Hugging Face Daily Papers

AlphaMaze enhances LLMs’ spatial intelligence via GRPO, achieving 93% accuracy in maze navigation and showing emergent reasoning.

RL optimizes quantum error-correcting codes, slashing physical qubit overhead for fault-tolerant quantum computing.

LLMs have ‘Temporal Heads’ that process time-specific facts!

Personalizing video models for dynamic concepts is now achievable with Set-and-Sequence: enabling high-fidelity generation, editing, and composition!

Packing new knowledge into LoRA adapters can harm LLMs! A delicate balance is needed to prevent performance decline.

PURE: LLM-driven user profile management boosts recommendation by harnessing user reviews for personalized insights while tackling token limits. PURE enhances LLMs for better recommendations.

Logic-RL unlocks LLM reasoning via rule-based reinforcement learning, generalizing to math problems after training on logic puzzles.

MLGYM: A new framework & benchmark to advance AI Research Agents

PC-Agent: A new hierarchical framework that significantly improves complex task automation on PCs by 32%!