Paper Archive

Ruohan Liu, Shukang Yin, Tao Wang, Dong Zhang, Weiji Zhuang, Shuhuai Ren, Ran He, Caifeng Shan, Chaoyou Fu 4/22/2026 arxiv

Paralinguistic cues are essential for natural human-computer interaction, yet their evaluation in Large Audio-Language Models (LALMs) remains limited by coarse feature coverage and the inherent subjectivity of assessment. To address these challenges, we introduce SpeechParaling-Bench, a comprehensiv...

Hyeonwoo Kim, Jeonghwan Kim, Kyungwon Cho, Hanbyul Joo 4/22/2026 arxiv

Recent advances in video generative models enable the synthesis of realistic human-object interaction videos across a wide range of scenarios and object categories, including complex dexterous manipulations that are difficult to capture with motion capture systems. While the rich interaction knowled...

Yupeng Zheng, Xiang Li, Songen Gu, Yuhang Zheng, Shuai Tian, Weize Li, Linbo Wang, Senyu Fei, Pengfei Li, Yinfeng Gao, Zebin Xing, Yilun Chen, Qichao Zhang, Haoran Li, Wenchao Ding 4/22/2026 arxiv

Recent advances in Vision-Language-Action (VLA) models have opened new avenues for robot manipulation, yet existing methods exhibit limited efficiency and a lack of high-level knowledge and spatial awareness. To address these challenges, we propose PokeVLA, a lightweight yet powerful foundation mode...

Mikko Lempinen, Joni Kemppainen, Niklas Raesalmi 4/22/2026 arxiv

As artificial intelligence (AI) systems are increasingly deployed across critical domains, their security vulnerabilities pose growing risks of high-profile exploits and consequential system failures. Yet systematic approaches to evaluating AI security remain underdeveloped. In this paper, we introd...

Sina Gholami, Abdulmoneam Ali, Tania Haghighi, Ahmed Arafa, Minhaj Nur Alam 4/22/2026 arxiv

Federated learning (FL) enables collaborative model training without sharing raw data; however, the presence of noisy labels across distributed clients can severely degrade the learning performance. In this paper, we propose FedSIR, a multi-stage framework for robust FL under noisy labels. Different...

Ana Sanchez-Fernandez, Thomas Pinetz, Werner Zellinger, Günter Klambauer 4/22/2026 arxiv

The central problem in biomedical imaging are batch effects: systematic technical variations unrelated to the biological signal of interest. These batch effects critically undermine experimental reproducibility and are the primary cause of failure of deep learning systems on new experimental batches...

Thorsten Hoeser, Felix Bachofer, Claudia Kuenzer 4/22/2026 arxiv

The offshore wind energy sector is expanding rapidly, increasing the need for independent, high-temporal-resolution monitoring of infrastructure deployment and operation at global scale. While Earth Observation based offshore wind infrastructure mapping has matured for spatial localization, existing...

Yiming Bian, Joshua M. Akey 4/22/2026 arxiv

The scalability of long-context large language models is fundamentally limited by the quadratic memory cost of exact self-attention, which often leads to out-of-memory (OOM) failures on modern hardware. Existing methods improve memory efficiency to near-linear complexity, while assuming that the ful...

Deqing Fu, Tianyi Zhou, Mikhail Belkin, Vatsal Sharan, Robin Jia 4/22/2026 arxiv

Language models trained on natural text learn to represent numbers using periodic features with dominant periods at $T=2, 5, 10$. In this paper, we identify a two-tiered hierarchy of these features: while Transformers, Linear RNNs, LSTMs, and classical word embeddings trained in different ways all l...

Shelly Golan, Michael Finkelson, Ariel Bereslavsky, Yotam Nitzan, Or Patashnik 4/22/2026 arxiv

Reinforcement Learning (RL) post-training has become the standard for aligning generative models with human preferences, yet most methods rely on a single scalar reward. When multiple criteria matter, the prevailing practice of ``early scalarization'' collapses rewards into a fixed weighted sum. Thi...