Paper Trail

Tag: pku

6 items with this tag.

  • Mar 25, 2026

    2026-03 MLLM

    • paper
    • image-generation-posttrain
    • hkust
    • tencent
    • pku
    • modality/video
  • Mar 18, 2026

    Safe RLHF: Safe Reinforcement Learning from Human Feedback

    • paper
    • reward-model
    • pku
    • modality/text
  • Mar 18, 2026

    Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

    • paper
    • reward-model
    • pku
    • deepseek
    • modality/text
  • Mar 18, 2026

    VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models

    • paper
    • reward-model
    • hku
    • pku
    • allen-ai
    • modality/image
    • modality/text
  • Mar 18, 2026

    LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation

    • paper
    • understanding-generation
    • multimodal
    • pku
  • Mar 18, 2026

    Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

    • paper
    • vision-tokenizer
    • multimodal
    • pku

Created with Quartz v4.5.2 © 2026

  • GitHub