AI研究論文デイリー

DeepCritic: Deliberate Critique with Large Language Models

A Survey of Interactive Generative Video

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks

KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution

LLMs for Engineering: Teaching Models to Design High Powered Rockets

TF1-EN-3M: Three Million Synthetic Moral Fables for Training Small, Open Language Models

AdaR1: From Long-CoT to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization

Spatial Speech Translation: Translating Across Space With Binaural Hearables

MediAug: Exploring Visual Augmentation in Medical Imaging

Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs

A Robust Deep Networks based Multi-Object MultiCamera Tracking System for City Scale Traffic