4 citations · 19 across the 18 of their papers we have counts for
19 papers
Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems
Zixu Wang, Bingbing Xu, Yige Yuan +2
Multi-Agent Systems (MAS) built on large language models typically solve complex tasks by coordinating multiple agents through workflows. Existing approaches generates workflows ei…
RPO: Decoupling Rollout and Inference Policies for LLM Reasoning
Jingchu Wang, Bingbing Xu, Yige Yuan +4
Existing reinforcement learning methods for LLM reasoning implicitly assume that the policy generating training trajectories should coincide with the one producing inference respon…
GIFT: Games as Informal Training for Generalizable LLMs
Nuoyan Lyu, Bingbing Xu, Xueyun Tian +6
Recent LLMs excel at formal tasks such as mathematical reasoning and code generation, but still struggle with broader abilities such as planning, creativity, and social intelligenc…
Multi-Personality Generation of LLMs at Decoding-time
Rongxin Chen, Yunfan Li, Yige Yuan +2
Multi-personality generation for LLMs, enabling simultaneous embodiment of multiple personalization attributes, is a fundamental challenge. Existing retraining-based approaches are…
From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time Alignment
Bin Xie, Bingbing Xu, Yige Yuan +2
Inference-time alignment methods have gained significant attention for their efficiency and effectiveness in aligning large language models (LLMs) with human preferences. However,…
InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning
Zixu Wang, Bingbing Xu, Yige Yuan +2
As an important graph pre-training method, Graph Contrastive Learning (GCL) continues to play a crucial role in the ongoing surge of research on graph foundation models or LLM as e…
Inference-time Alignment in Continuous Space
Yige Yuan, Teng Xiao, Li Yunfan +5
Aligning large language models with human feedback at inference time has received increasing attention due to its flexibility. Existing methods rely on generating multiple response…
Incentivizing Strong Reasoning from Weak Supervision
Yige Yuan, Teng Xiao, Shuchang Tao +4
Large language models (LLMs) have demonstrated impressive performance on reasoning-intensive tasks, but enhancing their reasoning abilities typically relies on either reinforcement…
MIGE: Mutually Enhanced Multimodal Instruction-Based Image Generation and Editing
Xueyun Tian, Wei Li, Bingbing Xu +3
Despite significant progress in diffusion-based image generation, subject-driven generation and instruction-based editing remain challenging. Existing methods typically treat them…
Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment
Teng Xiao, Yige Yuan, Huaisheng Zhu +2
We study the problem of aligning large language models (LLMs) with human preference data. Contrastive preference optimization has shown promising results in aligning LLMs with avai…
Fact-Level Confidence Calibration and Self-Correction
Yige Yuan, Bingbing Xu, Hexiang Tan +5
Confidence calibration in LLMs, i.e., aligning their self-assessed confidence with the actual accuracy of their responses, enabling them to self-evaluate the correctness of their o…
How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective
Teng Xiao, Mingxiao Li, Yige Yuan +3
This paper introduces a novel generalized self-imitation learning () framework, which effectively and efficiently aligns large language models with offline demonstra…
MITA: Bridging the Gap between Model and Data for Test-time Adaptation
Yige Yuan, Bingbing Xu, Teng Xiao +4
Test-Time Adaptation (TTA) has emerged as a promising paradigm for enhancing the generalizability of models. However, existing mainstream TTA methods, predominantly operating at ba…
Negative as Positive: Enhancing Out-of-distribution Generalization for Graph Contrastive Learning
Zixu Wang, Bingbing Xu, Yige Yuan +2
Graph contrastive learning (GCL), standing as the dominant paradigm in the realm of graph pre-training, has yielded considerable progress. Nonetheless, its capacity for out-of-dist…
TEA: Test-time Energy Adaptation
Yige Yuan, Bingbing Xu, Liang Hou +3
Test-time adaptation (TTA) aims to improve model generalizability when test data diverges from training distribution, offering the distinct advantage of not requiring access to tra…
PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion
Yige Yuan, Bingbing Xu, Bo Lin +4
The generalization of neural networks is a central challenge in machine learning, especially concerning the performance under distributions that differ from training ones. Current…
Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective
Yige Yuan, Bingbing Xu, Huawei Shen +4
Graph contrastive learning (GCL) emerges as the most representative approach for graph representation learning, which leverages the principle of maximizing mutual information (Info…
Hierarchical Estimation for Effective and Efficient Sampling Graph Neural Network
Yang Li, Bingbing Xu, Qi Cao +2
Improving the scalability of GNNs is critical for large graphs. Existing methods leverage three sampling paradigms including node-wise, layer-wise and subgraph sampling, then desig…
Augmentation-Aware Self-Supervision for Data-Efficient GAN Training
Liang Hou, Qi Cao, Yige Yuan +7
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation…