- AIED
Reliability as a Teammate: Budgeted Verifier-in-the-Loop (BVIL) Policies for Reliable LLM Tutoring Actions
Artificial Intelligence in Education (AIED 2026), Springer LNAI 16583
PaperSummary
Policies for deciding when to invoke verification under a budget, with the goal of making LLM tutoring actions more reliable.
- IJCV
Context Aware Grounded Teacher for Source Free Object Detection
International Journal of Computer Vision, 134, Article 306 (2026)
* Equal Contribution
PaperSummary
A context-aware teacher framework for source-free object detection that addresses class imbalance and unstable pseudo-labels.
- REALM
DySAS: Dynamic State-Aware Student Simulation Beyond Static Personas
Research on Agent Language Models (REALM) Workshop at EMNLP 2026 · Accepted
WorkshopSummary
Psychologically grounded student simulation with evolving states, designed to evaluate adaptive LLM tutors across multi-turn interactions.
- FAGEN
When Thinking Before Retrieval Hurts: TraceBound Diagnostics for Adaptive Knowledge-Graph Retrieval
Failure Modes in Agentic AI (FAGEN) Workshop at ICML 2026 · Accepted
Workshop papers are identified by their workshop and host conference. See also Google Scholar.