arXiv:2603.18620v1 Announce Type: cross Abstract: We introduce Learning to Self-Evolve (LSE), a reinforcement learning framework that trains large language models (LLMs) to improve their own contexts at test time. We situate LSE in the setting of test-time self-evolution, where a model iteratively refines its context from feedback on seen problems to perform better on new […]
Semantic Chameleon: Corpus-Dependent Poisoning Attacks and Defenses in RAG Systems
arXiv:2603.18034v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems extend large language models (LLMs) with external knowledge sources but introduce new attack surfaces through the retrieval pipeline. In particular, adversaries can poison retrieval corpora so that malicious documents are preferentially retrieved at inference time, enabling targeted manipulation of model outputs. We study gradient-guided corpus poisoning […]
Representation Finetuning for Continual Learning
arXiv:2603.11201v2 Announce Type: replace-cross Abstract: The world is inherently dynamic, and continual learning aims to enable models to adapt to ever-evolving data streams. While pre-trained models have shown powerful performance in continual learning, they still require finetuning to adapt effectively to downstream tasks. However, prevailing Parameter-Efficient Fine-Tuning (PEFT) methods operate through empirical, black-box optimization at […]
Probabilistic Federated Learning on Uncertain and Heterogeneous Data with Model Personalization
arXiv:2603.18083v1 Announce Type: cross Abstract: Conventional federated learning (FL) frameworks often suffer from training degradation due to data uncertainty and heterogeneity across local clients. Probabilistic approaches such as Bayesian neural networks (BNNs) can mitigate this issue by explicitly modeling uncertainty, but they introduce additional runtime, latency, and bandwidth overhead that has rarely been studied in […]
AutORAN: LLM-driven Natural Language Programming for Agile xApp Development
arXiv:2603.18604v1 Announce Type: cross Abstract: Traditional RAN systems are closed and monolithic, stifling innovation. The openness and programmability enabled by Open Radio Access Network (O-RAN) are envisioned to revolutionize cellular networks with control-plane applications–xApps. The development of xApps (typically by third-party developers), however, remains time-consuming and cumbersome, often requiring months of manual coding and integration, […]
Discovery of Bimodal Drift Rate Structure in FRB 20240114A: Evidence for Dual Emission Regions
arXiv:2603.18109v1 Announce Type: cross Abstract: We report the discovery of bimodal structure in the drift rate distribution of upward-drifting burst clusters from the hyperactive repeating fast radio burst FRB 20240114A. Using unsupervised machine learning (UMAP dimensionality reduction combined with HDBSCAN density-based clustering) applied to 233 upward-drifting burst clusters from the FAST telescope dataset, we identify […]
Thousand-GPU Large-Scale Training and Optimization Recipe for AI-Native Cloud Embodied Intelligence Infrastructure
arXiv:2603.11101v2 Announce Type: replace-cross Abstract: Embodied intelligence is a key step towards Artificial General Intelligence (AGI), yet its development faces multiple challenges including data, frameworks, infrastructure, and evaluation systems. To address these issues, we have, for the first time in the industry, launched a cloud-based, thousand-GPU distributed training platform for embodied intelligence, built upon the […]
How LLMs Distort Our Written Language
arXiv:2603.18161v1 Announce Type: cross Abstract: Large language models (LLMs) are used by over a billion people globally, most often to assist with writing. In this work, we demonstrate that LLMs not only alter the voice and tone of human writing, but also consistently alter the intended meaning. First, we conduct a human user study to […]
myMNIST: Benchmark of PETNN, KAN, and Classical Deep Learning Models for Burmese Handwritten Digit Recognition
arXiv:2603.18597v1 Announce Type: cross Abstract: We present the first systematic benchmark on myMNIST (formerly BHDD), a publicly available Burmese handwritten digit dataset important for Myanmar NLP/AI research. We evaluate eleven architectures spanning classical deep learning models (Multi-Layer Perceptron, Convolutional Neural Network, Long Short-Term Memory, Gated Recurrent Unit, Transformer), recent alternatives (FastKAN, EfficientKAN), an energy-based model […]
LRConv-NeRV: Low Rank Convolution for Efficient Neural Video Compression
arXiv:2603.18261v1 Announce Type: cross Abstract: Neural Representations for Videos (NeRV) encode entire video sequences within neural network parameters, offering an alternative paradigm to conventional video codecs. However, the convolutional decoder of NeRV remains computationally expensive and memory intensive, limiting its deployment in resource-constrained environments. This paper proposes LRConv-NeRV, an efficient NeRV variant that replaces selected […]
A Unified View of Drifting and Score-Based Models
arXiv:2603.07514v2 Announce Type: replace-cross Abstract: Drifting models train one-step generators by optimizing a mean-shift discrepancy induced by a kernel between the data and model distributions, with Laplace kernels used by default in practice. At each point, this discrepancy compares the kernel-weighted displacement toward nearby data samples with the corresponding displacement toward nearby model samples, yielding […]
Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought
arXiv:2603.18334v1 Announce Type: cross Abstract: As Large Language Models (LLMs) increasingly assist secure software development, their ability to meet the rigorous demands of Rust program verification remains unclear. Existing evaluations treat Rust verification as a black box, assessing models only by binary pass or fail outcomes for proof hints. This obscures whether models truly understand […]