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 4901–4950 of 661570 papers

TitleStatusHype
Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMs—2
OmniGAIA: Towards Native Omni-Modal AI Agents—2
DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories—2
CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering—2
StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?—2
Deforming Videos to Masks: Flow Matching for Referring Video Segmentation—2
AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories—2
Enhancing Spatial Understanding in Image Generation via Reward Modeling—2
EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing—2
Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion—2
Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator—2
ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding—2
Latent Denoising Makes Good Tokenizers—2
VLANeXt: Recipes for Building Strong VLA Models—2
NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents—2
Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation—2
WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories—2
Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?—2
How to Correctly Report LLM-as-a-Judge Evaluations—2
The Trinity of Consistency as a Defining Principle for General World Models—2
Kanade: A Simple Disentangled Tokenizer for Spoken Language Modeling—2
XSkill: Continual Learning from Experience and Skills in Multimodal Agents—2
OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot—2
Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention—2
UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation—2
Unified Multimodal Models as Auto-Encoders—2
OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams—2
Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding—2
Streaming Autoregressive Video Generation via Diagonal Distillation—2
Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs—2
Experiential Reinforcement Learning—2
SimVLA: A Simple VLA Baseline for Robotic Manipulation—2
InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation—2
SDPose: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation—2
Efficient Reasoning with Balanced Thinking—2
Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs—2
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion—2
MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation—2
EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings—2
Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing—2
Hyperspherical Latents Improve Continuous-Token Autoregressive Generation—2
RealWonder: Real-Time Physical Action-Conditioned Video Generation—2
X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests—2
From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors—2
Towards Pixel-Level VLM Perception via Simple Points Prediction—2
The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs—2
Learning a Generative Meta-Model of LLM Activations—2
Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?—2
ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation—2
EEG Foundation Models: Progresses, Benchmarking, and Open Problems—2
Show:102550
← PrevPage 99 of 13232Next →