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 4801–4850 of 661570 papers

TitleStatusHype
EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings—2
Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation—2
XSkill: Continual Learning from Experience and Skills in Multimodal Agents—2
OmniForcing: Unleashing Real-time Joint Audio-Visual Generation—2
IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse—2
OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams—2
NeuralOS: Towards Simulating Operating Systems via Neural Generative Models—2
Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training—2
Mobile-GS: Real-time Gaussian Splatting for Mobile Devices—2
Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct—2
ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation—2
Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention—2
Streaming Autoregressive Video Generation via Diagonal Distillation—2
LLM2Vec-Gen: Generative Embeddings from Large Language Models—2
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data—2
ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA—2
Robot Control Stack: A Lean Ecosystem for Robot Learning at Scale—2
Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports—2
HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising—2
Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding—2
OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning—2
WildActor: Unconstrained Identity-Preserving Video Generation—2
ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning—2
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion—2
Physical Simulator In-the-Loop Video Generation—2
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs—2
NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation—2
MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing—2
From Word to World: Can Large Language Models be Implicit Text-based World Models?—2
Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs—2
Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator—2
Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels—2
RealWonder: Real-Time Physical Action-Conditioned Video Generation—2
ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding—2
OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs—2
Hyperspherical Latents Improve Continuous-Token Autoregressive Generation—2
EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding—2
CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video—2
Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models—2
RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies—2
Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents—2
VidEoMT: Your ViT is Secretly Also a Video Segmentation Model—2
Phi-4-reasoning-vision-15B Technical Report—2
Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling—2
SimRecon: SimReady Compositional Scene Reconstruction from Real Videos—2
Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle—2
InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation—2
Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization—2
Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing—2
HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images—2
Show:102550
← PrevPage 97 of 13232Next →