arXiv:2601.06123v1 Announce Type: new Abstract: Solving increasingly complex problems with large language models (LLMs) necessitates a move beyond individual models and towards multi-model systems that can effectively collaborate. While text has traditionally served as the medium for inter-model communication, a…
arXiv:2512.24124v2 Announce Type: replace Abstract: The presence of outliers in Large Language Models (LLMs) weights and activations makes them difficult to quantize. Recent work has leveraged rotations to mitigate these outliers. In this work, we propose methods that learn fusible…
arXiv:2601.06124v1 Announce Type: new Abstract: Accurate roadway travel-time prediction is foundational to transportation systems analysis, yet widespread reliance on either data-intensive congestion models or overly na”ive heuristics limits scalability and practical adoption in engineering workflows. This paper develops a lightweight…
arXiv:2502.03377v4 Announce Type: replace-cross Abstract: As next-generation Internet of Things (NG-IoT) networks continue to grow, the number of connected devices is rapidly increasing, along with their energy demands, creating challenges for resource management and sustainability. Energy-efficient communication, particularly for power-limited…
arXiv:2601.06127v1 Announce Type: new Abstract: Automatic Identification System (AIS) data are vital for maritime domain awareness, yet they often suffer from domain shifts, data sparsity, and class imbalance, which hinder the performance of predictive models. In this paper, we propose…
arXiv:2508.08211v2 Announce Type: replace-cross Abstract: Watermarking LLM-generated text is critical for content attribution and misinformation prevention. However, existing methods compromise text quality, require white-box model access and logit manipulation. These limitations exclude API-based models and multilingual scenarios. We propose SAEMark,…
arXiv:2601.06133v1 Announce Type: new Abstract: Diffusion policies have emerged as a powerful approach for robotic control, demonstrating superior expressiveness in modeling multimodal action distributions compared to conventional policy networks. However, their integration with online reinforcement learning remains challenging due to…
arXiv:2601.07191v1 Announce Type: cross Abstract: This paper introduces Lie groups in degenerate geometric (Clifford) algebras that preserve four fundamental subspaces determined by the grade involution and reversion under the adjoint and twisted adjoint representations. We prove that these Lie groups…
arXiv:2601.06134v1 Announce Type: new Abstract: Electroencephalography (EEG) foundation models hold significant promise for universal Brain-Computer Interfaces (BCIs). However, existing approaches often rely on end-to-end fine-tuning and exhibit limited efficacy under frozen-probing protocols, lacking the intrinsic universality required for broad generalization.…
arXiv:2601.07516v1 Announce Type: cross Abstract: Vision-language models are increasingly employed as multimodal conversational agents (MCAs) for diverse conversational tasks. Recently, reinforcement learning (RL) has been widely explored for adapting MCAs to various human-AI interaction scenarios. Despite showing great enhancement in…
