6 papers
FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration
Yaojie Zhang, Jianuo Huang, Junlong Ke +5
Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and the target model to verify…
Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning
Junlong Ke, Zichen Wen, Weijia Li +2
On-policy self-distillation trains a reasoning model on its own rollouts while a teacher, often the same model conditioned on privileged context, provides dense token-level supervi…
EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant
Zichen Wen, Boxue Yang, Junlong Ke +5
Streaming video understanding demands more than watching longer videos: assistants must decide when to speak in real time, balancing responsiveness against verbosity. Yet most vide…
Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models
Junlong Ke, Zichen Wen, Boxue Yang +6
Native unified multimodal models, which integrate both generative and understanding capabilities, face substantial computational overhead that hinders their real-world deployment.…
Innovator-VL: A Multimodal Large Language Model for Scientific Discovery
Zichen Wen, Boxue Yang, Shuang Chen +30
We present Innovator-VL, a scientific multimodal large language model designed to advance understanding and reasoning across diverse scientific domains while maintaining excellent…
SignalLLM: A General-Purpose LLM Agent Framework for Automated Signal Processing
Junlong Ke, Qiying Hu, Shenghai Yuan +2
Modern signal processing (SP) pipelines, whether model-based or data-driven, often constrained by complex and fragmented workflow, rely heavily on expert knowledge and manual engin…