ReDIL-GNN is a framework for resynthesis domain‑incremental learning in circuit graph neural networks. It adapts a fixed prediction or representation head as new synthesis styles appear and evaluates retention across all previously seen domains. The method introduces the Resynthesis Adaptability Index (RAI), a pre‑adaptation score that combines adaptation need, source‑equivalence recoverability, structural coverage, and update compatibility to decide whether to adapt, reuse, or defer updates.
By Rupesh Raj Karn, Johann Knechtel, Ozgur Sinanoglu
TACTICS is a method for selecting evaluation samples in machine translation that explicitly optimizes for coverage of rare linguistic categories, document-level coherence, and distributional fidelity to the full corpus. It builds a hierarchical taxonomy from a locale style guide, classifies segments, and chooses a fixed-budget subset that better represents the full range of phenomena a system must handle. Compared to random, lexical, or embedding-based selection, TACTICS improves coverage of rare categories and yields more accurate system rankings with fewer segments.
By Prasanth Bathala, Anubhav Shrimal, Sukhdeep Singh Kharbhanda, Pradyumna Lanka, Rohit Dhaipule
The study investigates which components of a neural network contribute to rapid generalization (grokking) and how stable that improvement remains during further training. By transferring internal attention and MLP weights along with token embeddings and readout, the authors achieve a 5.46‑percentage‑point boost in early accuracy and a 558‑step reduction in confirmation latency, while also demonstrating that freezing transferred representations largely prevents post‑grokking relapse. The work delineates clear component‑level differences between acceleration and stability, and identifies architectural limits where omitting donor embeddings leads to significant performance loss.
By Zeyu Jia
The paper introduces a benchmark for recommending SNOMED CT concepts from masked clinical contexts, using data from the SNOMED CT Entity Linking Challenge v1.2.1 derived from MIMIC-IV-Note. It evaluates several methods—including a popularity baseline, sparse TF‑IDF prototypes, dense embeddings, and retrieval‑augmented hybrids—finding that sparse TF‑IDF achieves the best performance with Recall@1 of 14.81% and Recall@10 of 33.43%. The study highlights that concept frequency and lexical context strongly influence recommendation quality, with many test pairs involving concepts unseen during training.
By Ali Noori
The paper audits vision‑language models (CLIP) for gender bias using 1,500 artworks from the Metropolitan Museum of Art, focusing on zero‑shot logit differences for prompts like "masterpiece," "quality," and "influence." Unadjusted results show no significant gender effect and statistical equivalence across models, but high residual variance suggests that global zero‑shot metrics are largely noise‑dominated and may miss fine‑grained biases. The study underscores the need for multivariate confound control, equivalence testing, and provenance auditing when evaluating AI fairness in cultural heritage data.
By Manpreet Singh, Rhythm Bhatia, Rahul Joshi
The paper introduces MVLGeo, a unified framework for cross-view object geo-localization that combines multiple viewpoints into a single model. It employs Vision‑Language Reranking to use contextual text from the query view, a multi‑view Mixture‑of‑Experts architecture to share knowledge and reduce redundancy, and an adaptive elliptical prior for positional encoding. Experiments on CVOGL benchmarks show that MVLGeo achieves state‑of‑the‑art performance and robustness to input degradation.
By Xuyu Fan, Qi Ming, Zhu Han, Liuqian Wang, Siyuan Cao, Xiaohan Zhang, Xudong Zhao, Mingjing Zhao, Yuhan Zhang
The paper argues that computational text‑based ideal point estimation (CT‑IPE) methods should be viewed as configurable measurement pipelines rather than fixed estimators. It presents a large‑scale comparative experiment involving 17 CT‑IPE algorithms, 5,537 runs, and about 4.25 million left‑right position estimates, and describes shared infrastructure that enables joint execution of these heterogeneous methods. Sensitivity analyses reveal that most algorithms exhibit low hyperparameter sensitivity (ICC < .10), with any remaining sensitivity concentrated in a few key researcher choices such as the language or embedding model, seed keyword lists, and number of topics.
By Patrick Parschan
MoRE: Mixture of Reused Experts is a hybrid architecture that combines Mixture-of-Experts (MoE) with weight‑sharing techniques. It shares expert pools across adjacent layers while each layer keeps its own router, and introduces lightweight depth embeddings to help shared experts differentiate layer contexts. Experiments on models ranging from 114 M to 1.15 B parameters show MoRE achieves lower perplexity and better downstream performance than standard MoEs and other weight‑sharing models, with only minimal changes to existing MoE implementations.
By Eric S. Qiu, Utku Umur Acikalin, Justin Lovelace, Christian Belardi, Arjun B. Mulchandani, Carla P. Gomes, Kilian Q. Weinberger
The paper introduces EffiRAG, a graph-based retrieval‑augmented generation system that reduces the cost of building and querying a graph by using it only to locate relevant passages and generating answers from the original text. On the UltraDomain benchmark, EffiRAG outperforms LightRAG‑hybrid in 93 of 120 questions while cutting total system cost by 57 % (from USD 0.952 to USD 0.408). The study shows that graph‑based RAG can be both more accurate and cheaper, especially as the corpus grows, and recommends evaluating such systems on both answer quality and cost.
By Yuzhong Zhang, Haoyang Ma, Chao Peng, Lionel Briand, Boxi Yu, Jialun Cao
arXiv:2609.17548v1 Announce Type: new
Abstract: Myovox, from myo (muscle) and vox (voice), decodes open-vocabulary English text from 31-channel surface electromyography (sEMG) recorded from the muscl...
By Varshith Madishetty
This paper proposes a Retrieval-Augmented Generation (RAG) framework for scientific image quality assessment, designed to simultaneously address both the understanding track (SIQA-U) and the scoring t...
Conditioning a video generator on multiple images requires preserving appearance while associating each reference with its intended role. We present MSR (Multiple Subject Reference), a slot-aware cond...
Cross-view object geo-localization (CVOGL) locates a target in satellite imagery using drone or street-view queries. Existing methods train separate detectors for each viewpoint, leading to parameter...
Large language model (LLM) agents augmented by tools can automate complex, multi-step tasks, such as web navigation, code generation, and workflow orchestration, by acting on external systems through...
The study evaluates three automated methods for distinguishing intimal from medial intracranial arterial calcifications (IACs) on non‑contrast head CT scans. Using segmentation masks, the methods—an adapted visual score, a sphericity metric, and shape embeddings from a medical foundation model—achieved comparable performance, with the embedding approach achieving the highest weighted F1 scores (71.5% for single arteries, 59.8% for joint classification). The approach remains robust when using automated versus manual segmentation masks, demonstrating feasibility for fully automated IAC subtype quantification.
By Benjamin Jin, Maria del C. Vald\'es Hern\'andez, Richard Bortsov, Joanna M. Wardlaw, Daniel Bos, Grant Mair
arXiv:2604.18616v2 Announce Type: replace-cross
Abstract: LLM coding agents can generate correct GPU kernels, but their performance still trails expert libraries. Reaching peak throughput requires co...
By Haohui Mai, Xiaoyan Guo, Xiangyun Ding, Daifeng Li, Qiuchu Yu, Chenzhun Guo, Cong Wang, Jiacheng Zhao, Christos Kozyrakis, Binhang Yuan
arXiv:2609.17386v1 Announce Type: new
Abstract: Test-time prompt tuning (TPT) enables adaptation on a single test instance, achieving improved accuracy but often sacrificing calibration performance....
By Yuwei Liang, Jian Liang, Dapeng Hu, Yinuo Xu, Ran He
arXiv:2609.16380v1 Announce Type: new
Abstract: Class-balanced learning and label noise create a coupled failure mode: frequency correction prevents majority classes from dominating the decision rule...
By Mushir Akhtar, Akarsh J., M. Tanveer, Mohd. Arshad
arXiv:2602.10480v4 Announce Type: replace
Abstract: Large language models (LLMs) exhibit strong general-purpose reasoning capabilities, yet they frequently hallucinate when used as world models (WMs)...
By Hongyu Zhao, Siyu Zhou, Haolin Yang, Zengyi Qin, Tianyi Zhou
The study evaluates the use of frozen geospatial foundation embeddings (AlphaEarth) for mapping cultivated versus non‑cultivated land in Maine. Using 192 spatially separated patches and USDA Cropland Data Layer labels, a lightweight classifier achieved 93.7% overall accuracy without fine‑tuning, and a nearest‑class‑centroid rule reached 90.2%. A balanced sample of 60,000 labeled pixels was nearly as effective as the full 8.6 million‑pixel pool, and classifiers trained in one year remained accurate across 2018‑2023. In a blind human validation of 385 points, the AlphaEarth‑plus‑random‑forest map matched 95.3% of the consensus, outperforming the CDL reference (91.7%).
By Mohammad Ammar Mughees, Giovanni Montefoschi, Zhongxin Chen, Maria Antonia Brovelli