2 papers
cs.HC2026
AffectSim: A Controllable Interactive 3D Simulation Benchmark for Embodied Affective Perception
Ke Xing, Zhilong Wang, Zheng Lian +8
Existing affective benchmarks largely rely on fixed recordings, where observation conditions are predetermined before inference. Consequently, they mainly evaluate passive affect r…
cs.LG2026
Discovering Cross-Language Reasoning Invariance in LLMs with Geometry-Invariant Sparse Autoencoders
Igor Bogdanov, Changcheng Huang
Multilingual language models can solve the same mathematical problem in different languages, but it remains unclear whether they rely on shared features or on language-specific com…