arXiv subjects

Yi Duan

Publications and source records attributed to Yi Duan.

10 recordsLinked to original sources

arXiv2026

The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal the problems of existing LLMs, then introduce the RSI concept and its development roadmap: from improvement-execution autonomy, improvement-strategy autonomy, experience-acquisition autonomy, and environment-adaptation autonomy, to recursive meta-improvement. Next we examine RSI across scenarios (e.g., scientific discovery, embodied intelligence, software engineering), highlighting their distinct requirements and development speeds. Drawing on diverse industry practices and preliminary empirical evidence, we connect RSI research with practical systems and identify key challenges to achieving genuine RSI.

cs.LG↗

arXiv2026

BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language

We present BioMatrix, the first multimodal foundation model that natively integrates sequences, structures, and natural language for both molecules and proteins within a single decoder-only architecture. Existing biological foundation models pursue native multimodality and broad entity coverage separately: those that fuse multiple modalities under a shared objective remain confined to a single entity type, while those spanning multiple entity types either omit explicit structural modeling or rely on adapter-based designs in which the model cannot natively generate the very modalities it can read. BioMatrix closes this gap by mapping molecular sequences (supporting both SMILES and SELFIES notations), molecular structures, protein sequences, protein structures, and natural language into a shared discrete token space through a unified tokenization scheme, so that all modalities are consumed and produced uniformly under a single next-token prediction objective -- without external encoders, projection adapters, or modality-specific output heads. Built upon the Qwen3 language model (1.7B and 4B), BioMatrix is continually pretrained on 304.4 billion tokens spanning general and domain-specific text, sequence and structure views of molecules and proteins, and cross-modal corpora that interleave biomolecular entities with scientific text and link distinct entities through molecule-protein and protein-protein interaction data. After tuning on a comprehensive suite of downstream applications covering 80 tasks across 6 categories -- encompassing single-entity and multi-entity understanding and generation tasks across and within modalities -- BioMatrix achieves state-of-the-art or competitive performance on 77 out of 80 tasks, demonstrating that a single, natively multimodal generalist model can effectively match or surpass specialized approaches across a wide range of biological tasks.

cs.CL↗

arXiv2026

Biological Reasoning-Informed Regression for Interpretable Regulatory DNA Activity Prediction

DNA cis-regulatory elements (CREs) such as enhancers control gene expression levels. Accurately predicting regulatory activity from DNA sequences is valuable but challenging, as it requires understanding complex biological regulatory processes. Existing methods typically regress activity scores from sequences in a black-box manner, limiting both interpretability and regression performance. Meanwhile, large language models (LLMs) benefit from explicit reasoning processes, yet directly applying LLMs to raw DNA sequences performs poorly. In this paper, we bridge this gap by introducing R3LM, a framework that teaches LLMs reasoning-informed regression on regulatory DNA through structured biological knowledge. Specifically, we design a biologically grounded data format that structures DNA's regulatory information for improved LLM understanding, and construct CRE-ReasonBench, the first dataset that associates DNA sequences and activity scores with mechanistic reasoning traces. Through two-stage training that first teaches LLMs reasoning over structured biological information then performs regression, R3LM achieves state-of-the-art performance on enhancer prediction across three cell types, outperforming both LLMs with raw sequence input and specialized DNA models while providing interpretable mechanistic explanations. We expect R3LM as an interpretable reward model that can effectively assist biologists in CRE design. Code is available at https://github.com/DuanYi516/R3LM.

q-bio.GN↗

arXiv2026

Social-JEPA: Emergent Geometric Isomorphism

World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate agents acquire such models from distinct viewpoints of the same environment without any parameter sharing or coordination. After training, their internal representations exhibit a striking emergent property: the two latent spaces are related by an approximate linear isometry, enabling transparent translation between them. This geometric consensus survives large viewpoint shifts and scant overlap in raw pixels. Leveraging the learned alignment, a classifier trained on one agent can be ported to the other with no additional gradient steps, while distillation-like migration accelerates later learning and markedly reduces total compute. The findings reveal that predictive learning objectives impose strong regularities on representation geometry, suggesting a lightweight path to interoperability among decentralized vision systems. The code is available at https://anonymous.4open.science/r/Social-JEPA-5C57.

cs.CV↗

arXiv2026

Extending Sequence Length is Not All You Need: Effective Integration of Multimodal Signals for Gene Expression Prediction

Gene expression prediction, which predicts mRNA expression levels from DNA sequences, presents significant challenges. Previous works often focus on extending input sequence length to locate distal enhancers, which may influence target genes from hundreds of kilobases away. Our work first reveals that for current models, long sequence modeling can decrease performance. Even carefully designed algorithms only mitigate the performance degradation caused by long sequences. Instead, we find that proximal multimodal epigenomic signals near target genes prove more essential. Hence we focus on how to better integrate these signals, which has been overlooked. We find that different signal types serve distinct biological roles, with some directly marking active regulatory elements while others reflect background chromatin patterns that may introduce confounding effects. Simple concatenation may lead models to develop spurious associations with these background patterns. To address this challenge, we propose Prism, a framework that learns multiple combinations of high-dimensional epigenomic features to represent distinct background chromatin states and uses backdoor adjustment to mitigate confounding effects. Our experimental results demonstrate that proper modeling of multimodal epigenomic signals achieves state-of-the-art performance using only short sequences for gene expression prediction.

cs.LG↗

arXiv2025

Accuracy analysis and optimization of scale-independent third-order WENO-Z scheme with critical-point accuracy preservation

To address the order degradation at critical points in the WENO3-Z scheme, some improvements have been proposed , but these approaches generally fail to consider the occurrence of critical points at arbitrary positions within grid intervals, resulting in their inability to maintain third-order accuracy when a first-order critical point (CP1) occurs. Also, most previous improved schemes suffer from a relatively large exponent p of the ratio of global to local smoothness indicators, which adversely affects the numerical resolution. Concerning these limitations, introduced here is an accuracy-optimization lemma demonstrating that the accuracy of nonlinear weights can be enhanced providing that smoothness indicators satisfy specific conditions, thereby establishing a methodology for elevating the accuracy of nonlinear weights. Leveraging this lemma, a local smoothness indicator is constructed with error terms achieving second-order in smooth regions and fourth-order at CP1, alongside a global smoothness indicator yielding fourth-order accuracy in smooth regions and fifth-order at CP1, enabling the derivation of new nonlinear weights that meet accuracy requirements even when employing p=1. Furthermore, a resolution-optimization lemma is proposed to analyze the relationship between parameters in local smoothness indicators and resolution. By integrating theoretical analysis with numerical practices, free parameters in non-normalized weights and local smoothness indicators are determined under the balance of numerical resolution and robustness, which leads to the development of WENO3-ZES4, a new WENO3-Z improvement that preserves the optimal order at CP1 especially with p=1. 1D and 2D validating tests show that the new scheme consistently achieves third-order in the case of CP1 regardless of its position and exhibits good resolution as well as preferable robustness.

math.NA↗

arXiv2025

Evolution and sudden change of steady interactions of low enthalpy hypersonic double wedge flows with fore angle

The evolution and sudden change of steady interaction structures is numerically studied with the fore wedge angle theta_1 in a low enthalpy hypersonic double wedge configuration. It particularly focuses on the conditions of Swantek and Austin's experiments where Ma=7, and h_0=2 MJ/kg but with a reduced Reynolds number (Re). The sudden structural change indicates that when theta_1 reaches a critical value, minor angular variations can trigger a discontinuous transformation in flow structures. The analysis is based on the laminar Navier-Stokes equations, using ideal gas and non-equilibrium gas models. Under the condition of Re=1E5/m, detailed numerical simulations are conducted as theta_1 varies over 0 deg-40 deg. This study yields the following findings: (a) The upper and lower boundaries of theta_1 for the onset of unsteady flow are identified. When theta_1 lies outside these boundaries, the flow remains steady. (b) As theta_1 increases, the interaction patterns evolve sequentially, progressing from Type VI through Type VI->V, Type III, Type IV_r, and ultimately to a flow dominated solely by a bow shock. This evolution defines the boundaries between different interaction patterns and provides a comprehensive understanding of their progression with theta_1. Sudden structural changes occur during the transitions from Type III to Type IV_r and from Type IV_r to a bow shock-dominated flow. In addition, a comparative study is performed through shock polar analysis to compare its predictions with computational results. (c) An unconventional reflection pattern of the transmitted shock over the separation zone, called Type III_r, is observed in non-equilibrium gas flows, which differs from classical interaction patterns. (d) The aerodynamic distribution of wall properties under various interactions is obtained, indicating distinct features before and after the sudden structural change.

physics.flu-dyn↗

arXiv2024

Design of a variable-Mach-number waverider by the osculating-curved-cone method using a rational distribution function and incorporating the equilibrium-gas model

When a waverider flies at hypersonic speed, the thermodynamic properties of the surrounding gas change because of the rapid increase in temperature, so it is reasonable to consider real-gas effects in the vehicle design. In addition, a hypersonic waverider usually travels at varying speed during flight, and deviating from the default speed designed in terms of a constant Mach number often creates difficulties in preserving the expected performance. Therefore, research on the design of variable-Mach-number waveriders considering equilibrium-gas effects is important for applications. In this paper, a design method for a variable-Mach-number osculating-curved-cone waverider (VMOCCW) considering equilibrium-gas effects is introduced, then the influences of different gas models on the waverider design are studied by taking a VMOCCW designed with a linear Mach-number distribution as an example. Furthermore, a new Mach-number distribution method is proposed by using a parameterized rational function, which is combined with different gas models to achieve VMOCCW design. For comparison, waveriders designed with quadratic concave and convex increasing functions are also selected for comparison of their layouts and aerodynamic performances under design and off-design conditions. The results show that waveriders designed with the equilibrium-gas model exhibit differences in geometric features (e.g., volume and volumetric efficiency) and aerodynamic characteristics (e.g., lift-to-drag ratio and pitching moment coefficient) compared to those designed with the ideal-gas model. Specifically, waveriders designed with a rational function for the Ma distribution have a wing-like structure, and overall they have more-balanced geometric and aerodynamic characteristics than those designed with quadratic concave and convex functions.

physics.flu-dyn↗

arXiv2022

Improvements to enhance robustness of third-order scale-independent WENO-Z schemes

Although there are many improvements to WENO3-Z that target the achievement of optimal order in the occurrence of the first-order critical point (CP1), they mainly address resolution performance, while the robustness of schemes is of less concern and lacks understanding accordingly. In light of our analysis considering the occurrence of critical points within grid intervals, we theoretically prove that it is impossible for a scale-independent scheme that has the stencil of WENO3-Z to fulfill the above order achievement, and current scale-dependent improvements barely fulfill the job when CP1 occurs at the middle of the grid cell. In order to achieve scale-independent improvements, we devise new smoothness indicators that increase the error order from 2 to 4 when CP1 occurs and perform more stably. Meanwhile, we construct a new global smoothness indicator that increases the error order from 4 to 5 similarly, through which new nonlinear weights with regard to WENO3-Z are derived and new scale-independents improvements, namely WENO-ZES2 and -ZES3, are acquired. Through 1D scalar and Euler tests, as well as 2D computations, in comparison with typical scale-dependent improvement, the following performances of the proposed schemes are demonstrated: The schemes can achieve third-order accuracy at CP1 no matter its location in the stencil, indicate high resolution in resolving flow subtleties, and manifest strong robustness in hypersonic simulations (e.g., the accomplishment of computations on hypersonic half-cylinder flow with Mach numbers reaching 16 and 19, respectively, as well as essentially non-oscillatory solutions of inviscid sharp double cone flow at M=9.59), which contrasts the comparative WENO3-Z improvement.

cs.CE↗

arXiv2021

Third-order scale-independent WENO-Z scheme achieving optimal order at critical points

As we found previously, when critical points occur within grid intervals, the accuracy relations of smoothness indicators of WENO-JS would differ from that assuming critical points occurring on grid nodes, and accordingly the global smoothness indicator in WENO-Z scheme will differ from the original one. Based on above understandings, we first discuss several issues regarding current third-order WENO-Z improvements (e.g. WENO-NP3, -F3, -NN3, -PZ3 and -P+3), i.e. the numerical results with scale dependency, the validity of analysis assuming critical points occurring on nodes, and the sensitivity regarding computational time step and initial condition in order convergence studies. By analyses and numerical validations, the defections of present improvements are demonstrated, either scale-dependency of results or failure to recover optimal order when critical points occurring at half nodes, then a generic analysis is provided which considers the first-order critical point occurring within grid intervals. Based on achieved theoretical outcomes, two scale-independent, third-order WENO-Z schemes are proposed which could truly recover the optimal order at critical points: the first one is acquired by limited expansion of grid stencil, deriving new global smoothness indicator and incorporating with the mapping function; the second one is achieved by further expanding grid stencil and employing a different global smoothness indicator. For validating, typical 1-D scalar advection problems, 1-D and 2-D problems by Euler equations are chosen and tested. The consequences verify the optimal order recovery at critical points by proposed schemes and show that: the first scheme outperforms aforementioned third-order WENO-Z improvements in terms of numerical resolution, while the second scheme indicates weak numerical robustness in spite of improved resolution and is mainly of theoretical significance

math.NA↗