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.

DiffRetriever enhances retrieval efficiency by leveraging DLM's native masked-position prediction.

Shuai Wang, Yu Yin, Shengyao Zhuang et al.

StageCF introduces interest burn-down diffusion and reports competitive results against generative and diffusion baselines on three datasets.

Yifang Qin, Zhaobin Li, Arisa Watanabe et al.

Proposed DATR framework with multi-turn query fusion significantly improves health video retrieval, achieving R@1 of 19.5% on MHVRC.

Chengzheng Wu, Ke Qiu, Baoming Zhang et al.

Proposes a denoising-centric IR framework emphasizing signal-to-noise ratio optimization for LLM fidelity.

Lu Dai, Liang Sun, Fanpu Cao et al.

Compared Google Search, AI Overviews, and Gemini; found AIO generated in 51.5% of real queries, sources differ significantly.

Riley Grossman, Songjiang Liu, Michael K. Chen et al.

TimeMM employs time-conditioned spectral filtering with adaptive modal routing to model non-stationary user preferences in multimodal recommendation, outperforming SOTA.

Wei Yang, Rui Zhong, Zihan Lin et al.

HLTM framework improves LinkedIn Hiring Assistant's answer accuracy by over 5% and retrieval F1 by over 10%.

Zhentao Xu, Shangjin Zhang, Emir Poyraz et al.

Aligning Dense Retrievers with LLM Utility via Distillation, UAE improves Recall@1 by 30.59% on QASPER benchmark.

Rajinder Sandhu, Di Mu, Cheng Chang et al.

Research evaluates QPP for selecting the best query variant in RAG pipelines to enhance generation quality.

Negar Arabzadeh, Andrew Drozdov, Michael Bendersky et al.

Introduced TAWin method using WPAUC to optimize RL-based recommenders, enhancing Top-K performance.

Wentao Shi, Qifan Wang, Chen Chen et al.

Proposes a complementarity fusion method for semantic and collaborative views, avoiding global alignment limitations to enhance recommender systems.

Maolin Wang, Dongze Wu, Jianing Zhou et al.

ResRank enhances retrieval efficiency and effectiveness via residual passage compression and end-to-end joint training.

Xiaojie Ke, Shuai Zhang, Liansheng Sun et al.

ECLASS-augmented dense retrieval method achieves 94.3% HitRate@5 in semantic search for electronic components.

Nico Baumgart, Markus Lange-Hegermann, Jan Henze

Diagnosable ColBERT enhances ColBERT model diagnostics by aligning token embeddings to a clinically-grounded reference latent space.

François Remy

LoopCTR enhances CTR prediction through loop scaling, significantly reducing computational costs.

Jiakai Tang, Runfeng Zhang, Weiqiu Wang et al.

CAST framework models semantic-level transitions, achieving 17.6% Recall and 16.0% NDCG gains with 65x training acceleration.

Qian Zhang, Lech Szymanski, Haibo Zhang et al.

CS3 framework enhances two-tower recommendation systems with Cycle-Adaptive Structure, Cross-Tower Synchronization, and Cascade-Model Sharing, achieving an 8.36% revenue increase.

Lixiang Wang, Shaoyun Shi, Peng Wang et al.

Document-as-image representations underperform in scientific retrieval; interleaved text+image representations are more effective.

Ghazal Khalighinejad, Raghuveer Thirukovalluru, Alexander H. Oh et al.

MARC method improves recommendation efficiency by modular representation compression, achieving a 2.82% eCPM lift in online tests.

Yunjia Xi, Menghui Zhu, Jianghao Lin et al.