arXiv:2604.14306v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) have demonstrated high proficiency on English-centric medical examinations, their performance often declines when faced with non-English languages and multimodal diagnostic tasks. This study protocol describes the development of EuropeMedQA, the first comprehensive, multilingual, and multimodal medical examination dataset sourced from official regulatory exams in Italy, […]
Controllable Spoken Dialogue Generation: An LLM-Driven Grading System for K-12 Non-Native English Learners
arXiv:2604.22542v1 Announce Type: cross Abstract: Large language models (LLMs) often fail to meet the pedagogical needs of K-12 English learners in non-native contexts due to a proficiency mismatch. To address this widespread challenge, we introduce a proficiency-aligned framework that adapts LLM outputs to learner abilities, using China’s national curriculum (CSE) as a representative case. Our […]
Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLM
arXiv:2604.18655v2 Announce Type: replace-cross Abstract: Deploying large language models (LLMs) on smartphones poses significant engineering challenges due to stringent constraints on memory, latency, and runtime flexibility. In this work, we present a hardware-aware framework for efficient on-device inference of a LLaMA-based multilingual foundation model supporting multiple use cases on Samsung Galaxy S24 and S25 devices […]
ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoders
arXiv:2604.22550v1 Announce Type: cross Abstract: Self-supervised learning (SSL) encoders are invaluable intellectual property (IP). However, no existing SSL watermarking for IP protection can concurrently satisfy the following two practical requirements: (1) provide ownership verification capability under black-box suspect model access once the stolen encoders are used in downstream tasks; (2) be robust under adversarial watermark […]
QDTraj: Exploration of Diverse Trajectory Primitives for Articulated Objects Robotic Manipulation
arXiv:2604.22551v1 Announce Type: cross Abstract: Thanks to the latest advances in learning and robotics, domestic robots are beginning to enter homes, aiming to execute household chores autonomously. However, robots still struggle to perform autonomous manipulation tasks in open-ended environments. In this context, this paper presents a method that enables a robot to manipulate a wide […]
VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
arXiv:2604.21375v2 Announce Type: replace-cross Abstract: Autonomous GUI agents face two fundamental challenges: early stopping, where agents prematurely declare success without verifiable evidence, and repetitive loops, where agents cycle through the same failing actions without recovery. We present VLAA-GUI, a modular GUI agentic framework built around three integrated components that guide the system on when to […]
Math Takes Two: A test for emergent mathematical reasoning in communication
arXiv:2604.21935v1 Announce Type: new Abstract: Although language models demonstrate remarkable proficiency on mathematical benchmarks, it remains unclear whether this reflects true mathematical reasoning or statistical pattern matching over learning formal syntax. Most existing evaluations rely on symbolic problems grounded in established mathematical conventions, limiting insight into the models’ ability to construct abstract concepts from first […]
Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models
arXiv:2604.22411v1 Announce Type: new Abstract: Even when decoding with temperature $T=0$, large language models (LLMs) can produce divergent outputs for identical inputs. Recent work by Thinking Machines Lab highlights implementation-level sources of nondeterminism, including batch-size variation, kernel non-invariance, and floating-point non-associativity. In this short note we formalize this behavior by introducing the notion of emphbackground […]
Efficiency of Proportional Mechanisms in Online Auto-Bidding Advertising
arXiv:2604.12799v2 Announce Type: replace-cross Abstract: The rise of automated bidding strategies in online advertising presents new challenges in designing and analyzing efficient auction mechanisms. In this paper, we focus on proportional mechanisms within the context of auto-bidding and study the efficiency of pure Nash equilibria, specifically the price of anarchy (PoA), under the liquid welfare […]
AgentSearchBench: A Benchmark for AI Agent Search in the Wild
arXiv:2604.22436v1 Announce Type: new Abstract: The rapid growth of AI agent ecosystems is transforming how complex tasks are delegated and executed, creating a new challenge of identifying suitable agents for a given task. Unlike traditional tools, agent capabilities are often compositional and execution-dependent, making them difficult to assess from textual descriptions alone. However, existing research […]
On the Properties of Feature Attribution for Supervised Contrastive Learning
arXiv:2604.22540v1 Announce Type: cross Abstract: Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit classification layer. However, there exist alternative approaches, such as Contrastive Learning (CL). Instead of explicitly operating a classification, CL has the NN produce an embedding space where […]
On the Hybrid Nature of ABPMS Process Frames and its Implications on Automated Process Discovery
arXiv:2604.22455v1 Announce Type: new Abstract: A core component of any AI-Augmented Business Process Management System (ABPMS) is the process frame, which gives the system process-awareness and defines the boundaries in which the system must operate. Compared to traditional process models, the process frame should, in principle, provide a somewhat more permissive representation of the managed […]