DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
Paper • 2605.25604 • Published • 139
LuYanFCP
LuYanFCP123
AI & ML interests
None yet
Organizations
None yet
upvoted a paper 2 months ago
upvoted 8
papers 10 months ago
When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity
Paper • 2509.20293 • Published • 8
Thinking While Listening: Simple Test Time Scaling For Audio Classification
Paper • 2509.19676 • Published • 5
MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal Reasoning
Paper • 2509.21113 • Published • 6
Behind RoPE: How Does Causal Mask Encode Positional Information?
Paper • 2509.21042 • Published • 10
Quantized Visual Geometry Grounded Transformer
Paper • 2509.21302 • Published • 9
ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning
Paper • 2509.21070 • Published • 9
Residual Off-Policy RL for Finetuning Behavior Cloning Policies
Paper • 2509.19301 • Published • 20
VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models
Paper • 2509.19803 • Published • 122