PPL
Linfeng Zhang
Papers (6)
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative DecodingElastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMsEntropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning ModelsRespecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM ReasoningAttributing Emergence in Million-Agent SystemsAgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems