Encheng Su

Zixian Su, Hongkai Zhang, Fan Gao et al.

Multimodal Large Language Models (MLLMs) have shown strong performance on public medical benchmarks, yet existing evaluations often remain weak proxies for clinical use, relying on isolated inputs and simplified recognition-style tasks. We introduce CardioLens, a leakage-resistant evaluation testbed for multi-sequence Cardiovascular Magnetic Resonance (CMR), constructed from private hospital archives through a rigorous report-to-QA construction and verification pipeline. CardioLens contains 473,896 slices and 13,494 verified QA pairs across 4D Cine, LGE, perfusion, and T2-weighted imaging, and evaluates three stages of CMR interpretation: image understanding, report generation, and disease diagnosis. Across 24 state-of-the-art MLLMs, CardioLens reveals a substantial clinical reality gap: models perform poorly overall, with performance degrading along the real CMR workflow. Confusion analysis further shows a category-collapse failure mode, where models default to frequent abnormal categories rather than distinguishing clinically distinct findings. To rule out MLLM-compatible input construction as the primary cause, we compare random, clinically motivated, and data-driven slice selection protocols under different slice budgets; performance changes only marginally, typically by about 1%. Explicit reasoning prompts also fail to rescue performance, often making models more conservative rather than improving visual evidence use. These results show that current MLLMs remain far from reliable CMR interpretation, where clinical decisions require integrating distributed evidence across sequences, views, and temporal phases. CardioLens provides a clinically grounded testbed for developing next-generation MLLMs toward real-world clinical deployment.

Yiheng Wang, Yixin Chen, Shuo Li et al.

We introduce SciEvalKit, a unified benchmarking toolkit designed to evaluate AI models for science across a broad range of scientific disciplines and task capabilities. Unlike general-purpose evaluation platforms, SciEvalKit focuses on the core competencies of scientific intelligence, including Scientific Multimodal Perception, Scientific Multimodal Reasoning, Scientific Multimodal Understanding, Scientific Symbolic Reasoning, Scientific Code Generation, Science Hypothesis Generation and Scientific Knowledge Understanding. It supports six major scientific domains, spanning from physics and chemistry to astronomy and materials science. SciEvalKit builds a foundation of expert-grade scientific benchmarks, curated from real-world, domain-specific datasets, ensuring that tasks reflect authentic scientific challenges. The toolkit features a flexible, extensible evaluation pipeline that enables batch evaluation across models and datasets, supports custom model and dataset integration, and provides transparent, reproducible, and comparable results. By bridging capability-based evaluation and disciplinary diversity, SciEvalKit offers a standardized yet customizable infrastructure to benchmark the next generation of scientific foundation models and intelligent agents. The toolkit is open-sourced and actively maintained to foster community-driven development and progress in AI4Science.

Pengze Li, Jiaquan Zhang, Yunbo Long et al.

Recovering analytical solutions of physical fields from visual observations is a fundamental yet underexplored capability for AI-assisted scientific reasoning. We study visual-to-symbolic analytical solution inference (ViSA) for two-dimensional linear steady-state fields: given field visualizations (and first-order derivatives) plus minimal auxiliary metadata, the model must output a single executable SymPy expression with fully instantiated numeric constants. We introduce ViSA-R2 and align it with a self-verifying, solution-centric chain-of-thought pipeline that follows a physicist-like pathway: structural pattern recognition solution-family (ansatz) hypothesis parameter derivation consistency verification. We also release ViSA-Bench, a VLM-ready synthetic benchmark covering 30 linear steady-state scenarios with verifiable analytical/symbolic annotations, and evaluate predictions by numerical accuracy, expression-structure similarity, and character-level accuracy. Using an 8B open-weight Qwen3-VL backbone, ViSA-R2 outperforms strong open-source baselines and the evaluated closed-source frontier VLMs under a standardized protocol.

Yizhou Wang, Chen Tang, Han Deng et al.

We present a scientific reasoning foundation model that aligns natural language with heterogeneous scientific representations. The model is pretrained on a 206B-token corpus spanning scientific text, pure sequences, and sequence-text pairs, then aligned via SFT on 40M instructions, annealed cold-start bootstrapping to elicit long-form chain-of-thought, and reinforcement learning with task-specific reward shaping, which instills deliberate scientific reasoning. It supports four capability families, covering up to 103 tasks across workflows: (i) faithful translation between text and scientific formats, (ii) text/knowledge extraction, (iii) property prediction, (iv) property classification, (v) unconditional and conditional sequence generation and design. Compared with specialist systems, our approach broadens instruction coverage, improves cross-domain generalization, and enhances fidelity. We detail data curation and training and show that cross-discipline learning strengthens transfer and downstream reliability. The model, instruct tuning datasets and the evaluation code are open-sourced at https://huggingface.co/SciReason and https://github.com/open-sciencelab/SciReason.

Encheng Su, Jianyu Wu, Chen Tang et al.

As large language models (LLMs) transition from general knowledge retrieval to complex scientific discovery, their evaluation standards must also incorporate the rigorous norms of scientific inquiry. Existing benchmarks exhibit a critical blind spot: general instruction-following metrics focus on superficial formatting, while domain-specific scientific benchmarks assess only final-answer correctness, often rewarding models that arrive at the right result with the wrong reasons. To address this gap, we introduce scientific instruction following: the capability to solve problems while strictly adhering to the constraints that establish scientific validity. Specifically, we introduce SciIF, a multi-discipline benchmark that evaluates this capability by pairing university-level problems with a fixed catalog of constraints across three pillars: scientific conditions (e.g., boundary checks and assumptions), semantic stability (e.g., unit and symbol conventions), and specific processes(e.g., required numerical methods). Uniquely, SciIF emphasizes auditability, requiring models to provide explicit evidence of constraint satisfaction rather than implicit compliance. By measuring both solution correctness and multi-constraint adherence, SciIF enables finegrained diagnosis of compositional reasoning failures, ensuring that LLMs can function as reliable agents within the strict logical frameworks of science.

Chen Tang, Xinzhu Ma, Encheng Su et al.

Traditional spatiotemporal models generally rely on task-specific architectures, which limit their generalizability and scalability across diverse tasks due to domain-specific design requirements. In this paper, we introduce \textbf{UniSTD}, a unified Transformer-based framework for spatiotemporal modeling, which is inspired by advances in recent foundation models with the two-stage pretraining-then-adaption paradigm. Specifically, our work demonstrates that task-agnostic pretraining on 2D vision and vision-text datasets can build a generalizable model foundation for spatiotemporal learning, followed by specialized joint training on spatiotemporal datasets to enhance task-specific adaptability. To improve the learning capabilities across domains, our framework employs a rank-adaptive mixture-of-expert adaptation by using fractional interpolation to relax the discrete variables so that can be optimized in the continuous space. Additionally, we introduce a temporal module to incorporate temporal dynamics explicitly. We evaluate our approach on a large-scale dataset covering 10 tasks across 4 disciplines, demonstrating that a unified spatiotemporal model can achieve scalable, cross-task learning and support up to 10 tasks simultaneously within one model while reducing training costs in multi-domain applications. Code will be available at https://github.com/1hunters/UniSTD.

Encheng Su, Jinouwen Zhang, Jianyu Wu et al.

Long-horizon interactive agents often accumulate large trajectory histories yet still fail to answer questions about earlier events reliably. We argue that the main bottleneck is not context length alone, but the trajectory-to-answer interface of long-term memory. When histories are stored as plain-text chunks and queried with standard retrieval-augmented generation (RAG), systems often retrieve locally relevant but chain-incomplete evidence, especially for spatial, temporal, repeated-event, and multi-hop state questions. We propose S3MEM, a structured scene-event episodic memory framework for long-horizon interactive question answering (QA). S3MEM writes trajectories into structured memory units, retrieves evidence through anchor-sensitive retrieval, and exposes a compact token-budget-aware evidence interface for answer-time inference. In this sense, S3MEM is a structured evidence harness that converts agent trajectories into query-aligned support. We evaluate S3MEM on two internal headline environments (Crafter, Jericho) and two out-of-family environments (SciWorld, ALFWorld). Under a shared frozen answer-time protocol, S3MEM consistently outperforms Vanilla RAG across all four environments, surpasses Graph-NoReader on Crafter, Jericho, and ALFWorld, and matches it on SciWorld while using dramatically fewer evidence tokens. Three adapted recent baselines -- A-MEM-inspired, MemoryOS-adapted, and LightMem-adapted -- improve over Vanilla RAG in several settings, but none matches S3MEM's overall accuracy-efficiency frontier. Overall, the evidence supports a bounded conclusion: under the current frozen answer-time protocol, structured writing and anchor-sensitive evidence routing provide a stronger accuracy-efficiency frontier for long-horizon interactive QA than more generic memory interfaces.

Ming Hu, Chenglong Ma, Wei Li et al. · pku

Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research, yet their progress is shaped by the complex nature of scientific data. This survey presents a comprehensive, data-centric synthesis that reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate. We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge, emphasizing the multimodal, cross-scale, and domain-specific challenges that differentiate scientific corpora from general natural language processing datasets. We systematically review recent Sci-LLMs, from general-purpose foundations to specialized models across diverse scientific disciplines, alongside an extensive analysis of over 270 pre-/post-training datasets, showing why Sci-LLMs pose distinct demands -- heterogeneous, multi-scale, uncertainty-laden corpora that require representations preserving domain invariance and enabling cross-modal reasoning. On evaluation, we examine over 190 benchmark datasets and trace a shift from static exams toward process- and discovery-oriented assessments with advanced evaluation protocols. These data-centric analyses highlight persistent issues in scientific data development and discuss emerging solutions involving semi-automated annotation pipelines and expert validation. Finally, we outline a paradigm shift toward closed-loop systems where autonomous agents based on Sci-LLMs actively experiment, validate, and contribute to a living, evolving knowledge base. Collectively, this work provides a roadmap for building trustworthy, continually evolving artificial intelligence (AI) systems that function as a true partner in accelerating scientific discovery.

Lintao Wang, Encheng Su, Jiaqi Liu et al.

Physics problem-solving is a challenging domain for large AI models, requiring integration of conceptual understanding, mathematical reasoning, and interpretation of physical diagrams. Current evaluation methodologies show notable limitations in capturing the breadth and complexity of undergraduate-level physics, underscoring the need for more rigorous assessments. To this end, we present PhysUniBench, a large-scale multimodal benchmark designed to evaluate and improve the reasoning capabilities of multimodal large language models (MLLMs) specifically on undergraduate-level physics problems. PhysUniBench consists of 3,304 physics questions spanning 8 major sub-disciplines of physics, each accompanied by one visual diagrams. The benchmark includes both open-ended and multiple-choice questions, systematically curated and difficulty-rated through an iterative model-in-the-loop process. The benchmark's construction involved a rigorous multi-stage process, including multiple roll-outs, expert-level evaluation, automated filtering of easily solved problems, and a nuanced difficulty grading system with five levels. Through extensive experiments, we observe that current state-of-the-art models encounter substantial challenges in physics reasoning. For example, GPT-4o mini achieves only about 34.2% accuracy in the proposed PhysUniBench. These results highlight that current MLLMs struggle with advanced physics reasoning, especially on multi-step problems and those requiring precise diagram interpretation. By providing a broad and rigorous assessment tool, PhysUniBench aims to drive progress in AI for Science, encouraging the development of models with stronger physical reasoning, problem-solving skills, and multimodal understanding. The benchmark and evaluation scripts are available at https://prismax-team.github.io/PhysUniBenchmark/.

Songyan Xie, Jinghang Wen, Encheng Su et al.

Near-infrared (NIR) face recognition systems, which can operate effectively in low-light conditions or in the presence of makeup, exhibit vulnerabilities when subjected to physical adversarial attacks. To further demonstrate the potential risks in real-world applications, we design a novel, stealthy, and practical adversarial patch to attack NIR face recognition systems in a black-box setting. We achieved this by utilizing human-imperceptible infrared-absorbing ink to generate multiple patches with digitally optimized shapes and positions for infrared images. To address the optimization mismatch between digital and real-world NIR imaging, we develop a light reflection model for human skin to minimize pixel-level discrepancies by simulating NIR light reflection. Compared to state-of-the-art (SOTA) physical attacks on NIR face recognition systems, the experimental results show that our method improves the attack success rate in both digital and physical domains, particularly maintaining effectiveness across various face postures. Notably, the proposed approach outperforms SOTA methods, achieving an average attack success rate of 82.46% in the physical domain across different models, compared to 64.18% for existing methods. The artifact is available at https://anonymous.4open.science/r/Human-imperceptible-adversarial-patch-0703/.

Encheng Su, Hu Cao, Alois Knoll

Accurate segmentation of polyps and skin lesions is essential for diagnosing colorectal and skin cancers. While various segmentation methods for polyps and skin lesions using fully supervised deep learning techniques have been developed, the pixel-level annotation of medical images by doctors is both time-consuming and costly. Foundational vision models like the Segment Anything Model (SAM) have demonstrated superior performance; however, directly applying SAM to medical segmentation may not yield satisfactory results due to the lack of domain-specific medical knowledge. In this paper, we propose BiSeg-SAM, a SAM-guided weakly supervised prompting and boundary refinement network for the segmentation of polyps and skin lesions. Specifically, we fine-tune SAM combined with a CNN module to learn local features. We introduce a WeakBox with two functions: automatically generating box prompts for the SAM model and using our proposed Multi-choice Mask-to-Box (MM2B) transformation for rough mask-to-box conversion, addressing the mismatch between coarse labels and precise predictions. Additionally, we apply scale consistency (SC) loss for prediction scale alignment. Our DetailRefine module enhances boundary precision and segmentation accuracy by refining coarse predictions using a limited amount of ground truth labels. This comprehensive approach enables BiSeg-SAM to achieve excellent multi-task segmentation performance. Our method demonstrates significant superiority over state-of-the-art (SOTA) methods when tested on five polyp datasets and one skin cancer dataset.