Fraglingo is an autoregressive fragment-based molecular generator that jointly models fragment identity and attachment in a continuous latent space. It predicts attachment-aware fragment embeddings using a wildcard-anchored readout that captures the growing molecule’s active attachment site, then retrieves the next fragment via latent-space nearest-neighbor search. This approach allows new fragments to be added at inference time without retraining and achieves stronger joint property control on benchmarks while maintaining high validity, uniqueness, and novelty.
By Thao Nguyen, Jeonghwan Kim, Zhenhailong Wang, Heng Ji
arXiv:2609.14820v1 Announce Type: cross
Abstract: This work presents POLARIS, a training-free audio fingerprinting system that selects landmarks from a locally normalized saliency field and groups th...
By Jiheng Li
arXiv:2602.21061v2 Announce Type: replace
Abstract: Many current paths to more advanced AI depend on the assumption that large language models (LLMs) can generalize learned relationships to solve com...
By David Koplow, Tomer Galanti, Tomaso Poggio
arXiv:2609.13734v1 Announce Type: cross
Abstract: As large language models (LLMs) are increasingly deployed in real-world high-stakes applications, effective governance has become essential. Existing...
By Yuanchen Bei, Zhengzhang Chen, Yanjun Zhao, Haoyu Wang, Hanghang Tong, Haifeng Chen
arXiv:2609.14595v1 Announce Type: cross
Abstract: Multichannel time-series classification commonly assumes synchronized sensor streams, although latency, clock drift, and preprocessing can introduce...
By Sebastian Buschj\"ager, Michael Frichert, Daniel Kuhe, Jian-Jia Chen
arXiv:2609.14045v1 Announce Type: new
Abstract: Agentic learning systems are often required to adapt after deployment by observing new data and reusing prior knowledge under limited supervision or fe...
By Yingxu Wang, Kunyu Zhang, Siyang Gao
arXiv:2609.15620v1 Announce Type: new
Abstract: Adaptive meshes enable neural operators for partial differential equations (PDEs) to allocate spatial samples and computation according to local physic...
By Zixuan Shen, Quanxu Wan, Bingchuan Wang, Zhi Wang, Biao Luo
arXiv:2609.15915v1 Announce Type: new
Abstract: Meta-reinforcement learning (meta-RL) enables agents to adapt to unseen tasks with limited experience. Despite its promise, the application of meta-RL...
By Zeyang Li, Sunbochen Tang, Navid Azizan
arXiv:2609.15205v1 Announce Type: cross
Abstract: Table extraction from texts is an important task for information systems, and recent approaches that prompt large language models (LLMs) with instruc...
By Tong Li, Shuye Ding, Jiachuan Wang, Yongqi Zhang, Shuangyin Li, Lei Chen, Bo Li
arXiv:2609.14025v1 Announce Type: new
Abstract: Forward-looking sonar object detection is essential for underwater perception, yet deployment on embedded platforms requires highly compact models. To...
By Niloy Kumar Mondal, Poulomi Sarker Puja
arXiv:2609.15400v1 Announce Type: new
Abstract: Vessel segmentation in X-ray coronary angiography (XCA) is a fundamental step for quantitative coronary analysis and subsequent assessment of coronary...
By Wanxian Li, Jiaqian Qin, Qingyi Xian, Yazhi Li, Song Chen, Liman Li, Hao He
arXiv:2509.24975v4 Announce Type: replace-cross
Abstract: Diffusion large language models (dLLMs) enable parallel generation and are promising for unit test generation (UTG), where efficient and larg...
By Lekang Yang, Yuetong Liu, Yitong Zhang, Jia Li
arXiv:2609.14819v1 Announce Type: cross
Abstract: Large language models (LLMs) have a growing range of applications in medicine, and their evaluation is critical for ensuring they provide benefit and...
By Suzannah E McKinney, Phuc Vu, Samuel A Justice, Christopher Humphries, Alyssa Pradhan, Timothy J Keyes, Bernardo C Bizzo, Keith J Dreyer, Sarah F Mercaldo, James M Hillis
CHAI for LLMs is a framework that improves large language models’ performance on code‑mixed translation tasks by using LLMs as annotators to create preference data, applying reinforcement learning from AI feedback, incorporating LLM‑generated domain knowledge for iterative refinement, and evaluating on real‑world datasets. The approach yields a 68.45% average win rate over state‑of‑the‑art open‑source models in human‑adjudicated tests. It demonstrates a scalable method to enhance code‑mixed language understanding in open‑source LLMs.
By Wenbo Zhang, Aditya Majumdar, Asif Ekbal, Amulya Yadav
The paper introduces Learning Neighbor Regions (LNR), a coarse‑to‑fine framework for robust multi‑model fitting in noisy environments. LNR’s coarse module uses a neural network to analyze geometric features of minimum sets, selecting a small number of promising hypotheses to improve efficiency. The fine module encodes neighbor region features for each hypothesis, allowing simultaneous refinement and scoring while avoiding differentiation of the sampling process and solvers. Experiments on four classic tasks show state‑of‑the‑art performance and suggest easy adaptation to other robust fitting problems.
By Chang Nie, Guangming Wang, Zhe Liu, Hesheng Wang
ViCo-SAM3 introduces a Vision-Conditioned alignment framework for open-vocabulary camouflaged object segmentation. The approach adds a vision-conditioned (ViCo) module that dynamically adjusts text embeddings based on global visual context, and a vision-conditioned cross-modal binding (ViCoBind) module to improve interaction between visual and textual representations. These innovations close the semantic gap between text and pixel-level cues, enabling state‑of‑the‑art performance on the OVCamo benchmark without heavy parameter overhead.
By Qiangqiang Zhou, Wenjun Tang, Yong Chen, Dandan Zhu, Jiawei Xu
SAR-FAH is a Frequency‑Adaptive Hybrid network that uses Neural Ordinary Differential Equations (NODEs) to despeckle Synthetic Aperture Radar (SAR) images. It separates homogeneous and heterogeneous regions in the frequency domain via wavelet transform, then applies a NODE‑based module to low‑frequency sub‑bands for smooth denoising and an enhanced U‑Net with deformable convolutions to high‑frequency sub‑bands for edge and texture preservation. Experiments on synthetic and real SAR data show that SAR‑FAH outperforms current state‑of‑the‑art despeckling methods both quantitatively and qualitatively.
By Ziqing Ma, Chang Yang, Zhichang Guo, Yao Li
The paper argues that diffusion-based action policies can use a frozen, observation‑free backbone as a reusable trajectory prior, with task adaptation handled entirely by the conditioning pathway. By pretraining a general action head on forward‑kinematics data and then freezing it, the authors show that a single backbone can match or outperform normally trained models on MimicGen and LIBERO. Their experiments reveal that a small 5 M‑parameter MLP backbone can rival large U‑Net and transformer backbones, indicating that action backbones are often over‑parameterized and that image‑style architectures may not be the best fit for low‑dimensional action generation.
By Jian Zhou, Sihao Lin, Shuai Fu, Zerui Li, Gengze Zhou, Qi WU
DuoTok is a source‑aware dual‑track music tokenizer designed for vocal‑accompaniment generation. It first learns a semantic audio representation via self‑supervised pretraining, then refines source‑aware structure with feature‑replacement noise and multi‑task supervision (spectral reconstruction, source separation regularization, and an ASR head for lyric alignment). The encoder is frozen and hard‑routed codebooks for vocals and accompaniment are learned, while a diffusion decoder restores fine acoustic detail from the discrete tokens, achieving a favorable predictability‑fidelity trade‑off at ultra‑low bitrate across public benchmarks.
By Rui Lin, Zhiyue Wu, Jiahe Lei, Kangdi Wang, Weixiong Chen, Junyu Dai, Tao Jiang
arXiv:2609. 13954v1 Announce Type: new Abstract: Ensemble sampling offers a practical approach to randomized exploration by maintaining a collection of models, but how small an ensemble can be while retaining strong regret guarantees remains unresolved.
By Taehyun Hwang, Min-hwan Oh