Hou Pong Chan

Researcher@Alibaba Group·新加坡·OpenReview

研究方向

multilingual · LLM safety · hallucination · factuality · RAG · controllable text generation · text summarization · keyphrase generation · reinforcement learning

4.0

Incentivizing Multimodal Reasoning via Progressive Curriculum Reinforcement Learning

ICLR 2026Rejected

6.8

Scaling Language-centric Omnimodal Representation Learning

NeurIPS 2025Poster

二作

6.4

Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning

NeurIPS 2025Poster

6.0

M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework

合作者 (20)