# Research Papers — 2026-02 · bundle page 35 of 210

> Full-text markdown of papers #1701–1750 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/35
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/34.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/36.md)

### The Initial Exploration Problem in Knowledge Graph Exploration

Authors: Claire McNamara, Lucy Hederman, Declan O'Sullivan
Published: 2026-02-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.21066v2

Knowledge Graphs (KGs) enable the integration and representation of complex information across domains, but their semantic richness and structural complexity create substantial barriers for lay users without expertise in semantic web technologies. When encountering an unfamiliar KG, such users face a distinct orientation challenge: they do not know what questions are possible, how the knowledge is structured, or how to begin exploration. This paper identifies and theorises this phenomenon as the Initial Exploration Problem (IEP). Drawing on theories from information behaviour and human-computer interaction, including ASK, exploratory search, information foraging, and cognitive load theory, we develop a conceptual framing of the IEP characterised by three interdependent barriers: scope uncertainty, ontology opacity, and query incapacity. We argue that these barriers converge at the moment of first contact, distinguishing the IEP from related concepts that presuppose an existing starting point or information goal. Analysing KG exploration interfaces at the level of interaction primitives, we suggest that many systems rely on epistemic assumptions that do not hold at first contact. This reveals a structural gap in the design space: the absence of interaction primitives for scope revelation, mechanisms that communicate what a KG contains without requiring users to formulate queries or interpret ontological structures. In articulating the IEP, this paper provides a theoretical lens for evaluating KG interfaces and for designing entry-point scaffolding that supports initial exploration.

---

### Motivation is Something You Need

Authors: Mehdi Acheli, Walid Gaaloul
Published: 2026-02-24
Categories: cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.21064v1

This work introduces a novel training paradigm that draws from affective neuroscience. Inspired by the interplay of emotions and cognition in the human brain and more specifically the SEEKING motivational state, we design a dual-model framework where a smaller base model is trained continuously, while a larger motivated model is activated intermittently during predefined "motivation conditions". The framework mimics the emotional state of high curiosity and anticipation of reward in which broader brain regions are recruited to enhance cognitive performance. Exploiting scalable architectures where larger models extend smaller ones, our method enables shared weight updates and selective expansion of network capacity during noteworthy training steps. Empirical evaluation on the image classification task demonstrates that, not only does the alternating training scheme efficiently and effectively enhance the base model compared to a traditional scheme, in some cases, the motivational model also surpasses its standalone counterpart despite seeing less data per epoch. This opens the possibility of simultaneously training two models tailored to different deployment constraints with competitive or superior performance while keeping training cost lower than when training the larger model.

---

### Tool Use Reduces Depth-Induced Collapse in OOD Reasoning

Authors: David Koplow, Tomer Galanti, Tomaso Poggio
Published: 2026-02-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.21061v2

Many current paths to more advanced AI depend on the assumption that large language models (LLMs) can generalize learned relationships to solve complex, out-of-distribution (OOD) problems. However, this is not an easy quality to measure. For most real-world problems and benchmarks it suffices to exploit a few memorized subproblems or a small fraction of the available data to produce a correct solution. This is interpolation. Generalization requires the capacity to make use of all available data to solve problems without these shortcuts. To test this quality, we introduce a synthetic Boolean circuit reconstruction benchmark over $GF(2)$. We use an adversarial sampling oracle to block partial-information shortcuts, ensuring that each step requires the integration of all historical context with new evidence. Our evaluations reveal that standalone LLMs fall significantly short of sustained reasoning: as problem depth increases, both small and frontier models exhibit a catastrophic collapse in their ability to accurately predict the next logical step. However, we also demonstrate that tool synthesis provides a remedy to this depth-induced reasoning collapse. When allowed to generate, execute, and iteratively refine code, even small architectures can sustain accurate reasoning over long horizons and rival frontier model performance on this task. These results indicate that synthesizing tools plays a crucial role in generalization, beyond the conventional view of merely augmenting systems with specific capabilities.

---

### Tool Building as a Path to "Superintelligence"

Authors: David Koplow, Tomer Galanti, Tomaso Poggio
Published: 2026-02-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.21061v1

The Diligent Learner framework suggests LLMs can achieve superintelligence via test-time search, provided a sufficient step-success probability $γ$. In this work, we design a benchmark to measure $γ$ on logical out-of-distribution inference. We construct a class of tasks involving GF(2) circuit reconstruction that grow more difficult with each reasoning step, and that are, from an information-theoretic standpoint, impossible to reliably solve unless the LLM carefully integrates all of the information provided. Our analysis demonstrates that while the $γ$ value for small LLMs declines superlinearly as depth increases, frontier models exhibit partial robustness on this task. Furthermore, we find that successful reasoning at scale is contingent upon precise tool calls, identifying tool design as a critical capability for LLMs to achieve general superintelligence through the Diligent Learner framework.

---

### An Expert Schema for Evaluating Large Language Model Errors in Scholarly Question-Answering Systems

Authors: Anna Martin-Boyle, William Humphreys, Martha Brown, Cara Leckey, Harmanpreet Kaur
Published: 2026-02-24
Categories: cs.HC, cs.CL
arXiv: https://arxiv.org/abs/2602.21059v1

Large Language Models (LLMs) are transforming scholarly tasks like search and summarization, but their reliability remains uncertain. Current evaluation metrics for testing LLM reliability are primarily automated approaches that prioritize efficiency and scalability, but lack contextual nuance and fail to reflect how scientific domain experts assess LLM outputs in practice. We developed and validated a schema for evaluating LLM errors in scholarly question-answering systems that reflects the assessment strategies of practicing scientists. In collaboration with domain experts, we identified 20 error patterns across seven categories through thematic analysis of 68 question-answer pairs. We validated this schema through contextual inquiries with 10 additional scientists, which showed not only which errors experts naturally identify but also how structured evaluation schemas can help them detect previously overlooked issues. Domain experts use systematic assessment strategies, including technical precision testing, value-based evaluation, and meta-evaluation of their own practices. We discuss implications for supporting expert evaluation of LLM outputs, including opportunities for personalized, schema-driven tools that adapt to individual evaluation patterns and expertise levels.

---

### Adjacency Spectral Embeddings of Correlation Networks

Authors: Keith Levin
Published: 2026-02-24
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2602.21055v1

In many applications, weighted networks are constructed based on time series data: each time series is associated to a vertex and edge weights are given by pairwise correlations. The result is a network whose edge dependency structure violates the assumptions of most common network models. Nonetheless, it is common to analyze these "correlation networks" using embedding methods derived from edge-independent network models, based on a belief that the edges are approximately independent. In this work, we put this modeling choice on firm theoretical ground. We show that when the time series are expressible in terms of a small number of Fourier basis elements (or in some other suitably-chosen basis), correlation networks correspond to latent space networks with dependent edge noise in which the vertex-level latent variables encode the basis coefficients. Further, we show that when time series are observed subject to noise, spectral embedding of the resulting noisy correlation network still recovers these true vertex-level latent representations under suitable assumptions. This characterization of embeddings as learning Fourier coefficients appears to be folklore in the signal processing community in the context of principal component analysis, but is, to the best of our knowledge, new to the statistical network analysis literature.

---

### VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation

Authors: Seongheon Park, Changdae Oh, Hyeong Kyu Choi, Sean Du, Sharon Li
Published: 2026-02-24
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.21054v2

Large Vision-Language Models (LVLMs) frequently hallucinate, limiting their safe deployment in real-world applications. Existing LLM self-evaluation methods rely on a model's ability to estimate the correctness of its own outputs, which can improve deployment reliability; however, they depend heavily on language priors and are therefore ill-suited for evaluating vision-conditioned predictions. We propose VAUQ, a vision-aware uncertainty quantification framework for LVLM self-evaluation that explicitly measures how strongly a model's output depends on visual evidence. VAUQ introduces the Image-Information Score (IS), which captures the reduction in predictive uncertainty attributable to visual input, and an unsupervised core-region masking strategy that amplifies the influence of salient regions. Combining predictive entropy with this core-masked IS yields a training-free scoring function that reliably reflects answer correctness. Comprehensive experiments show that VAUQ consistently outperforms existing self-evaluation methods across multiple datasets.

---

### OCR-Agent: Agentic OCR with Capability and Memory Reflection

Authors: Shimin Wen, Zeyu Zhang, Xingdou Bian, Hongjie Zhu, Lulu He, Layi Shama, Daji Ergu, Ying Cai
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.21053v1

Large Vision-Language Models (VLMs) have demonstrated significant potential on complex visual understanding tasks through iterative optimization methods.However, these models generally lack effective self-correction mechanisms, making it difficult for them to independently rectify cognitive biases. Consequently, during multi-turn revisions, they often fall into repetitive and ineffective attempts, failing to achieve stable improvements in answer quality.To address this issue, we propose a novel iterative self-correction framework that endows models with two key capabilities: Capability Reflection and Memory Reflection. This framework guides the model to first diagnose errors and generate a correction plan via Capability Reflection, then leverage Memory Reflection to review past attempts to avoid repetition and explore new solutions, and finally, optimize the answer through rigorous re-reasoning. Experiments on the challenging OCRBench v2 benchmark show that OCR-Agent outperforms the current open-source SOTA model InternVL3-8B by +2.0 on English and +1.2 on Chinese subsets, while achieving state-of-the-art results in Visual Understanding (79.9) and Reasoning (66.5) - surpassing even larger fine-tuned models. Our method demonstrates that structured, self-aware reflection can significantly enhance VLMs' reasoning robustness without additional training. Code: https://github.com/AIGeeksGroup/OCR-Agent.

---

### Position-Aware Sequential Attention for Accurate Next Item Recommendations

Authors: Timur Nabiev, Evgeny Frolov
Published: 2026-02-24
Categories: cs.IR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.21052v1

Sequential self-attention models usually rely on additive positional embeddings, which inject positional information into item representations at the input. In the absence of positional signals, the attention block is permutation-equivariant over sequence positions and thus has no intrinsic notion of temporal order beyond causal masking. We argue that additive positional embeddings make the attention mechanism only superficially sensitive to sequence order: positional information is entangled with item embedding semantics, propagates weakly in deep architectures, and limits the ability to capture rich sequential patterns. To address these limitations, we introduce a kernelized self-attention mechanism, where a learnable positional kernel operates purely in the position space, disentangled from semantic similarity, and directly modulates attention weights. When applied per attention block, this kernel enables adaptive multi-scale sequential modeling. Experiments on standard next-item prediction benchmarks show that our positional kernel attention consistently improves over strong competing baselines.

---

### PIME: Prototype-based Interpretable MCTS-Enhanced Brain Network Analysis for Disorder Diagnosis

Authors: Kunyu Zhang, Yanwu Yang, Jing Zhang, Xiangjie Shi, Shujian Yu
Published: 2026-02-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.21046v1

Recent deep learning methods for fMRI-based diagnosis have achieved promising accuracy by modeling functional connectivity networks. However, standard approaches often struggle with noisy interactions, and conventional post-hoc attribution methods may lack reliability, potentially highlighting dataset-specific artifacts. To address these challenges, we introduce PIME, an interpretable framework that bridges intrinsic interpretability with minimal-sufficient subgraph optimization by integrating prototype-based classification and consistency training with structural perturbations during learning. This encourages a structured latent space and enables Monte Carlo Tree Search (MCTS) under a prototype-consistent objective to extract compact minimal-sufficient explanatory subgraphs post-training. Experiments on three benchmark fMRI datasets demonstrate that PIME achieves state-of-the-art performance. Furthermore, by constraining the search space via learned prototypes, PIME identifies critical brain regions that are consistent with established neuroimaging findings. Stability analysis shows 90% reproducibility and consistent explanations across atlases.

---

### PaperTrail: A Claim-Evidence Interface for Grounding Provenance in LLM-based Scholarly Q&A

Authors: Anna Martin-Boyle, Cara A. C. Leckey, Martha C. Brown, Harmanpreet Kaur
Published: 2026-02-24
Categories: cs.HC, cs.CL
arXiv: https://arxiv.org/abs/2602.21045v1

Large language models (LLMs) are increasingly used in scholarly question-answering (QA) systems to help researchers synthesize vast amounts of literature. However, these systems often produce subtle errors (e.g., unsupported claims, errors of omission), and current provenance mechanisms like source citations are not granular enough for the rigorous verification that scholarly domain requires. To address this, we introduce PaperTrail, a novel interface that decomposes both LLM answers and source documents into discrete claims and evidence, mapping them to reveal supported assertions, unsupported claims, and information omitted from the source texts. We evaluated PaperTrail in a within-subjects study with 26 researchers who performed two scholarly editing tasks using PaperTrail and a baseline interface. Our results show that PaperTrail significantly lowered participants' trust compared to the baseline. However, this increased caution did not translate to behavioral changes, as people continued to rely on LLM-generated scholarly edits to avoid a cognitively burdensome task. We discuss the value of claim-evidence matching for understanding LLM trustworthiness in scholarly settings, and present design implications for cognition-friendly communication of provenance information.

---

### LogicGraph : Benchmarking Multi-Path Logical Reasoning via Neuro-Symbolic Generation and Verification

Authors: Yanrui Wu, Lingling Zhang, Xinyu Zhang, Jiayu Chang, Pengyu Li, Xu Jiang, Jingtao Hu, Jun Liu
Published: 2026-02-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.21044v1

Evaluations of large language models (LLMs) primarily emphasize convergent logical reasoning, where success is defined by producing a single correct proof. However, many real-world reasoning problems admit multiple valid derivations, requiring models to explore diverse logical paths rather than committing to one route. To address this limitation, we introduce LogicGraph, the first benchmark aimed to systematically evaluate multi-path logical reasoning, constructed via a neuro-symbolic framework that leverages backward logic generation and semantic instantiation. This pipeline yields solver-verified reasoning problems formalized by high-depth multi-path reasoning and inherent logical distractions, where each instance is associated with an exhaustive set of minimal proofs. We further propose a reference-free evaluation framework to rigorously assess model performance in both convergent and divergent regimes. Experiments on state-of-the-art language models reveal a common limitation: models tend to commit early to a single route and fail to explore alternatives, and the coverage gap grows substantially with reasoning depth. LogicGraph exposes this divergence gap and provides actionable insights to motivate future improvements. Our code and data will be released at https://github.com/kkkkarry/LogicGraph.

---

### T1: One-to-One Channel-Head Binding for Multivariate Time-Series Imputation

Authors: Dongik Park, Hyunwoo Ryu, Suahn Bae, Keondo Park, Hyung-Sin Kim
Published: 2026-02-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.21043v4

Imputing missing values in multivariate time series remains challenging, especially under diverse missing patterns and heavy missingness. Existing methods suffer from suboptimal performance as corrupted temporal features hinder effective cross-variable information transfer, amplifying reconstruction errors. Robust imputation requires both extracting temporal patterns from sparse observations within each variable and selectively transferring information across variables--yet current approaches excel at one while compromising the other. We introduce T1 (Time series imputation with 1-to-1 channel-head binding), a CNN-Transformer hybrid architecture that achieves robust imputation through Channel-Head Binding--a mechanism creating one-to-one correspondence between CNN channels and attention heads. This design enables selective information transfer: when missingness corrupts certain temporal patterns, their corresponding attention pathways adaptively down-weight based on remaining observable patterns while preserving reliable cross-variable connections through unaffected channels. Experiments on 11 benchmark datasets demonstrate that T1 achieves state-of-the-art performance, reducing MSE by 46% on average compared to the second-best baseline, with particularly strong gains under extreme sparsity (70% missing ratio). The model generalizes to unseen missing patterns without retraining and uses a consistent hyperparameter configuration across all datasets. The code is available at https://github.com/Oppenheimerdinger/T1.

---

### OmniOCR: Generalist OCR for Ethnic Minority Languages

Authors: Bonan Liu, Zeyu Zhang, Bingbing Meng, Han Wang, Hanshuo Zhang, Chengping Wang, Daji Ergu, Ying Cai
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.21042v1

Optical character recognition (OCR) has advanced rapidly with deep learning and multimodal models, yet most methods focus on well-resourced scripts such as Latin and Chinese. Ethnic minority languages remain underexplored due to complex writing systems, scarce annotations, and diverse historical and modern forms, making generalization in low-resource or zero-shot settings challenging. To address these challenges, we present OmniOCR, a universal framework for ethnic minority scripts. OmniOCR introduces Dynamic Low-Rank Adaptation (Dynamic LoRA) to allocate model capacity across layers and scripts, enabling effective adaptation while preserving knowledge.A sparsity regularization prunes redundant updates, ensuring compact and efficient adaptation without extra inference cost. Evaluations on TibetanMNIST, Shui, ancient Yi, and Dongba show that OmniOCR outperforms zero-shot foundation models and standard post training, achieving state-of-the-art accuracy with superior parameter efficiency, and compared with the state-of-the-art baseline models, it improves accuracy by 39%-66% on these four datasets. Code: https://github.com/AIGeeksGroup/OmniOCR.

---

### Is Multi-Distribution Learning as Easy as PAC Learning: Sharp Rates with Bounded Label Noise

Authors: Rafael Hanashiro, Abhishek Shetty, Patrick Jaillet
Published: 2026-02-24
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.21039v1

Towards understanding the statistical complexity of learning from heterogeneous sources, we study the problem of multi-distribution learning. Given $k$ data sources, the goal is to output a classifier for each source by exploiting shared structure to reduce sample complexity. We focus on the bounded label noise setting to determine whether the fast $1/ε$ rates achievable in single-task learning extend to this regime with minimal dependence on $k$. Surprisingly, we show that this is not the case. We demonstrate that learning across $k$ distributions inherently incurs slow rates scaling with $k/ε^2$, even under constant noise levels, unless each distribution is learned separately. A key technical contribution is a structured hypothesis-testing framework that captures the statistical cost of certifying near-optimality under bounded noise-a cost we show is unavoidable in the multi-distribution setting. Finally, we prove that when competing with the stronger benchmark of each distribution's optimal Bayes error, the sample complexity incurs a \textit{multiplicative} penalty in $k$. This establishes a \textit{statistical} separation between random classification noise and Massart noise, highlighting a fundamental barrier unique to learning from multiple sources.

---

### Empirically Calibrated Conditional Independence Tests

Authors: Milleno Pan, Antoine de Mathelin, Wesley Tansey
Published: 2026-02-24
Categories: stat.ME, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.21036v1

Conditional independence tests (CIT) are widely used for causal discovery and feature selection. Even with false discovery rate (FDR) control procedures, they often fail to provide frequentist guarantees in practice. We highlight two common failure modes: (i) in small samples, asymptotic guarantees for many CITs can be inaccurate and even correctly specified models fail to estimate the noise levels and control the error, and (ii) when sample sizes are large but models are misspecified, unaccounted dependencies skew the test's behavior and fail to return uniform p-values under the null. We propose Empirically Calibrated Conditional Independence Tests (ECCIT), a method that measures and corrects for miscalibration. For a chosen base CIT (e.g., GCM, HRT), ECCIT optimizes an adversary that selects features and response functions to maximize a miscalibration metric. ECCIT then fits a monotone calibration map that adjusts the base-test p-values in proportion to the observed miscalibration. Across empirical benchmarks on synthetic and real data, ECCIT achieves valid FDR with higher power than existing calibration strategies while remaining test agnostic.

---

### Not Just What's There: Enabling CLIP to Comprehend Negated Visual Descriptions Without Fine-tuning

Authors: Junhao Xiao, Zhiyu Wu, Hao Lin, Yi Chen, Yahui Liu, Xiaoran Zhao, Zixu Wang, Zejiang He
Published: 2026-02-24
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2602.21035v1

Vision-Language Models (VLMs) like CLIP struggle to understand negation, often embedding affirmatives and negatives similarly (e.g., matching "no dog" with dog images). Existing methods refine negation understanding via fine-tuning CLIP's text encoder, risking overfitting. In this work, we propose CLIPGlasses, a plug-and-play framework that enhances CLIP's ability to comprehend negated visual descriptions. CLIPGlasses adopts a dual-stage design: a Lens module disentangles negated semantics from text embeddings, and a Frame module predicts context-aware repulsion strength, which is integrated into a modified similarity computation to penalize alignment with negated semantics, thereby reducing false positive matches. Experiments show that CLIP equipped with CLIPGlasses achieves competitive in-domain performance and outperforms state-of-the-art methods in cross-domain generalization. Its superiority is especially evident under low-resource conditions, indicating stronger robustness across domains.

---

### MIP Candy: A Modular PyTorch Framework for Medical Image Processing

Authors: Tianhao Fu, Yucheng Chen
Published: 2026-02-24
Categories: cs.CV, cs.AI, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2602.21033v1

Medical image processing demands specialized software that handles high-dimensional volumetric data, heterogeneous file formats, and domain-specific training procedures. Existing frameworks either provide low-level components that require substantial integration effort or impose rigid, monolithic pipelines that resist modification. We present MIP Candy (MIPCandy), a freely available, PyTorch-based framework designed specifically for medical image processing. MIPCandy provides a complete, modular pipeline spanning data loading, training, inference, and evaluation, allowing researchers to obtain a fully functional process workflow by implementing a single method, $\texttt{build_network}$, while retaining fine-grained control over every component. Central to the design is $\texttt{LayerT}$, a deferred configuration mechanism that enables runtime substitution of convolution, normalization, and activation modules without subclassing. The framework further offers built-in $k$-fold cross-validation, dataset inspection with automatic region-of-interest detection, deep supervision, exponential moving average, multi-frontend experiment tracking (Weights & Biases, Notion, MLflow), training state recovery, and validation score prediction via quotient regression. An extensible bundle ecosystem provides pre-built model implementations that follow a consistent trainer--predictor pattern and integrate with the core framework without modification. MIPCandy is open-source under the Apache-2.0 license and requires Python~3.12 or later. Source code and documentation are available at https://github.com/ProjectNeura/MIPCandy.

---

### Exchangeable Gaussian Processes for Staggered-Adoption Policy Evaluation

Authors: Hayk Gevorgyan, Konstantinos Kalogeropoulos, Angelos Alexopoulos
Published: 2026-02-24
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2602.21031v1

We study the use of exchangeable multi-task Gaussian processes (GPs) for causal inference in panel data, applying the framework to two settings: one with a single treated unit subject to a once-and-for-all treatment and another with multiple treated units and staggered treatment adoption. Our approach models the joint evolution of outcomes for treated and control units through a GP prior that ensures exchangeability across units while allowing for flexible nonlinear trends over time. The resulting posterior predictive distribution for the untreated potential outcomes of the treated unit provides a counterfactual path, from which we derive pointwise and cumulative treatment effects, along with credible intervals to quantify uncertainty. We implement several variations of the exchangeable GP model using different kernel functions. To assess prediction accuracy, we conduct a placebo-style validation within the pre-intervention window by selecting a ``fake'' intervention date. Ultimately, this study illustrates how exchangeable GPs serve as a flexible tool for policy evaluation in panel data settings and proposes a novel approach to staggered-adoption designs with a large number of treated and control units.

---

### Matching Multiple Experts: On the Exploitability of Multi-Agent Imitation Learning

Authors: Antoine Bergerault, Volkan Cevher, Negar Mehr
Published: 2026-02-24
Categories: cs.LG, cs.GT, cs.MA
arXiv: https://arxiv.org/abs/2602.21020v1

Multi-agent imitation learning (MA-IL) aims to learn optimal policies from expert demonstrations of interactions in multi-agent interactive domains. Despite existing guarantees on the performance of the resulting learned policies, characterizations of how far the learned polices are from a Nash equilibrium are missing for offline MA-IL. In this paper, we demonstrate impossibility and hardness results of learning low-exploitable policies in general $n$-player Markov Games. We do so by providing examples where even exact measure matching fails, and demonstrating a new hardness result on characterizing the Nash gap given a fixed measure matching error. We then show how these challenges can be overcome using strategic dominance assumptions on the expert equilibrium. Specifically, for the case of dominant strategy expert equilibria, assuming Behavioral Cloning error $ε_{\text{BC}}$, this provides a Nash imitation gap of $\mathcal{O}\left(nε_{\text{BC}}/(1-γ)^2\right)$ for a discount factor $γ$. We generalize this result with a new notion of best-response continuity, and argue that this is implicitly encouraged by standard regularization techniques.

---

### From Perception to Action: An Interactive Benchmark for Vision Reasoning

Authors: Yuhao Wu, Maojia Song, Yihuai Lan, Lei Wang, Zhiqiang Hu, Yao Xiao, Heng Zhou, Weihua Zheng, Dylan Raharja, Soujanya Poria, Roy Ka-Wei Lee
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.21015v1

Understanding the physical structure is essential for real-world applications such as embodied agents, interactive design, and long-horizon manipulation. Yet, prevailing Vision-Language Model (VLM) evaluations still center on structure-agnostic, single-turn setups (e.g., VQA), which fail to assess agents' ability to reason about how geometry, contact, and support relations jointly constrain what actions are possible in a dynamic environment. To address this gap, we introduce the Causal Hierarchy of Actions and Interactions (CHAIN) benchmark, an interactive 3D, physics-driven testbed designed to evaluate whether models can understand, plan, and execute structured action sequences grounded in physical constraints. CHAIN shifts evaluation from passive perception to active problem solving, spanning tasks such as interlocking mechanical puzzles and 3D stacking and packing. We conduct a comprehensive study of state-of-the-art VLMs and diffusion-based models under unified interactive settings. Our results show that top-performing models still struggle to internalize physical structure and causal constraints, often failing to produce reliable long-horizon plans and cannot robustly translate perceived structure into effective actions. The project is available at https://social-ai-studio.github.io/CHAIN/.

---

### Le-DETR: Revisiting Real-Time Detection Transformer with Efficient Encoder Design

Authors: Jiannan Huang, Aditya Kane, Fengzhe Zhou, Yunchao Wei, Humphrey Shi
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.21010v1

Real-time object detection is crucial for real-world applications as it requires high accuracy with low latency. While Detection Transformers (DETR) have demonstrated significant performance improvements, current real-time DETR models are challenging to reproduce from scratch due to excessive pre-training overheads on the backbone, constraining research advancements by hindering the exploration of novel backbone architectures. In this paper, we want to show that by using general good design, it is possible to have \textbf{high performance} with \textbf{low pre-training cost}. After a thorough study of the backbone architecture, we propose EfficientNAT at various scales, which incorporates modern efficient convolution and local attention mechanisms. Moreover, we re-design the hybrid encoder with local attention, significantly enhancing both performance and inference speed. Based on these advancements, we present Le-DETR (\textbf{L}ow-cost and \textbf{E}fficient \textbf{DE}tection \textbf{TR}ansformer), which achieves a new \textbf{SOTA} in real-time detection using only ImageNet1K and COCO2017 training datasets, saving about 80\% images in pre-training stage compared with previous methods. We demonstrate that with well-designed, real-time DETR models can achieve strong performance without the need for complex and computationally expensive pretraining. Extensive experiments show that Le-DETR-M/L/X achieves \textbf{52.9/54.3/55.1 mAP} on COCO Val2017 with \textbf{4.45/5.01/6.68 ms} on an RTX4090. It surpasses YOLOv12-L/X by \textbf{+0.6/-0.1 mAP} while achieving similar speed and \textbf{+20\%} speedup. Compared with DEIM-D-FINE, Le-DETR-M achieves \textbf{+0.2 mAP} with slightly faster inference, and surpasses DEIM-D-FINE-L by \textbf{+0.4 mAP} with only \textbf{0.4 ms} additional latency. Code and weights will be open-sourced.

---

### HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders

Authors: Kun Yuan, Junyu Bi, Daixuan Cheng, Changfa Wu, Shuwen Xiao, Binbin Cao, Jian Wu, Yuning Jiang
Published: 2026-02-24
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2602.21009v2

Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory constraints. While summarizing history via interest centers offers a practical alternative, existing methods struggle to (1) identify user-specific centers at appropriate granularity and (2) accurately assign behaviors, leading to quantization errors and loss of long-tail preferences. To alleviate these issues, we propose Hierarchical Sparse Activation Compression (HiSAC), an efficient framework for personalized sequence modeling. HiSAC encodes interactions into multi-level semantic IDs and constructs a global hierarchical codebook. A hierarchical voting mechanism sparsely activates personalized interest-agents as fine-grained preference centers. Guided by these agents, Soft-Routing Attention aggregates historical signals in semantic space, weighting by similarity to minimize quantization error and retain long-tail behaviors. Deployed on Taobao's "Guess What You Like" homepage, HiSAC achieves significant compression and cost reduction, with online A/B tests showing a consistent 1.65% CTR uplift -- demonstrating its scalability and real-world effectiveness.

---

### VII: Visual Instruction Injection for Jailbreaking Image-to-Video Generation Models

Authors: Bowen Zheng, Yongli Xiang, Ziming Hong, Zerong Lin, Chaojian Yu, Tongliang Liu, Xinge You
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20999v2

Image-to-Video (I2V) generation models, which condition video generation on reference images, have shown emerging visual instruction-following capability, allowing certain visual cues in reference images to act as implicit control signals for video generation. However, this capability also introduces a previously overlooked risk: adversaries may exploit visual instructions to inject malicious intent through the image modality. In this work, we uncover this risk by proposing Visual Instruction Injection (VII), a training-free and transferable jailbreaking framework that intentionally disguises the malicious intent of unsafe text prompts as benign visual instructions in the safe reference image. Specifically, VII coordinates a Malicious Intent Reprogramming module to distill malicious intent from unsafe text prompts while minimizing their static harmfulness, and a Visual Instruction Grounding module to ground the distilled intent onto a safe input image by rendering visual instructions that preserve semantic consistency with the original unsafe text prompt, thereby inducing harmful content during I2V generation. Empirically, our extensive experiments on four state-of-the-art commercial I2V models (Kling-v2.5-turbo, Gemini Veo-3.1, Seedance-1.5-pro, and PixVerse-V5) demonstrate that VII achieves Attack Success Rates of up to 83.5% while reducing Refusal Rates to near zero, significantly outperforming existing baselines.

---

### Generative Pseudo-Labeling for Pre-Ranking with LLMs

Authors: Junyu Bi, Xinting Niu, Daixuan Cheng, Kun Yuan, Tao Wang, Binbin Cao, Jian Wu
Published: 2026-02-24
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2602.20995v2

Pre-ranking is a critical stage in industrial recommendation systems, tasked with efficiently scoring thousands of recalled items for downstream ranking. A key challenge is the train-serving discrepancy: pre-ranking models are trained only on exposed interactions, yet must score all recalled candidates -- including unexposed items -- during online serving. This mismatch not only induces severe sample selection bias but also degrades generalization, especially for long-tail content. Existing debiasing approaches typically rely on heuristics (e.g., negative sampling) or distillation from biased rankers, which either mislabel plausible unexposed items as negatives or propagate exposure bias into pseudo-labels. In this work, we propose Generative Pseudo-Labeling (GPL), a framework that leverages large language models (LLMs) to generate unbiased, content-aware pseudo-labels for unexposed items, explicitly aligning the training distribution with the online serving space. By offline generating user-specific interest anchors and matching them with candidates in a frozen semantic space, GPL provides high-quality supervision without adding online latency. Deployed in a large-scale production system, GPL improves click-through rate by 3.07%, while significantly enhancing recommendation diversity and long-tail item discovery.

---

### Multimodal MRI Report Findings Supervised Brain Lesion Segmentation with Substructures

Authors: Yubin Ge, Yongsong Huang, Xiaofeng Liu
Published: 2026-02-24
Categories: eess.IV, cs.AI, cs.CL, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.20994v1

Report-supervised (RSuper) learning seeks to alleviate the need for dense tumor voxel labels with constraints derived from radiology reports (e.g., volumes, counts, sizes, locations). In MRI studies of brain tumors, however, we often involve multi-parametric scans and substructures. Here, fine-grained modality/parameter-wise reports are usually provided along with global findings and are correlated with different substructures. Moreover, the reports often describe only the largest lesion and provide qualitative or uncertain cues (``mild,'' ``possible''). Classical RSuper losses (e.g., sum volume consistency) can over-constrain or hallucinate unreported findings under such incompleteness, and are unable to utilize these hierarchical findings or exploit the priors of varied lesion types in a merged dataset. We explicitly parse the global quantitative and modality-wise qualitative findings and introduce a unified, one-sided, uncertainty-aware formulation (MS-RSuper) that: (i) aligns modality-specific qualitative cues (e.g., T1c enhancement, FLAIR edema) with their corresponding substructures using existence and absence losses; (ii) enforces one-sided lower-bounds for partial quantitative cues (e.g., largest lesion size, minimal multiplicity); and (iii) adds extra- vs. intra-axial anatomical priors to respect cohort differences. Certainty tokens scale penalties; missing cues are down-weighted. On 1238 report-labeled BraTS-MET/MEN scans, our MS-RSuper largely outperforms both a sparsely-supervised baseline and a naive RSuper method.

---

### Cycle-Consistent Tuning for Layered Image Decomposition

Authors: Zheng Gu, Min Lu, Zhida Sun, Dani Lischinski, Daniel Cohen-Or, Hui Huang
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20989v3

Disentangling visual layers in real-world images is a persistent challenge in vision and graphics, as such layers often involve non-linear and globally coupled interactions, including shading, reflection, and perspective distortion. In this work, we present an in-context image decomposition framework that leverages large diffusion foundation models for layered separation. We focus on the challenging case of logo-object decomposition, where the goal is to disentangle a logo from the surface on which it appears while faithfully preserving both layers. Our method fine-tunes a pretrained diffusion model via lightweight LoRA adaptation and introduces a cycle-consistent tuning strategy that jointly trains decomposition and composition models, enforcing reconstruction consistency between decomposed and recomposed images. This bidirectional supervision substantially enhances robustness in cases where the layers exhibit complex interactions. Furthermore, we introduce a progressive self-improving process, which iteratively augments the training set with high-quality model-generated examples to refine performance. Extensive experiments demonstrate that our approach achieves accurate and coherent decompositions and also generalizes effectively across other decomposition types, suggesting its potential as a unified framework for layered image decomposition.

---

### EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer

Authors: Munish Monga, Vishal Chudasama, Pankaj Wasnik, C. V. Jawahar
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20985v2

Real-world object detection must operate in evolving environments where new classes emerge, domains shift, and unseen objects must be identified as "unknown": all without accessing prior data. We introduce Evolving World Object Detection (EWOD), a paradigm coupling incremental learning, domain adaptation, and unknown detection under exemplar-free constraints. To tackle EWOD, we propose EW-DETR framework that augments DETR-based detectors with three synergistic modules: Incremental LoRA Adapters for exemplar-free incremental learning under evolving domains; a Query-Norm Objectness Adapter that decouples objectness-aware features from DETR decoder queries; and Entropy-Aware Unknown Mixing for calibrated unknown detection. This framework generalises across DETR-based detectors, enabling state-of-the-art RF-DETR to operate effectively in evolving-world settings. We also introduce FOGS (Forgetting, Openness, Generalisation Score) to holistically evaluate performance across these dimensions. Extensive experiments on Pascal Series and Diverse Weather benchmarks show EW-DETR outperforms other methods, improving FOGS by 57.24%.

---

### Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models

Authors: Christian Simon, Masato Ishii, Wei-Yao Wang, Koichi Saito, Akio Hayakawa, Dongseok Shim, Zhi Zhong, Shuyang Cui, Shusuke Takahashi, Takashi Shibuya, Yuki Mitsufuji
Published: 2026-02-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.20981v3

Scaling multimodal alignment between video and audio is challenging, particularly due to limited data and the mismatch between text descriptions and frame-level video information. In this work, we tackle the scaling challenge in multimodal-to-audio generation, examining whether models trained on short instances can generalize to longer ones during testing. To tackle this challenge, we present multimodal hierarchical networks so-called MMHNet, an enhanced extension of state-of-the-art video-to-audio models. Our approach integrates a hierarchical method and non-causal Mamba to support long-form audio generation. Our proposed method significantly improves long audio generation up to more than 5 minutes. We also prove that training short and testing long is possible in the video-to-audio generation tasks without training on the longer durations. We show in our experiments that our proposed method could achieve remarkable results on long-video to audio benchmarks, beating prior works in video-to-audio tasks. Moreover, we showcase our model capability in generating more than 5 minutes, while prior video-to-audio methods fall short in generating with long durations.

---

### CrystaL: Spontaneous Emergence of Visual Latents in MLLMs

Authors: Yang Zhang, Danyang Li, Yuxuan Li, Xin Zhang, Tianyu Xie, Mingming Cheng, Xiang Li
Published: 2026-02-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.20980v2

Multimodal Large Language Models (MLLMs) have achieved remarkable performance by integrating powerful language backbones with large-scale visual encoders. Among these, latent Chain-of-Thought (CoT) methods enable implicit reasoning in continuous hidden states, facilitating seamless vision-language integration and faster inference. However, existing heuristically predefined supervision signals in latent CoT provide limited guidance for preserving critical visual information in intermediate latent states. To address this limitation, we propose CrystaL (Crystallized Latent Reasoning), a single-stage framework with two paths to process intact and corrupted images, respectively. By explicitly aligning the attention patterns and prediction distributions across the two paths, CrystaL crystallizes latent representations into task-relevant visual semantics, without relying on auxiliary annotations or external modules. Extensive experiments on perception-intensive benchmarks demonstrate that CrystaL consistently outperforms state-of-the-art baselines, achieving substantial gains in fine-grained visual understanding while maintaining robust reasoning capabilities.

---

### Toward an Agentic Infused Software Ecosystem

Authors: Mark Marron
Published: 2026-02-24
Categories: cs.SE, cs.AI, cs.PL
arXiv: https://arxiv.org/abs/2602.20979v1

Fully leveraging the capabilities of AI agents in software development requires a rethinking of the software ecosystem itself. To this end, this paper outlines the creation of an Agentic Infused Software Ecosystem (AISE), that rests on three pillars. The first, of course, is the AI agents themselves, which in the past 5 years have moved from simple code completion and toward sophisticated independent development tasks, a trend which will only continue. The second pillar is the programming language and APIs (or tools) that these agents use to accomplish tasks, and increasingly, serve as the communication substrate that humans and AI agents interact and collaborate through. The final pillar is the runtime environment and ecosystem that agents operate within, and which provide the capabilities that programmatic agents use to interface with (and effect actions in) the external world. To realize the vision of AISE, all three pillars must be advanced in a holistic manner, and critically, in a manner that is synergistic for AI agents as they exist today, those that will exist in the future, and for the human developers that work alongside them.

---

### Evaluating Proactive Risk Awareness of Large Language Models

Authors: Xuan Luo, Yubin Chen, Zhiyu Hou, Linpu Yu, Geng Tu, Jing Li, Ruifeng Xu
Published: 2026-02-24
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2602.20976v1

As large language models (LLMs) are increasingly embedded in everyday decision-making, their safety responsibilities extend beyond reacting to explicit harmful intent toward anticipating unintended but consequential risks. In this work, we introduce a proactive risk awareness evaluation framework that measures whether LLMs can anticipate potential harms and provide warnings before damage occurs. We construct the Butterfly dataset to instantiate this framework in the environmental and ecological domain. It contains 1,094 queries that simulate ordinary solution-seeking activities whose responses may induce latent ecological impact. Through experiments across five widely used LLMs, we analyze the effects of response length, languages, and modality. Experimental results reveal consistent, significant declines in proactive awareness under length-restricted responses, cross-lingual similarities, and persistent blind spots in (multimodal) species protection. These findings highlight a critical gap between current safety alignment and the requirements of real-world ecological responsibility, underscoring the need for proactive safeguards in LLM deployment.

---

### MAST: A Multi-fidelity Augmented Surrogate model via Spatial Trust-weighting

Authors: Ahmed Mohamed Eisa Nasr, Ali Elham, Haris Moazam Sheikh
Published: 2026-02-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.20974v2

In engineering design and scientific computing, computational cost and predictive accuracy are intrinsically coupled. High-fidelity simulations provide accurate predictions but at substantial computational costs, while lower-fidelity approximations offer efficiency at the expense of accuracy. Multi-fidelity surrogate modelling addresses this trade-off by combining abundant low-fidelity data with sparse high-fidelity observations. However, existing methods rely on global correlation assumptions that can often fail in practice to capture how fidelity relationships vary across the input space, leading to poor performance, particularly under tight budget constraints. We introduce MAST, a method that blends corrected low-fidelity observations with high-fidelity predictions, trusting high-fidelity near observed samples and relying on corrected low-fidelity elsewhere. MAST achieves this through explicit discrepancy modelling and distance-based weighting with closed-form variance propagation, producing a single heteroscedastic Gaussian process. Across multi-fidelity synthetic benchmarks, MAST shows a marked improvement over the current state-of-the-art techniques. Crucially, MAST maintains robust performance across varying total budget and fidelity gaps, conditions under which competing methods exhibit significant degradation or unstable behaviour. More broadly, MAST provides a spatially adaptive framework for multi-fidelity Gaussian-process modelling, in which the contribution of low-fidelity information is governed by its proximity to high-fidelity calibration data, opening a new direction for more reliable surrogate construction under sparse and budget-constrained settings.

---

### Linear Reasoning vs. Proof by Cases: Obstacles for Large Language Models in FOL Problem Solving

Authors: Yuliang Ji, Fuchen Shen, Jian Wu, Qiujie Xie, Yue Zhang
Published: 2026-02-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.20973v1

To comprehensively evaluate the mathematical reasoning capabilities of Large Language Models (LLMs), researchers have introduced abundant mathematical reasoning datasets. However, most existing datasets primarily focus on linear reasoning, neglecting other parts such as proof by contradiction and proof by cases, which are crucial for investigating LLMs' reasoning abilities. To address this limitation, we first introduce a novel first-order logic (FOL) dataset named PC-FOL, annotated by professional mathematicians, focusing on case-based reasoning problems. All instances in this dataset are equipped with a manually written natural language proof, clearly distinguishing it from conventional linear reasoning datasets. Our experimental results over leading LLMs demonstrate a substantial performance gap between linear reasoning and case-based reasoning problems. To further investigate this phenomenon, we provide a theoretical analysis grounded in graphical model, which provides an explanation for the observed disparity between the two types of reasoning problems. We hope this work can reveal the core challenges in the field of automated natural language mathematical proof generation, paving the way for future research.

---

### Are Multimodal Large Language Models Good Annotators for Image Tagging?

Authors: Ming-Kun Xie, Jia-Hao Xiao, Zhiqiang Kou, Zhongnian Li, Gang Niu, Masashi Sugiyama
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20972v1

Image tagging, a fundamental vision task, traditionally relies on human-annotated datasets to train multi-label classifiers, which incurs significant labor and costs. While Multimodal Large Language Models (MLLMs) offer promising potential to automate annotation, their capability to replace human annotators remains underexplored. This paper aims to analyze the gap between MLLM-generated and human annotations and to propose an effective solution that enables MLLM-based annotation to replace manual labeling. Our analysis of MLLM annotations reveals that, under a conservative estimate, MLLMs can reduce annotation cost to as low as one-thousandth of the human cost, mainly accounting for GPU usage, which is nearly negligible compared to manual efforts. Their annotation quality reaches about 50\% to 80\% of human performance, while achieving over 90\% performance on downstream training tasks.Motivated by these findings, we propose TagLLM, a novel framework for image tagging, which aims to narrow the gap between MLLM-generated and human annotations. TagLLM comprises two components: Candidates generation, which employs structured group-wise prompting to efficiently produce a compact candidate set that covers as many true labels as possible while reducing subsequent annotation workload; and label disambiguation, which interactively calibrates the semantic concept of categories in the prompts and effectively refines the candidate labels. Extensive experiments show that TagLLM substantially narrows the gap between MLLM-generated and human annotations, especially in downstream training performance, where it closes about 60\% to 80\% of the difference.

---

### Does Order Matter : Connecting The Law of Robustness to Robust Generalization

Authors: Mihir More, Aritra Das, Jaee Ponde, Himadri Mandal, Vishnu Varadarajan, Debayan Gupta
Published: 2026-02-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.20971v3

Bubeck and Selke (2021) propose the connection between the Law of Robustness and robust generalization error as an open problem. The Law of Robustness states that overparameterization is necessary for models to interpolate robustly, i.e., the interpolating function is required to be Lipschitz. Wu et al. (2023) extend this law to arbitrary data distributions, proving that the Lipschitz constant satisfies $L = Ω(n^{1/d})$. Robust generalization, on the other hand, asks whether small robust training loss implies small robust test loss. This can be studied using statistical learning techniques such as Rademacher complexities, where a bound on the Rademacher complexity of the robust loss class implies a bound on the Lipschitzness of the function class. We use this connection to explicitly link the two for arbitrary data distributions. (i) We prove that the order of the Lipschitz bound remains the same when considering the global Rademacher complexity of robust loss classes. (ii) At the local scale, i.e., for subsets of functions with small empirical error, the order of the Lipschitz bound changes with the perturbation radius $ρ$ and the localized concentration term $\sqrt{r/n}$.

---

### Training-Free Intelligibility-Guided Observation Addition for Noisy ASR

Authors: Haoyang Li, Changsong Liu, Wei Rao, Hao Shi, Sakriani Sakti, Eng Siong Chng
Published: 2026-02-24
Categories: eess.AS, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2602.20967v2

Automatic speech recognition (ASR) degrades severely in noisy environments. Although speech enhancement (SE) front-ends effectively suppress background noise, they often introduce artifacts that harm recognition. Observation addition (OA) addressed this issue by fusing noisy and SE enhanced speech, improving recognition without modifying the parameters of the SE or ASR models. This paper proposes an intelligibility-guided OA method, where fusion weights are derived from intelligibility estimates obtained directly from the backend ASR. Unlike prior OA methods based on trained neural predictors, the proposed method is training-free, reducing complexity and enhances generalization. Extensive experiments across diverse SE-ASR combinations and datasets demonstrate strong robustness and improvements over existing OA baselines. Additional analyses of intelligibility-guided switching-based alternatives and frame versus utterance-level OA further validate the proposed design.

---

### Blackbird Language Matrices: A Framework to Investigate the Linguistic Competence of Language Models

Authors: Paola Merlo, Chunyang Jiang, Giuseppe Samo, Vivi Nastase
Published: 2026-02-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.20966v1

This article describes a novel language task, the Blackbird Language Matrices (BLM) task, inspired by intelligence tests, and illustrates the BLM datasets, their construction and benchmarking, and targeted experiments on chunking and systematicity. BLMs are multiple-choice problems, structured at multiple levels: within each sentence, across the input sequence, within each candidate answer. Because of their rich structure, these curated, but naturalistic datasets are key to answer some core questions about current large language models abilities: do LLMs detect linguistic objects and their properties? Do they detect and use systematic patterns across sentences? Are they more prone to linguistic or reasoning errors, and how do these interact? We show that BLMs, while challenging, can be solved at good levels of performance, in more than one language, with simple baseline models or, at better performance levels, with more tailored models. We show that their representations contain the grammatical objects and attributes relevant to solve a linguistic task. We also show that these solutions are reached by detecting systematic patterns across sentences. The paper supports the point of view that curated, structured datasets support multi-faceted investigations of properties of language and large language models. Because they present a curated, articulated structure, because they comprise both learning contexts and expected answers, and because they are partly built by hand, BLMs fall in the category of datasets that can support explainability investigations, and be useful to ask why large language models behave the way they do.

---

### EKF-Based Depth Camera and Deep Learning Fusion for UAV-Person Distance Estimation and Following in SAR Operations

Authors: Luka Šiktar, Branimir Ćaran, Bojan Šekoranja, Marko Švaco
Published: 2026-02-24
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2602.20958v2

Vision-based Unmanned Aerial Vehicles (UAVs) frameworks aid human search tasks by detecting and recognizing specific individuals, then tracking and following them while maintaining a safe distance. A key safety requirement for UAV following is the accurate estimation of the distance between camera and target object under real-world conditions, achieved by fusing multiple image modalities. As part of the system for automatic people detection and face recognition using deep learning, in this paper we present the fusion of depth camera measurements and monocular camera-to-body distance estimation for robust tracking and following. Deep learning based filtering of depth camera data and estimation of camera-to-body distance from a monocular camera are achieved with YOLO-pose, enabling real-time fusion of depth information using the Extended Kalman Filter (EKF) algorithm. The proposed subsystem, designed for use in drones, estimates and measures the distance between the depth camera and the human body keypoints, to maintain the safe distance between the drone and the human target. Our system provides an accurate estimated distance, which has been validated against motion capture ground truth data. The system has been tested in real time indoors, where it reduces the average errors, RMSE and standard deviations of distance estimation up to 15,3% in three tested scenarios. Based on the test results, the EKF fusion-based approach increases the depth detection range by reducing the errors outside the optimal depth camera working range. It also shows improved robustness and precision in challenging conditions, such as reflections and poor visibility, making it suitable for SAR.

---

### See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis

Authors: Jaehyun Park, Minyoung Ahn, Minkyu Kim, Jonghyun Lee, Jae-Gil Lee, Dongmin Park
Published: 2026-02-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.20951v2

Despite recent advances in diffusion models, AI generated images still often contain visual artifacts that compromise realism. Although more thorough pre-training and bigger models might reduce artifacts, there is no assurance that they can be completely eliminated, which makes artifact mitigation a highly crucial area of study. Previous artifact-aware methodologies depend on human-labeled artifact datasets, which are costly and difficult to scale, underscoring the need for an automated approach to reliably acquire artifact-annotated datasets. In this paper, we propose ArtiAgent, which efficiently creates pairs of real and artifact-injected images. It comprises three agents: a perception agent that recognizes and grounds entities and subentities from real images, a synthesis agent that introduces artifacts via artifact injection tools through novel patch-wise embedding manipulation within a diffusion transformer, and a curation agent that filters the synthesized artifacts and generates both local and global explanations for each instance. Using ArtiAgent, we synthesize 100K images with rich artifact annotations and demonstrate both efficacy and versatility across diverse applications. Code is available at link.

---

### Estimation of Confidence Bounds in Binary Classification using Wilson Score Kernel Density Estimation

Authors: Thorbjørn Mosekjær Iversen, Zebin Duan, Frederik Hagelskjær
Published: 2026-02-24
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.20947v1

The performance and ease of use of deep learning-based binary classifiers have improved significantly in recent years. This has opened up the potential for automating critical inspection tasks, which have traditionally only been trusted to be done manually. However, the application of binary classifiers in critical operations depends on the estimation of reliable confidence bounds such that system performance can be ensured up to a given statistical significance. We present Wilson Score Kernel Density Classification, which is a novel kernel-based method for estimating confidence bounds in binary classification. The core of our method is the Wilson Score Kernel Density Estimator, which is a function estimator for estimating confidence bounds in Binomial experiments with conditionally varying success probabilities. Our method is evaluated in the context of selective classification on four different datasets, illustrating its use as a classification head of any feature extractor, including vision foundation models. Our proposed method shows similar performance to Gaussian Process Classification, but at a lower computational complexity.

---

### Some Simple Economics of AGI

Authors: Christian Catalini, Xiang Hui, Jane Wu
Published: 2026-02-24
Categories: econ.GN, cs.AI, cs.CY, cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2602.20946v2

For millennia, human cognition was the primary engine of progress on Earth. As AI decouples cognition from biology, the marginal cost of measurable execution falls to zero, absorbing any labor capturable by metrics--including creative, analytical, and innovative work. The binding constraint on growth is no longer intelligence but human verification bandwidth: the capacity to validate, audit, and underwrite responsibility when execution is abundant. We model the AGI transition as the collision of two racing cost curves: an exponentially decaying Cost to Automate and a biologically bottlenecked Cost to Verify. This structural asymmetry widens a Measurability Gap between what agents can execute and what humans can afford to verify. It also drives a shift from skill-biased to measurability-biased technical change. Rents migrate to verification-grade ground truth, cryptographic provenance, and liability underwriting--the ability to insure outcomes rather than merely generate them. The current human-in-the-loop equilibrium is unstable: eroded from below as apprenticeship collapses (Missing Junior Loop) and from within as experts codify their obsolescence (Codifier's Curse). Unverified deployment becomes privately rational--a Trojan Horse externality. Unmanaged, these forces pull toward a Hollow Economy. Yet by scaling verification alongside agentic capabilities, the forces that threaten collapse become the catalyst for unbounded discovery and experimentation--an Augmented Economy. We derive a practical playbook for individuals, companies, investors, and policymakers. Today's defining challenge is not the race to deploy the most autonomous systems; it is the race to secure the foundations of their oversight. Only by scaling our bandwidth for verification alongside our capacity for execution can we ensure that the intelligence we have summoned preserves the humanity that initiated it.

---

### The Art of Efficient Reasoning: Data, Reward, and Optimization

Authors: Taiqiang Wu, Zenan Xu, Bo Zhou, Ngai Wong
Published: 2026-02-24
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.20945v3

Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning, but also suffer from heavy computational overhead. To address this issue, efficient reasoning aims to incentivize short yet accurate thinking trajectories, typically through reward shaping with Reinforcement Learning (RL). In this paper, we systematically investigate the mechanics of efficient reasoning for LLMs. For comprehensive evaluation, we advocate for more fine-grained metrics, including length distribution conditioned on correctness and performance across a wide spectrum of token budgets ranging from 2k to 32k. First, we reveal that the training process follows a two-stage paradigm: length adaptation and reasoning refinement. Through extensive experiments (about 0.2 million GPU hours) in a unified protocol, we deconstruct training prompts and rollouts, reward shaping, and optimization strategies. A central finding is to maintain a sufficient density of positive reward signals and avoid the short-is-correct trap. Moreover, the learned length bias generalizes across domains and difficulty levels. We distill these findings into valuable insights and practical guidelines, and validate them across the Qwen3 models ranging from 0.6B to 30B, demonstrating the robustness and generalization. Weights are available at https://wutaiqiang.github.io/project/Art

---

### UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling

Authors: Kaiyuan Tan, Yingying Shen, Mingfei Tu, Haohui Zhu, Bing Wang, Guang Chen, Hangjun Ye, Haiyang Sun
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20943v1

Dynamic driving scene reconstruction is critical for autonomous driving simulation and closed-loop learning. While recent feed-forward methods have shown promise for 3D reconstruction, they struggle with long-range driving sequences due to quadratic complexity in sequence length and challenges in modeling dynamic objects over extended durations. We propose UFO, a novel recurrent paradigm that combines the benefits of optimization-based and feed-forward methods for efficient long-range 4D reconstruction. Our approach maintains a 4D scene representation that is iteratively refined as new observations arrive, using a visibility-based filtering mechanism to select informative scene tokens and enable efficient processing of long sequences. For dynamic objects, we introduce an object pose-guided modeling approach that supports accurate long-range motion capture. Experiments on the Waymo Open Dataset demonstrate that our method significantly outperforms both per-scene optimization and existing feed-forward methods across various sequence lengths. Notably, our approach can reconstruct 16-second driving logs within 0.5 second while maintaining superior visual quality and geometric accuracy.

---

### Extending $μ$P: Spectral Conditions for Feature Learning Across Optimizers

Authors: Akshita Gupta, Marieme Ngom, Sam Foreman, Venkatram Vishwanath
Published: 2026-02-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.20937v1

Several variations of adaptive first-order and second-order optimization methods have been proposed to accelerate and scale the training of large language models. The performance of these optimization routines is highly sensitive to the choice of hyperparameters (HPs), which are computationally expensive to tune for large-scale models. Maximal update parameterization $(μ$P$)$ is a set of scaling rules which aims to make the optimal HPs independent of the model size, thereby allowing the HPs tuned on a smaller (computationally cheaper) model to be transferred to train a larger, target model. Despite promising results for SGD and Adam, deriving $μ$P for other optimizers is challenging because the underlying tensor programming approach is difficult to grasp. Building on recent work that introduced spectral conditions as an alternative to tensor programs, we propose a novel framework to derive $μ$P for a broader class of optimizers, including AdamW, ADOPT, LAMB, Sophia, Shampoo and Muon. We implement our $μ$P derivations on multiple benchmark models and demonstrate zero-shot learning rate transfer across increasing model width for the above optimizers. Further, we provide empirical insights into depth-scaling parameterization for these optimizers.

---

### Architecting AgentOS: From Token-Level Context to Emergent System-Level Intelligence

Authors: ChengYou Li, XiaoDong Liu, XiangBao Meng, XinYu Zhao
Published: 2026-02-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.20934v1

The paradigm of Large Language Models is undergoing a fundamental transition from static inference engines to dynamic autonomous cognitive systems.While current research primarily focuses on scaling context windows or optimizing prompt engineering the theoretical bridge between micro scale token processing and macro scale systemic intelligence remains fragmented.This paper proposes AgentOS,a holistic conceptual framework that redefines the LLM as a "Reasoning Kernel" governed by structured operating system logic.Central to this architecture is Deep Context Management which conceptualizes the context window as an Addressable Semantic Space rather than a passive buffer.We systematically deconstruct the transition from discrete sequences to coherent cognitive states introducing mechanisms for Semantic Slicing and Temporal Alignment to mitigate cognitive drift in multi-agent orchestration.By mapping classical OS abstractions such as memory paging interrupt handling and process scheduling onto LLM native constructs, this review provides a rigorous roadmap for architecting resilient scalable and self-evolving cognitive environments.Our analysis asserts that the next frontier of AGI development lies in the architectural efficiency of system-level coordination.

---

### Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting

Authors: Shuangkang Fang, I-Chao Shen, Xuanyang Zhang, Zesheng Wang, Yufeng Wang, Wenrui Ding, Gang Yu, Takeo Igarashi
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20933v1

Recent 3D Gaussian Splatting (3DGS) Dropout methods address overfitting under sparse-view conditions by randomly nullifying Gaussian opacities. However, we identify a neighbor compensation effect in these approaches: dropped Gaussians are often compensated by their neighbors, weakening the intended regularization. Moreover, these methods overlook the contribution of high-degree spherical harmonic coefficients (SH) to overfitting. To address these issues, we propose DropAnSH-GS, a novel anchor-based Dropout strategy. Rather than dropping Gaussians independently, our method randomly selects certain Gaussians as anchors and simultaneously removes their spatial neighbors. This effectively disrupts local redundancies near anchors and encourages the model to learn more robust, globally informed representations. Furthermore, we extend the Dropout to color attributes by randomly dropping higher-degree SH to concentrate appearance information in lower-degree SH. This strategy further mitigates overfitting and enables flexible post-training model compression via SH truncation. Experimental results demonstrate that DropAnSH-GS substantially outperforms existing Dropout methods with negligible computational overhead, and can be readily integrated into various 3DGS variants to enhance their performances. Project Website: https://sk-fun.fun/DropAnSH-GS

---

### Hierarchic-EEG2Text: Assessing EEG-To-Text Decoding across Hierarchical Abstraction Levels

Authors: Anupam Sharma, Harish Katti, Prajwal Singh, Shanmuganathan Raman, Krishna Miyapuram
Published: 2026-02-24
Categories: cs.LG, cs.HC, eess.SP
arXiv: https://arxiv.org/abs/2602.20932v1

An electroencephalogram (EEG) records the spatially averaged electrical activity of neurons in the brain, measured from the human scalp. Prior studies have explored EEG-based classification of objects or concepts, often for passive viewing of briefly presented image or video stimuli, with limited classes. Because EEG exhibits a low signal-to-noise ratio, recognizing fine-grained representations across a large number of classes remains challenging; however, abstract-level object representations may exist. In this work, we investigate whether EEG captures object representations across multiple hierarchical levels, and propose episodic analysis, in which a Machine Learning (ML) model is evaluated across various, yet related, classification tasks (episodes). Unlike prior episodic EEG studies that rely on fixed or randomly sampled classes of equal cardinality, we adopt hierarchy-aware episode sampling using WordNet to generate episodes with variable classes of diverse hierarchy. We also present the largest episodic framework in the EEG domain for detecting observed text from EEG signals in the PEERS dataset, comprising $931538$ EEG samples under $1610$ object labels, acquired from $264$ human participants (subjects) performing controlled cognitive tasks, enabling the study of neural dynamics underlying perception, decision-making, and performance monitoring. We examine how the semantic abstraction level affects classification performance across multiple learning techniques and architectures, providing a comprehensive analysis. The models tend to improve performance when the classification categories are drawn from higher levels of the hierarchy, suggesting sensitivity to abstraction. Our work highlights abstraction depth as an underexplored dimension of EEG decoding and motivates future research in this direction.

---

### Computing a Characteristic Orientation for Rotation-Independent Image Analysis

Authors: Cristian Valero-Abundio, Emilio Sansano-Sansano, Raúl Montoliu, Marina Martínez García
Published: 2026-02-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.20930v1

Handling geometric transformations, particularly rotations, remains a challenge in deep learning for computer vision. Standard neural networks lack inherent rotation invariance and typically rely on data augmentation or architectural modifications to improve robustness. Although effective, these approaches increase computational demands, require specialised implementations, or alter network structures, limiting their applicability. This paper introduces General Intensity Direction (GID), a preprocessing method that improves rotation robustness without modifying the network architecture. The method estimates a global orientation for each image and aligns it to a canonical reference frame, allowing standard models to process inputs more consistently across different rotations. Unlike moment-based approaches that extract invariant descriptors, this method directly transforms the image while preserving spatial structure, making it compatible with convolutional networks. Experimental evaluation on the rotated MNIST dataset shows that the proposed method achieves higher accuracy than state-of-the-art rotation-invariant architectures. Additional experiments on the CIFAR-10 dataset, confirm that the method remains effective under more complex conditions.

---

### HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG

Authors: Yuqi Huang, Ning Liao, Kai Yang, Anning Hu, Shengchao Hu, Xiaoxing Wang, Junchi Yan
Published: 2026-02-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.20926v1

Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations, limiting their reliability in knowledge-intensive tasks. While Retrieval-Augmented Generation (RAG) mitigates these issues, it frequently overlooks structural interdependencies essential for multi-hop reasoning. Graph-based RAG approaches attempt to bridge this gap, yet they typically face trade-offs between accuracy and efficiency due to challenges such as costly graph traversals and semantic noise in LLM-generated summaries. In this paper, we propose HyperNode Expansion and Logical Path-Guided Evidence Localization strategies for GraphRAG (HELP), a novel framework designed to balance accuracy with practical efficiency through two core strategies: 1) HyperNode Expansion, which iteratively chains knowledge triplets into coherent reasoning paths abstracted as HyperNodes to capture complex structural dependencies and ensure retrieval accuracy; and 2) Logical Path-Guided Evidence Localization, which leverages precomputed graph-text correlations to map these paths directly to the corpus for superior efficiency. HELP avoids expensive random walks and semantic distortion, preserving knowledge integrity while drastically reducing retrieval latency. Extensive experiments demonstrate that HELP achieves competitive performance across multiple simple and multi-hop QA benchmarks and up to a 28.8$\times$ speedup over leading Graph-based RAG baselines.

---