Hengtong Shen, Li Yan, Hong Xie, Yaxuan Wei, Xinhao Li, Wenfei Shen, Peixian Lv, Fei Tan
Remote sensing (RS) change detection is essential for interpreting surface dynamics. Semantic change detection (SCD) further enables pixel-level understanding of multi-class transitions, yet remains sensitive to pseudo-changes induced by imaging conditions. Recent RS foundation models extract semantically consistent features across temporal and environmental variations, which is critical for mitigating pseudo-changes. However, existing SCD methods are often rigid and backbone-specific, lacking the flexibility to integrate diverse multi-scale features from emerging foundation models. To this end, we introduce a modular Cascaded Gated Decoder (CG-Decoder) that bridges various backbones and SCD tasks, processing multi-scale features in a coarse-to-fine manner while enabling adaptive change extraction. Building upon the RS foundation model PerA, we present PerASCD, a unified SCD framework. We further propose a Soft Semantic Consistency Loss (SSCLoss) to mitigate numerical instability in mixed-precision training. Extensive experiments on SECOND and LandsatSCD show that PerASCD achieves new state-of-the-art Sek scores (26.11% and 65.21%), surpassing the previous best by 0.61% and 4.95%, respectively. It also demonstrates exceptional data efficiency (outperforming the full-data baseline with 50% data), seamless cross-backbone generalization, and enhanced interpretability. Our approach maintains robust semantic consistency under radiometric variations, providing a reliable SCD solution. Code: https://github.com/SathShen/PerASCD.git.
Scientific workflows often require choosing among known relations before a deterministic calculation can proceed. Whether observations share a culture, treatment or reference standard can change the scientific meaning of the resulting count or comparison. Once the evidence is prepared and the calculation is written as code, this choice reduces to one semantic judgment among listed candidates. We evaluate Jev on this step, using a harness that follows its documented guidance. The study compares twelve model configurations on twenty Choices in ten scientific cases built from published sources, each repeated five times. We measure semantic selections, downstream outputs and final claim labels separately. Jev tied with five other configurations at complete semantic correctness and achieved the lowest observed median latency and known mean cost among successful responses. On one question, whether samples shared a culture, three comparison models made seven wrong selections that changed downstream counts while preserving the correct final label. These results support using Jev to select relations when the evidence and candidates are prepared in advance, and show that evaluating it requires checking the relations and quantities that a workflow will reuse.
Historical experience can guide scientific coding at multiple levels, but task-level retrieval may miss implementation lessons that become relevant during execution. We introduce MUSE, a memory management framework combining multi-level memory with selective runtime injection for scientific coding agents. MUSE builds global, approach-level, and implementation-level memory from historical trajectories. At initialization, the agent receives global memory and problem-matched approach-level memory. During execution, current interactions are used to retrieve implementation-level memory. An LLM gate selects relevant experience and generates specific review advice, or skips injection. Across four benchmarks spanning numerical problem solving, kernel optimization, and scientific software repair, MUSE outperforms retrieval and memory baselines on all evaluation metrics. Ablations support the multi-level design and gated injection, while transfer experiments show that memory remains useful across kernel benchmarks. These results show that multi-level memory and selective runtime injection enable effective reuse of experience in scientific coding. Code is available at https://github.com/hr-jin/MUSE.
Minimal binary linear codes play an important role in secret-sharing schemes and in the structural study of linear codes. We study the minimality of three classes of known constructions: codes from a single complete Hamming-weight layer, codes from arbitrary unions of such layers and graph cut-space codes. For the previously studied single-layer codes C, we give a complete minimality classification: C is minimal if and only if t is even. For t = 4, we determine the minimum and maximum weights, and show that the family strictly violates the binary Ashikhmin Barg sufficient condition for every k. We also calculate the minimum distance of the dual code. For arbitrary unions of complete Hamming-weight layers, we obtain an if-and-only-if classification of minimality and uniform criteria for evenness, self-orthogonality, the doubly even property and hull dimension. We further analyze the family for odd k. Finally, using the classical bond characterization of cuts, we translate minimality of graph cut space codes into a graph-theoretic condition: a nonempty simple graph has a minimal cut code precisely when it has one edge-containing component and that component is complete. We also give a graph-function realization of the known binary tetrahedron code and explicitly identify the resulting code equivalence.
In this paper, we investigate a family of trace codes over finite fields of odd characteristic defined by two quadratic trace conditions. By analyzing the quadratic forms associated with these trace conditions and evaluating the corresponding character sums, we obtain the parameters and complete weight distributions of the codes. We further exploit the natural multiplicative orbit structure of the defining sets to obtain punctured codes and determine their parameters, weight distributions and dual distances. Moreover, we establish self?orthogonality criteria and investigate divisibility and projectivity of the constructed codes. These results give a unified treatment for arbitrary odd prime fields and for extension degrees of both parities.
Gilad Fuchs, Leonid Ekimov, Fei Dong, Jiahong Xie, Wei Liu, Maxim Manco, Alexander Nus
Conversational AI is increasingly used at eBay to deliver personalized customer support. We present a production RAG-based How-To Assistant that answers support and how-to queries by grounding responses in a proprietary knowledge base. We study three factors that drive quality: (1) document chunking and contextualization for indexing, (2) query refinement methods, and (3) automatic LLM-based evaluation for rapid iteration and reliable measurement. We also describe the end-to-end system workflow - from offline indexing to real-time serving and report deployment metrics, offering practical guidance for building scalable, high-precision RAG assistants in commercial support settings.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表