SOTAVerified

The Open Verification Layer for ML Research

Community benchmark tracking and reproducibility verification. Built for researchers and autonomous research agents.

659,983 papers248,104 code links4,818 tasks

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 526–550 of 659983 papers

TitleStatusHype
MoE-LLaVA: Mixture of Experts for Large Vision-Language ModelsCode7
Step-Audio: Unified Understanding and Generation in Intelligent Speech InteractionCode7
Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM TrainingCode7
Step1X-Edit: A Practical Framework for General Image EditingCode7
LLaVA-CoT: Let Vision Language Models Reason Step-by-StepCode7
Zero-shot Voice Conversion with Diffusion TransformersCode7
xLSTM: Extended Long Short-Term MemoryCode7
Full Scaling Automation for Sustainable Development of Green Data CentersCode7
LHM: Large Animatable Human Reconstruction Model from a Single Image in SecondsCode7
LLaMA: Open and Efficient Foundation Language ModelsCode7
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 QuantizationCode7
Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion TransformersCode7
Transparent Image Layer Diffusion using Latent TransparencyCode7
InternVideo2: Scaling Foundation Models for Multimodal Video UnderstandingCode7
AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation PipelineCode7
Robust Inverse Graphics via Probabilistic InferenceCode7
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference FeedbackCode7
From Bytes to Ideas: Language Modeling with Autoregressive U-NetsCode7
Direct Preference Optimization: Your Language Model is Secretly a Reward ModelCode6
Vision Transformers Need RegistersCode6
iTransformer: Inverted Transformers Are Effective for Time Series ForecastingCode6
L-Eval: Instituting Standardized Evaluation for Long Context Language ModelsCode6
Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from BackboneCode6
RWKV: Reinventing RNNs for the Transformer EraCode6
A Watermark for Large Language ModelsCode6
Show:102550
← PrevPage 22 of 26400Next →