This work proposes MeCSAFNet, a multi-branch encoder-decoder architecture for land cover segmentation in multispectral imagery. The model separately processes visible and non-visible channels through dual ConvNeXt encoders, followed by individual decoders that reconstruct spatial information. A dedicated fusion decoder...
BONSAI is introduced, a default-aware BO policy that prunes low-impact deviations from a default configuration while explicitly controlling the loss in acquisition value and theoretically bound the regret incurred by BONSAI.
Sam Daulton, David Eriksson, M. Balandat et al.· arXiv.org· 1 citation
Attention-mass concentration creates an opportunity for sparse decoding, but retained mass alone does not guarantee a stable greedy decision: retrieval error, omitted value directions, and recursive decoding all matter. We formalize this distinction with an exact omitted-mass identity and a sufficient downstream margin...
Ensuring that API implementations and usage comply with natural language programming rules is critical for software correctness, security, and reliability. Formal verification can provide strong guarantees but requires precise specifications, which are difficult and costly to write manually. To address this challenge,...
Shihao Xia, Mengting He, Haomin Jia et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Quantitative imaging methods, such as magnetic resonance fingerprinting (MRF), aim to extract interpretable pathology biomarkers by estimating biophysical tissue parameters from signal evolutions. However, the pattern-matching algorithms or neural networks used in such inverse problems often lack principled uncertainty...
Alex Finkelstein, Ron Moneta, Or Zohar et al.· 0 citations
Large language model reasoning is often treated as a monolithic capability, relying on binary preference supervision that fails to capture partial progress or fine-grained reasoning quality. We introduce continuous utility direct preference optimization (CU-DPO), a framework that aligns models to a portfolio of prompt-...
Muhammad Ahmed Mohsin, Muhammad Umer, Emily Fox· 0 citations
Recently, flow-based generative models have shown superior efficiency compared to diffusion models. In this paper, we study rectified flow models, which constrain transport trajectories to be linear from the base distribution to the data distribution. This structural restriction greatly accelerates sampling, often enab...
Hari Krishna Sahoo, Mudit Gaur, Vaneet Aggarwal· 0 citations
Despite rapid progress in robotics, complex or long-horizon tasks remain a fundamental challenge. Most current approaches follow an open-loop paradigm with limited reasoning and no feedback, resulting in poor robustness to environmental changes and severe error accumulation. We present RoboPilot, a dual-thinking closed...
Xinyi Liu, Mohammadreza Fani Sani, Zewei Zhou et al.· 0 citations
Chain-of-Thought (CoT) prompting can substantially improve the reasoning ability of large language models (LLMs), but it often comes with high inference cost due to long and poorly controlled reasoning traces. This overhead is particularly problematic in software engineering tasks (e.g., code generation), where both la...
Kerui Huang, Shuhan Liu, Xing Hu et al.· 0 citations
Statutory corpora and judicial decisions are growing faster than legal professionals can read them, while individual judgments often exceed the context limits of standard encoder models. Transformer architectures dominate legal NLP benchmarks, but their quadratic attention complexity can require truncating or fragmenti...
Many physical systems do not merely move or deform; they grow, adding material and changing the geometry that a world model must represent. Existing world models are typically optimized for pixel prediction, reward prediction, or fixed-support physical dynamics, leaving open how to model systems whose underlying physic...
We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining model stability. Inspired by evolutionary optimization principles, APE evaluates multiple candidate parameter updates through fine-tuni...
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
