4 papers
Early Learning Shapes Later Directions Of Representation Change In Continual Learning
Yuantao Deng, Jinnuo Liu, Kaizhen Tan +1
Representations continually change as a network learns new tasks. We ask whether early representational changes naturally form a geometric structure that continues to shape later l…
NovelAPIBench: Diagnosing How A Code LLM Learns to Use Novel APIs
Jinnuo Liu, Yue Peng, Jinhan Niu +1
Rapidly evolving software libraries require coding language models to use unfamiliar APIs. Yet failed solutions alone tell us little about what API knowledge models need or how to…
ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems
Jinnuo Liu, Chuke Liu, Hua Shen
Multi-agent large language model (LLM) systems increasingly consist of agents that observe and respond to one another's outputs. While value alignment is typically evaluated for is…
From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity
Haoming Liu, Jinnuo Liu, Yanhao Li +5
Flow-based diffusion models have emerged as a leading paradigm for training generative models across images and videos. However, their memorization-generalization behavior remains…