← Search

Shaolun Zhang

2 accepted papers

2025

SegLLM: Multi-round Reasoning Segmentation with Large Language Models

ICLR 2025poster

We present SegLLM, a novel multi-round interactive reasoning segmentation model that enhances LLM-based segmentation by exploiting conversational memory of both visual and textual outputs. By leveraging a mask-aware multimodal LLM, SegLLM re-integrates previous segmentation results into its input st…

Cited by 0SourcePDFScholar
2024

Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics

NeurIPS 2024poster

Auto-regressive large language models (LLMs) show impressive capacities to solve many complex reasoning tasks while struggling with some simple logical reasoning tasks such as inverse search: when trained on ''$A \to B$'' (e.g., *Tom is the parent of John*), LLM fails to directly conclude ''$B \gets…