# Research Papers — 2026-02 · bundle page 9 of 210

> Full-text markdown of papers #401–450 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-02/page/9
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/8.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/10.md)

### The Stability of Online Algorithms in Performative Prediction

Authors: Gabriele Farina, Juan Carlos Perdomo
Published: 2026-02-27
Categories: cs.LG, cs.CY, cs.GT, stat.ML
arXiv: https://arxiv.org/abs/2602.24207v2

The use of algorithmic predictions in decision-making leads to a feedback loop where the models we deploy actively influence the data distributions we see, and later use to retrain on. This dynamic was formalized by Perdomo et al. 2020 in their work on performative prediction. Our main result is an unconditional reduction showing that any no-regret algorithm deployed in performative settings converges to a (mixed) performatively stable equilibrium: a solution in which models actively shape data distributions in ways that their own predictions look optimal in hindsight. Prior to our work, all positive results in this area imposed strong restrictions on how models influenced distributions. By using a martingale argument and allowing randomization, we avoid any assumption on how populations respond to predictions and sidestep recent hardness results showing that deterministic stable models are in general PPAD-hard to compute. Lastly, on a more conceptual note, our connection sheds light on why common algorithms, like gradient descent, are naturally stabilizing and prevent runaway feedback loops. We hope our work enables future technical transfer of ideas between online optimization and performativity.

---

### Flow-Based Density Ratio Estimation for Intractable Distributions with Applications in Genomics

Authors: Egor Antipov, Alessandro Palma, Lorenzo Consoli, Stephan Günnemann, Andrea Dittadi, Fabian J. Theis
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.24201v2

Estimating density ratios between pairs of intractable data distributions is a core problem in probabilistic modeling, enabling principled comparisons of sample likelihoods under different data-generating processes across conditions. While exact-likelihood models such as normalizing flows offer a promising approach to density ratio estimation, naive evaluations are computationally expensive and prone to discretization errors because they require simulating each distribution's likelihood independently. In this work, we leverage condition-aware flow matching to derive a single dynamical formulation for tracking density ratios along generative trajectories. We demonstrate competitive performance on simulated benchmarks for closed-form ratio estimation, and show that our method supports versatile tasks in single-cell genomics data analysis, where likelihood-based comparisons of cellular states across experimental conditions enable treatment effect estimation and batch correction evaluation.

---

### Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume

Authors: Gregory Kang Ruey Lau, Hieu Dao, Nicole Kan Hui Lin, Bryan Kian Hsiang Low
Published: 2026-02-27
Categories: cs.AI, cs.CL, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.24195v1

Despite their capabilities, Multimodal Large Language Models (MLLMs) may produce plausible but erroneous outputs, hindering reliable deployment. Accurate uncertainty metrics could enable escalation of unreliable queries to human experts or larger models for improved performance. However, existing uncertainty metrics have practical constraints, such as being designed only for specific modalities, reliant on external tools, or computationally expensive. We introduce UMPIRE, a training-free uncertainty quantification framework for MLLMs that works efficiently across various input and output modalities without external tools, relying only on the models' own internal modality features. UMPIRE computes the incoherence-adjusted semantic volume of sampled MLLM responses for a given task instance, effectively capturing both the global semantic diversity of samples and the local incoherence of responses based on internal model confidence. We propose uncertainty desiderata for MLLMs and provide theoretical analysis motivating UMPIRE's design. Extensive experiments show that UMPIRE consistently outperforms baseline metrics in error detection and uncertainty calibration across image, audio, and video-text benchmarks, including adversarial and out-of-distribution settings. We also demonstrate UMPIRE's generalization to non-text output tasks, including image and audio generation.

---

### Resilient Strategies for Stochastic Systems: How Much Does It Take to Break a Winning Strategy?

Authors: Kush Grover, Markel Zubia, Debraj Chakraborty, Muqsit Azeem, Nils Jansen, Jan Kretinsky
Published: 2026-02-27
Categories: cs.GT, cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2602.24191v1

We study the problem of resilient strategies in the presence of uncertainty. Resilient strategies enable an agent to make decisions that are robust against disturbances. In particular, we are interested in those disturbances that are able to flip a decision made by the agent. Such a disturbance may, for instance, occur when the intended action of the agent cannot be executed due to a malfunction of an actuator in the environment. In this work, we introduce the concept of resilience in the stochastic setting and present a comprehensive set of fundamental problems. Specifically, we discuss such problems for Markov decision processes with reachability and safety objectives, which also smoothly extend to stochastic games. To account for the stochastic setting, we provide various ways of aggregating the amounts of disturbances that may have occurred, for instance, in expectation or in the worst case. Moreover, to reason about infinite disturbances, we use quantitative measures, like their frequency of occurrence.

---

### MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games

Authors: Jacob Eisenstein, Fantine Huot, Adam Fisch, Jonathan Berant, Mirella Lapata
Published: 2026-02-27
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.24188v2

We present a scalable and verifiable methodology for evaluating language models in multi-turn interactions, using a suite of collaborative games that require effective communication about private information. This enables an interactive scaling analysis, in which a fixed token budget is divided over a variable number of turns. We find that language models often fail to use interactive collaboration to improve over the non-interactive baseline in which one agent summarizes its information and the other agent immediately acts, despite substantial headroom. This suggests that state-of-the-art models still suffer from significant weaknesses in planning and executing multi-turn collaborative conversations. We analyze the linguistic features of these dialogues, assessing the roles of sycophancy, information density, and discourse coherence. While there is no single linguistic explanation for the collaborative weaknesses of contemporary language models, we note that humans achieve comparable task success at superior token efficiency by producing more coherent dialogues. The proactive management of private information is a defining feature of real-world communication, and this work is designed to drive further progress on this capability.

---

### MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games

Authors: Jacob Eisenstein, Fantine Huot, Adam Fisch, Jonathan Berant, Mirella Lapata
Published: 2026-02-27
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.24188v1

We present a scalable methodology for evaluating language models in multi-turn interactions, using a suite of collaborative games that require effective communication about private information. This enables an interactive scaling analysis, in which a fixed token budget is divided over a variable number of turns. We find that in many cases, language models are unable to use interactive collaboration to improve over the non-interactive baseline scenario in which one agent attempts to summarize its information and the other agent immediately acts -- despite substantial headroom. This suggests that state-of-the-art models still suffer from significant weaknesses in planning and executing multi-turn collaborative conversations. We analyze the linguistic features of these dialogues, assessing the roles of sycophancy, information density, and discourse coherence. While there is no single linguistic explanation for the collaborative weaknesses of contemporary language models, we note that humans achieve comparable task success at superior token efficiency by producing dialogues that are more coherent than those produced by most language models. The proactive management of private information is a defining feature of real-world communication, and we hope that MT-PingEval will drive further work towards improving this capability.

---

### A multimodal slice discovery framework for systematic failure detection and explanation in medical image classification

Authors: Yixuan Liu, Kanwal K. Bhatia, Ahmed E. Fetit
Published: 2026-02-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.24183v1

Despite advances in machine learning-based medical image classifiers, the safety and reliability of these systems remain major concerns in practical settings. Existing auditing approaches mainly rely on unimodal features or metadata-based subgroup analyses, which are limited in interpretability and often fail to capture hidden systematic failures. To address these limitations, we introduce the first automated auditing framework that extends slice discovery methods to multimodal representations specifically for medical applications. Comprehensive experiments were conducted under common failure scenarios using the MIMIC-CXR-JPG dataset, demonstrating the framework's strong capability in both failure discovery and explanation generation. Our results also show that multimodal information generally allows more comprehensive and effective auditing of classifiers, while unimodal variants beyond image-only inputs exhibit strong potential in scenarios where resources are constrained.

---

### Multi-Objective Reinforcement Learning for Large-Scale Tote Allocation in Human-Robot Collaborative Fulfillment Centers

Authors: Sikata Sengupta, Guangyi Liu, Omer Gottesman, Joseph W Durham, Michael Kearns, Aaron Roth, Michael Caldara
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.24182v1

Optimizing the consolidation process in container-based fulfillment centers requires trading off competing objectives such as processing speed, resource usage, and space utilization while adhering to a range of real-world operational constraints. This process involves moving items between containers via a combination of human and robotic workstations to free up space for inbound inventory and increase container utilization. We formulate this problem as a large-scale Multi-Objective Reinforcement Learning (MORL) task with high-dimensional state spaces and dynamic system behavior. Our method builds on recent theoretical advances in solving constrained RL problems via best-response and no-regret dynamics in zero-sum games, enabling principled minimax policy learning. Policy evaluation on realistic warehouse simulations shows that our approach effectively trades off objectives, and we empirically observe that it learns a single policy that simultaneously satisfies all constraints, even if this is not theoretically guaranteed. We further introduce a theoretical framework to handle the problem of error cancellation, where time-averaged solutions display oscillatory behavior. This method returns a single iterate whose Lagrangian value is close to the minimax value of the game. These results demonstrate the promise of MORL in solving complex, high-impact decision-making problems in large-scale industrial systems.

---

### A Mixed Diet Makes DINO An Omnivorous Vision Encoder

Authors: Rishabh Kabra, Maks Ovsjanikov, Drew A. Hudson, Ye Xia, Skanda Koppula, Andre Araujo, Joao Carreira, Niloy J. Mitra
Published: 2026-02-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.24181v2

Pre-trained vision encoders like DINOv2 have demonstrated exceptional performance on unimodal tasks. However, we observe that their features are poorly aligned across different visual modalities. For instance, the feature embedding for an RGB image and its corresponding depth map of the same scene exhibit a cosine similarity that is nearly identical to that of two random, unrelated images. To address this, we propose the Omnivorous Vision Encoder, a post-training framework that learns a modality-agnostic feature space. We fine-tune the encoder with a dual objective: first, to maximize the feature alignment between different modalities of the same scene; and second, a distillation objective that anchors the learned representations to a fully frozen teacher. The resulting student encoder becomes "omnivorous" by producing more consistent embeddings for a given scene, regardless of the input modality (RGB, Depth, Segmentation, etc.). This approach enables robust cross-modal understanding while retaining the discriminative semantics of the original foundation model. Omnivorous model weights are available at https://github.com/google-deepmind/representations4d.

---

### Learning Flexible Job Shop Scheduling under Limited Buffers and Material Kitting Constraints

Authors: Shishun Zhang, Juzhan Xu, Yidan Fan, Chenyang Zhu, Ruizhen Hu, Yongjun Wang, Kai Xu
Published: 2026-02-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.24180v1

The Flexible Job Shop Scheduling Problem (FJSP) originates from real production lines, while some practical constraints are often ignored or idealized in current FJSP studies, among which the limited buffer problem has a particular impact on production efficiency. To this end, we study an extended problem that is closer to practical scenarios--the Flexible Job Shop Scheduling Problem with Limited Buffers and Material Kitting. In recent years, deep reinforcement learning (DRL) has demonstrated considerable potential in scheduling tasks. However, its capacity for state modeling remains limited when handling complex dependencies and long-term constraints. To address this, we leverage a heterogeneous graph network within the DRL framework to model the global state. By constructing efficient message passing among machines, operations, and buffers, the network focuses on avoiding decisions that may cause frequent pallet changes during long-sequence scheduling, thereby helping improve buffer utilization and overall decision quality. Experimental results on both synthetic and real production line datasets show that the proposed method outperforms traditional heuristics and advanced DRL methods in terms of makespan and pallet changes, and also achieves a good balance between solution quality and computational cost. Furthermore, a supplementary video is provided to showcase a simulation system that effectively visualizes the progression of the production line.

---

### Sandwiching Polynomials for Geometric Concepts with Low Intrinsic Dimension

Authors: Adam R. Klivans, Konstantinos Stavropoulos, Arsen Vasilyan
Published: 2026-02-27
Categories: cs.LG, cs.CC
arXiv: https://arxiv.org/abs/2602.24178v1

Recent work has shown the surprising power of low-degree sandwiching polynomial approximators in the context of challenging learning settings such as learning with distribution shift, testable learning, and learning with contamination. A pair of sandwiching polynomials approximate a target function in expectation while also providing pointwise upper and lower bounds on the function's values. In this paper, we give a new method for constructing low-degree sandwiching polynomials that yield greatly improved degree bounds for several fundamental function classes and marginal distributions. In particular, we obtain degree $\mathrm{poly}(k)$ sandwiching polynomials for functions of $k$ halfspaces under the Gaussian distribution, improving exponentially over the prior $2^{O(k)}$ bound. More broadly, our approach applies to function classes that are low-dimensional and have smooth boundary. In contrast to prior work, our proof is relatively simple and directly uses the smoothness of the target function's boundary to construct sandwiching Lipschitz functions, which are amenable to results from high-dimensional approximation theory. For low-dimensional polynomial threshold functions (PTFs) with respect to Gaussians, we obtain doubly exponential improvements without applying the FT-mollification method of Kane used in the best previous result.

---

### Task-Centric Acceleration of Small-Language Models

Authors: Dor Tsur, Sharon Adar, Ran Levy
Published: 2026-02-27
Categories: cs.CL, cs.AI, cs.IT
arXiv: https://arxiv.org/abs/2602.24174v1

Small language models (SLMs) have emerged as efficient alternatives to large language models for task-specific applications. However, they are often employed in high-volume, low-latency settings, where efficiency is crucial. We propose TASC, Task-Adaptive Sequence Compression, a framework for SLM acceleration comprising two use-cases: When performing SLM fine-tuning, we propose TASC-ft, which iteratively enriches the tokenizer vocabulary with high-frequency output n-grams and then fine-tunes the model to utilize the expanded vocabulary. Next, we propose an inference-time method, termed TASC-spec. TASC-spec is a lightweight, training-free speculative decoding method that constructs an n-gram draft model from the task's output corpus, mixing task and context n-gram information.TASC-spec avoids any additional training, while bypassing draft-target vocabulary alignment constraints. We demonstrate the effectiveness of both methods across multiple low output-variability generation tasks. Our methods show consistent improvements in inference efficiency while maintaining task performance.

---

### LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics

Authors: Antoine Peyronnet, Fabian Gloeckle, Amaury Hayat
Published: 2026-02-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.24173v2

We present a new approach for benchmarking Large Language Model (LLM) capabilities on research-level mathematics. Existing benchmarks largely rely on static, hand-curated sets of contest or textbook-style problems as proxies for mathematical research. Instead, we establish an updatable benchmark evaluating models directly on the latest research results in mathematics. This consists of an automatic pipeline that extracts lemmas from arXiv and rewrites them into self-contained statements by making all assumptions and required definitions explicit. It results in a benchmark that can be updated regularly with new problems taken directly from human mathematical research, while previous instances can be used for training without compromising future evaluations. We benchmark current state-of-the-art LLMs, which obtain around 10-15$\%$ accuracy in theorem proving (pass@1) depending on the model, showing that there is currently a large margin of progression for LLMs to reach human-level proving capabilities in a research context.

---

### ArgLLM-App: An Interactive System for Argumentative Reasoning with Large Language Models

Authors: Adam Dejl, Deniz Gorur, Francesca Toni
Published: 2026-02-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.24172v1

Argumentative LLMs (ArgLLMs) are an existing approach leveraging Large Language Models (LLMs) and computational argumentation for decision-making, with the aim of making the resulting decisions faithfully explainable to and contestable by humans. Here we propose a web-based system implementing ArgLLM-empowered agents for binary tasks. ArgLLM-App supports visualisation of the produced explanations and interaction with human users, allowing them to identify and contest any mistakes in the system's reasoning. It is highly modular and enables drawing information from trusted external sources. ArgLLM-App is publicly available at https://argllm.app, with a video demonstration at https://youtu.be/vzwlGOr0sPM.

---

### Hypothesis Testing over Observable Regimes in Singular Models

Authors: Sean Plummer
Published: 2026-02-27
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2602.24165v1

Hypothesis testing in singular statistical models is often regarded as inherently problematic due to non-identifiability and degeneracy of the Fisher information. We show that the fundamental obstruction to testing in such models is not singularity itself, but the formulation of hypotheses on non-identifiable parameter quantities. Testing is inherently a problem in distribution space: if two hypotheses induce overlapping subsets of the model class, then no uniformly consistent test exists. We formalize this overlap obstruction and show that hypotheses depending on non-identifiable parameter functions necessarily fail in this sense. In contrast, hypotheses formulated over identifiable observables-quantities that are determined by the induced distribution-reduce entirely to classical testing theory. When the corresponding distributional regimes are separated in Hellinger distance, uniformly consistent tests exist and posterior contraction follows from standard testing-based arguments. Near singular boundaries, separation may collapse locally, leading to scale-dependent detectability governed jointly by sample size and distance to the singular stratum. We illustrate these phenomena in Gaussian mixture models and reduced-rank regression, exhibiting both untestable non-identifiable hypotheses and classically testable identifiable ones. The results provide a structural classification of which hypotheses in singular models are statistically meaningful.

---

### GeoDiff4D: Geometry-Aware Diffusion for 4D Head Avatar Reconstruction

Authors: Chao Xu, Xiaochen Zhao, Xiang Deng, Jingxiang Sun, Donglin Di, Zhuo Su, Yebin Liu
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24161v2

Reconstructing photorealistic and animatable 4D head avatars from a single portrait image remains a fundamental challenge in computer vision. While diffusion models have enabled remarkable progress in image and video generation for avatar reconstruction, existing methods primarily rely on 2D priors and struggle to achieve consistent 3D geometry. We propose a novel framework that leverages geometry-aware diffusion to learn strong geometry priors for high-fidelity head avatar reconstruction. Our approach jointly synthesizes portrait images and corresponding surface normals, while a pose-free expression encoder captures implicit expression representations. Both synthesized images and expression latents are incorporated into 3D Gaussian-based avatars, enabling photorealistic rendering with accurate geometry. Extensive experiments demonstrate that our method substantially outperforms state-of-the-art approaches in visual quality, expression fidelity, and cross-identity generalization, while supporting real-time rendering.

---

### Manifold-Preserving Superpixel Hierarchies and Embeddings for the Exploration of High-Dimensional Images

Authors: Alexander Vieth, Boudewijn Lelieveldt, Elmar Eisemann, Anna Vilanova, Thomas Höllt
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24160v1

High-dimensional images, or images with a high-dimensional attribute vector per pixel, are commonly explored with coordinated views of a low-dimensional embedding of the attribute space and a conventional image representation. Nowadays, such images can easily contain several million pixels. For such large datasets, hierarchical embedding techniques are better suited to represent the high-dimensional attribute space than flat dimensionality reduction methods. However, available hierarchical dimensionality reduction methods construct the hierarchy purely based on the attribute information and ignore the spatial layout of pixels in the images. This impedes the exploration of regions of interest in the image space, since there is no congruence between a region of interest in image space and the associated attribute abstractions in the hierarchy. In this paper, we present a superpixel hierarchy for high-dimensional images that takes the high-dimensional attribute manifold into account during construction. Through this, our method enables consistent exploration of high-dimensional images in both image and attribute space. We show the effectiveness of this new image-guided hierarchy in the context of embedding exploration by comparing it with classical hierarchical embedding-based image exploration in two use cases.

---

### RAViT: Resolution-Adaptive Vision Transformer

Authors: Martial Guidez, Stefan Duffner, Christophe Garcia
Published: 2026-02-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.24159v1

Vision transformers have recently made a breakthrough in computer vision showing excellent performance in terms of precision for numerous applications. However, their computational cost is very high compared to alternative approaches such as Convolutional Neural Networks. To address this problem, we propose a novel framework for image classification called RAViT based on a multi-branch network that operates on several copies of the same image with different resolutions to reduce the computational cost while preserving the overall accuracy. Furthermore, our framework includes an early exit mechanism that makes our model adaptive and allows to choose the appropriate trade-off between accuracy and computational cost at run-time. For example in a two-branch architecture, the original image is first resized to reduce its resolution, then a prediction is performed on it using a first transformer and the resulting prediction is reused together with the original-size image to perform a final prediction on a second transformer with less computation than a classical Vision transformer architecture. The early-exit process allows the model to make a final prediction at intermediate branches, saving even more computation. We evaluated our approach on CIFAR-10, Tiny ImageNet, and ImageNet. We obtained an equivalent accuracy to the classical Vision transformer model with only around 70% of FLOPs.

---

### What You Read is What You Classify: Highlighting Attributions to Text and Text-Like Inputs

Authors: Daniel S. Berman, Brian Merritt, Stanley Ta, Dana Udwin, Amanda Ernlund, Jeremy Ratcliff, Vijay Narayan
Published: 2026-02-27
Categories: cs.LG, q-bio.GN
arXiv: https://arxiv.org/abs/2602.24149v2

At present, there are no easily understood explainable artificial intelligence (AI) methods for discrete token inputs, like text. Most explainable AI techniques do not extend well to token sequences, where both local and global features matter, because state-of-the-art models, like transformers, tend to focus on global connections. Therefore, existing explainable AI algorithms fail by (i) identifying disparate tokens of importance, or (ii) assigning a large number of tokens a low value of importance. This method for explainable AI for tokens-based classifiers generalizes a mask-based explainable AI algorithm for images. It starts with an Explainer neural network that is trained to create masks to hide information not relevant for classification. Then, the Hadamard product of the mask and the continuous values of the classifier's embedding layer is taken and passed through the classifier, changing the magnitude of the embedding vector but keeping the orientation unchanged. The Explainer is trained for a taxonomic classifier for nucleotide sequences and it is shown that the masked segments are less relevant to classification than the unmasked ones. This method focused on the importance the token as a whole (i.e., a segment of the input sequence), producing a human-readable explanation.

---

### HumanOrbit: 3D Human Reconstruction as 360° Orbit Generation

Authors: Keito Suzuki, Kunyao Chen, Lei Wang, Bang Du, Runfa Blark Li, Peng Liu, Ning Bi, Truong Nguyen
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24148v1

We present a method for generating a full 360° orbit video around a person from a single input image. Existing methods typically adapt image-based diffusion models for multi-view synthesis, but yield inconsistent results across views and with the original identity. In contrast, recent video diffusion models have demonstrated their ability in generating photorealistic results that align well with the given prompts. Inspired by these results, we propose HumanOrbit, a video diffusion model for multi-view human image generation. Our approach enables the model to synthesize continuous camera rotations around the subject, producing geometrically consistent novel views while preserving the appearance and identity of the person. Using the generated multi-view frames, we further propose a reconstruction pipeline that recovers a textured mesh of the subject. Experimental results validate the effectiveness of HumanOrbit for multi-view image generation and that the reconstructed 3D models exhibit superior completeness and fidelity compared to those from state-of-the-art baselines.

---

### Learning with a Budget: Identifying the Best Arm with Resource Constraints

Authors: Zitian Li, Wang Chi Cheung
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.24146v1

In many applications, evaluating the effectiveness of different alternatives comes with varying costs or resource usage. Motivated by such heterogeneity, we study the Best Arm Identification with Resource Constraints (BAIwRC) problem, where an agent seeks to identify the best alternative (aka arm) in the presence of resource constraints. Each arm pull consumes one or more types of limited resources. We make two key contributions. First, we propose the Successive Halving with Resource Rationing (SH-RR) algorithm, which integrates resource-aware allocation into the classical successive halving framework on best arm identification. The SH-RR algorithm unifies the theoretical analysis for both the stochastic and deterministic consumption settings, with a new \textit{effective consumption measure

---

### Fixed Anchors Are Not Enough: Dynamic Retrieval and Persistent Homology for Dataset Distillation

Authors: Muquan Li, Hang Gou, Yingyi Ma, Rongzheng Wang, Ke Qin, Tao He
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24144v3

Decoupled dataset distillation (DD) compresses large corpora into a few synthetic images by matching a frozen teacher's statistics. However, current residual-matching pipelines rely on static real patches, creating a fit-complexity gap and a pull-to-anchor effect that reduce intra-class diversity and hurt generalization. To address these issues, we introduce RETA -- a Retrieval and Topology Alignment framework for decoupled DD. First, Dynamic Retrieval Connection (DRC) selects a real patch from a prebuilt pool by minimizing a fit-complexity score in teacher feature space; the chosen patch is injected via a residual connection to tighten feature fit while controlling injected complexity. Second, Persistent Topology Alignment (PTA) regularizes synthesis with persistent homology: we build a mutual k-NN feature graph, compute persistence images of components and loops, and penalize topology discrepancies between real and synthetic sets, mitigating pull-to-anchor effect. Across CIFAR-100, Tiny-ImageNet, ImageNet-1K, and multiple ImageNet subsets, RETA consistently outperforms various baselines under comparable time and memory, especially reaching 64.3% top-1 accuracy on ImageNet-1K with ResNet-18 at 50 images per class, +3.1% over the best prior.

---

### CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning

Authors: Yuxuan Liu, Weikai Xu, Kun Huang, Changyu Chen, Jiankun Zhao, Pengzhi Gao, Wei Liu, Jian Luan, Shuo Shang, Bo Du, Ji-Rong Wen, Rui Yan
Published: 2026-02-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.24142v2

Mobile Agents can autonomously execute user instructions, which requires hybrid-capabilities reasoning, including screen summary, subtask planning, action decision and action function. However, existing agents struggle to achieve both decoupled enhancement and balanced integration of these capabilities. To address these challenges, we propose Channel-of-Mobile-Experts (CoME), a novel agent architecture consisting of four distinct experts, each aligned with a specific reasoning stage, CoME activates the corresponding expert to generate output tokens in each reasoning stage via output-oriented activation. To empower CoME with hybrid-capabilities reasoning, we introduce a progressive training strategy: Expert-FT enables decoupling and enhancement of different experts' capability; Router-FT aligns expert activation with the different reasoning stage; CoT-FT facilitates seamless collaboration and balanced optimization across multiple capabilities. To mitigate error propagation in hybrid-capabilities reasoning, we propose InfoGain-Driven DPO (Info-DPO), which uses information gain to evaluate the contribution of each intermediate step, thereby guiding CoME toward more informative reasoning. Comprehensive experiments show that CoME outperforms dense mobile agents and MoE methods on both AITZ and AMEX datasets.

---

### Multimodal Optimal Transport for Training-free Temporal Segmentation in Surgical Robotics

Authors: Omar Mohamed, Edoardo Fazzari, Ayah Al-Naji, Hamdan Alhadhrami, Khalfan Hableel, Saif Alkindi, Ivan Laptev, Cesare Stefanini
Published: 2026-02-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.24138v2

Automated recognition of surgical phases and steps is a fundamental capability for intraoperative decision support, workflow automation, and skill assessment in robotic-assisted surgery. Existing approaches either depend on large-scale annotated surgical datasets or require expensive domain-specific pretraining on thousands of labeled videos, limiting their practical deployability across diverse robotic platforms and clinical environments. In this work, we propose TASOT (Text-Augmented Action Segmentation Optimal Transport), an annotation-free framework for surgical temporal segmentation that requires no task-specific annotations or surgical-domain pretraining. TASOT extends the Action Segmentation Optimal Transport (ASOT) formulation by incorporating temporally aligned textual descriptions generated directly from the input video, fusing visual and semantic cues within a unified unbalanced Gromov-Wasserstein optimal transport objective. Visual representations are extracted using DINOv3, while temporal captions produced by a vision-language model are encoded via CLIP and temporally aligned to individual frames, providing complementary semantic structure to the transport cost. We evaluate TASOT on three public surgical datasets and four benchmark settings spanning laparoscopic and robotic procedures, showing substantial improvements over the strongest zero-shot baselines: +18.9 F1 on Cholec80, +33.7 on AutoLaparo, +23.7 on StrasByPass70, and +4.5 on BernByPass70. These results suggest that fine-grained surgical workflow understanding in robotic settings can be achieved without manual training annotations or surgical-specific pretraining pipelines, offering a promising alternative for real-world robotic surgical systems.

---

### Prune Wisely, Reconstruct Sharply: Compact 3D Gaussian Splatting via Adaptive Pruning and Difference-of-Gaussian Primitives

Authors: Haoran Wang, Guoxi Huang, Fan Zhang, David Bull, Nantheera Anantrasirichai
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24136v1

Recent significant advances in 3D scene representation have been driven by 3D Gaussian Splatting (3DGS), which has enabled real-time rendering with photorealistic quality. 3DGS often requires a large number of primitives to achieve high fidelity, leading to redundant representations and high resource consumption, thereby limiting its scalability for complex or large-scale scenes. Consequently, effective pruning strategies and more expressive primitives that can reduce redundancy while preserving visual quality are crucial for practical deployment. We propose an efficient, integrated reconstruction-aware pruning strategy that adaptively determines pruning timing and refining intervals based on reconstruction quality, thus reducing model size while enhancing rendering quality. Moreover, we introduce a 3D Difference-of-Gaussians primitive that jointly models both positive and negative densities in a single primitive, improving the expressiveness of Gaussians under compact configurations. Our method significantly improves model compactness, achieving up to 90\% reduction in Gaussian-count while delivering visual quality that is similar to, or in some cases better than, that produced by state-of-the-art methods. Code will be made publicly available.

---

### AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation

Authors: Zhengren Wang, Dongsheng Ma, Huaping Zhong, Jiayu Li, Wentao Zhang, Bin Wang, Conghui He
Published: 2026-02-27
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2602.24134v1

The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports. While page-level chunking and retrieval is a natural starting point, it creates a critical bottleneck: delivering entire pages to the generator introduces excessive extraneous context. This not only overloads the generator's attention mechanism but also dilutes the most salient evidence. Moreover, compressing these information-rich pages into a limited visual token budget further increases the risk of hallucinations. To address this, we introduce AgenticOCR, a dynamic parsing paradigm that transforms optical character recognition (OCR) from a static, full-text process into a query-driven, on-demand extraction system. By autonomously analyzing document layout in a "thinking with images" manner, AgenticOCR identifies and selectively recognizes regions of interest. This approach performs on-demand decompression of visual tokens precisely where needed, effectively decoupling retrieval granularity from rigid page-level chunking. AgenticOCR has the potential to serve as the "third building block" of the visual document RAG stack, operating alongside and enhancing standard Embedding and Reranking modules. Experimental results demonstrate that AgenticOCR improves both the efficiency and accuracy of visual RAG systems, achieving expert-level performance in long document understanding. Code and models are available at https://github.com/OpenDataLab/AgenticOCR.

---

### FocusTrack: One-Stage Focus-and-Suppress Framework for 3D Point Cloud Object Tracking

Authors: Sifan Zhou, Jiahao Nie, Ziyu Zhao, Yichao Cao, Xiaobo Lu
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24133v2

In 3D point cloud object tracking, the motion-centric methods have emerged as a promising avenue due to its superior performance in modeling inter-frame motion. However, existing two-stage motion-based approaches suffer from fundamental limitations: (1) error accumulation due to decoupled optimization caused by explicit foreground segmentation prior to motion estimation, and (2) computational bottlenecks from sequential processing. To address these challenges, we propose FocusTrack, a novel one-stage paradigms tracking framework that unifies motion-semantics co-modeling through two core innovations: Inter-frame Motion Modeling (IMM) and Focus-and-Suppress Attention. The IMM module employs a temp-oral-difference siamese encoder to capture global motion patterns between adjacent frames. The Focus-and-Suppress attention that enhance the foreground semantics via motion-salient feature gating and suppress the background noise based on the temporal-aware motion context from IMM without explicit segmentation. Based on above two designs, FocusTrack enables end-to-end training with compact one-stage pipeline. Extensive experiments on prominent 3D tracking benchmarks, such as KITTI, nuScenes, and Waymo, demonstrate that the FocusTrack achieves new SOTA performance while running at a high speed with 105 FPS.

---

### Efficient Targeted Maximum Likelihood Estimators for Two-Phase Design Problems

Authors: Sky Qiu, Susan Gruber, Pamela A. Shaw, Brian D. Williamson, Mark J. van der Laan
Published: 2026-02-27
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2602.24131v1

In a typical two-phase design, a random sample is drawn from the target population in phase 1, during which only a subset of variables is collected. In phase 2, a subsample of the phase-1 cohort is selected, and additional variables are measured. This setting induces a coarsened data structure on the data from the second phase. We assume coarsening at random, that is, the phase-2 sampling mechanism depends only on variables fully observed. We review existing estimators, including the generalized raking estimator and the inverse probability of censoring weighted targeted maximum likelihood estimation (IPCW-TMLE) along with its extensions that also target the phase-2 sampling mechanism to improve efficiency. We further introduce a new class of estimators constructed within the TMLE framework that are asymptotically equivalent.

---

### End-to-end Differentiable Calibration and Reconstruction for Optical Particle Detectors

Authors: Omar Alterkait, César Jesús-Valls, Ryo Matsumoto, Patrick de Perio, Kazuhiro Terao
Published: 2026-02-27
Categories: hep-ex, cs.LG, physics.ins-det
arXiv: https://arxiv.org/abs/2602.24129v3

Large-scale homogeneous detectors with optical readouts are widely used in particle detection, with Cherenkov and scintillator neutrino detectors as prominent examples. Analyses in experimental physics rely on high-fidelity simulators to translate sensor-level information into physical quantities of interest. This task critically depends on accurate calibration, which aligns simulation behavior with real detector data, and on tracking, which infers particle properties from optical signals. We present the first end-to-end differentiable optical particle detector simulator, enabling simultaneous calibration and reconstruction through gradient-based optimization. Our approach unifies simulation, calibration, and tracking, which are traditionally treated as separate problems, within a single differentiable framework. We demonstrate that it achieves smooth and physically meaningful gradients across all key stages of light generation, propagation, and detection while maintaining computational efficiency. We show that gradient-based calibration and reconstruction greatly simplify existing analysis pipelines while matching or surpassing the performance of conventional non-differentiable methods in both accuracy and speed. Moreover, the framework's modularity allows straightforward adaptation to diverse detector geometries and target materials, providing a flexible foundation for experiment design and optimization. The results demonstrate the readiness of this technique for adoption in current and future optical detector experiments, establishing a new paradigm for simulation and reconstruction in particle physics.

---

### End-to-end Differentiable Calibration and Reconstruction for Optical Particle Detectors

Authors: Omar Alterkait, César Jesús-Valls, Ryo Matsumoto, Patrick de Perio, Kazuhiro Terao
Published: 2026-02-27
Categories: hep-ex, cs.LG, physics.ins-det
arXiv: https://arxiv.org/abs/2602.24129v2

Large-scale homogeneous detectors with optical readouts are widely used in particle detection, with Cherenkov and scintillator neutrino detectors as prominent examples. Analyses in experimental physics rely on high-fidelity simulators to translate sensor-level information into physical quantities of interest. This task critically depends on accurate calibration, which aligns simulation behavior with real detector data, and on tracking, which infers particle properties from optical signals. We present the first end-to-end differentiable optical particle detector simulator, enabling simultaneous calibration and reconstruction through gradient-based optimization. Our approach unifies simulation, calibration, and tracking, which are traditionally treated as separate problems, within a single differentiable framework. We demonstrate that it achieves smooth and physically meaningful gradients across all key stages of light generation, propagation, and detection while maintaining computational efficiency. We show that gradient-based calibration and reconstruction greatly simplify existing analysis pipelines while matching or surpassing the performance of conventional non-differentiable methods in both accuracy and speed. Moreover, the framework's modularity allows straightforward adaptation to diverse detector geometries and target materials, providing a flexible foundation for experiment design and optimization. The results demonstrate the readiness of this technique for adoption in current and future optical detector experiments, establishing a new paradigm for simulation and reconstruction in particle physics.

---

### Evaluating LLM-Based Translation of a Low-Resource Technical Language: The Medical and Philosophical Greek of Galen

Authors: James L. Zainaldin, Cameron Pattison, Manuela Marai, Jacob Wu, Mark J. Schiefsky
Published: 2026-02-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.24119v2

Purpose: This study evaluates the quality of commercial large language model (LLM) machine translation (MT) for Ancient Greek technical prose and benchmarks standard automated MT evaluation metrics against expert human judgment. Design: We evaluated 60 translations by three LLMs (ChatGPT, Claude, Gemini) of 20 paragraph-length passages from 2 works by the Greek physician Galen (c. 129-216 CE): an expository text with two published English translations and a pharmacological text never before translated. Quality was assessed using seven automated metrics and systematic reference-free human evaluation via a modified Multidimensional Quality Metrics (MQM) framework applied by domain specialists. Findings: On the translated expository text, LLMs achieved high quality (mean MQM score 95.2/100). On the untranslated pharmacological text, quality was lower (79.9/100) but bimodally distributed: two passages with extreme terminological density produced catastrophic failures, while remaining passages scored within 4 points of the expository text. Terminology rarity, operationalized via corpus frequency, emerged as the dominant predictor of failure (r = -.97). Automated metrics showed moderate correlation with human judgment only on texts with wide quality variance; no metric discriminated among high-quality translations. Originality: This is the first systematic, reference-free expert human evaluation of LLM translation for any ancient language and the first study identifying textual properties predictive of translation failure.

---

### Agentic AI-RAN: Enabling Intent-Driven, Explainable and Self-Evolving Open RAN Intelligence

Authors: Zhizhou He, Yang Luo, Xinkai Liu, Mahdi Boloursaz Mashhadi, Mohammad Shojafar, Merouane Debbah, Rahim Tafazolli
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.24115v2

Open RAN (O-RAN) exposes rich control and telemetry interfaces across the Non-RT RIC, Near-RT RIC, and distributed units, but also makes it harder to operate multi-tenant, multi-objective RANs in a safe and auditable manner. In parallel, agentic AI systems with explicit planning, tool use, memory, and self-management offer a natural way to structure long-lived control loops. This article surveys how such agentic controllers can be brought into O-RAN: we review the O-RAN architecture, contrast agentic controllers with conventional ML/RL xApps, and organise the task landscape around three clusters: network slice life-cycle, radio resource management (RRM) closed loops, and cross-cutting security, privacy, and compliance. We then introduce a small set of agentic primitives (Plan-Act-Observe-Reflect, skills as tool use, memory and evidence, and self-management gates) and show, in a multi-cell O-RAN simulation, how they improve slice life-cycle and RRM performance compared to conventional baselines and ablations that remove individual primitives. Security, privacy, and compliance are discussed as architectural constraints and open challenges for standards-aligned deployments. This framework achieves an average 8.83\% reduction in resource usage across three classic network slices.

---

### Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification

Authors: Vikash Singh, Debargha Ganguly, Haotian Yu, Chengwei Zhou, Prerna Singh, Brandon Lee, Vipin Chaudhary, Gourav Datta
Published: 2026-02-27
Categories: cs.CV, cs.AI, cs.CL, cs.LO
arXiv: https://arxiv.org/abs/2602.24111v1

Vision-language models (VLMs) show promise in drafting radiology reports, yet they frequently suffer from logical inconsistencies, generating diagnostic impressions unsupported by their own perceptual findings or missing logically entailed conclusions. Standard lexical metrics heavily penalize clinical paraphrasing and fail to capture these deductive failures in reference-free settings. Toward guarantees for clinical reasoning, we introduce a neurosymbolic verification framework that deterministically audits the internal consistency of VLM-generated reports. Our pipeline autoformalizes free-text radiographic findings into structured propositional evidence, utilizing an SMT solver (Z3) and a clinical knowledge base to verify whether each diagnostic claim is mathematically entailed, hallucinated, or omitted. Evaluating seven VLMs across five chest X-ray benchmarks, our verifier exposes distinct reasoning failure modes, such as conservative observation and stochastic hallucination, that remain invisible to traditional metrics. On labeled datasets, enforcing solver-backed entailment acts as a rigorous post-hoc guarantee, systematically eliminating unsupported hallucinations to significantly increase diagnostic soundness and precision in generative clinical assistants.

---

### Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance

Authors: Yanwei Ren, Haotian Zhang, Likang Xiao, Xikai Zhang, Jiaxing Huang, Jiayan Qiu, Baosheng Yu, Quan Chen, Liu Liu
Published: 2026-02-27
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.24110v1

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the complex reasoning capabilities of Large Reasoning Models. However, standard outcome-based supervision suffers from a critical limitation that penalizes trajectories that are largely correct but fail due to several missteps as heavily as completely erroneous ones. This coarse feedback signal causes the model to discard valuable largely correct rollouts, leading to a degradation in rollout diversity that prematurely narrows the exploration space. Process Reward Models have demonstrated efficacy in providing reliable step-wise verification for test-time scaling, naively integrating these signals into RLVR as dense rewards proves ineffective.Prior methods attempt to introduce off-policy guided whole-trajectory replacement that often outside the policy model's distribution, but still fail to utilize the largely correct rollouts generated by the model itself and thus do not effectively mitigate the narrowing of the exploration space. To address these issues, we propose SCOPE (Step-wise Correction for On-Policy Exploration), a novel framework that utilizes Process Reward Models to pinpoint the first erroneous step in suboptimal rollouts and applies fine-grained, step-wise off-policy rectification. By applying precise refinement on partially correct rollout, our method effectively salvages partially correct trajectories and increases diversity score by 13.5%, thereby sustaining a broad exploration space. Extensive experiments demonstrate that our approach establishes new state-of-the-art results, achieving an average accuracy of 46.6% on math reasoning and exhibiting robust generalization with 53.4% accuracy on out-of-distribution reasoning tasks.

---

### ARGUS: Seeing the Influence of Narrative Features on Persuasion in Argumentative Texts

Authors: Sara Nabhani, Federico Pianzola, Khalid Al-Khatib, Malvina Nissim
Published: 2026-02-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.24109v1

Can narratives make arguments more persuasive? And to this end, which narrative features matter most? Although stories are often seen as powerful tools for persuasion, their specific role in online, unstructured argumentation remains underexplored. To address this gap, we present ARGUS, a framework for studying the impact of narration on persuasion in argumentative discourse. ARGUS introduces a new ChangeMyView corpus annotated for story presence and six key narrative features, integrating insights from two established theoretical frameworks that capture both textual narrative features and their effects on recipients. Leveraging both encoder-based classifiers and zero-shot large language models (LLMs), ARGUS identifies stories and narrative features and applies them at scale to examine how different narrative dimensions influence persuasion success in online argumentation.

---

### Artificial Agency Program: Curiosity, compression, and communication in agents

Authors: Richard Csaky
Published: 2026-02-27
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.24100v1

This paper presents the Artificial Agency Program (AAP), a position and research agenda for building AI systems as reality embedded, resource-bounded agents whose development is driven by curiosity-as-learning-progress under physical and computational constraints. The central thesis is that AI is most useful when treated as part of an extended human--tool system that increases sensing, understanding, and actuation capability while reducing friction at the interface between people, tools, and environments. The agenda unifies predictive compression, intrinsic motivation, empowerment and control, interface quality (unification), and language/self-communication as selective information bottlenecks. We formulate these ideas as a falsifiable program with explicit costs, staged experiments, and a concrete multimodal tokenized testbed in which an agent allocates limited budget among observation, action, and deliberation. The aim is to provide a conceptual and experimental framework that connects intrinsic motivation, information theory, thermodynamics, bounded rationality, and modern reasoning systems

---

### Bi-level RL-Heuristic Optimization for Real-world Winter Road Maintenance

Authors: Yue Xie, Zizhen Xu, William Beazley, Fumiya Iida
Published: 2026-02-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.24097v1

Winter road maintenance is critical for ensuring public safety and reducing environmental impacts, yet existing methods struggle to manage large-scale routing problems effectively and mostly reply on human decision. This study presents a novel, scalable bi-level optimization framework, validated on real operational data on UK strategic road networks (M25, M6, A1), including interconnected local road networks in surrounding areas for vehicle traversing, as part of the highway operator's efforts to solve existing planning challenges. At the upper level, a reinforcement learning (RL) agent strategically partitions the road network into manageable clusters and optimally allocates resources from multiple depots. At the lower level, a multi-objective vehicle routing problem (VRP) is solved within each cluster, minimizing the maximum vehicle travel time and total carbon emissions. Unlike existing approaches, our method handles large-scale, real-world networks efficiently, explicitly incorporating vehicle-specific constraints, depot capacities, and road segment requirements. Results demonstrate significant improvements, including balanced workloads, reduced maximum travel times below the targeted two-hour threshold, lower emissions, and substantial cost savings. This study illustrates how advanced AI-driven bi-level optimization can directly enhance operational decision-making in real-world transportation and logistics.

---

### DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer

Authors: Yuxuan Zhang, Katarína Tóthová, Zian Wang, Kangxue Yin, Haithem Turki, Riccardo de Lutio, Yen-Yu Chang, Or Litany, Sanja Fidler, Zan Gojcic
Published: 2026-02-27
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.24096v2

Simulation is essential to the development and evaluation of autonomous robots such as self-driving vehicles. Neural reconstruction is emerging as a promising solution as it enables simulating a wide variety of scenarios from real-world data alone in an automated and scalable way. However, while methods such as NeRF and 3D Gaussian Splatting can produce visually compelling results, they often exhibit artifacts particularly when rendering novel views, and fail to realistically integrate inserted dynamic objects, especially when they were captured from different scenes. To overcome these limitations, we introduce DiffusionHarmonizer, an online generative enhancement framework that transforms renderings from such imperfect scenes into temporally consistent outputs while improving their realism. At its core is a single-step temporally-conditioned enhancer that is converted from a pretrained multi-step image diffusion model, capable of running in online simulators on a single GPU. The key to training it effectively is a custom data curation pipeline that constructs synthetic-real pairs emphasizing appearance harmonization, artifact correction, and lighting realism. The result is a scalable system that significantly elevates simulation fidelity in both research and production environments.

---

### The Subjectivity of Monoculture

Authors: Nathanael Jo, Nikhil Garg, Manish Raghavan
Published: 2026-02-27
Categories: cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2602.24086v1

Machine learning models -- including large language models (LLMs) -- are often said to exhibit monoculture, where outputs agree strikingly often. But what does it actually mean for models to agree too much? We argue that this question is inherently subjective, relying on two key decisions. First, the analyst must specify a baseline null model for what "independence" should look like. This choice is inherently subjective, and as we show, different null models result in dramatically different inferences about excess agreement. Second, we show that inferences depend on the population of models and items under consideration. Models that seem highly correlated in one context may appear independent when evaluated on a different set of questions, or against a different set of peers. Experiments on two large-scale benchmarks validate our theoretical findings. For example, we find drastically different inferences when using a null model with item difficulty compared to previous works that do not. Together, our results reframe monoculture evaluation not as an absolute property of model behavior, but as a context-dependent inference problem.

---

### FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Casting

Authors: Matteo Ballegeer, Dries F. Benoit
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24084v2

Learning directly from boundary representations (B-reps) has significantly advanced 3D CAD analysis. However, state-of-the-art B-rep learning methods rely on absolute coordinates and normals to encode global context, making them highly sensitive to rotations. Our experiments reveal that models achieving over 95% accuracy on aligned benchmarks can collapse to as low as 10% under arbitrary $\mathbf{SO}(3)$ rotations. To address this, we introduce FoV-Net, the first B-rep learning framework that captures both local surface geometry and global structural context in a rotation-invariant manner. Each face is represented by a Local Reference Frame (LRF) UV-grid that encodes its local surface geometry, and by Field-of-View (FoV) grids that capture the surrounding 3D context by casting rays and recording intersections with neighboring faces. Lightweight CNNs extract per-face features, which are propagated over the B-rep graph using a graph attention network. FoV-Net achieves state-of-the-art performance on B-rep classification and segmentation benchmarks, demonstrating robustness to arbitrary rotations while also requiring less training data to achieve strong results.

---

### Neural Diffusion Intensity Models for Point Process Data

Authors: Xinlong Du, Harsha Honnappa, Vinayak Rao
Published: 2026-02-27
Categories: cs.LG, math.PR, stat.ML
arXiv: https://arxiv.org/abs/2602.24083v1

Cox processes model overdispersed point process data via a latent stochastic intensity, but both nonparametric estimation of the intensity model and posterior inference over intensity paths are typically intractable, relying on expensive MCMC methods. We introduce Neural Diffusion Intensity Models, a variational framework for Cox processes driven by neural SDEs. Our key theoretical result, based on enlargement of filtrations, shows that conditioning on point process observations preserves the diffusion structure of the latent intensity with an explicit drift correction. This guarantees the variational family contains the true posterior, so that ELBO maximization coincides with maximum likelihood estimation under sufficient model capacity. We design an amortized encoder architecture that maps variable-length event sequences to posterior intensity paths by simulating the drift-corrected SDE, replacing repeated MCMC runs with a single forward pass. Experiments on synthetic and real-world data demonstrate accurate recovery of latent intensity dynamics and posterior paths, with orders-of-magnitude speedups over MCMC-based methods.

---

### Preference Packing: Efficient Preference Optimization for Large Language Models

Authors: Jaekyung Cho
Published: 2026-02-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.24082v1

Resource-efficient training optimization techniques are becoming increasingly important as the size of large language models (LLMs) continues to grow. In particular, batch packing is commonly used in pre-training and supervised fine-tuning to achieve resource-efficient training. We propose preference packing, a method to enhance resource efficiency in training techniques that use data with different responses for the same input prompt, such as reward models or Direct Preference Optimization (DPO). Preference packing improves resource efficiency by reducing the attention operations for duplicate input prompts and decreasing KV cache memory usage. We conducted experiments on text-only datasets and image-included datasets and achieved at least 37% reduction in training time. Notably, this method can be applied alongside existing optimization techniques such as batch sorting, resulting in a 3.22x speedup.

---

### Adaptive Correlation-Weighted Intrinsic Rewards for Reinforcement Learning

Authors: Viet Bac Nguyen, Phuong Thai Nguyen
Published: 2026-02-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.24081v1

We propose ACWI (Adaptive Correlation Weighted Intrinsic), an adaptive intrinsic reward scaling framework designed to dynamically balance intrinsic and extrinsic rewards for improved exploration in sparse reward reinforcement learning. Unlike conventional approaches that rely on manually tuned scalar coefficients, which often result in unstable or suboptimal performance across tasks, ACWI learns a state dependent scaling coefficient online. Specifically, ACWI introduces a lightweight Beta Network that predicts the intrinsic reward weight directly from the agent state through an encoder based architecture. The scaling mechanism is optimized using a correlation based objective that encourages alignment between the weighted intrinsic rewards and discounted future extrinsic returns. This formulation enables task adaptive exploration incentives while preserving computational efficiency and training stability. We evaluate ACWI on a suite of sparse reward environments in MiniGrid. Experimental results demonstrate that ACWI consistently improves sample efficiency and learning stability compared to fixed intrinsic reward baselines, achieving superior performance with minimal computational overhead.

---

### Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction

Authors: Xiang Li, Jiabao Gao, Sipei Lin, Xuan Zhou, Chi Zhang, Bo Cheng, Jiale Han, Benyou Wang
Published: 2026-02-27
Categories: cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2602.24080v3

The pursuit of human-like conversational agents has long been guided by the Turing test. For modern speech-to-speech (S2S) systems, a critical yet unanswered question is whether they can converse like humans. To tackle this, we conduct the first Turing test for S2S systems, collecting 2,968 human judgments on dialogues between 9 state-of-the-art S2S systems and 28 human participants. Our results deliver a clear finding: no existing evaluated S2S system passes the test, revealing a significant gap in human-likeness. To diagnose this failure, we develop a fine-grained taxonomy of 18 human-likeness dimensions and crowd-annotate our collected dialogues accordingly. Our analysis shows that the bottleneck is not semantic understanding but stems from paralinguistic features, emotional expressivity, and conversational persona. Furthermore, we find that off-the-shelf AI models perform unreliably as Turing test judges. In response, we propose an interpretable model that leverages the fine-grained human-likeness ratings and delivers accurate and transparent human-vs-machine discrimination, offering a powerful tool for automatic human-likeness evaluation. Our work establishes the first human-likeness evaluation for S2S systems and moves beyond binary outcomes to enable detailed diagnostic insights, paving the way for human-like improvements in conversational AI systems.

---

### Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction

Authors: Xiang Li, Jiabao Gao, Sipei Lin, Xuan Zhou, Chi Zhang, Bo Cheng, Jiale Han, Benyou Wang
Published: 2026-02-27
Categories: cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2602.24080v2

The pursuit of human-like conversational agents has long been guided by the Turing test. For modern speech-to-speech (S2S) systems, a critical yet unanswered question is whether they can converse like humans. To tackle this, we conduct the first Turing test for S2S systems, collecting 2,968 human judgments on dialogues between 9 state-of-the-art S2S systems and 28 human participants. Our results deliver a clear finding: no existing evaluated S2S system passes the test, revealing a significant gap in human-likeness. To diagnose this failure, we develop a fine-grained taxonomy of 18 human-likeness dimensions and crowd-annotate our collected dialogues accordingly. Our analysis shows that the bottleneck is not semantic understanding but stems from paralinguistic features, emotional expressivity, and conversational persona. Furthermore, we find that off-the-shelf AI models perform unreliably as Turing test judges. In response, we propose an interpretable model that leverages the fine-grained human-likeness ratings and delivers accurate and transparent human-vs-machine discrimination, offering a powerful tool for automatic human-likeness evaluation. Our work establishes the first human-likeness evaluation for S2S systems and moves beyond binary outcomes to enable detailed diagnostic insights, paving the way for human-like improvements in conversational AI systems.

---

### SongSong: A Time Phonograph for Chinese SongCi Music from Thousand of Years Away

Authors: Jiajia Li, Jiliang Hu, Ziyi Pan, Chong Chen, Zuchao Li, Ping Wang, Lefei Zhang
Published: 2026-02-27
Categories: cs.SD, cs.CL
arXiv: https://arxiv.org/abs/2602.24071v1

Recently, there have been significant advancements in music generation. However, existing models primarily focus on creating modern pop songs, making it challenging to produce ancient music with distinct rhythms and styles, such as ancient Chinese SongCi. In this paper, we introduce SongSong, the first music generation model capable of restoring Chinese SongCi to our knowledge. Our model first predicts the melody from the input SongCi, then separately generates the singing voice and accompaniment based on that melody, and finally combines all elements to create the final piece of music. Additionally, to address the lack of ancient music datasets, we create OpenSongSong, a comprehensive dataset of ancient Chinese SongCi music, featuring 29.9 hours of compositions by various renowned SongCi music masters. To assess SongSong's proficiency in performing SongCi, we randomly select 85 SongCi sentences that were not part of the training set for evaluation against SongSong and music generation platforms such as Suno and SkyMusic. The subjective and objective outcomes indicate that our proposed model achieves leading performance in generating high-quality SongCi music.

---

### Leveraging Non-linear Dimension Reduction and Random Walk Co-occurrence for Node Embedding

Authors: Ryan DeWolfe
Published: 2026-02-27
Categories: cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2602.24069v1

Leveraging non-linear dimension reduction techniques, we remove the low dimension constraint from node embedding and propose COVE, an explainable high dimensional embedding that, when reduced to low dimension with UMAP, slightly increases performance on clustering and link prediction tasks. The embedding is inspired by neural embedding methods that use co-occurrence on a random walk as an indication of similarity, and is closely related to a diffusion process. Extending on recent community detection benchmarks, we find that a COVE UMAP HDBSCAN pipeline performs similarly to the popular Louvain algorithm.

---

### A Novel Hierarchical Multi-Agent System for Payments Using LLMs

Authors: Joon Kiat Chua, Donghao Huang, Zhaoxia Wang
Published: 2026-02-27
Categories: cs.MA, cs.CL
arXiv: https://arxiv.org/abs/2602.24068v1

Large language model (LLM) agents, such as OpenAI's Operator and Claude's Computer Use, can automate workflows but unable to handle payment tasks. Existing agentic solutions have gained significant attention; however, even the latest approaches face challenges in implementing end-to-end agentic payment workflows. To address this gap, this research proposes the Hierarchical Multi-Agent System for Payments (HMASP), which provides an end-to-end agentic method for completing payment workflows. The proposed HMASP leverages either open-weight or proprietary LLMs and employs a modular architecture consisting of the Conversational Payment Agent (CPA - first agent level), Supervisor agents (second agent level), Routing agents (third agent level), and the Process summary agent (fourth agent level). The CPA serves as the central entry point, handling all external requests and coordinating subsequent tasks across hierarchical levels. HMASP incorporates architectural patterns that enable modular task execution across agents and levels for payment operations, including shared state variables, decoupled message states, and structured handoff protocols that facilitate coordination across agents and workflows. Experimental results demonstrate the feasibility of the proposed HMASP. To our knowledge, HMASP is the first LLM-based multi-agent system to implement end-to-end agentic payment workflows. This work lays a foundation for extending agentic capabilities into the payment domain.

---

### pathsig: A GPU-Accelerated Library for Truncated and Projected Path Signatures

Authors: Tobias Nygaard
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.24066v1

Path signatures provide a rich representation of sequential data, with strong theoretical guarantees and good performance in a variety of machine-learning tasks. While signatures have progressed from fixed feature extractors to trainable components of machine-learning models, existing libraries often lack the required scalability for large-scale, gradient-based learning. To address this gap, this paper introduces pathsig, a PyTorch-native library that computes path signatures directly in the word basis. By using CUDA kernels to update signature coefficients in parallel over prefix-closed word sets, pathsig achieves high GPU throughput and near-minimal peak memory. Compared with other libraries, pathsig achieves 10-30x speedups for computation of truncated signatures and up to 4-10x speedups in training that require backpropagation through the signature. Beyond regular truncation, pathsig supports projections of the (infinite-dimensional) signature onto user-specified sets of words and anisotropic truncation motivated by inhomogeneous path regularity, enabling more compact representations that can reduce dimensionality, redundancy, and computational cost.

---

### EvalMVX: A Unified Benchmarking for Neural 3D Reconstruction under Diverse Multiview Setups

Authors: Zaiyan Yang, Jieji Ren, Xiangyi Wang, zonglin li, Xu Cao, Heng Guo, Zhanyu Ma, Boxin Shi
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24065v2

Recent advancements in neural surface reconstruction have significantly enhanced 3D reconstruction. However, current real world datasets mainly focus on benchmarking multiview stereo (MVS) based on RGB inputs. Multiview photometric stereo (MVPS) and multiview shape from polarization (MVSfP), though indispensable on high-fidelity surface reconstruction and sparse inputs, have not been quantitatively assessed together with MVS. To determine the working range of different MVX (MVS, MVSfP, and MVPS) techniques, we propose EvalMVX, a real-world dataset containing $25$ objects, each captured with a polarized camera under $20$ varying views and $17$ light conditions including OLAT and natural illumination, leading to $8,500$ images. Each object includes aligned ground-truth 3D mesh, facilitating quantitative benchmarking of MVX methods simultaneously. Based on our EvalMVX, we evaluate $13$ MVX methods published in recent years, record the best-performing methods, and identify open problems under diverse geometric details and reflectance types. We hope EvalMVX and the benchmarking results can inspire future research on multiview 3D reconstruction.

---