AVMeme Exam, a human-curated benchmark of over one thousand iconic Internet sounds and videos spanning speech, songs, music, and sound effects, is introduced, showing current models perform poorly on textless music and sound effects, and struggle to think in context and in culture compared to surface content.
NeuroLens (Latent Embeddings of Neural Semantics), a self-supervised model based on the Joint-Embedding Predictive Architecture (JEPA) framework that learns denoised, semantically informative latents from chronic neural recordings, is introduced as a new paradigm for studying how neural representations change during le...
Hanrui Lyu, Bai-Yuan Chen, Tian Tan et al.· 0 citations
Understanding how Large Language Models (LLMs) encode linguistic structures remains a fundamental challenge in interpretability research. While diagnostic classifiers (or"probes") are widely used for this task, they face significant methodological criticism: training auxiliary classifiers introduces capacity confounds...
LiveMathematicianBench is presented, a dynamic multiple-choice benchmark for research-level mathematical reasoning built from recent arXiv papers published after model training cutoffs, and introduces a thirteen-category logical taxonomy of theorem types, enabling fine-grained evaluation across reasoning forms.
The Very Big Video Reasoning (VBVR) Dataset is introduced, an unprecedentedly large-scale resource spanning 200 curated reasoning tasks following a principled taxonomy and over one million video clips, approximately three orders of magnitude larger than existing datasets.
Maijunxian Wang, Rui-Si Wang, Ju-Yi Lin et al.· arXiv.org· 28 citations· ⚡5
The first ChineseBabyLM Challenge, organized as part of NLPCC 2026, asked participants to train language models from scratch using no more than 102M Chinese words and provides a benchmark for advancing data-efficient and cognitively plausible approaches to Chinese language modeling.