# Research Papers — 2026-05 · bundle page 183 of 326

> Full-text markdown of papers #9101–9150 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/183
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/182.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/184.md)

### Prompt Segmentation and Annotation Optimisation: Controlling LLM Behaviour via Optimised Segment-Level Annotations

Authors: Devika Prasad, Luke Gerschwitz, Tong Li, Henry Xiao, Anjin Liu, Coco Wu, Anna Leontjeva, Luiz Pizzato
Published: 2026-05-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.14561v1

Prompt engineering is crucial for effective interaction with generative artificial intelligence systems, yet existing optimisation methods often operate over an unstructured and vast prompt space, leading to high computational costs and potential distortions of the original intent. We introduce Prompt Segmentation and Annotation Optimisation (PSAO), a structured prompt optimisation framework designed to improve prompt optimisation controllability and efficiency. PSAO decomposes a prompt into interpretable segments (e.g., sentences) and augments each with human-readable annotations (e.g., {not important}, {important}, {very important}). These annotations guide large language models (LLMs) in allocating focus and clarifying confusion during response generation. We formally define the segmentations and annotations and demonstrate that optimised segment-level annotations can lead to improved LLM responses, with the original prompt retained as a candidate in the optimisation space to prevent performance degradation. Empirical evaluations indicate that PSAO benefits from annotations in terms of improved reasoning accuracy and self-consistency. However, developing efficient methods for identifying optimal segmentations and annotations remains challenging and is reserved for future investigation. This work is intended as a proof of concept, demonstrating the feasibility and potential of segment-level annotation optimisation.

---

### PyCSP3-Scheduling: A Scheduling Extension for PyCSP3

Authors: Sohaib Afifi
Published: 2026-05-14
Categories: cs.AI, math.OC
arXiv: https://arxiv.org/abs/2605.14559v1

PyCSP$^3$ provides a productive way to build constraint models for solving combinatorial constrained problems and export them to XCSP$^3$, preserving a complete separation between modeling and solving. However, it lacks native support for scheduling abstractions such as interval variables, sequence variables, and resource functions. As a result, scheduling models must be encoded with low-level integer variables and manual channeling constraints, even though PyCSP$^3$ already provides global constraints like NoOverlap and Cumulative on integer arrays. We present PyCSP$^3$ Scheduling, a library that adds scheduling abstractions to PyCSP$^3$ through 53 dedicated constraints and 27 expressions, and compiles them down to standard PyCSP$^3$/XCSP$^3$ constraints, maintaining the modeling/solving separation that underpins the PyCSP$^3$ ecosystem. On 261 paired instances across 17 model families (5 runs each), both formulations produce identical objectives on all 72 doubly-proved optimal pairs and nearly half of the families (8/17) remain structurally unchanged after compilation; however, runtime performance diverges across families, with clear gains on some (up to 5.8x) and regressions on others due to the overhead of compilation decompositions. Code and benchmarks are available at: https://github.com/sohaibafifi/pycsp3-scheduling

---

### Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy

Authors: Langzhou He, Junyou Zhu, Yue Zhou, Zhengyao Gu, Junhua Liu, Wei-Chieh Huang, Henry Peng Zou, David Wipf, Philip S. Yu, Qitian Wu
Published: 2026-05-14
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.14558v1

Agentic reinforcement learning trains large language models using multi-turn trajectories that interleave long reasoning traces with short environment-facing actions. Common policy-gradient methods, such as PPO and GRPO, treat each token in a trajectory equally, leading to uniform credit assignment. In this paper, we critically demonstrate that such uniform credit assignment largely misallocates token-level training signals. From an energy-based modeling perspective, we show that token-level training signals, quantified by their correlations with reward variance of different rollouts sampled from a given prompt, concentrate sharply on action tokens rather than reasoning tokens, even though action tokens account for only a small fraction of the trajectory. We refer to this phenomenon as the Action Bottleneck. Motivated by this observation, we propose an embarrassingly simple token reweighting approach, ActFocus, that downweights gradients on reasoning tokens, along with an additional energy-based redistribution mechanism that further increases the weights on action tokens with higher uncertainty. Across four environments and different model sizes, ActFocus consistently outperforms PPO and GRPO, yielding final-step gains of up to 65.2 and 63.7 percentage points, respectively, without any additional runtime or memory cost.

---

### TeachAnything: A Multimodal Crowdsourcing Platform for Training Embodied AI Agents in Symmetrical Reality

Authors: Zidong Liu, Rongkai Liu, Yue Li, Zhenliang Zhang
Published: 2026-05-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.14556v1

Symmetrical Reality (SR) is emerging as a future trend for human-agent coexistence, placing higher demands on agents to acquire human-like intelligence. It calls for richer and more diverse human guidance. We introduce a three-stage demonstration paradigm integrating multimodal demonstration signals. Building on this paradigm, we developed TeachAnything, a cloud-based, crowdsourcing-oriented demonstration platform with physics simulation capable of collecting diverse demonstration data across varied scenes, tasks, and embodiments. By unifying virtual and physical interactions through both methodological design and physics simulation, the system serves as a practical foundation for developing embodied agents aligned with Symmetrical Reality.

---

### Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis

Authors: Shuyang Cui, Zhi Zhong, Qiyu Wu, Zachary Novack, Woosung Choi, Keisuke Toyama, Kin Wai Cheuk, Junghyun Koo, Yukara Ikemiya, Christian Simon, Chihiro Nagashima, Shusuke Takahashi
Published: 2026-05-14
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2605.14555v1

Current methods for creating drum loop audio in digital music production, such as using one-shot samples or resampling, often demand non-trivial efforts of creators. While recent generative models achieve high fidelity and adhere to text, they lack the specific control needed for such a task. Existing symbolic-to-audio research often focuses on single, tonal instruments, leaving the challenge of polyphonic, percussive drum synthesis unaddressed. We address this gap by introducing ``Break-the-Beat!,'' a model capable of rendering a drum MIDI with the timbre of a reference audio. It is built by fine-tuning a pre-trained text-to-audio model with our proposed content encoder and a effective hybrid conditioning mechanism. To enable this, we construct a new dataset of paired target-reference drum audio from existing drum audio datasets. Experiments demonstrate that our model generates high-quality drum audio that follows high-resolution drum MIDI, achieving strong performance across metrics of audio quality, rhythmic alignment, and beat continuity. This offer producers a new, controllable tool for creative production. Demo page: https://ik4sumii.github.io/break-the-beat/

---

### Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits

Authors: Donghao Li, Chengshuai Shi, Weijuan Ou, Cong Shen, Jing Yang
Published: 2026-05-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.14553v1

Prompt engineering has become central to eliciting the capabilities of large language models (LLMs). At its core lies prompt selection -- efficiently identifying the most effective prompts. However, most prior investigations overlook a key challenge: the inherently multi-faceted nature of prompt performance, which cannot be captured by a single metric. To fill this gap, we study the multi-objective prompt selection problem under two practical settings: Pareto prompt set recovery and best feasible prompt identification. Casting the problem into the pure-exploration bandits framework, we adapt provably efficient algorithms from multi-objective bandits and further introduce a novel design for best feasible arm identification in structured bandits, with theoretical guarantees on the identification error in the linear case. Extensive experiments across multiple LLMs show that the bandit-based approaches yield significant improvements over baselines, establishing a principled and efficient framework for multi-objective prompt optimization.

---

### LiWi: Layering in the Wild

Authors: Yu He, Fang Li, Haoyang Tong, Lichen Ma, Xinyuan Shan, Jingling Fu, Dong Chen, Luohang Liu, Junshi Huang, Yan Li
Published: 2026-05-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.14552v3

Recent advances in generative models have empowered impressive layered image generation, yet their success is largely confined to graphic design domains. The layering of in-the-wild images remains an underexplored problem, limiting fine-grained editing and applications of images in real-world scenarios. Specifically, challenges remain in scalable layered data and the modeling of object interaction in natural images, such as illumination effects and structural boundary. To address these bottlenecks, we propose a novel framework for high-fidelity natural image decomposition. First, we introduce an Agent-driven Data Decomposition (ADD) pipeline that orchestrates agents and tools to synthesize layered data without manual intervention. Utilizing this pipeline, we construct a large-scale dataset, named LiWi-100k, with over 100,000 high-quality layered in-the-wild images. Second, we present a novel framework that jointly improves photometric fidelity and alpha boundary accuracy. Specifically, shadow-guided learning explicitly models the illumination effects, and degradation-restoration objective provides boundary-correction supervision by recovering clean foreground image from degraded one. Extensive experiments demonstrate that our framework achieves state-of-the-art (SoTA) performance in natural image decomposition, outperforming existing models in RGB L1 and Alpha IoU metrics. We will soon release our code and dataset.

---

### SeesawNet: Towards Non-stationary Time Series Forecasting with Balanced Modeling of Common and Specific Dependencies

Authors: Hao Li, Lu Zhang, Liu Chong, Yankai Chen, Pengyang Wang, Yingjie Zhou
Published: 2026-05-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.14551v1

Instance normalization (IN) is widely used in non-stationary multivariate time series forecasting to reduce distribution shifts and highlight common patterns across samples. However, IN can over-smooth instance-specific structural information that is essential for modeling temporal and cross-channel heterogeneity. While prior methods further suppress distribution discrepancies or attempt to recover temporal specific dependencies, they often ignore a central tension: how to adaptively model common and instance-specific dependency based on each instance's non-stationary structures. To address this dilemma, we propose SeesawNet, a unified architecture that dynamically balances common and instance-specific dependency modeling in both temporal and channel dimensions. At its core is Adaptive Stationary-Nonstationary Attention (ASNA), which captures common dependencies from normalized sequences and specific dependencies from raw sequences, and adaptively fuses them according to instance-level non-stationarity. Built upon ASNA, SeesawNet alternates dedicated temporal and channel relationship modeling to jointly capture long-range and cross-variable dependencies. Extensive experiments on multiple real-world benchmarks demonstrate that SeesawNet consistently outperforms state-of-the-art methods.

---

### Multi-Dimensional Model Integrity and Responsibility Assessment Index and Scoring Framework

Authors: Phuc Truong Loc Nguyen, Thanh Hung Do, Truong Thanh Hung Nguyen, Hung Cao
Published: 2026-05-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.14550v1

Artificial intelligence in high-stakes tabular domains cannot be evaluated by predictive performance alone, yet current practice still assesses explainability, fairness, robustness, privacy, and sustainability mostly in isolation. We propose the Model Integrity and Responsibility Assessment Index (MIRAI), a unified evaluation framework that measures tabular models across these five dimensions under a controlled comparison setting and aggregates them into a single score. MIRAI combines established metrics through normalized and direction-aligned dimension scores, which enables direct comparison across models with different architectural and computational profiles. Experiments on healthcare, financial, and socioeconomic datasets show that higher predictive performance does not necessarily imply better overall integrity and responsibility. In several cases, simpler models achieve a stronger cross-dimensional balance than more complex deep tabular architectures. MIRAI provides a compact and practical basis for responsible model selection in regulated settings.

---

### Local Spatiotemporal Convolutional Network for Robust Gait Recognition

Authors: Xiaoyun Wang, Cunrong Li, Wu Wang
Published: 2026-05-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.14548v1

Gait recognition, as a promising biometric technology, identifies individuals through their unique walking patterns and offers distinctive advantages including non-invasiveness, long-range applicability, and resistance to deliberate disguise. Despite these merits, capturing the intrinsic motion patterns concealed within consecutive video frames remains challenging due to the complexity of video data and the interference of external covariates such as viewpoint changes, clothing variations, and carrying conditions. Existing approaches predominantly rely on either static appearance features extracted from individual silhouette frames or employ complex sequential models (\eg, LSTM, 3D convolutions) that demand substantial computational resources and sophisticated training strategies. To address these limitations, we propose a Local Spatiotemporal Convolutional Network (LSTCN), a structurally simple yet highly effective dual-branch architecture that endows standard two-dimensional convolutional networks with the capacity to extract temporal information. Specifically, we introduce a Global Bidirectional Spatial Pooling (GBSP) mechanism that reduces the dimensionality of gait tensors by decomposing spatial features into horizontal and vertical strip-based local representations, enabling the temporal dimension to participate in standard 2D convolution operations. Building upon this, we design a Local Spatiotemporal Convolutional (LSTC) layer that jointly processes temporal and spatial dimensions, allowing the network to adaptively learn strip-based gait motion patterns. We further extend this formulation with asymmetric convolution kernels that independently attend to the temporal, spatial, and joint spatiotemporal domains, thereby enriching the extracted feature representations.

---

### Discovering Physical Directions in Weight Space: Composing Neural PDE Experts

Authors: Pengkai Wang, Pengwei Liu, Yuanyi Wang, Guanyu Chen, Xingyu Ren, Xiaolong Li, Zhongkai Hao, Yuting Kong, Qixin Zhang, Dong Ni
Published: 2026-05-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.14546v1

Recent advances in neural operators have made partial differential equation (PDE) surrogate modeling increasingly scalable and transferable through large-scale pretraining and in-context adaptation. However, after a shared operator is fine-tuned to multiple regimes within a continuous physical family, it remains unclear whether the resulting weight-space updates merely form isolated regime experts or reveal reusable physical structure. Starting from a shared family anchor, we fine-tune low- and high-regime endpoint experts and show that their updates can be separated into a family-shared adaptation and a direction aligned with the underlying physical parameter. This separation reinterprets endpoint experts as finite-difference probes of a local physical direction in weight space, explaining why static averaging can interpolate between regimes but attenuates endpoint-specific physics. Building on this perspective, we propose Calibration-Conditioned Merge (CCM), a post-hoc coordinate readout method for composing neural PDE experts along this physical direction. Given physical metadata, a calibrated coordinate mapping, or a short observed rollout prefix, CCM infers the target composition coordinate and deploys a single merged checkpoint for the remaining rollout. We evaluate CCM on the reaction--diffusion system, viscosity-parameterized two-dimensional Navier--Stokes equations, and radial dam-break dynamics. Across these benchmarks, CCM achieves its strongest gains in extrapolative regimes, reducing out-of-distribution rollout error relative to the family anchor by 54.2%, 42.8%, and 13.8%, respectively. Further experiments across FNO scales, a DPOT-style backbone, and ablations confirm that endpoint fine-tuning is not arbitrary checkpoint drift, but reveals a calibratable physical direction for training-free transfer across PDE regimes.

---

### Complacent, Not Sycophantic: Reframing Large Language Models and Designing AI Literacy for Complacent Machines

Authors: Federico Germani, Giovanni Spitale
Published: 2026-05-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.14544v1

Large language models are often described as sycophantic, in the sense that they appear to flatter users or mirror their beliefs. We argue that this label is conceptually misleading: sycophancy implies motives and strategic intent, which LLMs do not possess. Their behaviour is better understood as complacency, a structural tendency to agree with user input because training data, reward signals and design favour agreement and reinforcement over correction. We argue that this distinction matters. Whether developers act sycophantically or not, models themselves never are sycophants; they can only be made more or less complacent. This reframing locates agency in developers and institutions, not in the model. Because complacent models reinforce users' prior beliefs, we argue that AI literacy educational approaches should particularly focus on strategies to counter confirmation bias.

---

### RxEval: A Prescription-Level Benchmark for Evaluating LLM Medication Recommendation

Authors: Shuhao Chen, Weisen Jiang, Changmiao Wang, Xiaoqing Wu, Xuanren Shi, Yu Zhang, James T. Kwok
Published: 2026-05-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.14543v1

Inpatient medication recommendation requires clinicians to repeatedly select specific medications, doses, and routes as a patient's condition evolves. Existing benchmarks formulate this task as admission-level prediction over coarse drug codes with multi-hot diagnostic and procedure code inputs, failing to capture the per-timepoint, information-rich nature of real prescribing. We propose RxEval, a prescription-level benchmark that evaluates LLM prescribing capability by multiple-choice questions: each question presents a detailed patient profile and time-ordered clinical trajectory, requiring selection of specific medication-dose-route triples from real prescriptions and patient-specific distractors generated via reasoning-chain perturbation. RxEval comprises 1,547 questions spanning 584 patients, 18 diagnostic categories, and 969 unique medications. Evaluation of 16 LLMs shows that RxEval is both challenging and discriminative: F1 ranges from 45.18 to 77.10 across models, and the best Exact Match is only 46.10%. Error analysis reveals that even frontier models may overlook stated patient information and fail to derive clinical conclusions.

---

### Ottilie: A Socially Intelligent Virtual Host for Sales-Driven Live Commerce

Authors: Yuyan Chen
Published: 2026-05-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.14542v2

A skilled live-commerce host is not merely a narrator, but a sales agent who converts viewer curiosity into purchase intent through expert product knowledge, emotionally intelligent response tactics, and entertainment that serves as a vehicle for product exposure. Yet no existing AI system replicates this. Conversational recommenders treat recommendation as a terminal act, while general-purpose LLMs hallucinate product claims and default to generic promotional templates that fail to engage or persuade. We present Ottilie, a sales-conversion-oriented virtual host for Chinese beauty live commerce that grounds product responses in a verified knowledge base, adapts discourse strategy to viewer intent through empathetic amplification, evidence-backed rebuttal, and humor-mediated deflection, and supervises all four output fields simultaneously within a structured generation framework. Experiments demonstrate gains of 14% on informativeness and 5% on factual correctness, with consistent advantages in tactfulness and viewer engagement. Ottilie has been deployed as an autonomous English-language host on Twitch, where the same fine-tuned model runs unattended on a single commodity GPU and promotes the company's own product; we report how the system adapted to a new language, market, and product without retraining, and what the deployment revealed about latency and adversarial chat.

---

### VerbalValue: A Socially Intelligent Virtual Host for Sales-Driven Live Commerce

Authors: Yuyan Chen
Published: 2026-05-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.14542v1

A skilled live-commerce host is not merely a narrator, but a sales agent who converts viewer curiosity into purchase intent through expert product knowledge, emotionally intelligent response tactics, and entertainment that serves as a vehicle for product exposure. Yet no existing AI system replicates this: conversational recommenders treat recommendation as a terminal act, while general-purpose LLMs hallucinate product claims and default to generic promotional templates that fail to engage or persuade. We present VerbalValue, a sales-conversion-oriented virtual host that turns exceptional verbal ability into real commercial value, built on three contributions. First, we construct a domain knowledge base of product specifications and a curated sales terminology lexicon that anchor product-related responses in verified expertise. Second, we collect and annotate 1,475 live-commerce interactions spanning diverse viewer intents. Third, we fine-tune a large language model on this data to deliver empathetic, commercially oriented responses, adapting to viewer intent through empathetic amplification, evidence-backed rebuttal, and humor-mediated deflection. Experiments against GPT-5.4, Claude Sonnet 4.6, Gemini 3.1 Pro, and other baselines demonstrate gains of 23% on informativeness and 18% on factual correctness, with consistent advantages in tactfulness and viewer engagement.

---

### Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards

Authors: Mengjie Ren, Jie Lou, Boxi Cao, Xueru Wen, Hongyu Lin, Xianpei Han, Le Sun, Xing Yu, Yaojie Lu
Published: 2026-05-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.14539v1

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models. However, RLVR training is often hindered by sparse binary rewards and weak credit assignment, resulting in ambiguous optimization signals and underutilization of the useful information embedded in failed trajectories. To address this challenge, we propose Correction-Oriented Policy Optimization (CIPO), a simple and effective extension to RLVR that converts on-policy failed trajectories into correction-oriented supervision, without relying on any external signals. By jointly optimizing correction samples derived from the model's own failed attempts together with the standard RLVR objective, CIPO improves learning effectiveness while explicitly enhancing the model's ability to correct its own errors. Extensive experiments across 11 benchmarks spanning mathematical reasoning and code generation demonstrate that CIPO consistently and significantly outperforms strong baselines in both reasoning and correction performance. Moreover, CIPO yields stronger pass@K gains, indicating that it improves the model's intrinsic reasoning capacity rather than merely redistributing probability mass over existing correct answers.

---

### Cattle Trade: A Multi-Agent Benchmark for LLM Bluffing, Bidding, and Bargaining

Authors: Robert Müller, Clemens Müller
Published: 2026-05-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.14537v1

We introduce \textsc{Cattle Trade, a multi-agent benchmark for evaluating large language models (LLMs) as agents in strategic reasoning under imperfect information, adversarial interaction, and resource constraints. The benchmark combines auctions, hidden-offer trade challenges (TCs), bargaining, bluffing, opponent modeling, and resource allocation within a single long-horizon game lasting 50--60 turns. Unlike prior agent benchmarks that test these abilities in isolation, \textsc{Cattle Trade} evaluates whether agents integrate them across a competitive, multi-agent economic game with conflicting incentives. The benchmark logs every bid, TC offer, counteroffer, and card selection, enabling behavioural analysis beyond final scores or win rates. We evaluate seven cost-efficient language models and three deterministic code agents across 242 games. Strategic coherence, in particular spending efficiency, resource discipline, and phase-adaptive bidding, is associated with rank more strongly than spending volume or any single subskill. Two heuristic code agents outperform most tested LLMs, and behavioural traces surface recurring LLM failure modes including overbidding, self-bidding, bankrupt TC initiation, and weak opponent-state adaptation. Evaluating agentic competence requires benchmarks that test the joint deployment of multiple capabilities in multi-agent environments with conflicting incentives, uncertainty, and economic dynamics.

---

### Exploring Geographic Relative Space in Large Language Models through Activation Patching

Authors: Stef De Sabbata, Rahul Baiju, Stefano Mizzaro, Kevin Roitero
Published: 2026-05-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.14535v1

The increased use of Large Language Models (LLMs) in geography raises substantial questions about the safety of integrating these tools across a wide range of processes and analyses, given our very limited understanding of their inner workings. In this extended abstract, we examine how LLMs process relative geographic space using activation patching, an emerging tool for mechanistic interpretability.

---

### PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media

Authors: Fuhao Li, Shaofeng You, Jiagao Hu, Yu Liu, Yuxuan Chen, Zepeng Wang, Fei Wang, Daiguo Zhou, Jian Luan
Published: 2026-05-14
Categories: cs.CV, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2605.14534v2

Evaluating object removal in images and videos remains challenging because the task is inherently one-to-many, yet existing metrics frequently disagree with human perception. Full-reference metrics reward copy-paste behaviors over genuine erasure; no-reference metrics suffer from systematic biases such as favoring blurry results; and global temporal metrics are insensitive to localized artifacts within edited regions. To address these limitations, we propose RC (Removal Coherence), a pair of perception-aligned metrics: RC-S, which measures spatial coherence via sliding-window feature comparison between masked and background regions, and RC-T, which measures temporal consistency via distribution tracking within shared restored regions across adjacent frames. To validate RC and support community benchmarking, we further introduce PROVE-Bench, a two-tier real-world benchmark comprising PROVE-M, an 80-video paired dataset with motion augmentation, and PROVE-H, a 100-video challenging subset without ground truth. Together, RC metrics and PROVE-Bench form the PROVE (Perceptual RemOVal cohErence) evaluation framework for visual media. Experiments across diverse image and video benchmarks demonstrate that RC achieves substantially stronger alignment with human judgments than existing evaluation protocols. Project page: https://xiaomi-research.github.io/prove/.

---

### Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space

Authors: ZiYi Dong, Yuliang Huang, Weijian Deng, Xiangyang Ji, Liang Lin, Pengxu Wei
Published: 2026-05-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.14531v3

This work reformulates language generation as a stochastic optimal control problem, providing a unified theoretical perspective to analyze autoregressive and diffusion models and explain their limitations (Efficiency-Fidelity Paradox, Irreversibility Error Propagation, Optimization Tractability and Fidelity) in terms of combination of trajectory singularity, adjoint state vanishing, and gradient absence. To address these issues, we approximate the solution to the Hamilton-Jacobi-Bellman (HJB) equation, yielding an optimal policy that acts as a closed-loop controller. To bypass the intractability of directly solving the HJB PDE, we employ Flow Matching as the optimal trajectory solver within the rectified latent control space. This allows our Manta-LM with Global Integral Operator to approximate the global vector field, effectively realizing a model that simultaneously achieves high-fidelity text generation and efficient, low-cost parallel sampling. Empirically, our method achieves strong performance on language modeling and conditional generation tasks, while exhibiting improved stability, efficiency, and controllability.

---

### Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language Models

Authors: Sujung Hong, Chanyong Yoon, Seong Jae Hwang
Published: 2026-05-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.14530v2

Large diffusion vision-language models (LDVLMs) have recently emerged as a promising alternative to autoregressive models, enabling parallel decoding for efficient inference and leveraging bidirectional attention for global context. Despite these advances, their behavior under long-form generation remains underexplored. In this work, we show that existing LDVLMs suffer from repetitive generation and degraded visual grounding, and identify two underlying causes. First, repetitive generation originates from a mask token prior: since generation tokens are initialized as mask tokens, their hidden representations progressively drift toward a shared prior direction over generation steps. Second, a fundamental misalignment between the positional attention bias and the iterative unmasking process suppresses attention toward informative visual tokens, degrading visual grounding. Based on these insights, we propose a training-free approach, introducing Mask Prior Suppression and Monotonic RoPE Scaling to mitigate mask prior drift and positional attention collapse during decoding. Experiments on general multimodal benchmarks and visual grounding tasks demonstrate improvements over baseline LDVLMs, with robust gains on long-form description benchmarks. Our results show that these failures can be effectively addressed with a lightweight, plug-and-play strategy that requires no additional training and generalizes across diverse LDVLM architectures.

---

### Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflows

Authors: Wenwen Li, Yuki Orimo, Nontawat Charoenphakdee
Published: 2026-05-14
Categories: cs.LG, cond-mat.mtrl-sci, physics.comp-ph
arXiv: https://arxiv.org/abs/2605.14527v1

Developing machine learning interatomic potentials (MLIPs) for complex materials systems remains challenging because it requires expertise in atomistic simulations, machine learning, and workflow design, as well as iterative active learning procedures. Existing automated pipelines typically assume a fixed sequence of stages or depend on domain experts, which limits their adaptability to heterogeneous materials systems where the optimal curriculum is not known in advance. To lower the barrier to developing MLIPs for non-experts, we propose Lang2MLIP, a multi-agent framework that takes natural-language input and formulates end-to-end MLIP development as a sequential decision-making problem solved by large language models (LLMs). At each step, a decision-making agent observes the current dataset, model, evaluation results, and execution log, and then automatically selects an appropriate action to improve the model. This removes the need for a predefined pipeline and enables the agent to self-correct by revisiting earlier subsystems when new failures arise. We evaluate this approach on a solid electrolyte interphase (SEI) system with multiple components and interfaces. These results suggest that LLM-based multi-agent systems are a promising direction for automating MLIP development and making it more accessible to non-experts.

---

### From Sparse to Dense: Spatio-Temporal Fusion for Multi-View 3D Human Pose Estimation with DenseWarper

Authors: Ling Li, Changjie Chen, Yuyan Wang, Jiaqing Lyu, Kenglun Chang, Yiyun Chen, Zhidong Deng
Published: 2026-05-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.14525v1

In multi-view 3D human pose estimation, models typically rely on images captured simultaneously from different camera views to predict a pose at a specific moment. While providing accurate spatial information, this traditional approach often overlooks the rich temporal dependencies between adjacent frames. We propose a novel 3D human pose estimation input method: the sparse interleaved input to address this. This method leverages images captured from different camera views at various time points (e.g., View 1 at time $t$ and View 2 at time $t+δ$), allowing our model to capture rich spatio-temporal information and effectively boost performance. More importantly, this approach offers two key advantages: First, it can theoretically increase the output pose frame rate by N times with N cameras, thereby breaking through single-view frame rate limitations and enhancing the temporal resolution of the production. Second, using a sparse subset of available frames, our method can reduce data redundancy and simultaneously achieve better performance. We introduce the DenseWarper model, which leverages epipolar geometry for efficient spatio-temporal heatmap exchange. We conducted extensive experiments on the Human3.6M and MPI-INF-3DHP datasets. Results demonstrate that our method, utilizing only sparse interleaved images as input, outperforms traditional dense multi-view input approaches and achieves state-of-the-art performance. The source code for this work is available at: https://github.com/lingli1724/DenseWarper-ICLR2026

---

### Large Dimensional Kernel Ridge Regression: Extending to Product Kernels

Authors: Yang Zhou, Yicheng Li, Yuqian Cheng, Qian Lin
Published: 2026-05-14
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2605.14524v1

Recent studies have reported $\textit{saturation effects}$ and $\textit{multiple descent behavior}$ in large dimensional kernel ridge regression (KRR). However, these findings are predominantly derived under restrictive settings, such as inner product kernels on sphere or strong eigenfunction assumptions like hypercontractivity. Whether such behaviors hold for other kernels remains an open question. In this paper, we establish a broad, new family of large dimensional kernels and derive the corresponding convergence rates of the generalization error. As a result, we recover key phenomena previously associated with inner product kernels on sphere, including: $i)$ the $\textit{minimax optimality}$ when the source condition $s\le 1$; $ii)$ the $\textit{saturation effect}$ when $s>1$; $iii)$ a $\textit{periodic plateau phenomenon}$ in the convergence rate and a $\textit {multiple-descent behavior}$ with respect to the sample size $n$.

---

### Enjoy Your Layer Normalization with the Computational Efficiency of RMSNorm

Authors: Yuxin Guo, Yihao Yue, Yunhao Ni, Yizhou Ruan, Jie Luo, Wenjun Wu, Lei Huang
Published: 2026-05-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.14521v1

Layer normalization (LN) is a fundamental component in modern deep learning, but its per-sample centering and scaling introduce non-negligible inference overhead. RMSNorm improves efficiency by removing the centering operation, yet this may discard benefits associated with centering. This paper propose a framework to determine whether an LN in an arbitrary DNN can be replaced by RMSNorm without changing the model function. The key idea is to fold LN's centering operation into upstream general linear layers by enforcing zero-mean outputs through the column-centered constraint (CCC) and column-based weight centering (CBWC). We extend the analysis to arbitrary DNNs, define such LNs as foldable LNs, and develop a graph-based detection algorithm. Our analysis shows that many LNs in widely used architectures are foldable, enabling exact inference-time conversion and end-to-end acceleration of 2% to 12% without changing model predictions. Experiments across multiple task families further show that, when exact equivalence is partially broken in practical training settings, our method remains competitive with vanilla LN while improving efficiency.

---

### ArcGate: Adaptive Arctangent Gated Activation

Authors: Avik Bhattacharya, Siddhant Dnyanesh Gole, Subhasis Chaudhuri, Alejandro C. Frery, Biplab Banerjee
Published: 2026-05-14
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.14518v1

Activation functions are central to deep networks, influencing non-linearity, feature learning, convergence, and robustness. This paper proposes the Adaptive Arctangent Gated Activation (ArcGate) function, a flexible formulation that generates a broad spectrum of activation shapes via a three-stage non-linear transformation. Unlike conventional fixed-shape activations such as ReLU, GELU, or SiLU, ArcGate uses seven learnable parameters per layer, allowing the neural network to autonomously optimize its non-linearity to the specific requirements of the feature hierarchy and data distribution. We evaluate ArcGate using ResNet-50 and Vision Transformer (ViT-B/16) architectures on three widely used remote sensing benchmarks: PatternNet, UC Merced Land Use, and the 13-band EuroSAT MSI multispectral dataset. Experimental results show that ArcGate consistently outperforms standard baselines, achieving a peak overall accuracy of 99.67% on PatternNet. Most notably, ArcGate exhibits superior structural resilience in noisy environments, maintaining a 26.65% performance lead over ReLU under moderate Gaussian noise (standard deviation 0.1). Analysis of the learned parameters reveals a depth-dependent functional evolution, where the model increases gating strength in deeper layers to enhance signal propagation. These findings suggest that ArcGate is a robust and adaptive general node activation function for high-resolution earth observation tasks.

---

### Dimension-Level Intent Fidelity Evaluation for Large Language Models: Evidence from Structured Prompt Ablation

Authors: GAng Peng
Published: 2026-05-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.14517v1

Holistic evaluation scores capture overall output quality but do not distinguish whether a model reproduced the structural form of a user's request from whether it preserved the user's specific intent. We propose a dimension-level intent fidelity evaluation framework, applied here through a structured prompt ablation study across 2,880 outputs spanning three languages, three task domains, and six LLMs, that separately measures structural recovery and intent fidelity for each semantic dimension. This framework reveals a systematic structural-fidelity split: among Chinese-language outputs with complete paired scores, 25.7% received perfect holistic alignment scores (GA=5) while exhibiting measurable dimensional intent deficits; among English-language outputs, this proportion rose to 58.6%. Human evaluation confirmed that these split-zone outputs represent genuine quality deficits and that dimensional fidelity scores track human judgements more reliably than holistic scores do. A public-private decomposition of 2,520 ablation cells characterises when models successfully compensate for missing intent and when they fail, while proxy annotation distinguishes prior inferability from default recoverability. A weight-perturbation experiment shows that moderate misalignment is typically absorbed, whereas severe dimensional inversion is consistently harmful. These findings demonstrate that dimension-level intent fidelity evaluation is a necessary complement to holistic assessment when evaluating LLM outputs for user-specific tasks.

---

### HEART: Exploiting Head Heterogeneity in Sparse Attention for Video Diffusion

Authors: Xuzhe Zheng, Yuexiao Ma, Jing Xu, Xiawu Zheng, Rongrong Ji, Fei Chao
Published: 2026-05-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.14513v2

Sparse attention accelerates video diffusion by allowing each attention head to focus on only a small subset of interactions. Existing methods already construct head-specific sparse patterns conditioned on the input. However, we find that these heads also differ in two less obvious but practically important ways. First, for some heads, sparse attention masks remain stable across many denoising steps, whereas others change rapidly. Second, heads differ substantially in their sensitivity to sparsification: applying the same threshold can induce markedly different errors in the final denoising velocity. Ignoring these differences leads to redundant mask prediction and suboptimal threshold calibration across heads under a global sparsity budget. We present HEART, short for Heterogeneity-Exploiting Adaptive Refresh and Thresholding, a training-free framework that exploits both forms of head heterogeneity. First, Temporal Mask Reuse (TMR) uses a lightweight per-head query-key drift signal to determine whether a cached sparse mask remains reliable across denoising steps, refreshing it only when the drift exceeds a prescribed threshold. Second, Error-guided Budgeted Calibration (EBC) evaluates candidate thresholds offline using a frequency-weighted denoising-velocity error, and assigns each head an appropriate threshold under a global sparsity budget. HEART requires no retraining, weight modification, or sparse-kernel changes, and can be integrated directly into existing sparse-attention pipelines. Across Wan2.1-1.3B, Wan2.1-14B, and HunyuanVideo-13B, HEART consistently pushes the quality--efficiency frontier of advanced sparse attention methods such as XAttention and SVG2 outward.

---

### HASTE: Training-Free Video Diffusion Acceleration via Head-Wise Adaptive Sparse Attention

Authors: Xuzhe Zheng, Yuexiao Ma, Jing Xu, Xiawu Zheng, Rongrong Ji, Fei Chao
Published: 2026-05-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.14513v1

Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the quadratic complexity of full attention. Training-free sparse attention is attractive because it accelerates pretrained models without retraining, yet existing online top-$p$ sparse attention still spends non-negligible cost on mask prediction and applies shared thresholds despite strong head-level heterogeneity. We show that these two overlooked factors limit the practical speed-quality trade-off of training-free sparse attention in Video DiTs. To address them, we introduce a head-wise adaptive framework with two plug-in components: Temporal Mask Reuse, which skips unnecessary mask prediction based on query-key drift, and Error-guided Budgeted Calibration, which assigns per-head top-$p$ thresholds by minimizing measured model-output error under a global sparsity budget. On Wan2.1-1.3B and Wan2.1-14B, our method consistently improves XAttention and SVG2, achieving up to 1.93 times speedup at 720P while maintaining competitive video quality and similarity metrics.

---

### Asymmetric Generative Recommendation via Kronecker Residual Bridge and Multi-Faceted Hierarchical Quantization

Authors: Bin Huang, Xin Wang, Junwei Pan, Yongqi Zhou, Yifeng Zhou, Zhixiang Feng, Shudong Huang, Haijie Gu, Wenwu Zhu
Published: 2026-05-14
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2605.14512v2

Generative Recommendation (GenRec) models reformulate recommendation as a sequence generation task, representing items as discrete Semantic IDs used symmetrically as both inputs and prediction targets. We identify a critical dual-stage information bottleneck in this design: (1) the Input Bottleneck, where lossy quantization degrades fine-grained semantics, while popularity bias skews learned representations toward frequent items, and (2) the Output Bottleneck, where imprecise discrete targets limit supervision quality. To address these issues, we propose AsymRec, an asymmetric continuous-discrete framework that decouples input and output representations. Specifically, Kronecker Residual Bridge (KRB) maps continuous embeddings into the Transformer's hidden space via a Kronecker projection with a residual pathway, preserving semantic richness and improving generalization to infrequent items. Multi-faceted Hierarchical Quantization (MHQ) constructs high-capacity, structured discrete targets through multi-view and multi-level quantization with semantic regularization, preventing dimensional collapse while retaining fine-grained distinctions. Extensive experiments demonstrate that AsymRec consistently outperforms state-of-the-art generative recommenders by an average of 18.7%. Our project page is available at https://github.com/huangb23/AsymRec.

---

### When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution

Authors: Zilin Zhu, Longteng Guo, Yanghong Mei, Bowen Pang, Zongxun Zhang, Xingjian He, Ruyi Ji, Jing Liu
Published: 2026-05-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.14504v2

Long-horizon household tasks demand robust high-level planning and sustained reasoning capabilities, which are largely overlooked by existing embodied AI benchmarks that emphasize short-horizon navigation or manipulation and rely on fixed task categories. We introduce LongAct, a benchmark designed to evaluate planning-level autonomy in long-horizon household tasks specified through free-form instructions. By abstracting away embodiment-specific low-level control, LongAct isolates high-level cognitive capabilities such as instruction understanding, dependency management, memory maintenance, and adaptive planning. We further propose HoloMind, a VLM-driven agent with a DAG-based long-horizon hierarchical planner, a Multimodal Spatial Memory for persistent world modeling, an Episodic Memory for experience reuse, and a global Critic for reflective supervision. Experiments with GPT-5 and Qwen3-VL models show that HoloMind substantially improves long-horizon performance while reducing reliance on model scale. Even top models achieve only 59% goal completion and 16% full-task success, underscoring the difficulty of LongAct and the need for stronger long-horizon planning in embodied agents.

---

### Quantifying Cyber-Vulnerability in Power Electronics Systems via an Impedance-Based Attack Reachable Domain

Authors: Hongwei Zhen, Ze Yu, Xin Xiang, Wuhua Li, Mingyang Sun
Published: 2026-05-14
Categories: eess.SY, cs.AI
arXiv: https://arxiv.org/abs/2605.14502v1

Power electronics systems are increasingly exposed to cyber threats due to their integration with digital controllers and communication networks. However, an attacker-oriented metric is still lacking to quantify the extent to which a node can be pushed toward instability within a privilege-constrained action space. This letter proposes an impedance-based Attack Reachable Domain (ARD) framework that maps feasible adversarial actions to critical-eigenvalue migration through impedance reshaping. Based on the ARD, an Attack Penetration Index is defined to quantify node-level cyber-vulnerability by jointly characterizing the penetration of the nominal stability margin and the accessibility of successful destabilizing attacks within a privilege-constrained action space. To make the proposed assessment computable when inverter models are unavailable, a practical gray-box workflow is further established by integrating existing impedance identification and differentiable surrogate tools. Case studies on a 4-bus system and a modified IEEE 39-bus system show that coordinated cross-layer manipulations are markedly more damaging than isolated single-layer attacks, and that the proposed metric reveals vulnerability patterns that cannot be inferred from grid-strength indicators.

---

### Fully Dynamic Rebalancing in Dockless Bike-Sharing Systems via Deep Reinforcement Learning

Authors: Edoardo Scarpel, Alberto Pettena, Matteo Cederle, Federico Chiariotti, Marco Fabris, Gian Antonio Susto
Published: 2026-05-14
Categories: eess.SY, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.14501v1

This paper proposes a fully dynamic Deep Reinforcement Learning (DRL) method for rebalancing dockless bike-sharing systems, overcoming the limitations of periodic, system-wide interventions. We model the service through a graph-based simulator and cast rebalancing as a Markov decision process. A DRL agent routes a single truck in real time, executing localized pick-up, drop-off, and charging actions guided by spatiotemporal criticality scores. Experiments on real-world data show significant reductions in availability failures with a minimal fleet size, while limiting spatial inequality and mobility deserts. Our approach demonstrates the value of learning-based rebalancing for efficient and reliable shared micromobility.

---

### GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations

Authors: Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang, Shiyu Chang, Yaar Harari, Evgeniy Gabrilovich
Published: 2026-05-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.14498v2

Large Language Model (LLM) agents increasingly serve as personal assistants and workplace collaborators, where their utility depends on memory systems that extract, retrieve, and apply information across long-running conversations. However, both existing memory systems and benchmarks are built around the dyadic, single-user setup, even though real deployments routinely span groups and channels with multiple users interacting with the agent and with each other. This mismatch leaves three properties of group memory unmeasured: (i) group dynamics that go beyond concatenated one-on-one chats, (ii) speaker-grounded belief tracking, where the per-user memory modeling is needed, and (iii) audience-adapted language, where Theory-of-Mind shifts produce role-specific vocabulary. We introduce GroupMemBench, a benchmark that exposes all three. A graph-grounded synthesis pipeline produces multi-party conversations with controllable reply structure and conditions each message on per-user personas and target audiences. An adversarial query pipeline then binds every question to a specific asker across six categories, spanning multi-hop reasoning, knowledge update, term ambiguity, user-implicit reasoning, temporal reasoning, and abstention, and iteratively searches challenging, realistic queries that reflect comprehensive memory capability. Benchmarking leading memory systems exposes a sharp collapse: the strongest one reaches only 46.0% average accuracy, with knowledge update at 27.1% and term ambiguity at 37.7%, while a simple BM25 baseline matches or exceeds most agent memory systems. This indicates current memory ingestion erases the structural and lexical features group memory depends on, leaving multi-user memory far from solved.

---

### ROAD: Adaptive Data Mixing for Offline-to-Online Reinforcement Learning via Bi-Level Optimization

Authors: Letian Yang, Xu Liu, Yiqiang Lu, Jian Liu, Weiqiang Wang, Shuai Li
Published: 2026-05-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.14497v1

Offline-to-online reinforcement learning harnesses the stability of offline pretraining and the flexibility of online fine-tuning. A key challenge lies in the non-stationary distribution shift between offline datasets and the evolving online policy. Common approaches often rely on static mixing ratios or heuristic-based replay strategies, which lack adaptability to different environments and varying training dynamics, resulting in suboptimal tradeoff between stability and asymptotic performance. In this work, we propose Reinforcement Learning with Optimized Adaptive Data-mixing (ROAD), a dynamic plug-and-play framework that automates the data replay process. We identify a fundamental objective misalignment in existing approaches. To tackle this, we formulate the data selection problem as a bi-level optimization process, interpreting the data mixing strategy as a meta-decision governing the policy performance (outer-level) during online fine-tuning, while the conventional Q-learning updates operate at the inner level. To make it tractable, we propose a practical algorithm using a multi-armed bandit mechanism. This is guided by a surrogate objective approximating the bi-level gradient, which simultaneously maintains offline priors and prevents value overestimation. Our empirical results demonstrate that this approach consistently outperforms existing data replay methods across various datasets, eliminating the need for manual, context-specific adjustments while achieving superior stability and asymptotic performance.

---

### Contestable Multi-Agent Debate with Arena-based Argumentative Computation for Multimedia Verification

Authors: Truong Thanh Hung Nguyen, Vo Thanh Khang Nguyen, Hoang-Loc Cao, Phuc Ho, Van Pham, Hung Cao
Published: 2026-05-14
Categories: cs.MM, cs.AI
arXiv: https://arxiv.org/abs/2605.14495v1

Multimedia verification requires not only accurate conclusions but also transparent and contestable reasoning. We propose a contestable multi-agent framework that integrates multimodal large language models, external verification tools, and arena-based quantitative bipolar argumentation (A-QBAF) as a submission to the ICMR 2026 Grand Challenge on Multimedia Verification. Our method decomposes each case into claim-centered sections, retrieves targeted evidence, and converts evidence into structured support and attack arguments with provenance and strength scores. These arguments are resolved through small local argument graphs with selective clash resolution and uncertainty-aware escalation. The resulting system generates section-wise verification reports that are transparent, editable, and computationally practical for real-world multimedia verification. Our implementation is public at: https://github.com/Analytics-Everywhere-Lab/MV2026_the_liems.

---

### Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty

Authors: Tianjue Lin, Jianan Zhou, Jieyi Bi, Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang
Published: 2026-05-14
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.14494v1

Two-Stage Robust Optimization (2RO) with discrete uncertainty is challenging, often rendering exact solutions prohibitive. Scenario reduction alleviates this issue by selecting a small, representative subset of scenarios to enable tractable computation. However, existing methods are largely problem-agnostic, operating solely on the uncertainty set without consulting the feasible region or recourse structure. In this paper, we introduce PRISE, a problem-driven sequential lookahead heuristic that constructs reduced scenario sets by evaluating the marginal impact of each scenario. While PRISE yields high-quality scenario subsets, each selection step requires solving multiple subproblems, making it computationally expensive at scale. To address this, we propose NeurPRISE, a neural surrogate model built on a GNN-Transformer backbone that encodes the per-scenario structure via graph convolution and captures cross-scenario interactions through attention. NeurPRISE is trained via imitation learning with a gain-aware ranking objective, which distills marginal gain information from PRISE into a learned scoring function for scenario ranking and selection. Extensive results on three 2RO problems show that NeurPRISE consistently achieves competitive regret relative to comprehensive methods, maintains strong calability with varying numbers of scenarios, and delivers 7-200x speedup over PRISE. NeurPRISE also exhibits strong zero-shot generalization, effectively handling instances with larger problem scales (up to 5x), more scenarios (up to 4x), and distribution shifts.

---

### A Novel Schur-Decomposition-Based Weight Projection Method for Stable State-Space Neural-Network Architectures

Authors: Sergio Vanegas, Lasse Lensu, Fredy Ruiz
Published: 2026-05-14
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2605.14489v1

Building black-box models for dynamical systems from data is a challenging problem in machine learning, especially when asymptotic stability guarantees are required. In this paper, we introduce a novel stability-ensuring and backpropagation-compatible projection scheme based on the Schur decomposition for the state matrix of linear discrete-time state-space layers, as well as an alternative pre-factorized formulation of the methodology. The proposed methods dynamically project the quasi-triangular factor of the state matrix's real Schur decomposition onto its nearest stable peer, ensuring stable dynamics with minimal overparameterization. Experiments on synthetic linear systems demonstrate that the method achieves accuracy and convergence rates comparable to those of state-of-the-art stable-system identification techniques, despite a marginal increase in computational complexity. Furthermore, the lower weight count facilitates convergence during training without sacrificing accuracy in stacked neural-network architectures with static nonlinearities targeting real-world datasets. These results suggest that the Schur-based projection provides a numerically robust framework for identifying complex dynamics on par with the State of the Art while satisfying strict asymptotic-stability requirements.

---

### Deepchecks: Evaluating Retrieval-Augmented Generation (RAG)

Authors: Assaf Gerner, Netta Madvil, Nadav Barak, Alex Zaikman, Jonatan Liberman, Liron Hamra, Rotem Brazilay, Shay Tsadok, Yaron Friedman, Neal Harow, Noam Bresler, Shir Chorev et al.
Published: 2026-05-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.14488v1

Large Language Models (LLMs) augmented with Retrieval-Augmented Generation (RAG) techniques are revolutionizing applications across multiple domains, such as healthcare, finance, and customer service. Despite their potential, evaluating RAG systems remains a complex challenge due to the stochastic nature of generated outputs and the intricate interplay between retrieval and generation components. This paper introduces Deepchecks, a comprehensive framework tailored for evaluating RAG applications. Deepchecks' evaluation framework addresses RAG applications evaluation through a multi-faceted approach, root cause analysis and production monitoring. By ensuring alignment with application-specific requirements, Deepchecks framework provides a robust foundation for assessing reliability, relevance, and user satisfaction in RAG systems.

---

### Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity

Authors: Jiahao Tian, Yiwei Wang, Gang Yu, Chi Zhang
Published: 2026-05-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.14487v1

Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve functionally distinct roles as local heads for detail refinement, anchor heads for structural stabilization, and memory heads for long-range context aggregation, yet existing methods treat them uniformly, leading to suboptimal KV cache allocation. We propose Head Forcing, a training-free framework that assigns each head type a tailored KV cache strategy: local and anchor heads retain only essential tokens, while memory heads employ a hierarchical memory system with dynamic episodic updates for long-range consistency. A head-wise RoPE re-encoding scheme further ensures positional encodings remain within the pretrained range. Without additional training, Head Forcing extends generation from 5 seconds to minute-level duration, supports multi-prompt interactive synthesis, and consistently outperforms existing baselines. Project Page: https://jiahaotian-sjtu.github.io/headforcing.github.io/.

---

### Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection

Authors: Yiheng Li, Yang Yang, Wenhao Wang, Zichang Tan, Zecheng Lin, Li Gao, Zhen Lei
Published: 2026-05-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.14486v2

As the misuse of AI-generated images grows, generalizable image detection techniques are urgently needed. Recent state-of-the-art (SOTA) methods adopt aligned training datasets to reduce content, size, and format biases, empowering models to capture robust forgery cues. A common strategy employs reconstruction techniques, e.g., VAE and DDIM, to construct aligned synthetic negatives. However, relying on a single reconstruction process yields a narrow and homogeneous artifact distribution, leaving forensic traces from other artifact-forming mechanisms underrepresented. To broaden artifact coverage without sacrificing alignment, we construct adversarial restoration-based negatives with SRGAN, whose learned upsampling and texture restoration yield traces complementary to VAE reconstruction while preserving content, size, and format. Directly mixing the two aligned fake domains is nontrivial because their artifact manifolds and optimization directions can conflict. We therefore propose Artifact-Complementary Expert Fusion (ACEF), a two-stage framework for robust AIGC detection. ACEF first constructs two artifact-specific experts via LoRA adaptation on a frozen foundation backbone. It then freezes them and introduces Layer-wise Artifact-Complementary Fusion (LACF) to integrate multi-layer source-specific and cross-artifact evidence through an adaptive gate. Extensive experiments on 13 diverse benchmarks demonstrate the effectiveness of our method.

---

### Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection

Authors: Yiheng Li, Yang Yang, Zichang Tan, Gao Li, Zhen Lei, Wenhao Wang
Published: 2026-05-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.14486v1

As the misuse of AI-generated images grows, generalizable image detection techniques are urgently needed. Recent state-of-the-art (SOTA) methods adopt aligned training datasets to reduce content, size, and format biases, empowering models to capture robust forgery cues. A common strategy is to employ reconstruction techniques, e.g., VAE and DDIM, which show remarkable results in diffusion-based methods. However, such reconstruction-based approaches typically introduce limited and homogeneous artifacts, which cannot fully capture diverse generative patterns, such as GAN-based methods. To complement reconstruction-based fake images with aligned yet diverse artifact patterns, we propose a GAN-based upsampling approach that mimics GAN-generated fake patterns while preserving content, size, and format alignment. This naturally results in two aligned but distinct types of fake images. However, due to the domain shift between reconstruction-based and upsampling-based fake images, direct mixed training causes suboptimal results, where one domain disrupts feature learning of the other. Accordingly, we propose a Separate Expert Fusion (SEF) framework to extract complementary artifact information and reduce inter-domain interference. We first train domain-specific experts via LoRA adaptation on a frozen foundational model, then conduct decoupled fusion with a gating network to adaptively combine expert features while retaining their specialized knowledge. Rather than merely benefiting GAN-generated image detection, this design introduces diverse and complementary artifact patterns that enable SEF to learn a more robust decision boundary and improve generalization across broader generative methods. Extensive experiments demonstrate that our method yields strong results across 13 diverse benchmarks. Codes are released at: https://github.com/liyih/SEF_AIGC_detection.

---

### LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning

Authors: Xudong Chen, Yixin Liu, Hua Wei, Kaize Ding
Published: 2026-05-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.14483v1

Large language models (LLMs) have become a strong foundation for multi-agent systems, but their effectiveness depends heavily on orchestration design. Across different tasks, role design, capacity assignment, and dependency construction jointly affect both solution quality and execution efficiency. Existing approaches automate parts of this design process, yet they often optimize these decisions partially or sequentially, and rely on execution-level feedback that provides limited credit assignment for local orchestration decisions. We propose LEMON (\textbf{L}earning \textbf{E}xecutable \textbf{M}ulti-agent \textbf{O}rchestratio\textbf{N} via Counterfactual Reinforcement Learning), an LLM-based orchestrator that generates an executable orchestration specification. The specification integrates task-specific roles, customized duties, capacity levels, and dependency structure into a single deployable system. To train the orchestrator, we augment the orchestration-level GRPO objective with a localized counterfactual signal that edits role, capacity, or dependency fields and applies the resulting reward contrast only to the edited spans. Experiments on six reasoning and coding benchmarks, including MMLU, GSM8K, AQuA, MultiArith, SVAMP, and HumanEval, show that LEMON achieves state-of-the-art performance among the evaluated multi-agent orchestration methods. Our code is available at https://anonymous.4open.science/r/LEMON-B23C.

---

### Cross-Linguistic Transcription and Phonological Representation in the Huìtóngguǎnxì Huáyíyìyǔ

Authors: Ji-eun Kim
Published: 2026-05-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.14480v2

Purpose: This study investigates the transcription principles underlying Huìtóngguǎnxì Huáyíyìyǔ (HHY), a series of multilingual glossaries compiled by the Ming government between the fifteenth and sixteenth centuries for interpreter training. The study treats HHY not as a collection of isolated language materials, but as a coherent multilingual transcription system representing spoken forms of non-Chinese languages through Chinese characters. Methods: A substantial portion of HHY was digitized and aligned with Chinese phonological categories. Previous reconstructions of individual language sections were critically reviewed and integrated into a unified comparative database. The analysis focuses on cross-linguistic regularities in Main Transcription (MT) and Supplementary Transcription (ST) across eight language sections. Results: MT generally represents sounds compatible with the Chinese syllable structure of the period, whereas ST mainly encodes phonetic features less compatible with Chinese phonology. The analysis further shows that Chinese phonological categories were used more flexibly in foreign-language transcription than previously assumed. HHY therefore functioned as a relatively systematic method of phonetic approximation rather than a direct projection of Chinese phonology onto non-Chinese languages. Conclusion: HHY can be analyzed as an internally structured transcription system rather than merely as a collection of glossaries. More broadly, the study demonstrates that historical transcription systems can provide valuable evidence for historical phonology, particularly for under-documented Asian languages with limited historical records.

---

### When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context

Authors: Haojun Weng, Qianqian Yang, Hao Fu, Haobin Pan, Xinwei Lv
Published: 2026-05-14
Categories: cs.SE, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.14478v1

Context: Retrieval-augmented code generation relies on cross-file repository context, but retrieved snippets may come from obsolete project states. Objectives: We study whether temporally stale repository snippets act as harmless noise or actively induce current-state-incompatible code. Methods: We conduct a controlled diagnostic study on a curated 17-sample set of production-helper signature changes from five Python repositories. For each sample, we compare current-only, stale-only, no-retrieval, and mixed current/stale retrieval conditions under prompts that hide commit freshness and expected current signatures. Results: Under neutralized prompts, stale-only retrieval induces stale helper references on 15/17 Qwen2.5-Coder-7B-Instruct samples and 13/17 gpt-4.1-mini samples, corresponding to 88.2 and 76.5 percentage-point increases over current-only retrieval. No retrieval produces zero stale references but only 1/17 passing completions. The two models share 75.0% Jaccard overlap among stale-triggering samples, and mixed conditions show that adding valid current evidence largely rescues stale-only failures. Conclusion: Temporal validity of retrieved repository context is a distinct diagnostic variable for Code RAG robustness: stale context can actively bias models toward obsolete repository state rather than merely removing useful evidence.

---

### Test-Time Learning with an Evolving Library

Authors: Weijia Xu, Alessandro Sordoni, Chandan Singh, Zelalem Gero, Michel Galley, Xingdi Yuan, Jianfeng Gao
Published: 2026-05-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.14477v2

We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates or external supervision. Instead of adapting model parameters, our approach maintains a shared library of knowledge abstractions, including modular skills and reflective insights, automatically extracted from the model's own inference trajectories. To support continual improvement, we introduce a principled weighting and consolidation mechanism that jointly optimizes for immediate utility and long-term value. This allows simple, instance-specific abstractions to evolve into more general and reusable ones over time. Across challenging benchmarks in mathematical reasoning, code generation, and multi-turn agentic environments, EvoLib improves substantially over the top test-time scaling and learning methods without ground-truth feedback.

---

### GeoVista: Visually Grounded Active Perception for Vision-Language Understanding of Ultra-High-Resolution Remote Sensing Images

Authors: Jiashun Zhu, Ronghao Fu, Jiasen Hu, Jing Huang, Nachuan Xing, Bo Yang
Published: 2026-05-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.14475v2

Interpreting ultra-high-resolution (UHR) remote sensing images requires models to search for sparse and tiny visual evidence across large-scale scenes. Existing remote sensing vision-language models can inspect local regions with zooming and cropping tools, but most exploration strategies follow either a one-shot focus or a single sequential trajectory. Such single-path exploration can lose global context, leave scattered regions unvisited, and revisit or count the same evidence multiple times. To this end, we propose GeoVista, a planning-driven active perception framework for UHR remote sensing interpretation. Instead of committing to one zooming path, GeoVista first builds a global exploration plan, then verifies multiple candidate regions through branch-wise local inspection, while maintaining an explicit evidence state for cross-region aggregation and de-duplication. To enable this behavior, we introduce APE-GRO, a cold-start supervised trajectory corpus that reformulates diverse UHR tasks as Global-Region-Object interactive reasoning processes with a unified, scale-invariant spatial representation. We further design an Observe-Plan-Track mechanism for global observation, adaptive region inspection, and evidence tracking, and align the model with a GRPO-based strategy using step-wise rewards for planning, localization, and final answer correctness. Experiments on RSHR-Bench, XLRS-Bench, and LRS-VQA show that GeoVista achieves state-of-the-art performance. Code and dataset are available at https://github.com/ryan6073/GeoVista.

---

### Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict

Authors: Yihang Chen, Pin Qian, Su Wang, Sipeng Zhang, Huan Xu, Shuhuai Lin, Xinpeng Wei
Published: 2026-05-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.14473v4

Retrieval-Augmented Generation (RAG) is usually evaluated by whether the final answer is correct. Under knowledge conflict, this hides a key question: did the model follow retrieved evidence, rely on its parametric prior, or produce a post-hoc rationale? We study this as context compliance, the regime in which retrieved context controls the answer even when it conflicts with the model's prior knowledge. We introduce Context-Driven Decomposition (CDD), an inference-time diagnostic intervention that elicits contextual and prior answers, isolates the conflicting premise, and records a resolution trace that can be perturbed. Across Epi-Scale stress tests, TruthfulQA misconception injection, and cross-model reruns, CDD makes three behaviors visible. First, misleading retrieval can severely degrade accuracy: under a worst-case TruthfulQA misconception-injection probe, Standard RAG reaches only 15.0%. Second, better answers need not share the same mechanism: CDD improves adversarial accuracy on Gemini-2.5-Flash and shows directional gains across Claude variants, yet trace-perturbation sensitivity is high only on Gemini. Third, explicit decomposition improves controlled-conflict robustness over a conflict-aware instruction baseline on localized factual conflicts, with the clearest margins on Entity Swap (88.0% vs 79.3%) and Logical Contradiction (83.2% vs 75.4%). We frame RAG conflict handling as an observability problem.

---

### Focused PU learning from imbalanced data

Authors: Elias Zavitsanos, Georgios Paliouras
Published: 2026-05-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.14467v2

We propose a new method of learning from positive and unlabeled (PU) examples in highly imbalanced datasets. Many real-world problems, such as disease gene identification, targeted marketing, fraud detection, and recommender systems, are hard to address with machine learning methods, due to limited labeled data. Often, training data comprises positive and unlabeled instances, the latter typically being dominated by negative, but including also several positive instances. While PU learning is well-studied, few methods address imbalanced settings or hard-to-detect positive examples that resemble negative ones. Our approach uses a focused empirical risk estimator, incorporating both positive and unlabeled examples to train binary classifiers. Empirical evaluations demonstrate state-of-the-art performance on imbalanced datasets under two labeling mechanisms - selecting positives completely at random (SCAR) and selecting at random (SAR). Beyond these controlled experiments, we demonstrate the value of the proposed method in the real-world application of financial misstatement detection.

---

### Focused PU learning from imbalanced data

Authors: Elias Zavitsanos, Georgios Paliouras
Published: 2026-05-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.14467v1

We propose a new method of learning from positive and unlabeled (PU) examples in highly imbalanced datasets. Many real-world problems, such as disease gene identification, targeted marketing, fraud detection, and recommender systems, are hard to address with machine learning methods, due to limited labeled data. Often, training data comprises positive and unlabeled instances, the latter typically being dominated by negative, but including also several positive instances. While PU learning is well-studied, few methods address imbalanced settings or hard-to-detect positive examples that resemble negative ones. Our approach uses a focused empirical risk estimator, incorporating both positive and unlabeled examples to train binary classifiers. Empirical evaluations demonstrate state-of-the-art performance on imbalanced datasets under two labeling mechanisms - selecting positives completely at random (SCAR) and selecting at random (SAR). Beyond these controlled experiments, we demonstrate the value of the proposed method in the real-world application of financial misstatement detection.

---