Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
Paper • 2610.08077 • Published • 131
Minhyeok
minnkim199
AI & ML interests
None yet
Recent Activity
upvoted a paper about 18 hours ago
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight upvoted a paper about 18 hours ago
SGF+: Decoupling Gradient Flows for Autoregressive Video Generation upvoted a paper about 18 hours ago
UniWAM: Unified World-Action ModelOrganizations
None yet
upvoted 9
papers about 18 hours ago
SGF+: Decoupling Gradient Flows for Autoregressive Video Generation
Paper • 2610.10429 • Published • 55
UniWAM: Unified World-Action Model
Paper • 2610.02054 • Published • 53
Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective
Paper • 2610.03185 • Published • 29
Semifactual Credit-Augmented Policy Optimization
Paper • 2609.40360 • Published • 31
Questioning the Questions: Sustaining Self-Evolution in Reasoning Models
Paper • 2610.04299 • Published • 68
Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards
Paper • 2610.02967 • Published • 23
V-CoLA: Vision Token Compression with Linear Attention
Paper • 2610.11251 • Published • 9
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
Paper • 2610.12299 • Published • 41
upvoted 7
papers 7 days ago
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
Paper • 2609.39045 • Published • 93
Beyond Pixels: From Video Priors to 4D Worlds
Paper • 2608.10744 • Published • 192
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence
Paper • 2609.17488 • Published • 559
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
Paper • 2609.39982 • Published • 119
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 397
Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation
Paper • 2609.38024 • Published • 64
World Observer: Joint Actor-Observer Generation for Persistent World Modeling
Paper • 2610.02162 • Published • 88