LitCurate uses large language models within a configurable, stage-wise workflow to build a structured EOS database with 1334 entries from 205 papers.

Abin Shakya, Wilson Samuels, Dominica Wilson et al.

TAGR introduces a temporally adaptive generative recommender with LSID, IAG, and IOPO, boosting live-stream ad engagement by 8.5%.

Wencai Ye, Guangyi Liu, Chaoyi Wang et al.

Wontopos Tablet 2 achieves multilingual and multimodal retrieval without lexical matching, scoring 95.7% on LongMemEval-S.

Sunwoo Kim

Proposes Graph Engineering to organize tasks, coordinate heterogeneous agents, and manage states for system-level intelligence.

Yuyuan Feng, Zhishang Xiang, Chaobin Yang et al.

KoViDoRe employs multi-stage synthetic data generation to benchmark Korean multi-page document retrieval, revealing current models' struggles with complex, structured content.

Yongbin Choi, Yongwoo Song, Mujeen Sung

Proposes CAIRO, a framework that structures large-scale metadata for personalized item profiling, boosting LLM reranking performance.

Dojun Hwang, Seunghan Lee, Cheonyoung Park et al.

Daedalus-150M employs a convolution-attention hybrid with 6 full attention and 12 convolution layers, trained on 59.9B tokens, outperforming similar models in quality and inference speed.

Christos Koutsiaris

SCoRD employs semantic reasoning-assisted continual distillation to enhance LLM-based retrieval and reranking in dynamic recommendation environments.

Seunghyun Baek, Gyuseok Lee, Seunghan Lee et al.

Proposes CoRRe, a training-free recommendation framework that refines item embeddings post-LLM inference using collaborative signals, achieving state-of-the-art results.

Kyungho Kim, Sunwoo Kim, Geon Lee et al.

OneModel unifies multi-scenario ranking using long-context user modeling, achieving +0.33% Time Spent and +8.18% CTR online.

Yinqi Zhang, Peiyu Hu, Yuntian Tang et al.

Introduced impression share prediction as an offline evaluation task using causal modeling, reducing prediction error by 49% on seen models and improving early-hour accuracy by 22%.

Mohsen Malmir, Houssam Nassif, Danish Nasir Shaikh et al.

Proposes a control function-based unbiased ranking framework, correcting position bias and improving ranking accuracy.

Md Aminul Islam

EXCISE employs query-side modules to solve exclusion inversion in late-interaction retrieval, boosting exclusion success@10 to 0.691 and Boolean NOT accuracy to 0.92.

Mohammed Ali, Abdelrahman Abdallah, Adam Jatowt

Ontology-based student profiling and content personalization framework utilizing knowledge graphs enhances adaptive learning with 25% higher content matching accuracy.

José Luiz M. Morais, Arlindo F. da Conceição, Cacilda Encarnação Augusto Alvarenga et al.

MemoryCPT employs an end-to-end trainable memory framework combining QAD and QAR, achieving a QPC of 0.138 with significant cost reduction and answer quality improvement.

Songxin Lei, Kun Ouyang, Weilin Ruan et al.

Sun develops the ISMIE framework, combining crowdsourcing surveys, neurophysiological signals, and preference modeling to analyze GenAI's impact on modern information seeking, revealing preference shifts and cognitive load dynamics.

Shuoqi Sun

Proposes a multi-objective ranking framework combining immediate and delayed signals with Segment-Aware targeting, boosting Twitch DAU by 0.09% and ARPU by 0.56%, with 41.9% fewer parameters.

Xiaoyi Gu, Julia Tavares, Eder Santana et al.

CILER models latent environments using user-conditioned exponential families to enhance OOD recommendation performance.

Qianqian Wang, Wenwu Gong, Yunshan Li et al.

Proposes MODE algorithm to optimize mutual direct effects in reciprocal matching, boosting match counts by 20%.

Yoji Tomita

Introduces Tevatron 3.0 with Megatron backend, enabling efficient training of billion-parameter MoE rerankers, surpassing FSDP in speed and scale.

Zhichao Xu, Xueguang Ma, Shengyao Zhuang et al.