arXiv subjects

Khiem Le

Publications and source records attributed to Khiem Le.

10 recordsLinked to original sources

arXiv2026

Can Decision Trees Teach Large Language Models? Distilling Verbalized Knowledge for Molecular Property Prediction

Molecular Property Prediction (MPP) is a fundamental problem in drug discovery that has recently attracted growing attention. Large Language Models (LLMs), known for their impressive proficiency across domains, show promise as generalist models for MPP. However, their current performance remains below the threshold needed for practical adoption. To bridge this gap, we propose TreeKD for distilling the knowledge of tree-based specialist models into LLMs to complement the internal knowledge of LLMs and improve their predictive accuracy. For each property, we train a specialist decision tree using features derived from 40K functional groups in the input molecules. Then, the predictive rule learned by the decision tree, which encodes its knowledge, is verbalized and incorporated into the prompts for training LLMs. In addition, by replacing a single decision tree with a Random Forest, we introduce a test-time scaling technique called rule-consistency, which aggregates predictions generated from different prompts constructed with different rules. An extensive evaluation with two LLMs, Gemma-2-2B and Granite-3.3-2B, on the TDC benchmark with 22 prediction tasks shows that our method substantially enhances the performance of LLMs, advancing the development of generalist models for MPP.

cs.LG↗

arXiv2026

Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models

Group Relative Policy Optimization (GRPO) has become the dominant method for reinforcement learning with verifiable rewards in large language models, but it suffers from two critical limitations: gradient vanishing and diversity collapse. When training questions are too easy or too hard, all sampled responses receive identical rewards, yielding zero gradients. Meanwhile, the model tends to collapse its responses toward a single reasoning pattern rather than exploring diverse strategies. We propose Transformation-Augmented GRPO (TA-GRPO), a simple but effective method that addresses both issues via question rephrasing. For each training question, we automatically generate multiple problem-equivalent rephrasings that alter wording, format, and information order while preserving the underlying meaning. Because these rephrasings shift the model's perceived difficulty, pooling responses across the original and its rephrasings yields mixed rewards and more diverse reasoning paths. TA-GRPO jointly computes advantages over this expanded response set and aligns all importance ratios to the original question, enabling the model to learn from a richer set of solution attempts. Experiments on four LLMs (Qwen3-1.7B, Qwen3-4B, Llama-3.2-1B, Llama-3.2-3B) show that TA-GRPO consistently improves pass@$k$ on competition-level benchmarks (AMC, OlympiadBench, AIME24, AIME25) and out-of-distribution benchmarks (Minerva, GPQA-Diamond). Notably, it improves the average pass@32 of Qwen3-1.7B and Qwen3-4B by \textbf{4.97} and \textbf{4.34} points, respectively, and matches the exploration quality of baselines trained on up to 2.5$\times$ more data.

cs.LG↗

arXiv2025

FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE

Existing resource-adaptive LoRA federated fine-tuning methods enable clients to fine-tune models using compressed versions of global LoRA matrices, in order to accommodate various compute resources across clients. This compression requirement will lead to suboptimal performance due to information loss. To address this, we propose FLAME, a novel federated learning framework based on the Sparse Mixture-of-Experts (SMoE) architecture. Unlike prior approaches, FLAME retains full (uncompressed) global LoRA matrices and achieves client-side adaptability by varying the number of activated experts per client. However, incorporating SMoE into federated learning introduces unique challenges, specifically, the mismatch in output magnitude from partial expert activation and the imbalance in expert training quality across clients. FLAME tackles these challenges through a lightweight rescaling mechanism and an activation-aware aggregation scheme. Empirical results across diverse computational settings demonstrate that FLAME consistently outperforms existing methods, providing a robust and effective solution for resource-adaptive federated learning.

cs.LG↗

arXiv2025

Bridging the AI Adoption Gap: Designing an Interactive Pedagogical Agent for Higher Education Instructors

Instructors play a pivotal role in integrating AI into education, yet their adoption of AI-powered tools remains inconsistent. Despite this, limited research explores how to design AI tools that support broader instructor adoption. This study applies a human-centered design approach, incorporating qualitative methods, to investigate the design of interactive pedagogical agents that provide instructional suggestions in response to instructors' questions. We conducted a formative study involving interviews with five pedagogy experts to examine existing strategies for supporting instructors' pedagogical needs. Building on these insights, we facilitated a participatory design session with ten pedagogy experts, where participants reviewed a storyboard depicting a chatbot designed for instructors with varying levels of AI literacy and differing attitudes toward AI. Experts also evaluated the quality of LLM-generated suggestions based on common teaching challenges. Our findings highlight the need for chatbot interactions that foster trust, especially for AI-conservative instructors. Experts emphasized the importance of social transparency (for example, showing how peers use the tool) and allowing instructors to flexibly control how much or how little they engage with the system. We also propose design recommendations to enhance the quality of AI-generated teaching suggestions, such as adapting them to reflect instructors' prior teaching experience. This work underscores the urgent need to support AI-conservative instructors, as AI literacy and attitudes are closely intertwined. Without thoughtful design, there is a risk of widening pedagogical divides and reducing students' learning opportunities.

cs.HC↗

arXiv2025

Dynamic Noise Preference Optimization: Self-Improvement of Large Language Models with Self-Synthetic Data

Although LLMs have achieved significant success, their reliance on large volumes of human-annotated data has limited their potential for further scaling. In this situation, utilizing self-generated synthetic data has become crucial for fine-tuning LLMs without extensive human annotation. However, current methods often fail to ensure consistent improvements across iterations, with performance stagnating after only minimal updates. To overcome these challenges, we introduce Dynamic Noise Preference Optimization (DNPO), which combines dynamic sample labeling for constructing preference pairs with controlled, trainable noise injection during preference optimization. Our approach effectively prevents stagnation and enables continuous improvement. In experiments with Llama-3.2-3B and Zephyr-7B, DNPO consistently outperforms existing methods across multiple benchmarks. Additionally, with Zephyr-7B, DNPO shows a significant improvement in model-generated data quality, with a 29.4% win-loss rate gap compared to the baseline in GPT-4 evaluations.

cs.CL↗

arXiv2024

AgentDrug: Utilizing Large Language Models in An Agentic Workflow for Zero-Shot Molecular Editing

Molecular editing-modifying a given molecule to improve desired properties-is a fundamental task in drug discovery. While LLMs hold the potential to solve this task using natural language to drive the editing, straightforward prompting achieves limited accuracy. In this work, we propose AgentDrug, an agentic workflow that leverages LLMs in a structured refinement process to achieve significantly higher accuracy. AgentDrug defines a nested refinement loop: the inner loop uses feedback from cheminformatics toolkits to validate molecular structures, while the outer loop guides the LLM with generic feedback and a gradient-based objective to steer the molecule toward property improvement. We evaluate AgentDrug on benchmarks with both single- and multi-property editing under loose and strict thresholds. Results demonstrate significant performance gains over previous methods. With Qwen-2.5-3B, AgentDrug improves accuracy by 20.7% (loose) and 16.8% (strict) on six single-property tasks, and by 7.0% and 5.3% on eight multi-property tasks. With larger model Qwen-2.5-7B, AgentDrug further improves accuracy on 6 single-property objectives by 28.9% (loose) and 29.0% (strict), and on 8 multi-property objectives by 14.9% (loose) and 13.2% (strict).

cs.LG↗

arXiv2024

MolX: Enhancing Large Language Models for Molecular Understanding With A Multi-Modal Extension

Large Language Models (LLMs) with their strong task-handling capabilities have shown remarkable advancements across a spectrum of fields, moving beyond natural language understanding. However, their proficiency within the chemistry domain remains restricted, especially in solving molecule-related tasks. This challenge is attributed to their inherent limitations in comprehending molecules using only common textual representations, i.e. SMILES strings. In this study, we seek to enhance the ability of LLMs to comprehend molecules by equipping them with a multi-modal external module, termed MolX. Instead of directly using SMILES strings to represent a molecule, we utilize specific encoders to extract fine-grained features from both SMILES string and 2D molecular graph representations for feeding into an LLM. A hand-crafted molecular fingerprint is incorporated to leverage its embedded domain knowledge. To establish an alignment between MolX and the LLM's textual input space, the model in which the LLM is frozen, is pre-trained with a strategy including a diverse set of tasks. Experimental evaluations show that our proposed method outperforms baselines across downstream molecule-related tasks ranging from molecule-to-text translation to molecular property prediction, with and without fine-tuning the LLM, while only introducing a small number of trainable parameters-0.53% and 0.82%, respectively.

cs.CV↗

arXiv2024

Exploring the Practicality of Federated Learning: A Survey Towards the Communication Perspective

Federated Learning (FL) is a promising paradigm that offers significant advancements in privacy-preserving, decentralized machine learning by enabling collaborative training of models across distributed devices without centralizing data. However, the practical deployment of FL systems faces a significant bottleneck: the communication overhead caused by frequently exchanging large model updates between numerous devices and a central server. This communication inefficiency can hinder training speed, model performance, and the overall feasibility of real-world FL applications. In this survey, we investigate various strategies and advancements made in communication-efficient FL, highlighting their impact and potential to overcome the communication challenges inherent in FL systems. Specifically, we define measures for communication efficiency, analyze sources of communication inefficiency in FL systems, and provide a taxonomy and comprehensive review of state-of-the-art communication-efficient FL methods. Additionally, we discuss promising future research directions for enhancing the communication efficiency of FL systems. By addressing the communication bottleneck, FL can be effectively applied and enable scalable and practical deployment across diverse applications that require privacy-preserving, decentralized machine learning, such as IoT, healthcare, or finance.

cs.LG↗

arXiv2024

Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalization

Domain shift is a formidable issue in Machine Learning that causes a model to suffer from performance degradation when tested on unseen domains. Federated Domain Generalization (FedDG) attempts to train a global model using collaborative clients in a privacy-preserving manner that can generalize well to unseen clients possibly with domain shift. However, most existing FedDG methods either cause additional privacy risks of data leakage or induce significant costs in client communication and computation, which are major concerns in the Federated Learning paradigm. To circumvent these challenges, here we introduce a novel architectural method for FedDG, namely gPerXAN, which relies on a normalization scheme working with a guiding regularizer. In particular, we carefully design Personalized eXplicitly Assembled Normalization to enforce client models selectively filtering domain-specific features that are biased towards local data while retaining discrimination of those features. Then, we incorporate a simple yet effective regularizer to guide these models in directly capturing domain-invariant representations that the global model's classifier can leverage. Extensive experimental results on two benchmark datasets, i.e., PACS and Office-Home, and a real-world medical dataset, Camelyon17, indicate that our proposed method outperforms other existing methods in addressing this particular problem.

cs.CV↗

arXiv2023

HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts

By routing input tokens to only a few split experts, Sparse Mixture-of-Experts has enabled efficient training of large language models. Recent findings suggest that fixing the routers can achieve competitive performance by alleviating the collapsing problem, where all experts eventually learn similar representations. However, this strategy has two key limitations: (i) the policy derived from random routers might be sub-optimal, and (ii) it requires extensive resources during training and evaluation, leading to limited efficiency gains. This work introduces \HyperRout, which dynamically generates the router's parameters through a fixed hypernetwork and trainable embeddings to achieve a balance between training the routers and freezing them to learn an improved routing policy. Extensive experiments across a wide range of tasks demonstrate the superior performance and efficiency gains of \HyperRouter compared to existing routing methods. Our implementation is publicly available at {\url{https://github.com/giangdip2410/HyperRouter}}.

cs.LG↗