Appears on
Articles6
Beyond Accuracy: Why Diversity and Robustness Matter for Routing in Multi-Model Language Systems
Routing policies for multi-model systems are evaluated almost exclusively on task accuracy and inference cost. We argue that two properties, orthogonal to performance, determine whether routing is meaningful. First, the society of actors must be behaviour
Shared by @dair_ai βBeyond Accuracy: Why Diversity and Robustness Matter for Routing in Multi-Model Language Systems
Routing policies for multi-model systems are evaluated almost exclusively on task accuracy and inference cost. We argue that two properties, orthogonal to performance, determine whether routing is meaningful. First, the society of actors must be behaviour
Shared by @dair_ai βWan-Dancer: A hierarchical AI framework enabling minute-scale coherent music-to-dance video generation
Generating long-duration, high-definition, and rhythmically synchronized dance videos directly from music remains a significant challenge, primarily due to the temporal constraints of current diffusion models, which typically fail beyond 20 seconds. Exist
Study reveals kinetic barriers to stripe phase formation in Ising antiferromagnet cooling dynamics
The finite-rate cooling dynamics of the triangular-lattice $J_1-J_2$ Ising antiferromagnet is studied under local Metropolis updates. Although an antiferromagnetic next-nearest-neighbor coupling selects a stripe phase in equilibrium, the simulations show
LLMs for Quantum Program Repair: Benchmark Validation Challenges in Bugs4Q Across Qiskit Versions
In quantum programs, Bugs4Q is a widely used benchmark containing real quantum defects. However, its evaluation assumes that benchmark labels remain valid and that generated fixes execute in the target environment. We evaluate two Bugs4Q versions containi



