arXiv AI & Jobs Research (Yushun Zhang, Bingran Li, Congliang Chen, Zhi-Quan) • Published: 2026-03-02
Adam is the default algorithm for training neural networks, including large language models (LLMs). However, \citet{reddi2019convergence} provided an example that Adam diverges, raising concerns for its deployment in AI model training. We identify a key mismatch between the divergence example and practice: \citet{reddi2019convergence} pick the prob
arXiv AI & Jobs Research (Loan Do, Thanh Ngoc Nguyen, Thanh Pham, Vinh Do, H) • Published: 2026-03-02
We introduce VietSuperSpeech, a large-scale Vietnamese automatic speech recognition (ASR) dataset of 52,023 audio-text pairs totaling 267.39 hours, with a distinctive focus on casual conversational speech. Unlike existing Vietnamese ASR corpora that predominantly feature read speech, news narration, or audiobook content, VietSuperSpeech is sourced
arXiv AI & Jobs Research (Chi-Ning Chou, Artem Kirsanov, Yao-Yuan Yang, SueY) • Published: 2026-03-02
Generalization, the ability to perform well beyond the training context, is a hallmark of biological and artificial intelligence, yet anticipating unseen failures remains a central challenge. Conventional approaches often take a ``bottom-up'' mechanistic route by reverse-engineering interpretable features or circuits to build explanatory models. Wh
arXiv AI & Jobs Research (Dragos Costea, Alina Marcu, Cristina Lazar, Marius) • Published: 2026-03-02
We study the ongoing debate regarding the statistical fidelity of AI-generated data compared to human-generated data in the context of non-verbal communication using full body motion. Concretely, we ask if contemporary generative models move beyond surface mimicry to participate in the silent, but expressive dialogue of body language. We tackle thi
arXiv AI & Jobs Research (Wenye Lin, Kai Han) • Published: 2026-03-02
Enhancing the reasoning capabilities of Large Language Models (LLMs) via post-training is often constrained by the trade-off between efficiency and catastrophic forgetting. While prior research emphasizes the role of on-policy data in mitigating forgetting, we uncover--and validate both theoretically and empirically--an overlooked yet critical mech
arXiv AI & Jobs Research (Anka Chandrahas Tummepalli, Preethu Rose Anish) • Published: 2026-03-02
Understanding and predicting judicial outcomes demands nuanced analysis of legal documents. Traditional approaches treat judgments and proceedings as unstructured text, limiting the effectiveness of large language models (LLMs) in tasks such as summarization, argument generation, and judgment prediction. We propose LexChronos, an agentic framework
AI Skill Now