AI研究論文デイリー

VITA: Towards Open-Source Interactive Omni Multimodal LLM

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Kalman-Inspired Feature Propagation for Video Face Super-Resolution

BRAT: Bonus oRthogonAl Token for Architecture Agnostic Textual Inversion

MooER: LLM-based Speech Recognition and Translation Models from Moore Threads

MulliVC: Multi-lingual Voice Conversion With Cycle Consistency

Generating novel experimental hypotheses from language models: A case study on cross-dative generalization