◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

DiJia Su

8 papers hereh-index 7819 citations10 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author3
  • middle author4

Across the 7 of 8 papers where every author was matched, so the position is known.

fields
  • cs.CL3
  • cs.AI2
  • cs.LG2
  • cs.SE1

identity via Semantic Scholar / OpenAlex

collaborators
Showing cs.AIShow all

2 papers · 1 filter

cs.AI2026

Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training

Yixin Liu, Yue Yu, DiJia Su +7

Reasoning LLMs-as-Judges, which can benefit from inference-time scaling, provide a promising path for extending the success of reasoning models to non-verifiable domains where the…

cs.AI2025

Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces

DiJia Su, Sainbayar Sukhbaatar, Michael Rabbat +2

In cognition theory, human thinking is governed by two systems: the fast and intuitive System 1 and the slower but more deliberative System 2. Analogously, Large Language Models (L…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.