The growing demand for intelligent mobile applications has made the deployment and operation of Deep Neural Networks (DNNs) on mobile Edge Devices (EDs) increasingly essential. However, the highly dynamic nature of edge environments and the limited computational resources of EDs result in significant energy consumption and compromised inference quality. To address these issues, we propose the Demand-Aware Evolutionary Reinforcement Learning (DA-ERL) framework, a novel approach for optimizing Partitioned Collaborative Inference (PCI) across multiple EDs and Mobile Edge Computing (MEC) servers. At the core of DA-ERL is a Demand-Aware Spatio-Temporal Graph Convolutional Network (DA-STGCN). This new architecture creates a predictive state representation by uniquely integrating two channels: a Spatial Graph Channel using Graph Convolutional Networks to model the network topology, and a Temporal Prediction Channel using Temporal Convolutional Networks to capture the evolution of system dynamics. Moreover, we design and formulate a task dynamic demand index to model the dynamic task characteristics, which guides the agent's learning policy. Furthermore, we train DA-ERL within a Cross-Entropy Method (CEM) based evolutionary framework that leverages elite-guided exploration to enhance sample efficiency in complex search spaces. Extensive simulations demonstrate that the proposed DA-ERL framework significantly outperforms conventional methods, achieving a 23.4% reduction in system cost while maintaining a near-perfect task completion rate in high-density scenarios.

Recent advancements in LLMs unlearning have shown remarkable success in removing unwanted data-model influences while preserving the model’s utility for legitimate knowledge. Despite these strides, sparse Mixture-of-Experts (MoE) LLMs–a key subset of the LLM family–have remained unexplored in the context of unlearning. As MoE LLMs are celebrated for their exceptional performance, we ask:How can unlearning be performed effectively and efficiently on MoE LLMs? Our pilot study shows that the dynamic routing nature of MoE LLMs introduces unique challenges, leading to excessive forgetting, uncontrolled knowledge erasure and substantial utility drops when existing unlearning methods are applied. To address this, we propose a novel Selected-Expert Unlearning Framework (SEUF). Through expert attribution, unlearning is concentrated on the most actively engaged experts for the specified knowledge. Concurrently, an anchor loss is applied to the router to stabilize the active state of this targeted expert, ensuring focused and controlled unlearning. SEUF is compatible with various standard unlearning algorithms. Extensive experiments demonstrate that SEUF enhances both forget quality up to 5% and model utility by 35% on MoE LLMs across various benchmarks and LLM architectures (compared to standard unlearning algorithms), while only unlearning 0.06% of the model parameters.

Reaction yield prediction underpins computer-aided synthesis prediction (CASP). Formulated as a regression problem that takes both reactants and products as input, this task has been extensively studied using machine learning methods, based on handcrafted fingerprint features, SMILES encoded by Transformers, and molecular graphs encoded by Graph Neural Networks. However, a major limitation of these methods is their inability to effectively capture and model the underlying uncertainties, arising both from the inherently stochastic nature of chemical reaction processes and from inconsistencies or noise in how yields are measured and reported. What makes this seemingly simple regression problem even more challenging is the lack of any principled way to account for the underlying uncertainties, due to missing or unrecorded experimental process (commonly happens in chemical labs).

The rapid advent of machine learning (ML) and artificial intelligence (AI) has catalyzed major transformations in chemistry, yet the application of these methods to spectroscopic and spectrometric data—termed Spectroscopy Machine Learning (SpectraML)—remains relatively underexplored. Modern spectroscopic techniques (MS, NMR, IR, Raman, UV-Vis) generate an ever-growing volume of high-dimensional data, creating a pressing need for automated and intelligent analysis beyond traditional expert-based workflows. In this survey, we provide a unified review of SpectraML, systematically examining state-of-the-art approaches for both forward tasks (molecule-to-spectrum prediction) and inverse tasks (spectrum-to-molecule inference). We trace the historical evolution of ML in spectroscopy—from early pattern recognition to the latest foundation models capable of advanced reasoning—and offer a taxonomy of representative neural architectures, including graph-based and transformer-based methods. Addressing key challenges such as data quality, multimodal integration, and computational scalability, we highlight emerging directions like synthetic data generation, large-scale pretraining, and few- or zero-shot learning. To foster reproducible research, we release an open-source repository containing curated datasets and code implementations. Our survey serves as a roadmap for researchers, guiding advancements at the intersection of spectroscopy and AI.

Empowering large language models (LLMs) with chemical intelligence remains a challenge due to the scarcity of high-quality, domain-specific instruction-response datasets and the misalignment of existing synthetic data generation pipelines with the inherently hierarchical and rule-governed structure of chemical information. To address this, we propose ChemOrch, a framework that synthesizes chemically grounded instruction–response pairs through a two-stage process: task-controlled instruction generation and tool-aware response construction. ChemOrch enables controllable diversity and levels of difficulty for the generated tasks and ensures response precision through tool planning \& distillation, and tool-based self-repair mechanisms. The effectiveness of ChemOrch is evaluated based on: 1) the \textbf{high quality} of generated instruction data, demonstrating superior diversity and strong alignment with chemical constraints; 2) the \textbf{dynamic generation of evaluation tasks} that more effectively reveal LLM weaknesses in chemistry; and 3) the significant \textbf{improvement of LLM chemistry capabilities} when the generated instruction data are used for fine-tuning. Our work thus represents a critical step toward scalable and verifiable chemical intelligence in LLMs. The code is available at \url{https://anonymous.4open.science/r/ChemOrch-854A}.

LLMs often need effective configurations, like temperature and reasoning steps, to handle tasks requiring sophisticated reasoning and problem-solving, ranging from joke generation to mathematical reasoning. Existing prompting approaches usually adopt general-purpose, fixed configurations that work “well enough” across tasks but seldom achieve task-specific optimality. To address this gap, we introduce AdaReasoner, an LLM-agnostic plugin designed for any LLM to automate adaptive reasoning configurations for tasks requiring different types of thinking. AdaReasoner is trained using a reinforcement learning (RL) framework, combining a factorized action space with a targeted exploration strategy, along with a pretrained reward model to optimize the policy model for reasoning configurations with only a few-shot guide. AdaReasoner is backed by theoretical guarantees and experiments of fast convergence and a sublinear policy gap. Across six different LLMs and a variety of reasoning tasks, it consistently outperforms standard baselines, preserves out-of-distribution robustness, and yield gains on knowledge-intensive tasks through tailored prompts.

Predicting chemical reaction yields is pivotal for efficient chemical synthesis, an area that focuses on the creation of novel compounds for diverse uses. Yield prediction demands accurate representations of reactions for forecasting practical transformation rates. Yet, the uncertainty issues broadcasting in real-world situations prohibit current models to excel in this task owing to the high sensitivity of yield activities and the uncertainty in yield measurements. Existing models often utilize single-modal feature representations, such as molecular fingerprints, SMILES sequences, or molecular graphs, which is not sufficient to capture the complex interactions and dynamic behavior of molecules in reactions. In this paper, we present an advanced Uncertainty-Aware Multimodal model (UAM) to tackle these challenges. Our approach seamlessly integrates data sources from multiple modalities by encompassing sequence representations, molecular graphs, and expert-defined chemical reaction features for a comprehensive representation of reactions. Additionally, we address both the model and data-based uncertainty, refining the model's predictive capability. Extensive experiments on three datasets, including two high throughput experiment (HTE) datasets and one chemist-constructed Amide coupling reaction dataset, demonstrate that UAM outperforms the state-of-the-art methods. The code and used datasets are available at https://github.com/jychen229/Multimodal-reaction-yield-prediction.

Large Language Models (LLMs) demonstrate remarkable capabilities across diverse applications.However, concerns regarding their security, particularly the vulnerability to jailbreak attacks, persist.Drawing inspiration from adversarial training in deep learning and LLM agent learning processes, we introduce the In-Context Adversarial Game (ICAG) for defending against jailbreaks without the need for fine-tuning.ICAG leverages agent learning to conduct an adversarial game, aiming to dynamically extend knowledge to defend against jailbreaks.Unlike traditional methods that rely on static datasets, ICAG employs an iterative process to enhance both the defense and attack agents.This continuous improvement process strengthens defenses against newly generated jailbreak prompts.Our empirical studies affirm ICAG's efficacy, where LLMs safeguarded by ICAG exhibit significantly reduced jailbreak success rates across various attack scenarios.Moreover, ICAG demonstrates remarkable transferability to other LLMs, indicating its potential as a versatile defense mechanism.The code is available at https://github.com/YujunZhou/ In-Context-Adversarial-Game.28 1 82 8 8 28 3 31 9 2 1 92 82 3 31 2 98 !" "1 3"1 28 1 82 8 8 28 3 31 # $ % # &81 !" ' " 2("2 1 % 28 1 82 8 8 28 3 31 01 23 56 781 92 81 2 8 6 9 2 1 92 82 3 31 2 98 !" "1 3"1 28 1 82 8 8 28 3 31 # $ % # &81 !" ' " 2("2 1 % "&&2 !" 8 28 1 8 8 28 "&&2 !" ) "1 ! 8 2 8 28 1 8 ! 8 2) 9 *+8& 91 ,8 2 *+8& 91 ) 2'2 ! 8 2 8 28% 2 8 28 3 31 28 1 82 8 2 8 28 3 31 01 23 56 781 92 81 2 8 6 "5-.2! 2 2 "/-*+8& *+8&2 .2! 22 .2! 2 2 001 *+8& 001 .2! 2 2 * 1 81 001 (a) Self Reminder 01 23 56 781 92 81 2 8 6 28 1 82 8 8 28 3 31 9 2 1 92 82 3 31 2 98 !" "1 3"1 28 1 82 8 8 28 3 31 # $ % # &81 !" ' " 2("2 1 % 28 1 82 8 8 28 3 31 01 23 56 781 92 81 2 8 6 9 2 1 92 82 3 31 2 98 !" "1 3"1 28 1 82 8 8 28 3 31 # $ % # &81 !" ' " 2("2 1 % "&&2 !" 8 28 1 8 8 28 "&&2 !" ) "1 ! 8 2 8 28 1 8 ! 8 2) 9 *+8& 91 ,8 2 *+8& 91 ) 2'2 ! 8 2 8 28% 2 8 28 3 31 28 1 82 8 2 8 28 3 31 01 23 56 781 92 81 2 8 6 "5-.2! 2 2 "/-*+8& *+8&2 .2! 22 .2! 2 2 001 *+8& 001 .2! 2 2 * 1 81 001 (b) Our proposed In-Context Adversarial Game 0 1 2 :. 1 9 2 15 9 5 5 4-2 1*"1.9 "1 7 2 1!9 9 4 0 1 2 *"1.9 "1 7 : 2 1!9 9 4 0 1 2 : 7 :.7 18 4-9 9 -9 7 :C., 49 -99 1 =2 9 7 ::.7 49 9 ; 9 45 4 9 A49 5 :.B A49 5 :C.7 * 7 :2 1 2 1 7 :.7 18 4-9 9 -9 ,!! 57 7 :

Large Language Models (LLMs) have shown significant problem-solving capabilities across predictive and generative tasks in chemistry. However, their proficiency in multi-step chemical reasoning remains underexplored. We introduce a new challenge: molecular structure elucidation, which involves deducing a molecule’s structure from various types of spectral data. Solving such a molecular puzzle, akin to solving crossword puzzles, poses reasoning challenges that require integrating clues from diverse sources and engaging in iterative hypothesis testing. To address this challenging problem with LLMs, we present \textbf{MolPuzzle}, a benchmark comprising 217 instances of structure elucidation, which feature over 23,000 QA samples presented in a sequential puzzle-solving process, involving three interlinked sub-tasks: molecule understanding, spectrum interpretation, and molecule construction. Our evaluation of 12 LLMs reveals that the best-performing LLM, GPT-4o, performs significantly worse than humans, with only a small portion (1.4\%) of its answers exactly matching the ground truth. However, it performs nearly perfectly in the first subtask of molecule understanding, achieving accuracy close to 100\%. This discrepancy highlights the potential of developing advanced LLMs with improved chemical reasoning capabilities in the other two sub-tasks. Our MolPuzzle dataset and evaluation code are available at this \href{https://github.com/KehanGuo2/MolPuzzle}{link}.

Molecular representation learning (MRL) is a key step to build the connection between machine learning and chemical science. In particular, it encodes molecules as numerical vectors preserving the molecular structures and features, on top of which the downstream tasks (e.g., property prediction) can be performed. Recently, MRL has achieved considerable progress, especially in methods based on deep molecular graph learning. In this survey, we systematically review these graph-based molecular representation techniques, especially the methods incorporating chemical domain knowledge. Specifically, we first introduce the features of 2D and 3D molecular graphs. Then we summarize and categorize MRL methods into three groups based on their input. Furthermore, we discuss some typical chemical applications supported by MRL. To facilitate studies in this fast-developing area, we also list the benchmarks and commonly used datasets in the paper. Finally, we share our thoughts on future research directions.

Large Language Models (LLMs) with strong abilities in natural language processing tasks have emerged and have been applied in various kinds of areas such as science, finance and software engineering. However, the capability of LLMs to advance the field of chemistry remains unclear. In this paper, rather than pursuing state-of-the-art performance, we aim to evaluate capabilities of LLMs in a wide range of tasks across the chemistry domain. We identify three key chemistry-related capabilities including understanding, reasoning and explaining to explore in LLMs and establish a benchmark containing eight chemistry tasks. Our analysis draws on widely recognized datasets facilitating a broad exploration of the capacities of LLMs within the context of practical chemistry. Five LLMs (GPT-4,GPT-3.5, Davinci-003, Llama and Galactica) are evaluated for each chemistry task in zero-shot and few-shot in-context learning settings with carefully selected demonstration examples and specially crafted prompts. Our investigation found that GPT-4 outperformed other models and LLMs exhibit different competitive levels in eight chemistry tasks. In addition to the key findings from the comprehensive benchmark analysis, our work provides insights into the limitation of current LLMs and the impact of in-context learning settings on LLMs’ performance across various chemistry tasks. The code and datasets used in this study are available at https://github.com/ChemFoundationModels/ChemLLMBench.