AI研究論文デイリー

Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization

On the Compositional Generalization of Multimodal LLMs for Medical Imaging

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Efficiently Serving LLM Reasoning Programs with Certaindex

Bringing Objects to Life: 4D generation from 3D objects

TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization

Edicho: Consistent Image Editing in the Wild

Training Software Engineering Agents and Verifiers with SWE-Gym

OneKE: A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System

PERSE: Personalized 3D Generative Avatars from A Single Portrait

Facilitating large language model Russian adaptation with Learned Embedding Propagation

Slow Perception: Let's Perceive Geometric Figures Step-by-step

HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation