February 2026

arXiv:2602.20199v1 Announce Type: new Abstract: Class imbalance, overlap, and noise degrade data quality, reduce model reliability, and limit generalization. Although widely studied in binary classification, these issues remain underexplored in multi-class settings, where complex inter-class relationships make minority-majority structures unclear and traditional clustering fails to capture distribution shape. Approaches that rely only on geometric distances risk removing informative samples and generating low-quality synthetic data, while binarization approaches treat imbalance locally and ignore global inter-class dependencies. At the algorithmic […]

Ver mais

arXiv:2602.20197v1 Announce Type: new Abstract: Reinforcement Learning with verifiable rewards (RLVR) has emerged as a primary learning paradigm for enhancing the reasoning capabilities of multi-modal large language models (MLLMs). However, during RL training, the enormous state space of MLLM and sparse rewards often leads to entropy collapse, policy degradation, or over-exploitation of suboptimal behaviors. This necessitates an exploration strategy that maintains productive stochasticity while avoiding the drawbacks of uncontrolled random sampling, yielding inefficient exploration. In this paper, we […]

Ver mais

arXiv:2602.20196v1 Announce Type: new Abstract: AI agents increasingly require direct, structured access to application data and actions, but production deployments still struggle to express and verify the governance properties that matter in practice: least-privilege authorization, controlled write execution, predictable failure handling, abuse resistance, and auditability. This paper introduces OpenPort Protocol (OPP), a governance-first specification for exposing application tools through a secure server-side gateway that is model- and runtime-neutral and can bind to existing tool ecosystems. OpenPort defines authorization-dependent […]

Ver mais

arXiv:2602.20193v1 Announce Type: new Abstract: Standard evaluations of backdoor attacks on text-to-image (T2I) models primarily measure trigger activation and visual fidelity. We challenge this paradigm, demonstrating that encoder-side poisoning induces persistent, trigger-free semantic corruption that fundamentally reshapes the representation manifold. We trace this vulnerability to a geometric mechanism: a Jacobian-based analysis reveals that backdoors act as low-rank, target-centered deformations that amplify local sensitivity, causing distortion to propagate coherently across semantic neighborhoods. To rigorously quantify this structural degradation, we […]

Ver mais

arXiv:2602.20191v1 Announce Type: new Abstract: Changing runtime complexity on cloud and edge devices necessitates elastic large language model (LLM) deployment, where an LLM can be inferred with various quantization precisions based on available computational resources. However, it has been observed that the calibration parameters for quantization are typically linked to specific precisions, which presents challenges during elastic-precision calibration and precision switching at runtime. In this work, we attribute the source of varying calibration parameters to the varying token-level […]

Ver mais

arXiv:2602.20181v1 Announce Type: new Abstract: Residential energy retrofit decision-making is constrained by an expertise gap, as homeowners lack the technical literacy required for energy assessments. To address this challenge, this study develops a domain-specific large language model (LLM) that provides optimal retrofit recommendations using homeowner-accessible descriptions of basic dwelling characteristics. The model is fine-tuned on physics-based energy simulations and techno-economic calculations derived from 536,416 U.S. residential building prototypes across nine major retrofit categories. Using Low-Rank Adaptation (LoRA), the […]

Ver mais

arXiv:2602.20180v1 Announce Type: new Abstract: As sidewalk delivery robots become increasingly integrated into urban life, this paper begins with a critical provocation: Is robot labor labor? More than a rhetorical question, this inquiry invites closer attention to the social and political arrangements that robot labor entails. Drawing on ethnographic fieldwork across two smart-city districts in Seoul, we examine how delivery robot labor is collectively sustained. While robotic actions are often framed as autonomous and efficient, we show that […]

Ver mais

arXiv:2602.20177v1 Announce Type: new Abstract: In this work, we present a methodology using Physics Informed Neural Networks (PINNs) to determine the required velocity of a coolant, given inlet and outlet temperatures for a given heat flux in a multilayered metal-oxide-semiconductor field-effect transistor (MOSFET). MOSFETs are integral components of Power Electronic Building Blocks (PEBBs) and experiences the majority of the thermal load. Effective cooling of MOSFETs is therefore essential to prevent overheating and potential burnout. Determining the required velocity […]

Ver mais

arXiv:2602.20175v1 Announce Type: new Abstract: We present an application of the tensor network generator-enhanced optimization (TN-GEO) framework to address the traveling salesman problem (TSP), a fundamental combinatorial optimization challenge. Our approach employs a tensor network Born machine based on automatically differentiable matrix product states (MPS) as the generative model, using the Born rule to define probability distributions over candidate solutions. Unlike approaches based on binary encoding, which require $N^2$ variables and penalty terms to enforce valid tour constraints, […]

Ver mais

arXiv:2602.20170v1 Announce Type: new Abstract: Existing red-teaming benchmarks, when adapted to new languages via direct translation, fail to capture socio-technical vulnerabilities rooted in local culture and law, creating a critical blind spot in LLM safety evaluation. To address this gap, we introduce CAGE (Culturally Adaptive Generation), a framework that systematically adapts the adversarial intent of proven red-teaming prompts to new cultural contexts. At the core of CAGE is the Semantic Mold, a novel approach that disentangles a prompt’s […]

Ver mais