LifeSentence leverages pretrained language models with structured event data to predict and analyze human life trajectories, outperforming baselines with 35.3% joint accuracy.

Samuel Liu, Muchen Xi, William Yeoh et al.

ML-Embed integrates 3D-ML framework with MEL, MLL, MRL for efficient, inclusive multilingual embeddings; achieves SOTA on 9/17 MTEB benchmarks.

Ziyin Zhang, Zihan Liao, Hang Yu et al.

Introduces SciPaths, a dataset with 262 expert-annotated pathways, using ML models like GPT-4 to predict scientific dependencies with F1=0.189.

Eric Chamoun, Yizhou Chi, Yulong Chen et al.

CDD method enhances RAG model accuracy under knowledge conflict, especially in entity swap and logical contradiction scenarios.

Yihang Chen, Pin Qian, Su Wang et al.

MARS employs a three-tier memory architecture with adaptive lifecycle management, achieving 26.4% HR@1 improvement in recommendation tasks.

Xiang Shen, Yuhang Zhou, Yifan Wu et al.

LongMemEval-V2 achieves 72.5% accuracy with AgentRunbook-C, evaluating long-term memory in agents.

Di Wu, Zixiang Ji, Asmi Kawatkar et al.

Task-Adaptive Embedding Refinement via Test-time LLM Guidance improves zero-shot search and classification by up to 25%.

Ariel Gera, Shir Ashury-Tahan, Gal Bloch et al.

Using a Computational Social Science framework, audit LLM-generated political discourse across nine crisis events, finding it more negative and structurally consistent.

Gunjan, Sidahmed Benabderrahmane, Talal Rahwan

Q-DAPS estimates question difficulty by computing the entropy of plausibility scores, excelling on four QA datasets.

Jamshid Mozafari, Bhawna Piryani, Adam Jatowt

MedHopQA evaluates biomedical QA via multi-hop reasoning with 1,000 expert-curated question-answer pairs.

Rezarta Islamaj, Robert Leaman, Joey Chan et al.

Dynamic Cognitive Reconciliation Decoding (DCRD) predicts and mitigates context-memory conflicts, achieving state-of-the-art performance across six QA datasets.

Yigeng Zhou, Wu Li, Yifan Lu et al.

SOMA enables efficient multi-turn LLM serving via small models, reducing costs and latency while maintaining high response quality.

Xueqi Cheng, Qiong Wu, Zhengyi Zhou et al.

Proposes DPUA framework combining disagreement perception and uncertainty calibration, improving reliability in subjective analysis.

Junyu Lu, Deyi Ji, Xuanyi Liu et al.

SkillRAE's two-stage skill graph and compact context improve task performance by 11.7%.

Xiangcheng Meng, Shu Wang, Yixiang Fang

Scratchpad Patching method achieves near-baseline quality at 16-byte patches with 16x compute efficiency.

Lin Zheng, Vasilisa Bashlovkina, Timothy Dozat et al.

Budgeted Subset Refinement improves execution-aware LLM research ideation, with MMR-k showing best results.

Micah Zhang

SOD uses step-wise reweighted OPD to lift a 0.6B agent to 26.13% on AIME 2025.

Qiyong Zhong, Mao Zheng, Mingyang Song et al.

Proposes a unified architecture-lifecycle framework to enhance CUA reliability in real environments, analyzing perception, decision, execution layers and stages of creation, deployment, operation, maintenance.

Zejian Chen, Zhanyuan Liu, Chaozhuo Li et al.

Proposes a robust linear semantic segmentation model for low-resource spoken dialects, outperforming baselines with over 1000 multi-genre samples.

Kirill Chirkunov, Younes Samih, Abed Alhakim Freihat et al.

StoryAlign evaluates reward models for story generation using StoryRMB; StoryReward achieves 66.3% accuracy on StoryRMB.

Haotian Xia, Hao Peng, Yunjia Qi et al.