AI研究論文デイリー

AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction

LSNet: See Large, Focus Small

VerifiAgent: a Unified Verification Agent in Language Model Reasoning

Target-Aware Video Diffusion Models

MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis

Improved Visual-Spatial Reasoning via R1-Zero-Like Training

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

Adaptive Layer-skipping in Pre-trained LLMs

Understanding R1-Zero-Like Training: A Critical Perspective

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement

Medical large language models are easily distracted

ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations

VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step

DASH: Detection and Assessment of Systematic Hallucinations of VLMs

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models

Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks

PaperBench: Evaluating AI's Ability to Replicate AI Research

Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations

Boost Your Own Human Image Generation Model via Direct Preference Optimization with AI Feedback

Towards Physically Plausible Video Generation via VLM Planning

DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance

Articulated Kinematics Distillation from Video Diffusion Models