6 papers
From Sketch to Fresco: Efficient Diffusion Transformer with Progressive Resolution
Shikang Zheng, Guantao Chen, Lixuan He +4
Diffusion Transformers achieve impressive generative quality but remain computationally expensive due to iterative sampling. Recently, dynamic resolution sampling has emerged as a…
MASC: Boosting Autoregressive Image Generation with a Manifold-Aligned Semantic Clustering
Lixuan He, Shikang Zheng, Linfeng Zhang
Autoregressive (AR) models have shown great promise in image generation, yet they face a fundamental inefficiency stemming from their core component: a vast, unstructured vocabular…
Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers
Shikang Zheng, Guantao Chen, Qinming Zhou +6
Diffusion Transformers offer state-of-the-art fidelity in image and video synthesis, but their iterative sampling process remains a major bottleneck due to the high cost of transfo…
Towards a Unified View of Large Language Model Post-Training
Xingtai Lv, Yuxin Zuo, Youbang Sun +8
Two major sources of training data exist for post-training modern language models: online (model-generated rollouts) data, and offline (human or other-model demonstrations) data. T…
AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance
Lixuan He, Jie Feng, Yong Li
Large Language Models (LLMs) are typically fine-tuned for reasoning tasks through a two-stage pipeline of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL), a pr…
Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System
Lixuan He, Haoyu Dong, Zhenxing Chen +3
Vision-and-Language Navigation (VLN) in large-scale urban environments requires embodied agents to ground linguistic instructions in complex scenes and recall relevant experiences…