# Research Papers — 2026-04 · bundle page 115 of 233

> Full-text markdown of papers #5701–5750 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-04/page/115
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/114.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/116.md)

### Training-Free Semantic Multi-Object Tracking with Vision-Language Models

Authors: Laurence Bonat, Francesco Tonini, Elisa Ricci, Lorenzo Vaquero
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.14074v1

Semantic Multi-Object Tracking (SMOT) extends multi-object tracking with semantic outputs such as video summaries, instance-level captions, and interaction labels, aiming to move from trajectories to human-interpretable descriptions of dynamic scenes. Existing SMOT systems are trained end-to-end, coupling progress to expensive supervision, limiting the ability to rapidly adapt to new foundation models and new interactions. We propose TF-SMOT, a training-free SMOT pipeline that composes pretrained components for detection, mask-based tracking, and video-language generation. TF-SMOT combines D-FINE and the promptable SAM2 segmentation tracker to produce temporally consistent tracklets, uses contour grounding to generate video summaries and instance captions with InternVideo2.5, and aligns extracted interaction predicates to BenSMOT WordNet synsets via gloss-based semantic retrieval with LLM disambiguation. On BenSMOT, TF-SMOT achieves state-of-the-art tracking performance within the SMOT setting and improves summary and caption quality compared to prior art. Interaction recognition, however, remains challenging under strict exact-match evaluation on the fine-grained and long-tailed WordNet label space; our analysis and ablations indicate that semantic overlap and label granularity substantially affect measured performance.

---

### Neural architectures for resolving references in program code

Authors: Gergő Szalay, Gergely Zsolt Kovács, Sándor Teleki, Balázs Pintér, Tibor Gregorics
Published: 2026-04-15
Categories: cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2604.14073v1

Resolving and rewriting references is fundamental in programming languages. Motivated by a real-world decompilation task, we abstract reference rewriting into the problems of direct and indirect indexing by permutation. We create synthetic benchmarks for these tasks and show that well-known sequence-to-sequence machine learning architectures are struggling on these benchmarks. We introduce new sequence-to-sequence architectures for both problems. Our measurements show that our architectures outperform the baselines in both robustness and scalability: our models can handle examples that are ten times longer compared to the best baseline. We measure the impact of our architecture in the real-world task of decompiling switch statements, which has an indexing subtask. According to our measurements, the extended model decreases the error rate by 42%. Multiple ablation studies show that all components of our architectures are essential.

---

### Towards Unconstrained Human-Object Interaction

Authors: Francesco Tonini, Alessandro Conti, Lorenzo Vaquero, Cigdem Beyan, Elisa Ricci
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.14069v1

Human-Object Interaction (HOI) detection is a longstanding computer vision problem concerned with predicting the interaction between humans and objects. Current HOI models rely on a vocabulary of interactions at training and inference time, limiting their applicability to static environments. With the advent of Multimodal Large Language Models (MLLMs), it has become feasible to explore more flexible paradigms for interaction recognition. In this work, we revisit HOI detection through the lens of MLLMs and apply them to in-the-wild HOI detection. We define the Unconstrained HOI (U-HOI) task, a novel HOI domain that removes the requirement for a predefined list of interactions at both training and inference. We evaluate a range of MLLMs on this setting and introduce a pipeline that includes test-time inference and language-to-graph conversion to extract structured interactions from free-form text. Our findings highlight the limitations of current HOI detectors and the value of MLLMs for U-HOI. Code will be available at https://github.com/francescotonini/anyhoi

---

### Deep Neural Network-guided PSO for Tracking a Global Optimal Position in Complex Dynamic Environment

Authors: Stephen Raharja, Toshiharu Sugawara
Published: 2026-04-15
Categories: cs.NE
arXiv: https://arxiv.org/abs/2604.14064v1

We propose novel particle swarm optimization (PSO) variants incorporated with deep neural networks (DNNs) for particles to pursue globally optimal positions in dynamic environments. PSO is a heuristic approach for solving complex optimization problems. However, canonical PSO and its variants struggle to adapt efficiently to dynamic environments, in which the global optimum moves over time, and to track them accurately. Many PSO algorithms improve convergence by increasing the swarm size beyond potential optima, which are global/local optima but are not identified until they are discovered. Additionally, in dynamic environments, several methods use multiple sub-population and re-diversification mechanisms to address outdated memory and local optima entrapment. To track the global optimum in dynamic environments with smaller swarm sizes, the DNNs in our methods determine particle movement by learning environmental characteristics and adapting dynamics to pursue moving optimal positions. This enables particles to adapt to environmental changes and predict the moving optima. We propose two variants: a swarm with a centralized network and distributed networks for all particles. Our experimental results show that both variants can track moving potential optima with lower cumulative tracking error than those of several recent PSO-based algorithms, with fewer particles than potential optima.

---

### OneHOI: Unifying Human-Object Interaction Generation and Editing

Authors: Jiun Tian Hoe, Weipeng Hu, Xudong Jiang, Yap-Peng Tan, Chee Seng Chan
Published: 2026-04-15
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2604.14062v1

Human-Object Interaction (HOI) modelling captures how humans act upon and relate to objects, typically expressed as <person, action, object> triplets. Existing approaches split into two disjoint families: HOI generation synthesises scenes from structured triplets and layout, but fails to integrate mixed conditions like HOI and object-only entities; and HOI editing modifies interactions via text, yet struggles to decouple pose from physical contact and scale to multiple interactions. We introduce OneHOI, a unified diffusion transformer framework that consolidates HOI generation and editing into a single conditional denoising process driven by shared structured interaction representations. At its core, the Relational Diffusion Transformer (R-DiT) models verb-mediated relations through role- and instance-aware HOI tokens, layout-based spatial Action Grounding, a Structured HOI Attention to enforce interaction topology, and HOI RoPE to disentangle multi-HOI scenes. Trained jointly with modality dropout on our HOI-Edit-44K, along with HOI and object-centric datasets, OneHOI supports layout-guided, layout-free, arbitrary-mask, and mixed-condition control, achieving state-of-the-art results across both HOI generation and editing. Code is available at https://jiuntian.github.io/OneHOI/.

---

### Two-Sided Bounds for Entropic Optimal Transport via a Rate-Distortion Integral

Authors: Jingbo Liu
Published: 2026-04-15
Categories: cs.IT, math.PR, stat.ML
arXiv: https://arxiv.org/abs/2604.14061v1

We show that the maximum expected inner product between a random vector and the standard normal vector over all couplings subject to a mutual information constraint or regularization is equivalent to a truncated integral involving the rate-distortion function, up to universal multiplicative constants. The proof is based on a lifting technique, which constructs a Gaussian process indexed by a random subset of the type class of the probability distribution involved in the information-theoretic inequality, and then applying a form of the majorizing measure theorem.

---

### A Comparative Study of Dynamic Programming and Reinforcement Learning in Finite Horizon Dynamic Pricing

Authors: Lev Razumovskiy, Nikolay Karenin
Published: 2026-04-15
Categories: econ.GN, cs.LG
arXiv: https://arxiv.org/abs/2604.14059v1

This paper provides a systematic comparison between Fitted Dynamic Programming (DP), where demand is estimated from data, and Reinforcement Learning (RL) methods in finite-horizon dynamic pricing problems. We analyze their performance across environments of increasing structural complexity, ranging from a single typology benchmark to multi-typology settings with heterogeneous demand and inter-temporal revenue constraints. Unlike simplified comparisons that restrict DP to low-dimensional settings, we apply dynamic programming in richer, multi-dimensional environments with multiple product types and constraints. We evaluate revenue performance, stability, constraint satisfaction behavior, and computational scaling, highlighting the trade-offs between explicit expectation-based optimization and trajectory-based learning.

---

### $π$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data

Authors: Yaocheng Zhang, Yuanheng Zhu, Wenyue Chong, Songjun Tu, Qichao Zhang, Jiajun Chai, Xiaohan Wang, Wei Lin, Guojun Yin, Dongbin Zhao
Published: 2026-04-15
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2604.14054v2

Deep search agents have emerged as a promising paradigm for addressing complex information-seeking tasks, but their training remains challenging due to sparse rewards, weak credit assignment, and limited labeled data. Self-play offers a scalable route to reduce data dependence, but conventional self-play optimizes students only through sparse outcome rewards, leading to low learning efficiency. In this work, we observe that self-play naturally produces a question construction path (QCP) during task generation, an intermediate artifact that captures the reverse solution process. This reveals a new source of privileged information: self-play can provide high-quality privileged information for the self-distillation at low cost and at scale, without relying on human feedback or curated privileged information. Leveraging this insight, we propose Privileged Information Self-Play ($π$-Play), a novel multi-agent self-evolution framework combining self-play and self-distillation. In $π$-Play, an examiner generates tasks together with QCPs, and a teacher employs QCP as privileged context to densely supervise a student via self-distillation. This design transforms sparse-reward self-play into a dense-feedback co-evolution. Extensive experiments show that data-free $π$-Play surpasses fully supervised search agents and improves evolutionary efficiency by 2-3$\times$ over conventional self-play. Code is available at https://github.com/zhyaoch/pi-play.

---

### From Where Words Come: Efficient Regularization of Code Tokenizers Through Source Attribution

Authors: Pavel Chizhov, Egor Bogomolov, Ivan P. Yamshchikov
Published: 2026-04-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.14053v1

Efficiency and safety of Large Language Models (LLMs), among other factors, rely on the quality of tokenization. A good tokenizer not only improves inference speed and language understanding but also provides extra defense against jailbreak attacks and lowers the risk of hallucinations. In this work, we investigate the efficiency of code tokenization, in particular from the perspective of data source diversity. We demonstrate that code tokenizers are prone to producing unused, and thus under-trained, tokens due to the imbalance in repository and language diversity in the training data, as well as the dominance of source-specific, repetitive tokens that are often unusable in future inference. By modifying the BPE objective and introducing merge skipping, we implement different techniques under the name Source-Attributed BPE (SA-BPE) to regularize BPE training and minimize overfitting, thereby substantially reducing the number of under-trained tokens while maintaining the same inference procedure as with regular BPE. This provides an effective tool suitable for production use.

---

### Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself

Authors: Yuhang Dai, Xingyi Yang
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.14048v1

Feed-forward 3D reconstruction models are efficient but rigid: once trained, they perform inference in a zero-shot manner and cannot adapt to the test scene. As a result, visually plausible reconstructions often contain errors, particularly under occlusions, specularities, and ambiguous cues. To address this, we introduce Free Geometry, a framework that enables feed-forward 3D reconstruction models to self-evolve at test time without any 3D ground truth. Our key insight is that, when the model receives more views, it produces more reliable and view-consistent reconstructions. Leveraging this property, given a testing sequence, we mask a subset of frames to construct a self-supervised task. Free Geometry enforces cross-view feature consistency between representations from full and partial observations, while maintaining the pairwise relations implied by the held-out frames. This self-supervision allows for fast recalibration via lightweight LoRA updates, taking less than 2 minutes per dataset on a single GPU. Our approach consistently improves state-of-the-art foundation models, including Depth Anything 3 and VGGT, across 4 benchmark datasets, yielding an average improvement of 3.73% in camera pose accuracy and 2.88% in point map prediction. Code is available at https://github.com/hiteacherIamhumble/Free-Geometry .

---

### Decoding the Delta: Unifying Remote Sensing Change Detection and Understanding with Multimodal Large Language Models

Authors: Xiaohe Li, Jiahao Li, Kaixin Zhang, Yuqiang Fang, Leilei Lin, Hong Wang, Haohua Wu, Zide Fan
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.14044v1

While Multimodal Large Language Models (MLLMs) excel in general vision-language tasks, their application to remote sensing change understanding is hindered by a fundamental "temporal blindness". Existing architectures lack intrinsic mechanisms for multi-temporal contrastive reasoning and struggle with precise spatial grounding. To address this, we first introduce Delta-QA, a comprehensive benchmark comprising 180k visual question-answering samples. Delta-QA unifies pixel-level segmentation and visual question answering across bi- and tri-temporal scenarios, structuring change interpretation into four progressive cognitive dimensions. Methodologically, we propose Delta-LLaVA, a novel MLLM framework explicitly tailored for multi-temporal remote sensing interpretation. It overcomes the limitations of naive feature concatenation through three core innovations: a Change-Enhanced Attention module that systematically isolates and amplifies visual differences, a Change-SEG module utilizing Change Prior Embedding to extract differentiable difference features as input for the LLM, and Local Causal Attention to prevent cross-temporal contextual leakage. Extensive experiments demonstrate that Delta-LLaVA decisively outperforms leading generalist MLLMs and specialized segmentation models in complex change deduction and high-precision boundary localization, establishing a unified framework for earth observation intelligence.

---

### Seek-and-Solve: Benchmarking MLLMs for Visual Clue-Driven Reasoning in Daily Scenarios

Authors: Xiaomin Li, Tala Wang, Zichen Zhong, Ying Zhang, Zirui Zheng, Takashi Isobe, Dezhuang Li, Huchuan Lu, You He, Xu Jia
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.14041v2

Daily scenarios are characterized by visual richness, requiring Multimodal Large Language Models (MLLMs) to filter noise and identify decisive visual clues for accurate reasoning. Yet, current benchmarks predominantly aim at evaluating MLLMs' pre-existing knowledge or perceptual understanding, often neglecting the critical capability of reasoning. To bridge this gap, we introduce DailyClue, a benchmark designed for visual clue-driven reasoning in daily scenarios. Our construction is guided by two core principles: (1) strict grounding in authentic daily activities, and (2) challenging query design that necessitates more than surface-level perception. Instead of simple recognition, our questions compel MLLMs to actively explore suitable visual clues and leverage them for subsequent reasoning. To this end, we curate a comprehensive dataset spanning four major daily domains and 16 distinct subtasks. Comprehensive evaluation across MLLMs and agentic models underscores the formidable challenge posed by our benchmark. Our analysis reveals several critical insights, emphasizing that the accurate identification of visual clues is essential for robust reasoning.

---

### A Complete Symmetry Classification of Shallow ReLU Networks

Authors: Pranavkrishnan Ramakrishnan
Published: 2026-04-15
Categories: cs.LG, math.AG, math.CO
arXiv: https://arxiv.org/abs/2604.14037v2

Parameter space is not function space for neural network architectures. This fact, investigated as early as the 1990s under terms such as ``reverse engineering," or ``parameter identifiability", has led to the natural question of parameter space symmetries\textemdash the study of distinct parameters in neural architectures which realize the same function. Indeed, the quotient space obtained by identifying parameters giving rise to the same function, called the \textit{neuromanifold}, has been shown in some cases to have rich geometric properties, impacting optimization dynamics. Thus far, techniques towards complete classifications have required the analyticity of the activation function, notably excising the important case of ReLU. Here, in contrast, we exploit the non-differentiability of the ReLU activation to provide a complete classification of the symmetries in the shallow case.

---

### First-See-Then-Design: A Multi-Stakeholder View for Optimal Performance-Fairness Trade-Offs

Authors: Kavya Gupta, Nektarios Kalampalikis, Christoph Heitz, Isabel Valera
Published: 2026-04-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.14035v1

Fairness in algorithmic decision-making is often defined in the predictive space, where predictive performance - used as a proxy for decision-maker (DM) utility - is traded off against prediction-based fairness notions, such as demographic parity or equality of opportunity. This perspective, however, ignores how predictions translate into decisions and ultimately into utilities and welfare for both DM and decision subjects (DS), as well as their allocation across social-salient groups. In this paper, we propose a multi-stakeholder framework for fair algorithmic decision-making grounded in welfare economics and distributive justice, explicitly modeling the utilities of both the DM and DS, and defining fairness via a social planner's utility that captures inequalities in DS utilities across groups under different justice-based fairness notions (e.g., Egalitarian, Rawlsian). We formulate fair decision-making as a post-hoc multi-objective optimization problem, characterizing the achievable performance-fairness trade-offs in the two-dimensional utility space of DM utility and the social planner's utility, under different decision policy classes (deterministic vs. stochastic, shared vs. group-specific). Using the proposed framework, we then identify conditions (in terms of the stakeholders' utilities) under which stochastic policies are more optimal than deterministic ones, and empirically demonstrate that simple stochastic policies can yield superior performance-fairness trade-offs by leveraging outcome uncertainty. Overall, we advocate a shift from prediction-centric fairness to a transparent, justice-based, multi-stakeholder approach that supports the collaborative design of decision-making policies.

---

### Large Language Models to Enhance Business Process Modeling: Past, Present, and Future Trends

Authors: João Bettencourt, Sérgio Guerreiro
Published: 2026-04-15
Categories: cs.SE, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2604.14034v1

Recent advances in Generative Artificial Intelligence, particularly Large Language Models (LLMs), have stimulated growing interest in automating or assisting Business Process Modeling tasks using natural language. Several approaches have been proposed to transform textual process descriptions into BPMN and related workflow models. However, the extent to which these approaches effectively support complex process modeling in organizational settings remains unclear. This article presents a literature review of AI-driven methods for transforming natural language into BPMN process models, with a particular focus on the role of LLMs. Following a structured review strategy, relevant studies were identified and analyzed to classify existing approaches, examine how LLMs are integrated into text-to-model pipelines, and investigate the evaluation practices used to assess generated models. The analysis reveals a clear shift from rule-based and traditional NLP pipelines toward LLM-based architectures that rely on prompt engineering, intermediate representations, and iterative refinement mechanisms. While these approaches significantly expand the capabilities of automated process model generation, the literature also exposes persistent challenges related to semantic correctness, evaluation fragmentation, reproducibility, and limited validation in real-world organizational contexts. Based on these findings, this review identifies key research gaps and discusses promising directions for future research, including the integration of contextual knowledge through Retrieval-Augmented Generation (RAG), its integration with LLMs, the development of interactive modeling architectures, and the need for more comprehensive and standardized evaluation frameworks.

---

### Hierarchical Reinforcement Learning with Runtime Safety Shielding for Power Grid Operation

Authors: Gitesh Malik
Published: 2026-04-15
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.14032v1

Reinforcement learning has shown promise for automating power-grid operation tasks such as topology control and congestion management. However, its deployment in real-world power systems remains limited by strict safety requirements, brittleness under rare disturbances, and poor generalization to unseen grid topologies. In safety-critical infrastructure, catastrophic failures cannot be tolerated, and learning-based controllers must operate within hard physical constraints. This paper proposes a safety-constrained hierarchical control framework for power-grid operation that explicitly decouples long-horizon decision-making from real-time feasibility enforcement. A high-level reinforcement learning policy proposes abstract control actions, while a deterministic runtime safety shield filters unsafe actions using fast forward simulation. Safety is enforced as a runtime invariant, independent of policy quality or training distribution. The proposed framework is evaluated on the Grid2Op benchmark suite under nominal conditions, forced line-outage stress tests, and zero-shot deployment on the ICAPS 2021 large-scale transmission grid without retraining. Results show that flat reinforcement learning policies are brittle under stress, while safety-only methods are overly conservative. In contrast, the proposed hierarchical and safety-aware approach achieves longer episode survival, lower peak line loading, and robust zero-shot generalization to unseen grids. These results indicate that safety and generalization in power-grid control are best achieved through architectural design rather than increasingly complex reward engineering, providing a practical path toward deployable learning-based controllers for real-world energy systems.

---

### Dual-Enhancement Product Bundling: Bridging Interactive Graph and Large Language Model

Authors: Zhe Huang, Peng Wang, Yan Zheng, Sen Song, Longjun Cai
Published: 2026-04-15
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2604.14030v1

Product bundling boosts e-commerce revenue by recommending complementary item combinations. However, existing methods face two critical challenges: (1) collaborative filtering approaches struggle with cold-start items owing to dependency on historical interactions, and (2) LLMs lack inherent capability to model interactive graph directly. To bridge this gap, we propose a dual-enhancement method that integrates interactive graph learning and LLM-based semantic understanding for product bundling. Our method introduces a graph-to-text paradigm, which leverages a Dynamic Concept Binding Mechanism (DCBM) to translate graph structures into natural language prompts. The DCBM plays a critical role in aligning domain-specific entities with LLM tokenization, enabling effective comprehension of combinatorial constraints. Experiments on three benchmarks (POG, POG_dense, Steam) demonstrate 6.3%-26.5% improvements over state-of-the-art baselines.

---

### POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management

Authors: Yikun Liu, Yuan Liu, Haicheng Wang, Zhongyin Zhao, Le Tian, Xiao Zhou, Jiangchao Yao, Yanfeng Wang, Weidi Xie
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.14029v2

Large Multimodal Models (LMMs) excel at visual perception but struggle with real-time, knowledge-intensive queries due to their reliance on static parametric knowledge. While multimodal search agents offer a promising solution, developing them from vanilla LMMs presents two major challenges: the lack of open recipes to cultivate search agency from scratch, and the severe context explosion (attention dilution) that occurs during long-horizon multi-turn investigations. In this paper, we address both challenges by developing a native multimodal search agent. First, we introduce an open training recipe featuring Agentic Seeding, a formative training stage that bootstraps tool-use and planning abilities directly from a non-agentic foundation. Second, to overcome the context bottleneck, we propose V-Fold, an adaptive memory management mechanism. V-Fold retains recent interactions as high-fidelity text while folding stale historical context into the visual space via rendering, exploiting the model's cross-modal alignment to preserve raw evidence without text token redundancy. Combining these innovations, we present POINTS-Seeker-8B, which achieves state-of-the-art performance among models of comparable scale across six multimodal search benchmarks.

---

### Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective

Authors: Weijie Wang, Qihang Cao, Sensen Gao, Donny Y. Chen, Haofei Xu, Wenjing Bian, Songyou Peng, Tat-Jen Cham, Chuanxia Zheng, Andreas Geiger, Jianfei Cai, Jia-Wang Bian et al.
Published: 2026-04-15
Categories: cs.CV, cs.AI, cs.GR
arXiv: https://arxiv.org/abs/2604.14025v1

Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understanding and interacting with the physical world. While traditional methods achieve high fidelity, they are limited by slow per-scene optimization or category-specific training, which hinders their practical deployment and scalability. Hence, generalizable feed-forward 3D reconstruction has witnessed rapid development in recent years. By learning a model that maps images directly to 3D representations in a single forward pass, these methods enable efficient reconstruction and robust cross-scene generalization. Our survey is motivated by a critical observation: despite the diverse geometric output representations, ranging from implicit fields to explicit primitives, existing feed-forward approaches share similar high-level architectural patterns, such as image feature extraction backbones, multi-view information fusion mechanisms, and geometry-aware design principles. Consequently, we abstract away from these representation differences and instead focus on model design, proposing a novel taxonomy centered on model design strategies that are agnostic to the output format. Our proposed taxonomy organizes the research directions into five key problems that drive recent research development: feature enhancement, geometry awareness, model efficiency, augmentation strategies and temporal-aware models. To support this taxonomy with empirical grounding and standardized evaluation, we further comprehensively review related benchmarks and datasets, and extensively discuss and categorize real-world applications based on feed-forward 3D models. Finally, we outline future directions to address open challenges such as scalability, evaluation standards, and world modeling.

---

### Stochastic Trust-Region Methods for Over-parameterized Models

Authors: Aike Yang, Hao Wang
Published: 2026-04-15
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2604.14017v1

Under interpolation-type assumptions such as the strong growth condition, stochastic optimization methods can attain convergence rates comparable to full-batch methods, but their performance, particularly for SGD, remains highly sensitive to step-size selection. To address this issue, we propose a unified stochastic trust-region framework that eliminates manual step-size tuning and extends naturally to equality-constrained problems. For unconstrained optimization, we develop a first-order stochastic trust-region algorithm and show that, under the strong growth condition, it achieves an iteration and stochastic first-order oracle complexity of $O(\varepsilon^{-2} \log(1/\varepsilon))$ for finding an $\varepsilon$-stationary point. For equality-constrained problems, we introduce a quadratic-penalty-based stochastic trust-region method with penalty parameter $μ$, and establish an iteration and oracle complexity of $O(\varepsilon^{-4} \log(1/\varepsilon))$ to reach an $\varepsilon$-stationary point of the penalized problem, corresponding to an $O(\varepsilon)$-approximate KKT point of the original constrained problem. Numerical experiments on deep neural network training and orthogonally constrained subspace fitting demonstrate that the proposed methods achieve performance comparable to well-tuned stochastic baselines, while exhibiting stable optimization behavior and effectively handling hard constraints without manual learning-rate scheduling.

---

### MAny: Merge Anything for Multimodal Continual Instruction Tuning

Authors: Zijian Gao, Wangwang Jia, Xingxing Zhang, Pengfei Qian, Tao Sun, Bo Ding, Yong Dou, Huaimin Wang, Kele Xu
Published: 2026-04-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.14016v1

Multimodal Continual Instruction Tuning (MCIT) is essential for sequential task adaptation of Multimodal Large Language Models (MLLMs) but is severely restricted by catastrophic forgetting. While existing literature focuses on the reasoning language backbone, in this work, we expose a critical yet neglected dual-forgetting phenomenon across both perception drift in Cross-modal Projection Space and reasoning collapse in Low-rank Parameter Space. To resolve this, we present \textbf{MAny} (\textbf{M}erge \textbf{Any}thing), a framework that merges task-specific knowledge through \textbf{C}ross-modal \textbf{P}rojection \textbf{M}erging (\textbf{CPM}) and \textbf{L}ow-rank \textbf{P}arameter \textbf{M}erging (\textbf{LPM}). Specifically, CPM recovers perceptual alignment by adaptively merging cross-modal visual representations via visual-prototype guidance, ensuring accurate feature recovery during inference. Simultaneously, LPM eliminates mutual interference among task-specific low-rank modules by recursively merging low-rank weight matrices. By leveraging recursive least squares, LPM provides a closed-form solution that mathematically guarantees an optimal fusion trajectory for reasoning stability. Notably, MAny operates as a training-free paradigm that achieves knowledge merging via efficient CPU-based algebraic operations, eliminating additional gradient-based optimization beyond initial tuning. Our extensive evaluations confirm the superior performance and robustness of MAny across multiple MLLMs and benchmarks. Specifically, on the UCIT benchmark, MAny achieves significant leads of up to 8.57\% and 2.85\% in final average accuracy over state-of-the-art methods across two different MLLMs, respectively.

---

### Towards Multi-Object-Tracking with Radar on a Fast Moving Vehicle: On the Potential of Processing Radar in the Frequency Domain

Authors: Tim Hansen, Arturo Gomez-Chavez, Ilya Shimchik, Andreas Birk
Published: 2026-04-15
Categories: cs.RO, cs.AI, cs.CV, eess.IV, eess.SP
arXiv: https://arxiv.org/abs/2604.14013v1

We promote in this paper the processing of radar data in the frequency domain to achieve higher robustness against noise and structural errors, especially in comparison to feature-based methods. This holds also for high dynamics in the scene, i.e., ego-motion of the vehicle with the sensor plus the presence of an unknown number of other moving objects. In addition to the high robustness, the processing in the frequency domain has the so far neglected advantage that the underlying correlation based methods used for, e.g., registration, provide information about all moving structures in the scene. A typical automotive application case is overtaking maneuvers, which in the context of autonomous racing are used here as a motivating example. Initial experiments and results with Fourier SOFT in 2D (FS2D) are presented that use the Boreas dataset to demonstrate radar-only-odometry, i.e., radar-odometry without sensor-fusion, to support our arguments.

---

### Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning

Authors: Zekai Lin, Chao Xue, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Lei Jiang, Yu Lu, Haibo Shi, Shuang Liang, Minlong Peng
Published: 2026-04-15
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2604.14010v1

Supervised Fine-Tuning (SFT) of large language models often suffers from task interference and catastrophic forgetting. Recent approaches alleviate this issue by isolating task-critical parameters during training. However, these methods represent a static solution to a dynamic problem, assuming that parameter importance remains fixed once identified. In this work, we empirically demonstrate that parameter importance exhibits temporal drift over the course of training. To address this, we propose Evolving Parameter Isolation (EPI), a fine-tuning framework that adapts isolation decisions based on online estimates of parameter importance. Instead of freezing a fixed subset of parameters, EPI periodically updates isolation masks using gradient-based signals, enabling the model to protect emerging task-critical parameters while releasing outdated ones to recover plasticity. Experiments on diverse multi-task benchmarks demonstrate that EPI consistently reduces interference and forgetting compared to static isolation and standard fine-tuning, while improving overall generalization. Our analysis highlights the necessity of synchronizing isolation mechanisms with the evolving dynamics of learning diverse abilities.

---

### Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents

Authors: Kangsan Kim, Minki Kang, Taeil Kim, Yanlai Yang, Mengye Ren, Sung Ju Hwang
Published: 2026-04-15
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.14004v1

Memory-based self-evolution has emerged as a promising paradigm for coding agents. However, existing approaches typically restrict memory utilization to homogeneous task domains, failing to leverage the shared infrastructural foundations, such as runtime environments and programming languages, that exist across diverse real-world coding problems. To address this limitation, we investigate \textbf{Memory Transfer Learning} (MTL) by harnessing a unified memory pool from heterogeneous domains. We evaluate performance across 6 coding benchmarks using four memory representations, ranging from concrete traces to abstract insights. Our experiments demonstrate that cross-domain memory improves average performance by 3.7\%, primarily by transferring meta-knowledge, such as validation routines, rather than task-specific code. Importantly, we find that abstraction dictates transferability; high-level insights generalize well, whereas low-level traces often induce negative transfer due to excessive specificity. Furthermore, we show that transfer effectiveness scales with the size of the memory pool, and memory can be transferred even between different models. Our work establishes empirical design principles for expanding memory utilization beyond single-domain silos. Project page: https://memorytransfer.github.io/

---

### Diffusion Language Models for Speech Recognition

Authors: Davyd Naveriani, Albert Zeyer, Ralf Schlüter, Hermann Ney
Published: 2026-04-15
Categories: cs.CL, cs.AI, cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2604.14001v2

Diffusion language models have recently emerged as a leading alternative to standard language models, due to their ability for bidirectional attention and parallel text generation. In this work, we explore variants for their use in speech recognition. Specifically, we introduce a comprehensive guide to incorporating masked diffusion language models (MDLM) and uniform-state diffusion models (USDMs) for rescoring ASR hypotheses. Additionally, we design a new joint-decoding method that combines CTC and USDM by integrating the framewise probability distributions derived from CTC with the labelwise probability distributions computed by USDM at each decoding step, thereby generating new candidates that combine strong language knowledge from USDM and acoustic information from CTC. Our findings reveal that USDM, as well as MDLM, can significantly improve the accuracy of recognized text. We publish all our code and recipes.

---

### Depth-Aware Image and Video Orientation Estimation

Authors: Muhammad Z. Alam, Larry Stetsiuk, M. Umair Mukati, Zeeshan Kaleem
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.13995v1

This paper introduces a novel approach for image and video orientation estimation by leveraging depth distribution in natural images. The proposed method estimates the orientation based on the depth distribution across different quadrants of the image, providing a robust framework for orientation estimation suited for applications such as virtual reality (VR), augmented reality (AR), autonomous navigation, and interactive surveillance systems. To further enhance fine-scale perceptual alignment, we incorporate depth gradient consistency (DGC) and horizontal symmetry analysis (HSA), enabling precise orientation correction. This hybrid strategy effectively exploits depth cues to support spatial coherence and perceptual stability in immersive visual content. Qualitative and quantitative evaluations demonstrate the robustness and accuracy of the proposed approach, outperforming existing techniques across diverse scenarios.

---

### Remote Sensing Image Super-Resolution for Imbalanced Textures: A Texture-Aware Diffusion Framework

Authors: Enzhuo Zhang, Sijie Zhao, Dilxat Muhtar, Zhenshi Li, Xueliang Zhang, Pengfeng Xiao
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.13994v1

Generative diffusion priors have recently achieved state-of-the-art performance in natural image super-resolution, demonstrating a powerful capability to synthesize photorealistic details. However, their direct application to remote sensing image super-resolution (RSISR) reveals significant shortcomings. Unlike natural images, remote sensing images exhibit a unique texture distribution where ground objects are globally stochastic yet locally clustered, leading to highly imbalanced textures. This imbalance severely hinders the model's spatial perception. To address this, we propose TexADiff, a novel framework that begins by estimating a Relative Texture Density Map (RTDM) to represent the texture distribution. TexADiff then leverages this RTDM in three synergistic ways: as an explicit spatial conditioning to guide the diffusion process, as a loss modulation term to prioritize texture-rich regions, and as a dynamic adapter for the sampling schedule. These modifications are designed to endow the model with explicit texture-aware capabilities. Experiments demonstrate that TexADiff achieves superior or competitive quantitative metrics. Furthermore, qualitative results show that our model generates faithful high-frequency details while effectively suppressing texture hallucinations. This improved reconstruction quality also results in significant gains in downstream task performance. The source code of our method can be found at https://github.com/ZezFuture/TexAdiff.

---

### Reward Design for Physical Reasoning in Vision-Language Models

Authors: Derek Lilienthal, Manisha Mukherjee, Sameera Horawalavithana
Published: 2026-04-15
Categories: cs.AI, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2604.13993v1

Physical reasoning over visual inputs demands tight integration of visual perception, domain knowledge, and multi-step symbolic inference. Yet even state-of-the-art Vision Language Models (VLMs) fall far short of human performance on physics benchmarks. While post-training algorithms such as Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO) have demonstrated strong reasoning gains in language models, how reward design shapes VLM physical reasoning behavior remains poorly understood. We present a systematic reward ablation study for GRPO-based VLM training on physical reasoning. We compare four reward signals of increasing semantic richness: format compliance, answer accuracy, a composite rubric reward (answer correctness, physics principle identification, and unit consistency), and a novel internal reward derived from model attention weights over input image regions. We evaluate on PhyX, a 3,000-problem benchmark spanning six physics domains and six reasoning types across multiple-choice and open-ended formats, using IBM Granite Vision 3.3 (2B). Across both formats, GRPO with accuracy-based rewards outperforms SFT on most domains, though gains vary substantially by reward type and domain. Reward design does not uniformly improve performance. Instead, it induces domain-specific reasoning behaviors. Accuracy-based rewards provide the strongest overall gains. Rubric rewards improve structured reasoning quality without consistent accuracy improvements. Attention-based rewards enhance spatial reasoning while degrading performance in symbolic domains. Our internal attention-weight reward requires no spatial annotations and improves spatial relation accuracy from 0.27 to 0.50, suggesting that supervising where the model attends during generation is a promising direction for visually grounded physical reasoning.

---

### Physics-Informed Neural Networks for Methane Sorption: Cross-Gas Transfer Learning, Ensemble Collapse Under Physics Constraints, and Monte Carlo Dropout Uncertainty Quantification

Authors: Mohammad Nooraiepour, Zezhang Song, Wei Li, Sarah Perez
Published: 2026-04-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.13992v1

Accurate methane sorption prediction across heterogeneous coal ranks requires models that combine thermodynamic consistency, efficient knowledge transfer across data-scarce geological systems, and calibrated uncertainty estimates, capabilities that are rarely addressed together in existing frameworks. We present a physics-informed transfer learning framework that adapts a hydrogen sorption PINN to methane sorption prediction via Elastic Weight Consolidation, coal-specific feature engineering, and a three-phase curriculum that progressively balances transfer preservation with thermodynamic fine-tuning. Trained on 993 equilibrium measurements from 114 independent coal experiments spanning lignite to anthracite, the framework achieves R2 = 0.932 on held-out coal samples, a 227% improvement over pressure-only classical isotherms, while hydrogen pre-training delivers 18.9% lower RMSE and 19.4% faster convergence than random initialization. Five Bayesian uncertainty quantification approaches reveal a systematic divergence in performance across physics-constrained architectures. Monte Carlo Dropout achieves well-calibrated uncertainty at minimal overhead, while deep ensembles, regardless of architectural diversity or initialization strategy, exhibit performance degradation because shared physics constraints narrow the admissible solution manifold. SHAP and ALE analyses confirm that learned representations remain physically interpretable and aligned with established coal sorption mechanisms: moisture-volatile interactions are most influential, pressure-temperature coupling captures thermodynamic co-dependence, and features exhibit non-monotonic effects. These results identify Monte Carlo Dropout as the best-performing UQ method in this physics-constrained transfer learning framework, and demonstrate cross-gas transfer learning as a data-efficient strategy for geological material modeling.

---

### Adaptive Conformal Prediction for Improving Factuality of Generations by Large Language Models

Authors: Aleksandr Rubashevskii, Dzianis Piatrashyn, Preslav Nakov, Maxim Panov
Published: 2026-04-15
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.13991v1

Large language models (LLMs) are prone to generating factually incorrect outputs. Recent work has applied conformal prediction to provide uncertainty estimates and statistical guarantees for the factuality of LLM generations. However, existing approaches are typically not prompt-adaptive, limiting their ability to capture input-dependent variability. As a result, they may filter out too few items (leading to over-coverage) or too many (under-coverage) for a given task or prompt. We propose an adaptive conformal prediction approach that extends conformal score transformation methods to LLMs, with applications to long-form generation and multiple-choice question answering. This enables prompt-dependent calibration, retaining marginal coverage guarantees while improving conditional coverage. In addition, the approach naturally supports selective prediction, allowing unreliable claims or answer choices to be filtered out in downstream applications. We evaluate our approach on multiple white-box models across diverse domains and show that it significantly outperforms existing baselines in terms of conditional coverage.

---

### Unsupervised domain transfer: Overcoming signal degradation in sleep monitoring by increasing scoring realism

Authors: Mohammad Ahangarkiasari, Andreas Tind Damgaard, Casper Haurum, Kaare B. Mikkelsen
Published: 2026-04-15
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2604.13988v1

Objective: Investigate whether hypnogram 'realism' can be used to guide an unsupervised method for handling arbitrary types of signal degradation in mobile sleep monitoring. Approach: Combining a pretrained, state-of-the-art 'u-sleep' model with a 'discriminator' network, we align features from a target domain with a feature space learned during pretraining. To test the approach, we distort the source domain with realistic signal degradations, to see how well the method can adapt to different types of degradation. We compare the performance of the resulting model with best-case models designed in a supervised manner for each type of transfer. Main Results: Depending on the type of distortion, we find that the unsupervised approach can increase Cohen's kappa with as little as 0.03 and up to 0.29, and that for all transfers, the method does not decrease performance. However, the approach never quite reaches the estimated theoretical optimal performance, and when tested on a real-life domain mismatch between two sleep studies, the benefit was insignificant. Significance: 'Discriminator-guided fine tuning' is an interesting approach to handling signal degradation for 'in the wild' sleep monitoring, with some promise. In particular, what it says about sleep data in general is interesting. However, more development will be necessary before using it 'in production'.

---

### PRiMeFlow: Capturing Complex Expression Heterogeneity in Perturbation Response Modelling

Authors: Zichao Yan, Yan Wu, Mica Xu Ji, Chaitra Agrahar, Esther Wershof, Marcel Nassar, Mehrshad Sadria, Ridvan Eksi, Vladimir Trifonov, Ignacio Ibarra, Telmo Felgueira, Błażej Osiński et al.
Published: 2026-04-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.13986v2

Predicting the effects of perturbations in-silico on cell state can identify drivers of cell behavior at scale and accelerate drug discovery. However, modeling challenges remain due to the inherent heterogeneity of single cell gene expression and the complex, latent gene dependencies. Here, we present PRiMeFlow, an end-to-end flow matching based approach to directly model the effects of genetic and small molecule perturbations in the gene expression space. The distribution-fitting approach taken by PRiMeFlow enables it to accurately approximate the empirical distribution of single-cell gene expression, which we demonstrate through extensive benchmarking inside PerturBench. Through ablation studies, we also validate important model design choices such as operating in gene expression space and parameterizing the velocity field with a U-Net architecture. Finally, by scaling PRiMeFlow to a broad perturbation data atlas spanning multiple datasets and employing a carefully designed pretraining-finetuning strategy, we demonstrate its outstanding performance on the H1 human embryonic stem cells from the ARC Virtual Cell Challenge benchmark.

---

### PIEDet: Prototype-Driven Intrinsically Explainable Object Detection

Authors: Jianlin Xiang, Linhui Dai, Xue Yang, Chaolei Yang, Yanshan Li
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.13981v2

Existing object detectors typically make predictions in a black-box manner and struggle to simultaneously provide discriminative evidence for their predictions, which limits their deployment in safety-critical scenarios. To explain model predictions, existing post-hoc explanation methods mostly rely on gradient-based or perturbation-based operators. These methods not only introduce additional memory and computational overhead but also make it difficult to ensure that the generated explanations faithfully reflect the model's internal decision-making process. To address these limitations, we propose PIEDet, a prototype-driven intrinsically explainable object detection framework. PIEDet innovatively embeds class prototypes as explicit discriminative units into the classification branch of a one-stage detector, thereby improving detection performance while providing intrinsic interpretability. First, PIEDet constructs hierarchical class prototypes at different detection levels, enabling the model to learn scale-aware class-semantic representations. Second, we propose a prototype-driven feature learning method consisting of prototype regularization and a region-to-prototype matching loss. The former enhances the inter-class discriminability of the prototypes, while the latter encourages prototype responses to focus on object regions. Finally, we introduce a scale-aligned hierarchical prototype supervision mechanism that assigns scale-matched supervision signals to different detection levels, thereby enhancing the scale specificity of the hierarchical prototypes. On the ExDark, RTTS, and VOC2012-FOG datasets, PIEDet improves mAP@0.5 over the baseline by 4.7%, 1.6%, and 4.8%, respectively, while demonstrating superior computational efficiency. Compared with mainstream post-hoc explanation methods, PIEDet achieves a better balance between explanation quality and explanation cost.

---

### HiProto: Hierarchical Prototype Learning for Interpretable Object Detection Under Low-quality Conditions

Authors: Jianlin Xiang, Linhui Dai, Xue Yang, Chaolei Yang, Yanshan Li
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.13981v1

Interpretability is essential for deploying object detection systems in critical applications, especially under low-quality imaging conditions that degrade visual information and increase prediction uncertainty. Existing methods either enhance image quality or design complex architectures, but often lack interpretability and fail to improve semantic discrimination. In contrast, prototype learning enables interpretable modeling by associating features with class-centered semantics, which can provide more stable and interpretable representations under degradation. Motivated by this, we propose HiProto, a new paradigm for interpretable object detection based on hierarchical prototype learning. By constructing structured prototype representations across multiple feature levels, HiProto effectively models class-specific semantics, thereby enhancing both semantic discrimination and interpretability. Building upon prototype modeling, we first propose a Region-to-Prototype Contrastive Loss (RPC-Loss) to enhance the semantic focus of prototypes on target regions. Then, we propose a Prototype Regularization Loss (PR-Loss) to improve the distinctiveness among class prototypes. Finally, we propose a Scale-aware Pseudo Label Generation Strategy (SPLGS) to suppress mismatched supervision for RPC-Loss, thereby preserving the robustness of low-level prototype representations. Experiments on ExDark, RTTS, and VOC2012-FOG demonstrate that HiProto achieves competitive results while offering clear interpretability through prototype responses, without relying on image enhancement or complex architectures. Our code will be available at https://github.com/xjlDestiny/HiProto.git.

---

### BOAT: Navigating the Sea of In Silico Predictors for Antibody Design via Multi-Objective Bayesian Optimization

Authors: Jackie Rao, Ferran Gonzalez Hernandez, Leon Gerard, Alexandra Gessner
Published: 2026-04-15
Categories: cs.LG, q-bio.QM, stat.ML
arXiv: https://arxiv.org/abs/2604.13980v1

Antibody lead optimization is inherently a multi-objective challenge in drug discovery. Achieving a balance between different drug-like properties is crucial for the development of viable candidates, and this search becomes exponentially challenging as desired properties grow. The ever-growing zoo of sophisticated in silico tools for predicting antibody properties calls for an efficient joint optimization procedure to overcome resource-intensive sequential filtering pipelines. We present BOAT, a versatile Bayesian optimization framework for multi-property antibody engineering. Our `plug-and-play' framework couples uncertainty-aware surrogate modeling with a genetic algorithm to jointly optimize various predicted antibody traits while enabling efficient exploration of sequence space. Through systematic benchmarking against genetic algorithms and newer generative learning approaches, we demonstrate competitive performance with state-of-the-art methods for multi-objective protein optimization. We identify clear regimes where surrogate-driven optimization outperforms expensive generative approaches and establish practical limits imposed by sequence dimensionality and oracle costs.

---

### Leveraging LLM-GNN Integration for Open-World Question Answering over Knowledge Graphs

Authors: Hussein Abdallah, Ibrahim Abdelaziz, Panos Kalnis, Essam Mansour
Published: 2026-04-15
Categories: cs.CL, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2604.13979v1

Open-world Question Answering (OW-QA) over knowledge graphs (KGs) aims to answer questions over incomplete or evolving KGs. Traditional KGQA assumes a closed world where answers must exist in the KG, limiting real-world applicability. In contrast, open-world QA requires inferring missing knowledge based on graph structure and context. Large language models (LLMs) excel at language understanding but lack structured reasoning. Graph neural networks (GNNs) model graph topology but struggle with semantic interpretation. Existing systems integrate LLMs with GNNs or graph retrievers. Some support open-world QA but rely on structural embeddings without semantic grounding. Most assume observed paths or complete graphs, making them unreliable under missing links or multi-hop reasoning. We present GLOW, a hybrid system that combines a pre-trained GNN and an LLM for open-world KGQA. The GNN predicts top-k candidate answers from the graph structure. These, along with relevant KG facts, are serialized into a structured prompt (e.g., triples and candidates) to guide the LLM's reasoning. This enables joint reasoning over symbolic and semantic signals, without relying on retrieval or fine-tuning. To evaluate generalization, we introduce GLOW-BENCH, a 1,000-question benchmark over incomplete KGs across diverse domains. GLOW outperforms existing LLM-GNN systems on standard benchmarks and GLOW-BENCH, achieving up to 53.3% and an average 38% improvement. GitHub code and data are available.

---

### How Can We Synthesize High-Quality Pretraining Data? A Systematic Study of Prompt Design, Generator Model, and Source Data

Authors: Joel Niklaus, Atsuki Yamaguchi, Michal Štefánik, Guilherme Penedo, Hynek Kydlíček, Elie Bakouch, Lewis Tunstall, Edward Emanuel Beeching, Thibaud Frere, Colin Raffel, Leandro von Werra, Thomas Wolf
Published: 2026-04-15
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.13977v2

Synthetic data is a standard component in training large language models, yet systematic comparisons across design dimensions, including rephrasing strategy, generator model, and source data, remain absent. We conduct extensive controlled experiments, generating over one trillion tokens, to identify critical factors in rephrasing web text into synthetic pretraining data. Our results reveal that structured output formats, such as tables, math problems, FAQs, and tutorials, consistently outperform both curated web baselines and prior synthetic methods. Notably, increasing the size of the generator model beyond 1B parameters provides no additional benefit. Our analysis also demonstrates that the selection of the original data used for mixing substantially influences performance. By applying our findings, we develop \textbf{\textsc{FinePhrase}}, a 486-billion-token open dataset of rephrased web text. We show that \textsc{FinePhrase} outperforms all existing synthetic data baselines while reducing generation costs by up to 30 times. We provide the dataset, all prompts, and the generation framework to the research community.

---

### MApLe: Multi-instance Alignment of Diagnostic Reports and Large Medical Images

Authors: Felicia Bader, Philipp Seeböck, Anastasia Bartashova, Ulrike Attenberger, Georg Langs
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.13970v1

In diagnostic reports, experts encode complex imaging data into clinically actionable information. They describe subtle pathological findings that are meaningful in their anatomical context. Reports follow relatively consistent structures, expressing diagnostic information with few words that are often associated with tiny but consequential image observations. Standard vision language models struggle to identify the associations between these informative text components and small locations in the images. Here, we propose "MApLe", a multi-task, multi-instance vision language alignment approach that overcomes these limitations. It disentangles the concepts of anatomical region and diagnostic finding, and links local image information to sentences in a patch-wise approach. Our method consists of a text embedding trained to capture anatomical and diagnostic concepts in sentences, a patch-wise image encoder conditioned on anatomical structures, and a multi-instance alignment of these representations. We demonstrate that MApLe can successfully align different image regions and multiple diagnostic findings in free-text reports. We show that our model improves the alignment performance compared to state-of-the-art baseline models when evaluated on several downstream tasks. The code is available at https://github.com/cirmuw/MApLe.

---

### Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation

Authors: Shangzhe Li, Weitong Zhang
Published: 2026-04-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.13966v1

We study value adaptation in offline-to-online reinforcement learning under general function approximation. Starting from an imperfect offline pretrained $Q$-function, the learner aims to adapt it to the target environment using only a limited amount of online interaction. We first characterize the difficulty of this setting by establishing a minimax lower bound, showing that even when the pretrained $Q$-function is close to optimal $Q^\star$, online adaptation can be no more efficient than pure online RL on certain hard instances. On the positive side, under a novel structural condition on the offline-pretrained value functions, we propose O2O-LSVI, an adaptation algorithm with problem-dependent sample complexity that provably improves over pure online RL. Finally, we complement our theory with neural-network experiments that demonstrate the practical effectiveness of the proposed method.

---

### (Emerging Ideas) Artificial Tripartite Intelligence: A Bio-Inspired, Sensor-First Architecture for Physical AI

Authors: You Rim Choi, Subeom Park, Hyung-Sin Kim
Published: 2026-04-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.13959v1

As AI moves from data centers to robots and wearables, scaling ever-larger models becomes insufficient. Physical AI operates under tight latency, energy, privacy, and reliability constraints, and its performance depends not only on model capacity but also on how signals are acquired through controllable sensors in dynamic environments. We present Artificial Tripartite Intelligence (ATI), a bio-inspired, sensor-first architectural contract for physical AI. ATI is tripartite at the systems level: a Brainstem (L1) provides reflexive safety and signal-integrity control, a Cerebellum (L2) performs continuous sensor calibration, and a Cerebral Inference Subsystem spanning L3/L4 supports routine skill selection and execution, coordination, and deep reasoning. This modular organization allows sensor control, adaptive sensing, edge-cloud execution, and foundation model reasoning to co-evolve within one closed-loop architecture, while keeping time-critical sensing and control on device and invoking higher-level inference only when needed. We instantiate ATI in a mobile camera prototype under dynamic lighting and motion. In our routed evaluation (L3-L4 split inference), compared to the default auto-exposure setting, ATI (L1/L2 adaptive sensing) improves end-to-end accuracy from 53.8% to 88% while reducing remote L4 invocations by 43.3%. These results show the value of co-designing sensing and inference for embodied AI.

---

### Creo: From One-Shot Image Generation to Progressive, Co-Creative Ideation

Authors: Zoe De Simone, Angie Boggust, Fredo Durand, Ashia Wilson, Arvind Satyanarayan
Published: 2026-04-15
Categories: cs.HC, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2604.13956v1

Text-to-image (T2I) systems enable rapid generation of high-fidelity imagery but are misaligned with how visual ideas develop. T2I systems generate outputs that make implicit visual decisions on behalf of the user, often introduce fine-grained details that can anchor users prematurely and limit their ability to keep options open early on, and cause unintended changes during editing that are difficult to correct and reduce users' sense of control. To address these concerns, we present Creo, a multi-stage T2I system that scaffolds image generation by progressing from rough sketches to high-resolution outputs, exposing intermediary abstractions where users can make incremental changes. Sketch-like abstractions invite user editing and allow users to keep design options open when ideas are still forming due to their provisional nature. Each stage in Creo can be modified with manual changes and AI-assisted operations, enabling fine-grained, step-wise control through a locking mechanism that preserves prior decisions so subsequent edits affect only specified regions or attributes. Users remain in the loop, making and verifying decisions across stages, while the system applies diffs instead of regenerating full images, reducing drift as fidelity increases. A comparative study with a one-shot baseline shows that participants felt stronger ownership over Creo outputs, as they were able to trace their decisions in building up the image. Furthermore, embedding-based analysis indicates that Creo outputs are less homogeneous than one-shot results. These findings suggest that multi-stage generation, combined with intermediate control and decision locking, is a key design principle for improving controllability, user agency, creativity, and output diversity in generative systems.

---

### HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark

Authors: Jiacheng Wang, Jinchang Hou, Fabian Wang, Ping Jian, Chenfu Bao, Zhonghou Lv
Published: 2026-04-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.13954v2

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of \emph{intrinsic} risk, where intrinsic failures remain latent, propagate across long-horizon execution, and eventually lead to high-consequence outcomes. To evaluate this setting, we introduce \emph{non-attack intrinsic risk auditing}, a guard-oriented safety evaluation task, and present \textbf{HINTBench}, a benchmark of 596 agent trajectories, comprising 400 synthetic risky trajectories, 136 synthetic safe trajectories, 30 reconstructed real-world risky trajectories, and 30 reconstructed real-world safe trajectories, with an average length of 24.0 steps. HINTBench supports three tasks: risk detection, risk-step localization, and intrinsic failure-type identification, with annotations organized under a unified five-constraint taxonomy. Experiments reveal a substantial capability gap: strong LLMs perform well on trajectory-level risk detection, but the best model remains below 37 on fine-grained Strict-F1 for risk-step localization. Existing off-the-shelf guard models evaluated under their native prompts transfer poorly to this setting. These findings establish intrinsic risk auditing as an open challenge for agent safety.

---

### HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark

Authors: Jiacheng Wang, Jinchang Hou, Fabian Wang, Ping Jian, Chenfu Bao, Zhonghou Lv
Published: 2026-04-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.13954v1

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of \emph{intrinsic} risk, where intrinsic failures remain latent, propagate across long-horizon execution, and eventually lead to high-consequence outcomes. To evaluate this setting, we introduce \emph{non-attack intrinsic risk auditing} and present \textbf{HINTBench}, a benchmark of 629 agent trajectories (523 risky, 106 safe; 33 steps on average) supporting three tasks: risk detection, risk-step localization, and intrinsic failure-type identification. Its annotations are organized under a unified five-constraint taxonomy. Experiments reveal a substantial capability gap: strong LLMs perform well on trajectory-level risk detection, but their performance drops to below 35 Strict-F1 on risk-step localization, while fine-grained failure diagnosis proves even harder. Existing guard models transfer poorly to this setting. These findings establish intrinsic risk auditing as an open challenge for agent safety.

---

### Quantum Machine Learning for Colorectal Cancer Data: Anastomotic Leak Classification and Risk Factors

Authors: Vojtěch Novák, Ivan Zelinka, Lenka Přibylová, Lubomír Martínek, Vladimír Benčurík, Martin Beseda
Published: 2026-04-15
Categories: cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2604.13951v1

This study evaluates colorectal risk factors and compares classical models against Quantum Neural Networks (QNNs) for anastomotic leak prediction. Analyzing clinical data with 14\% leak prevalence, we tested ZZFeatureMap encodings with RealAmplitudes and EfficientSU2 ansatze under simulated noise. $F_β$-optimized quantum configurations yielded significantly higher sensitivity (83.3\%) than classical baselines (66.7\%). This demonstrates that quantum feature spaces better prioritize minority class identification, which is critical for low-prevalence clinical risk prediction. Our work explores various optimizers under noisy conditions, highlighting key trade-offs and future directions for hardware deployment.

---

### Causal Drawbridges: Characterizing Gradient Blocking of Syntactic Islands in Transformer LMs

Authors: Sasha Boguraev, Kyle Mahowald
Published: 2026-04-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.13950v1

We show how causal interventions in Transformer models provide insights into English syntax by focusing on a long-standing challenge for syntactic theory: syntactic islands. Extraction from coordinated verb phrases is often degraded, yet acceptability varies gradiently with lexical content (e.g., "I know what he hates art and loves" vs. "I know what he looked down and saw"). We show that modern Transformer language models replicate human judgments across this gradient. Using causal interventions that isolate functionally relevant subspaces in Transformer blocks, attention modules, and MLPs, we demonstrate that extraction from coordination islands engages the same filler-gap mechanisms as canonical wh-dependencies, but that these mechanisms are selectively blocked to varying degrees. By projecting a large corpus of unrelated text onto these causally identified subspaces, we derive a novel linguistic hypothesis: the conjunction "and" is represented differently in extractable versus non-extractable constructions, corresponding to expressions encoding relational dependencies versus purely conjunctive uses. These results illustrate how mechanistic interpretability can inform syntax, generating new hypotheses about linguistic representation and processing.

---

### Heuristic Style Transfer for Real-Time, Efficient Weather Attribute Detection

Authors: Hamed Ouattara, Pierre Duthon, Pascal Houssam Salmane, Frédéric Bernardin, Omar Ait Aider
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.13947v1

We present lightweight and efficient architectures to detect weather conditions from RGB images, predicting the weather type (sunny, rain, snow, fog) and 11 complementary attributes such as intensity, visibility, and ground condition, for a total of 53 classes across the tasks. This work examines to what extent weather conditions manifest as variations in visual style. We investigate style-inspired techniques, including Gram matrices, a truncated ResNet-50 targeting lower and intermediate layers, and PatchGAN-style architectures, within a multi-task framework with attention mechanisms. Two families are introduced: RTM (ResNet50-Truncated-MultiTasks) and PMG (PatchGAN-MultiTasks-Gram), together with their variants. Our contributions include automation of Gram-matrix computation, integration of PatchGAN into supervised multi-task learning, and local style capture through local Gram for improved spatial coherence. We also release a dataset of 503,875 images annotated with 12 weather attributes under a Creative Commons Attribution (CC-BY) license. The models achieve F1 scores above 96 percent on our internal test set and above 78 percent in zero-shot evaluation on several external datasets, confirming their generalization ability. The PMG architecture, with fewer than 5 million parameters, runs in real time with a small memory footprint, making it suitable for embedded systems. The modular design of the models also allows style-related or weather-related tasks to be added or removed as needed.

---

### CollabCoder: Plan-Code Co-Evolution via Collaborative Decision-Making for Efficient Code Generation

Authors: Duy Tung Doan, Quang Huy Phung, Dzung Nguyen, Khac-Hoai Nam Bui
Published: 2026-04-15
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2604.13946v2

Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated execution, high computational overhead, and limited adaptability to complex tasks. This paper introduces CollabCoder, a novel Plan-Code Co-Evolution framework that improves code generation through dynamic multi-agent collaboration. The core idea is to design a collaborative decision-making process between the plan module and the code module to decide which module should be executed for the debugging process. Extensive experiments on widely used benchmarks demonstrate that CollabCoder consistently improves code quality and robustness across tasks. Importantly, CollabCoder achieves performance comparable to or exceeding current state-of-the-art methods while reducing computational overhead, with efficiency gains becoming more pronounced as benchmark difficulty increases. On the more challenging LiveCodeBench and xCodeEval benchmarks, our approach improves performance by 11-20% over strong baselines while reducing the number of API calls by an average of 4-10 per execution.

---

### SceneGlue: Scene-Aware Transformer for Feature Matching without Scene-Level Annotation

Authors: Songlin Du, Xiaoyong Lu, Yaping Yan, Guobao Xiao, Xiaobo Lu, Takeshi Ikenaga
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.13941v1

Local feature matching plays a critical role in understanding the correspondence between cross-view images. However, traditional methods are constrained by the inherent local nature of feature descriptors, limiting their ability to capture non-local scene information that is essential for accurate cross-view correspondence. In this paper, we introduce SceneGlue, a scene-aware feature matching framework designed to overcome these limitations. SceneGlue leverages a hybridizable matching paradigm that integrates implicit parallel attention and explicit cross-view visibility estimation. The parallel attention mechanism simultaneously exchanges information among local descriptors within and across images, enhancing the scene's global context. To further enrich the scene awareness, we propose the Visibility Transformer, which explicitly categorizes features into visible and invisible regions, providing an understanding of cross-view scene visibility. By combining explicit and implicit scene-level awareness, SceneGlue effectively compensates for the local descriptor constraints. Notably, SceneGlue is trained using only local feature matches, without requiring scene-level groundtruth annotations. This scene-aware approach not only improves accuracy and robustness but also enhances interpretability compared to traditional methods. Extensive experiments on applications such as homography estimation, pose estimation, image matching, and visual localization validate SceneGlue's superior performance. The source code is available at https://github.com/songlin-du/SceneGlue.

---

### AI-Assisted Peer Review at Scale: The AAAI-26 AI Review Pilot

Authors: Joydeep Biswas, Sheila Schoepp, Gautham Vasan, Anthony Opipari, Arthur Zhang, Zichao Hu, Sebastian Joseph, Matthew Lease, Junyi Jessy Li, Peter Stone, Kiri L. Wagstaff, Matthew E. Taylor et al.
Published: 2026-04-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.13940v1

Scientific peer review faces mounting strain as submission volumes surge, making it increasingly difficult to sustain review quality, consistency, and timeliness. Recent advances in AI have led the community to consider its use in peer review, yet a key unresolved question is whether AI can generate technically sound reviews at real-world conference scale. Here we report the first large-scale field deployment of AI-assisted peer review: every main-track submission at AAAI-26 received one clearly identified AI review from a state-of-the-art system. The system combined frontier models, tool use, and safeguards in a multi-stage process to generate reviews for all 22,977 full-review papers in less than a day. A large-scale survey of AAAI-26 authors and program committee members showed that participants not only found AI reviews useful, but actually preferred them to human reviews on key dimensions such as technical accuracy and research suggestions. We also introduce a novel benchmark and find that our system substantially outperforms a simple LLM-generated review baseline at detecting a variety of scientific weaknesses. Together, these results show that state-of-the-art AI methods can already make meaningful contributions to scientific peer review at conference scale, opening a path toward the next generation of synergistic human-AI teaming for evaluating research.

---

### A Multi-Stage Optimization Pipeline for Bethesda Cell Detection in Pap Smear Cytology

Authors: Martin Amster, Camila María Polotto
Published: 2026-04-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.13939v1

Computer vision techniques have advanced significantly in recent years, finding diverse and impactful applications within the medical field. In this paper, we introduce a new framework for the detection of Bethesda cells in Pap smear images, developed for Track B of the Riva Cytology Challenge held in association with the International Symposium on Biomedical Imaging (ISBI). This work focuses on enhancing computer vision models for cell detection, with performance evaluated using the mAP50-95 metric. We propose a solution based on an ensemble of YOLO and U-Net architectures, followed by a refinement stage utilizing overlap removal techniques and a binary classifier. Our framework achieved second place with a mAP50-95 score of 0.5909 in the competition. The implementation and source code are available at the following repository: github.com/martinamster/riva-trackb

---