PPL
Wei Chen
Papers (11)
The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-trainingExtra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-TrainingSynGR: Unleashing the Potential of Cross-Modal Synergy for Generative RecommendationMore Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model EditingSample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution ShiftGELATO: Generative Entropy- and Lyapunov-based Adaptive Token Offloading for Device-Edge Speculative LLM InferenceWhen and Why Grouping Attention Heads Accelerates Muon OptimizationWhen Are Experts Misrouted? Counterfactual Routing Analysis in Mixture-of-Experts Language ModelsPaT: Planning-after-Trial for Efficient Test-Time Code GenerationTemporal Smoothness Doubly Robust Learning for Debiased Knowledge TracingStochastic Schrödinger Diffusion Models for Pure-State Ensemble Generation