Adaptive Reward Routing Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL paper:

AK @_akhaliq ·
Adaptive Reward Routing Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forwa…

更多来自 @_akhaliq

  1. #1

    OmniReasoning Pushing the Limits of Audio-Visual Joint Reasoning paper:

    AK @_akhaliq ·
    OmniReasoning Pushing the Limits of Audio-Visual Joint Reasoning paper:
  2. #2

    ALoDLM Adaptively Looped Diffusion Language Models paper:

    AK @_akhaliq ·
    ALoDLM Adaptively Looped Diffusion Language Models paper:
  3. #3

    Rollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation paper:

    AK @_akhaliq ·
    视频封面
  4. #4

    Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite paper:

    AK @_akhaliq ·
    Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite paper:
  5. #5

    Octrees as an Explicit 3D Language paper:

    AK @_akhaliq ·
    视频封面
  6. #6

    EditHero A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling paper:

    AK @_akhaliq ·
    视频封面

查看 @_akhaliq 的全部帖子