SOTAVerified

The Open Verification Layer for ML Research

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

661,570 papers248,326 code links4,818 tasks

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 4851–4900 of 661570 papers

TitleStatusHype
HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images—2
Proact-VL: A Proactive VideoLLM for Real-Time AI Companions—2
D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI—2
StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?—2
SciDER: Scientific Data-centric End-to-end Researcher—2
WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories—2
Spotlight on Token Perception for Multimodal Reinforcement Learning—2
Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy—2
CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives—2
VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection—2
SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs—2
SoFlow: Solution Flow Models for One-Step Generative Modeling—2
CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering—2
Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?—2
ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning—2
OmniGAIA: Towards Native Omni-Modal AI Agents—2
EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing—2
Enhancing Spatial Understanding in Image Generation via Reward Modeling—2
MLP Memory: A Retriever-Pretrained Memory for Large Language Models—2
From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors—2
Unified Multimodal Models as Auto-Encoders—2
Solaris: Building a Multiplayer Video World Model in Minecraft—2
The Trinity of Consistency as a Defining Principle for General World Models—2
Deforming Videos to Masks: Flow Matching for Referring Video Segmentation—2
Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation—2
EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents—2
G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior—2
LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?—2
Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformers—2
RebuttalAgent: Strategic Persuasion in Academic Rebuttal via Theory of Mind—2
VecGlypher: Unified Vector Glyph Generation with Language Models—2
Seeing the Forest and the Trees: Query-Aware Tokenizer for Long-Video Multimodal Language Models—2
Should We Still Pretrain Encoders with Masked Language Modeling?—2
SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation—2
Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device—2
NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents—2
PyVision-RL: Forging Open Agentic Vision Models via RL—2
UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation—2
Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight—2
OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot—2
On Predictability of Reinforcement Learning Dynamics for Large Language Models—2
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics—2
Esoteric Language Models: Bridging Autoregressive and Masked Diffusion LLMs—2
Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control—2
Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Tooling—2
SAGE: Scalable Agentic 3D Scene Generation for Embodied AI—2
VLANeXt: Recipes for Building Strong VLA Models—2
SimVLA: A Simple VLA Baseline for Robotic Manipulation—2
UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing—2
MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation—2
Show:102550
← PrevPage 98 of 13232Next →