by
  • Strategies for preparing effective academic conference posters

    Conference & Academic Exchange

    A good poster needs concise logic, readable visuals and clear core conclusions. Avoid stuffing excessive text; reserve space for communication with onsite peers.

    Jeffrey Clark, Jason Sanchez and 53 others
    6 Comments
    View more comments
  • Small‑domain fine‑tuning: is parameter‑efficient fine‑tuning always the opti...

    Research Idea

    PEFT methods are everywhere these days. But I’m starting to question: for extremely niche small‑size domain data, are LoRA/QLoRA consistently better than full fine‑tune with careful regularization? Would love real‑world hands‑on observations, not just paper results.

    Matthew Wilson, Tping and 4 others
    3 Comments
    View more comments
    • From my limited tests: full fine‑tune can still outperform LoRA if you have decent regularization, though memory cost is obviously way higher.

      14
      • It also depends on how domain‑different your target corpus is from the base model’s training data. Big domain gap usually favors PEFT.

        71
        • View more comments