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 1251–1300 of 659983 papers

TitleStatusHype
DFlash: Block Diffusion for Flash Speculative Decoding—4
Causal World Modeling for Robot Control—4
A Pragmatic VLA Foundation Model—4
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
Diffusion Models in Low-Level Vision: A SurveyCode4
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question AnsweringCode4
VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language ModelCode4
Dólares or Dollars? Unraveling the Bilingual Prowess of Financial LLMs Between Spanish and EnglishCode4
SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model InferenceCode4
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine TranslationCode4
DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree SearchCode4
Conditional Prompt Learning for Vision-Language ModelsCode4
DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image EditingCode4
Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2Code4
Show:102550
← PrevPage 26 of 13200Next →