Long-Lived Characters, Local Inference: Incremental Memory Maintenance for Game NPCs
It centres on Inference, and also names Qwen. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI Intelligence Hub
What’s Trending in AI?
Discover the latest AI news, tools, models, launches and trends shaping the future.
Results for “Benchmarks”
2,656 stories · best match
Last updated 4 hours ago
AI could make thinking cheap. What happens to jobs, education and human purpose?
What happens to jobs, education and human purpose? The story centres on IISc. Reported by YourStory.
Source: YourStoryRead original(opens YourStory)
Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model
The story centres on Benchmarks. Reported by arXiv.
Source: arXivRead original(opens arXiv)
IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications
It centres on Benchmarks, and also names GitHub. Reported by arXiv.
Source: arXivRead original(opens arXiv)
Retrofitting Code Using LLMs to Support Exceptional Behavior
It centres on Benchmarks, and also names GitHub and Qwen. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI AgentsBharatHunt Trend Score21
Automated agent evaluation with Amazon Bedrock AgentCore and GitHub Actions
It centres on Benchmarks, and also names Amazon and GitHub. Reported by AWS.
Source: AWSRead original(opens AWS)
MindTopo reveals VLMs’ spatial reasoning abilities
It centres on Benchmarks, and also names Microsoft. Reported by Microsoft Research.
Source: Microsoft ResearchRead original(opens Microsoft Research)
AI ResearchBharatHunt Trend Score28
The Structure Gap: When More Data Cannot Replace Structured Reasoning
Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ModelsBharatHunt Trend Score27
ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents
Reported by arXiv.
Source: arXivRead original(opens arXiv)
Generative AIBharatHunt Trend Score21
Beyond Best-of-$k$: Prior-Consistent DAPS for Ambiguous Nonlinear Inverse Problems
The story centres on Benchmarks. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ModelsBharatHunt Trend Score21
Training Small Language Models for Transferable Tool Selection
It centres on Claude, and also names GPT and Llama. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ResearchBharatHunt Trend Score21
SurveyGraph: Generating Academic Surveys via Methods-Entity Knowledge Graphs
It centres on Benchmarks, and also names Qwen and GitHub. Reported by arXiv.
Source: arXivRead original(opens arXiv)