OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation
Paper
• 2601.15369 • Published
• 21
My notification
-
-
Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model
Paper • 2601.15892 • Published • 53 -
Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
Paper • 2601.16208 • Published • 54 -
NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems
Paper • 2601.11004 • Published • 30 -
Behavior Knowledge Merge in Reinforced Agentic Models
Paper • 2601.13572 • Published • 26 -
microsoft/VibeVoice-ASR
Automatic Speech Recognition • 9B • Updated • 670k • 907 -
zai-org/GLM-4.7-Flash
Text Generation • Updated • 1.74M • • 1.61k -
LongCat-Flash-Thinking-2601 Technical Report
Paper • 2601.16725 • Published • 178 -
iFSQ: Improving FSQ for Image Generation with 1 Line of Code
Paper • 2601.17124 • Published • 33 -
Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs
Paper • 2601.17058 • Published • 190 -
Less is More: Optimizing Function Calling for LLM Execution on Edge Devices
Paper • 2411.15399 • Published • 1 -
nvidia/personaplex-7b-v1
Audio-to-Audio • Updated • 477k • 2.27k -
Qwen/Qwen3-ASR-0.6B
Automatic Speech Recognition • Updated • 338k • 234 -
Qwen3-ASR Technical Report
Paper • 2601.21337 • Published • 36 -
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Paper • 2601.19895 • Published • 25 -
DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
Paper • 2601.22153 • Published • 73 -
Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models
Paper • 2601.20354 • Published • 111 -
Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation
Paper • 2601.21406 • Published • 5 -
Revisiting Parameter Server in LLM Post-Training
Paper • 2601.19362 • Published • 8 -
ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation
Paper • 2601.21420 • Published • 42 -
SERA: Soft-Verified Efficient Repository Agents
Paper • 2601.20789 • Published • 13 -
moonshotai/Kimi-K2.5
Image-Text-to-Text • 1.1T • Updated • 2.69M • • 2.27k -
DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation
Paper • 2601.22904 • Published • 15 -
Phr00t/LTX2-Rapid-Merges
Image-Text-to-Video • Updated • 336 -
ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought
Paper • 2601.23184 • Published • 36 -
FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space
Paper • 2602.02092 • Published • 18 -
PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss
Paper • 2602.02493 • Published • 44 -
TTCS: Test-Time Curriculum Synthesis for Self-Evolving
Paper • 2601.22628 • Published • 35 -
RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
Paper • 2602.02488 • Published • 33 -
Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models
Paper • 2602.02185 • Published • 115 -
Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization
Paper • 2601.21358 • Published • 7 -
Balancing Understanding and Generation in Discrete Diffusion Models
Paper • 2602.01362 • Published • 17 -
3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation
Paper • 2602.03796 • Published • 62 -
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
Paper • 2602.01785 • Published • 95 -
LIVE: Long-horizon Interactive Video World Modeling
Paper • 2602.03747 • Published • 12 -
Qwen/Qwen3-Coder-Next
Text Generation • 80B • Updated • 1.16M • • 1.12k -
Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers
Paper • 2602.03510 • Published • 27 -
RISE-Video: Can Video Generators Decode Implicit World Rules?
Paper • 2602.05986 • Published • 26 -
FASA: Frequency-aware Sparse Attention
Paper • 2602.03152 • Published • 150 -
DFlash: Block Diffusion for Flash Speculative Decoding
Paper • 2602.06036 • Published • 43 -
GEBench: Benchmarking Image Generation Models as GUI Environments
Paper • 2602.09007 • Published • 39 -
When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
Paper • 2602.08236 • Published • 9 -
AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research
Paper • 2602.06540 • Published • 21 -
Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models
Paper • 2602.04649 • Published • 12 -
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
Paper • 2602.05400 • Published • 347 -
AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders
Paper • 2602.05027 • Published • 60 -
Judging What We Cannot Solve: A Consequence-Based Approach for Oracle-Free Evaluation of Research-Level Math
Paper • 2602.06291 • Published • 23 -
Towards Autonomous Mathematics Research
Paper • 2602.10177 • Published • 36 -
Free(): Learning to Forget in Malloc-Only Reasoning Models
Paper • 2602.08030 • Published • 5 -
Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
Paper • 2602.07775 • Published • 8 -
TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
Paper • 2602.08711 • Published • 28 -
Qute: Towards Quantum-Native Database
Paper • 2602.14699 • Published • 13 -
Qwen/Qwen3.5-397B-A17B
Image-Text-to-Text • 403B • Updated • 1.66M • • 1.3k -
DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning
Paper • 2602.16742 • Published • 12 -
tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
Paper • 2602.20160 • Published • 10 -
From Perception to Action: An Interactive Benchmark for Vision Reasoning
Paper • 2602.21015 • Published • 23 -
SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model
Paper • 2602.21818 • Published • 52 -
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
Paper • 2602.24286 • Published • 85 -
From Scale to Speed: Adaptive Test-Time Scaling for Image Editing
Paper • 2603.00141 • Published • 134 -
RubricBench: Aligning Model-Generated Rubrics with Human Standards
Paper • 2603.01562 • Published • 57 -
SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale
Paper • 2602.23866 • Published • 82 -
Qwen3-Coder-Next Technical Report
Paper • 2603.00729 • Published • 44 -
CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video
Paper • 2603.04291 • Published • 13 -
Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling
Paper • 2603.04791 • Published • 16 -
InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions
Paper • 2603.03646 • Published • 8 -
Utonia: Toward One Encoder for All Point Clouds
Paper • 2603.03283 • Published • 164 -
DreamWorld: Unified World Modeling in Video Generation
Paper • 2603.00466 • Published • 16 -
On-Policy Self-Distillation for Reasoning Compression
Paper • 2603.05433 • Published • 6 -
fal/virtual-tryoff-lora
Image-to-Image • Updated • 548 • 24 -
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
Paper • 2603.06569 • Published • 97 -
PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstruction
Paper • 2603.05888 • Published • 2 -
Scale Space Diffusion
Paper • 2603.08709 • Published • 11