Weight space Detection of Backdoors in LoRA Adapters
arXiv:2602.15195v1 Announce Type: cross Abstract: LoRA adapters let users fine-tune large language models (LLMs) efficiently. However, LoRA adapters are shared through open repositories like Hugging Face Hub \citep{huggingface_hub_docs}, making them vulnerable to backdoor attacks. Current detection methods require running the...
FrameRef: A Framing Dataset and Simulation Testbed for Modeling Bounded Rational Information Health
arXiv:2602.15273v1 Announce Type: cross Abstract: Information ecosystems increasingly shape how people internalize exposure to adverse digital experiences, raising concerns about the long-term consequences for information health. In modern search and recommendation systems, ranking and personalization policies play a central role...
Hybrid Feature Learning with Time Series Embeddings for Equipment Anomaly Prediction
arXiv:2602.15089v1 Announce Type: new Abstract: In predictive maintenance of equipment, deep learning-based time series anomaly detection has garnered significant attention; however, pure deep learning approaches often fail to achieve sufficient accuracy on real-world data. This study proposes a hybrid approach...
Hybrid Federated and Split Learning for Privacy Preserving Clinical Prediction and Treatment Optimization
arXiv:2602.15304v1 Announce Type: new Abstract: Collaborative clinical decision support is often constrained by governance and privacy rules that prevent pooling patient-level records across institutions. We present a hybrid privacy-preserving framework that combines Federated Learning (FL) and Split Learning (SL) to...
On Surprising Effectiveness of Masking Updates in Adaptive Optimizers
arXiv:2602.15322v1 Announce Type: new Abstract: Training large language models (LLMs) relies almost exclusively on dense adaptive optimizers with increasingly sophisticated preconditioners. We challenge this by showing that randomly masking parameter updates can be highly effective, with a masked variant of...
Doubly Stochastic Mean-Shift Clustering
arXiv:2602.15393v1 Announce Type: new Abstract: Standard Mean-Shift algorithms are notoriously sensitive to the bandwidth hyperparameter, particularly in data-scarce regimes where fixed-scale density estimation leads to fragmentation and spurious modes. In this paper, we propose Doubly Stochastic Mean-Shift (DSMS), a novel...
Fairness over Equality: Correcting Social Incentives in Asymmetric Sequential Social Dilemmas
arXiv:2602.15407v1 Announce Type: new Abstract: Sequential Social Dilemmas (SSDs) provide a key framework for studying how cooperation emerges when individual incentives conflict with collective welfare. In Multi-Agent Reinforcement Learning, these problems are often addressed by incorporating intrinsic drives that encourage...
LLM-as-Judge on a Budget
arXiv:2602.15481v1 Announce Type: new Abstract: LLM-as-a-judge has emerged as a cornerstone technique for evaluating large language models by leveraging LLM reasoning to score prompt-response pairs. Since LLM judgments are stochastic, practitioners commonly query each pair multiple times to estimate mean...
1-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means Quantization
arXiv:2602.15563v1 Announce Type: new Abstract: Quantization-aware training (QAT) is an effective method to drastically reduce the memory footprint of LLMs while keeping performance degradation at an acceptable level. However, the optimal choice of quantization format and bit-width presents a challenge...
Uniform error bounds for quantized dynamical models
arXiv:2602.15586v1 Announce Type: new Abstract: This paper provides statistical guarantees on the accuracy of dynamical models learned from dependent data sequences. Specifically, we develop uniform error bounds that apply to quantized models and imperfect optimization algorithms commonly used in practical...
Certified Per-Instance Unlearning Using Individual Sensitivity Bounds
arXiv:2602.15602v1 Announce Type: new Abstract: Certified machine unlearning can be achieved via noise injection leading to differential privacy guarantees, where noise is calibrated to worst-case sensitivity. Such conservative calibration often results in performance degradation, limiting practical applicability. In this work,...
Join the Largest Global Community in Computing
IEEE Computer Society is the top source for information, inspiration, and collaboration in computer science and engineering, empowering technologist worldwide
Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric
arXiv:2602.14069v1 Announce Type: new Abstract: Scalar reward models compress multi-dimensional human preferences into a single opaque score, creating an information bottleneck that often leads to brittleness and reward hacking in open-ended alignment. We argue that robust alignment for non-verifiable tasks...
Annotation-Efficient Vision-Language Model Adaptation to the Polish Language Using the LLaVA Framework
arXiv:2602.14073v1 Announce Type: new Abstract: Most vision-language models (VLMs) are trained on English-centric data, limiting their performance in other languages and cultural contexts. This restricts their usability for non-English-speaking users and hinders the development of multimodal systems that reflect diverse...
Index Light, Reason Deep: Deferred Visual Ingestion for Visual-Dense Document Question Answering
arXiv:2602.14162v1 Announce Type: new Abstract: Existing multimodal document question answering methods universally adopt a supply-side ingestion strategy: running a Vision-Language Model (VLM) on every page during indexing to generate comprehensive descriptions, then answering questions through text retrieval. However, this "pre-ingestion"...
AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents
arXiv:2602.14257v1 Announce Type: new Abstract: While Large Language Model (LLM) agents have achieved remarkable progress in complex reasoning tasks, evaluating their performance in real-world environments has become a critical problem. Current benchmarks, however, are largely restricted to idealized simulations, failing...
Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook
arXiv:2602.14299v1 Announce Type: new Abstract: As large language model agents increasingly populate networked environments, a fundamental question arises: do artificial intelligence (AI) agent societies undergo convergence dynamics similar to human social systems? Lately, Moltbook approximates a plausible future scenario in...
BLUEPRINT Rebuilding a Legacy: Multimodal Retrieval for Complex Engineering Drawings and Documents
arXiv:2602.13345v1 Announce Type: new Abstract: Decades of engineering drawings and technical records remain locked in legacy archives with inconsistent or missing metadata, making retrieval difficult and often manual. We present Blueprint, a layout-aware multimodal retrieval system designed for large-scale engineering...
Accelerated Discovery of Cryoprotectant Cocktails via Multi-Objective Bayesian Optimization
arXiv:2602.13398v1 Announce Type: new Abstract: Designing cryoprotectant agent (CPA) cocktails for vitrification is challenging because formulations must be concentrated enough to suppress ice formation yet non-toxic enough to preserve cell viability. This tradeoff creates a large, multi-objective design space in...
Preventing Rank Collapse in Federated Low-Rank Adaptation with Client Heterogeneity
arXiv:2602.13486v1 Announce Type: new Abstract: Federated low-rank adaptation (FedLoRA) has facilitated communication-efficient and privacy-preserving fine-tuning of foundation models for downstream tasks. In practical federated learning scenarios, client heterogeneity in system resources and data distributions motivates heterogeneous LoRA ranks across clients....
TrasMuon: Trust-Region Adaptive Scaling for Orthogonalized Momentum Optimizers
arXiv:2602.13498v1 Announce Type: new Abstract: Muon-style optimizers leverage Newton-Schulz (NS) iterations to orthogonalize updates, yielding update geometries that often outperform Adam-series methods. However, this orthogonalization discards magnitude information, rendering training sensitive to step-size hyperparameters and vulnerable to high-energy bursts. To...
Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling
arXiv:2602.13659v1 Announce Type: new Abstract: Fine-tuning large pretrained language models (LLMs) is a cornerstone of modern NLP, yet its growing memory demands (driven by backpropagation and large optimizer States) limit deployment in resource-constrained settings. Zero-order (ZO) methods bypass backpropagation by...
HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models
arXiv:2602.13710v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models enable instruction-following embodied control, but their large compute and memory footprints hinder deployment on resource-constrained robots and edge platforms. While reducing weights to 1-bit precision through binarization can greatly improve efficiency, existing...
Discrete Double-Bracket Flows for Isotropic-Noise Invariant Eigendecomposition
arXiv:2602.13759v1 Announce Type: new Abstract: We study matrix-free eigendecomposition under a matrix-vector product (MVP) oracle, where each step observes a covariance operator $C_k = C_{sig} + \sigma_k^2 I + E_k$. Standard stochastic approximation methods either use fixed steps that couple...
MEMTS: Internalizing Domain Knowledge via Parameterized Memory for Retrieval-Free Domain Adaptation of Time Series Foundation Models
arXiv:2602.13783v1 Announce Type: new Abstract: While Time Series Foundation Models (TSFMs) have demonstrated exceptional performance in generalized forecasting, their performance often degrades significantly when deployed in real-world vertical domains characterized by temporal distribution shifts and domain-specific periodic structures. Current solutions...
sleep2vec: Unified Cross-Modal Alignment for Heterogeneous Nocturnal Biosignals
arXiv:2602.13857v1 Announce Type: new Abstract: Tasks ranging from sleep staging to clinical diagnosis traditionally rely on standard polysomnography (PSG) devices, bedside monitors and wearable devices, which capture diverse nocturnal biosignals (e.g., EEG, EOG, ECG, SpO$_2$). However, heterogeneity across devices and...
Adani pledges $100B to build AI data centers as India seeks bigger role in the global AI race
Adani's plan targets up to 5 gigawatts of capacity, with data centers planned alongside partnerships with Google, Microsoft, and Flipkart.