ChartWalker constructs hierarchical knowledge graphs and uses structure-aware sampling to improve cross-chart multi-hop reasoning, boosting multimodal QA.

Ning Tang, Chenghan Xie, Hanyang Yuan et al.

Using BGE-M3 embeddings, analysis of 66 brands across 12 European languages reveals significant language bias in AI-generated brand reputation, with model choice affecting stability more than language.

Dmitrij Żatuchin

Using Gini coefficient, Category Ownership Index, and Displacement Score, the study analyzes recommendation concentration across 50 brands in three LLMs, revealing moderate industry-level diversity.

Dmitrij Żatuchin

SPRINT mitigates popularity bias amplification in scaling Transformer-based recommenders, improving accuracy and fairness.

Weiqin Yang, Yue Pan, Chongming Gao et al.

ELVA employs a ranking-driven reinforcement learning framework with rule-based rewards, achieving 13.1% improvement on MRBench for multi-grain retrieval.

Yuhan Liu, Pei Fu, Hang Li et al.

ScholarQuest introduces a taxonomy-guided benchmark with over 1000 CS topics, four research intents, and automated answer construction, advancing systematic evaluation of academic search agents.

Tingyue Pan, Mingyue Cheng, Daoyu Wang et al.

This study introduces RecLoop, a closed-loop simulation framework, comparing generative and traditional recommenders; findings show generative models better preserve diversity but still face cocoon effects.

Jiyuan Yang, Gengxin Sun, Mengqi Zhang et al.

Developed a theoretical framework for reranking risk based on DCG variation, validated by experiments on TREC data showing close alignment between predicted and observed deviations.

Debasis Ganguly

CQC-RAG introduces cross-query consistency to enhance robustness in retrieval-augmented generation, outperforming baselines by +4.76 EM on TriviaQA and +9.12 EM on MuSiQue.

Yanjia Sun, Sifan Liu, Jie Shao

miniReranker employs visual cache reuse and interaction sparsity to reduce reranking runtime to <1% with >96% performance, based on Qwen3-VL.

Yingqi Fan, Xuan Lu, Anhao Zhao et al.

Introduces SkillResolve-Bench and SkillResolve, achieving Recall@3 0.766, NDCG@3 0.699, and HSR@3=0, effectively reducing same-capability ambiguity risks.

Jiandong Ding

Popcorn benchmark combines title-aligned full-movie/trailer embeddings with VLM-encoded thumbnails to evaluate visual evidence in multimodal movie recommendation.

Ali Tourani, Fatemeh Nazary, Yashar Deldjoo et al.

Proposes a Constrained Dominant Set (CDS) method for multimodal long-document QA, achieving 66.99 on VisDoMBench, surpassing previous SOTA by 37.1 points.

Ambuj Mehrish, Sebatiano Vascon

SSRLive combines static and dynamic semantic IDs, raising online watch time by 3.38% in live-streaming recommendation.

Teng Shi, Zhaoheng Li, Yuanhang Qu et al.

Proposes Shallow-RHS, an asymmetric graph architecture for cold-start content recommendation, mapping intrinsic features into a collaborative filtering space for immediate deployment.

Anh Truong, John Trenkle, Yuanbo Chen et al.

Proposes Dual-Stream MLP with knowledge distillation, achieving state-of-the-art CTR prediction performance with simplified architecture.

Kesha Ou, Zhen Tian, Wayne Xin Zhao et al.

BAHSD improves long-tail user performance in black-box recommendation via adaptive distillation, achieving an 80% Recall@10 boost for tail users.

Xi Zhou, Famin Wu, Mingming Li et al.

Rec-Distill employs decoupled training to distill 24B-parameter teacher models, achieving over 60% transferability in industrial recommendation tasks.

Haoran Ding, Wenlin Zhao, Yuchen Jiang et al.

StructuredSemanticSearch improves model discovery via structured table retrieval, boosting nugget coverage on 597 queries

Zhengyuan Dong, Renée J. Miller

SkillSelect-Serve recommends QoS-aware budgeted skill services for LLM agents, improving hit rate to 0.9091.

Jingyuan Zheng, Dongjing Wang, Xin Zhang et al.