1 citations · 1 across the 6 of their papers we have counts for
7 papers
Divergence-Routed On-Policy Distillation for Language Models
Tiantian Peng, Guannan Lv, Hongyang Li +5
On-policy distillation (OPD) transfers knowledge from a teacher model to a student along student-generated trajectories, typically by minimizing the reverse Kullback-Leibler (RKL)…
ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning
Guannan Lv, Ren Nie, Hongjian Dou +1
Multimodal Large Language Models (MLLMs) have increasingly localized and interleaved visual evidence for deliberative reasoning. Grounding-based approaches typically focus on regio…
DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantage
Haowen Gao, Zhenyu Zhang, Liang Pang +7
Reinforcement learning (RL) with group relative policy optimization (GRPO) has become a widely adopted approach for enhancing the reasoning capabilities of multimodal large languag…
QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling
Tian Xia, Jiaqi Zhang, Yueyang Liu +25
With the evolution of large language models (LLMs), there is growing interest in leveraging their rich semantic understanding to enhance industrial recommendation systems (RecSys).…
OneMall: One Architecture, More Scenarios -- End-to-End Generative Recommender Family at Kuaishou E-Commerce
Kun Zhang, Jingming Zhang, Wei Cheng +29
In the wave of generative recommendation, we present OneMall, an end-to-end generative recommendation framework tailored for e-commerce services at Kuaishou. Our OneMall systematic…
Enhancing Supervised Composed Image Retrieval via Reasoning-Augmented Representation Engineering
Jun Li, Hongjian Dou, Zhenyu Zhang +3
Composed Image Retrieval (CIR) presents a significant challenge as it requires jointly understanding a reference image and a modified textual instruction to find relevant target im…
Reliable Imputed-Sample Assisted Vertical Federated Learning
Yaopei Zeng, Lei Liu, Shaoguo Liu +3
Vertical Federated Learning (VFL) is a well-known FL variant that enables multiple parties to collaboratively train a model without sharing their raw data. Existing VFL approaches…