Code as Agent Harness
Paper • 2605.18747 • Published • 224
paper-reading
-
-
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Paper • 2605.12500 • Published • 198 -
From Context to Skills: Can Language Models Learn from Context Skillfully?
Paper • 2604.27660 • Published • 73 -
PhysBrain 1.0 Technical Report
Paper • 2605.15298 • Published • 61 -
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Paper • 2605.20025 • Published • 89 -
MMSkills: Towards Multimodal Skills for General Visual Agents
Paper • 2605.13527 • Published • 122 -
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
Paper • 2605.06130 • Published • 73 -
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
Paper • 2605.18739 • Published • 117 -
Qwen-Image-2.0 Technical Report
Paper • 2605.10730 • Published • 119 -
Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
Paper • 2605.18233 • Published • 91 -
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
Paper • 2605.00658 • Published • 87 -
Lance: Unified Multimodal Modeling by Multi-Task Synergy
Paper • 2605.18678 • Published • 78 -
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
Paper • 2605.23902 • Published • 45 -
Qwen/Qwen-Image-Bench
Image-Text-to-Text • 27B • Updated • 37.1k • 100 -
CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era
Paper • 2503.12329 • Published • 28 -
baidu/ERNIE-Image
Text-to-Image • 8B • Updated • 990 • • 674 -
GenClaw: Code-Driven Agentic Image Generation
Paper • 2605.30248 • Published • 40 -
ByteDance-Seed/Cola-DLM
Text Generation • Updated • 117 • 46 -
deepseek-ai/DeepSeek-V4-Pro
Text Generation • 1.6T • Updated • 479k • • 5.6k -
Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE
Paper • 2605.02641 • Published • 1 -
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
Paper • 2605.28816 • Published • 148 -
MeiGen-AI/GenEvolve
Image-Text-to-Text • 9B • Updated • 90 • 10 -
CostaliyA/Flow-OPD
Text-to-Image • Updated • 20 • 1 -
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Paper • 2604.13016 • Published • 116 -
ByteDance/Bernini-R
Image-Text-to-Video • Updated • 95 • 299 -
Trust Region On-Policy Distillation
Paper • 2606.01249 • Published • 46 -
nvidia/Cosmos3-Super
65B • Updated • 127k • 263 -
VLM3: Vision Language Models Are Native 3D Learners
Paper • 2605.30561 • Published • 24 -
Cosmos 3: Omnimodal World Models for Physical AI
Paper • 2606.02800 • Published • 142 -
Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation
Paper • 2606.04527 • Published • 28 -
Personal AI Agent for Camera Roll VQA
Paper • 2606.05275 • Published • 20 -
Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing
Paper • 2606.05172 • Published • 2 -
Representation Forcing for Bottleneck-Free Unified Multimodal Models
Paper • 2605.31604 • Published • 61 -
Watch, Remember, Reason: Human-View Video Understanding with MLLMs
Paper • 2606.07433 • Published • 20 -
Latent Spatial Memory for Video World Models
Paper • 2606.09828 • Published • 71 -
CoVEBench: Can Video Editing Models Handle Complex Instructions?
Paper • 2606.08415 • Published • 53 -
Trajectory-Refined Distillation
Paper • 2606.08432 • Published • 6 -
CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
Paper • 2509.22647 • Published • 38 -
Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation
Paper • 2602.11401 • Published -
HiDream-ai/HiDream-O1-Image
Image-Text-to-Image • 9B • Updated • 6.07k • 551 -
Kwai Keye-VL-2.0 Technical Report
Paper • 2606.10651 • Published • 102 -
MiniMax Sparse Attention
Paper • 2606.13392 • Published • 168 -
InterleaveThinker: Reinforcing Agentic Interleaved Generation
Paper • 2606.13679 • Published • 37 -
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data
Paper • 2606.13432 • Published • 63 -
Rethinking RAG in Long Videos: What to Retrieve and How to Use It?
Paper • 2606.13141 • Published • 34 -
Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions
Paper • 2606.09076 • Published • 67 -
JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence
Paper • 2606.14777 • Published • 217 -
VisualClaw: A Real-Time, Personalized Agent for the Physical World
Paper • 2606.16295 • Published • 28 -
Memento: Reconstruct to Remember for Consistent Long Video Generation
Paper • 2606.14667 • Published • 18 -
PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions
Paper • 2606.14832 • Published • 11 -
Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification
Paper • 2606.18249 • Published • 15 -
Sumi: Open Uniform Diffusion Language Model from Scratch
Paper • 2606.19005 • Published • 12 -
PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models
Paper • 2606.19534 • Published • 66 -
DanceOPD: On-Policy Generative Field Distillation
Paper • 2606.27377 • Published • 84 -
Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation
Paper • 2606.26907 • Published • 55 -
Qwen-Image-2.0-RL Technical Report
Paper • 2606.27608 • Published • 54 -
deepseek-ai/DeepSeek-V4-Pro-DSpark
Text Generation • 1.7T • Updated • 4.47k • 541 -
LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing
Paper • 2606.26740 • Published • 81 -
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
Paper • 2607.00248 • Published • 30 -
PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space
Paper • 2607.05373 • Published • 41 -
ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
Paper • 2607.04438 • Published • 60 -
Wan-Streamer v0.2: Higher Resolution, Same Latency
Paper • 2607.04443 • Published • 41 -
quanhaol/DiffusionOPD
Text-to-Image • Updated • 1 -
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Paper • 2607.07675 • Published • 63 -
Video Generation Models are General-Purpose Vision Learners
Paper • 2607.09024 • Published • 82 -
Trust Region Policy Distillation
Paper • 2607.04751 • Published • 33 -
Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget
Paper • 2607.13125 • Published • 138 -
KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill
Paper • 2607.12625 • Published • 55 -
Registers Matter for Pixel-Space Diffusion Transformers
Paper • 2605.16147 • Published • 18 -
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
Paper • 2606.29538 • Published • 144 -
Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence
Paper • 2607.16401 • Published • 44 -
Bridging Supervised Learning and Reinforcement Learning in Math Reasoning
Paper • 2505.18116 • Published • 5 -
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
Paper • 2607.19064 • Published • 77 -
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
Paper • 2607.19191 • Published • 113 -
Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis
Paper • 2603.06507 • Published • 7 -
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Paper • 2410.06940 • Published • 14 -
ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding
Paper • 2507.14533 • Published • 9 -
moonshotai/Kimi-K3
Image-Text-to-Text • 2.8T • Updated • 1.7M • • 11.5k -
MiniMaxAI/MiniMax-H3
Image-Text-to-Video • 33B • Updated • 3.66M • • 5.68k -
openbmb/MiniCPM-V-4.6
Image-Text-to-Text • 1B • Updated • 389k • 1.22k -
AgPerry/rsi-bench
Viewer • Updated • 300 • 95 • 2 -
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
Paper • 2607.07508 • Published • 32 -
Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
Paper • 2504.02792 • Published • 4 -
Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
Paper • 2601.16163 • Published • 15 -
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
Paper • 2607.28227 • Published • 157 -
GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?
Paper • 2608.21833 • Published • 18 -
EchoWM: Open and Enterable Omnimodal World Models
Paper • 2608.23189 • Published • 79