arXiv:2604.04225v1 Announce Type: cross Abstract: Learning robot control policies from demonstrations is a powerful paradigm, yet real-world data is often suboptimal, noisy, or otherwise imperfect, posing significant challenges for imitation and reinforcement learning. In this work, we present a formal framework that leverages Temporal Behavior Trees (TBT), an extension of Signal Temporal Logic (STL) with […]
Threshold Modulation for Online Test-Time Adaptation of Spiking Neural Networks
arXiv:2505.05375v3 Announce Type: replace-cross Abstract: Recently, spiking neural networks (SNNs), deployed on neuromorphic chips, provide highly efficient solutions on edge devices in different scenarios. However, their ability to adapt to distribution shifts after deployment has become a crucial challenge. Online test-time adaptation (OTTA) offers a promising solution by enabling models to dynamically adjust to new […]
Towards Context-Aware Image Anonymization with Multi-Agent Reasoning
arXiv:2603.27817v2 Announce Type: replace-cross Abstract: Street-level imagery contains personally identifiable information (PII), some of which is context-dependent. Existing anonymization methods either over-process images or miss subtle identifiers, while API-based solutions compromise data sovereignty. We present an agentic framework CAIAMAR (underlineContext-underlineAware underlineImage underlineAnonymization with underlineMulti-underlineAgent underlineReasoning) for context-aware PII segmentation with diffusion-based anonymization, combining pre-defined processing […]
LLMs Judge Themselves: A Game-Theoretic Framework for Human-Aligned Evaluation
arXiv:2510.15746v2 Announce Type: replace-cross Abstract: Ideal or real – that is the question.In this work, we explore whether principles from game theory can be effectively applied to the evaluation of large language models (LLMs). This inquiry is motivated by the growing inadequacy of conventional evaluation practices, which often rely on fixed-format tasks with reference answers […]
LOCARD: An Agentic Framework for Blockchain Forensics
arXiv:2604.04211v1 Announce Type: cross Abstract: Blockchain forensics inherently involves dynamic and iterative investigations, while many existing approaches primarily model it through static inference pipelines. We propose a paradigm shift towards Agentic Blockchain Forensics (ABF), modeling forensic investigation as a sequential decision-making process. To instantiate this paradigm, we introduce LOCARD, the first agentic framework for blockchain […]
Large Language Models for Combinatorial Optimization of Design Structure Matrix
arXiv:2506.09749v3 Announce Type: replace-cross Abstract: In complex engineering systems, the dependencies among components or development activities are often modeled and analyzed using Design Structure Matrix (DSM). Reorganizing elements within a DSM to minimize feedback loops and enhance modularity or process efficiency constitutes a challenging combinatorial optimization (CO) problem in engineering design and operations. As problem […]
Toward Evaluation Frameworks for Multi-Agent Scientific AI Systems
arXiv:2603.26718v2 Announce Type: replace-cross Abstract: We analyze the challenges of benchmarking scientific (multi)-agentic systems, including the difficulty of distinguishing reasoning from retrieval, the risks of data/model contamination, the lack of reliable ground truth for novel research problems, the complications introduced by tool use, and the replication challenges due to the continuously changing/updating knowledge base. We […]
Low-Bitrate Video Compression through Semantic-Conditioned Diffusion
arXiv:2512.00408v2 Announce Type: replace-cross Abstract: Traditional video codecs optimized for pixel fidelity collapse at ultra-low bitrates and produce severe artifacts. This failure arises from a fundamental misalignment between pixel accuracy and human perception. We propose a semantic video compression framework named DiSCo that transmits only the most meaningful information while relying on generative priors for […]
Which English Do LLMs Prefer? Triangulating Structural Bias Towards American English in Foundation Models
arXiv:2604.04204v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains, yet they expose only limited language settings, most notably “English (US),” despite the global diversity and colonial history of English. Through a postcolonial framing to explain the broader significance, we investigate how geopolitical histories of data curation, digital dominance, and […]
Geometric early warning indicator from stochastic separatrix structure in a random two-state ecosystem model
arXiv:2603.08861v2 Announce Type: replace-cross Abstract: Under-ice blooms in the Arctic can develop rapidly under conditions where conventional early warning signals based on critical slowing down fail due to strong noise or limited observational records. We analyze noise-induced transitions in a temperature phytoplankton stochastic differential equation model exhibiting bistability between background and bloom states. The committor […]
MuDD: A Multimodal Deception Detection Dataset and GSR-Guided Progressive Distillation for Non-Contact Deception Detection
arXiv:2603.26064v2 Announce Type: replace-cross Abstract: Non-contact automatic deception detection remains challenging because visual and auditory deception cues often lack stable cross-subject patterns. In contrast, galvanic skin response (GSR) provides more reliable physiological cues and has been widely used in contact-based deception detection. In this work, we leverage stable deception-related knowledge in GSR to guide representation […]
Security in LLM-as-a-Judge: A Comprehensive SoK
arXiv:2603.29403v2 Announce Type: replace-cross Abstract: LLM-as-a-Judge (LaaJ) is a novel paradigm in which powerful language models are used to assess the quality, safety, or correctness of generated outputs. While this paradigm has significantly improved the scalability and efficiency of evaluation processes, it also introduces novel security risks and reliability concerns that remain largely unexplored. In […]