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 consist of fixed recordings whose observation conditions are determined before inference, making it difficult to systematically study how embo…
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…