Deep classifiers deployed in safety-critical services like autonomous-driving perception remain vulnerable to small adversarial perturbations. Certified $\ell_2$ defenses today face a costly trade-off: randomized smoothing (RS) requires hundreds of noisy queries per input, while Lipschitz networks (LN) constrain the ar...
Rui Zhang, Xinle Cao, Huazhen Yu et al.· 0 citations
Amyotrophic lateral sclerosis (ALS) diagnosis remains challenging due to heterogeneous symptoms and reliance on clinical assessment, underscoring the need for objective, data-driven approaches that leverage patient-generated physiological signals. We propose Siam-ALS, an explainable Siamese deep learning framework that...
Abdur Rahman, A. A. M. Muzahid, Istiak Ahmed et al.· 0 citations
We present Gugak-VocalSet, the first publicly available audio dataset for Korean traditional singing with dense annotations of sigimsae, a structured pitch contour system of vocal expressions. Gugak-VocalSet contains 24.5 hours of unaccompanied solo vocal recordings across 305 tracks of representative repertoire curate...
Danbinaerin Han, Wonil Kim, Se-Ah Hong et al.· 0 citations
High-quality coding problems are expensive to collect. Benchmarks such as SWE-bench rely on substantial human curation, while synthetic alternatives typically rely on costly model generation and validation. In this work, we show that new coding problems can be created at almost no cost by composing existing ones. We fo...
Jiaxin Fang, Runyuan He, Arnav Gupta et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
World models and video understanding models are increasingly deployed in dynamic visual environments, yet their robustness to physical adversarial threats remains largely underexplored. We study whether a single physical adversarial texture can mislead the victim model across different real-world scenarios where observ...
Song Xia, Mei-Wen Ding, Chen-Qi Kong et al.· 0 citations
The inherent variability of fMRI responses across trials encourages a generative view of the stimulus-to-response mapping. Prior generative encoders often operate in compressed latent spaces and condition predominantly on semantic features, which provide limited low-level cues for early visual cortex. We propose StimFl...
Bui Van Hung, Dang Thanh Vu, Hoang-Son Vo et al.· 0 citations
Influence functions enable principled data selection for large language models (e.g., identifying influential training samples for model editing, debugging, or efficient fine-tuning). However, scaling IFs to LLMs is hindered by the intractability of billion-scale Hessian matrices and the prohibitive memory overhead of...
Li-Song He, Yun-Xuan Jiang, Hai-Shan Ye et al.· 0 citations
We introduce Anchor-and-Harvest Curriculum (AHC), a domain-informed, rule-based training system for Craftax-Full. AHC combines achievement-oriented tasks, harvested initial-state progress, difficulty adaptation, bounded selection, and original-task practice. It uses no LLM inference and keeps all 43 actions available....
Jiayu Zhu, Luyuan Li, Yuyuan Shi et al.· 0 citations
A deception detector is only as useful as the trust its alarms deserve. Like a polygraph, detectors that read a language model's internal activations can catch deceptive responses that look honest. Yet current detectors depend on which layers they read, weaken on broader tests, and do not state how certain their alarms...
Misclassification is a critical problem in many machine learning applications. Since even the classifier models with high accuracy (e.g., > 95%) still introduce some misclassification error, it may not be possible to rely on the output of a classifier. In this paper, we introduce trustable learning, which prompts the l...
A training-free PTQ framework for ARVG, consisting of Tail-Aware Bounded-init Grid Refinement (T-BGR) and Coarse-to-Fine Activation Precision Scheduling (CAPS), which achieves near full-precision image generation quality at an effective W4A5.6 activation precision.
Xin-Meng Liu, Xiang-Long Yan, Kai-Cheng Yang et al.· 0 citations
We present Co-DSL, a framework in which users and LLMs co-design reusable spatial concepts for layout generation. In the first stage, our system allows users to create a library of personalized operations. To add a concept, a user provides a description, which the LLM converts into an initial implementation. The user c...
R. Kenny Jones, Jiajun Wu, Maneesh Agrawala· 0 citations
