27 citations · 56 across the 11 of their papers we have counts for
11 papers
Semantic DLM+: Improving Diffusion Language Models through Bias-variance Trade-off in Transition Kernel Design
Keyue Jiang, Yuxiang Wang, Yanan Zhao +7
Diffusion Language Models (DLMs) have demonstrated strong scaling capacity as alternatives to autoregressive language models. However, their performance is highly sensitive to the…
GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models
Xiaohang Tang, Keyue Jiang, Che Liu +4
Reinforcement learning (RL) can be used to improve the policy (denoiser) of diffusion large language models (dLLMs), while being hindered by the intractability of the policy likeli…
On the Trainability of Masked Diffusion Language Models via Blockwise Locality
Yuxiang Wang, Yu Xiang, Baojian Zhou +4
Masked diffusion language models (MDMs) have recently emerged as a promising alternative to standard autoregressive large language models (AR-LLMs), yet their optimization can be s…
Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement
Mingyu Xu, Cheng Fang, Keyue Jiang +16
We present Logics-STEM, a state-of-the-art reasoning model fine-tuned on Logics-STEM-SFT-Dataset, a high-quality and diverse dataset at 10M scale that represents one of the largest…
GraphGPT: Generative Pre-trained Graph Eulerian Transformer
Qifang Zhao, Weidong Ren, Tianyu Li +3
We introduceGraphGPT, a novel self-supervised generative pre-trained model for graph learning based on the Graph Eulerian Transformer (GET). First, we propose GET, which combines a…
UniMatch: A Unified User-Item Matching Framework for the Multi-purpose Merchant Marketing
Qifang Zhao, Tianyu Li, Meng Du +5
When doing private domain marketing with cloud services, the merchants usually have to purchase different machine learning models for the multiple marketing purposes, leading to a…
Learning to Profile: User Meta-Profile Network for Few-Shot Learning
Hao Gong, Qifang Zhao, Tianyu Li +2
Meta-learning approaches have shown great success in vision and language domains. However, few studies discuss the practice of meta-learning for large-scale industrial applications…
Learning Classifiers on Positive and Unlabeled Data with Policy Gradient
Tianyu Li, Chien-Chih Wang, Yukun Ma +4
Existing algorithms aiming to learn a binary classifier from positive (P) and unlabeled (U) data generally require estimating the class prior or label noises ahead of building a cl…
From Disordered Quantum Walk to Physics of Off-diagonal Disorder
Qifang Zhao, Jiangbin Gong
Systems with purely off-diagonal disorder have peculiar features such as the localization-delocalization transition and long-range correlations in their wavefunctions. To motivate…
Quantum and Classical Superballistic Transport in a Relativistic Kicked-Rotor System
Qifang Zhao, Cord A. Muller, Jiangbin Gong
As an unusual type of anomalous diffusion behavior, superballistic transport is not well known but has been experimentally simulated recently. Quantum superballistic transport mode…
Localization behavior of Dirac particles in disordered graphene superlattices
Qifang Zhao, Jiangbin Gong, Cord A. Mueller
Graphene superlattices (GSLs), formed by subjecting a monolayer graphene sheet to a periodic potential, can be used to engineer band structures and, from there, charge transport pr…