research note
This paper investigates the transparency of DiffusionGemma, a large text diffusion model developed by Google DeepMind, in comparison to standard autoregressive language models like Gemma 4
research note
This paper addresses a foundational question at the interface of information-theoretic and spacetime (relativistic) notions of causality — can operationally detectable causal loops exist without vio…
research note
This paper addresses the critical challenge of accurately detecting infant faces in neonatal clinical environments, which is foundational for non-contact assessments such as pain expression analysi…
research note
This work tackles the challenge of multi-objective molecular discovery under computational restrictions and data scarcity by introducing an interpretable and data-efficient meta-learning framework …
research note
This paper addresses the gap in AI-driven game development regarding project-level code engineering on professional game engines by introducing JamSet and JamBench, the first large-scale dataset an…
research note
This paper addresses the challenging problem of 3D visual illusions, where a single 3D mesh reveals entirely different semantics from specific viewing angles
research note
This experience report explores the use of puzzle-based learning activities to develop Critical Testing Literacy (CTL) in software testing education
research note
This paper addresses the safety and robustness of large language model (LLM) agents deployed as operators in multi-agent teams for safety-critical systems, focused on nuclear power plant control ro…
research note
MemoryWAM addresses a core challenge in world action models (WAMs) for robotic manipulation — balancing robust long-term memory of past observations with computational efficiency during inference
research note
This work studies the realization and characterization of time-reversal-broken Weyl semimetals in Floquet synthetic dimensions generated by two incommensurate periodic drives applied to a one-dimen…
research note
This paper addresses the challenges of semantic understanding, adaptability, and scalability faced by traditional ML, deep learning, and reinforcement learning methods in dynamic and heterogeneous …
research note
Multi-LCB addresses a critical limitation of the LiveCodeBench (LCB) benchmark, which evaluates large language models (LLMs) on code generation tasks exclusively in Python
