Found 2,475 document(s)
Page 110 of 165
-
Skills provide agents with reusable experience to guide future decisions without modifying the underlying model. However, coding trajectories are often entangled with task- and repository-specific contexts, making it cha...
-
Due to the inherent discrepancies in imaging viewpoints and field-of-view mismatches among multi-modal sensors, existing fusion methods have long struggled to achieve complete scene-level information integration beyond t...
-
Large Language Models (LLMs) are widely adopted for reflective error correction in task planning; however, existing approaches primarily rely on autonomous exploration, rendering them prone to accumulating erroneous expe...
-
Deep click-through rate (CTR) prediction has achieved substantial success through increasingly expressive feature interaction architectures. However, predictive performance also depends on how input-side information is c...
-
Clinical trial prescreening requires distinguishing unmet conditions from insufficient evidence in patient records. Given patient records, criterion questions, and predefined answer options, we retrospectively compared J...
-
High-resolution video matting requires preserving fine details, such as hair strands and soft transparency, while maintaining consistency across frames. Memory-based methods achieve strong matting quality by matching cur...
-
Multi-objective multi-agent reinforcement learning (MOMARL) addresses agent coordination and objective trade-offs simultaneously while optimising overall system performance. Existing work tends to treat multi-agent coope...
-
Existing jailbreak attackers fall into two classes: static planners fix their single- or multi-turn adversarial plans in advance, remaining simple but losing sight of the victim's replies, wasting turns and limiting tran...
-
Sparse outcome rewards make it difficult for long-horizon language-model agents to assign credit to earlier actions. Learned critics provide value estimates for intermediate states, but these estimates can be inaccurate,...
-
Diffusion large language models (dLLMs) can generate multiple tokens in parallel, but often require many decoding rounds to complete a response. Efficient generation depends not only on which tokens are easy to predict, ...
-
A robot policy needs to understand what a task is asking for in a scene, and how to move the robot to accomplish that task. To achieve these two skills, we introduce Zero-real Agent Policy (ZAP), a recipe that teaches a ...
-
This scientific study investigates how intergranular particles inhibit grain boundary sliding in fine-grained ice, providing implications for understanding planetary ice masses. The research explores rheological properti...
-
This scientific paper examines the jet kinematics of the quasar 4C+21.35 using observational data obtained from the KaVA very long baseline interferometry array....
-
This manuscript introduces a novel channel-synthesizing method designed to reduce uncertainties in satellite radiative transfer modeling. It details the methodology and potential impacts on improving predictive accuracy ...
-
This accepted manuscript examines the sensitivity of airborne radio occultation techniques to tropospheric properties across both ocean and land environments. It provides scientific analysis regarding atmospheric remote ...