Current AI alignment through RLHF follows a single directional paradigm that AI conforms to human preferences while treating human cognition as fixed. We propose a shift to co-alignment through Bidirectional Cognitive Alignment (BiCA), where humans and AI mutually adapt. BiCA uses learnable protocols, representation mapping, and KL-budget constraints for controlled co-evolution. In collaborative navigation, BiCA achieved 85.5% success versus 70.3% baseline, with 230% better mutual adaptation and 332% better protocol convergence. Emergent protocols outperformed handcrafted ones by 84%, while bidirectional adaptation unexpectedly improved safety (+23% out-of-distribution robustness). The 46% synergy improvement demonstrates optimal collaboration exists at the intersection, not union, of human and AI capabilities, validating the shift from single-directional to co-alignment paradigms.

Nowadays, transformer-based models gradually become the default choice for artificial intelligence pioneers. The models also show superiority even in the few-shot scenarios. In this paper, we revisit the classical methods and propose a new few-shot alternative. Specifically, we investigate the few-shot one-class problem, which actually takes a known sample as a reference to detect whether an unknown instance belongs to the same class. This problem can be studied from the perspective of sequence match. It is shown that with meta-learning, the classical sequence match method, i.e. Compare-Aggregate, significantly outperforms transformer ones. The classical approach requires much less training cost. Furthermore, we perform an empirical comparison between two kinds of sequence match approaches under simple fine-tuning and meta-learning. Meta-learning causes the transformer models' features to have high-correlation dimensions. The reason is closely related to the number of layers and heads of transformer models. Experimental codes and data are available at https://github.com/hmt2014/FewOne

Neuroethology has been an active field of study for more than a century now. Out of some of the most interesting species that has been studied so far, weakly electric fish is a fascinating one. It performs communication, echo-location and inter-species detection efficiently with an interesting configuration of sensors, neu-rons and a simple brain. In this paper we propose a cognitive architecture inspired by the way these fishes handle and process information. We believe that it is eas-ier to understand and mimic the neural architectures of a simpler species than that of human. Hence, the proposed architecture is expected to both help research in cognitive robotics and also help understand more complicated brains like that of human beings.

The 2016 Annual International Conference on Biologically Inspired Cognitive Architectures (BICA) is part of a joint effort between other major conferences and academic events targeting work towards the computational recreation of human-level intelligence.– "It is actually the first time we had approximately 250 participants all together, certainly this shows a steady progress over many years," Samsonovich said on Monday. John Laird, a professor of engineering at the University of Michigan, told Sputnik the conference is unique in that it involves collaboration between numerous experts and universities. "I think that's one of the unique things that's happened this year is these three or four conferences coming together and making it possible for people that are interested in different sort of sides of it to come together," Laird said. "I think that's been a unique experience and from what I've heard people talking about it, it's been very successful."