新闻
CoT-Space: A Theoretical Framework for Internal Slow-Thinking via Reinforcement Learning
arXiv:2509.04027v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has become a pivotal approach for enhancing...
CoSyn: The open-source tool that’s making GPT-4V-level vision AI accessible to everyone
Researchers at the University of Pennsylvania and the Allen Institute for Artificial Intelligence have developed...
CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering
arXiv:2507.04756v3 Announce Type: replace Abstract: Personalization has become crucial for adapting models to the diverse...
ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations
arXiv:2511.05359v1 Announce Type: cross Abstract: As language models evolve into autonomous agents that act and...
Conversation Forests: The Key to Fine Tuning Large Language Models for Multi-Turn Medical Conversations is Branching
arXiv:2507.04099v2 Announce Type: replace Abstract: Fine-tuning methods such as Direct Preference Optimization (DPO) and Group...
Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning
arXiv:2511.02755v1 Announce Type: new Abstract: Large language models (LLMs) exhibit complementary strengths across domains and...
Controlled Self-Evolution for Algorithmic Code Optimization
arXiv:2601.07348v4 Announce Type: replace Abstract: Self-evolution methods enhance code generation through iterative “generate-verify-refine” cycles, yet...
Context-level Language Modeling by Learning Predictive Context Embeddings
arXiv:2510.20280v3 Announce Type: replace Abstract: We propose ContextLM, a framework that implicitly learns multi-token prediction...
Context Selection and Rewriting for Video-based Educational Question Generation
arXiv:2504.19406v2 Announce Type: replace Abstract: Educational question generation (EQG) is a crucial component of intelligent...
Context Parametrization with Compositional Adapters
arXiv:2509.22158v1 Announce Type: new Abstract: Large language models (LLMs) often seamlessly adapt to new tasks...
Constellations
I. We had crash-landed on the planet. We were far from home. The spaceship could...
Computational Fact-Checking of Online Discourse: Scoring scientific accuracy in climate change related news articles
arXiv:2505.07409v2 Announce Type: replace Abstract: Democratic societies need reliable information. Misinformation in popular media, such...
