Paper Reviews by AI

Auto-built benchmark with up-to-date knowledge ensures contamination-free LLM evaluation.

AniDoc automates cartoon animation line art video colorization, making animation creation easier!

VidTok: an open-source, top performing video tokenizer.

OmniEval: Automatic benchmark for evaluating financial RAG systems.

New benchmark reveals how well AI understands and meets real-world human needs.

Move-in-2D generates realistic human motion sequences conditioned on a 2D scene image and text prompt, overcoming limitations of existing approaches and improving video synthesis.

Edit many objects at once in videos! MIVE does it accurately without affecting other areas, a big step for AI video editing.

MoDE makes AI for robot control faster and more efficient.

ChatDiT enables zero-shot, multi-turn image generation using pretrained diffusion transformers and a novel multi-agent framework.

G-Pass@k & LiveMathBench: Evaluating the stability of LLMs.

Generate wide-scope 3D scenes from single images in a snap!

Whisper-GPT, a hybrid audio LLM, improves music/speech generation by combining audio waveforms and text.

Create realistic 3D heads with specific hairstyles from text, no 3D hair data needed!

Self-play method SPAR enhances LLMs instruction following abilities, beating GPT-4 on IFEval

Leveraging video models, researchers achieve state-of-the-art 3D super-resolution by generating ‘video-like’ sequences from unordered images, eliminating artifacts and computational demands.

SepLLM shrinks LLMs, speeding them up by over 50% without losing much accuracy.

RetroLLM unifies retrieval & generation in LLMs, boosting accuracy and cutting costs.

MOVIS enhances 3D scene generation by improving cross-view consistency in multi-object novel view synthesis.

Simple tweak, big privacy win: MLP-based architectures boost data protection in federated learning.

IDArb: A diffusion model for decomposing images into intrinsic components like albedo, normal, and material properties, handling varying views and lighting.