MSR is W[1]-hard parameterized by k+Delta on weighted bipartite graphs and by vertex cover number plus k, but FPT parameterized by treewidth plus Delta on weighted graphs.
InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
verdicts
UNVERDICTED 12representative citing papers
Agentic browsers are vulnerable to 20 web and LLM attacks with 18 implemented, exposing five failure modes across four major LLM models that require redesign before safe deployment.
RESTestBench shows that LLM-generated REST API test effectiveness drops when interacting with faulty or mutated code, especially for vague requirements, indicating that high-detail requirements make direct SUT interaction unnecessary.
MCP lifecycle is defined with four phases and 16 activities; a threat taxonomy of 16 scenarios is constructed, validated via case studies, and paired with phase-specific safeguards.
Anonymization placement in RAG—at the dataset or at the generated answer—creates observable differences in privacy protection versus response utility.
Baguan-solar integrates Baguan weather foundation model forecasts with geostationary satellite data via a decoupled two-stage multimodal framework to deliver kilometer-scale 24-hour solar irradiance predictions, cutting RMSE by 16% versus baselines over East Asia.
SCOPE introduces an edge-deployable natural-language PTZ camera agent, a simulation benchmark, and evaluations showing that stronger small language models reduce hallucinations while perception remains the main bottleneck.
Pista decomposes AI agent actions in spreadsheets into auditable steps, enabling real-time user intervention that improves task outcomes, user comprehension, agent perception, and sense of co-ownership over baseline agents.
RAG-DIVE uses an LLM to dynamically generate, validate, and evaluate multi-turn dialogues for assessing RAG system performance in interactive settings.
BifrostRAG combines dual knowledge graphs with hybrid retrieval to improve multi-hop question answering on construction safety regulations, reporting 87.3% F1 on a custom dataset.
The authors define Deontic Argumentation Theory and introduce a new semantics supporting weak permission, unlike grounded semantics in obligation conflicts.
Simulated SKA-Mid surveys reach radio-AGN completeness at L_1.4GHz ~ 10^23 W Hz^-1 up to z~6.
citing papers explorer
-
On the Parameterized Complexity of Min-Sum-Radii
MSR is W[1]-hard parameterized by k+Delta on weighted bipartite graphs and by vertex cover number plus k, but FPT parameterized by treewidth plus Delta on weighted graphs.
-
WAAA! Web Adversaries Against Agentic Browsers
Agentic browsers are vulnerable to 20 web and LLM attacks with 18 implemented, exposing five failure modes across four major LLM models that require redesign before safe deployment.
-
RESTestBench: A Benchmark for Evaluating the Effectiveness of LLM-Generated REST API Test Cases from NL Requirements
RESTestBench shows that LLM-generated REST API test effectiveness drops when interacting with faulty or mutated code, especially for vague requirements, indicating that high-detail requirements make direct SUT interaction unnecessary.
-
Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
MCP lifecycle is defined with four phases and 16 activities; a threat taxonomy of 16 scenarios is constructed, validated via case studies, and paired with phase-specific safeguards.
-
A Case Study on the Impact of Anonymization Along the RAG Pipeline
Anonymization placement in RAG—at the dataset or at the generated answer—creates observable differences in privacy protection versus response utility.
-
Integrating Weather Foundation Model and Satellite to Enable Fine-Grained Solar Irradiance Forecasting
Baguan-solar integrates Baguan weather foundation model forecasts with geostationary satellite data via a decoupled two-stage multimodal framework to deliver kilometer-scale 24-hour solar irradiance predictions, cutting RMSE by 16% versus baselines over East Asia.
-
SCOPE: Real-Time Natural Language Camera Agent at the Edge
SCOPE introduces an edge-deployable natural-language PTZ camera agent, a simulation benchmark, and evaluations showing that stronger small language models reduce hallucinations while perception remains the main bottleneck.
-
Auditing and Controlling AI Agent Actions in Spreadsheets
Pista decomposes AI agent actions in spreadsheets into auditable steps, enabling real-time user intervention that improves task outcomes, user comprehension, agent perception, and sense of co-ownership over baseline agents.
-
RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation
RAG-DIVE uses an LLM to dynamically generate, validate, and evaluate multi-turn dialogues for assessing RAG system performance in interactive settings.
-
Bridging Dual Knowledge Graphs for Multi-Hop Question Answering in Construction Safety
BifrostRAG combines dual knowledge graphs with hybrid retrieval to improve multi-hop question answering on construction safety regulations, reporting 87.3% F1 on a custom dataset.
-
Deontic Argumentation
The authors define Deontic Argumentation Theory and introduce a new semantics supporting weak permission, unlike grounded semantics in obligation conflicts.
-
Evolution of AGN Across Cosmic Epochs with the SKAO
Simulated SKA-Mid surveys reach radio-AGN completeness at L_1.4GHz ~ 10^23 W Hz^-1 up to z~6.