TIP: Token Importance in On-Policy Distillation
Paper • 2604.14084 • Published • 11
XYX
xuyd16
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
TIP: Token Importance in On-Policy DistillationOrganizations
None yet
upvoted 5
papers 2 days ago
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models
Paper • 2604.10866 • Published • 58
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
Paper • 2604.14144 • Published • 61
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
Paper • 2604.11626 • Published • 99
Seedance 2.0: Advancing Video Generation for World Complexity
Paper • 2604.14148 • Published • 136
submitted a
paper to Daily Papers 3 days ago
submitted a
paper to Daily Papers about 1 month ago
authored 4
papers about 1 month ago
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
Paper • 2602.21420 • Published • 6
On-Policy Self-Distillation for Reasoning Compression
Paper • 2603.05433 • Published • 8
Not all tokens are needed(NAT): token efficient reinforcement learning
Paper • 2603.06619 • Published • 1
PACED: Distillation at the Frontier of Student Competence
Paper • 2603.11178 • Published • 4
upvoted 3
papers about 1 month ago
PACED: Distillation at the Frontier of Student Competence
Paper • 2603.11178 • Published • 4
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
Paper • 2602.21420 • Published • 6
Flash-KMeans: Fast and Memory-Efficient Exact K-Means
Paper • 2603.09229 • Published • 82