About
Research & Development
AI’s Internal Clock: When Information Was Learned Matters
TLDR: A new study reveals that language models linearly encode the order in which they learn information during training. By sequentially fine-tuning a Llama...
Research & Development
PDDL-INSTRUCT: Enhancing LLMs for Precise Symbolic Planning
TLDR: PDDL-INSTRUCT is a new framework that significantly improves Large Language Models' (LLMs) ability to perform symbolic planning by teaching them logical chain-of-thought reasoning....
Research & Development
Agent²: Automating Reinforcement Learning Agent Design with LLMs
TLDR: Agent² is a novel framework that automates the entire reinforcement learning (RL) agent design process using large language models (LLMs). It features a...
Research & Development
Understanding When Vision-Language Models Say ‘Maybe’: A Deep Dive into Uncertainty
TLDR: A new study comprehensively benchmarks uncertainty quantification in 16 state-of-the-art Vision-Language Models (VLMs) using conformal prediction. Findings reveal that larger models exhibit better...
Research & Development
THOR: Bridging LLM Reasoning and Precise Computation for Math Problems
TLDR: THOR is a new framework that enhances Large Language Models' (LLMs) mathematical reasoning by integrating external tools. It addresses key challenges in tool-integrated...
Research & Development
MIRA: Contextual AI Suggestions for Effortless Smartphone Tasks
TLDR: MIRA is a new framework that enables one-touch AI services on smartphones. By long-pressing images or text, users receive contextually relevant AI task...