Olfactory Perception Benchmark for Large Language Models
Discover the Olfactory Perception benchmark to evaluate large language models' ability to reason about smell across multiple tasks and languages.
Optimizer-Aware Online Data Selection for LLM Fine-Tuning
Discover a two-stage optimizer-aware method for online data selection that boosts large language model fine-tuning efficiency and performance.
AI-Driven Particle Physics Analysis with LEP Open Data
Discover how AI agents collaborate with physicists to analyze LEP open data, enhancing experimental particle physics measurements and research.
HippoCamp: Benchmarking AI Agents for PC File Management
Discover HippoCamp, a benchmark evaluating AI agents' contextual reasoning and multimodal file management on personal computers with real-world data.
Do Language Models Think Before Deciding? New Insights
Discover how early-encoded decisions shape reasoning in language models, revealing new insights into AI decision-making and cognitive processes.