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 2451–2500 of 659983 papers

TitleStatusHype
Leveraging tropical reef, bird and unrelated sounds for superior transfer learning in marine bioacousticsCode3
VisionLLaMA: A Unified LLaMA Backbone for Vision TasksCode3
StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image SynthesisCode3
LayerSkip: Enabling Early Exit Inference and Self-Speculative DecodingCode3
Revisiting Image Pyramid Structure for High Resolution Salient Object DetectionCode3
Travel Time Prediction using Tree-Based EnsemblesCode3
All-atom Diffusion Transformers: Unified generative modelling of molecules and materialsCode3
CtrLoRA: An Extensible and Efficient Framework for Controllable Image GenerationCode3
MambaGlue: Fast and Robust Local Feature Matching With MambaCode3
Sparser, Better, Faster, Stronger: Sparsity Detection for Efficient Automatic DifferentiationCode3
Neural networks for abstraction and reasoning: Towards broad generalization in machinesCode3
Concept Sliders: LoRA Adaptors for Precise Control in Diffusion ModelsCode3
RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust AdaptationCode3
Revisiting VerilogEval: A Year of Improvements in Large-Language Models for Hardware Code GenerationCode3
OneFormer: One Transformer to Rule Universal Image SegmentationCode3
The Surprising Effectiveness of Test-Time Training for Few-Shot LearningCode3
Prefix-Tuning: Optimizing Continuous Prompts for GenerationCode3
Tina: Tiny Reasoning Models via LoRACode3
Pushing the limits of raw waveform speaker recognitionCode3
Discovering and exploring cases of educational source code plagiarism with DolosCode3
UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform GenerationCode3
LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language ModelsCode3
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling StrategiesCode3
Bidirectional Multi-Scale Implicit Neural Representations for Image DerainingCode3
Accelerating Transformer Inference for Translation via Parallel DecodingCode3
DiM: Diffusion Mamba for Efficient High-Resolution Image SynthesisCode3
GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and EditingCode3
ConceptAttention: Diffusion Transformers Learn Highly Interpretable FeaturesCode3
A Distractor-Aware Memory for Visual Object Tracking with SAM2Code3
TAPIP3D: Tracking Any Point in Persistent 3D GeometryCode3
CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent EvaluationCode3
Data Generation for Hardware-Friendly Post-Training QuantizationCode3
LLMmap: Fingerprinting For Large Language ModelsCode3
SongComposer: A Large Language Model for Lyric and Melody Generation in Song CompositionCode3
PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic ThinkingCode3
ExCoT: Optimizing Reasoning for Text-to-SQL with Execution FeedbackCode3
MagicPIG: LSH Sampling for Efficient LLM GenerationCode3
MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMsCode3
Qihoo-T2X: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Any-TaskCode3
What Language Model to Train if You Have One Million GPU Hours?Code3
FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion ModelCode3
An Evolved Universal Transformer MemoryCode3
Instruct-IPT: All-in-One Image Processing Transformer via Weight ModulationCode3
DFormerv2: Geometry Self-Attention for RGBD Semantic SegmentationCode3
SegFormer3D: an Efficient Transformer for 3D Medical Image SegmentationCode3
CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-ResolutionCode3
Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few LabelsCode3
From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by StepCode3
Diffusion Feedback Helps CLIP See BetterCode3
HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG SystemsCode3
Show:102550
← PrevPage 50 of 13200Next →