$T^5$: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training
Paper • 2609.32791 • Published • 1
AI & ML interests
None defined yet.
Recent Activity
Papers
Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL
Draft-KV: Learning Useful Latent Communication Between Language Models
psp-dada
authored a
paper 2 days ago
EddieYang428
submitted a
paper to Daily Papers 2 days ago
Svard
submitted a
paper to Daily Papers 5 days ago
huaXiaKyrie
submitted a
paper to Daily Papers 5 days ago
kailinjiang
submitted a
paper to Daily Papers 5 days ago
YanZhanPKU
submitted a
paper to Daily Papers 6 days ago
EddieYang428
submitted a
paper to Daily Papers 10 days ago
wbhu-tc
authored a
paper 11 days ago
wbhu-tc
authored 6
papers 12 days ago
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
Paper • 2609.24984 • Published • 157
RayPE: Ray-Space Positional Encoding for 3D-Aware Video Generation
Paper • 2606.27345 • Published • 1
Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
Paper • 2603.02573 • Published • 13
Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers
Paper • 2604.21592 • Published • 1
MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE
Paper • 2602.08961 • Published • 5
Pixal3D: Pixel-Aligned 3D Generation from Images
Paper • 2605.10922 • Published • 34
xiaoxiaoshadiao
updated 2
models 12 days ago
Longin-Yu
submitted a
paper to Daily Papers 16 days ago
Longin-Yu
updated a
collection 16 days ago
Longin-Yu
updated 2
models 16 days ago