Researchers have proposed an unsupervised image translation method to improve the nighttime navigation capabilities of agricultural robots.
The CT-Repair framework introduces an agentic approach to automated program repair by integrating static and dynamic code analysis to improve patch generation.
The authors introduce an RG-Flow Transformer that incorporates scale-aware inductive biases to improve neural data analysis in sleep EEG recordings.
Researchers propose using signal detection theory to better distinguish between an LLM's actual knowledge and its metacognitive confidence levels.
Researchers have proposed a new sampling method for masked diffusion language models to improve token generation stability by addressing prediction coupling.
The paper proposes a calibration-first reward auditing framework to improve the transparency and interpretability of reinforcement learning policies used in smart greenhouse climate control.
Researchers propose a hybrid semantic search method that combines public SVD-based indexing with encrypted query reranking to balance privacy and performance.
This research introduces a graph-constrained policy learning approach to improve the accuracy of clinical code prediction from discharge summaries.
This study examines the limitations of existing reward models and proposes new approaches for evaluating reasoning during test-time scaling in large language models.
The paper proposes a generalized framework for semi-supervised learning that avoids reliance on specific distributional assumptions.
Researchers compared institutional policies on generative AI in higher education, focusing on the specific challenges faced by computer science departments.
Researchers evaluate factors influencing the effectiveness of training-free methods for identifying the source generators of AI-created images.
Researchers have developed a zero-setup framework to automate the multi-phase segmentation of X-ray tomography data, reducing the need for manual intervention.
Researchers have developed an exact algorithm for calculating Data Shapley values in weighted k-nearest-neighbor regression and soft-label prediction tasks.
A new diagnostic benchmark called FlipSet reveals that current vision-language models struggle with visual perspective-taking tasks.
This study evaluates methods for managing input uncertainty in machine learning models used for probabilistic load forecasting in smart buildings.
Startup Lingju Innovation has raised angel funding to develop consumer-grade desktop metal CNC machines integrated with AI control algorithms.
A new in-context learning framework improves pilot-based beamforming in multi-user communication systems by adapting to various channel models without retraining.
Researchers propose a new architecture called DoYouRemember that enables multimodal large language models to utilize reconstructive memory rather than relying on one-shot processing.
The SkillSelect-Serve framework assists LLM agents in selecting and managing reusable skills based on quality-of-service requirements and resource constraints.
Researchers developed a method to improve visual attribution in multimodal large language models by addressing the mismatch between context-mixed visual tokens and independent decoding.
UK-based telecommunications provider CityFibre is reportedly planning to reduce its workforce as part of a broader cost-optimization strategy.
Stellar Auto has issued a formal denial regarding rumors that it is separating from the Huawei-backed Harmony Intelligent Mobility Alliance.
Om AI has introduced VLX, a series of streaming multimodal models designed for edge-based physical AI applications.