9 papers
SwiftExplorer: Training-free Diffusion Model Alignment with Swift Diversity Exploration
Renye Yan, Jikang Cheng, You Wu +5
Diffusion models have general generative abilities but struggle to align with specific objectives. Fine-tuning can improve alignment, yet its training cost is often prohibitive. Th…
Pixel-Space Diffusion Transformers
Renye Yan, Jikang Cheng, You Wu +8
Latent diffusion models (LDMs) enable efficient high-resolution image synthesis by denoising in a VAE-compressed latent space. However, fixed visual tokenizers can discard fine tex…
PAST: Prompt-Adaptive Sampling Termination for Efficient Diffusion Model
Renye Yan, Jikang Cheng, You Wu +4
While diffusion models have made significant progress in text-to-image tasks, they still exhibit limitations when directly optimizing downstream objectives. Although Reinforcement…
Explore or Converge? Stage-Guided Per-Step Optimization for Diffusion Models
Renye Yan, Jikang Cheng, You Wu +4
Diffusion models have strong generative capabilities. However, their maximum likelihood training objective only focuses on reconstructing the data distribution, making it difficult…
HEMERA: A Heterogeneous Memory-Centric Accelerator with Recursive Dataflow for Edge-Constrained State-Space-Duality Models Inference
Hao Ding, Ling Liang, Ruitong Qiao +9
Structured State Space Models (SSMs), such as Mamba, enable efficient long-sequence modeling with linear time complexity. Recent implementations realize this capability through Str…
NASiC: 3D NAND-based CAM-Selected Multibit CIM Architecture for Efficient On-Device Mixture-of-Experts LLM Inference
Weikai Xu, Meng Li, Shuzhang Zhong +7
The Mixture-of-Experts (MoE) models have emerged as the state-of-the-art paradigm for scaling up large language models (LLMs) without proportionally increased computational cost. H…
Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?
Renye Yan, Jikang Cheng, Shikun Sun +7
Despite strong image-generation performance, diffusion models' reconstruction objectives limit alignment with human preferences. RL enables such alignment through explicit rewards.…
AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement Learning
Renye Yan, Yaozhong Gan, You Wu +4
In sparse reward scenarios of reinforcement learning (RL), the memory mechanism provides promising shortcuts to policy optimization by reflecting on past experiences like humans. H…
Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture
Qichao Ma, Rui-Jie Zhu, Peiye Liu +8
Large Language Models (LLMs) utilize extensive knowledge databases and show powerful text generation ability. However, their reliance on high-quality copyrighted datasets raises co…