Dahua Lin

lindahua's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 4 days ago

Visual Agentic Reinforcement Fine-Tuning

Paper • 2505.14246 • Published 5 days ago • 31

authored 3 papers about 1 month ago

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Paper • 2504.10479 • Published Apr 14 • 260

MM-IFEngine: Towards Multimodal Instruction Following

Paper • 2504.07957 • Published Apr 10 • 34

GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography

Paper • 2504.07083 • Published Apr 9 • 23

authored a paper about 2 months ago

HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance

Paper • 2504.06232 • Published Apr 8 • 14

authored 3 papers 2 months ago

LEGION: Learning to Ground and Explain for Synthetic Image Detection

Paper • 2503.15264 • Published Mar 19 • 21

Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM

Paper • 2503.14478 • Published Mar 18 • 48

Long Context Tuning for Video Generation

Paper • 2503.10589 • Published Mar 13 • 14

authored 5 papers 3 months ago

Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs

Paper • 2503.02846 • Published Mar 4 • 19

Visual-RFT: Visual Reinforcement Fine-Tuning

Paper • 2503.01785 • Published Mar 3 • 78

SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation

Paper • 2502.13128 • Published Feb 18 • 42

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Paper • 2502.06781 • Published Feb 10 • 61

VideoRoPE: What Makes for Good Video Rotary Position Embedding?

Paper • 2502.05173 • Published Feb 7 • 65

authored a paper 4 months ago

InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model

Paper • 2501.12368 • Published Jan 21 • 46

authored 6 papers 5 months ago

Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction

Paper • 2501.03218 • Published Jan 6 • 37

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning

Paper • 2501.03226 • Published Jan 6 • 45

IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations

Paper • 2412.12083 • Published Dec 16, 2024 • 12

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

Paper • 2412.09596 • Published Dec 12, 2024 • 99

3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation

Paper • 2412.07759 • Published Dec 10, 2024 • 18

FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models

Paper • 2412.07674 • Published Dec 10, 2024 • 20