-
MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data
Paper • 2603.25319 • Published • 32 -
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
Paper • 2603.25040 • Published • 131 -
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding
Paper • 2603.22458 • Published • 135 -
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model
Paper • 2603.21986 • Published • 123
Collections
Discover the best community collections!
Collections including paper arxiv:2603.22458
-
Endless Terminals: Scaling RL Environments for Terminal Agents
Paper • 2601.16443 • Published • 18 -
Linear representations in language models can change dramatically over a conversation
Paper • 2601.20834 • Published • 21 -
Scaling Embeddings Outperforms Scaling Experts in Language Models
Paper • 2601.21204 • Published • 102 -
Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
Paper • 2601.18778 • Published • 42
-
LTX-2: Efficient Joint Audio-Visual Foundation Model
Paper • 2601.03233 • Published • 176 -
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Paper • 2601.07832 • Published • 52 -
Motion Attribution for Video Generation
Paper • 2601.08828 • Published • 72 -
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Paper • 2601.19895 • Published • 27
-
HunyuanOCR Technical Report
Paper • 2511.19575 • Published • 22 -
DeepSeek-OCR 2: Visual Causal Flow
Paper • 2601.20552 • Published • 68 -
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
Paper • 2602.01785 • Published • 96 -
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding
Paper • 2603.22458 • Published • 135
-
dLLM: Simple Diffusion Language Modeling
Paper • 2602.22661 • Published • 152 -
OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
Paper • 2603.15594 • Published • 149 -
Qianfan-OCR: A Unified End-to-End Model for Document Intelligence
Paper • 2603.13398 • Published • 153 -
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
Paper • 2603.06569 • Published • 119
-
OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation
Paper • 2601.15369 • Published • 21 -
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 • 55 -
NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems
Paper • 2601.11004 • Published • 30
-
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain
Paper • 2509.26507 • Published • 550 -
mHC: Manifold-Constrained Hyper-Connections
Paper • 2512.24880 • Published • 322 -
NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
Paper • 2601.00393 • Published • 133 -
LTX-2: Efficient Joint Audio-Visual Foundation Model
Paper • 2601.03233 • Published • 176
-
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Paper • 2503.09573 • Published • 77 -
Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective
Paper • 2505.15045 • Published • 56 -
Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding
Paper • 2505.16990 • Published • 22 -
D-AR: Diffusion via Autoregressive Models
Paper • 2505.23660 • Published • 34
-
MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data
Paper • 2603.25319 • Published • 32 -
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
Paper • 2603.25040 • Published • 131 -
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding
Paper • 2603.22458 • Published • 135 -
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model
Paper • 2603.21986 • Published • 123
-
dLLM: Simple Diffusion Language Modeling
Paper • 2602.22661 • Published • 152 -
OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
Paper • 2603.15594 • Published • 149 -
Qianfan-OCR: A Unified End-to-End Model for Document Intelligence
Paper • 2603.13398 • Published • 153 -
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
Paper • 2603.06569 • Published • 119
-
Endless Terminals: Scaling RL Environments for Terminal Agents
Paper • 2601.16443 • Published • 18 -
Linear representations in language models can change dramatically over a conversation
Paper • 2601.20834 • Published • 21 -
Scaling Embeddings Outperforms Scaling Experts in Language Models
Paper • 2601.21204 • Published • 102 -
Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
Paper • 2601.18778 • Published • 42
-
OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation
Paper • 2601.15369 • Published • 21 -
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 • 55 -
NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems
Paper • 2601.11004 • Published • 30
-
LTX-2: Efficient Joint Audio-Visual Foundation Model
Paper • 2601.03233 • Published • 176 -
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Paper • 2601.07832 • Published • 52 -
Motion Attribution for Video Generation
Paper • 2601.08828 • Published • 72 -
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Paper • 2601.19895 • Published • 27
-
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain
Paper • 2509.26507 • Published • 550 -
mHC: Manifold-Constrained Hyper-Connections
Paper • 2512.24880 • Published • 322 -
NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
Paper • 2601.00393 • Published • 133 -
LTX-2: Efficient Joint Audio-Visual Foundation Model
Paper • 2601.03233 • Published • 176
-
HunyuanOCR Technical Report
Paper • 2511.19575 • Published • 22 -
DeepSeek-OCR 2: Visual Causal Flow
Paper • 2601.20552 • Published • 68 -
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
Paper • 2602.01785 • Published • 96 -
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding
Paper • 2603.22458 • Published • 135
-
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Paper • 2503.09573 • Published • 77 -
Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective
Paper • 2505.15045 • Published • 56 -
Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding
Paper • 2505.16990 • Published • 22 -
D-AR: Diffusion via Autoregressive Models
Paper • 2505.23660 • Published • 34