What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
Paper • 2609.34981 • Published • 138
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
Linearizing Vision Transformer with Test-Time Training
rpzhou
submitted a
paper to Daily Papers 11 days ago
LemonTea03
submitted a
paper to Daily Papers 11 days ago
LemonTea03
authored 3
papers 11 days ago
On-policy Distillation with Verifiable Reward
Paper • 2608.24696 • Published • 17
Thickening-to-Thinning: Reward Shaping via Human-Inspired Learning Dynamics for LLM Reasoning
Paper • 2602.04265 • Published
From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
Paper • 2605.22074 • Published • 2
JiayiGuo821
authored 4
papers about 2 months ago
InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
Paper • 2605.14333 • Published • 33
Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models
Paper • 2604.25636 • Published • 25
Elastic Diffusion Transformer
Paper • 2602.13993 • Published
FastVMT: Eliminating Redundancy in Video Motion Transfer
Paper • 2602.05551 • Published • 3
lucasleeeee
submitted a
paper to Daily Papers 4 months ago
lucasleeeee
authored a
paper 4 months ago
yueyang2000
authored 2
papers 5 months ago
yueyang2000
submitted a
paper to Daily Papers 5 months ago
yueyang2000
authored 6
papers 5 months ago
EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones
Paper • 2211.09703 • Published
AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition
Paper • 2112.14238 • Published
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Paper • 2505.03335 • Published • 191
Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Model
Paper • 2512.22288 • Published • 3
Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models
Paper • 2604.25636 • Published • 25
Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
Paper • 2605.05781 • Published • 5