Papers by Heng Tian

4 papers
Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization (2026.acl-long)

Copied to clipboard

Challenge: Recent studies show that supervised fine-tuning (SFT) is a common approach for reasoning in large language models.
Approach: They propose to use supervised fine-tuning (SFT) on chain-of-thought trajectories demonstrations . they find that incorporating negative traxories yields substantial OOD generalization gains .
Outcome: The proposed scheme yields 5.51% OOD gain over positive-only training.
Specialization without Sparsity: Efficient and Expressive Split-Path Experts for LLM Fine-Tuning (2026.findings-acl)

Copied to clipboard

Challenge: Parameter-efficient fine-tuning (PEFT) is a low-cost alternative to full fine-timing due to the massive overhead.
Approach: They propose a Mixture-of-Experts approach that enhances specialization while maintaining low resource overhead.
Outcome: The proposed approach outperforms or matches state-of-the-art methods on GLUE, GSM8K, MBPP, and a text rewriting task from SmolTalk.
Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for timeline summarization ignore the events’ intra-structures and inter-structure connections.
Approach: They propose to represent news articles as an event-graph, thus compressing the whole graph to its salient sub-graph.
Outcome: The proposed method significantly improves on the state-of-the-art on three real-world datasets, including two public benchmarks and a Timeline100 dataset.
ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding (2026.findings-acl)

Copied to clipboard

Challenge: Existing omni-multimodal large language models lack incomplete modality support or lack autonomous proactive monitoring.
Approach: They propose a real-time omni-multimodal assistant for unified reactive and proactive interaction that decouples response initiation from generation to ensure precise triggering without task conflict.
Outcome: The proposed model achieves state-of-the-art performance on proactive tasks while competing in reactive settings.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations