Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Paper • 2605.21573 • Published • 106
Kaixu Chen
kaixuChen
AI & ML interests
None yet
Recent Activity
upvoted a paper 7 days ago
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models upvoted a paper 10 days ago
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows upvoted a paper 13 days ago
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code SynthesisOrganizations
None yet
upvoted a paper 7 days ago
upvoted a paper 10 days ago
upvoted a paper 13 days ago
upvoted an article 18 days ago
Article
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
NormalUhr
• • 125 upvoted 2
papers 4 months ago
upvoted a paper 11 months ago
upvoted 7
papers about 1 year ago
AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
Paper • 2505.23716 • Published • 31
MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space
Paper • 2504.13835 • Published • 38
GaussianAnything: Interactive Point Cloud Latent Diffusion for 3D Generation
Paper • 2411.08033 • Published • 25
NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenes
Paper • 2503.16375 • Published • 10
Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation
Paper • 2503.13424 • Published • 30
Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM
Paper • 2503.14478 • Published • 48
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning
Paper • 2503.07365 • Published • 61