Hongjian Dou

Guannan Lv, Ren Nie, Hongjian Dou

Multimodal Large Language Models (MLLMs) have increasingly localized and interleaved visual evidence for deliberative reasoning. Grounding-based approaches typically focus on regions of interest (RoIs) by injecting cropped image patches or RoI-specific features into the reasoning context. However, such designs can weaken holistic scene understanding and inter-object relations, while incurring decoding costs that scale with the number and size of RoIs. Alternatively, adaptive visual feature selection often requires fine-grained supervision or complex heuristics. To address these limitations, we propose ROVER (Routing Object-centric Visual Evidence for grounded multi-image Reasoning), a lightweight, learnable plugin for efficient global visual evidence routing. Upon each object grounding prediction, ROVER injects a step-specific token triplet to synergistically: (i) aggregate the ongoing reasoning context, (ii) distill intra-image cues into a visual working space via object-centric differential attention, and (iii) route and integrate history-aware evidence across objects and images within this space for subsequent reasoning. We integrate ROVER into Qwen2.5-VL-7B and develop an interleaved SFT-to-GRPO training pipeline. Strictly adhering to the original datasets and evaluation protocols, our method achieves the best performance on MM-GCoT (+4.8% answer accuracy, +14.6% grounding accuracy) and VideoEspresso (+8.6% answer accuracy). The VideoEspresso-trained model demonstrates strong transferability, outperforming the base model by +4.7% on average across diverse benchmarks.

Haowen Gao, Zhenyu Zhang, Liang Pang et al.

Reinforcement learning (RL) with group relative policy optimization (GRPO) has become a widely adopted approach for enhancing the reasoning capabilities of multimodal large language models (MLLMs). While GRPO enables long-chain reasoning without a critic, it often suffers from sparse rewards on difficult problems and advantage vanishing when group-level rewards are too consistent for overly easy or hard problems. Existing solutions (sample expansion, selective utilization, and indirect reward design) often fail to maintain enough variance in within-group reward distributions to yield clear optimization signals. To address this, we propose DIVA-GRPO, a difficulty-adaptive variant advantage method that adjusts variant difficulty distributions from a global perspective. DIVA-GRPO dynamically assesses problem difficulty, samples variants with appropriate difficulty levels, and calculates advantages across local and global groups using difficulty-weighted and normalized scaling. This alleviates reward sparsity and advantage vanishing while improving training stability. Extensive experiments on six reasoning benchmarks demonstrate that DIVA-GRPO outperforms existing approaches in training efficiency and reasoning performance. Code: https://github.com/Siaaaaaa1/DIVA-GRPO

Yaopei Zeng, Lei Liu, Shaoguo Liu et al.

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 focus on overlapping samples among different parties, while their performance is constrained by the limited number of these samples, leaving numerous non-overlapping samples unexplored. Some previous work has explored techniques for imputing missing values in samples, but often without adequate attention to the quality of the imputed samples. To address this issue, we propose a Reliable Imputed-Sample Assisted (RISA) VFL framework to effectively exploit non-overlapping samples by selecting reliable imputed samples for training VFL models. Specifically, after imputing non-overlapping samples, we introduce evidence theory to estimate the uncertainty of imputed samples, and only samples with low uncertainty are selected. In this way, high-quality non-overlapping samples are utilized to improve VFL model. Experiments on two widely used datasets demonstrate the significant performance gains achieved by the RISA, especially with the limited overlapping samples, e.g., a 48% accuracy gain on CIFAR-10 with only 1% overlapping samples.

Penghui Wei, Hongjian Dou, Shaoguo Liu et al.

Conversion rate (CVR) estimation aims to predict the probability of conversion event after a user has clicked an ad. Typically, online publisher has user browsing interests and click feedbacks, while demand-side advertising platform collects users' post-click behaviors such as dwell time and conversion decisions. To estimate CVR accurately and protect data privacy better, vertical federated learning (vFL) is a natural solution to combine two sides' advantages for training models, without exchanging raw data. Both CVR estimation and applied vFL algorithms have attracted increasing research attentions. However, standardized and systematical evaluations are missing: due to the lack of standardized datasets, existing studies adopt public datasets to simulate a vFL setting via hand-crafted feature partition, which brings challenges to fair comparison. We introduce FedAds, the first benchmark for CVR estimation with vFL, to facilitate standardized and systematical evaluations for vFL algorithms. It contains a large-scale real world dataset collected from Alibaba's advertising platform, as well as systematical evaluations for both effectiveness and privacy aspects of various vFL algorithms. Besides, we also explore to incorporate unaligned data in vFL to improve effectiveness, and develop perturbation operations to protect privacy well. We hope that future research work in vFL and CVR estimation benefits from the FedAds benchmark.

Wayne Xin Zhao, Gaole He, Hongjian Dou et al.

To develop a knowledge-aware recommender system, a key data problem is how we can obtain rich and structured knowledge information for recommender system (RS) items. Existing datasets or methods either use side information from original recommender systems (containing very few kinds of useful information) or utilize private knowledge base (KB). In this paper, we present the first public linked KB dataset for recommender systems, named KB4Rec v1.0, which has linked three widely used RS datasets with the popular KB Freebase. Based on our linked dataset, we first preform some interesting qualitative analysis experiments, in which we discuss the effect of two important factors (i.e. popularity and recency) on whether a RS item can be linked to a KB entity. Finally, we present the comparison of several knowledge-aware recommendation algorithms on our linked dataset.