arXiv subjects

Lijun Liu

Publications and source records attributed to Lijun Liu.

At least 19 recordsLinked to original sources

arXiv2026

MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking

We present MagicSelector, a joint optimization framework integrating Counterfactual task decomposition, Progressive reranking, and Dynamic Top-K, designed to address the fundamental challenges of tool retrieval in agents. MagicSelector is a specialized framework capable of translating ambiguous user instructions into executable atomic subtasks and guiding high-precision tool retrieval, effectively mitigating redundant noise and severe context distraction in out-of-domain (OOD) scenarios. We empower MagicSelector with these capabilities through three key contributions: (1) a preference-guided counterfactual task decomposition mechanism that utilizes a counterfactual reward to quantify the marginal causal gain of decomposition on retrieval ranking, effectively imposing fine-grained structural supervision on logical coherence; (2) a progressive tool reranking method driven by self-distillation hard negative mining, which optimizes both point-wise and list-wise relevance to enhance fine-grained discrimination among highly similar tools; and (3) a dual semantic boundary-aware dynamic Top-K strategy that adaptively monitors reranking score cliffs and inter-tool semantic shifts to dynamically truncate the candidate list, maximizing relevant tool recall while filtering long-tail noise. Evaluated on MTDTool, the first task decomposition benchmark we constructed tailored for mobile multi-turn interactions with process-level annotations, MagicSelector yields promising performance. Extensive experiments demonstrate that MagicSelector significantly outperforms state-of-the-art methods in terms of tool retrieval accuracy, OOD generalization capability, and overall token efficiency, thereby demonstrating the effectiveness of our proposed framework.

cs.IR↗

arXiv2026

Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care

Baichuan-M4 is Baichuan Intelligence's clinical-grade medical large model, designed for continuous care rather than single-turn medical question answering. It is built as a coordinated medical agent system around three pillars: Baichuan-Harness, a unified runtime that keeps reinforcement-learning training and real-world deployment consistent while enforcing action constraints, tool use, long-term patient memory, and multi-agent coordination; a core reasoning model trained with a continuous-care reinforcement-learning framework that integrates span-level reward modeling (SPAR++), reasoning-path compression, curriculum learning, and stabilized policy optimization; and a clinical tool layer for patient-memory management, authoritative evidence-based retrieval, and multimodal medical perception across documents, X-rays, and dermatology. On a cross-dimensional medical evaluation suite, Baichuan-M4 attains leading results in static medical knowledge and safety, dynamic OSCE-style consultation, long-context clinical memory, evidence-based retrieval, medical document OCR, and multimodal image understanding, while lowering the hallucination rate to 3.3%.

cs.AI↗

arXiv2026

Intensity-guided pose-free multiview fusion for single photon sensing

Single-photon light detection and ranging (LiDAR) extends active three-dimensional sensing at the fundamental level and has found applications in extreme environments involving long-range operation, low-reflectance targets, and adverse visibility. However, the acquired measurements often give rise to single-photon point clouds that are sparse, spatially non-uniform, and corrupted by outliers and depth distortions, making multi-view registration challenging especially when sensor poses are not accurately known. In this work, we present a geometry-intensity coupled registration framework (GIC-Reg) of pose-free multi-view fusion for single-photon sensing. It is established by combining physical-aware preprocessing, joint geometry-intensity grid feature aggregation, global matching, and local ambiguity disambiguation to estimate inter-view rigid transformations and hence to construct a globally consistent reconstruction. On the synthetic benchmark, it admits the lowest relative rotation error (RRE), relative translation error, and root mean square error across all background-noise and dropout rates, in comparison to baselines. Notably, under the most degraded dropout, it reduces the RRE from $13.167^\circ$ to $8.459^\circ$ compared with the learning-based baseline. Furthermore, experimental results on real multi-view data acquired at about 80~m show that it achieves more reliable global orientation and local alignment. Our results show that photon intensity provides an effective physical cue for stabilizing multiview registration in single-photon point cloud, and thus our work aids significant progress in exploring practical utility of single-photon sensing.

physics.optics↗

arXiv2026

Co-Diffusion: An Affinity-Aware Two-Stage Latent Diffusion Framework for Generalizable Drug-Target Affinity Prediction

Predicting drug-target affinity is fundamental to virtual screening and lead optimization. However, existing deep models often suffer from representation collapse in stringent cold-start regimes, where the scarcity of labels and domain shifts prevent the learning of transferable pharmacophores and binding motifs. In this paper, we propose Co-Diffusion, a novel affinity-aware framework that redefines DTA prediction as a constrained latent denoising process to enhance generalization. Co-Diffusion employs a two-stage paradigm: Stage I establishes an affinity-steered latent manifold by aligning drug and target embeddings under an explicit supervised objective, ensuring that the latent space reflects the intrinsic binding landscape. Stage II introduces modality-specific latent diffusion as a stochastic perturb-and-denoise regularizer, forcing the model to recover consistent affinity semantics from noisy structural representations. This approach effectively mitigates the reconstruction-regression conflict common in generative DTA models. Theoretically, we show that Co-Diffusion maximizes a variational lower bound on the joint likelihood of drug structures, protein sequences, and binding strength. Extensive experiments across multiple benchmarks demonstrate that Co-Diffusion significantly outperforms state-of-the-art baselines, particularly yielding superior zero-shot generalization on unseen molecular scaffolds and novel protein families-paving a robust path for in silico drug prioritization in unexplored chemical spaces.

stat.ML↗

arXiv2026

CORE-Acu: Structured Reasoning Traces and Knowledge Graph Safety Verification for Acupuncture Clinical Decision Support

Large language models (LLMs) show significant potential for clinical decision support (CDS), yet their black-box nature -- characterized by untraceable reasoning and probabilistic hallucinations -- poses severe challenges in acupuncture, a field demanding rigorous interpretability and safety. To address this, we propose CORE-Acu, a neuro-symbolic framework for acupuncture clinical decision support that integrates Structured Chain-of-Thought (S-CoT) with knowledge graph (KG) safety verification. First, we construct the first acupuncture Structured Reasoning Trace dataset and a schema-constrained fine-tuning framework. By enforcing an explicit causal chain from pattern identification to treatment principles, treatment plans, and acupoint selection, we transform implicit Traditional Chinese Medicine (TCM) reasoning into interpretable generation constraints, mitigating the opacity of LLM-based CDS. Furthermore, we construct a TCM safety knowledge graph and establish a ``Generate--Verify--Revise'' closed-loop inference system based on a Symbolic Veto Mechanism, employing deterministic rules to intercept hallucinations and enforce hard safety boundaries. Finally, we introduce the Lexicon-Matched Entity-Reweighted Loss (LMERL), which corrects terminology drift caused by the frequency--importance mismatch in general optimization by adaptively amplifying gradient contributions of high-risk entities during fine-tuning. Experiments on 1,000 held-out cases demonstrate CORE-Acu's superior entity fidelity and reasoning quality. Crucially, CORE-Acu achieved 0/1,000 observed safety violations (95\% CI: 0--0.37\%), whereas GPT-4o exhibited an 8.5\% violation rate under identical rules. These results establish CORE-Acu as a robust neuro-symbolic framework for acupuncture clinical decision support, guaranteeing both reasoning auditability and strict safety compliance.

cs.AI↗

arXiv2026

SkinFlow: Efficient Information Transmission for Open Dermatological Diagnosis via Dynamic Visual Encoding and Staged RL

General-purpose Large Vision-Language Models (LVLMs), despite their massive scale, often falter in dermatology due to "diffuse attention" - the inability to disentangle subtle pathological lesions from background noise. In this paper, we challenge the assumption that parameter scaling is the only path to medical precision. We introduce SkinFlow, a framework that treats diagnosis as an optimization of visual information transmission efficiency. Our approach utilizes a Virtual-Width Dynamic Vision Encoder (DVE) to "unfold" complex pathological manifolds without physical parameter expansion, coupled with a two-stage Reinforcement Learning strategy. This strategy sequentially aligns explicit medical descriptions (Stage I) and reconstructs implicit diagnostic textures (Stage II) within a constrained semantic space. Furthermore, we propose a clinically grounded evaluation protocol that prioritizes diagnostic safety and hierarchical relevance over rigid label matching. Empirical results are compelling: our 7B model establishes a new state-of-the-art on the Fitzpatrick17k benchmark, achieving a +12.06% gain in Top-1 accuracy and a +28.57% boost in Top-6 accuracy over the massive general-purpose models (e.g., Qwen3VL-235B and GPT-5.2). These findings demonstrate that optimizing geometric capacity and information flow yields superior diagnostic reasoning compared to raw parameter scaling.

cs.CV↗

arXiv2025

Deep Learning-Enabled Supercritical Flame Simulation at Detailed Chemistry and Real-Fluid Accuracy Towards Trillion-Cell Scale

For decades, supercritical flame simulations incorporating detailed chemistry and real-fluid transport have been limited to millions of cells, constraining the resolved spatial and temporal scales of the physical system. We optimize the supercritical flame simulation software DeepFlame -- which incorporates deep neural networks while retaining the real-fluid mechanical and chemical accuracy -- from three perspectives: parallel computing, computational efficiency, and I/O performance. Our highly optimized DeepFlame achieves supercritical liquid oxygen/methane (LOX/\ce{CH4}) turbulent combustion simulation of up to 618 and 154 billion cells with unprecedented time-to-solution, attaining 439/1186 and 187/316 PFlop/s (32.3\%/21.8\% and 37.4\%/31.8\% of the peak) in FP32/mixed-FP16 precision on Sunway (98,304 nodes) and Fugaku (73,728 nodes) supercomputers, respectively. This computational capability surpasses existing capacities by three orders of magnitude, enabling the first practical simulation of rocket engine combustion with >100 LOX/\ce{CH4} injectors. This breakthrough establishes high-fidelity supercritical flame modeling as a critical design tool for next-generation rocket propulsion and ultra-high energy density systems.

cs.DC↗

arXiv2025

Point upsampling networks for single-photon sensing

Single-photon sensing has generated great interest as a prominent technique of long-distance and ultra-sensitive imaging, however, it tends to yield sparse and spatially biased point clouds, thus limiting its practical utility. In this work, we propose using point upsampling networks to increase point density and reduce spatial distortion in single-photon point cloud. Particularly, our network is built on the state space model which integrates a multi-path scanning mechanism to enrich spatial context, a bidirectional Mamba backbone to capture global geometry and local details, and an adaptive upsample shift module to correct offset-induced distortions. Extensive experiments are implemented on commonly-used datasets to confirm its high reconstruction accuracy and strong robustness to the distortion noise, and also on real-world data to demonstrate that our model is able to generate visually consistent, detail-preserving, and noise suppressed point clouds. Our work is the first to establish the upsampling framework for single-photon sensing, and hence opens a new avenue for single-photon sensing and its practical applications in the downstreaming tasks.

physics.optics↗

arXiv2025

Efficient Medical VIE via Reinforcement Learning

Visual Information Extraction (VIE) converts unstructured document images into structured formats like JSON, critical for medical applications such as report analysis and online consultations. Traditional methods rely on OCR and language models, while end-to-end multimodal models offer direct JSON generation. However, domain-specific schemas and high annotation costs limit their effectiveness in medical VIE. We base our approach on the Reinforcement Learning with Verifiable Rewards (RLVR) framework to address these challenges using only 100 annotated samples. Our approach ensures dataset diversity, a balanced precision-recall reward mechanism to reduce hallucinations and improve field coverage, and innovative sampling strategies to enhance reasoning capabilities. Fine-tuning Qwen2.5-VL-7B with our RLVR method, we achieve state-of-the-art performance on medical VIE tasks, significantly improving F1, precision, and recall. While our models excel on tasks similar to medical datasets, performance drops on dissimilar tasks, highlighting the need for domain-specific optimization. Case studies further demonstrate the value of reasoning during training and inference for VIE.

cs.CL↗

arXiv2025

Scaling Neural-Network-Based Molecular Dynamics with Long-Range Electrostatic Interactions to 51 Nanoseconds per Day

Neural network-based molecular dynamics (NNMD) simulations incorporating long-range electrostatic interactions have significantly extended the applicability to heterogeneous and ionic systems, enabling effective modeling critical physical phenomena such as protein folding and dipolar surface and maintaining ab initio accuracy. However, neural network inference and long-range force computation remain the major bottlenecks, severely limiting simulation speed. In this paper, we target DPLR, a state-of-the-art NNMD package that supports long-range electrostatics, and propose a set of comprehensive optimizations to enhance computational efficiency. We introduce (1) a hardware-offloaded FFT method to reduce the communication overhead; (2) an overlapping strategy that hides long-range force computations using a single core per node, and (3) a ring-based load balancing method that enables atom-level task evenly redistribution with minimal communication overhead. Experimental results on the Fugaku supercomputer show that our work achieves a 37x performance improvement, reaching a maximum simulation speed of 51 ns/day.

cs.DC↗

arXiv2025

The boundary of Kirkwood-Dirac quasiprobability

The Kirkwood-Dirac (KD) quasiprobability describes measurement statistics of joint quantum observables, and has generated great interest as prominent indicators of non-classical features in various quantum information processing tasks. It relaxes the Kolmogorov axioms of probability by allowing for negative and even imaginary probabilities, and thus incorporates the classical probability theory as its inner boundary. In this work, we introduce the postquantum quasiprobability under mild assumptions to provide an outer boundary for KD quasiprobability. Specifically, we present qualitative and quantitative evidence to show that the classical, KD, and postquantum quasiprobabilities form a strict hierarchy, in the sense that joint probability distributions are a strict subset of KD quasiprobability distributions that are a strict subset of postquantum ones. Surprisingly, we are able to derive some nontrivial bounds valid for both classical probability and KD quasiprobability, and even valid for the KD quasiprobability generated by an arbitrary number of measurements. Finally, other interesting bounds are obtained, and their implications are noted. Our work solves the fundamental problems of what and how to bound the KD quasiprobability, and hence provides a deeper understanding of utilizing it in quantum information processing.

quant-ph↗

arXiv2025

Assess Space-Based Solar Power in European-Scale Power System Decarbonization

Meeting net-zero targets remains formidable as terrestrial renewables grapple with intermittency and regional variability. Here, we integrate space-based solar power (SBSP) -- a potential near-constant, orbital solar technology -- into a high-resolution, Europe-wide capacity-expansion and dispatch model to quantify its contribution under net-zero constraints. We examine two advanced SBSP designs: (1) a near-baseload, low Technology Readiness Level (TRL) concept (heliostat-based Representative Design RD1) and (2) a partially intermittent, higher-TRL concept (planar-based RD2), both drawing on NASA's 2050 cost and performance projections. Our results show that RD1 can reduce total system costs by 7--15%, displace up to 80% of intermittent wind and solar, and cut battery usage by over 70%, if it meets its forecast cost reductions -- though long-duration storage (e.g., hydrogen) remains essential for seasonal balancing. By contrast, RD2 is economically unattractive at its projected 2050 costs. Through extensive sensitivity analyses, we identify cost thresholds at which SBSP shifts from cost-prohibitive to complementary and ultimately to a dominant baseload technology. Specifically, RD1 becomes complementary at roughly 14x and dominant at 9x the 2050 solar PV capital cost, benefiting from its continuous power generation. Meanwhile, RD2 must achieve even lower cost levels (9x to be complementary and 6x to dominate) and would rely on short-duration storage to mitigate its partial intermittency. These findings provide quantified techno-economic benchmarks and reveal alternative net-zero pathways, offering critical guidance for policymakers and industry stakeholders seeking large-scale, centrally coordinated renewable solutions with non- or low-intermittency.

physics.soc-ph↗

arXiv2025

Baichuan-Omni-1.5 Technical Report

We introduce Baichuan-Omni-1.5, an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities. To achieve fluent and high-quality interaction across modalities without compromising the capabilities of any modality, we prioritized optimizing three key aspects. First, we establish a comprehensive data cleaning and synthesis pipeline for multimodal data, obtaining about 500B high-quality data (text, audio, and vision). Second, an audio-tokenizer (Baichuan-Audio-Tokenizer) has been designed to capture both semantic and acoustic information from audio, enabling seamless integration and enhanced compatibility with MLLM. Lastly, we designed a multi-stage training strategy that progressively integrates multimodal alignment and multitask fine-tuning, ensuring effective synergy across all modalities. Baichuan-Omni-1.5 leads contemporary models (including GPT4o-mini and MiniCPM-o 2.6) in terms of comprehensive omni-modal capabilities. Notably, it achieves results comparable to leading models such as Qwen2-VL-72B across various multimodal medical benchmarks.

cs.CL↗

arXiv2025

Large Scale Finite-Temperature Real-time Time Dependent Density Functional Theory Calculation with Hybrid Functional on ARM and GPU Systems

Ultra-fast electronic phenomena originating from finite temperature, such as nonlinear optical excitation, can be simulated with high fidelity via real-time time dependent density functional theory (rt-TDDFT) calculations with hybrid functional. However, previous rt-TDDFT simulations of real materials using the optimal gauge--known as the parallel transport gauge--have been limited to low-temperature systems with band gaps. In this paper, we introduce the parallel transport-implicit midpoint (PT-IM) method, which significantly accelerates finite-temperature rt-TDDFT calculations of real materials with hybrid function. We first implement PT-IM with hybrid functional in our plane wave code PWDFT, and optimized it on both GPU and ARM platforms to build a solid baseline code. Next, we propose a diagonalization method to reduce computation and communication complexity, and then, we employ adaptively compressed exchange (ACE) method to reduce the frequency of the most expensive Fock exchange operator. Finally, we adopt the ring\_based method and the shared memory mechanism to overlap computation and communication and alleviate memory consumption respectively. Numerical results show that our optimized code can reach 3072 atoms for rt-TDDFT simulation with hybrid functional at finite temperature on 192 computing nodes, the time-to-solution for one time step is 429.3s, which is 41.4 times faster compared to the baseline.

cond-mat.mtrl-sci↗

arXiv2024

Scaling Molecular Dynamics with ab initio Accuracy to 149 Nanoseconds per Day

Physical phenomena such as chemical reactions, bond breaking, and phase transition require molecular dynamics (MD) simulation with ab initio accuracy ranging from milliseconds to microseconds. However, previous state-of-the-art neural network based MD packages such as DeePMD-kit can only reach 4.7 nanoseconds per day on the Fugaku supercomputer. In this paper, we present a novel node-based parallelization scheme to reduce communication by 81%, then optimize the computationally intensive kernels with sve-gemm and mixed precision. Finally, we implement intra-node load balance to further improve the scalability. Numerical results on the Fugaku supercomputer show that our work has significantly improved the time-to-solution of the DeePMD-kit by a factor of 31.7x, reaching 149 nanoseconds per day on 12,000 computing nodes. This work has opened the door for millisecond simulation with ab initio accuracy within one week for the first time.

cs.DC↗

arXiv2024

The polygon relation and subadditivity of entropic measures for discrete and continuous multipartite entanglement

In a recent work [Ge {\it et al.}, arXiv: 2312. 17496 (2023)], we have derived the polygon relation of bipartite entanglement measures that is useful to reveal the entanglement properties of discrete, continuous, and even hybrid multipartite quantum systems. In this work, with the information-theoretical measures of Rényi and Tsallis entropies, we study the relationship between the polygon relation and the subadditivity of entropy. In particular, the entropy-polygon relations are derived for pure multi-qubit states and generalized to multi-mode Gaussian states, by utilizing the known results from the quantum marginal problem. Moreover, the equivalence between the polygon relation and subadditivity is established, in the sense that for all discrete or continuous multipartite states, the polygon relation holds if and only if the underlying entropy is subadditive. As byproduct, the subadditivity of Rényi and Tsallis entropies is proven for all bipartite Gaussian states. Finally, the difference between polygon relations and monogamy relations is clarified, and generalizations of our results are discussed. Our work provides a better understanding of the rich structure of multipartite states, and hence is expected to be helpful for the study of multipartite entanglement.

quant-ph↗

arXiv2024

Faithful geometric measures for genuine tripartite entanglement

We present a faithful geometric picture for genuine tripartite entanglement of discrete, continuous, and hybrid quantum systems. We first find that the triangle relation $\mathcal{E}^α_{i|jk}\leq \mathcal{E}^α_{j|ik}+\mathcal{E}^α_{k|ij}$ holds for all subadditive bipartite entanglement measure $\mathcal{E}$, all permutations under parties $i, j, k$, all $α\in [0, 1]$, and all pure tripartite states. It provides a geometric interpretation that bipartition entanglement, measured by $\mathcal{E}^α$, corresponds to the side of a triangle, of which the area with $α\in (0, 1)$ is nonzero if and only if the underlying state is genuinely entangled. Then, we rigorously prove the non-obtuse triangle area with $0<α\leq 1/2$ is a measure for genuine tripartite entanglement. Useful lower and upper bounds for these measures are obtained, and generalizations of our results are also presented. Finally, it is significantly strengthened for qubits that, given a set of subadditive and non-additive measures, some state is always found to violate the triangle relation for any $α>1$, and the triangle area is not a measure for any $α>1/2$. Hence, our results are expected to aid significant progress in studying both discrete and continuous multipartite entanglement.

quant-ph↗

arXiv2024

Efficient factored gradient descent algorithm for quantum state tomography

Reconstructing the state of quantum many-body systems is of fundamental importance in quantum information tasks, but extremely challenging due to the curse of dimensionality. In this work, we present an efficient quantum tomography protocol that combines the state-factored with eigenvalue mapping to address the rank-deficient issue and incorporates a momentum-accelerated gradient descent algorithm to speed up the optimization process. We implement extensive numerical experiments to demonstrate that our factored gradient descent algorithm efficiently mitigates the rank-deficient problem and admits orders of magnitude better tomography accuracy and faster convergence. We also find that our method can accomplish the full-state tomography of random 11-qubit mixed states within one minute.

quant-ph↗