A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space
Paper • 2511.10555 • Published • 63
toread
-
-
Scaling Latent Reasoning via Looped Language Models
Paper • 2510.25741 • Published • 241 -
Depth Anything 3: Recovering the Visual Space from Any Views
Paper • 2511.10647 • Published • 103 -
The Trinity of Consistency as a Defining Principle for General World Models
Paper • 2602.23152 • Published • 190 -
Your Group-Relative Advantage Is Biased
Paper • 2601.08521 • Published • 158 -
Continuous Latent Diffusion Language Model
Paper • 2605.06548 • Published • 89 -
Kimi K3: Open Frontier Intelligence
Paper • 2607.24653 • Published • 537 -
Attention Residuals
Paper • 2603.15031 • Published • 202 -
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
Paper • 2609.22068 • Published • 138 -
VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models
Paper • 2606.16140 • Published • 128 -
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Paper • 2609.14858 • Published • 233 -
Process-Verified Reinforcement Learning for Theorem Proving via Lean
Paper • 2606.20068 • Published -
DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
Paper • 2504.21801 • Published • 9 -
MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement
Paper • 2610.11959 • Published • 90 -
Recursive Self-Improvement through Multi-Agent Self-Supervision
Paper • 2610.12176 • Published • 4 -
A Fix for Softmax and Cross-Entropy
Paper • 2610.31642 • Published • 4