Found 327 document(s)
Page 4 of 22
-
Continuous diffusion models have emerged as a promising non-autoregressive paradigm for text generation over continuous embedding spaces. Along the continuous trajectory, the residual token identity directly shapes the d...
-
Instruction-based image editing models exhibit pronounced sample-specific performance variation: different models can produce substantially different results for the same source image and editing instruction, and the bes...
-
Advanced Driver Assistance Systems have become increasingly widespread, aiming to support drivers, reduce workload, and improve traffic safety. However, many systems are rarely used because their behavior feels unnatural...
-
Sparse linear regression is a fundamental problem in high-dimensional statistics, and its private counterparts leave a large gap between the central and the local model of differential privacy. Shuffled differential priv...
-
Open access biomedical research article published in Matern Fetal Med....
-
Open access biomedical research article published in Front Oncol....
-
Sluggish vacancy-mediated self-diffusion in lithium metal limits the critical current density (CCD) of Li anodes in solid-state batteries by promoting interfacial void formation during stripping. To enhance the effective...
-
Training agents for front-end web development requires demonstrations of code editing, execution, browser inspection and revision, yet public trajectories and reusable task environments remain limited. We introduce WebUn...
-
Of Chains and Gains: What Reinforcement Learning changes on Reasoning-based Image Quality AssessmentReinforcement Learning with Verifiable Rewards (RLVR) has improved the performance of large Vision-Language Models (VLMs) on image quality assessment (IQA). Existing approaches often attribute these gains to improved rea...
-
Life experiences can shape policy attitudes, but we only live one life. Citizens may therefore fail to support policies addressing risks they have never personally experienced. Narratives can make such risks immediate an...
-
During post-training, large language models (LLMs) learn value preferences from corpora that may contain imbalanced proportions of opinions associated with different demographic groups. Amplifying these imbalances may fu...
-
Aggregation platforms and smart-inverter control channels can allow a compromised coordination layer to alter active- and reactive-power commands across a geographically distributed DER fleet. This paper introduces the C...
-
Recent DETR-based tiny object detectors adopt dynamic query mechanisms to handle severe density imbalance. However, existing designs entangle two effects: how many and which queries are decoded. This entanglement obscure...
-
Web platforms run on multivariate time series, from service telemetry and Web traffic logs to sensor streams served through Web APIs. Yet, retention policies often archive them at coarse granularity to save storage and b...
-
Learning visual design is essential for prompt enhancement (PE) to turn underspecified user requests into coherent visual specifications for text-to-image (T2I) generation. Existing methods preserve user intent and impro...