SOTAVerified

2k

Papers

Showing 2650 of 288 papers

TitleStatusHype
Any-resolution Training for High-resolution Image SynthesisCode2
High-fidelity 3D Human Digitization from Single 2K Resolution ImagesCode2
TextCrafter: Accurately Rendering Multiple Texts in Complex Visual ScenesCode2
Towards Metrical Reconstruction of Human FacesCode2
PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise TrainingCode2
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationCode2
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationCode2
RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head AvatarsCode2
Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion ModelsCode2
Ultra-Resolution Adaptation with EaseCode2
FastVAR: Linear Visual Autoregressive Modeling via Cached Token PruningCode2
LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language ModelsCode1
MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D ScenesCode1
How Good Are LLMs for Literary Translation, Really? Literary Translation Evaluation with Humans and LLMsCode1
Hierarchical Losses and New Resources for Fine-grained Entity Typing and LinkingCode1
360MonoDepth: High-Resolution 360° Monocular Depth EstimationCode1
Identifying concept libraries from language about object structureCode1
Meticulous Object SegmentationCode1
ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data CharacteristicCode1
Gated Linear Attention Transformers with Hardware-Efficient TrainingCode1
CascadeV: An Implementation of Wurstchen Architecture for Video GenerationCode1
ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable CompressionCode1
CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large InputCode1
BuildingNet: Learning to Label 3D BuildingsCode1
End-to-End Speech Recognition from Federated Acoustic ModelsCode1
Show:102550
← PrevPage 2 of 12Next →

No leaderboard results yet.