17 papers
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
Changhai Zhou, Kieran Liu, Yuhua Zhou +17
Long-context RL post-training is constrained by the lifetime of state and gradients, not attention cost alone. In GRPO, one multi-million-token prompt must serve old-policy and ref…
Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization
Weilin Wan, Jingtao Han, Weizhong Zhang +2
Scaling laws govern macroscopic resource allocation for LLMs, yet precise architectural configurations for Mixture-of-Experts (MoE) models remain guided by heuristics. Existing MoE…
AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning
Changhai Zhou, Shiyang Zhang, Yuhua Zhou +5
Quantization followed by parameter-efficient fine-tuning has emerged as a promising paradigm for downstream adaptation under tight GPU memory constraints. However, this sequential…
Advanced Black-Box Tuning of Large Language Models with Limited API Calls
Zhikang Xie, Weilin Wan, Peizhu Gong +2
Black-box tuning is an emerging paradigm for adapting large language models (LLMs) to better achieve desired behaviors, particularly when direct access to model parameters is unava…
Explore and Establish Synergistic Effects Between Weight Pruning and Coreset Selection in Neural Network Training
Weilin Wan, Fan Yi, Weizhong Zhang +2
Modern deep neural networks rely heavily on massive model weights and training samples, incurring substantial computational costs. Weight pruning and coreset selection are two emer…
Computational Budget Should Be Considered in Data Selection
Weilin Wan, Weizhong Zhang, Cheng Jin
Data selection improves computational efficiency by choosing informative subsets of training samples. However, existing methods ignore the compute budget, treating data selection a…
Balancing Fidelity and Plasticity: Aligning Mixed-Precision Fine-Tuning with Linguistic Hierarchies
Changhai Zhou, Shiyang Zhang, Yuhua Zhou +5
Deploying and fine-tuning Large Language Models (LLMs) on resource-constrained edge devices requires navigating a strict trade-off between memory footprint and task performance. Wh…
Large Language Model Compression with Global Rank and Sparsity Optimization
Changhai Zhou, Qian Qiao, Yuhua Zhou +4
Low-rank and sparse composite approximation is a natural idea to compress Large Language Models (LLMs). However, such an idea faces two primary challenges that adversely affect the…
MagicFace: Training-free Universal-Style Human Image Customized Synthesis
Yibin Wang, Weizhong Zhang, Cheng Jin
Current human image customization methods leverage Stable Diffusion (SD) for its rich semantic prior. However, since SD is not specifically designed for human-oriented generation,…
ELiTe: Efficient Image-to-LiDAR Knowledge Transfer for Semantic Segmentation
Zhibo Zhang, Ximing Yang, Weizhong Zhang +1
Cross-modal knowledge transfer enhances point cloud representation learning in LiDAR semantic segmentation. Despite its potential, the \textit{weak teacher challenge} arises due to…
DreamText: High Fidelity Scene Text Synthesis
Yibin Wang, Weizhong Zhang, Honghui Xu +1
Scene text synthesis involves rendering specified texts onto arbitrary images. Current methods typically formulate this task in an end-to-end manner but lack effective character-le…
Robust Fine-tuning for Pre-trained 3D Point Cloud Models
Zhibo Zhang, Ximing Yang, Weizhong Zhang +1
This paper presents a robust fine-tuning method designed for pre-trained 3D point cloud models, to enhance feature robustness in downstream fine-tuned models. We highlight the limi…
PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering
Yibin Wang, Weizhong Zhang, Jianwei Zheng +1
Image composition involves seamlessly integrating given objects into a specific visual context. Current training-free methods rely on composing attention weights from several sampl…
Out-of-Distribution Detection using Neural Activation Prior
Weilin Wan, Weizhong Zhang, Quan Zhou +2
Out-of-distribution detection (OOD) is a crucial technique for deploying machine learning models in the real world to handle the unseen scenarios. In this paper, we first propose a…
Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection
Kaiyi Zhang, Yang Chen, Ximing Yang +2
Ideal part editing should guarantee the diversity of edited parts, the fidelity to the remaining parts, and the quality of the results. However, previous methods do not disentangle…
Enhancing Object Coherence in Layout-to-Image Synthesis
Yibin Wang, Changhai Zhou, Honghui Xu
Layout-to-image synthesis is an emerging technique in conditional image generation. It aims to generate complex scenes, where users require fine control over the layout of the obje…
High-fidelity Person-centric Subject-to-Image Synthesis
Yibin Wang, Weizhong Zhang, Jianwei Zheng +1
Current subject-driven image generation methods encounter significant challenges in person-centric image generation. The reason is that they learn the semantic scene and person gen…