# Research Papers — 2026-02 · bundle page 46 of 210

> Full-text markdown of papers #2251–2300 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/46
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/45.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/47.md)

### Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework

Authors: Yibo Yan, Mingdong Ou, Yi Cao, Xin Zou, Jiahao Huo, Shuliang Liu, James Kwok, Xuming Hu
Published: 2026-02-23
Categories: cs.CL, cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2602.19549v2

Visual Document Retrieval (VDR), which aims to retrieve relevant pages within vast corpora of visually-rich documents, is of significance in current multimodal retrieval applications. The state-of-the-art multi-vector paradigm excels in performance but suffers from prohibitive overhead, a problem that current efficiency methods like pruning and merging address imperfectly, creating a difficult trade-off between compression rate and feature fidelity. To overcome this dilemma, we introduce Prune-then-Merge, a novel two-stage framework that synergizes these complementary approaches. Our method first employs an adaptive pruning stage to filter out low-information patches, creating a refined, high-signal set of embeddings. Subsequently, a hierarchical merging stage compresses this pre-filtered set, effectively summarizing semantic content without the noise-induced feature dilution seen in single-stage methods. Extensive experiments on 29 VDR datasets demonstrate that our framework consistently outperforms existing methods, significantly extending the near-lossless compression range and providing robust performance at high compression ratios.

---

### Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining

Authors: Jeffrey Li, Josh Gardner, Doug Kang, Fangping Shi, Karanjeet Singh, Chun-Liang Li, Herumb Shandilya, David Hall, Oncel Tuzel, Percy Liang, Ludwig Schmidt, Hadi Pour Ansari et al.
Published: 2026-02-23
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.19548v1

One of the first pre-processing steps for constructing web-scale LLM pretraining datasets involves extracting text from HTML. Despite the immense diversity of web content, existing open-source datasets predominantly apply a single fixed extractor to all webpages. In this work, we investigate whether this practice leads to suboptimal coverage and utilization of Internet data. We first show that while different extractors may lead to similar model performance on standard language understanding tasks, the pages surviving a fixed filtering pipeline can differ substantially. This suggests a simple intervention: by taking a Union over different extractors, we can increase the token yield of DCLM-Baseline by up to 71% while maintaining benchmark performance. We further show that for structured content such as tables and code blocks, extractor choice can significantly impact downstream task performance, with differences of up to 10 percentage points (p.p.) on WikiTQ and 3 p.p. on HumanEval.

---

### Hyper-KGGen: A Skill-Driven Knowledge Extractor for High-Quality Knowledge Hypergraph Generation

Authors: Rizhuo Huang, Yifan Feng, Rundong Xue, Shihui Ying, Jun-Hai Yong, Chuan Shi, Shaoyi Du, Yue Gao
Published: 2026-02-23
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2602.19543v2

Knowledge hypergraphs surpass traditional binary knowledge graphs by encapsulating complex n-ary atomic facts, providing a more comprehensive paradigm for semantic representation. However, constructing high-quality hypergraphs remains challenging due to the scenario gap: generic extractors struggle to generalize across diverse domains with specific jargon, while existing methods often fail to balance structural skeletons with fine-grained details. To bridge this gap, we propose Hyper-KGGen, a skill-driven framework that reformulates extraction as a dynamic skill-evolving process. First, Hyper-KGGen employs a coarse-to-fine mechanism to systematically decompose documents, ensuring full-dimensional coverage from binary links to complex hyperedges. Crucially, it incorporates an adaptive skill acquisition module that actively distills domain expertise into a Global Skill Library. This is achieved via a stability-based feedback loop, where extraction stability serves as a relative reward signal to induce high-quality skills from unstable traces and missed predictions. Additionally, we present HyperDocRED, a rigorously annotated benchmark for document-level knowledge hypergraph extraction. Experiments demonstrate that Hyper-KGGen significantly outperforms strong baselines, validating that evolved skills provide substantially richer guidance than static few-shot examples in multi-scenario settings.

---

### Vinedresser3D: Agentic Text-guided 3D Editing

Authors: Yankuan Chi, Xiang Li, Zixuan Huang, James M. Rehg
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19542v1

Text-guided 3D editing aims to modify existing 3D assets using natural-language instructions. Current methods struggle to jointly understand complex prompts, automatically localize edits in 3D, and preserve unedited content. We introduce Vinedresser3D, an agentic framework for high-quality text-guided 3D editing that operates directly in the latent space of a native 3D generative model. Given a 3D asset and an editing prompt, Vinedresser3D uses a multimodal large language model to infer rich descriptions of the original asset, identify the edit region and edit type (addition, modification, deletion), and generate decomposed structural and appearance-level text guidance. The agent then selects an informative view and applies an image editing model to obtain visual guidance. Finally, an inversion-based rectified-flow inpainting pipeline with an interleaved sampling module performs editing in the 3D latent space, enforcing prompt alignment while maintaining 3D coherence and unedited regions. Experiments on diverse 3D edits demonstrate that Vinedresser3D outperforms prior baselines in both automatic metrics and human preference studies, while enabling precise, coherent, and mask-free 3D editing.

---

### A Green Learning Approach to LDCT Image Restoration

Authors: Wei Wang, Yixing Wu, C. -C. Jay Kuo
Published: 2026-02-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.19540v1

This work proposes a green learning (GL) approach to restore medical images. Without loss of generality, we use low-dose computed tomography (LDCT) images as examples. LDCT images are susceptible to noise and artifacts, where the imaging process introduces distortion. LDCT image restoration is an important preprocessing step for further medical analysis. Deep learning (DL) methods have been developed to solve this problem. We examine an alternative solution using the Green Learning (GL) methodology. The new restoration method is characterized by mathematical transparency, computational and memory efficiency, and high performance. Experiments show that our GL method offers state-of-the-art restoration performance at a smaller model size and with lower inference complexity.

---

### Can a Teenager Fool an AI? Evaluating Low-Cost Cosmetic Attacks on Age Estimation Systems

Authors: Xingyu Shen, Tommy Duong, Xiaodong An, Zengqi Zhao, Zebang Hu, Haoyu Hu, Ziyou Wang, Finn Guo, Simiao Ren
Published: 2026-02-23
Categories: cs.CV, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2602.19539v1

Age estimation systems are increasingly deployed as gatekeepers for age-restricted online content, yet their robustness to cosmetic modifications has not been systematically evaluated. We investigate whether simple, household-accessible cosmetic changes, including beards, grey hair, makeup, and simulated wrinkles, can cause AI age estimators to classify minors as adults. To study this threat at scale without ethical concerns, we simulate these physical attacks on 329 facial images of individuals aged 10 to 21 using a VLM image editor (Gemini 2.5 Flash Image). We then evaluate eight models from our prior benchmark: five specialized architectures (MiVOLO, Custom-Best, Herosan, MiViaLab, DEX) and three vision-language models (Gemini 3 Flash, Gemini 2.5 Flash, GPT-5-Nano). We introduce the Attack Conversion Rate (ACR), defined as the fraction of images predicted as minor at baseline that flip to adult after attack, a population-agnostic metric that does not depend on the ratio of minors to adults in the test set. Our results reveal that a synthetic beard alone achieves 28 to 69 percent ACR across all eight models; combining all four attacks shifts predicted age by +7.7 years on average across all 329 subjects and reaches up to 83 percent ACR; and vision-language models exhibit lower ACR (59 to 71 percent) than specialized models (63 to 83 percent) under the full attack, although the ACR ranges overlap and the difference is not statistically tested. These findings highlight a critical vulnerability in deployed age-verification pipelines and call for adversarial robustness evaluation as a mandatory criterion for model selection.

---

### Cost-Aware Diffusion Active Search

Authors: Arundhati Banerjee, Jeff Schneider
Published: 2026-02-23
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.19538v1

Active search for recovering objects of interest through online, adaptive decision making with autonomous agents requires trading off exploration of unknown environments with exploitation of prior observations in the search space. Prior work has proposed information gain and Thompson sampling based myopic, greedy approaches for agents to actively decide query or search locations when the number of targets is unknown. Decision making algorithms in such partially observable environments have also shown that agents capable of lookahead over a finite horizon outperform myopic policies for active search. Unfortunately, lookahead algorithms typically rely on building a computationally expensive search tree that is simulated and updated based on the agent's observations and a model of the environment dynamics. Instead, in this work, we leverage the sequence modeling abilities of diffusion models to sample lookahead action sequences that balance the exploration-exploitation trade-off for active search without building an exhaustive search tree. We identify the optimism bias in prior diffusion based reinforcement learning approaches when applied to the active search setting and propose mitigating solutions for efficient cost-aware decision making with both single and multi-agent teams. Our proposed algorithm outperforms standard baselines in offline reinforcement learning in terms of full recovery rate and is computationally more efficient than tree search in cost-aware active decision making.

---

### Fore-Mamba3D: Mamba-based Foreground-Enhanced Encoding for 3D Object Detection

Authors: Zhiwei Ning, Xuanang Gao, Jiaxi Cao, Runze Yang, Huiying Xu, Xinzhong Zhu, Jie Yang, Wei Liu
Published: 2026-02-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.19536v1

Linear modeling methods like Mamba have been merged as the effective backbone for the 3D object detection task. However, previous Mamba-based methods utilize the bidirectional encoding for the whole non-empty voxel sequence, which contains abundant useless background information in the scenes. Though directly encoding foreground voxels appears to be a plausible solution, it tends to degrade detection performance. We attribute this to the response attenuation and restricted context representation in the linear modeling for fore-only sequences. To address this problem, we propose a novel backbone, termed Fore-Mamba3D, to focus on the foreground enhancement by modifying Mamba-based encoder. The foreground voxels are first sampled according to the predicted scores. Considering the response attenuation existing in the interaction of foreground voxels across different instances, we design a regional-to-global slide window (RGSW) to propagate the information from regional split to the entire sequence. Furthermore, a semantic-assisted and state spatial fusion module (SASFMamba) is proposed to enrich contextual representation by enhancing semantic and geometric awareness within the Mamba model. Our method emphasizes foreground-only encoding and alleviates the distance-based and causal dependencies in the linear autoregression model. The superior performance across various benchmarks demonstrates the effectiveness of Fore-Mamba3D in the 3D object detection task.

---

### Large Language Model-Assisted UAV Operations and Communications: A Multifaceted Survey and Tutorial

Authors: Yousef Emami, Hao Zhou, Radha Reddy, Atefeh Hajijamali Arani, Biliang Wang, Kai Li, Luis Almeida, Zhu Han
Published: 2026-02-23
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2602.19534v2

Uncrewed Aerial Vehicles (UAVs) are widely deployed across diverse applications due to their mobility and agility. Recent advances in Large Language Models (LLMs) offer a transformative opportunity to enhance UAV intelligence beyond conventional optimization-based and learning-based approaches. By integrating LLMs into UAV systems, advanced environmental understanding, swarm coordination, mobility optimization, and high-level task reasoning can be achieved, thereby allowing more adaptive and context-aware aerial operations. This survey systematically explores the intersection of LLMs and UAV technologies and proposes a unified framework that consolidates existing architectures, methodologies, and applications for UAVs. We first present a structured taxonomy of LLM adaptation techniques for UAVs, including pretraining, fine-tuning, Retrieval-Augmented Generation (RAG), and prompt engineering, along with key reasoning capabilities such as Chain-of-Thought (CoT) and In-Context Learning (ICL). We then examine LLM-assisted UAV communications and operations, covering navigation, mission planning, swarm control, safety, autonomy, and network management. After that, the survey further discusses Multimodal LLMs (MLLMs) for human-swarm interaction, perception-driven navigation, and collaborative control. Finally, we address ethical considerations, including bias, transparency, accountability, and Human-in-the-Loop (HITL) strategies, and outline future research directions. Overall, this work positions LLM-assisted UAVs as a foundation for intelligent and adaptive aerial systems.

---

### Grokking Finite-Dimensional Algebra

Authors: Pascal Jr Tikeng Notsawo, Guillaume Dumas, Guillaume Rabusseau
Published: 2026-02-23
Categories: cs.LG, cs.AI, math.RA
arXiv: https://arxiv.org/abs/2602.19533v2

This paper investigates the grokking phenomenon, which refers to the sudden transition from a long memorization to generalization observed during neural networks training, in the context of learning multiplication in finite-dimensional algebras (FDA). While prior work on grokking has focused mainly on group operations, we extend the analysis to more general algebraic structures, including non-associative, non-commutative, and non-unital algebras. We show that learning group operations is a special case of learning FDA, and that learning multiplication in FDA amounts to learning a bilinear product specified by the algebra's structure tensor. For algebras over the reals, we connect the learning problem to matrix factorization with an implicit low-rank bias, and for algebras over finite fields, we show that grokking emerges naturally as models must learn discrete representations of algebraic elements. This leads us to experimentally investigate the following core questions: (i) how do algebraic properties such as commutativity, associativity, and unitality influence both the emergence and timing of grokking, (ii) how structural properties of the structure tensor of the FDA, such as sparsity and rank, influence generalization, and (iii) to what extent generalization correlates with the model learning latent embeddings aligned with the algebra's representation. Our work provides a unified framework for grokking across algebraic structures and new insights into how mathematical structure governs neural network generalization dynamics.

---

### A Statistical Approach for Modeling Irregular Multivariate Time Series with Missing Observations

Authors: Dingyi Nie, Yixing Wu, C. -C. Jay Kuo
Published: 2026-02-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.19531v1

Irregular multivariate time series with missing values present significant challenges for predictive modeling in domains such as healthcare. While deep learning approaches often focus on temporal interpolation or complex architectures to handle irregularities, we propose a simpler yet effective alternative: extracting time-agnostic summary statistics to eliminate the temporal axis. Our method computes four key features per variable-mean and standard deviation of observed values, as well as the mean and variability of changes between consecutive observations to create a fixed-dimensional representation. These features are then utilized with standard classifiers, such as logistic regression and XGBoost. Evaluated on four biomedical datasets (PhysioNet Challenge 2012, 2019, PAMAP2, and MIMIC-III), our approach achieves state-of-the-art performance, surpassing recent transformer and graph-based models by 0.5-1.7% in AUROC/AUPRC and 1.1-1.7% in accuracy/F1-score, while reducing computational complexity. Ablation studies demonstrate that feature extraction-not classifier choice-drives performance gains, and our summary statistics outperform raw/imputed input in most benchmarks. In particular, we identify scenarios where missing patterns themselves encode predictive signals, as in sepsis prediction (PhysioNet, 2019), where missing indicators alone can achieve 94.2% AUROC with XGBoost, only 1.6% lower than using original raw data as input. Our results challenge the necessity of complex temporal modeling when task objectives permit time-agnostic representations, providing an efficient and interpretable solution for irregular time series classification.

---

### ORION: ORthonormal Text Encoding for Universal VLM AdaptatION

Authors: Omprakash Chakraborty, Jose Dolz, Ismail Ben Ayed
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19530v2

Vision language models (VLMs) have demonstrated remarkable generalization across diverse tasks, yet their performance remains constrained by the quality and geometry of the textual prototypes used to represent classes. Standard zero shot classifiers, derived from frozen text encoders and handcrafted prompts, may yield correlated or weakly separated embeddings that limit task specific discriminability. We introduce ORION, a text encoder fine tuning framework that improves pretrained VLMs using only class names. Our method optimizes, via low rank adaptation, a novel loss integrating two terms, one promoting pairwise orthogonality between the textual representations of the classes of a given task and the other penalizing deviations from the initial class prototypes. Furthermore, we provide a probabilistic interpretation of our orthogonality penalty, connecting it to the general maximum likelihood estimation (MLE) principle via Huygens theorem. We report extensive experiments on 11 benchmarks and three large VLM backbones, showing that the refined textual embeddings yield powerful replacements for the standard CLIP prototypes. Added as plug and play module on top of various state of the art methods, and across different prediction settings (zero shot, few shot and test time adaptation), ORION improves the performance consistently and significantly.

---

### Beyond Accuracy: A Unified Random Matrix Theory Diagnostic Framework for Crash Classification Models

Authors: Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Published: 2026-02-23
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.19528v1

Crash classification models in transportation safety are typically evaluated using accuracy, F1, or AUC, metrics that cannot reveal whether a model is silently overfitting. We introduce a spectral diagnostic framework grounded in Random Matrix Theory (RMT) and Heavy-Tailed Self-Regularization (HTSR) that spans the ML taxonomy: weight matrices for BERT/ALBERT/Qwen2.5, out-of-fold increment matrices for XGBoost/Random Forest, empirical Hessians for Logistic Regression, induced affinity matrices for Decision Trees, and Graph Laplacians for KNN. Evaluating nine model families on two Iowa DOT crash classification tasks (173,512 and 371,062 records respectively), we find that the power-law exponent $α$ provides a structural quality signal: well-regularized models consistently yield $α$ within $(2, 4)$ (mean $2.87 \pm 0.34$), while overfit variants show $α< 2$ or spectral collapse. We observe a strong rank correlation between $α$ and expert agreement (Spearman $ρ= 0.89$, $p < 0.001$), suggesting spectral quality captures model behaviors aligned with expert reasoning. We propose an $α$-based early stopping criterion and a spectral model selection protocol, and validate both against cross-validated F1 baselines. Sparse Lanczos approximations make the framework scalable to large datasets.

---

### How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1

Authors: Yinuo Xu, Shuo Lu, Jianjie Cheng, Meng Wang, Qianlong Xie, Xingxing Wang, Ran He, Jian Liang
Published: 2026-02-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.19526v1

Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. While reinforcement learning (RL) has been shown to improve performance in this paradigm, its contributions remain underexplored. To fully understand the role of RL, we conduct a systematic study along three decoupled dimensions: prompt template, reward function, and policy optimization. Our study reveals that: 1) the Fast Thinking template yields greater stability and better performance than the Slow Thinking template used in prior work; 2) the F1-based reward underperforms the EM due to training collapse driven by answer avoidance; this can be mitigated by incorporating action-level penalties, ultimately surpassing EM; 3) REINFORCE outperforms PPO while requiring fewer search actions, whereas GRPO shows the poorest stability among policy optimization methods. Building on these insights, we then introduce Search-R1++, a strong baseline that improves the performance of Search-R1 from 0.403 to 0.442 (Qwen2.5-7B) and 0.289 to 0.331 (Qwen2.5-3B). We hope that our findings can pave the way for more principled and reliable RL training strategies in Deep Research systems.

---

### OSInsert: Towards High-authenticity and High-fidelity Image Composition

Authors: Jingyuan Wang, Li Niu
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19523v1

Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image. Some high-authenticity methods can adjust foreground pose/view to be compatible with background, while some high-fidelity methods can preserve the foreground details accurately. However, existing methods can hardly achieve both goals at the same time. In this work, we propose a two-stage strategy to achieve both goals. In the first stage, we use high-authenticity method to generate reasonable foreground shape, serving as the condition of high-fidelity method in the second stage. The experiments on MureCOM dataset verify the effectiveness of our two-stage strategy. The code and model have been released at https://github.com/bcmi/OSInsert-Image-Composition.

---

### Ada-RS: Adaptive Rejection Sampling for Selective Thinking

Authors: Yirou Ge, Yixi Li, Alec Chiu, Shivani Shekhar, Zijie Pan, Avinash Thangali, Yun-Shiuan Chuang, Chaitanya Kulkarni, Uma Kona, Linsey Pang, Prakhar Mehrotra
Published: 2026-02-23
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.19519v1

Large language models (LLMs) are increasingly being deployed in cost and latency-sensitive settings. While chain-of-thought improves reasoning, it can waste tokens on simple requests. We study selective thinking for tool-using LLMs and introduce Adaptive Rejection Sampling (Ada-RS), an algorithm-agnostic sample filtering framework for learning selective and efficient reasoning. For each given context, Ada-RS scores multiple sampled completions with an adaptive length-penalized reward then applies stochastic rejection sampling to retain only high-reward candidates (or preference pairs) for downstream optimization. We demonstrate how Ada-RS plugs into both preference pair (e.g. DPO) or grouped policy optimization strategies (e.g. DAPO). Using Qwen3-8B with LoRA on a synthetic tool call-oriented e-commerce benchmark, Ada-RS improves the accuracy-efficiency frontier over standard algorithms by reducing average output tokens by up to 80% and reducing thinking rate by up to 95% while maintaining or improving tool call accuracy. These results highlight that training-signal selection is a powerful lever for efficient reasoning in latency-sensitive deployments.

---

### Classroom Final Exam: An Instructor-Tested Reasoning Benchmark

Authors: Chongyang Gao, Diji Yang, Shuyan Zhou, Xichen Yan, Luchuan Song, Shuo Li, Kezhen Chen
Published: 2026-02-23
Categories: cs.AI, cs.CE, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2602.19517v2

We introduce CFE-Bench (Classroom Final Exam), a multimodal benchmark for evaluating the reasoning capabilities of large language models across more than 20 STEM domains. CFE-Bench is curated from repeatedly used, authentic university homework and exam problems, paired with reference solutions provided by course instructors. CFE-Bench remains challenging for frontier models: the newly released Gemini-3.1-pro-preview achieves 59.69% overall accuracy, while the second-best model, Gemini-3-flash-preview, reaches 55.46%, leaving substantial room for improvement. Beyond aggregate scores, we conduct a diagnostic analysis by decomposing instructor reference solutions into structured reasoning flows. We find that while frontier models often answer intermediate sub-questions correctly, they struggle to reliably derive and maintain correct intermediate states throughout multi-step solutions. We further observe that model-generated solutions typically contain more reasoning steps than instructor solutions, indicating lower step efficiency and a higher risk of error accumulation. Data and code are available at https://github.com/Analogy-AI/CFE_Bench.

---

### Real-time Win Probability and Latent Player Ability via STATS X in Team Sports

Authors: Yasutaka Shimizu, Atsushi Yamanobe
Published: 2026-02-23
Categories: stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2602.19513v1

This study proposes a statistically grounded framework for real-time win probability evaluation and player assessment in score-based team sports, based on minute-by-minute cumulative box-score data. We introduce a continuous dominance indicator (T-score) that maps final scores to real values consistent with win/lose outcomes, and formulate it as a time-evolving stochastic representation (T-process) driven by standardized cumulative statistics. This structure captures temporal game dynamics and enables sequential, analytically tractable updates of in-game win probability. Through this stochastic formulation, competitive advantage is decomposed into interpretable statistical components. Furthermore, we define a latent contribution index, STATS X, which quantifies a player's involvement in favorable dominance intervals identified by the T-process. This allows us to separate a team's baseline strength from game-specific performance fluctuations and provides a coherent, structural evaluation framework for both teams and players. While we do not implement AI methods in this paper, our framework is positioned as a foundational step toward hybrid integration with AI. By providing a structured time-series representation of dominance with an explicit probabilistic interpretation, the framework enables flexible learning mechanisms and incorporation of high-dimensional data, while preserving statistical coherence and interpretability. This work provides a basis for advancing AI-driven sports analytics.

---

### Variational Trajectory Optimization of Anisotropic Diffusion Schedules

Authors: Pengxi Liu, Zeyu Michael Li, Xiang Cheng
Published: 2026-02-23
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.19512v1

We introduce a variational framework for diffusion models with anisotropic noise schedules parameterized by a matrix-valued path $M_t(θ)$ that allocates noise across subspaces. Central to our framework is a trajectory-level objective that jointly trains the score network and learns $M_t(θ)$, which encompasses general parameterization classes of matrix-valued noise schedules. We further derive an estimator for the derivative with respect to $θ$ of the score that enables efficient optimization of the $M_t(θ)$ schedule. For inference, we develop an efficiently-implementable reverse-ODE solver that is an anisotropic generalization of the second-order Heun discretization algorithm. Across CIFAR-10, AFHQv2, FFHQ, and ImageNet-64, our method consistently improves upon the baseline EDM model in all NFE regimes. Code is available at https://github.com/lizeyu090312/anisotropic-diffusion-paper.

---

### Less is More: Convergence Benefits of Fewer Data Weight Updates over Longer Horizon

Authors: Rudrajit Das, Neel Patel, Meisam Razaviyayn, Vahab Mirrokni
Published: 2026-02-23
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2602.19510v1

Data mixing--the strategic reweighting of training domains--is a critical component in training robust machine learning models. This problem is naturally formulated as a bilevel optimization task, where the outer loop optimizes domain weights to minimize validation loss, and the inner loop optimizes model parameters to minimize the weighted training loss. Classical bilevel optimization relies on hypergradients, which theoretically require the inner optimization to reach convergence. However, due to computational constraints, state-of-the-art methods use a finite, often small, number of inner update steps before updating the weights. The theoretical implications of this approximation are not well understood. In this work, we rigorously analyze the convergence behavior of data mixing with a finite number of inner steps $T$. We prove that the "greedy" practical approach of using $T=1$ can fail even in a simple quadratic example. Under a fixed parameter update budget $N$ and assuming the per-domain losses are strongly convex, we show that the optimal $T$ scales as $Θ(\log N)$ (resp., $Θ({(N \log N)}^{1/2})$) for the data mixing problem with access to full (resp., stochastic) gradients. We complement our theoretical results with proof-of-concept experiments.

---

### Pyramid MoA: A Probabilistic Framework for Cost-Optimized Anytime Inference

Authors: Arindam Khaled
Published: 2026-02-23
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.19509v3

We observe that LLM cascading and routing implicitly solves an anytime computation problem -- a class of algorithms, well-studied in classical AI, that improve solutions as additional computation is allocated. We formalize this connection and propose Pyramid MoA, a hierarchical Mixture-of-Agents architecture governed by a decision-theoretic router that escalates queries only when necessary. We establish a Probabilistic Anytime Property with provable monotonicity guarantees and derive a generalized escalation rule from Value of Computation theory that accounts for imperfect oracles, extending the Hansen-Zilberstein monitoring framework to stochastic LLM inference. On MBPP, the router intercepts 81.6% of bugs; on GSM8K/MMLU, the system nearly matches the 68.1% Oracle baseline while achieving up to 42.9% compute savings. The router transfers zero-shot to unseen benchmarks: matching Oracle accuracy on HumanEval (81.1%) and MATH 500 (58.0%) with significant cost reductions. We further discover a context-conditioned anchoring effect across four benchmarks: passing correct SLM reasoning improves Oracle accuracy by up to +19.2pp, while incorrect reasoning degrades it by up to -18.0pp, revealing a fundamental tension in hierarchical MoA architectures.

---

### Relational Feature Caching for Accelerating Diffusion Transformers

Authors: Byunggwan Son, Jeimin Jeon, Jeongwoo Choi, Bumsub Ham
Published: 2026-02-23
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.19506v1

Feature caching approaches accelerate diffusion transformers (DiTs) by storing the output features of computationally expensive modules at certain timesteps, and exploiting them for subsequent steps to reduce redundant computations. Recent forecasting-based caching approaches employ temporal extrapolation techniques to approximate the output features with cached ones. Although effective, relying exclusively on temporal extrapolation still suffers from significant prediction errors, leading to performance degradation. Through a detailed analysis, we find that 1) these errors stem from the irregular magnitude of changes in the output features, and 2) an input feature of a module is strongly correlated with the corresponding output. Based on this, we propose relational feature caching (RFC), a novel framework that leverages the input-output relationship to enhance the accuracy of the feature prediction. Specifically, we introduce relational feature estimation (RFE) to estimate the magnitude of changes in the output features from the inputs, enabling more accurate feature predictions. We also present relational cache scheduling (RCS), which estimates the prediction errors using the input features and performs full computations only when the errors are expected to be substantial. Extensive experiments across various DiT models demonstrate that RFC consistently outperforms prior approaches significantly. Project page is available at https://cvlab.yonsei.ac.kr/projects/RFC

---

### Test-Time Computing for Referring Multimodal Large Language Models

Authors: Mingrui Wu, Hao Chen, Jiayi Ji, Xiaoshuai Sun, Zhiyuan Liu, Liujuan Cao, Ming-Ming Cheng, Rongrong Ji
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19505v1

We propose ControlMLLM++, a novel test-time adaptation framework that injects learnable visual prompts into frozen multimodal large language models (MLLMs) to enable fine-grained region-based visual reasoning without any model retraining or fine-tuning. Leveraging the insight that cross-modal attention maps intrinsically encode semantic correspondences between textual tokens and visual regions, ControlMLLM++ optimizes a latent visual token modifier during inference via a task-specific energy function to steer model attention towards user-specified areas. To enhance optimization stability and mitigate language prompt biases, ControlMLLM++ incorporates an improved optimization strategy (Optim++) and a prompt debiasing mechanism (PromptDebias). Supporting diverse visual prompt types including bounding boxes, masks, scribbles, and points, our method demonstrates strong out-of-domain generalization and interpretability. The code is available at https://github.com/mrwu-mac/ControlMLLM.

---

### A Text-Guided Vision Model for Enhanced Recognition of Small Instances

Authors: Hyun-Ki Jung
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19503v1

As drone-based object detection technology continues to evolve, the demand is shifting from merely detecting objects to enabling users to accurately identify specific targets. For example, users can input particular targets as prompts to precisely detect desired objects. To address this need, an efficient text-guided object detection model has been developed to enhance the detection of small objects. Specifically, an improved version of the existing YOLO-World model is introduced. The proposed method replaces the C2f layer in the YOLOv8 backbone with a C3k2 layer, enabling more precise representation of local features, particularly for small objects or those with clearly defined boundaries. Additionally, the proposed architecture improves processing speed and efficiency through parallel processing optimization, while also contributing to a more lightweight model design. Comparative experiments on the VisDrone dataset show that the proposed model outperforms the original YOLO-World model, with precision increasing from 40.6% to 41.6%, recall from 30.8% to 31%, F1 score from 35% to 35.5%, and mAP@0.5 from 30.4% to 30.7%, confirming its enhanced accuracy. Furthermore, the model demonstrates superior lightweight performance, with the parameter count reduced from 4 million to 3.8 million and FLOPs decreasing from 15.7 billion to 15.2 billion. These results indicate that the proposed approach provides a practical and effective solution for precise object detection in drone-based applications.

---

### Human-Guided Agentic AI for Multimodal Clinical Prediction: Lessons from the AgentDS Healthcare Benchmark

Authors: Lalitha Pranathi Pulavarthy, Raajitha Muthyala, Aravind V Kuruvikkattil, Zhenan Yin, Rashmita Kudamala, Saptarshi Purkayastha
Published: 2026-02-23
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.19502v2

Agentic AI systems are increasingly capable of autonomous data science workflows, yet clinical prediction tasks demand domain expertise that purely automated approaches struggle to provide. We investigate how human guidance of agentic AI can improve multimodal clinical prediction, presenting our approach to all three AgentDS Healthcare benchmark challenges: 30-day hospital readmission prediction (Macro-F1 = 0.8986), emergency department cost forecasting (MAE = $465.13), and discharge readiness assessment (Macro-F1 = 0.7939). Across these tasks, human analysts directed the agentic workflow at key decision points, multimodal feature engineering from clinical notes, scanned PDF billing receipts, and time-series vital signs; task-appropriate model selection; and clinically informed validation strategies. Our approach ranked 5th overall in the healthcare domain, with a 3rd-place finish on the discharge readiness task. Ablation studies reveal that human-guided decisions compounded to a cumulative gain of +0.065 F1 over automated baselines, with multimodal feature extraction contributing the largest single improvement (+0.041 F1). We distill three generalizable lessons: (1) domain-informed feature engineering at each pipeline stage yields compounding gains that outperform extensive automated search; (2) multimodal data integration requires task-specific human judgment that no single extraction strategy generalizes across clinical text, PDFs, and time-series; and (3) deliberate ensemble diversity with clinically motivated model configurations outperforms random hyperparameter search. These findings offer practical guidance for teams deploying agentic AI in healthcare settings where interpretability, reproducibility, and clinical validity are essential.

---

### Softmax is not Enough (for Adaptive Conformal Classification)

Authors: Navid Akhavan Attar, Hesam Asadollahzadeh, Ling Luo, Uwe Aickelin
Published: 2026-02-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.19498v1

The merit of Conformal Prediction (CP), as a distribution-free framework for uncertainty quantification, depends on generating prediction sets that are efficient, reflected in small average set sizes, while adaptive, meaning they signal uncertainty by varying in size according to input difficulty. A central limitation for deep conformal classifiers is that the nonconformity scores are derived from softmax outputs, which can be unreliable indicators of how certain the model truly is about a given input, sometimes leading to overconfident misclassifications or undue hesitation. In this work, we argue that this unreliability can be inherited by the prediction sets generated by CP, limiting their capacity for adaptiveness. We propose a new approach that leverages information from the pre-softmax logit space, using the Helmholtz Free Energy as a measure of model uncertainty and sample difficulty. By reweighting nonconformity scores with a monotonic transformation of the energy score of each sample, we improve their sensitivity to input difficulty. Our experiments with four state-of-the-art score functions on multiple datasets and deep architectures show that this energy-based enhancement improves the adaptiveness of the prediction sets, leading to a notable increase in both efficiency and adaptiveness compared to baseline nonconformity scores, without introducing any post-hoc complexity.

---

### MICON-Bench: Benchmarking and Enhancing Multi-Image Context Image Generation in Unified Multimodal Models

Authors: Mingrui Wu, Hang Liu, Jiayi Ji, Xiaoshuai Sun, Rongrong Ji
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19497v1

Recent advancements in Unified Multimodal Models (UMMs) have enabled remarkable image understanding and generation capabilities. However, while models like Gemini-2.5-Flash-Image show emerging abilities to reason over multiple related images, existing benchmarks rarely address the challenges of multi-image context generation, focusing mainly on text-to-image or single-image editing tasks. In this work, we introduce \textbf{MICON-Bench}, a comprehensive benchmark covering six tasks that evaluate cross-image composition, contextual reasoning, and identity preservation. We further propose an MLLM-driven Evaluation-by-Checkpoint framework for automatic verification of semantic and visual consistency, where multimodal large language model (MLLM) serves as a verifier. Additionally, we present \textbf{Dynamic Attention Rebalancing (DAR)}, a training-free, plug-and-play mechanism that dynamically adjusts attention during inference to enhance coherence and reduce hallucinations. Extensive experiments on various state-of-the-art open-source models demonstrate both the rigor of MICON-Bench in exposing multi-image reasoning challenges and the efficacy of DAR in improving generation quality and cross-image coherence. Github: https://github.com/Angusliuuu/MICON-Bench.

---

### Botson: An Accessible and Low-Cost Platform for Social Robotics Research

Authors: Samuel Bellaire, Abdalmalek Abu-raddaha, Natalie Kim, Nathan Morhan, William Elliott, Samir Rawashdeh
Published: 2026-02-23
Categories: cs.RO, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2602.19491v1

Trust remains a critical barrier to the effective integration of Artificial Intelligence (AI) into human-centric domains. Disembodied agents, such as voice assistants, often fail to establish trust due to their inability to convey non-verbal social cues. This paper introduces the architecture of Botson: an anthropomorphic social robot powered by a large language model (LLM). Botson was created as a low-cost and accessible platform for social robotics research.

---

### Federated Learning Playground

Authors: Bryan Shan, Alysa Ziying Tan, Han Yu
Published: 2026-02-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.19489v2

We present Federated Learning Playground, an interactive browser-based platform inspired by and extends TensorFlow Playground that teaches core Federated Learning (FL) concepts. Users can experiment with heterogeneous client data distributions, model hyperparameters, and aggregation algorithms directly in the browser without coding or system setup, and observe their effects on client and global models through real-time visualizations, gaining intuition for challenges such as non-IID data, local overfitting, and scalability. The playground serves as an easy to use educational tool, lowering the entry barrier for newcomers to distributed AI while also offering a sandbox for rapidly prototyping and comparing FL methods. By democratizing exploration of FL, it promotes broader understanding and adoption of this important paradigm.

---

### Exploiting Label-Independent Regularization from Spatial Dependencies for Whole Slide Image Analysis

Authors: Weiyi Wu, Xinwen Xu, Chongyang Gao, Xingjian Diao, Siting Li, Jiang Gui
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19487v1

Whole slide images, with their gigapixel-scale panoramas of tissue samples, are pivotal for precise disease diagnosis. However, their analysis is hindered by immense data size and scarce annotations. Existing MIL methods face challenges due to the fundamental imbalance where a single bag-level label must guide the learning of numerous patch-level features. This sparse supervision makes it difficult to reliably identify discriminative patches during training, leading to unstable optimization and suboptimal solutions. We propose a spatially regularized MIL framework that leverages inherent spatial relationships among patch features as label-independent regularization signals. Our approach learns a shared representation space by jointly optimizing feature-induced spatial reconstruction and label-guided classification objectives, enforcing consistency between intrinsic structural patterns and supervisory signals. Experimental results on multiple public datasets demonstrate significant improvements over state-of-the-art methods, offering a promising direction.

---

### Making Conformal Predictors Robust in Healthcare Settings: a Case Study on EEG Classification

Authors: Arjun Chatterjee, Sayeed Sajjad Razin, John Wu, Siddhartha Laghuvarapu, Jathurshan Pradeepkumar, Jimeng Sun
Published: 2026-02-23
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2602.19483v2

Quantifying uncertainty in clinical predictions is critical for high-stakes diagnosis tasks. Conformal prediction offers a principled approach by providing prediction sets with theoretical coverage guarantees. However, in practice, patient distribution shifts violate the i.i.d. assumptions underlying standard conformal methods, leading to poor coverage in healthcare settings. In this work, we evaluate several conformal prediction approaches on EEG seizure classification, a task with known distribution shift challenges and label uncertainty. We demonstrate that personalized calibration strategies can improve coverage by over 20 percentage points while maintaining comparable prediction set sizes. Our implementation is available via PyHealth, an open-source healthcare AI framework: https://github.com/sunlabuiuc/PyHealth.

---

### Scale-PINN: Learning Efficient Physics-Informed Neural Networks Through Sequential Correction

Authors: Pao-Hsiung Chiu, Jian Cheng Wong, Chin Chun Ooi, Chang Wei, Yuchen Fan, Yew-Soon Ong
Published: 2026-02-23
Categories: cs.CE, cs.AI, cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2602.19475v1

Physics-informed neural networks (PINNs) have emerged as a promising mesh-free paradigm for solving partial differential equations, yet adoption in science and engineering is limited by slow training and modest accuracy relative to modern numerical solvers. We introduce the Sequential Correction Algorithm for Learning Efficient PINN (Scale-PINN), a learning strategy that bridges modern physics-informed learning with numerical algorithms. Scale-PINN incorporates the iterative residual-correction principle, a cornerstone of numerical solvers, directly into the loss formulation, marking a paradigm shift in how PINN losses can be conceived and constructed. This integration enables Scale-PINN to achieve unprecedented convergence speed across PDE problems from different physics domain, including reducing training time on a challenging fluid-dynamics problem for state-of-the-art PINN from hours to sub-2 minutes while maintaining superior accuracy, and enabling application to representative problems in aerodynamics and urban science. By uniting the rigor of numerical methods with the flexibility of deep learning, Scale-PINN marks a significant leap toward the practical adoption of PINNs in science and engineering through scalable, physics-informed learning. Codes are available at https://github.com/chiuph/SCALE-PINN.

---

### Structured Bitmap-to-Mesh Triangulation for Geometry-Aware Discretization of Image-Derived Domains

Authors: Wei Feng, Haiyong Zheng
Published: 2026-02-23
Categories: cs.CG, cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2602.19474v2

We propose a template-driven triangulation framework that embeds raster- or segmentation-derived boundaries into a regular triangular grid for stable PDE discretization on image-derived domains. Unlike constrained Delaunay triangulation (CDT), which may trigger global connectivity updates, our method retriangulates only triangles intersected by the boundary, preserves the base mesh, and supports synchronization-free parallel execution. To ensure determinism and scalability, we classify all local boundary-intersection configurations up to discrete equivalence and triangle symmetries, yielding a finite symbolic lookup table that maps each case to a conflict-free retriangulation template. We prove that the resulting mesh is closed, has bounded angles, and is compatible with cotangent-based discretizations and standard finite element methods. Experiments on elliptic and parabolic PDEs, signal interpolation, and structural metrics show fewer sliver elements, more regular triangles, and improved geometric fidelity near complex boundaries. The framework is well suited for real-time geometric analysis and physically based simulation over image-derived domains.

---

### The generalized underlap coefficient with an application in clustering

Authors: Zhaoxi Zhang, Vanda Inácio, Sara Wade
Published: 2026-02-23
Categories: stat.ME, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2602.19473v3

Quantifying distributional separation across groups is fundamental in statistical learning and scientific discovery, yet most classical discrepancy measures are tailored to two-group comparisons. We generalize the underlap coefficient (UNL), a multi-group separation measure, to multivariate settings. We study its relationship with Bayes risk and mutual information, and further interpret the UNL as a measure of dependence between group labels and variables of interest. We propose an efficient importance sampling estimator of the UNL that can be combined with flexible density estimation methods. A key application is the assessment of partition-covariate dependence in clustering, where the UNL provides an interpretable measure of whether latent group structure can be explained by specific covariates. The methodology is illustrated on two real-world datasets.

---

### Forgetting-Resistant and Lesion-Aware Source-Free Domain Adaptive Fundus Image Analysis with Vision-Language Model

Authors: Zheang Huai, Hui Tang, Hualiang Wang, Xiaomeng Li
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19471v2

Source-free domain adaptation (SFDA) aims to adapt a model trained in the source domain to perform well in the target domain, with only unlabeled target domain data and the source model. Taking into account that conventional SFDA methods are inevitably error-prone under domain shift, recently greater attention has been directed to SFDA assisted with off-the-shelf foundation models, e.g., vision-language (ViL) models. However, existing works of leveraging ViL models for SFDA confront two issues: (i) Although mutual information is exploited to consider the joint distribution between the predictions of ViL model and the target model, we argue that the forgetting of some superior predictions of the target model still occurs, as indicated by the decline of the accuracies of certain classes during adaptation; (ii) Prior research disregards the rich, fine-grained knowledge embedded in the ViL model, which offers detailed grounding for fundus image diagnosis. In this paper, we introduce a novel forgetting-resistant and lesion-aware (FRLA) method for SFDA of fundus image diagnosis with ViL model. Specifically, a forgetting-resistant adaptation module explicitly preserves the confident predictions of the target model, and a lesion-aware adaptation module yields patch-wise predictions from ViL model and employs them to help the target model be aware of the lesion areas and leverage the ViL model's fine-grained knowledge. Extensive experiments show that our method not only significantly outperforms the vision-language model, but also achieves consistent improvements over the state-of-the-art methods. Our code will be released.

---

### Forgetting-Resistant and Lesion-Aware Source-Free Domain Adaptive Fundus Image Analysis with Vision-Language Model

Authors: Zheang Huai, Hui Tang, Hualiang Wang, Xiaomeng Li
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19471v1

Source-free domain adaptation (SFDA) aims to adapt a model trained in the source domain to perform well in the target domain, with only unlabeled target domain data and the source model. Taking into account that conventional SFDA methods are inevitably error-prone under domain shift, recently greater attention has been directed to SFDA assisted with off-the-shelf foundation models, e.g., vision-language (ViL) models. However, existing works of leveraging ViL models for SFDA confront two issues: (i) Although mutual information is exploited to consider the joint distribution between the predictions of ViL model and the target model, we argue that the forgetting of some superior predictions of the target model still occurs, as indicated by the decline of the accuracies of certain classes during adaptation; (ii) Prior research disregards the rich, fine-grained knowledge embedded in the ViL model, which offers detailed grounding for fundus image diagnosis. In this paper, we introduce a novel forgetting-resistant and lesion-aware (FRLA) method for SFDA of fundus image diagnosis with ViL model. Specifically, a forgetting-resistant adaptation module explicitly preserves the confident predictions of the target model, and a lesion-aware adaptation module yields patch-wise predictions from ViL model and employs them to help the target model be aware of the lesion areas and leverage the ViL model's fine-grained knowledge. Extensive experiments show that our method not only significantly outperforms the vision-language model, but also achieves consistent improvements over the state-of-the-art methods. Our code will be released.

---

### Physics-informed Active Polarimetric 3D Imaging for Specular Surfaces

Authors: Jiazhang Wang, Hyelim Yang, Tianyi Wang, Florian Willomitzer
Published: 2026-02-23
Categories: cs.CV, physics.optics
arXiv: https://arxiv.org/abs/2602.19470v2

3D imaging of specular surfaces remains challenging in real-world scenarios, such as in-line inspection or hand-held scanning, requiring fast and accurate measurement of complex geometries. Optical metrology techniques such as deflectometry achieve high accuracy but typically rely on multi-shot acquisition, making them unsuitable for dynamic environments. Fourier-based single-shot approaches alleviate this constraint, yet their performance deteriorates when measuring surfaces with high spatial frequency structure or large curvature. Alternatively, polarimetric 3D imaging in computer vision operates in a single-shot fashion and exhibits robustness to geometric complexity. However, its accuracy is fundamentally limited by the orthographic imaging assumption. In this paper, we propose a physics-informed deep learning framework for single-shot 3D imaging of complex specular surfaces. Polarization cues provide orientation priors that assist in interpreting geometric information encoded by structured illumination. These complementary cues are processed through a dual-encoder architecture with mutual feature modulation, allowing the network to resolve their nonlinear coupling and directly infer surface normals. The proposed method achieves accurate and robust normal estimation in single-shot with fast inference, enabling practical 3D imaging of complex specular surfaces.

---

### Can Large Language Models Replace Human Coders? Introducing ContentBench

Authors: Michael Haman
Published: 2026-02-23
Categories: cs.CY, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.19467v1

Can low-cost large language models (LLMs) take over the interpretive coding work that still anchors much of empirical content analysis? This paper introduces ContentBench, a public benchmark suite that helps answer this replacement question by tracking how much agreement low-cost LLMs achieve and what they cost on the same interpretive coding tasks. The suite uses versioned tracks that invite researchers to contribute new benchmark datasets. I report results from the first track, ContentBench-ResearchTalk v1.0: 1,000 synthetic, social-media-style posts about academic research labeled into five categories spanning praise, critique, sarcasm, questions, and procedural remarks. Reference labels are assigned only when three state-of-the-art reasoning models (GPT-5, Gemini 2.5 Pro, and Claude Opus 4.1) agree unanimously, and all final labels are checked by the author as a quality-control audit. Among the 59 evaluated models, the best low-cost LLMs reach roughly 97-99% agreement with these jury labels, far above GPT-3.5 Turbo, the model behind early ChatGPT and the initial wave of LLM-based text annotation. Several top models can code 50,000 posts for only a few dollars, pushing large-scale interpretive coding from a labor bottleneck toward questions of validation, reporting, and governance. At the same time, small open-weight models that run locally still struggle on sarcasm-heavy items (for example, Llama 3.2 3B reaches only 4% agreement on hard-sarcasm). ContentBench is released with data, documentation, and an interactive quiz at contentbench.github.io to support comparable evaluations over time and to invite community extensions.

---

### PuppetChat: Fostering Intimate Communication through Bidirectional Actions and Micronarratives

Authors: Emma Jiren Wang, Siying Hu, Zhicong Lu
Published: 2026-02-23
Categories: cs.HC, cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2602.19463v2

As a primary channel for sustaining modern intimate relationships, instant messaging facilitates frequent connection across distances. However, today's tools often dilute care; they favor single tap reactions and vague emojis that do not support two way action responses, do not preserve the feeling that the exchange keeps going without breaking, and are weakly tied to who we are and what we share. To address this challenge, we present PuppetChat, a dyadic messaging prototype that restores this expressive depth through embodied interaction. PuppetChat uses a reciprocity aware recommender to encourage responsive actions and generates personalized micronarratives from user stories to ground interactions in personal history. Our 10-day field study with 11 dyads of close partners or friends revealed that this approach enhanced social presence, supported more expressive self disclosure, and sustained continuity and shared memories.

---

### Laplacian Multi-scale Flow Matching for Generative Modeling

Authors: Zelin Zhao, Petr Molodyk, Haotian Xue, Yongxin Chen
Published: 2026-02-23
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.19461v1

In this paper, we present Laplacian multiscale flow matching (LapFlow), a novel framework that enhances flow matching by leveraging multi-scale representations for image generative modeling. Our approach decomposes images into Laplacian pyramid residuals and processes different scales in parallel through a mixture-of-transformers (MoT) architecture with causal attention mechanisms. Unlike previous cascaded approaches that require explicit renoising between scales, our model generates multi-scale representations in parallel, eliminating the need for bridging processes. The proposed multi-scale architecture not only improves generation quality but also accelerates the sampling process and promotes scaling flow matching methods. Through extensive experimentation on CelebA-HQ and ImageNet, we demonstrate that our method achieves superior sample quality with fewer GFLOPs and faster inference compared to single-scale and multi-scale flow matching baselines. The proposed model scales effectively to high-resolution generation (up to 1024$\times$1024) while maintaining lower computational overhead.

---

### ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making

Authors: Ziyang Guo, Yifan Wu, Jason Hartline, Kenneth Holstein, Jessica Hullman
Published: 2026-02-23
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2602.19458v1

Multi-agent decision pipelines can outperform single agent workflows when complementarity holds, i.e., different agents bring unique information to the table to inform a final decision. We propose ComplLLM, a post-training framework based on decision theory that fine-tunes a decision-assistant LLM using complementary information as reward to output signals that complement existing agent decisions. We validate ComplLLM on synthetic and real-world tasks involving domain experts, demonstrating how the approach recovers known complementary information and produces plausible explanations of complementary signals to support downstream decision-makers.

---

### SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning

Authors: Zelin He, Boran Han, Xiyuan Zhang, Shuai Zhang, Haotian Lin, Qi Zhu, Haoyang Fang, Danielle C. Maddix, Abdul Fatir Ansari, Akash Chandrayan, Abhinav Pradhan, Bernie Wang et al.
Published: 2026-02-23
Categories: cs.LG, cs.AI, cs.CL, stat.ML
arXiv: https://arxiv.org/abs/2602.19455v1

Time-series diagnostic reasoning is essential for many applications, yet existing solutions face a persistent gap: general reasoning large language models (GRLMs) possess strong reasoning skills but lack the domain-specific knowledge to understand complex time-series patterns. Conversely, fine-tuned time-series LLMs (TSLMs) understand these patterns but lack the capacity to generalize reasoning for more complicated questions. To bridge this gap, we propose a hybrid knowledge-injection framework that injects TSLM-generated insights directly into GRLM's reasoning trace, thereby achieving strong time-series reasoning with in-domain knowledge. As collecting data for knowledge injection fine-tuning is costly, we further leverage a reinforcement learning-based approach with verifiable rewards (RLVR) to elicit knowledge-rich traces without human supervision, then transfer such an in-domain thinking trace into GRLM for efficient knowledge injection. We further release SenTSR-Bench, a multivariate time-series-based diagnostic reasoning benchmark collected from real-world industrial operations. Across SenTSR-Bench and other public datasets, our method consistently surpasses TSLMs by 9.1%-26.1% and GRLMs by 7.9%-22.4%, delivering robust, context-aware time-series diagnostic insights.

---

### HD-TTA: Hypothesis-Driven Test-Time Adaptation for Safer Brain Tumor Segmentation

Authors: Kartik Jhawar, Lipo Wang
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19454v1

Standard Test-Time Adaptation (TTA) methods typically treat inference as a blind optimization task, applying generic objectives to all or filtered test samples. In safety-critical medical segmentation, this lack of selectivity often causes the tumor mask to spill into healthy brain tissue or degrades predictions that were already correct. We propose Hypothesis-Driven TTA, a novel framework that reformulates adaptation as a dynamic decision process. Rather than forcing a single optimization trajectory, our method generates intuitive competing geometric hypotheses: compaction (is the prediction noisy? trim artifacts) versus inflation (is the valid tumor under-segmented? safely inflate to recover). It then employs a representation-guided selector to autonomously identify the safest outcome based on intrinsic texture consistency. Additionally, a pre-screening Gatekeeper prevents negative transfer by skipping adaptation on confident cases. We validate this proof-of-concept on a cross-domain binary brain tumor segmentation task, applying a source model trained on adult BraTS gliomas to unseen pediatric and more challenging meningioma target domains. HD-TTA improves safety-oriented outcomes (Hausdorff Distance (HD95) and Precision) over several state-of-the-art representative baselines in the challenging safety regime, reducing the HD95 by approximately 6.4 mm and improving Precision by over 4%, while maintaining comparable Dice scores. These results demonstrate that resolving the safety-adaptation trade-off via explicit hypothesis selection is a viable, robust path for safe clinical model deployment. Code will be made publicly available upon acceptance.

---

### Red-Teaming Claude Opus and ChatGPT-based Security Advisors for Trusted Execution Environments

Authors: Kunal Mukherjee, Spandan Mukherjee
Published: 2026-02-23
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.19450v3

Trusted Execution Environments (TEEs) (e.g., Intel SGX and ArmTrustZone) aim to protect sensitive computation from a compromised operating system, yet real deployments remain vulnerable to microarchitectural leakage, side-channel attacks, and fault injection. In parallel, security teams increasingly rely on Large Language Model (LLM) assistants as security advisors for TEE architecture review, mitigation planning, and vulnerability triage. This creates a socio-technical risk surface: assistants may hallucinate TEE mechanisms, overclaim guarantees (e.g., what attestation does and does not establish), or behave unsafely under adversarial prompting. We present a red-teaming study of two prevalently deployed LLM assistants in the role of TEE security advisors: ChatGPT-5.2 and Claude Opus-4.6, focusing on the inherent limitations and transferability of prompt-induced failures across LLMs. We introduce TEE-RedBench, a TEE-grounded evaluation methodology comprising (i) a TEE-specific threat model for LLM-mediated security work, (ii) a structured prompt suite spanning SGX and TrustZone architecture, attestation and key management, threat modeling, and non-operational mitigation guidance, along with policy-bound misuse probes, and (iii) an annotation rubric that jointly measures technical correctness, groundedness, uncertainty calibration, refusal quality, and safe helpfulness. We find that some failures are not purely idiosyncratic, transferring up to 12.02% across LLM assistants, and we connect these outcomes to secure architecture by outlining an "LLM-in-the-loop" evaluation pipeline: policy gating, retrieval grounding, structured templates, and lightweight verification checks that, when combined, reduce failures by 80.62%.

---

### Decoupling Vision and Language: Codebook Anchored Visual Adaptation

Authors: Jason Wu, Tianchen Zhao, Chang Liu, Jiarui Cai, Zheng Zhang, Zhuowei Li, Aaditya Singh, Xiang Xu, Mani Srivastava, Jonathan Wu
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19449v1

Large Vision-Language Models (LVLMs) use their vision encoders to translate images into representations for downstream reasoning, but the encoders often underperform in domain-specific visual tasks such as medical image diagnosis or fine-grained classification, where representation errors can cascade through the language model, leading to incorrect responses. Existing adaptation methods modify the continuous feature interface between encoder and language model through projector tuning or other parameter-efficient updates, which still couples the two components and requires re-alignment whenever the encoder changes. We introduce CRAFT (Codebook RegulAted Fine-Tuning), a lightweight method that fine-tunes the encoder using a discrete codebook that anchors visual representations to a stable token space, achieving domain adaptation without modifying other parts of the model. This decoupled design allows the adapted encoder to seamlessly boost the performance of LVLMs with different language architectures, as long as they share the same codebook. Empirically, CRAFT achieves an average gain of 13.51% across 10 domain-specific benchmarks such as VQARAD and PlantVillage, while preserving the LLM's linguistic capabilities and outperforming peer methods that operate on continuous tokens.

---

### PIS: A Physics-Informed System for Accurate State Partitioning of $Aβ_{42}$ Protein Trajectories

Authors: Qianfeng Yu, Ningkang Peng, Yanhui Gu
Published: 2026-02-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.19444v1

Understanding the conformational evolution of $β$-amyloid ($Aβ$), particularly the $Aβ_{42}$ isoform, is fundamental to elucidating the pathogenic mechanisms underlying Alzheimer's disease. However, existing end-to-end deep learning models often struggle to capture subtle state transitions in protein trajectories due to a lack of explicit physical constraints. In this work, we introduce PIS, a Physics-Informed System designed for robust metastable state partitioning. By integrating pre-computed physical priors, such as the radius of gyration and solvent-accessible surface area, into the extraction of topological features, our model achieves superior performance on the $Aβ_{42}$ dataset. Furthermore, PIS provides an interactive platform that features dynamic monitoring of physical characteristics and multi-dimensional result validation. This system offers biological researchers a powerful set of analytical tools with physically grounded interpretability. A demonstration video of PIS is available on https://youtu.be/AJHGzUtRCg0.

---

### UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment

Authors: Yecheng Zhang, Rong Zhao, Zhizhou Sha, Yong Li, Lei Wang, Ce Hou, Wen Ji, Hao Huang, Yunshan Wan, Jian Yu, Junhao Xia, Yuru Zhang et al.
Published: 2026-02-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.19442v4

Vision-language models (VLMs) can describe urban scenes in rich detail, yet consistently fail to produce reliable human preference labels in domain-specific tasks such as safety assessment and aesthetic evaluation. The standard fix, fine-tuning or RLHF, requires large-scale annotations and model retraining. We ask a different question: can a frozen VLM be aligned with human preferences without modifying any weights? Our key insight is that VLMs are strong concept extractors but poor decision calibrators. We propose a three-stage post-hoc pipeline that exploits this asymmetry: (i) interpretable evaluation dimensions are automatically mined from consensus exemplars; (ii) an Observer-Debater-Judge chain extracts robust concept scores from the frozen VLM; and (iii) locally-weighted ridge regression on a hybrid manifold calibrates these scores to human ratings. Applied as UrbanAlign on Place Pulse 2.0, the framework reaches 72.2% accuracy (kappa=0.45) across six perception categories, outperforming all baselines by +11.0 pp and zero-shot VLM by +15.5 pp, with full interpretability and zero weight modification.

---

### When AI Teammates Meet Code Review: Collaboration Signals Shaping the Integration of Agent-Authored Pull Requests

Authors: Costain Nachuma, Minhaz Zibran
Published: 2026-02-23
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.19441v1

Autonomous coding agents increasingly contribute to software development by submitting pull requests on GitHub; yet, little is known about how these contributions integrate into human-driven review workflows. We present a large empirical study of agent-authored pull requests using the public AIDev dataset, examining integration outcomes, resolution speed, and review-time collaboration signals. Using logistic regression with repository-clustered standard errors, we find that reviewer engagement has the strongest correlation with successful integration, whereas larger change sizes and coordination-disrupting actions, such as force pushes, are associated with a lower likelihood of merging. In contrast, iteration intensity alone provides limited explanatory power once collaboration signals are considered. A qualitative analysis further shows that successful integration occurs when agents engage in actionable review loops that converge toward reviewer expectations. Overall, our results highlight that the effective integration of agent-authored pull requests depends not only on code quality but also on alignment with established review and coordination practices.

---

### OptiRepair: Closed-Loop Diagnosis and Repair of Supply Chain Optimization Models with LLM Agents

Authors: Ruicheng Ao, David Simchi-Levi, Xinshang Wang
Published: 2026-02-23
Categories: cs.AI, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2602.19439v2

Supply chain optimization models frequently become infeasible because of modeling errors. Diagnosis and repair require scarce OR expertise: analysts must interpret solver diagnostics, trace root causes across echelons, and fix formulations without sacrificing operational soundness. Whether AI agents can perform this task remains untested. We decompose this task into two phases: a domain-agnostic feasibility phase that iteratively repairs any LP using IIS-guided diagnosis, and a domain-specific validation phase that enforces five rationality checks grounded in inventory theory. We test 22 API models from seven families on 976 multi-echelon supply chain problems and train two 8B-parameter models with self-taught reasoning and solver-verified rewards. The trained models reach 81.7% Rational Recovery Rate (RRR) -- the fraction of problems resolved to both feasibility and operational rationality -- versus 42.2% for the best API model and 21.3% on average. The gap concentrates in Phase 1 repair, where API models average 27.6% recovery rate versus 97.2% for trained models. Two gaps separate current AI from reliable model repair: solver interaction, as API models restore only 27.6% of infeasible formulations; and operational rationale, as roughly one in four feasible repairs violate supply chain theory. Each gap requires a different intervention -- targeted training closes the solver interaction gap, while explicit specification as solver-verifiable checks closes the rationality gap. For organizations adopting AI in operational planning, formalizing what 'rational' means in their context is the higher-return investment.

---

### FinSight-Net:A Physics-Aware Decoupled Network with Frequency-Domain Compensation for Underwater Fish Detection in Smart Aquaculture

Authors: Jinsong Yang, Zeyuan Hu, Yichen Li, Hong Yu
Published: 2026-02-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.19437v1

Underwater fish detection (UFD) is a core capability for smart aquaculture and marine ecological monitoring. While recent detectors improve accuracy by stacking feature extractors or introducing heavy attention modules, they often incur substantial computational overhead and, more importantly, neglect the physics that fundamentally limits UFD: wavelength-dependent absorption and turbidity-induced scattering significantly degrade contrast, blur fine structures, and introduce backscattering noise, leading to unreliable localization and recognition. To address these challenges, we propose FinSight-Net, an efficient and physics-aware detection framework tailored for complex aquaculture environments. FinSight-Net introduces a Multi-Scale Decoupled Dual-Stream Processing (MS-DDSP) bottleneck that explicitly targets frequency-specific information loss via heterogeneous convolutional branches, suppressing backscattering artifacts while compensating distorted biological cues through scale-aware and channel-weighted pathways. We further design an Efficient Path Aggregation FPN (EPA-FPN) as a detail-filling mechanism: it restores high-frequency spatial information typically attenuated in deep layers by establishing long-range skip connections and pruning redundant fusion routes, enabling robust detection of non-rigid fish targets under severe blur and turbidity. Extensive experiments on DeepFish, AquaFishSet, and our challenging UW-BlurredFish benchmark demonstrate that FinSight-Net achieves state-of-the-art performance. In particular, on UW-BlurredFish, FinSight-Net reaches 92.8% mAP, outperforming YOLOv11s by 4.8% while reducing parameters by 29.0%, providing a strong and lightweight solution for real-time automated monitoring in smart aquaculture.

---