dblp computer science bibliography
PulseAugur coverage of dblp computer science bibliography — every cluster mentioning dblp computer science bibliography across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Reinforcement learning boosts zero-shot Text-to-SPARQL generation
Researchers have explored the use of reinforcement learning for zero-shot Text-to-SPARQL generation, a task crucial for knowledge graph question answering. They applied Group-Relative Policy Optimization (GRPO) to the Q…
-
New research questions usability of graph evidence in LLMs
A new research paper titled "Graph Evidence Is Not Enough: Diagnosing Native Decoder Use in Graph-Augmented LLMs" explores the limitations of current graph-augmented large language models. The study introduces a diagnos…
-
AI framework COCI extracts structured metadata from conference calls for papers
A new AI-powered framework called COCI has been developed to extract structured metadata from Conference Calls for Papers (CfPs). This system uses Large Language Models and semantic mapping to identify and link entities…
-
New research suggests LLM-based metrics improve dynamic topic model evaluation
A new research paper proposes a revised approach to evaluating dynamic topic models, which track evolving word distributions. The study found that traditional coherence metrics often fail to align with human judgments, …
-
Brazilian AI Conference Sees Rise in LLMs, Open Science
A meta-scientific study analyzing eleven years of the Brazilian Conference on Intelligent Systems (BRACIS) reveals trends in AI research within Brazil. The study found that Large Language Model research has significantl…
-
New Blackknife framework enables black-box attacks on graph neural networks
Researchers have developed Blackknife, a novel framework designed to perform black-box adversarial attacks on heterogeneous graph neural networks (HGNNs). This attack method operates under strict limitations, requiring …
-
DBLP protocol enhances distributed ML training by managing gradient loss during network congestion.
Researchers have developed a new transport protocol called DBLP designed to improve the efficiency and resilience of distributed machine learning training. DBLP addresses issues of tail latency and training variability …
-
Topological Neural Tangent Kernel enhances graph neural networks with higher-order structure
Researchers have introduced the Topological Neural Tangent Kernel (TopoNTK), a novel kernel designed for simplicial message passing that extends beyond pairwise relationships. Unlike traditional graph kernels, TopoNTK c…
-
TypeBandit method improves attribute completion in heterogeneous graphs
Researchers have introduced TypeBandit, a new method designed to improve attribute completion in heterogeneous graph neural networks. This approach addresses the challenge of missing node attributes by recognizing that …