Deep learning models for coronary vessel segmentation in X-ray angiography often perform poorly on data from centres that were not represented in training. Apart from differences in equipment, the labels of the largest public dataset (ARCADE) are incomplete, as only the segments defined in the SYNTAX score are annotate...
Danial Moafi, Aida Moafi, Mostafa Aryafar et al.· 0 citations
Large language model serving is limited by facility power. Energy per token determines how many tokens a datacenter can serve, while a latency target bounds how quickly each user receives them. During decode, every weight is read from memory for every generated token. Batching amortizes this read across users but makes...
Bole Ma, Ayesha Afzal, Jan Eitzinger et al.· 0 citations
Building general game agents requires both high-level task reasoning and low-latency action control in rapidly changing visual environments. These capabilities favor models with substantially different computational profiles, making them difficult to realize within a single model. In this work, we present TaskFrame, a...
Guangzhi Wang, Junfu Pu, Yiran Wang et al.· 0 citations
This paper proposes a hybrid MPC and RL framework for highway driving in autonomous trucks, where a finite-horizon MPC, solved via dynamic programming, uses a pre-trained RL model for terminal cost estimation.
Hooman Hamze, Benjamin Houshmand, Deepthi Pathare et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Recent advances in Time Series Foundation Models (TSFMs) increasingly rely on axial attention mechanisms, but despite their empirical success, the theoretical properties of axial attention remain largely unexplored. To bridge this gap, we extend the Single Location Regression framework introduced in Marion et al. [2025...
This paper presents EventSeeColor, which uses event-reconstructed grayscale and aligned events to jointly guide a diffusion colorizer that achieves the best structural similarity, learned perceptual scores, and chromatic-region color difference among the external methods.
Chuanzhi Xu, Lang-Yi Chen, Hao-Xian Zhou et al.· 0 citations
Retail sales forecasting underpins inventory planning, yet promotions and calendar events reshape short-term demand. Although each factor usually has historical occurrences, the complete factor combination of a target week often has few precedents. The challenge is therefore to retrieve informative partial matches and...
Chenghao Gu, Zhuokang Shen, Shenghao Wu et al.· 0 citations
Offline goal-conditioned reinforcement learning remains challenging in stochastic long-horizon settings, where compounding value estimation errors hinder reliable goal reaching. While prior methods have sought to address this challenge through various approaches, a key challenge remains path mirage, where agents overco...
Junhyeon Bae, Jaebak Hwang, Gwanwoo Choi et al.· 0 citations
Effective multi-domain adaptation of large language models requires prioritizing relevant domain knowledge while minimizing interference from irrelevant domains. Existing approaches commonly use Low-Rank Adaptation (LoRA) to train a separate adapter for each domain and combine these adapters within one model. However,...
Ming-Zi Cao, Xi Wang, Nikolaos Aletras· 0 citations
Robot foundation models increasingly rely on flow-based action generation for general-purpose manipulation, yet the generated actions are not guaranteed to satisfy physical constraints such as joint limits and collision avoidance. This problem is especially challenging when the feasible set cannot be described analytic...
Jianming Ma, Rongjun Jin, Yizhi Chen et al.· 0 citations
Understanding the internal routing of visual concepts is crucial for the safe and controllable adaptation of generative models. While concept localization has been widely studied in diffusion models, the emerging paradigm of next-scale visual autoregressive models remains largely unexplored. In this paper, we introduce...
Nanxiang Jiang, Yang Liu, Yuanhao Wang et al.· 0 citations
Activation steering changes what a language model generates by editing its hidden states at inference time. Its most common form adds one vector, the difference of class means (DiM), to every hidden state. CHaRS (concept heterogeneity-aware representation steering) uses optimal transport instead: an entropic plan pairs...
