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 1451–1500 of 659983 papers

TitleStatusHype
Rerender A Video: Zero-Shot Text-Guided Video-to-Video TranslationCode4
Theseus: A Library for Differentiable Nonlinear OptimizationCode4
SnAG: Scalable and Accurate Video GroundingCode4
From Discrete Tokens to High-Fidelity Audio Using Multi-Band DiffusionCode4
DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer ModelsCode4
FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual GuidanceCode4
Old Optimizer, New Norm: An AnthologyCode4
Time-LLM: Time Series Forecasting by Reprogramming Large Language ModelsCode4
The Llama 3 Herd of ModelsCode4
ControlVAE: Tuning, Analytical Properties, and Performance AnalysisCode4
UltimateDO: An Efficient Framework to Marry Occupancy Prediction with 3D Object Detection via Channel2heightCode4
Diffusion Policy Policy OptimizationCode4
Scaling Granite Code Models to 128K ContextCode4
Region-Aware Text-to-Image Generation via Hard Binding and Soft RefinementCode4
Recognize Anything: A Strong Image Tagging ModelCode4
Replace Anyone in VideosCode4
Phased Consistency ModelsCode4
A Survey on Vision-Language-Action Models for Autonomous DrivingCode4
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment AnythingCode4
InternLM-Math: Open Math Large Language Models Toward Verifiable ReasoningCode4
Training-free Regional Prompting for Diffusion TransformersCode4
Your ViT is Secretly an Image Segmentation ModelCode4
SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image SegmentationCode4
MedMamba: Vision Mamba for Medical Image ClassificationCode4
CLAIMED -- the open source framework for building coarse-grained operators for accelerated discovery in scienceCode4
SepLLM: Accelerate Large Language Models by Compressing One Segment into One SeparatorCode4
SVFR: A Unified Framework for Generalized Video Face RestorationCode4
Hidden Biases of End-to-End Driving DatasetsCode4
MoH: Multi-Head Attention as Mixture-of-Head AttentionCode4
Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM InferenceCode4
Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-FreeCode4
Partition Generative Modeling: Masked Modeling Without MasksCode4
You Only Need One Color Space: An Efficient Network for Low-light Image EnhancementCode4
InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond LanguageCode4
Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent DiffusionCode4
Retrieval-Augmented Generation with Hierarchical KnowledgeCode4
Light-A-Video: Training-free Video Relighting via Progressive Light FusionCode4
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4VCode4
UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised PretrainingCode4
Cosmos-Reason1: From Physical Common Sense To Embodied ReasoningCode4
Scaling Law for Quantization-Aware TrainingCode4
Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge GraphsCode4
LIMA: Less Is More for AlignmentCode4
VToonify: Controllable High-Resolution Portrait Video Style TransferCode4
PP-YOLOE: An evolved version of YOLOCode4
LLM2CLIP: Powerful Language Model Unlocks Richer Visual RepresentationCode4
SDXS: Real-Time One-Step Latent Diffusion Models with Image ConditionsCode4
BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical TextCode4
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language ModelsCode4
Self-attention Does Not Need O(n^2) MemoryCode4
Show:102550
← PrevPage 30 of 13200Next →