Ziru Liu

Ziru Liu, Jiejie Tian, Qingpeng Cai et al.

In recent years, Multi-task Learning (MTL) has yielded immense success in Recommender System (RS) applications. However, current MTL-based recommendation models tend to disregard the session-wise patterns of user-item interactions because they are predominantly constructed based on item-wise datasets. Moreover, balancing multiple objectives has always been a challenge in this field, which is typically avoided via linear estimations in existing works. To address these issues, in this paper, we propose a Reinforcement Learning (RL) enhanced MTL framework, namely RMTL, to combine the losses of different recommendation tasks using dynamic weights. To be specific, the RMTL structure can address the two aforementioned issues by (i) constructing an MTL environment from session-wise interactions and (ii) training multi-task actor-critic network structure, which is compatible with most existing MTL-based recommendation models, and (iii) optimizing and fine-tuning the MTL loss function using the weights generated by critic networks. Experiments on two real-world public datasets demonstrate the effectiveness of RMTL with a higher AUC against state-of-the-art MTL-based recommendation models. Additionally, we evaluate and validate RMTL's compatibility and transferability across various MTL models.

Ziru Liu, Kecheng Chen, Fengyi Song et al.

In the domain of streaming recommender systems, conventional methods for addressing new user IDs or item IDs typically involve assigning initial ID embeddings randomly. However, this practice results in two practical challenges: (i) Items or users with limited interactive data may yield suboptimal prediction performance. (ii) Embedding new IDs or low-frequency IDs necessitates consistently expanding the embedding table, leading to unnecessary memory consumption. In light of these concerns, we introduce a reinforcement learning-driven framework, namely AutoAssign+, that facilitates Automatic Shared Embedding Assignment Plus. To be specific, AutoAssign+ utilizes an Identity Agent as an actor network, which plays a dual role: (i) Representing low-frequency IDs field-wise with a small set of shared embeddings to enhance the embedding initialization, and (ii) Dynamically determining which ID features should be retained or eliminated in the embedding table. The policy of the agent is optimized with the guidance of a critic network. To evaluate the effectiveness of our approach, we perform extensive experiments on three commonly used benchmark datasets. Our experiment results demonstrate that AutoAssign+ is capable of significantly enhancing recommendation performance by mitigating the cold-start problem. Furthermore, our framework yields a reduction in memory usage of approximately 20-30%, verifying its practical effectiveness and efficiency for streaming recommender systems.

Zhiyuan Li, Ziru Liu, Anna Zou et al.

Deep metric learning techniques have been used for visual representation in various supervised and unsupervised learning tasks through learning embeddings of samples with deep networks. However, classic approaches, which employ a fixed distance metric as a similarity function between two embeddings, may lead to suboptimal performance for capturing the complex data distribution. The Bregman divergence generalizes measures of various distance metrics and arises throughout many fields of deep metric learning. In this paper, we first show how deep metric learning loss can arise from the Bregman divergence. We then introduce a novel method for learning empirical Bregman divergence directly from data based on parameterizing the convex function underlying the Bregman divergence with a deep learning setting. We further experimentally show that our approach performs effectively on five popular public datasets compared to other SOTA deep metric learning methods, particularly for pattern recognition problems.

Zijian Zhang, Shuchang Liu, Jiaao Yu et al.

Multi-domain recommendation and multi-task recommendation have demonstrated their effectiveness in leveraging common information from different domains and objectives for comprehensive user modeling. Nonetheless, the practical recommendation usually faces multiple domains and tasks simultaneously, which cannot be well-addressed by current methods. To this end, we introduce M3oE, an adaptive Multi-domain Multi-task Mixture-of-Experts recommendation framework. M3oE integrates multi-domain information, maps knowledge across domains and tasks, and optimizes multiple objectives. We leverage three mixture-of-experts modules to learn common, domain-aspect, and task-aspect user preferences respectively to address the complex dependencies among multiple domains and tasks in a disentangled manner. Additionally, we design a two-level fusion mechanism for precise control over feature extraction and fusion across diverse domains and tasks. The framework's adaptability is further enhanced by applying AutoML technique, which allows dynamic structure optimization. To the best of the authors' knowledge, our M3oE is the first effort to solve multi-domain multi-task recommendation self-adaptively. Extensive experiments on two benchmark datasets against diverse baselines demonstrate M3oE's superior performance. The implementation code is available to ensure reproducibility.

Jinpeng Chen, Cheng Gong, Hanbo Li et al.

Developing multi-turn interactive tool-use agents is challenging because real-world user needs are often complex and ambiguous, yet agents must execute deterministic actions to satisfy them. To address this gap, we introduce \textbf{CoVe} (\textbf{Co}nstraint-\textbf{Ve}rification), a post-training data synthesis framework designed for training interactive tool-use agents while ensuring both data complexity and correctness. CoVe begins by defining explicit task constraints, which serve a dual role: they guide the generation of complex trajectories and act as deterministic verifiers for assessing trajectory quality. This enables the creation of high-quality training trajectories for supervised fine-tuning (SFT) and the derivation of accurate reward signals for reinforcement learning (RL). Our evaluation on the challenging $τ^2$-bench benchmark demonstrates the effectiveness of the framework. Notably, our compact \textbf{CoVe-4B} model achieves success rates of 43.0\% and 59.4\% in the Airline and Retail domains, respectively; its overall performance significantly outperforms strong baselines of similar scale and remains competitive with models up to $17\times$ its size. These results indicate that CoVe provides an effective and efficient pathway for synthesizing training data for state-of-the-art interactive tool-use agents. To support future research, we open-source our code, trained model, and the full set of 12K high-quality trajectories used for training.

Kecheng Chen, Ziru Liu, Xijia Tao et al.

Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive language models, offering stronger global awareness and highly parallel generation. However, post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient: training reconstructs randomly masked tokens in a single step, whereas inference follows a confidence-guided, multi-step easy-to-hard denoising trajectory. Recent trajectory-based self-distillation methods exploit such inference trajectories mainly for sampling-step compression and acceleration, often improving decoding efficiency without substantially enhancing the model's underlying capability, and may even degrade performance under full diffusion decoding. In this work, we ask whether self-distilled trajectories can be used not merely for faster inference, but for genuine knowledge acquisition. Although these trajectories lie on the pretrained DLM's own distributional manifold and thus offer a potentially lower optimization barrier, we find that naively fine-tuning on them with standard NELBO objectives yields only marginal gains. To address this limitation, we propose \textbf{T}rajectory-\textbf{A}ligned optimization via \textbf{Bo}ltzmann \textbf{M}odeling (\textbf{TABOM}), a self-distilled trajectory-based post-training framework that aligns training with the easy-to-hard structure of inference. TABOM models the inference unmasking preference as a Boltzmann distribution over predictive entropies and derives a tractable pairwise ranking objective to align the model's certainty ordering with the observed decoding trajectory. Empirically, TABOM achieves substantial gains in new domains, expands the effective knowledge boundary of DLMs, and significantly mitigates catastrophic forgetting compared with standard SFT.

Yuhao Wang, Xiaopeng Li, Cheng Gong et al.

Reinforcement learning with verifiable rewards (RLVR) has been shown to enhance the reasoning capabilities of large language models (LLMs), enabling the development of large reasoning models (LRMs). However, LRMs such as DeepSeek-R1 and OpenAI o1 often generate verbose responses containing redundant or irrelevant reasoning step-a phenomenon known as overthinking-which substantially increases computational costs. Prior efforts to mitigate this issue commonly incorporate length penalties into the reward function, but we find they frequently suffer from two critical issues: length collapse and training collapse, resulting in sub-optimal performance. To address them, we propose a pipeline for training a Conciseness Reward Model (CRM) that scores the conciseness of reasoning path. Additionally, we introduce a novel reward formulation named Conciseness Reward Function (CRF) with explicit dependency between the outcome reward and conciseness score, thereby fostering both more effective and more efficient reasoning. From a theoretical standpoint, we demonstrate the superiority of the new reward from the perspective of variance reduction and improved convergence properties. Besides, on the practical side, extensive experiments on five mathematical benchmark datasets demonstrate the method's effectiveness and token efficiency, which achieves an 8.1% accuracy improvement and a 19.9% reduction in response token length on Qwen2.5-7B. Furthermore, the method generalizes well to other LLMs including Llama and Mistral. The implementation code and datasets are publicly available for reproduction: https://anonymous.4open.science/r/CRM.

Xijia Tao, Yihua Teng, Xinxing Su et al.

Existing multimodal browsing benchmarks often fail to require genuine multimodal reasoning, as many tasks can be solved with text-only heuristics without vision-in-the-loop verification. We introduce MMSearch-Plus, a 311-task benchmark that enforces multimodal understanding by requiring extraction and propagation of fine-grained visual cues through iterative image-text retrieval and cross-validation under retrieval noise. Our curation procedure seeds questions whose answers require extrapolating from spatial cues and temporal traces to out-of-image facts such as events, dates, and venues. Beyond the dataset, we provide a model-agnostic agent framework with standard browsing tools and a set-of-mark (SoM) module, which lets the agent place marks, crop subregions, and launch targeted image/text searches. SoM enables provenance-aware zoom-and-retrieve and improves robustness in multi-step reasoning. We evaluated closed- and open-source MLLMs in this framework. The strongest system achieves an end-to-end accuracy of 36.0%, and integrating SoM produces consistent gains in multiple settings, with improvements up to +3.9 points. From failure analysis, we observe recurring errors in locating relevant webpages and distinguishing between visually similar events. These results underscore the challenges of real-world multimodal search and establish MMSearch-Plus as a rigorous benchmark for advancing agentic MLLMs.

Guangyan Zhang, Ziru Liu, Jichen Dai et al.

Motivation: Since long non-coding RNAs (lncRNAs) have involved in a wide range of functions in cellular and developmental processes, an increasing number of methods have been proposed for distinguishing lncRNAs from coding RNAs. However, most of the existing methods are designed for lncRNAs in animal systems, and only a few methods focus on the plant lncRNA identification. Different from lncRNAs in animal systems, plant lncRNAs have distinct characteristics. It is desirable to develop a computational method for accurate and robust identification of plant lncRNAs. Results: Herein, we present a plant lncRNA identification method ItLnc-BXE, which utilizes multiple features and the ensemble learning strategy. First, a diversity of lncRNA features is collected and filtered by feature selection to represent RNA transcripts. Then, several base learners are trained and further combined into a single meta-learner by ensemble learning, and thus an ItLnc-BXE model is constructed. ItLnc-BXE models are evaluated on datasets of six plant species, the results show that ItLnc-BXE outperforms other state-of-the-art plant lncRNA identification methods, achieving better and robust performances (AUC>95.91%). We also perform some experiments about cross-species lncRNA identification, and the results indicate that dicots-based and monocots-based models can be used to accurately identify lncRNAs in lower plant species, such as mosses and algae. Availability: source codes are available at https://github.com/BioMedicalBigDataMiningLab/ItLnc-BXE. Contact: zhangwen@mail.hzau.edu.cn (or) zhangwen@whu.edu.cn Supplementary information: Supplementary data are available at Bioinformatics online.

Zijian Zhang, Shuchang Liu, Ziru Liu et al.

User simulators can rapidly generate a large volume of timely user behavior data, providing a testing platform for reinforcement learning-based recommender systems, thus accelerating their iteration and optimization. However, prevalent user simulators generally suffer from significant limitations, including the opacity of user preference modeling and the incapability of evaluating simulation accuracy. In this paper, we introduce an LLM-powered user simulator to simulate user engagement with items in an explicit manner, thereby enhancing the efficiency and effectiveness of reinforcement learning-based recommender systems training. Specifically, we identify the explicit logic of user preferences, leverage LLMs to analyze item characteristics and distill user sentiments, and design a logical model to imitate real human engagement. By integrating a statistical model, we further enhance the reliability of the simulation, proposing an ensemble model that synergizes logical and statistical insights for user interaction simulations. Capitalizing on the extensive knowledge and semantic generation capabilities of LLMs, our user simulator faithfully emulates user behaviors and preferences, yielding high-fidelity training data that enrich the training of recommendation algorithms. We establish quantifying and qualifying experiments on five datasets to validate the simulator's effectiveness and stability across various recommendation scenarios.

Ziru Liu, Cheng Gong, Xinyu Fu et al.

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularly in the domain of complex reasoning tasks. However, prevailing on-policy RL methods often contend with significant training instability and inefficiency. This is primarily due to a capacity-difficulty mismatch, where the complexity of training data frequently outpaces the model's current capabilities, leading to critically sparse reward signals and stalled learning progress. This challenge is particularly acute for smaller, more resource-efficient LLMs. To overcome this, we introduce the Guided Hybrid Policy Optimization (GHPO), a novel difficulty-aware reinforcement learning framework. GHPO dynamically calibrates task difficulty by employing adaptive prompt refinement to provide targeted guidance. This unique approach adaptively balances direct imitation learning for problems currently beyond the model's reach with exploration-based reinforcement learning for more manageable tasks, effectively creating a smooth and optimized learning curriculum. Extensive experiments demonstrate that GHPO achieves an average performance gain of approximately 5% across six challenging mathematics benchmarks, consistently outperforming strong on-policy reinforcement learning and curriculum learning baselines. Further analysis confirms that our framework significantly enhances both training stability and final reasoning performance, thus offering a scalable and efficient solution for developing powerful and robust reasoning models.

Kecheng Chen, Ziru Liu, Xijia Tao et al.

Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics such as confidence or entropy which inherently lack a more reliable perspective. This limitation frequently leads to inconsistent sampling trajectories and suboptimal generation quality. To address this, we propose Coherent Contextual Decoding (CCD), a novel inference framework built upon two core innovations. First, CCD employs a trajectory rectification mechanism that leverages historical context to enhance sequence coherence, enabling the early rejection of suboptimal paths. We demonstrate that this mechanism is theoretically equivalent to modeling the consistency of historical steps via the conditional mutual information between context and token predictions. Building on this theoretical insight, we further address the inefficiency of conventional uniform decoding budgets. Instead of rigid allocations based on diffusion steps, we introduce an adaptive sampling strategy that dynamically adjusts the unmasking budget for each step according to our consistency metric. Consequently, our method significantly improves the quality of generation trajectories while accelerating the sampling process. Empirically, our method achieves a simultaneous enhancement in both inference speed and performance across diverse benchmarks on Dream and LLaDA, delivering up to 3.48x speedup alongside 3.91% performance improvement.

Rui Peng, Ziru Liu, Lingyuan Ye et al.

Accurately modeling the relationship between perturbations, transcriptional responses, and phenotypic changes is essential for building an AI Virtual Cell (AIVC). However, existing methods typically constrained to modeling direct associations, such as Perturbation $\rightarrow$ RNA or Perturbation $\rightarrow$ Morphology, overlook the crucial causal link from RNA to morphology. To bridge this gap, we propose TRIDENT, a cascade generative framework that synthesizes realistic cellular morphology by conditioning on both the perturbation and the corresponding gene expression profile. To train and evaluate this task, we construct MorphoGene, a new dataset pairing L1000 gene expression with Cell Painting images for 98 compounds. TRIDENT significantly outperforms state-of-the-art approaches, achieving up to 7-fold improvement with strong generalization to unseen compounds. In a case study on docetaxel, we validate that RNA-guided synthesis accurately produces the corresponding phenotype. An ablation study further confirms that this RNA conditioning is essential for the model's high fidelity. By explicitly modeling transcriptome-phenome mapping, TRIDENT provides a powerful in silico tool and moves us closer to a predictive virtual cell.

Cheng Wang, ziru Liu, Pengcheng Tang et al.

Identifying user preferences in dialogue systems is a pivotal aspect of providing satisfying services. Current research shows that using large language models (LLMs) to fine-tune a task-specific preference extractor yields excellent results in terms of accuracy and generalization. However, the primary challenge stems from the inherent difficulty in obtaining high-quality labeled multi-turn dialogue data. Accurately tracking user preference transitions across turns not only demands intensive domain expertise and contextual consistency maintenance for annotators (termed \textbf{``Annotating Disaster''}) but also complicates model training due to error propagation in sequential dependency learning. Inspired by the observation that multi-turn preference extraction can be decomposed into iterative executions of one-turn extraction processes. We propose a novel dialogue data generation framework named \textbf{IterChat}. First, we construct a new data format that categorizes the dialogue data into attributed historical preferences and one-turn dialogues. This reduces the probability of annotation errors and improves annotation efficiency. Then, to generate a high-quality and diverse dialogue dataset, we adopt GPT4 to pre-define the preference slots in the target preference extractor task and then randomly sample the subset of the slots and their corresponding schema values to create the dialogue datasets. Experimental results indicate that fine-tuning or only few-shot prompting with the new dialogue format yields superior performance compared to the original multi-turn dialogues. Additionally, the new data format improves annotator efficiency with a win rate of 28.4\% higher than the original multi-turn dialogues.