidance within heterogeneous lived ecologies; and counterfactual reparation, which acknowledges and repairs foreclosed alternatives when AI-mediated decision-making pathways fail.

---

### Robust Contrastive Graph Clustering with Adaptive Local-Global Integration

Authors: Lei Zhang, Fubo Sun, Haipeng Yang, Zhong Guan, Likang Wu
Published: 2026-05-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.28209v2

Graph clustering is essential in graph analysis for revealing structural patterns and node communities. Despite recent advances in self-supervised contrastive learning that have improved clustering via structural and attribute signals, existing methods still struggle to flexibly capture high-order local structures and often overlook global semantics in complex graphs. These limitations lead to suboptimal node representations, especially in real-world graphs with fragmented structures and ambiguous cluster boundaries. To address these limitations, a contrastive graph clustering framework is proposed to jointly integrate multi-scale local structures with global semantics via attention mechanisms. At the local level, GNN-based topological signals extracted from multiple propagation depths are adaptively fused through attention-based weighting to capture multi-scale neighborhood features. At the global level, semantic prototypes derived from dynamically evolving cluster centers are adaptively aggregated through attention to guide node representations and enhance inter-cluster separability. The model is trained under a dual-view contrastive learning paradigm with a hybrid objective that combines instance-level and structure-aware losses to improve representation robustness and discrimination. Experiments on eight real-world graph datasets demonstrate that our method achieves competitive clustering performance. Code is available at https://github.com/vege12138/w2.

---

### Pruning and Distilling Mixture-of-Experts into Dense Language Models

Authors: Junhyuck Kim, Jihun Yun, Haechan Kim, Gyeongman Kim, Joonghyun Bae, Jaewoong Cho
Published: 2026-05-27
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.28207v2

Mixture-of-Experts (MoE) is now the dominant architecture for frontier language models, yet it requires all expert parameters to be loaded in memory, making it less preferable for memory-constrained deployment. Existing compression methods reduce the number of experts but the output remains an MoE model with the same fundamental limitation. We present the first systematic framework for converting a trained MoE into a standard fully dense architecture: experts are scored, selected, and grouped, then concatenated into a dense FFN and refined by knowledge distillation from the MoE teacher. We evaluate 7 scoring, 5 grouping, and 2 magnitude scaling methods across a range of selected expert counts on Qwen3-30B-A3B, yielding 350 configurations. We find that the choice of scoring method is the most impactful, with our novel diversity-aware scoring consistently outperforming prior methods on Qwen3-30B-A3B, DeepSeek-V2-Lite, and GPT-OSS-20B. Under a controlled comparison at matched parameter count, MoE-to-dense outperforms dense-to-dense pruning by +6.3 pp in average downstream accuracy after ~4B-token distillation at 1.6x faster training wall-clock speed.

---

### Refining Multidimensional Video Reward Models via Disentangled Influence Functions

Authors: Muyao Wang, Zeke Xie, Hideki Nakayama
Published: 2026-05-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.28203v1

As Text-to-Video (T2V) generation models continue to evolve, the complexity of video evaluation necessitates a fine-grained assessment across various axes. To address this, recent works have focused on developing Multidimensional Video Reward Models (MVRMs), which decompose the evaluation process to better align with the multifaceted nature of human visual perception. However, training effective MVRMs is fundamentally challenged by the complex nature of video data. In this work, we identify a critical phenomenon termed Dimensional Heterogeneity: the reliability of a training sample can vary substantially across evaluation dimensions, meaning that a sample may provide reliable supervision for one objective while inducing high supervision risk for another. Consequently, prevailing data-centric methods that filter based on global scalar metrics are ill-posed for T2V tasks. To address this, we propose a disentangled influence framework that that efficiently estimates dimension-specific supervision risk. Leveraging this framework, we introduce two dimension-disentangled refinement strategies: Dimension-Disentangled Pruning, which removes extreme high-risk samples, and Dimension-Disentangled Reweighting, which softly down-weights high-risk supervision. Extensive experiments demonstrate that our disentangled strategies significantly outperform global filtering baselines, yielding reward models with superior alignment to ground truth.

---

### Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents

Authors: Yongxiang Li, Moxin Li, Zhixin Ma, Fengbin Zhu, Dongrui Liu, Wenjie Wang, Fuli Feng
Published: 2026-05-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.28201v1

Large Language Model (LLM) agents remain vulnerable to safety threats from the external environment, where attackers inject adversarial content into external observations such as tool-returned data, webpages, or MCP context, causing harmful agentic behaviors such as unsafe actions or incorrect outputs. Existing studies typically focus on single-interaction attacks, where the agent observes adversarial content and immediately exhibits harmful behavior within one user request. However, we show that adversarial content can also persist across interactions served by the same agent, making such threats harder to detect and mitigate. Specifically, adversarial content may persist in the agent state, remain dormant across interactions, and later be activated by a benign user query. We formalize this type of safety threat as Sleeper Attack. To evaluate it, we construct a benchmark with 1,896 instances covering six real-world harmful outcomes, three attack strategies, and three agent state targets: session context, memory, and reusable skills. Experiments on seven strong open-source and closed-source LLMs show that state-of-the-art LLM agents remain vulnerable to Sleeper Attack, even when they achieve low attack success rates under a single-interaction baseline. Our code and data are available at https://anonymous.4open.science/r/skdvnfu23ihr9wdscnksf1asdffsaef.

---

### Geometry-First Generative Spatial Single-Cell Reconstruction

Authors: Ehtesamul Azim, Muhtasim Noor Alif, Tae Hyun Hwang, Yanjie Fu, Wei Zhang
Published: 2026-05-27
Categories: cs.LG, q-bio.GN
arXiv: https://arxiv.org/abs/2605.28200v1

Single-cell RNA sequencing (scRNA-seq) profiles large numbers of cells but loses spatial context, whereas spatial transcriptomics (ST) preserves partial spatial structure at lower resolution. Most existing integration methods either deconvolve spot mixtures or map cells onto a measured spot lattice, which ties reconstructions to a fixed grid and slide-specific coordinate systems, a limitation that is especially problematic in unpaired settings. We propose GEARS, a geometry-first framework that reconstructs an intrinsic single-cell spatial geometry guided by ST, without relying on cell-type labels, histological images, or cell-to-spot assignment. GEARS first learns a domain-invariant expression encoder that aligns ST spots and dissociated cells, and then trains a permutation-equivariant generator with a diffusion-based refiner with EDM-style preconditioning to generate local spatial geometries under pose-invariant supervision derived from ST coordinates. At inference, GEARS reconstructs geometry on many overlapping subsets of scRNA-seq cells, aggregates predicted pairwise distances across subsets, and solves a global distance-geometry problem to obtain canonical two-dimensional coordinates and a dense distance matrix. Extensive quantitative and qualitative experiments, including cross-section generalization, show that GEARS consistently improves global distance preservation, local neighborhood fidelity, and spatial distribution alignment compared to strong spatial mapping and deconvolution baselines.

---

### Hierarchical Synthetic Tabular Data Generation: A Hybrid Top-Down and Bottom-Up Framework

Authors: Junfeng Nie, Alvin Jin, Xiaohui Chen
Published: 2026-05-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.28198v2

Existing approaches for synthetic tabular data generation are based on either purely generative models or LLMs, both of which struggle with data heterogeneity, logical consistency, rare-event coverage, and robustness in low-data regimes. In this paper, we propose a hierarchical hybrid top-down and bottom-up (H-TDBU) framework that decouples semantic structures from stochastic texture. In the top-down path, structure-driven logical constraints and cross-modal alignment rules are constructed, while in the bottom-up path, lightweight tabular generators are used to learn local statistical patterns from real data. The two paths are consolidated in a unified synthesis engine with an iterative feedback loop. We evaluate the framework on weak multimodal financial benchmarks combining tabular and sentiment-text data. Experimental results show that our H-TDBU approach improves train-synthetic-test-real performance over neural baseline methods while preserving semantic consistency. Our results suggest that hierarchical rule-guided synthesis provides an effective mechanism for combining controllability, semantic coherence, and statistical fidelity in synthetic data generation.

---

### Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning

Authors: Ke Xu, Yuhao Wang, Ziyang Cheng, Hongcheng Liu, Yanfeng Wang, Yu Wang
Published: 2026-05-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.28192v1

Multi-hop audio-visual reasoning remains challenging for Omni-LLMs, as relevant evidence is often sparse, temporally dispersed, and distributed across both audio and visual streams. Existing benchmarks provide limited investigation of this setting, typically involving only a limited number of modalities, relevant temporal segments, or reasoning steps. In this work, we introduce MOV-Bench, a benchmark containing 519 carefully curated questions that require multi-hop reasoning over temporally dispersed audio-visual evidence. Evaluations on MOV-Bench reveal that current Omni-LLMs still struggle with multi-hop cross-modal reasoning. To address this challenge, we further propose AOP-Agent, an efficient agentic framework built on open-source Omni-LLMs for active omni-modal perception. By combining a hierarchical omni-modal memory with a collaborative observe-reflect-replan loop, AOP-Agent enables open-source Omni-LLMs to perform active perception without additional training or proprietary models. Experiments on MOV-Bench and OmniVideoBench demonstrate that AOP-Agent consistently improves reasoning performance, with particularly notable gains on long videos and reasoning-intensive questions.

---

### The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness

Authors: Manuel Frank, Haithem Afli
Published: 2026-05-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.28190v2

Embedding benchmarks like MTEB report a single score per model, implicitly treating robustness as a static, scalar property. We argue that embedding robustness is multidimensional, since models respond differently to different types of variation, and requires dynamic evaluation to expose failures hidden by static benchmarks. We introduce the Harder Text Embedding Benchmark (HTEB), a dynamic evaluation framework that challenges model robustness along three practically interpretable axes (Lexical/Stylistic, Length and Language) by stochastically transforming inputs at evaluation time with an LLM. Evaluating 16 open-weight embedding models on 32 datasets covering 42 languages under transformations validated by 4,800 individual human ratings on an English subsample, supplemented by a Spanish-source evaluation and an exploratory STS-B study of pair-level label preservation, we find three patterns: (1) Models exhibit specific, partly decoupled robustness profiles across axes. (2) Across three model families, scale increases absolute scores but does not close the gap between original and transformed evaluations. Here, scaling tends to improve specifically the Language axis. (3) English datasets are more sensitive to HTEB transformations than multilingual datasets. This demonstrates that HTEB identifies strengths and weaknesses of models along deployment-relevant axes, challenging current embedding benchmarks and arguing for multidimensional, dynamic robustness evaluation. We make the code to run HTEB publicly available.

---

### The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness

Authors: Manuel Frank, Haithem Afli
Published: 2026-05-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.28190v1

Embedding benchmarks like MTEB report a single score per model, implicitly treating robustness as a static, scalar property. We argue that embedding robustness is multidimensional, since models respond differently to different types of variation, and requires dynamic evaluation to expose failures hidden by static benchmarks. We introduce the Harder Text Embedding Benchmark (HTEB), a dynamic evaluation framework that challenges model robustness along three practically interpretable axes (Lexical/Stylistic, Length and Language) by stochastically transforming inputs at evaluation time with an LLM. Evaluating 16 open-weight embedding models on 32 datasets covering 42 languages under transformations validated by 4,800 human ratings on an English subsample, we find three patterns: (1) Models exhibit specific, partly decoupled robustness profiles across axes. (2) Across three model families, scale increases absolute scores but does not close the gap between original and transformed evaluations. Here, scaling tends to improve specifically the Language axis. (3) English datasets are more sensitive to HTEB transformations than multilingual datasets. This demonstrates that HTEB identifies strengths and weaknesses of models along deployment-relevant axes, challenging current embedding benchmarks and arguing for multidimensional, dynamic robustness evaluation.

---

### Framing Matters: Addressing Framing Sensitivity in Decision-Making through Behaviorally-Grounded Value Alignment

Authors: Seojin Hwang, Minju Kim, Junhyuk Choi, JeongHyun Park, Hwanhee Lee
Published: 2026-05-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.28188v1

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making settings such as legal reasoning, where consistency under factually equivalent inputs is critical. However, we find that fact-preserved but differently framed inputs can significantly destabilize LLM decisions. To systematically investigate this problem, we introduce Fragile, a large-scale benchmark that isolates fact-preserving semantic framing across three controlled dimensions: value-tinted narration, temporal slice, and narrative vividness. Our experiments reveal a high susceptibility of LLMs to framing, with an average decision flip rate of 28.6%. We find that simple prior prompt-level and activation-level interventions not only fail to suppress framing sensitivity but actively amplify it. We therefore propose Valign, a representation-level method that explicitly targets these framing dimensions by anchoring decisions to a stable value prior, steering hidden states toward the model's value-consistent direction, and projecting out temporal-vividness-sensitive directions from the model's hidden states. Valign consistently reduces framing-induced decision flips, demonstrating that robust mitigation requires directly targeting the internal pathways in which framing operates.

---

### Whose Name Comes Up? III: Persona Prompting Effects in LLM-Based Scholar Recommendation

Authors: Annabella Sánchez-Guzmán, Lukas Eberhard, Denis Helic, Lisette Espín-Noboa
Published: 2026-05-27
Categories: cs.IR, cs.AI, cs.CY, cs.SI
arXiv: https://arxiv.org/abs/2605.28187v1

Large language models (LLMs) are increasingly used as scholar recommenders, shaping who is seen as an expert in academia. Existing audits remain English-centric, single discipline, and persona-agnostic, leaving the source of output variability poorly understood. To this end, we propose a benchmark that disentangles the effects of model choice and prompt design on recommendations. We audit 43 LLMs by varying persona prompts (language, location, role-and-task) and context (field, seniority, k). Recommended scholars are compared against Semantic Scholar over six scientific disciplines to measure technical quality (factuality, coverage) and social representativeness (diversity, parity). Basic technical quality is driven by model choice, factuality and parity by context, and diversity by location. South Africa prompts yield less factual lists, while Japan prompts yield highly factual but homogeneous lists skewed toward highly productive scholars. Prompt design is thus a non-trivial axis of LLM-based scholar discovery and should be systematically audited alongside model choice.

---

### Visualizing Latent Phase Structures in Locomotion Policies: A Multi-Environment Study with Temporal Feature Extension

Authors: Daisuke Yasui, Toshitaka Matuki, Hiroshi Sato
Published: 2026-05-27
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2605.28186v1

Deep reinforcement learning (DRL) has been shown to achieve high performance on locomotion control tasks in MuJoCo benchmarks such as HalfCheetah, Ant, and Walker2D. However, visualizing the motion structures internally obtained by a trained policy function implemented as a deep neural network remains challenging. It is known from biomechanics and related fields that locomotion control is realized through the repetition of motion phases such as the stance phase and swing phase. In this study, we propose a framework for uncovering latent motion phase structures from trajectories generated by locomotion control policies through interaction with the environment. The proposed method extends the clustering features from state observations alone to augmented features including actions, next states, and next actions, and introduces a method for determining the number of clusters that suppresses self-transitions. Applying the proposed method to three environments -- Ant-v5, HalfCheetah-v5, and Walker2D-v5 -- we successfully identified phase structures with clearer and more regular transition rules than those obtained by the existing method.

---

### Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration

Authors: Zili Wang, Jiajun Chai, Lin Chen, Xiaohan Wang, Shiming Xiang, Guojun Yin
Published: 2026-05-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.28184v1

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as the standard paradigm for improving reasoning capability of large language models, while Multi-Token Prediction (MTP) has been a widely adopted module in pretraining. Combining them is a natural approach, yet current RL practices detach MTP gradients because joint training degrades the performance. We revisit this failure from an optimization perspective. We show that the per-step effect of MTP on the RL objective can be decomposed into two terms: a first-order correlation and a second-order perturbation penalty. This decomposition unifies three MTP training regimes: Detach, Cross-Entropy loss, and Policy loss, and explains why each succeeds or fails. Further analysis of policy loss reveals that, although it aligns with intuition, performance still degrades: the correlation term decays while the quadratic penalty persists. Guided by the analysis, we propose Optimal Coefficient Calibration (OCC), an adaptive scheme that tracks the optimal coefficient online via a log-probability proxy at negligible cost. Across six competition-level mathematical reasoning benchmarks, OCC consistently matches or exceeds the detach baseline, delivering improved joint MTP-RL training performance.

---

### BenGER: Benchmarking LLM Systems on Subsumption-Based Legal Reasoning in German Law

Authors: Sebastian Nagl, Ann-Kristin Mayrhofer, Martin Heidebach, Aleyna Koçak, Anne Zettelmeier, Elly Breu, Angelina Greiner, Sofija Milijas, Matthias Grabmair
Published: 2026-05-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.28183v4

We introduce BenGER (Benchmark for German Law), a benchmark and dataset for evaluating LLM systems on subsumption-based legal reasoning in German law. The dataset combines 596 exam-style free-text legal case tasks across multiple levels of legal education and 531 short doctrinal reasoning tasks. It includes a controlled validation subset of timed human-written solutions under both unaided and human-AI co-creation conditions. We evaluate 12 contemporary LLM systems - closed flagship, efficiency-oriented, and open-weight - with a rubric-aligned LLM-as-a-Judge cross-validated against a multi-rater human-grading layer (three blind reviews per solution, six judge families benchmarked against the human pool). Closed-flagship systems lead the leaderboard across all three corpora, human-AI co-creation measurably improves on unaided human work, and the LLM judge tracks human grading at Pearson r=0.76 and Cohen's k=0.60. System rankings are stable across judge families and two judges from independent providers clear the Calderon single-reviewer replacement bar on human-authored solutions.

---

### BenGER: Benchmarking LLM Systems on Subsumption-Based Legal Reasoning in German Law

Authors: Sebastian Nagl, Ann-Kristin Mayrhofer, Martin Heidebach, Aleyna Koçak, Anne Zettelmeier, Elly Breu, Angelina Greiner, Sofija Milijas, Matthias Grabmair
Published: 2026-05-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.28183v3

We introduce BenGER (Benchmark for German Law), a benchmark and dataset for evaluating LLM systems on subsumption-based legal reasoning in German law. The dataset combines 596 exam-style free-text legal case tasks across multiple levels of legal education and 531 short doctrinal reasoning tasks. It includes a controlled validation subset of timed human-written solutions under both unaided and human-AI co-creation conditions. We evaluate 12 contemporary LLM systems - closed flagship, efficiency-oriented, and open-weight - with a rubric-aligned LLM-as-a-Judge cross-validated against a multi-rater human-grading layer (three blind reviews per solution, six judge families benchmarked against the human pool). Closed-flagship systems lead the leaderboard across all three corpora, human-AI co-creation measurably improves on unaided human work, and the LLM judge tracks human grading at Pearson r=0.76 and Cohen's \k{appa}=0.60. System rankings are stable across judge families and two judges from independent providers clear the Calderon single-reviewer replacement bar on human-authored solutions.

---

### When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models

Authors: Jungwon Park, Jimyeong Kim, Jungmin Ko, Nojun Kwak, Wonjong Rhee
Published: 2026-05-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.28181v2

Diffusion language models generate text by iteratively selecting and denoising masked positions, making position selection a central inference-time decision. Most training-free methods rely on model confidence, assuming that high-confidence positions are ready to be decoded. However, this assumption can fail in fully non-autoregressive (fully non-AR) decoding, where selection spans the entire masked response sequence. This can cause incomplete generation, partly due to EOT overconfidence. Existing remedies directly suppress EOT tokens, but provide limited gains or require additional fine-tuning. We show that placing even a semantically minimal suffix anchor near the end of the response region discourages premature EOT prediction and promotes complete generation. However, despite providing little supporting context, the anchor makes nearby positions highly confident and causes them to be decoded too early. We therefore propose Suffix-Anchored Confidence Modulation, a simple training-free method that uses suffix anchoring with progress-dependent confidence modulation near the anchor. Across text-only reasoning, vision-language reasoning, and code-generation benchmarks, our method outperforms diverse fully non-AR and semi-AR baselines. It also achieves particularly large gains under highly parallel decoding, demonstrating the benefit of improving the fully non-AR regime over block-wise semi-AR regime.

---

### When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models

Authors: Jungwon Park, Jimyeong Kim, Jungmin Ko, Nojun Kwak, Wonjong Rhee
Published: 2026-05-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.28181v1

Diffusion language models decode text by iteratively denoising masked token sequences, making the choice of which positions to decode a central inference-time decision. Most training-free decoding strategies use model confidence for position selection, assuming that high-confidence positions are ready to be decoded. In this work, we revisit this assumption by studying when confidence misleads fully non-autoregressive (fully non-AR) decoding. EOT tokens can receive high confidence and cause incomplete generation; inserting a suffix anchor can mitigate this issue but introduces local overconfidence near the anchor, causing anchor-adjacent tokens to be decoded too early. To address these issues, we propose Suffix-Anchored Confidence Modulation, a simple training-free method that inserts a short suffix anchor to encourage response completion and modulates confidence near the anchor according to decoding progress. This preserves the response-completion benefit of suffix anchoring while reducing premature decoding of anchor-adjacent tokens. Across text-only reasoning, vision-language reasoning, and code-generation benchmarks, our method consistently improves confidence-based fully non-AR decoding, outperforms explicit EOT suppression, and preserves the parallel decoding advantage of fully non-AR generation.

---

### SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling

Authors: Quanen Sun, Changxin Tian, Ke Shi, Cai Chen, Cunyin Peng, Jia Liu, Kunlong Chen, Zhiqiang Zhang, Jun Zhou
Published: 2026-05-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.28179v2

Scaling laws guide large language model training by relating compute to cross-entropy loss, and recent work further extends them to predict downstream benchmark performance. However, prior approaches face generalization limitations from two aspects: focusing on benchmark-level performance introduces scenario-specific artifacts, while relying on IID validation loss fails to track capability improvements when training distributions vary. In this work, we argue that downstream scaling should be studied at the capability level, which captures shared skill factors across related tasks while abstracting away benchmark-specific noise. We propose SuperValid, a framework that synthesizes OOD (out-of-distribution), capability-aligned validation data by distilling core concepts from benchmarks within a capability domain and expanding them into diverse, knowledge-rich texts. Extensive experiments spanning 16 benchmarks grouped into 6 capability domains show that SuperValid loss exhibits strong and stable correlation with downstream performance across models of different architectures, scales, and training data distributions. As a training-free metric computable during training without benchmark evaluation, SuperValid enables effective model selection, early stopping, and scaling decisions.

---

### SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling

Authors: Quanen Sun, Changxin Tian, Ke Shi, Cai Chen, Cunyin Peng, Jia Liu, Kunlong Chen, Zhiqiang Zhang
Published: 2026-05-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.28179v1

Scaling laws guide large language model training by relating compute to cross-entropy loss, and recent work further extends them to predict downstream benchmark performance. However, prior approaches face generalization limitations from two aspects: focusing on benchmark-level performance introduces scenario-specific artifacts, while relying on IID validation loss fails to track capability improvements when training distributions vary. In this work, we argue that downstream scaling should be studied at the capability level, which captures shared skill factors across related tasks while abstracting away benchmark-specific noise. We propose SuperValid, a framework that synthesizes OOD (out-of-distribution), capability-aligned validation data by distilling core concepts from benchmarks within a capability domain and expanding them into diverse, knowledge-rich texts. Extensive experiments spanning 17 benchmarks grouped into 6 capability domains show that SuperValid loss exhibits strong and stable correlation with downstream performance across models of different architectures, scales, and training data distributions. As a training-free metric computable during training without benchmark evaluation, SuperValid enables effective model selection, early stopping, and scaling decisions.

---

### From Kellgren-Lawrence to Calcium Pyrophosphate Crystal Deposition: A Soft-Labelling Framework for Knee Osteoarthritis Assessmen

Authors: Francisco Bérchez-Moreno, Riccardo Rosati, Maria Chiara Fiorentino, Víctor M. Vargas, Edoardo Cipolletta, Emilio Filippucci, Luca Romeo, Pedro A. Gutiérrez, César Hervás-Martínez
Published: 2026-05-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.28176v1

Background and objective. Conventional Deep Learning (DL) approaches for Knee Osteoarthritis (KOA) grading rely on one-hot labels, which fail to capture both the ordinal uncertainty of Kellgren--Lawrence (KL) and Calcium Pyrophosphate Deposition Disease (CPPD) severity scores and the asymmetric relationship between the two scales observed in clinical practice. Methods. We retrospectively collected 2172 knee X-ray images, including 968 radiographs jointly annotated for KL and CPPD severity. An ordinal DL framework based on soft-labelling was developed for both tasks, replacing one-hot targets with unimodal probability distributions centred on the annotated grade. Four formulations were investigated: binomial, beta, triangular, and exponential. Results. All soft-labelling strategies consistently outperformed the nominal baseline. For CPPD grading, the triangular formulation achieved the highest Quadratic Weighted Kappa (QWK) and the lowest Mean Absolute Error (MAE) (QWK = 0.796; MAE = 0.438), while the beta formulation yielded the most balanced class-wise performance considering Average MAE (AMAE) and Maximum MAE (MMAE) across classes (AMAE = 0.458; MMAE = 0.573). For KL grading, the beta-based approach provided the best overall performance, achieving the highest QWK together with the lowest MAE and class-wise errors (QWK = 0.777; MAE = 0.529; AMAE = 0.523; MMAE = 0.775). Statistical analysis demonstrated significant improvements over conventional one-hot supervision (p < 0.001).

---

### FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales

Authors: Jorge L. Rodriguez, Victor Angulo Morales, Areej Alwahas, Mariana Elias Lara, Fida Mohammad Thoker, Kasper Johansen, Bernard Ghanem, Fernando T. Maestre, Matthew F. McCabe
Published: 2026-05-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.28174v1

Foundation models offer a promising route to transferable remote sensing representations, but many current approaches depend on very large pretraining datasets and fixed sensor configurations, limiting their suitability for ecological and environmental applications, where observations often vary across platforms, spatial and spectral resolutions, and available modalities. We introduce FLORO, a multimodal geospatial foundation model designed to learn transferable representations from a small but highly diverse remote sensing corpus. FLORO is pretrained using masked autoencoding on a heterogeneous combination of Sentinel-1, Sentinel-2, SkySAT imagery, elevation, and UAV-derived data. To accommodate sensor variability, FLORO incorporates availability-aware inputs that indicate which spectral bands and auxiliary modalities are present in each sample, enabling a unified input space across heterogeneous sensor configurations. We evaluated FLORO on the PANGAEA benchmark under a frozen-encoder protocol across scene classification, segmentation, and regression tasks. Despite being pretrained on a smaller corpus than competing foundation models, FLORO achieved strong and stable transfer across optical, optical-SAR, and optical-elevation benchmarks spanning medium-resolution satellite, airborne, and ultra-high-resolution UAV imagery. FLORO obtained the second-best average segmentation performance across six PANGAEA benchmarks, trailing only a recently introduced foundation model pretrained on over two orders of magnitude more images, remained competitive on scene classification, and was robust in regression tasks, while qualitative results showed improved preservation of spatial structure in flood, urban, biomass, and canopy-height prediction settings. In a separate controlled experiment on EuroSAT-MS, geo-positional encoding further improved classification relative to absolute positional encoding.

---

### MangaFlow: An End-to-End Agentic Framework for Controllable Story to Manga Generation

Authors: Muyao Wang, Zeke Xie, Yanhao Chen, Lixin Xiu, Hideki Nakayama
Published: 2026-05-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.28173v2

End-to-end manga generation is a structured visual storytelling task that requires story decomposition, recurring character and scene grounding, page layout design, panel rendering, page composition, and lettering. However, existing generative models often perform direct page synthesis, entangling these factors in a single visual output and limiting precise control over layout geometry, visual references, and cross-panel consistency. To address these limitations, we propose MangaFlow, an agentic framework for controllable long-form manga generation that decomposes manga creation into planning, grounding, layout construction, reference-conditioned rendering, composition, and text placement. By treating layout and visual references as explicit intermediate variables, MangaFlow enables both simple text-to-manga generation and more precise user-controlled manga creation. This design exposes layout, visual assets, and lettering as editable intermediate controls for refining panel geometry, references, and text placement. To support long-form consistency, MangaFlow introduces a story section memory that links section descriptions with corresponding character, scene, and object references for reuse across panels. We further present a meta-benchmark for evaluating layout controllability, visual consistency, and generation quality. Experiments show that MangaFlow improves layout adherence and cross-panel consistency over direct generation baselines while supporting flexible human control.

---

### MangaFlow: An End-to-End Agentic Framework for Controllable Story to Manga Generation

Authors: Muyao Wang, Zeke Xie, Yanhao Chen, Lixin Xiu, Hideki Nakayama
Published: 2026-05-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.28173v1

End-to-end manga generation is a structured visual storytelling task that requires story decomposition, recurring character and scene grounding, page layout design, panel rendering, page composition, and lettering. However, existing generative models often perform direct page synthesis, entangling these factors in a single visual output and limiting precise control over layout geometry, visual references, and cross-panel consistency. To address these limitations, we propose MangaFlow, an agentic framework for controllable long-form manga generation that decomposes manga creation into planning, grounding, layout construction, reference-conditioned rendering, composition, and text placement. By treating layout and visual references as explicit intermediate variables, MangaFlow enables both simple text-to-manga generation and more precise user-controlled manga creation. This design exposes layout, visual assets, and lettering as editable intermediate controls for refining panel geometry, references, and text placement. To support long-form consistency, MangaFlow introduces a story section memory that links section descriptions with corresponding character, scene, and object references for reuse across panels. We further present a meta-benchmark for evaluating layout controllability, visual consistency, and generation quality. Experiments show that MangaFlow improves layout adherence and cross-panel consistency over direct generation baselines while supporting flexible human control.

---

### Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values

Authors: Seongjun Lee, Suwan Yoon, Changhee Lee
Published: 2026-05-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.28170v1

As large language models (LLMs) are increasingly integrated into high-stakes decision-making, the ability to reliably quantify uncertainty has become a critical requirement for safety and trust. However, current uncertainty quantification methods primarily operate at the output level, often failing to distinguish whether uncertainty arises from the model's lack of knowledge or from ambiguity in the user's input. While input-centric uncertainty quantification has recently emerged as a promising direction, it remains relatively underexplored and typically relies on coarse, input-level information. Consequently, users are provided with scalar uncertainty scores that offer little actionable guidance on which parts of the input should be clarified to improve reliability. To address this limitation, we propose Shapley-based input uncertainty Quantification (ShaQ), a framework for span-level attribution of input-induced uncertainty. Our approach models ambiguous spans in the input as players in a cooperative game and quantifies their contributions using Shapley values, defined via the weighted average of marginal reductions in conditional entropy obtained by clarifying each span coalition. Unlike existing input-level approaches, our formulation captures complex interactions among spans and provides a principled decomposition in which individual attributions sum exactly to the total input-induced uncertainty. We evaluate ShaQ on the AmbigQA and AmbiEnt benchmarks, where it achieves state-of-the-art performance in ambiguity detection. We further demonstrate its utility on MediTOD, showing that ShaQ can localize under-specified clinical utterances and facilitate human-AI collaboration in high-stakes settings. Overall, ShaQ improves uncertainty estimation and provides actionable insights for targeted input clarification.

---

### OccuReward: LLM-Guided Occupant-Centric Reward Shaping for Demographic Equity in Grid-Interactive Buildings

Authors: Shadmehr Zaregarizi, Khashayar Yavari
Published: 2026-05-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.28168v1

Large language models (LLMs) have demonstrated promising capability in generating reward functions for deep reinforcement learning (DRL)-based building energy management. However, their potential to exhibit or exacerbate disparities in occupant comfort across heterogeneous demographic populations remains unexplored. We present OccuReward, a framework investigating how LLM-mediated reward design affects demographic equity. Our contribution is three-fold: the introduction of the Comfort Equity Index (CEI) as a novel feedback signal; a methodology for iterative, equity-aware LLM reward shaping; and a performance analysis of DRL agents under these refined objectives. Utilizing four empirically grounded occupant profiles from the ASHRAE Global Thermal Comfort Database II (13,440 votes), we deploy a Soft Actor-Critic agent in CityLearn v2. Our approach employs the Gemini API to generate reward function logic and weights--rather than performing per-step inference--across three refinement rounds. Results across 15 experimental runs reveal that elderly female occupants consistently experience the lowest satisfaction in initial rounds. By Round 3, equity-aware LLM refinement activates specific reward components that improve satisfaction for Young Males (+17.6%), Mid-aged Females (+28.2%), Health Sensitive (+53.8%), and Elderly Females (+567%), while simultaneously reducing energy costs by 3.2%. Our findings highlight that while reward-level intervention significantly improves equity, demographic disparities in AI-driven controllers persist, necessitating further research into algorithmic fairness in building systems.

---

### DebFilter: Eradicating Biases Stashed in Value

Authors: Seung Hyuk Lee, Songkuk Kim
Published: 2026-05-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.28167v1

Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising process guided by text embeddings extracted from pretrained vision-language models such as CLIP. However, these text embeddings inherently encode social and semantic biases -- such as those related to gender and age -- that are subsequently propagated and amplified through the guidance mechanism, along with the model's training on large-scale datasets that are imbalanced with respect to these bias-related concepts, often leading to skewed outputs in text-to-image generation. We propose DebFilter, a lightweight and training-free framework for mitigating such biases in text-to-image diffusion models. Observing that the model's error prediction at each denoising step is primarily influenced by cross-attention dynamics, we introduce a bias-correction strategy that adjusts the value components within cross-attention. Specifically, we apply a fixed offset to the slice of guidance embedding, effectively steering the semantic direction of cross-attention values toward unbiased representations. This adjustment reconfigures the score landscape to produce balanced outputs while maintaining alignment with the intended text semantics. Unlike prior approaches that rely on fine-tuning or retraining, DebFilter operates entirely at inference time, requiring no additional data or model updates. Our results demonstrate that this method effectively mitigates social biases in generated images, offering an efficient and scalable pathway toward fairer and more inclusive text-to-image generation.

---

### QuITE: Query-Based Irregular Time Series Embedding

Authors: Junghoon Lim
Published: 2026-05-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.28166v3

Irregular Multivariate Time Series (IMTS) are common in practice, yet their irregular sampling complicates effective modeling. Existing approaches typically either (i) design specialized architectures that limit the reuse of proven Multivariate Time Series (MTS) models, or (ii) map IMTS onto regular temporal grids through interpolation, which may distort temporal dynamics by introducing artificial values. To address these limitations, we propose a new input-embedding-based approach. We identify that the key bottleneck lies not in the backbone architecture, but in conventional embedding layers that assume uniform sampling. In this work, we introduce QuITE (Query-Based Irregular Time Series Embedding), a simple yet effective plug-and-play embedding module for IMTS. QuITE employs learnable query tokens to aggregate irregular observations through a single self-attention layer, directly producing backbone-compatible latent representations without artificial value generation or architectural modification. Extensive experiments on real-world benchmarks show that QuITE consistently improves MTS models, yielding average relative gains of up to $54.7\%$ in forecasting and $15.8\%$ in classification across diverse datasets and backbone architectures. Code is available at: https://github.com/Meaningfull9502/QuITE.

---

### Unification and Optimization of Robust Supervised Learning

Authors: Jonas Hanselle, Valentin Margraf, Clemens Damke, Eyke Hüllermeier
Published: 2026-05-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.28165v1

The literature has proposed various robust alternatives to empirical risk minimisation to address failure modes such as distribution shift, label noise and finite-sample degeneracies. Examples include distributionally robust optimization, label smoothing, vicinal risk minimization, and Mixup. However, such approaches are typically developed in isolation, forcing practitioners to commit a priori to a single failure mode even when the dominant mode for the task is unclear. To address this, we organize a broad class of existing methods along three common design axes and derive a tractable training procedure that decomposes robust learning into sequential stages (reference distribution enrichment, input-space perturbation, label-space perturbation, and sample-level aggregation), each with a choice of stance (pessimistic, neutral, or optimistic). This results in a unified design space in which joint hyperparameter optimization can compose and configure robustness strategies suited to the task at hand. Across tabular, image, and reward modeling benchmarks, joint hyperparameter optimization is competitive with the best single-method baseline in each setting, offering a reliable default for practitioners who do not know a priori which failure mode dominates their task.

---

### Performance and Explainability Requirements of Evolutionary Algorithms in Real-World Physics-Informed Optimization

Authors: Helena Stegherr, Michael Heider, Nils Meyer, Tobias Thummerer, Thomas Wendler, Pierre Aublin, Ennio Idrobo-Àvila, Lars Mikelsons, Sebastian Zaunseder, Jörg Hähner
Published: 2026-05-27
Categories: cs.NE, cs.AI
arXiv: https://arxiv.org/abs/2605.28164v1

Evolutionary computation offers a variety of tools to solve complex real-world optimization problems. However, research often focuses on smaller, simplified problems and optimization algorithms that sometimes miss expectations in real-world scenarios. Additionally, trust in the applied algorithm and the solutions it provides is often essential in such settings, but requires an understanding of the search process itself. This leads to evolutionary computation often not being seriously considered by practitioners in many application contexts, among them physics-based modeling. In this article, techniques from evolutionary computation are detailed that can alleviate these problems. First, five real-world physics-based optimization problems are introduced and described by domain experts. For each of these, the requirements for the evolutionary algorithm regarding performance and explainability to increase trust and usability are presented. We found that all domain experts expect fast convergence to a good solution and want some explanations for how the results were formed, while other requirements strongly depend on the respective problem. Finally, we present existing approaches that can be leveraged to improve those aspects of evolutionary algorithms but have to our knowledge never been employed in complex real-world scenarios. This implies a gap between both domains that needs to be closed to exploit the full potential of evolutionary computation.

---

### DEPART: DEcomposing PARiTy across Multilingual LLMs

Authors: Manan Uppadhyay, Prashant Kodali, Pranjal Chitale, Reshma Ramaprasad, Himanshu Beniwal, Sunayana Sitaram
Published: 2026-05-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.28163v1

Multilingual Large Language Models (mLLMs) leaderboards report per-language accuracy but rarely explain why disparities emerge, leaving systemic biases unattributed and offering practitioners no actionable levers. We first establish that these gaps are systematic rather than artifacts of sampling noise via distribution-free Friedman and Kruskal--Wallis tests, then introduce a two-step Bayesian hierarchical framework that decomposes multilingual performance variance into interpretable components. First, isolating the variance attributable to language identity, we show that observable language features (script, family, typological distance) explain $R^2_{\text{ling}} = 79\%$ of this variance on understanding tasks and $92\%$ on reasoning, with a model's internal representational similarity to English emerging as the dominant predictor across both task buckets. Second, decomposing the full (model$\times$benchmark$\times$language) cube, we find that NLU and reasoning have fundamentally divergent variance profiles: model identity dominates understanding ($66.7\%$ of variance), whereas the benchmark$\times$model interaction dominates reasoning ($46.3\%$). Together these results recast multilingual evaluation from passive performance mapping into an explainable, diagnostic framework with concrete levers for targeting the root drivers of language disparity.

---

### Learning Logical Operations for Arbitrary Quantum Error Correction Codes

Authors: Nico Meyer, Christopher Mutschler, Dominik Seuß, Andreas Maier, Daniel D. Scherer
Published: 2026-05-27
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2605.28162v3

Logical operations are essential for quantum computation within quantum error-correcting codes. However, discovering their physical realizations is challenging, especially for non-additive codes that lack a stabilizer description. We present a general learning-based framework that, given only an encoding circuit, constructs physical implementations of logical operations while enforcing structural properties such as transversality or shallow depth. Our approach is validated by rediscovering known logical operations of standard stabilizer codes. We then extend it to a co-design procedure, dubbed variational early fault-tolerant quantum computing (VarEFTQC), which tailors non-additive encodings to a given noise model and enforces desired logical gate sets, such as transversal IQP-type families or low-depth universal sets. A software library implements the complete learning pipeline, including loss-function variants, ansatz families, and optimization routines. Together, these results position VarEFTQC as a proof-of-concept framework for discovering hardware-adapted logical gadgets for early fault-tolerant quantum computing.

---

### Learning Logical Operations for Arbitrary Quantum Error Correction Codes

Authors: Nico Meyer, Christopher Mutschler, Dominik Seuß, Andreas Maier, Daniel D. Scherer
Published: 2026-05-27
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2605.28162v2

Logical operations are essential for quantum computation within quantum error-correcting codes. However, discovering their physical realizations is challenging, especially for non-additive codes that lack a stabilizer description. We present a general learning-based framework that, given only an encoding circuit, constructs physical implementations of logical operations while enforcing structural properties such as transversality or shallow depth. Our approach is validated by rediscovering known logical operations of standard stabilizer codes. We then extend it to a co-design procedure, dubbed variational early fault-tolerant quantum computing (VarEFTQC), which tailors non-additive encodings to a given noise model and enforces desired logical gate sets, such as transversal IQP-type families or low-depth universal sets. A software library implements the complete learning pipeline, including loss-function variants, ansatz families, and optimization routines. Together, these results position VarEFTQC as a practical tool for discovering hardware-adapted logical gadgets for early fault-tolerant quantum computing.

---

### MeniOmni: A Structured Multimodal Benchmark for Holistic Meniscus Injury Assessment

Authors: Shurui Xu, Siqi Yang, Weiping Ding, Hui Wang, Mengzhen Fan, Yuyu Sun, Shuyan Li
Published: 2026-05-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.28161v1

Clinical diagnosis of meniscus injuries requires radiologists to integrate volumetric MRI evidence with patient context (e.g., sex, age, BMI) and to produce structured diagnostic reports. Existing knee MRI benchmarks are typically unimodal and rely on coarse labels, limiting their ability to evaluate holistic clinical reasoning. We introduce MeniOmni, a structured multimodal benchmark for meniscus injury assessment, consisting of 746 multi-center MRI studies with tri-planar volumetric inputs, Clinical Priors, and expert-annotated clinical text. MeniOmni supports two tasks: (1) fine-grained Stoller severity grading and (2) diagnostic report generation. We further propose risk-aware ordinal evaluation and a semantic consistency metric (Meni-Score) to better reflect clinical relevance. Baseline experiments show that incorporating Clinical Priors improves grading performance and reduces severe errors, highlighting the value of multimodal context for safer assessment. Code and data are available at https://github.com/ShuruiXu/MeniOmni.

---

### Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning

Authors: Yang Zhang, Xiaoshuai Sun, Rui Zhao, Wujin Sun, Yidong Chen, Jiayi Ji, Qian Chen, Rongrong Ji
Published: 2026-05-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.28160v1

Existing multimodal reasoning approaches predominantly follow two paradigms: converting visual inputs into text prior to reasoning, or performing end-to-end reasoning within a unified vision-language representation space. Despite their empirical progress, both paradigms suffer from fundamental structural limitations. The former relies on static visual-to-text conversion, which tends to compress and lose fine-grained visual details. The latter is prone to linguistic dominance induced by joint optimization and attention mechanisms, leading to systematically weakened faithfulness to visual evidence during reasoning. In this work, we argue that a central challenge is how and when visual evidence is introduced into the reasoning process. Motivated by this insight, we propose CSMR, a multimodal reasoning framework in which a language model controls the reasoning process by deciding when to invoke an independent visual perception module to acquire task-relevant visual evidence. Experiments across multiple multimodal reasoning benchmarks show that CSMR consistently outperforms representative baseline methods in accuracy under a zero-shot setting. Further experimental analysis confirms that these advantages primarily arise from the proposed cognitive scheduling mechanism.

---

### OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents

Authors: Chenyu Zhou, Xinyun Lu, Jiangyue Zhao, Jianghao Lin, Dongdong Ge, Yinyu Ye
Published: 2026-05-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.28158v1

Large language model (LLM) agents are increasingly used to assist with operations research (OR) modeling, yet existing OR-oriented benchmarks often reduce evaluation to one-shot translation from a self-contained problem statement into a mathematical formulation or solver program. Such settings abstract away two characteristics of real industrial OR workflows: persistent multi-artifact workspaces and multi-stage task lifecycles. We introduce OR-Space, a full-lifecycle workspace benchmark for evaluating industrial optimization agents across model construction, model revision, and grounded explanation. Each instance is an executable workspace containing business documents, structured data, optional code artifacts, solver outputs, and task-specific evaluators distributed across interdependent files. OR-Space defines three task modes: Build, where agents construct solver-ready optimization models from heterogeneous artifacts; Revise, where agents modify existing models under changing requirements or solver feedback while preserving valid prior logic; and Explain, where agents answer grounded questions about solutions, constraints, and business implications using evidence spread across workspace artifacts. By combining persistent workspaces with lifecycle-oriented tasks, OR-Space evaluates whether agents can perform reliable optimization work beyond end-to-end text generation. We describe the benchmark design, evaluation protocol, and quality-control pipeline, and position OR-Space as a benchmark for studying the reliability, failure modes, and practical readiness of LLM agents in industrial OR workflows.

---

### Intra-YOLO: A Small Object Detection Model for Caries and Molar-Incisor Hypomineralization in Intraoral Photography Based on Transfer Learning with Reinforcement Learning

Authors: Po-Lun Chwang, Po-Yu Chang, Wen-Liang Lin, Tung-Sheng Wu, Min-Ching Wang, Yun-Chien Cheng
Published: 2026-05-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.28157v1

This study developed a computer-aided diagnosis (CAD) system for detecting caries and molar-incisor hypomineralization (MIH) in intraoral photographs. These lesions share similar appearances, making clinical differentiation challenging, especially given their small size and variability in imaging conditions.

---

### Temporal Hyperbolic Graph Representation Learning for Scale-Free Internet Routing and Delay Prediction

Authors: Yi-Ling Kuo, Hao-Yu Tien, Shih-Yu Tsai
Published: 2026-05-27
Categories: cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2605.28155v1

Predicting Internet round-trip time (RTT) is critical for routing optimization, quality-of-service (QoS) provisioning, and traffic engineering, yet remains challenging due to long-term temporal dependencies, evolving routing dynamics, and heavy-tailed latency distributions. While Temporal Graph Neural Networks (TGNNs) can model evolving network topologies, most existing approaches operate in Euclidean space, which poorly captures the hierarchical and scale-free structure of Internet routing graphs. Hyperbolic geometry provides a more suitable representation space. We propose HERMIT (Hyperbolic Edge-aware RTT Modeling via Integrated Topology), a hybrid framework combining a hyperbolic manifold-preserving temporal GNN with a Random Forest regressor for joint link prediction and RTT prediction. Built on HMPTGN, HERMIT introduces RTT-aware edge features and a learnable edge encoder to improve modeling of evolving link states and routing behavior. The resulting hyperbolic node representations are combined with historical RTT statistics for robust latency prediction. We evaluate HERMIT on a large-scale real Internet dataset spanning 2015-2024. HERMIT consistently outperforms a strong Random Forest baseline using only historical RTT statistics, achieving a 6% RMSE improvement while reducing large errors on heavy-tailed samples. It also surpasses prior hyperbolic TGNN models, including HMPTGN and HTGN, in link prediction performance. These results demonstrate that combining hyperbolic temporal graph learning with tree-based regression provides a scalable solution for RTT prediction in real-world Internet topologies.

---

### Skillful high-resolution weather forecasting independent of physical models

Authors: Pengcheng Zhao, Siqi Xiang, Weixin Jin, Zekun Ni, Jiang Bian, Zuliang Fang, Hongyu Sun, Bin Zhang, Richard E. Turner, Jonathan Weyn, Haiyu Dong, Kit Thambiratnam et al.
Published: 2026-05-27
Categories: physics.ao-ph, cs.LG
arXiv: https://arxiv.org/abs/2605.28153v1

Accurate and timely weather forecasts are critical for high-impact decisions in modern society. Machine-learning-based weather prediction is emerging as an alternative for producing initial conditions, forecasts, and even both in end-to-end systems. These methods deliver predictions faster and often with higher skill than traditional numerical weather prediction (NWP). However, even end-to-end models typically rely on NWP-generated reanalyses for supervision, thereby inheriting the biases and resolution limitations of those NWPs, and limiting adaptation to settings where suitable reanalysis products are unavailable, infrequently updated, or expensive to produce. Here we introduce ObsCast, a regional system that generates both analysis and predictions, without using any NWP-derived data in either training or inference, while still achieving state-of-the-art performance in short-term high-resolution regional modeling. Over the contiguous United States and Europe, ObsCast outperforms operational NWP for near-surface variables through 18 h and produces skillful precipitation forecasts. It provides a simpler and more adaptable route to build and refine regional forecasting services directly from local observations, without the need to develop complex and costly traditional forecasting pipelines.

---

### A novel ordinal multi-view aggregation scheme for oak defoliation

Authors: Francisco Bérchez-Moreno, Ricardo Enrique Hernández-Lambraño, David Guijo-Rubio, Víctor Manuel Vargas, Francisco José Ruiz-Gómez, Juan Carlos Fernández, Pablo González-Moreno
Published: 2026-05-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.28151v1

Forest decline driven by climate and biotic stressors threatens ecosystem functioning, making accurate monitoring of tree health essential. In this work, we address tree defoliation estimation as an ordinal classification problem using ground-level imagery. We propose a novel multi-view ensemble framework that aggregates predictions from Convolutional Neural Networks (CNNs) trained on different perspectives of individual trees (north, south, and crown). This approach leverages complementary visual information while preserving modelling consistency through a homogeneous ensemble design. A comprehensive evaluation is conducted by comparing multiple ordinal classification methods and analysing the contribution of each view and their combinations. Results show that modelling the ordinal structure of defoliation levels improves performance over nominal approaches, while the proposed multi-view ensemble consistently outperforms single-view and pairwise configurations. In particular, the three-view ensemble achieves the most robust and accurate predictions across all evaluation metrics. These findings highlight the potential of combining Deep Learning (DL), Ordinal Classification (OC), and multi-view aggregation for scalable, consistent, and objective forest health assessment in complex ecosystems such as Mediterranean dehesas.

---

### Off-Policy Learning to Reason Works Because It Is More Pessimistic Than You Think

Authors: Otmane Sakhi, Aleksei Arzhantsev, Imad Aouali, Flavian Vasile
Published: 2026-05-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.28150v1

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This makes learning inherently off-policy. Most existing approaches nevertheless remain rooted in PPO-style trust-region objectives, treating training as approximately on-policy and using importance weights to correct distribution mismatch. These corrections can introduce high variance, destabilize optimization, and accelerate entropy collapse. Recent work suggests an alternative: rather than correcting the mismatch, one can embrace off-policy data and remove importance weights, often yielding stronger algorithms. In this paper, we provide an intuitive construction of off-policy objectives that include successful off-policy objectives and show that their effectiveness can be understood through implicit pessimism: they optimize toward target policies that are more conservative than their nominal objectives suggest. This perspective explains why some particular implementation choices improve stability: they implicitly control the effective target distribution. We then propose a principled modification that stabilize this induced distribution and improve off-policy learning.

---

### Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations

Authors: Bartosz Wieciech, Zmnako Awrahman, Marcin Czelej, Victor Hugo Jaramillo Velasquez, Wioletta Stobieniecka
Published: 2026-05-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.28149v3

Sparse Autoencoders (SAEs) extract interpretable features from Large Language Model activations, but standard variants enforce non-negative latents, so a bidirectional semantic axis (e.g., "pressure too high" vs. "pressure too low") must be split across two latents, wasting dictionary capacity on anticorrelated features. We propose the Sign-Aware Gated SAE (SA-GSAE), which combines two-sided gated sparsity, signed shrinkage-free magnitudes, and auxiliary gate supervision in a new Bi-Jump-ReLU activation, so that a single latent carries both polarities of one decoder direction; parameter accounting shows sign-awareness stays parameter-efficient even when anticorrelated pairs are rare. Across three mid-depth hookpoints on Pythia-1B and SmolLM3-3B (six cells, three seeds), a half-width SA-GSAE empirically dominates the aggregate mean frontier of a full-width Gated SAE on three of six cells, matches its R^2 within 0.025 on the remaining three, and cuts dead fraction by 0.35-0.82 absolute at matched L_0 = 64 on all six. Ablations show the two-sided gate and the auxiliary loss are essential whereas per-polarity asymmetry is not; we recommend the fully tied symmetric variant as the default. A blinded semantic audit finds nameable opposition between a latent's two sides is rare for SA-GSAE and all tested baselines, while sign-conditioned interventions show a single signed latent acts as a bidirectional causal dial where a pair of "opposite" non-negative latents does not; we scope interpretability claims accordingly. At full width, SA-GSAE is over-parameterized and its reported configuration exhibits a reproducible reconstruction collapse at the SmolLM3-3B residual-stream site; the recommended configuration (small threshold initialization with dead-latent threshold resets) prevents it.

---

### DeltaMCP: Incremental Regeneration via Spec-Aware Transformation for MCP servers

Authors: Aditya Pujara, Xiaogang Zhu, Hsiang-Ting Chen
Published: 2026-05-27
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2605.28148v1

The rapid development of LLMs coupled with the introduction of Model Context Protocol (MCP) has revolutionized how intelligent agents interact with APIs through deterministic and structured methods \cite{ModelContextProtocolIntro2025}. While some existing systems like AutoMCP attempt to automate a previously completely manual process of generating MCP servers, they fail to address the recurring challenge of maintaining synchronization between evolving enterprise-level APIs and their corresponding MCP toolset implementation \cite{mastouri2025makingrestapisagentready}. This paper introduces DeltaMCP, a specification-aware, incremental regeneration tool for enterprise-grade MCP servers. DeltaMCP enables developers to only update the affected tooling of MCP servers, given a new release of it's corresponding service's OpenAPI specification. Using Azure REST API specifications as the evaluation dataset, DeltaMCP is benchmarked against baseline full generation methods on generation quality and system performance. The results demonstrate the reduction in developer overhead through DeltaMCP whilst improving maintainability and version consistency. This research offers a scalable approach for enterprises seeking to maintain high-fidelity, up-to-date MCP server infrastructures for LLM-based systems.

---

### Adaptive Reservoir Computing for Multi-Scenario Chaotic System Forecasting

Authors: Shadmehr Zaregarizi, Khashayar Yavari
Published: 2026-05-27
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.28145v1

We present an adaptive reservoir computing framework for the CTF-4-Science Lorenz benchmark, which evaluates machine learning models across twelve distinct tasks spanning five qualitatively different scenarios: baseline forecasting, noisy signal reconstruction, forecasting under noise, few-shot learning, and parametric generalization. Rather than applying a uniform inference strategy, we tailor the training and prediction procedure of Echo State Networks (ESNs) to the specific demands of each evaluation scenario. Our key contributions are fourfold: (1) exact reservoir state synchronization that eliminates warmup approximation error in short-time prediction; (2) histogram-guided candidate selection that directly optimizes the long-time ergodic evaluation metric; (3) multi-seed reservoir search for few-shot regimes with severely limited training data; and (4) sequential multi-sequence training that resolves state-distribution mismatch in parametric generalization tasks. The proposed framework achieves a score of 74.91 on the public benchmark leaderboard, demonstrating that carefully adapted reservoir computing constitutes a competitive and computationally efficient approach for diverse chaotic system modeling challenges.

---

### Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning

Authors: Yi Wang, Haojie Lu, Zhaofan Zhang, Li Chen, Sihong Xie
Published: 2026-05-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.28144v1

LLMs have shown remarkable proficiency in general language understanding and reasoning. However, they consistently underperform in spatial reasoning that severely limits their application, particularly in embodied intelligence. Inspired by the success of hierarchical reinforcement learning, this paper introduces a novel method for hierarchical task decomposition in LLM spatial reasoning. Our approach guides LLMs to decompose complex tasks into manageable sub-tasks by identifying key intermediate states and generating simplified sub-environments. However, we identify that LLMs often fail to derive optimal intermediate states due to their insufficient spatial prior, leading to sub-optimal task decomposition. To address this limitation and enhance its planning capability, we propose the MCTS-Guided Group Relative Policy Optimization (M-GRPO), where we reformulate the UCT formula by incorporating the LLM's prior predictive probabilities alongside its epistemic uncertainty. Furthermore, we implement a more fine-grained advantage function, enabling the model to learn optimal path planning. Experimental results demonstrate that our method substantially improves LLM performance on spatial tasks, including navigation, planning, and strategic games, achieving state-of-the-art results. This work paves the way for LLMs in real-world applications.

---

### Sequential Neural Probabilistic Amplitude Shaping: Learning the Channel's Language

Authors: Mohammad Taha Askari, Lutz Lampe, Amirhossein Ghazisaeidi
Published: 2026-05-27
Categories: cs.LG, cs.IT, eess.SP
arXiv: https://arxiv.org/abs/2605.28143v1

We present the first neural probabilistic amplitude shaping that outperforms existing methods while accounting for all implementation losses, using a block-less, easily implementable sequential autoregressive encoder compatible with arithmetic distribution matching, yielding reduced rate loss and higher achievable information rates.

---

### Self-Consistency via Marginal Sharpening

Authors: Aleksei Arzhantsev, Otmane Sakhi, Nicolas Chopin
Published: 2026-05-27
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.28142v1

Inference-time sampling can elicit strong reasoning abilities from language models without additional training. Existing power-sampling methods do so by sharpening the distribution over full generated outputs, favoring completions that are individually likely under the model. We argue that this is the wrong object to target for reasoning: a completion entangles a reasoning trace with a final answer, whereas what matters is whether an answer is supported by many plausible reasoning paths. We therefore shift the target from the full-output distribution to the sharpened answer marginal, making self-consistency an inference-time objective rather than a post-hoc voting criterion. Surprisingly, this marginal target admits an efficient approximation: we propose a simple, purely autoregressive parallel sampling algorithm that approximately samples from the sharpened answer marginal, eliciting stronger performance than standard power sampling on mathematics and coding benchmarks while being orders of magnitude faster.

---

### Data-Efficient On-Policy Distillation for Automatic Speech Recognition

Authors: Yu Lin, Yiming Wang, Runyuan Cai, Xiaodong Zeng
Published: 2026-05-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.28139v1

Building competitive automatic speech recognition (ASR) models usually requires large-scale au- dio supervision, which makes reproduction and specialization expensive. We study Ark-ASR, a 0.6B- parameter audio-conditioned language model trained with 100k hours of speech, and examine whether a strong Qwen-ASR teacher can transfer additional recognition capability through on-policy distillation. Across Mandarin and English ASR benchmarks, the proposed training recipe consistently improves over supervised fine-tuning alone and outperforms the same-scale Qwen3-ASR-0.6B baseline on four of five evaluation sets. This is achieved with only 100k hours of speech, compared with the 20M hours of super- vised audio reported for the Qwen3-Omni AuT encoder. The larger Qwen3-ASR-1.7B remains stronger, but the results show that teacher-guided on-policy training can substantially close the gap for compact ASR models under a much smaller audio budget. A support-overlap diagnostic further suggests that the teacher-data stage improves local student-teacher compatibility, matching recent analyses of when on-policy distillation is effective.

---