Searcharxiv⌕ Search

arXiv subjects

Jie Hou

Publications and source records attributed to Jie Hou.

At least 19 recordsLinked to original sources

Sage S2.1 Flash Technical Report

We introduce Sage S2.1 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents spectra as ordered patches of measurements. Modality-specific projectors map these representations into the input space of a shared backbone, which processes them alongside text and images. To develop the model's agent capabilities, we construct verifiable environments for tool use, search, and coding, as well as specialized workflows involving machine learning experiments and scientific software. Task completion is checked against execution results, changes in environment state, or submitted artifacts. We evaluate Sage S2.1 Flash on 33 benchmarks across seven domains. In the primary comparison against five baselines, it ranks first on OfficeQA Pro (72.2), MLE-bench Lite (90.3 HumanRank), Harvey LAB, and SpreadsheetBench 2, and second on OSWorld-Verified (85.2), WebArena-Verified (67.6), and DeepResearch Bench II (54.2). These results show particular strengths in using documentary evidence, producing verifiable workbooks, and carrying out machine learning tasks, alongside competitive performance in desktop and browser workflows that require the model to act on visual feedback.

cs.AI↗

Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery

We introduce Sage-Taiyi, a metacognition-inspired architecture that uses accumulated scientific understanding to guide what to investigate next and how to investigate it. Through explicit monitoring and control, the system revises its understanding of evidence, assumptions, and unresolved questions, then uses these assessments to adapt research targets and select reusable reasoning methods. On Taiyi-Bench, an AI co-scientist ideation benchmark comprising 265 tasks from 50 papers across ten disciplines, Sage-Taiyi ranks first on all eight metrics of historical rediscovery and open-ended ideation, achieving an Overall score of 54.0 compared with 47.9 for the strongest baseline, AI Scientist-v2. It also performs well on two external scientific ideation benchmarks. Five expert-guided collaborations further connect its proposals to experimental and computational validation across chemistry, materials science, and engineering. In chemistry, reaction-condition optimization raises the yield of cobalt-catalyzed carbonylation from trace amounts to 84% and photocatalytic allylic amination from 13% to 69%. These results support metacognitive regulation as an approach to scientific ideation and its progression toward practical validation.

cs.AI↗

MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE), where sustained self-evolution becomes a key capability. However, existing MLE agents suffer from isolated exploration, inefficient experience reuse, and lack of hierarchical control, which together hinder long-horizon optimization. We present MLEvolve, an LLM-based self-evolving multi-agent framework for end-to-end machine learning algorithm discovery. By extending tree search to Progressive MCGS, MLEvolve enables cross-branch information flow through graph-based reference edges and gradually shifts the search from broad exploration to focused exploitation with an entropy-inspired progressive schedule. To allow the agent to evolve with accumulated experience, we introduce Retrospective Memory, which combines a cold-start domain knowledge base with a dynamic global memory for task-specific experience retrieval and reuse. For stable long-horizon iteration, we further decouple strategic planning from code generation with adaptive coding modes. Evaluation on MLE-Bench shows that MLEvolve achieves state-of-the-art performance across multiple dimensions including average medal rate and valid submission rate under a 12-hour budget (half the standard runtime). Moreover, MLEvolve also outperforms specialized algorithm discovery methods including AlphaEvolve on mathematical algorithm optimization tasks, demonstrating strong cross-domain generalization. Code is available at https://github.com/InternScience/MLEvolve.

cs.AI↗

Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition

In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1, Sage-A1.5 learns not only to solve individual tasks, but also to organize work and revise its approach during execution. Sage-A1.5 highlights three improvements: agentic orchestration, verification, and open scientific discovery. First, agentic orchestration extends single-agent execution through task delegation and parallel collaboration among subagents with isolated contexts, enabling complex tasks to be decomposed and addressed concurrently and supporting efficient execution while reducing interference across concurrent subagents. Second, agentic verification strengthens long-horizon reliability through progress checking, evidence validation, and reflective strategy revision, allowing the agent to recognize unproductive search paths and pursue alternative approaches. Third, open scientific discovery extends agentic capabilities beyond answering predefined questions to conducting exploratory research, connecting scientific inquiry with interactive analysis and inspectable research artifacts. We showcase these capabilities through complicated agentic tasks and multidisciplinary scientific applications. Besides, we hope Sage-A1.5 provides the community with an accessible foundation for open scientific discovery, offering a practical path from long-horizon task execution to collaborative, verifiable, and inspectable scientific exploration.

cs.AI↗

Atria Dawn: The Dawn of Agentic Superintelligence

As AI agents become participants in the development of their successors, they reshape both the production of intelligence and the role of human researchers. We introduce Atria Dawn Preview, a foundation agentic language model designed for scientific research and engineering workflows, with the goal of expanding the frontier of agent productivity in the real world. This model is trained via a Verifiable Experience Pipeline that connects tool-mediated interactions to executable environments and externally verified outcomes. Across 16 benchmarks spanning real-world research, engineering, and digital work, Atria Dawn Preview is competitive with frontier agents and achieves the highest reported score on five of them. Beyond standalone performance, we examine the real research-and-development process behind this model as a case study of human--AI collaboration, analyzing 769 task records from 56 participants together with agent logs. When asked to evaluate completed tasks under comparable conditions, participants rated about one-third of completed AI-assisted tasks as infeasible without AI. More strikingly, agents frequently propose methods and implement revisions, while humans retain most final decisions and guide exploration through judgment and feedback. These observations indicate a shift from task-level execution to project-level partnership, with human effort concentrating on what is worth pursuing and how evidence should guide research. Progress toward more autonomous AI research must therefore advance both the capacity for discovery and the capacity for meaningful human oversight, preserving accountable human authority over the risks and direction of continued development.

cs.AI↗

Group theory of Raman effect in magnetic materials

Despite the wealth of experimental observations on Raman scattering in magnetic materials, the underlying selection rules have remained largely unexplored. In this work, we use Onsager reciprocity relation, other than the conventional corepresentation method, to deal with the mathematical structures of Raman tensors in magnetic groups. Using this approach, we generate Raman tensor tables for all magnetic point groups, and present a comprehensive understanding of the Raman selection rules in magnetic materials with direct product representations method. Our theoretical and numerical results match previous experiments well, and resolve a recent puzzle in the Raman spectroscopy of CrSBr. Moreover, we identify a common but overlooked phenomenon: the magneto-Raman vector can be orthogonal to the magnetic moment direction. Our method and associated Raman tensor tables will be helpful for the Raman studies in both experimental and theoretical domains.

cond-mat.mtrl-sci↗

Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning

We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores knowledge vectors and multiple Reasoners (Self-Attn) that iteratively achieve compositional reasoning. Using hidden states as cache and carrier, reasoners repeatedly query memory for required knowledge-vectors, while the knowledge is transmitted back to reasoning operators. Through this knowledge-reasoning-separation architecture, Mobius achieves better knowledge compression and reasoning efficiency. Built upon Mobius-v0 architecture: 1) Our 7B model trained-from-scratch achieves similar downstream score as a 7B Transformer baseline with 62.6% of baseline's training data. 2) Our Intern-S2-Mobius, continually-pretrained from Qwen3.5-35B, achieves similar downstream score while delivering nearly 4x end-to-end inference speedup.

cs.AI↗

Categorical Optimization with Bayesian Anchored Latent Trust Regions for Structural Design under High-Dimensional Uncertainty

Categorical structural optimization under aleatoric uncertainty is challenging because each design variable must be selected from a finite catalog of admissible instances, while each candidate design may require expensive stochastic finite-element evaluations. Existing latent-space optimization strategies can reduce the dimensionality of catalog attributes, but they often treat the reduced space as a continuous search domain. The resulting continuous optimum must then be rounded off to a nearby catalog instance, which may alter the objective value, constraint status, or physical interpretation of the design. To address this issue, this paper proposes the \textbf{C}ategorical \textbf{O}ptimization with \textbf{B}ayesian \textbf{A}nchored \textbf{L}atent \textbf{T}rust Regions (\textbf{COBALT}) framework for high-dimensional categorical Optimization Under Uncertainty. COBALT first embeds the physical catalog into a low-dimensional latent representation and locks the mapped instances as a discrete anchored graph. A data-independent random tree decomposition is then used to provide bounded-complexity additive modeling over high-dimensional categorical variables. On this anchored domain, an additive SAAS-GP surrogate is fitted to heteroscedastic MC-FEA observations, and a trust-region discrete graph acquisition search selects the next admissible catalog configuration without continuous relaxation or rounding-off. The proposed strategy is applied to robust design optimization of complex bar structures, considering structural weight, strain energy, and local buckling performance. By evaluating only valid catalog designs through the MC-FEA oracle, COBALT preserves physical admissibility throughout the active learning loop and improves the efficiency of robust categorical structural optimization.

cs.LG↗

Evaluating noises of fast-simulated boson sampling with statistical benchmark methods

It is important to know noise levels of boson sampling in order to cautiously demonstrate the quantum computational advantage or realize certain tasks. Based on those statistical benchmark methods such as the correlators and clouds, which are initially proposed to discriminate boson sampling and other mockups, we quantificationally evaluate noises of photon partial distinguishability and photon loss compensated by dark counts. This is feasible owing to the fact that the output distribution unbalances are suppressed by noises, which are actually results of multi-photon interferences. This is why the evaluation performance is better when high order correlators or correspondent clouds are employed. Our results indicate that the statistical benchmark methods can also work in the task of evaluating noises of boson sampling. An effective scheme is also introduced to fast simulate noisy samples, especially those with photon partial distinguishability.

quant-ph↗

Preferences Order, Ratings Anchor: From Fused Expert Aesthetic Ground Truth to Self-Distillation

Pairwise preferences and pointwise ratings are the two dominant annotation protocols in image aesthetic assessment (IAA), yet existing benchmarks adopt only one, leaving their complementarity unmeasured under controlled conditions. We introduce PPaint, a matched dual-protocol benchmark in which 15 domain experts, 5 per category, annotate 150 Chinese paintings under both protocols across five aesthetic dimensions, collecting 45,900 pairwise expert judgments through a locally dense preference design alongside the matched ratings. The matched design reveals complementary strengths: preferences yield more consistent ordinal rankings, while ratings anchor the absolute score scale. Fusing both signals via two independent preference-to-score methods yields a fused expert ground truth on which the two constructions converge to nearly identical scores. The same preference-to-score principle extends to label-free VLM training. PSDistill converts VLM pairwise judgments into calibrated pseudo-scores via an Elo reference pool, and trains the same VLM with confidence-weighted ranking optimization to produce a single-pass aesthetic scorer. Trained on a single painting category, the distilled Qwen3-VL-8B improves mean SRCC from 0.504 to 0.709 across all three categories, outperforming all open-source baselines including the dedicated aesthetic model ArtiMuse and matching closed-source Gemini-3.1-Pro within 0.04 SRCC at single-pass inference cost, with cross-domain transfer further validated on APDDv2. We will release the full PPaint dataset and training code.

cs.CV↗

Extended validations on photon number resolving detector based Gaussian boson sampling with low noises

Gaussian boson sampling (GBS) is a variety of boson sampling overcoming the stable single-photon preparation difficulty of the later. However, like those in the original version, noises in GBS will also result in the deviation of output patterns and the reduction of classical simulation complexity. We extend the pattern recognition validation, together with the correlation approach as a comparison, on GBS using photon number resolving detectors, with noises of both photon loss and distinguishability, to quantificationally evaluate noise levels. As for the classical simulation with noises to be used during validations, it is actually a simulation of mixed states where we employ an existing photon-pair strategy to realize polynomial speedup locally. Furthermore, we use an output-binning strategy to realize validation speedup. Our simulation indicates that the pattern recognition protocol is useful for noise evaluations of GBS even when noises are sufficiently low.

quant-ph↗

Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence

As large models evolve from conversational assistants into autonomous agents, challenges increasingly arise from long-horizon decision making, tool use, and real environment interaction. Existing agenticinfrastructure remain fragmented across evaluation, data management, and agent evolution, making it difficult to discover risks systematically and improve models in a continuous closed loop. In this report, we present \textbf{Safactory}, a scalable agent factory for trustworthy autonomous intelligence. Safactory integrates three tightly coupled platforms: a \textbf{Parallel Simulation Platform} for trajectory generation, a \textbf{Trustworthy Data Platform} for trajectory storage and experience extraction, and an \textbf{Autonomous Evolution Platform} for asynchronous reinforcement learning and on-policy distillation. As far as we know, Safactory is the first framework to propose a unified evolutionary pipeline for next-generation trustworthy autonomous intelligence.

cs.AI↗

Thermodynamics of stacking faults and phase stability in cobalt alloys: A combined computational and experimental study

Stacking fault energy dictates phase stability and deformation behavior in Co alloys and WC-Co cemented carbides, yet a quantitative assessment of alloying effects at finite temperatures remains poorly established. By integrating first-principles thermodynamics with microstructural characterization, we provide a rigorous evaluation of these influences across atomic and macroscopic scales. We show that stacking fault energetics at 0K for transition metal solutes are primarily governed by atomic misfit volume. While 4d and 5d elements follow a consistent linear trend, specific 3d solutes exhibit significant deviations due to non-negligible magnetic contributions. By incorporating phonon, electronic, longitudinal spin-fluctuation, and magnetic free-energy contributions, the model accurately captures the fcc-hcp transformation and quantifies how diverse solutes modulate the phase landscape. We demonstrate that V, Ni, Fe, Mo, and W lower the transformation temperature by stabilizing fcc phase, while Cr and C exhibit the opposite effect, consistent with experimental phase diagrams. Furthermore, microscopic analysis confirms that higher W content dissolved in the Co suppresses stacking-fault formation by elevating the stacking fault energy at finite temperatures. This work clarifies the physical mechanisms by which alloying regulates stacking fault energy and phase stability in Co-based systems, providing guidance for the design of Co-based alloys and WC-Co cemented carbides.

cond-mat.mtrl-sci↗

A transferable framework for structure-energy mapping of nanovoid-solute complexes: Tungsten alloys as a model system

Understanding the structures and energetics of nanovoid-solute complexes is essential for elucidating the coupled evolution of defects in metals. Yet their vast and complex configurational space poses a major challenge to conventional approaches. Using W-Re as a representative system, we demonstrate that solute segregation at nanovoid surfaces can be decomposed into direct nanovoid-solute interactions and nanovoid-mediated solute-solute interactions. Both are governed by local coordination motifs, with identical motifs giving nearly identical energetics. Based on first-principles data, we trained machine-learning models to map diverse local motifs to their energetics, enabling the energetics of any nanovoid-solute complex to be reconstructed from a finite set of constituent local motifs. We further developed a size-dependent configurational-search framework to efficiently identify thermodynamically stable structures, using exhaustive enumeration, simulated annealing, and greedy addition for small, medium-sized, and large complexes, respectively. This framework enabled the construction of a large database, revealed the staircase-like segregation behavior of Re, and derived a simple criterion based on Re surface coverage for rapid energy prediction across a wide size range. It also links Re segregation to vacancy-mediated nanovoid evolution and provides benchmarks for existing models and empirical potentials. Extensions to Os and Ta support the generality of the local-motif concept, and the predicted segregation behavior of solutes at nanovoids agrees with a range of experimental observations. This work establishes a physically transparent, accurate, and transferable framework for studying nanovoid-solute co-evolution in metals and provides reliable energetic inputs for multiscale simulations.

cond-mat.mtrl-sci↗

Atomic-Scale Insights into Solute Drag Effects on Grain Boundary Motion in Mg-Al and Mg-Ca Alloys

The slip behavior of dislocations and grain boundaries critically governs recrystallization and plastic deformation in Mg alloys and can be strongly influenced by solutes. However, the quantitative effects of solute distribution on defect mobility remain unclear. Using molecular dynamics and Monte Carlo simulations, we systematically investigate how Al and Ca solutes affect the motion of dislocations, low-angle grain boundaries (LAGBs), and high-angle grain boundaries (HAGBs) in Mg. Within the idealized framework of random solid-solution, solute drag is dominated by elastic interactions arising from atomic size mismatch, resulting in a stronger resistance from Ca than from Al. In contrast, under the more realistic condition where solute segregation occurs, the dominant mechanism shifts to chemically driven pinning, whose effectiveness is governed by the attainable segregation density. Owing to strong Ca-Ca repulsion, Al achieves substantially higher segregation concentrations than Ca and therefore exerts much stronger pinning effects. Notably, solute-induced retardation is significantly more pronounced for HAGBs than for LAGBs, leading to amplified solute effects during the late stages of recrystallization, where grain growth is controlled primarily by HAGB migration. These results provide atomic-scale insight into experimentally observed grain refinement in Mg alloys.

cond-mat.mtrl-sci↗

Segregation-Controlled Diffusion-Induced Grain Boundary Migration in Alloy 690

Grain boundary (GB) migration accompanied by Cr depletion is widely observed in Alloy 690 and is closely linked to intergranular degradation and stress corrosion cracking. However, the fundamental driving force for GB migration and its link with Cr depletion remains unclear. In this work, hybrid molecular dynamics and semi-grand canonical Monte Carlo simulations were employed to investigate GB migration in Alloy 690 under coupled solute diffusion and segregation effects across a range of GB characters. The results show that Cr segregation at GBs, while generally considered favorable for GB stability, can facilitate diffusion-induced GB migration and Cr depletion. Cr diffusion along GBs produces localized Cr depletion zones that are energetically incompatible with positively segregating GBs, generating a chemical driving force that drives GB migration toward the Cr-rich matrix, which ultimately results in persistent GB migration accompanied by a Cr depletion. By quantifying solute-GB interaction energetics, we demonstrate that GB migration is quantitively controlled by the coupled effects of solute diffusivity and segregation strength. These mechanistic insights provide a unified framework that rationalizes experimentally observed correlations between GB character, Cr depletion, and GB migration in Cr-containing alloys.

cond-mat.mtrl-sci↗

From Mannequin to Human: A Pose-Aware and Identity-Preserving Video Generation Framework for Lifelike Clothing Display

Mannequin-based clothing displays offer a cost-effective alternative to real-model showcases for online fashion presentation, but lack realism and expressive detail. To overcome this limitation, we introduce a new task called mannequin-to-human (M2H) video generation, which aims to synthesize identity-controllable, photorealistic human videos from footage of mannequins. We propose M2HVideo, a pose-aware and identity-preserving video generation framework that addresses two key challenges: the misalignment between head and body motion, and identity drift caused by temporal modeling. In particular, M2HVideo incorporates a dynamic pose-aware head encoder that fuses facial semantics with body pose to produce consistent identity embeddings across frames. To address the loss of fine facial details due to latent space compression, we introduce a mirror loss applied in pixel space through a denoising diffusion implicit model (DDIM)-based one-step denoising. Additionally, we design a distribution-aware adapter that aligns statistical distributions of identity and clothing features to enhance temporal coherence. Extensive experiments on the UBC fashion dataset, our self-constructed ASOS dataset, and the newly collected MannequinVideos dataset captured on-site demonstrate that M2HVideo achieves superior performance in terms of clothing consistency, identity preservation, and video fidelity in comparison to state-of-the-art methods.

cs.CV↗

Dislocation Transmission Across Tilt Low-Angle Grain Boundaries in BCC Fe: The Role of Elastic Interactions

Low-angle grain boundaries (LAGBs) are often regarded as penetrable interfaces to dislocation motion, yet recent studies suggest they can also act as strong barriers. The origin of this duality remains debated, particularly regarding the role of elastic interactions. Here, large-scale molecular dynamics simulations are employed to investigate dislocation transmission across various tilt LAGBs in BCC Fe. The results show that transmission resistance varies widely with boundary-dislocation geometry. Contrary to the prevailing view that dislocation reactions dominate, elastic interactions between lattice and boundary dislocations emerge as the primary controlling factor. Screw and screw-like dislocations generate shear stresses that bend GB dislocations and produce strong barriers, whereas edge dislocations lack such stresses and transmit more readily. Consequently, barrier strength increases as the dislocation character angle decreases, with screw dislocations experiencing the strongest resistance. From these insights, we develop an analytical model that quantitatively links net transmission stress to dislocation character, boundary inclination, and boundary misorientation, reproducing the simulation results with excellent agreement. These results establish the dominant role of elastic interactions in dislocation-LAGB interactions and provide a predictive basis for designing materials strengthened by controlled boundary architectures.

cond-mat.mtrl-sci↗