7 papers
Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation
Luxi Lin, Zhihang Lin, Zhanpeng Zeng +5
Speculative decoding accelerates LLM inference but suffers from performance degradation when target models are fine-tuned for specific domains. A naive solution is to retrain draft…
Parallel Vision Token Scheduling for Fast and Accurate Multimodal LMMs Inference
Wengyi Zhan, Mingbao Lin, Zhihang Lin +1
Multimodal large language models (MLLMs) deliver impressive vision-language reasoning but suffer steep inference latency because self-attention scales quadratically with sequence l…
CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
Zhihang Lin, Mingbao Lin, Yuan Xie +1
This paper introduces Completion Pruning Policy Optimization (CPPO) to accelerate the training of reasoning models based on Group Relative Policy Optimization (GRPO). GRPO, while e…
AccDiffusion v2: Towards More Accurate Higher-Resolution Diffusion Extrapolation
Zhihang Lin, Mingbao Lin, Wengyi Zhan +1
Diffusion models suffer severe object repetition and local distortion when the inference resolution differs from its pre-trained resolution. We propose AccDiffusion v2, an accurate…
Speculative Decoding Reimagined for Multimodal Large Language Models
Luxi Lin, Zhihang Lin, Zhanpeng Zeng +1
This paper introduces Multimodal Speculative Decoding (MSD) to accelerate Multimodal Large Language Models (MLLMs) inference. Speculative decoding has been shown to accelerate Larg…
LightMotion: A Light and Tuning-free Method for Simulating Camera Motion in Video Generation
Quanjian Song, Zhihang Lin, Zhanpeng Zeng +3
Existing camera motion-controlled video generation methods face computational bottlenecks in fine-tuning and inference. This paper proposes LightMotion, a light and tuning-free met…