Cognitive impairment is becoming a major public health challenge. Cognitive Stimulation Therapy (CST) is an effective intervention for cognitive impairment, but traditional methods are difficult to scale, and existing digital systems struggle with group dialogues and cognitive stimulation principles. While Large Language Models (LLMs) are powerful, their application in this context faces key challenges: cognitive stimulation dialogue paradigms, a lack of therapeutic reasoning, and static-only user modeling. To address these issues, we propose a principle-driven adaptive policy actualized through a Group Cognitive Stimulation Dialogue (GCSD) system. We first construct a dataset with over 500 hours of real-world CST conversations and 10,000+ simulated dialogues generated via our Principle-Guided Scenario Simulation strategy. Our GCSD system then integrates four core modules to overcome LLM limitations: (i) a multi-speaker context controller to resolve role confusion; (ii) dynamic participant cognitive state modeling for personalized interaction; (iii) a cognitive stimulation-focused attention loss to instill cognitive stimulation reasoning; and (iv) a multi-dimensional reward strategy to enhance response value. Experimental results demonstrate that GCSD significantly outperforms baseline models across various evaluation metrics. Future work will focus on long-term clinical validation to bridge the gap between computational performance and clinical efficacy.

Biological sequences, including RNAs and proteins, share similarities with natural languages, enabling the application of advanced language models to various biological tasks. However, due to its flexibility and lack of experimental data, RNA is a particularly challenging biological ``language'' compared to other biological sequences like proteins. RNA multiple sequence alignments (MSAs), which align evolutionarily related RNA sequences, can greatly enhance RNA biology modeling, as evidenced by their significant roles in structure prediction and function annotation. This raises the question of whether RNA MSAs can also benefit RNA design, which remains unexplored. This paper introduces RMSAGen, a model comprising RMSA-Encoder and RMSA-Decoder, that leverages MSAs to design functional RNA sequences. RMSA-Encoder effectively extracts MSA features, enhancing performance in functional prediction and solvent accessibility prediction tasks and supporting RMSA-Decoder in accurate RNA generation. RMSAGen can design RNA sequences that effectively bind to target RNA-binding proteins, and the design performance improves with an increasing number of sequences. In addition, the ribozymes designed with structural features by RMSAGen show strong computational metrics and exhibit biological activity during gel electrophoresis. These results highlight the effectiveness of RMSAGen, establishing it as a powerful tool and a new direction for RNA design.

Inverse Protein Folding (IPF) is a critical subtask in the field of protein design, aiming to engineer amino acid sequences capable of folding correctly into a specified three-dimensional (3D) conformation. Although substantial progress has been achieved in recent years, existing methods generally rely on either backbone coordinates or molecular surface features alone, which restricts their ability to fully capture the complex chemical and geometric constraints necessary for precise sequence prediction. To address this limitation, we present DS-ProGen, a dual-structure deep language model for functional protein design, which integrates both backbone geometry and surface-level representations. By incorporating backbone coordinates as well as surface chemical and geometric descriptors into a next-amino-acid prediction paradigm, DS-ProGen is able to generate functionally relevant and structurally stable sequences while satisfying both global and local conformational constraints. On the PRIDE dataset, DS-ProGen attains the current state-of-the-art recovery rate of 61.47%, demonstrating the synergistic advantage of multi-modal structural encoding in protein design. Furthermore, DS-ProGen excels in predicting interactions with a variety of biological partners, including ligands, ions, and RNA, confirming its robust functional retention capabilities.

Biological foundation models (BioFMs), pretrained on large-scale biological sequences, have recently shown strong potential in providing meaningful representations for diverse downstream bioinformatics tasks. However, such models often rely on millions to billions of training sequences and billions of parameters, resulting in prohibitive computational costs and significant barriers to reproducibility and accessibility—particularly for academic labs. To address these challenges, we investigate the feasibility of data pruning for BioFM pretraining and propose a post-hoc influence-guided data pruning framework tailored to biological domains. Our approach first introduces a subset-based self-influence formulation that enables efficient estimation of sample importance at low computational cost. Built upon this, we propose two simple yet effective selection strategies: Top-k Influence (Top I) and Coverage-Centric Influence (CCI). Then, we empirically validate our method on two representative BioFMs: RNA-FM and ESM-C. For RNA, our framework consistently outperforms random selection baselines under an extreme pruning rate of over 99%, which displays our framework's effectiveness. Furthermore, we demonstrate the generalizability of our framework on protein-related tasks using ESM-C. Specifically, our coreset even outperforms random 10x subsets in both RNA and protein settings, revealing substantial redundancy in biological sequence datasets. These findings underscore the potential of influence-guided data pruning to substantially reduce the computational cost of BioFM pretraining, paving the way for more efficient, accessible, and sustainable biological AI research.

The evaluation of Deep Research Agents is a critical challenge, as conventional outcome-based metrics fail to capture the nuances of their complex reasoning. Current evaluation faces two primary challenges: 1) a reliance on singular metrics like Pass@1, creating a ''high-score illusion'' that ignores the quality, efficiency, and soundness of the reasoning process; and 2) the failure of static benchmarks to quantify crucial attributes like robustness and latent capability. To address these gaps, we introduce TRACE (Trajectory-Aware Comprehensive Evaluation), a framework that holistically assesses the entire problem-solving trajectory. To counter the ''high-score illusion'', we propose a Hierarchical Trajectory Utility Function that quantifies process efficiency and cognitive quality, including evidence grounding, alongside accuracy. To measure deeper attributes, TRACE introduces a Scaffolded Capability Assessment protocol, quantifying an agent's latent ability by determining the minimum guidance needed for success. Our contributions include the TRACE framework, its novel metrics, and the accompanying DeepResearch-Bench with controllable complexity. Experiments show TRACE delivers a granular ranking that uncovers critical trade-offs between agent accuracy, efficiency, and robustness entirely missed by singular metrics.

Jiyue Jiang, Yitao Xu, Zikang Wang, Yihan Ye, Yanruisheng Shao, Yuheng Shan, Jiuming Wang, Xiaodan Fan, Jiao Yuan, Yu Li. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks.However, they often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation.To tackle this issue, we first identify the drawbacks of existing solutions (i.e., limited multi-modal reasoning capacities, and insufficient and irrelevant visual descriptions).We then decompose visual reasoning process into two stages: proactive visual perception (i.e., eyesight) and textual reasoning (i.e., wisdom), and introduce a novel visual reasoning framework named PROREASON.This framework features decoupled vision-reasoning capabilities and multi-run proactive perception.Briefly, given a multi-modal question, PRORE-ASON iterates proactive information collection and reasoning until the answer can be concluded with necessary and sufficient visual descriptions.Notably, the disassociation of capabilities allows seamless integration of existing large language models (LLMs) to compensate for the reasoning deficits of LVLMs.Our extensive experiments demonstrate that PROREASON outperforms existing multi-step reasoning frameworks on various benchmarks for both open-source and closed-source models, with the average performance gain reaching 13.2%.Besides, the integration of LLMs allows PROREASON to produce high-quality visual reasoning data, which empowers PRORE-ASON-distilled models (i.e., ProReason-VL and ProReason-Q3) to achieve superior performance in downstream tasks.Our insights into existing solutions and the decoupled perspective for feasible integration of LLMs illuminate future research on visual reasoning techniques, especially LLM-assisted ones.

The rapid scaling of large language models necessitates more lightweight finetuning methods to reduce the explosive GPU memory overhead when numerous customized models are served simultaneously. Targeting more parameter-efficient low-rank adaptation (LoRA), parameter sharing presents a promising solution. Empirically, our research into high-level sharing principles highlights the indispensable role of differentiation in reversing the detrimental effects of pure sharing. Guided by this finding, we propose Mixture of Shards (MoS), incorporating both inter-layer and intra-layer sharing schemes, and integrating four nearly cost-free differentiation strategies, namely subset selection, pair dissociation, vector sharding, and shard privatization. Briefly, it selects a designated number of shards from global pools with a Mixture-of-Experts (MoE)-like routing mechanism before sequentially concatenating them to low-rank matrices. Hence, it retains all the advantages of LoRA while offering enhanced parameter efficiency, and effectively circumvents the drawbacks of peer parameter-sharing methods. Our empirical experiments demonstrate approximately $8\times$ parameter savings in a standard LoRA setting. The ablation study confirms the significance of each component. Our insights into parameter sharing and MoS method may illuminate future developments of more parameter-efficient finetuning methods. The code is officially available at https://github.com/Forence1999/MoS.

Model customization necessitates high-quality and diverse datasets, but acquiring such data remains time-consuming and labor-intensive. Despite the great potential of large language models (LLMs) for data synthesis, current approaches are constrained by limited seed data, model biases and low-variation prompts, resulting in limited diversity and biased distribution with the increase of data scales. To tackle this challenge, we introduce TreeSynth, a tree-guided subspace-based data synthesis approach inspired by decision trees. It constructs a spatial partitioning tree to recursively divide a task-specific full data space (i.e., root node) into numerous atomic subspaces (i.e., leaf nodes) with mutually exclusive and exhaustive attributes to ensure both distinctiveness and comprehensiveness, before synthesizing samples within each atomic subspace. This globally divide-and-synthesize method finally collects subspace samples into a comprehensive dataset, effectively circumventing repetition and space collapse to ensure the diversity of large-scale data synthesis. Furthermore, the spatial partitioning tree enables sample allocation into atomic subspaces, allowing the re-balancing of existing datasets for more balanced and comprehensive distributions. Empirically, extensive experiments across diverse benchmarks consistently validates the superior data diversity, model performance, and robust scalability of TreeSynth compared to both human-crafted datasets and peer data synthesis methods, with the average performance gain reaching 10%. Besides, the consistent improvements of TreeSynth-balanced datasets highlight its efficacious application to redistribute existing datasets for more comprehensive coverage and the induced performance enhancement. The code is available at https://github.com/cpa2001/TreeSynth.

The widespread adoption of high-throughput sequencing technologies and multi-omics approaches has led to rapid accumulation of genomic, transcriptomic, proteomic, and even single-cell multimodal datasets, resulting in an exponential growth of biological data. The massive scale and inherent complexity of these datasets pose significant challenges for data management, analysis, and interpretation in the field of bioinformatics. Concurrently, artificial intelligence (AI) techniques, particularly deep learning and reinforcement learning, have achieved groundbreaking advances in medical diagnostics, drug discovery, and genomic analyses, providing novel theoretical tools and analytical paradigms for bioinformatics research. AI techniques are now extensively applied to DNA, RNA, and protein sequence prediction and design, 3D structural elucidation, functional annotation, integrative analysis of multi-omics data, and personalized drug design for precision medicine, significantly advancing biological research. This review systematically summarizes recent research progress and representative applications of AI techniques in bioinformatics, specifically discussing suitable scenarios and advantages of traditional machine learning algorithms, deep learning models, and reinforcement learning methods. We highlight AI's transformative impact with quantitative metrics from landmark achievements: accurate near-atomic protein structure prediction (median 0.96 Å on CASP14), robust single-cell modeling (AvgBIO $\approx $ 0.82), high protein design success rates (up to 92%), and sensitive cancer detection (Area Under Curve (AUC) $\approx $ 0.93). Furthermore, the paper provides an in-depth analysis of the latest advancements of AI in specific tasks, including biomedical text mining, multimodal omics integration, and single-cell analyses, while highlighting current challenges such as data noise and sparsity, difficulties in modeling long biological sequences, complexities in multimodal data integration, insufficient model interpretability, and ethical and privacy concerns. Finally, the paper outlines promising future research directions, emphasizing large-scale data mining, cross-domain model generalization, innovations in drug design and personalized medicine, and advocates for establishing an open and collaborative research ecosystem.

MOTIVATION: Accurate and generalizable prediction of drug-target interactions (DTIs) remains a critical challenge for drug discovery, particularly when addressing underexplored targets and compounds. Recent advances in graph neural networks and large-scale pre-trained models offer new opportunities to capture rich structural and functional features essential for DTI prediction while enhancing the generalization ability. RESULTS: We present GS-DTI, a graph structure-based DTI prediction framework that integrates molecular graph transformers, protein language models, and protein tertiary structure. Our method achieved robust and interpretable DTI predictions. GS-DTI extracts drug features from SMILES-derived molecular graphs using a knowledge-guided pre-trained transformer, while protein features are derived from both sequence and predicted 3D structure for comprehensive representation. A multi-task loss function equipped with contrastive learning is adopted to enhance generalization and functional interpretability. Extensive experiments on the benchmarks and challenging cross-domain settings demonstrate that GS-DTI achieves state-of-the-art performance. Notably, our model improves the MCC by over 10% compared to previous methods in the drug-target pair cold start test. The model can pinpoint the binding pockets of the targets, offering robust interpretability, and case studies show GS-DTI's promising potential in virtual screening for new candidate drugs of BACE1. AVAILABILITY AND IMPLEMENTATION: The GS-DTI source code and processed datasets are available at https://github.com/purvavideha/GSDTI. All experimental data are derived from public sources.

Sheng Wang, Boyang Xue, Jiacheng Ye, Jiyue Jiang, Liheng Chen, Lingpeng Kong, Chuan Wu. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

When communicating with elders with cognitive impairment, cognitive stimulation (CS) help to maintain the cognitive health of elders.Data sparsity is the main challenge in building CS-based dialogue systems, particularly in the Chinese language.To fill this gap, we construct a Chinese CS conversation (CSConv) dataset, which contains about 2.6K groups of dialogues with therapy principles and emotional support strategy labels.Making chit chat while providing emotional support is overlooked by the majority of existing cognitive dialogue systems.In this paper, we propose a multi-source knowledge fusion method for CS dialogue (CSD), to generate open-ended responses guided by the therapy principle and emotional support strategy.We first use a progressive mask method based on external knowledge to learn encoders as effective classifiers, which is the prerequisite to predict the therapy principle and emotional support strategy of the target response.Then a decoder interacts with the perceived therapy principle and emotional support strategy to generate responses.Extensive experiments conducted on the CSConv dataset demonstrate the effectiveness of the proposed method, while there is still a large space for improvement compared to human performance 1 .