arXiv subjects

Yuqiang Li

Publications and source records attributed to Yuqiang Li.

At least 91 records · Page 5Linked to original sources

arXiv2025

CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

We introduce CMPhysBench, designed to assess the proficiency of Large Language Models (LLMs) in Condensed Matter Physics, as a novel Benchmark. CMPhysBench is composed of more than 520 graduate-level meticulously curated questions covering both representative subfields and foundational theoretical frameworks of condensed matter physics, such as magnetism, superconductivity, strongly correlated systems, etc. To ensure a deep understanding of the problem-solving process,we focus exclusively on calculation problems, requiring LLMs to independently generate comprehensive solutions. Meanwhile, leveraging tree-based representations of expressions, we introduce the Scalable Expression Edit Distance (SEED) score, which provides fine-grained (non-binary) partial credit and yields a more accurate assessment of similarity between prediction and ground-truth. Our results show that even the best models, Grok-4, reach only 36 average SEED score and 28% accuracy on CMPhysBench, underscoring a significant capability gap, especially for this practical and frontier domain relative to traditional physics. The code anddataset are publicly available at https://github.com/CMPhysBench/CMPhysBench.

cs.LG↗

arXiv2025

Intern-S1: A Scientific Multimodal Foundation Model

In recent years, a plethora of open-source foundation models have emerged, achieving remarkable progress in some widely attended fields, with performance being quite close to that of closed-source models. However, in high-value but more challenging scientific professional fields, either the fields still rely on expert models, or the progress of general foundation models lags significantly compared to those in popular areas, far from sufficient for transforming scientific research and leaving substantial gap between open-source models and closed-source models in these scientific domains. To mitigate this gap and explore a step further toward Artificial General Intelligence (AGI), we introduce Intern-S1, a specialized generalist equipped with general understanding and reasoning capabilities with expertise to analyze multiple science modal data. Intern-S1 is a multimodal Mixture-of-Experts (MoE) model with 28 billion activated parameters and 241 billion total parameters, continually pre-trained on 5T tokens, including over 2.5T tokens from scientific domains. In the post-training stage, Intern-S1 undergoes offline and then online reinforcement learning (RL) in InternBootCamp, where we propose Mixture-of-Rewards (MoR) to synergize the RL training on more than 1000 tasks simultaneously. Through integrated innovations in algorithms, data, and training systems, Intern-S1 achieved top-tier performance in online RL training. On comprehensive evaluation benchmarks, Intern-S1 demonstrates competitive performance on general reasoning tasks among open-source models and significantly outperforms open-source models in scientific domains, surpassing closed-source state-of-the-art models in professional tasks, such as molecular synthesis planning, reaction condition prediction, predicting thermodynamic stabilities for crystals. Our models are available at https://huggingface.co/internlm/Intern-S1.

cs.LG↗

arXiv2025

Chem3DLLM: 3D Multimodal Large Language Models for Chemistry

In the real world, a molecule is a 3D geometric structure. Compared to 1D SMILES sequences and 2D molecular graphs, 3D molecules represent the most informative molecular modality. Despite the rapid progress of autoregressive-based language models, they cannot handle the generation of 3D molecular conformation due to several challenges: 1) 3D molecular structures are incompatible with LLMs' discrete token space, 2) integrating heterogeneous inputs like proteins, ligands, and text remains difficult within a unified model, and 3) LLMs lack essential scientific priors, hindering the enforcement of physical and chemical constraints during generation. To tackle these issues, we present Chem3DLLM, a unified protein-conditioned multimodal large language model. Our approach designs a novel reversible text encoding for 3D molecular structures using run-length compression, achieving 3x size reduction while preserving complete structural information. This enables seamless integration of molecular geometry with protein pocket features in a single LLM architecture. We employ reinforcement learning with stability-based rewards to optimize chemical validity and incorporate a lightweight protein embedding projector for end-to-end training. Experimental results on structure-based drug design demonstrate state-of-the-art performance with a Vina score of -7.21, validating our unified multimodal approach for practical drug discovery applications.

cs.CE↗

arXiv2025

Iterative Pretraining Framework for Interatomic Potentials

Machine learning interatomic potentials (MLIPs) enable efficient molecular dynamics (MD) simulations with ab initio accuracy and have been applied across various domains in physical science. However, their performance often relies on large-scale labeled training data. While existing pretraining strategies can improve model performance, they often suffer from a mismatch between the objectives of pretraining and downstream tasks or rely on extensive labeled datasets and increasingly complex architectures to achieve broad generalization. To address these challenges, we propose Iterative Pretraining for Interatomic Potentials (IPIP), a framework designed to iteratively improve the predictive performance of MLIP models. IPIP incorporates a forgetting mechanism to prevent iterative training from converging to suboptimal local minima. Unlike general-purpose foundation models, which frequently underperform on specialized tasks due to a trade-off between generality and system-specific accuracy, IPIP achieves higher accuracy and efficiency using lightweight architectures. Compared to general-purpose force fields, this approach achieves over 80% reduction in prediction error and up to 4x speedup in the challenging Mo-S-O system, enabling fast and accurate simulations.

physics.comp-ph↗

arXiv2025

PAC Off-Policy Prediction of Contextual Bandits

This paper investigates off-policy evaluation in contextual bandits, aiming to quantify the performance of a target policy using data collected under a different and potentially unknown behavior policy. Recently, methods based on conformal prediction have been developed to construct reliable prediction intervals that guarantee marginal coverage in finite samples, making them particularly suited for safety-critical applications. To further achieve coverage conditional on a given offline data set, we propose a novel algorithm that constructs probably approximately correct prediction intervals. Our method builds upon a PAC-valid conformal prediction framework, and we strengthen its theoretical guarantees by establishing PAC-type bounds on coverage. We analyze both finite-sample and asymptotic properties of the proposed method, and compare its empirical performance with existing methods in simulations.

stat.ML↗

arXiv2025

TrialBench: Multi-Modal Artificial Intelligence-Ready Clinical Trial Datasets

Clinical trials are pivotal for developing new medical treatments but typically carry risks such as patient mortality and enrollment failure that waste immense efforts spanning over a decade. Applying artificial intelligence (AI) to predict key events in clinical trials holds great potential for providing insights to guide trial designs. However, complex data collection and question definition requiring medical expertise have hindered the involvement of AI thus far. This paper tackles these challenges by presenting a comprehensive suite of 23 meticulously curated AI-ready datasets covering multi-modal input features and 8 crucial prediction challenges in clinical trial design, encompassing prediction of trial duration, patient dropout rate, serious adverse event, mortality rate, trial approval outcome, trial failure reason, drug dose finding, design of eligibility criteria. Furthermore, we provide basic validation methods for each task to ensure the datasets' usability and reliability. We anticipate that the availability of such open-access datasets will catalyze the development of advanced AI approaches for clinical trial design, ultimately advancing clinical trial research and accelerating medical solution development.

cs.LG↗

arXiv2025

CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning

Large language models (LLMs) have recently demonstrated promising capabilities in chemistry tasks while still facing challenges due to outdated pretraining knowledge and the difficulty of incorporating specialized chemical expertise. To address these issues, we propose an LLM-based agent that synergistically integrates 137 external chemical tools created ranging from basic information retrieval to complex reaction predictions, and a dataset curation pipeline to generate the dataset ChemToolBench that facilitates both effective tool selection and precise parameter filling during fine-tuning and evaluation. We introduce a Hierarchical Evolutionary Monte Carlo Tree Search (HE-MCTS) framework, enabling independent optimization of tool planning and execution. By leveraging self-generated data, our approach supports step-level fine-tuning (FT) of the policy model and training task-adaptive PRM and ORM that surpass GPT-4o. Experimental evaluations demonstrate that our approach significantly improves performance in Chemistry QA and discovery tasks, offering a robust solution to integrate specialized tools with LLMs for advanced chemical applications. All datasets and code are available at https://github.com/AI4Chem/ChemistryAgent .

cs.LG↗

arXiv2025

SELT: Self-Evaluation Tree Search for LLMs with Task Decomposition

While Large Language Models (LLMs) have achieved remarkable success in a wide range of applications, their performance often degrades in complex reasoning tasks. In this work, we introduce SELT (Self-Evaluation LLM Tree Search), a novel framework that leverages a modified Monte Carlo Tree Search (MCTS) to enhance LLM reasoning without relying on external reward models. By redefining the Upper Confidence Bound scoring to align with intrinsic self-evaluation capabilities of LLMs and decomposing the inference process into atomic subtasks augmented with semantic clustering at each node, SELT effectively balances exploration and exploitation, reduces redundant reasoning paths, and mitigates hallucination. We validate our approach on challenging benchmarks, including the knowledge-based MMLU and the Tool Learning dataset Seal-Tools, where SELT achieves significant improvements in answer accuracy and reasoning robustness compared to baseline methods. Notably, our framework operates without task-specific fine-tuning, demonstrating strong generalizability across diverse reasoning tasks. Relevant results and code are available at https://github.com/fairyshine/SELT .

cs.CL↗

arXiv2025

Control-R: Towards controllable test-time scaling

This paper target in addressing the challenges of underthinking and overthinking in long chain-of-thought (CoT) reasoning for Large Reasoning Models (LRMs) by introducing Reasoning Control Fields (RCF)--a novel test-time approach that injects structured control signals to guide reasoning from a tree search perspective. RCF enables models to adjust reasoning effort according to given control conditions when solving complex tasks. Additionally, we present the Control-R-4K dataset, which consists of challenging problems annotated with detailed reasoning processes and corresponding control fields. To further enhance reasoning control, we propose a Conditional Distillation Finetuning (CDF) method, which trains model--particularly Control-R-32B--to effectively adjust reasoning effort during test time. Experimental results on benchmarks such as AIME2024 and MATH500 demonstrate that our approach achieves state-of-the-art performance at the 32B scale while enabling a controllable Long CoT reasoning process (L-CoT). Overall, this work introduces an effective paradigm for controllable test-time scaling reasoning.

cs.AI↗

arXiv2025

DCO$^+$ and DCN 1-0 survey toward a sample of Planck cold clumps

Deuterated molecules can be used to study the physical conditions and the astro-chemical evolution of molecular clouds. large-sample surveys for deuterated molecules are needed to understand the enhancement of deuterated molecules from diffuse molecular gas to cold cores. A single-pointing survey toward the 559 Planck cold clumps of the Early Cold Core Catalogue (ECC) has been conducted using the Arizona Radio Observatory 12-meter telescope, focusing on the $J$=1-0 transitions of DCO$^+$ and DCN. The survey included observations of 309 cores for DCO$^+$ and DCN 1-0 simultaneously, followed by 71 of these cores where DCO$^+$ 1-0 was detected for H$^{13}$CO$^+$ and H$^{13}$CN 1-0 simultaneously, aiming to determine the deuterated fraction ($D_{\rm frac}$). Additionally, 250 cores were observed for DCO$^+$, DCN, H$^{13}$CO$^+$ and H$^{13}$CN 1-0 simultaneously. Among the 309 sources, DCO$^+$ and DCN 1-0 were detected in 79 and 11 sources, with a detection rates of 25.6 % and 3.6 % respectively. In the 250 sources observed for all four species, DCO$^+$, DCN, H$^{13}$CO$^+$ and H$^{13}$CN 1-0 were detected in 58, 9, 57 and 13 sources, with a detection rate of 23.2 %, 3.6 %, 22.8 % and 5.2 % respectively. The $D_{\rm frac}$(HCO$^+$) values in 112 sources range from 0.89 % to 7.4 % with a median value of 3.1 %, while $D_{\rm frac}$(HCN) values in 11 sources range from 1.5 % to 5.5 % with a median value of 2.3 %. The line widths of DCO$^+$ and H$^{13}$CO$^+$ 1-0 detections are mostly within 1 km s$^{-1}$. The similarity in $D_{\rm frac}$ values between HCO$^+$ and HCN indicates that the higher detection rate of DCO$^+$ 1-0 compared with DCN 1-0 is due to the lower critical density of DCO$^+$ 1-0. We suggest that the enhancement of DCO$^+$ and DCN likely begins in the early diffuse stage of the molecular cloud, rather than during the cold core formation stage.

astro-ph.GA↗

arXiv2025

Evidential Deep Learning for Interatomic Potentials

Machine learning interatomic potentials (MLIPs) have been widely used to facilitate large-scale molecular simulations with accuracy comparable to ab initio methods. In practice, MLIP-based molecular simulations often encounter the issue of collapse due to reduced prediction accuracy for out-of-distribution (OOD) data. Addressing this issue requires enriching the training dataset through active learning, where uncertainty serves as a critical indicator for identifying and collecting OOD data. However, existing uncertainty quantification (UQ) methods tend to involve either expensive computations or compromise prediction accuracy. In this work, we introduce evidential deep learning for interatomic potentials (eIP) with a physics-inspired design. Our experiments indicate that eIP provides reliable UQ results without significant computational overhead or decreased prediction accuracy, consistently outperforming other UQ methods across a variety of datasets. Furthermore, we demonstrate the applications of eIP in exploring diverse atomic configurations, using examples including water and universal potentials. These results highlight the potential of eIP as a robust and efficient alternative for UQ in molecular simulations.

physics.comp-ph↗

arXiv2025

Large Language Models are In-Context Molecule Learners

Large Language Models (LLMs) have demonstrated exceptional performance in biochemical tasks, especially the molecule caption translation task, which aims to bridge the gap between molecules and natural language texts. However, previous methods in adapting LLMs to the molecule-caption translation task required extra domain-specific pre-training stages, suffered weak alignment between molecular and textual spaces, or imposed stringent demands on the scale of LLMs. To resolve the challenges, we propose In-Context Molecule Adaptation (ICMA), as a new paradigm allowing LLMs to learn the molecule-text alignment from context examples via In-Context Molecule Tuning. Specifically, ICMA incorporates the following three stages: Hybrid Context Retrieval, Post-retrieval Re-ranking, and In-context Molecule Tuning. Initially, Hybrid Context Retrieval utilizes BM25 Caption Retrieval and Molecule Graph Retrieval to retrieve similar informative context examples. Additionally, Post-retrieval Re-ranking is composed of Sequence Reversal and Random Walk selection to further improve the quality of retrieval results. Finally, In-Context Molecule Tuning unlocks the in-context learning and reasoning capability of LLMs with the retrieved examples and adapts the parameters of LLMs for better alignment between molecules and texts. Experimental results demonstrate that ICMA can empower LLMs to achieve state-of-the-art or comparable performance without extra training corpora and intricate structures, showing that LLMs are inherently in-context molecule learners.

cs.CL↗

arXiv2024

The deuterium fractionation of NH$_3$ in massive star-forming regions

Deuteration is sensitive to environmental conditions in star-forming regions. To investigate NH$_2$D chemistry, we compared the spatial distribution of ortho-NH$_2$D $1_{11}^s-1_{01}^a$, NH$_3$(1,1) and NH$_3$(2,2) in 12 late-stage massive star-forming regions. By averaging several pixels along the spatial slices of ortho-NH$_2$D $1_{11}^s-1_{01}^a$, we obtained the deuterium fractionation of NH$_3$. In seven targets, the deuterium fractionation of NH$_3$ shows a decreasing trend with increasing rotational temperature. This trend is less clear in the remaining five sources, likely due to limited spatial resolution. However, when considering all 12 sources together, the anticorrelation between NH$_3$ deuterium fractionation and rotational temperature becomes less significant, suggesting that other physical parameters may influence the fractionation. Additionally, we found that the region of highest deuterium fractionation of NH$_3$ is offset from the NH$_3$ peak in each source, likely because the temperature is higher near the NH$_3$ peaks and NH$_2$D may be depleted from the gas phase as the molecular cloud core evolves, as well as the increased release of CO from grains into the gas phase.

astro-ph.GA↗

arXiv2024

LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

This paper presents an advanced mathematical problem-solving framework, LLaMA-Berry, for enhancing the mathematical reasoning ability of Large Language Models (LLMs). The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path and utilizes a pairwise reward model to evaluate different paths globally. By leveraging the self-critic and rewriting capabilities of LLMs, Self-Refine applied to MCTS (SR-MCTS) overcomes the inefficiencies and limitations of conventional step-wise and greedy search algorithms by fostering a more efficient exploration of solution spaces. Pairwise Preference Reward Model~(PPRM), inspired by Reinforcement Learning from Human Feedback (RLHF), is then used to model pairwise preferences between solutions, utilizing an Enhanced Borda Count (EBC) method to synthesize these preferences into a global ranking score to find better answers. This approach addresses the challenges of scoring variability and non-independent distributions in mathematical reasoning tasks. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability compared to existing methods like ToT and rStar, particularly in complex Olympiad-level benchmarks, including GPQA, AIME24 and AMC23.

cs.AI↗

arXiv2024

A novel ephemeris model for Martian moons incorporating their free rotation

High precision ephemerides not only support space missions, but can also be used to study the origin and future of celestial bodies. In this paper, a coupled orbit rotation dynamics model that fully takes into account the rotation of the Martian moons is developed. Phobos and Deimos rotation are firstly described by Eulerian rotational equations, and integrated simultaneously with the orbital motion equations. Orbital and orientational parameters of Mars satellites were simultaneously obtained by numerical integration for the first time. In order to compare the differences between our newly developed model and the one now used in the ephemerides, we first reproduced and simulated the current model using our own parameters, and then fit it to the IMCCE ephemerides using least square procedures. The adjustment test simulations show Phobos and Deimos orbital differences between the refined model and the current model is no more than 300 meters and 125 meters, respectively. The orientation parameters are confirmed and the results are in good agreement with the IAU results. Moreover, we simulated two perturbations (main asteroids and mutual torques) which were not included in our refined model, and find that their effects on the orbits are completely negligible. As for the effect on rotation, we propose to take care of the role of mutual attraction in future models.

astro-ph.EP↗

arXiv2024

Analysis of the Effect of Tilted Corner Cube Reflector Arrays on Lunar Laser Ranging

This paper primarily investigates the effect of the tilt of corner cube reflector (CCR) arrays on lunar laser ranging (LLR). A mathematical model was established to study the random errors caused by the tilt of the CCR arrays. The study found that, ideally, when the laser ranging pulse width is 10 picoseconds or less, it is possible to distinguish from which specific corner cubes within the CCR array each peak in the echo signal originates. Consequently, partial data from the echo can be extracted for signal processing, significantly reducing random errors and improving the single-shot precision of LLR. The distance obtained by extracting part of the echo can be reduced to the center position of the array, thereby providing multiple higher-precision ranging results from each measurement. This not only improves the precision of LLR but also increases the data volume. A simulation experiment based on the 1.2 m laser ranging system at Yunnan Observatories was conducted. By extracting one peak for signal processing, the single-shot precision improved from 32.24 mm to 2.52 mm, validating the theoretical analysis results. Finally, an experimental laser ranging system based on a 53 cm binocular telescope system was established for ground experiments. The experimental results indicated that the echo signal could identify the tilt state of the CCR array. By extracting the peak returned by the central CCR for signal processing, the ranging precision was greatly improved. Through theoretical analyses, simulation experiments, and ground experiments, a solution to reduce the random errors caused by the tilt of the CCR array was provided. This offers an approach to enhance the single-shot precision of future LLR and provides a reference for upgrading ground-based equipment at future laser ranging stations.

astro-ph.IM↗

arXiv2024

Spatial distribution of C4H and c-C3H2 in cold molecular cores

C$_4$H and $c$-C$_3$H$_2$, as unsaturated hydrocarbon molecules, are important for forming large organic molecules in the interstellar medium. We present mapping observations of C$_4$H ($N$=9$-8$) lines, $c$-C$_3$H$_2$ ($J_{Ka,Kb}$=2$_{1,2}$-1$_{0,1}$) %at 85338.894 MHz and H$^{13}$CO$^+$ ($J$=1$-0$) %at 86754.2884 MHz toward 19 nearby cold molecular cores in the Milky Way with the IRAM 30m telescope. C$_4$H 9--8 was detected in 13 sources, while $c$-C$_3$H$_2$ was detected in 18 sources. The widely existing C$_4$H and $c$-C$_3$H$_2$ molecules in cold cores provide material to form large organic molecules. Different spatial distributions between C$_4$H 9--8 and $c$-C$_3$H$_2$ 2--1 were found. The relative abundances of these three molecules were obtained under the assumption of local thermodynamic equilibrium conditions with a fixed excitation temperature. The abundance ratio of C$_4$H to $c$-C$_3$H$_2$ ranged from 0.34 $\pm$ 0.09 in G032.93+02 to 4.65 $\pm$ 0.50 in G008.67+22. A weak correlation between C$_4$H/H$^{13}$CO$^+$ and $c$-C$_3$H$_2$/H$^{13}$CO$^+$ abundance ratios was found, with a correlation coefficient of 0.46, which indicates that there is no tight astrochemical connection between C$_4$H and $c$-C$_3$H$_2$ molecules.

astro-ph.GA↗

arXiv2024

Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B

This paper introduces the MCT Self-Refine (MCTSr) algorithm, an innovative integration of Large Language Models (LLMs) with Monte Carlo Tree Search (MCTS), designed to enhance performance in complex mathematical reasoning tasks. Addressing the challenges of accuracy and reliability in LLMs, particularly in strategic and mathematical reasoning, MCTSr leverages systematic exploration and heuristic self-refine mechanisms to improve decision-making frameworks within LLMs. The algorithm constructs a Monte Carlo search tree through iterative processes of Selection, self-refine, self-evaluation, and Backpropagation, utilizing an improved Upper Confidence Bound (UCB) formula to optimize the exploration-exploitation balance. Extensive experiments demonstrate MCTSr's efficacy in solving Olympiad-level mathematical problems, significantly improving success rates across multiple datasets, including GSM8K, GSM Hard, MATH, and Olympiad-level benchmarks, including Math Odyssey, AIME, and OlympiadBench. The study advances the application of LLMs in complex reasoning tasks and sets a foundation for future AI integration, enhancing decision-making accuracy and reliability in LLM-driven applications.

cs.AI↗