DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
Paper • 2605.25604 • Published • 124
Bingzheng Wei
Bingzheng
AI & ML interests
None yet
Recent Activity
upvoted a paper about 15 hours ago
DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning upvoted a paper about 15 hours ago
SkillOpt: Executive Strategy for Self-Evolving Agent SkillsOrganizations
None yet
upvoted 2
papers about 15 hours ago
upvoted 5
papers 3 days ago
See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding
Paper • 2605.18018 • Published • 30
Rethinking Cross-Layer Information Routing in Diffusion Transformers
Paper • 2605.20708 • Published • 101
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Paper • 2605.21573 • Published • 98
StepAudio 2.5 Technical Report
Paper • 2605.23463 • Published • 45
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
Paper • 2605.21467 • Published • 202
upvoted 6
papers 6 days ago
Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
Paper • 2605.18233 • Published • 90
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
Paper • 2605.22012 • Published • 44
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
Paper • 2605.14678 • Published • 100
FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching
Paper • 2605.20910 • Published • 28
Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning
Paper • 2605.22642 • Published • 35
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
Paper • 2605.14747 • Published • 143
upvoted 4
papers 7 days ago
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond
Paper • 2605.19660 • Published • 39
Generative Recursive Reasoning
Paper • 2605.19376 • Published • 29
When Vision Speaks for Sound
Paper • 2605.16403 • Published • 148
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Paper • 2605.11609 • Published • 191
upvoted 3
papers 8 days ago
GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
Paper • 2605.19577 • Published • 56
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
Paper • 2605.19769 • Published • 57
Process Rewards with Learned Reliability
Paper • 2605.15529 • Published • 52