Found 42,749 document(s)
Page 22 of 2850
-
Arabic LLMs have improved rapidly, but aligning them with country-specific cultural behavioral preferences remains underexplored. Previous work has focused primarily on instruction-tuning for factual knowledge, overlooki...
-
Comparing the predictive performance and computational cost of flow-based intrusion detection experiments requires both quantities to be available for each run. GreenNIDS connects benchmark execution on public NetFlow da...
-
Tool poisoning has emerged as a critical security threat to LLM agents, where adversaries embed malicious instructions in tool descriptions or external resources that enter the agent's context, allowing adversaries to ma...
-
Classical data mining treats data as generated outside the learner. Emerging AI-native infrastructure invalidates this assumption: as agents observe system state, act, update retrieval stores and models, and promote new ...
-
Nella seconda metà del XV secolo, una mercantessa catalana vive a cavallo tra la Sicilia e la Catalogna. Madre di quattro figli, Caterina Llull i Sabastida maneggia perfettamente libri di contabilità, lettere di cambio, ...
-
Este trabajo reúne el conocimiento acumulado por la autora durante los últimos 23 años de investigación sobre el comportamiento de los peces teleósteos y cómo este puede ser alterado por las condiciones ambientales y de ...
-
This study addresses the role of local associations within territorial sustainability processes and analyzes how, through their own organizational dynamics, they contribute to strengthening communities and promoting sust...
-
Visual autoregressive models produce convincing images but can misassign attributes and spatial relations. Searching multiple generation paths can improve composition, yet completing every candidate is costly. We introdu...
-
We give a strongly polynomial time algorithm for submodular function minimization with overall running time $\widetilde{O}(n^{2}\mathsf{EO}+n^{3})$ time, where $\mathsf{EO}$ is the running time of a single evaluation of ...
-
Multimodal Large Language Models (MLLMs) face significant scalability challenges in long-video understanding due to quadratic attention complexity and context window constraints. Existing retrieval-based approaches typic...
-
Large language models store substantial factual knowledge in their parameters, yet this knowledge is difficult to control, update, and reliably elicit at inference time. Existing memory-augmented approaches typically rel...
-
SurGPT: A Multi-Task Foundation Model for Robotic Surgical Skills Assessment and Gesture RecognitionThe assessment of surgical skills in robotic surgery training has traditionally relied on subjective evaluations by human experts, creating bottlenecks in surgical education and limiting scalability. We present a novel f...
-
The Key-Value (KV) cache is the main memory bottleneck of long-context LLM inference. Token eviction methods such as SnapKV, H2O, AdaKV and L2Norm shrink it, but they give every transformer layer the same budget, althoug...
-
Shared autonomy is a control paradigm that combines human cognitive abilities with robot precision to enable effective remote manipulation in complex environments. A key challenge is how to adapt the level of autonomy us...
-
This work explores monocular motion capture for dragon-type characters, which currently relies on manual keyframing due to the lack of high-quality datasets and parametric models. The primary obstacle lies in the extreme...