TIP: Token Importance in On-Policy Distillation
Paper • 2604.14084 • Published • 14
XYX
xuyd16
AI & ML interests
None yet
Recent Activity
upvoted a paper 4 days ago
TIP: Token Importance in On-Policy Distillation liked a model 13 days ago
deepseek-ai/DeepSeek-V4-ProOrganizations
None yet
upvoted a paper 4 days ago
liked a
model 13 days ago
upvoted 4
papers 21 days ago
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models
Paper • 2604.10866 • Published • 65
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
Paper • 2604.14144 • Published • 63
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
Paper • 2604.11626 • Published • 101
Seedance 2.0: Advancing Video Generation for World Complexity
Paper • 2604.14148 • Published • 154
submitted a
paper to Daily Papers 21 days ago
submitted a
paper to Daily Papers about 2 months ago
authored 4
papers about 2 months 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 2 months 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