We have 5 of 12 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Mixture-of-Experts (MoE) transformers scale capacity by activating only a few experts per token, but this sparsity creates a hidden reliability problem: when routing is imperfect, load-balanced models may send tokens to experts that are insufficiently trained for the assigned inputs. We propose Distributionally Robust...
NovelAPIBench is presented, an automated diagnostic framework that builds benchmarks around the API knowledge gaps of a target model, identifies novel APIs, generates executable coding tasks with separately controllable knowledge components, and classifies failures into six categories.
CHORD (Coherence-aware Hidden-state Open-generation Reference Distance), a coherence-sensitive distributional metric, is introduced to establish representation design as central to reliable distributional evaluation.
This empirical study investigates whether procedural LLM skills can be represented as directions in activation space and whether vector-space operations over these directions can express skill-level behaviors and finds that procedural skills admit a vector-space representation.
EvoGenUI-Bench is introduced, a benchmark for multi-turn interface maintenance comprising 150 five-turn tasks and 750 turns across three scenarios: information presentation, executable interaction, and tool-grounded external state.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
