arXiv:2603.23902v1 Announce Type: cross Abstract: Retrieving partially relevant segments from untrimmed videos remains difficult due to two persistent challenges: the mismatch in information density between text and video segments, and limited attention mechanisms that overlook semantic focus and event correlations. We present KDC-Net, a Knowledge-Refined Dual Context-Aware Network that tackles these issues from both textual […]
The Price Reversal Phenomenon: When Cheaper Reasoning Models End Up Costing More
arXiv:2603.23971v1 Announce Type: cross Abstract: Developers and consumers increasingly choose reasoning language models (RLMs) based on their listed API prices. However, how accurately do these prices reflect actual inference costs? We conduct the first systematic study of this question, evaluating 8 frontier RLMs across 9 diverse tasks covering competition math, science QA, code generation, and […]
Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness
arXiv:2603.23860v1 Announce Type: cross Abstract: This work investigates the critical role of activation function curvature — quantified by the maximum second derivative $max|sigma”|$ — in adversarial robustness. Using the Recursive Curvature-Tunable Activation Family (RCT-AF), which enables precise control over curvature through parameters $alpha$ and $beta$, we systematically analyze this relationship. Our study reveals a fundamental […]
Ukrainian Visual Word Sense Disambiguation Benchmark
arXiv:2603.23627v1 Announce Type: cross Abstract: This study presents a benchmark for evaluating the Visual Word Sense Disambiguation (Visual-WSD) task in Ukrainian. The main goal of the Visual-WSD task is to identify, with minimal contextual information, the most appropriate representation of a given ambiguous word from a set of ten images. To construct this benchmark, we […]
Learning What Can Be Picked: Active Reachability Estimation for Efficient Robotic Fruit Harvesting
arXiv:2603.23679v1 Announce Type: cross Abstract: Agriculture remains a cornerstone of global health and economic sustainability, yet labor-intensive tasks such as harvesting high-value crops continue to face growing workforce shortages. Robotic harvesting systems offer a promising solution; however, their deployment in unstructured orchard environments is constrained by inefficient perception-to-action pipelines. In particular, existing approaches often rely […]
PoiCGAN: A Targeted Poisoning Based on Feature-Label Joint Perturbation in Federated Learning
arXiv:2603.23574v1 Announce Type: cross Abstract: Federated Learning (FL), as a popular distributed learning paradigm, has shown outstanding performance in improving computational efficiency and protecting data privacy, and is widely applied in industrial image classification. However, due to its distributed nature, FL is vulnerable to threats from malicious clients, with poisoning attacks being a common threat. […]
From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMs
arXiv:2603.24034v1 Announce Type: cross Abstract: Contextual automatic speech recognition (ASR) with Speech-LLMs is typically trained with oracle conversation history, but relies on error-prone history at inference, causing a train-test mismatch in the context channel that we term contextual exposure bias. We propose a unified training framework to improve robustness under realistic histories: (i) Teacher Error […]
Safe Reinforcement Learning with Preference-based Constraint Inference
arXiv:2603.23565v1 Announce Type: cross Abstract: Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be complex, subjective, and even hard to explicitly specify. Existing works on constraint inference rely on restrictive assumptions or extensive expert demonstrations, which is not realistic in many real-world applications. How to cheaply […]
LineMVGNN: Anti-Money Laundering with Line-Graph-Assisted Multi-View Graph Neural Networks
arXiv:2603.23584v1 Announce Type: cross Abstract: Anti-money laundering (AML) systems are important for protecting the global economy. However, conventional rule-based methods rely on domain knowledge, leading to suboptimal accuracy and a lack of scalability. Graph neural networks (GNNs) for digraphs (directed graphs) can be applied to transaction graphs and capture suspicious transactions or accounts. However, most […]
Echoes: A semantically-aligned music deepfake detection dataset
arXiv:2603.23667v1 Announce Type: cross Abstract: We introduce Echoes, a new dataset for music deepfake detection designed for training and benchmarking detectors under realistic and provider-diverse conditions. Echoes comprises 3,577 tracks (110 hours of audio) spanning multiple genres (pop, rock, electronic), and includes content generated by ten popular AI music generation systems. To prevent shortcut learning […]
CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records
arXiv:2603.23719v1 Announce Type: cross Abstract: Electronic health records (EHRs) are invaluable for clinical research, yet privacy concerns severely restrict data sharing. Synthetic data generation offers a promising solution, but EHRs present unique challenges: they contain both numerical and categorical features that evolve over time. While diffusion models have demonstrated strong performance in EHR synthesis, existing […]
Willful Disobedience: Automatically Detecting Failures in Agentic Traces
arXiv:2603.23806v1 Announce Type: cross Abstract: AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make validation difficult. Outcome-only benchmarks can miss critical procedural failures, such as incorrect workflow routing, unsafe tool usage, or violations of […]