AI ResearchBharatHunt Trend Score22
ExpBoN: Exponential-Noise Best-of-$n$ for Efficient Test-Time LLM Alignment
It centres on AI Safety, and also names Inference. 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 “AI Safety”
688 stories · best match
Last updated 12 hours ago
AI ResearchBharatHunt Trend Score21
CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents
It centres on Benchmarks, and also names AI Safety. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ResearchBharatHunt Trend Score21
Google’s Atlas of the human genome could pave the way for new treatments
It centres on Google, and also names Google DeepMind. Reported by The Verge.
Source: The VergeRead original(opens The Verge)
AI ResearchBharatHunt Trend Score24
BeNice! Closing Looping's Inference-Memory Gap via KV-Sharing
Closing Looping's Inference-Memory Gap via KV-Sharing. It centres on Inference, and also names Fine-tuning and Perplexity. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ResearchBharatHunt Trend Score23
Action Learning for Scientific Simulations
The story centres on Inference. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ResearchBharatHunt Trend Score22
CulturalRiddles: A Multicultural Benchmark of Riddles
The story centres on Benchmarks. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ModelsBharatHunt Trend Score22
Investigating the Impact of Learner Errors on Social Bias in Large Language Models
It centres on Benchmarks, and also names AI Safety and Fine-tuning. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ResearchBharatHunt Trend Score23
DISTRACT: Degradation-Indexed Study of Textual Reference Across Competing Targets
The story centres on Benchmarks. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ResearchBharatHunt Trend Score21
Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding Models
It centres on Benchmarks, and also names Fine-tuning. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ResearchBharatHunt Trend Score21
From Spectra to Joint Schedules in LLM Pre-training: 3+3(+2) Scaling-Law Regimes
Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ResearchBharatHunt Trend Score21
From DNA Design to DNA Slimming: Auditable Agentic Discovery of a Deletion-Only Designer
The story centres on Benchmarks. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ModelsBharatHunt Trend Score22
Traversing the solution space of neural networks with Hessian Null Space Continuation
It centres on AI Safety, and also names Fine-tuning. Reported by arXiv.
Source: arXivRead original(opens arXiv)