Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards
Paper • 2610.02967 • Published • 29
Shreeyut Maheshwari
Shreeyut
AI & ML interests
NLP, Data Science , Computer Vision
Recent Activity
upvoted a paper 6 days ago
Scaling Reinforcement Learning for Diffusion Models via Velocity MatchingOrganizations
upvoted a paper 3 days ago
upvoted 5
papers 6 days ago
RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation
Paper • 2608.09226 • Published • 1
Scaling Reinforcement Learning for Diffusion Models via Velocity Matching
Paper • 2608.23664 • Published • 1
Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding
Paper • 2609.09300 • Published • 1
Video Generation Models: A Survey of Post-Training and Alignment
Paper • 2610.00812 • Published • 63
Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL
Paper • 2609.37200 • Published • 140
upvoted a paper 12 days ago
upvoted 2
papers about 1 month ago
upvoted 3
papers about 2 months ago
upvoted 6
papers 2 months ago
Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark
Paper • 2606.30170 • Published • 6
DrugGen 2: A disease-aware language model for enhancing drug discovery
Paper • 2607.08404 • Published • 19
OpenCoF: Learning to Reason Through Video Generation
Paper • 2607.08763 • Published • 27
DiFA: Inference-Time Forward-Process Alignment for Diffusion Models
Paper • 2607.17972 • Published • 8
Parallel Decoding Distillation for Fast Image and Video Generation
Paper • 2607.26004 • Published • 17
Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification
Paper • 2607.24027 • Published • 40
upvoted 2
papers 4 months ago