We propose a novel swap-adversarial framework that mitigates high inter-subject variability and the high-dimensional low-sample-size problem in electrocorticography (ECoG) data. It achieves robust domain generalization across ECoG and electroencephalography (EEG)-based brain-computer interface datasets. Our framework i...
Seongwon Jin, Hanseul Choi, Sung-Gu Yang et al.· 0 citations
Vision-Language Models (VLMs) describe satellite images fluently but struggle with the quantitative spatial reasoning that remote sensing (RS) analysts perform routinely, such as counting buildings, measuring forest area in hectares and computing distances in meters. We introduce SQuID (Satellite Quantitative Intellige...
Peter A. Massih, Eric Cosatto, Martin Renqiang Min· 0 citations
Reinforcement learning (RL) has emerged as a paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human preferences and user-specified tasks. A fundamental limitation remains \textit{the curse of diversity collapse}, where the objective formulation and optimiz...
Jinmei Liu, Haoru Li, Zhenhong Sun et al.· 0 citations
In this paper, we propose a foreground-aware dataset distillation method that performs content-adaptive dual-path patch selection. With the rising computational cost of training large-scale deep models, dataset distillation has emerged as a promising approach for constructing compact synthetic datasets that retain know...
Mingzhuo Li, Guang Li, Longzhen Li et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A novel framework for dimensionality reduction by decomposing the problem into a horizontal RA subgame and a vertical RA subgame, and introducing a HJ-based tracking control algorithm in each subgame that guarantees not only capture of the attacker but also tracking of the attacker thereafter.
Minh Bui, S. Monckton, Mo Chen· Journal of Guidance Control...· 1 citation
Diffusion Policy (DP) excels in embodied control but suffers from high inference latency and computational cost due to multiple iterative denoising steps. Existing diffusion model (DMs) acceleration methods improve inference speed by reducing computational overhead, as DMs for image generation are computation-bound. In...
Large language models (LLM) have achieved remarkable performance across a wide range of tasks. However, their substantial parameter sizes pose significant challenges for deployment on edge devices with limited computational and memory resources. Low-rank compression is a promising approach to address this issue, as it...
Yu-Chen Lu, Sheng-Feng Yu, Hui-Hsien Weng et al.· 0 citations
Large language models (LLMs) excel on multiple-choice clinical diagnosis benchmarks, yet it is unclear how much of this performance reflects underlying probabilistic reasoning. We study this through questions from MedQA that ask for the most likely diagnosis. We introduce Frequency-Based Probabilistic Ranker (FBPR), a...
Large language model (LLM)-driven agents are emerging as a powerful new paradigm for solving complex problems. Despite the empirical success of these practices, a theoretical framework to understand and unify their macroscopic dynamics remains lacking. This paper proposes a method based on the least action principle to...
Zhuo-Yang Song, Qing-Hong Cao, Ming-xing Luo et al.· 0 citations
This paper organizes the general logic around three principles: situated choice, reproductive transmission, and institution-mediated coupling, which are constitutive rather than predictions of growth or improvement.
Experimental results demonstrate that SELF maintains high IP infringement detection accuracy while significantly outperforming state-of-the-art baselines in reducing false positives and showing strong robustness against various downstream modifications, including quantization, pruning, and fine-tuning attacks.
Language agents are moving from single-user assistants to shared collaborators in workspaces, forums, and group chats. A shared agent observes interleaved messages from multiple users, maintains persistent context, and executes tool actions, creating a boundary problem absent from standard single-user agents: the agent...
Atharv Singh Patlan, Peiyao Sheng, S. Ashwin Hebbar et al.· 0 citations
