AI研究論文デイリー

Adam-mini: Use Fewer Learning Rates To Gain More

Octo-planner: On-device Language Model for Planner-Action Agents

CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs

ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation

A Closer Look into Mixture-of-Experts in Large Language Models

WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records

Symbolic Learning Enables Self-Evolving Agents

MatchTime: Towards Automatic Soccer Game Commentary Generation

Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

Understanding and Diagnosing Deep Reinforcement Learning

Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning

MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool