↓Skip to main content

🏢 University of California, Los Angeles

OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement
·3214 words·16 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Multimodal Reasoning 🏢 University of California, Los Angeles
OpenVLThinker: Iteratively refining vision-language models for complex reasoning, bridging the gap to R1-style capabilities.
CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners
·3734 words·18 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Large Language Models 🏢 University of California, Los Angeles
CaKE: Editing LLMs to Enhance Knowledge Generalization Across Reasoning Tasks.
DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails
·2622 words·13 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Large Language Models 🏢 University of California, Los Angeles
DuoGuard: a novel two-player RL framework generates high-quality synthetic data, improving multilingual LLM safety by outperforming state-of-the-art models with a significantly smaller model size and …