arXiv:2605.15338v2 Announce Type: replace-cross Abstract: Large language models are increasingly augmented with persistent memory, allowing assistants to store user-specific information across sessions for personalization and continuity. This statefulness introduces a new security risk: adversarial content can corrupt what an assistant remembers and thereby influence future interactions. We propose and study sleeper memory poisoning, a delayed […]
Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDA
arXiv:2605.17932v1 Announce Type: cross Abstract: Prompt compression reduces inference cost and context length in large language models, but prior evaluations focus primarily on autoregressive architectures. This study investigates whether prompt compression transfers effectively to diffusion large language models (DLLMs) using LLMLingua-2, specifically the 8B-parameter DLLM LLaDA. We evaluate compression performance on GSM8K, DUC2004, and ShareGPT […]
Operator-Controlled 6G: From Connectivity Infrastructure to Guaranteed Digital Services
arXiv:2605.15553v2 Announce Type: replace-cross Abstract: Sixth-generation mobile networks (6G) are approaching a structural inflection point. Five generations of vendor-led architectures have left operators procuring and operating networks they do not own, on platforms they cannot modify, with AI layers they cannot audit. This paper argues that 6G must reverse this trajectory by reordering operator priorities: […]
No Free Swap: Protocol-Dependent Layer Redundancy in Transformers
arXiv:2605.16234v2 Announce Type: replace-cross Abstract: When researchers ask whether two transformer layers are “equivalent” for compression, they often conflate distinct tests. Replacement asks whether one layer’s map can substitute for another’s in place; interchange asks whether two layers approximately commute when their positions are swapped. Both are output-grounded swap-KL probes, but they need not agree: […]
Quantum Sidecar Architectures for Hybrid AI Training and Inference: Stateful Protected Registers, Stateless Reset-and-Reprepare Circuits and Quantum Weight-State Outlook
arXiv:2605.18031v1 Announce Type: cross Abstract: We propose a quantum sidecar architecture family for future hybrid AI training and inference. The central idea is not to store an entire Transformer in a small quantum memory, nor to claim one-shot collapse into a fully trained model or an optimal answer. Instead, we identify two physically distinct operating […]
Domain Transfer Becomes Identifiable via a Single Alignment
arXiv:2605.17918v1 Announce Type: cross Abstract: Domain transfer (DT) maps source to target distributions and supports tasks such as unsupervised image-to-image translation, single-cell analysis, and cross-platform medical imaging. However, DT is fundamentally ill-posed: push-forward mappings are generally non-identifiable, as measure-preserving automorphisms (MPAs) preserve marginals while altering cross-domain correspondences, leading to content-misaligned translation. Recent work shows that […]
An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments
arXiv:2605.18133v1 Announce Type: cross Abstract: LLM-based chatbot agents increasingly process user requests by combining natural-language reasoning with external tools such as web browsing. These capabilities improve usability, but they also create attack surfaces when untrusted external content is processed as part of a user’ s task. This paper studies a privacy-leakage attack chain based on […]
FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery
arXiv:2605.14854v2 Announce Type: replace-cross Abstract: Human Mesh Recovery (HMR) is fundamentally ambiguous: under occlusion or weak depth cues, multiple 3D bodies can explain the same image evidence. This ambiguity is not uniform across the body, as torso pose and root structure are often relatively well constrained, whereas distal articulations such as the arms and legs […]
Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
arXiv:2605.18591v1 Announce Type: cross Abstract: Natural policy gradients improve optimization by accounting for the geometry of distribution space, but their practical use is limited by the cost of estimating and inverting the Fisher matrix. We present Randomized Advantage Transformation (RAT), a method for estimating Tikhonov-regularized natural policy gradients via direct backpropagation. By applying the Woodbury […]
One Model to Translate Them All: Universal Any-to-Any Translation for Heterogeneous Collaborative Perception
arXiv:2605.17907v1 Announce Type: cross Abstract: By sharing intermediate features, collaborative perception extends each agent’s sensing beyond standalone limits, but real-world feature modality heterogeneity remains a key barrier to effective fusion. Most existing methods, including direct adaption and protocol-based transformation, typically rely on training adapters for newly emerging feature modalities and often require additional retraining or […]
FormuLLA: A Large Language Model Approach to Generating Novel 3D Printable Formulations
arXiv:2601.02071v3 Announce Type: replace Abstract: Pharmaceutical three-dimensional (3D) printing is an advanced fabrication technology with the potential to enable truly personalised dosage forms. Recent studies have integrated artificial intelligence (AI) to accelerate formulation and process development, drastically transforming current approaches to pharmaceutical 3D printing. To date, most AI-driven efforts remain narrowly focused, while failing to […]
ARES-LSHADE: Autoresearch-Enhanced LSHADE with Memetic Polish for the GNBG Benchmark
arXiv:2605.13877v2 Announce Type: replace-cross Abstract: We present ARES-LSHADE, a memetic differential-evolution variant submitted to the GECCO 2026 competition on LLM-designed evolutionary algorithms for the Generalized Numerical Benchmark Generator (GNBG). The algorithm builds on the LLM-LSHADE 2025 winner, contributing two new components: (a) a scout-augmented mutation operator with adaptive CMA-ES integration, produced by an autonomous research […]