6 papers
InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation
Jinqi Xiao, Qing Yan, Liming Jiang +8
Parameter-Efficient Fine-Tuning of Diffusion Transformers (DiTs) for diverse, multi-conditional tasks often suffers from task interference when using monolithic adapters like LoRA.…
Polysemantic Experts, Monosemantic Paths: Routing as Control in MoEs
Charles Ye, Bo Yuan, Lee Sharkey
An LLM's residual stream is both state and instruction: it encodes the current context and determines the next transformation. We introduce a parameter-free decomposition for Mixtu…
ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models
Cheng Yang, Jianhao Jiao, Lingyi Huang +8
Vision-Language-Action (VLA) models rely on current observations, including images, language instructions, and robot states, to predict actions and complete tasks. While accurate v…
Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs
Jie Cao, Tianwei Lin, Zhenxuan Fan +5
Long chain-of-thought~(CoT) has become a dominant paradigm for enhancing the reasoning capability of large reasoning models~(LRMs); however, the performance gains often come with a…
COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection
Jinqi Xiao, Shen Sang, Tiancheng Zhi +5
Training large-scale neural networks in vision, and multimodal domains demands substantial memory resources, primarily due to the storage of optimizer states. While LoRA, a popular…
HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading
Cheng Luo, Zefan Cai, Hanshi Sun +7
Transformer-based large language models (LLMs) demonstrate impressive performance in long context generation. Extending the context length has disproportionately shifted the memory…