9 papers
MI-Distillation: Selecting from Model-Interpolated Instruct-Reasoning Data Spectrum for Chain-of-Thought Distillation
Yangsong Lan, Renkai Hu, HongKai Zheng +4
Recent advances in large reasoning models (LRMs) have shown strong performance on complex problems through long chain-of-thought (Long CoT) reasoning. However, distilling such traj…
DeLS-Spec: Decoupled Long-Short Contexts for Parallel Speculative Drafting
Hong-Kai Zheng, Piji Li
Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in parallel. Block-parallel drafters such as DFlash further improve drafting efficienc…
Temporal Guidance for Large Language Models
Hong-Kai Zheng, Piji Li
Contrastive Decoding (CD) enhances the generation quality of large language models (LLMs) but incurs significant additional computational overhead due to the need for an auxiliary…
S^2F-Net:A Robust Spatial-Spectral Fusion Framework for Cross-Model AIGC Detection
Xiangyu Hu, Yicheng Hong, Hongchuang Zheng +2
The rapid development of generative models has imposed an urgent demand for detection schemes with strong generalization capabilities. However, existing detection methods generally…
Q-Regularized Generative Auto-Bidding: From Suboptimal Trajectories to Optimal Policies
Mingming Zhang, Na Li, Zhuang Feiqing +8
With the rapid development of e-commerce, auto-bidding has become a key asset in optimizing advertising performance under diverse advertiser environments. The current approaches fo…
LSRS: Latent Scale Rejection Sampling for Visual Autoregressive Modeling
Hong-Kai Zheng, Piji Li
Visual Autoregressive (VAR) modeling approach for image generation proposes autoregressive processing across hierarchical scales, decoding multiple tokens per scale in parallel. Th…
IGen: Scalable Data Generation for Robot Learning from Open-World Images
Chenghao Gu, Haolan Kang, Junchao Lin +10
The rise of generalist robotic policies has created an exponential demand for large-scale training data. However, on-robot data collection is labor-intensive and often limited to s…
Group-Wise Optimization for Self-Extensible Codebooks in Vector Quantized Models
Hong-Kai Zheng, Piji Li
Vector Quantized Variational Autoencoders (VQ-VAEs) leverage self-supervised learning through reconstruction tasks to represent continuous vectors using the closest vectors in a co…
There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training
Jiachen Lei, Keli Liu, Julius Berner +4
Pixel-space generative models are often more difficult to train and generally underperform compared to their latent-space counterparts, leaving a persistent performance and efficie…