collaborators

9 papers

cs.LG2026

SemStruct: Contextualizing Semantic Embeddings with Structural Information for Schema Matching

Inwon Kang, Kavitha Srinivas, Nandana Mihindukulasooriya +4

Schema matching is a fundamental step in integrating heterogeneous data sources. While Pre-trained Language Models (PLMs) have revolutionized this task by capturing linguistic sema…

cs.LG2026

Balancing Multi-modal Sensor Learning via Multi-objective Optimization

Heshan Fernando, Quan Xiao, Parikshit Ram +4

Learning-enabled control systems increasingly rely on multiple sensing modalities (e.g., vision, audio, language, etc.) for perception and decision support. A key challenge is that…

cs.CL2026

Language Model Representations for Efficient Few-Shot Tabular Classification

Inwon Kang, Parikshit Ram, Yi Zhou +2

The Web is a rich source of structured data in the form of tables, from product catalogs and knowledge bases to scientific datasets. However, the heterogeneity of the structure and…

cs.LG2025

Understanding Forgetting in LLM Supervised Fine-Tuning and Preference Learning -- A Convex Optimization Perspective

Heshan Fernando, Han Shen, Parikshit Ram +4

The post-training of LLMs, which typically consists of the supervised fine-tuning (SFT) stage and the preference learning stage (RLHF or DPO), is crucial to effective and safe LLM…

cs.AI2025

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills

Changsheng Wang, Chongyu Fan, Yihua Zhang +5

Recent advances in large reasoning models (LRMs) have enabled strong chain-of-thought (CoT) generation through test-time computation. While these multi-step reasoning capabilities…

cs.LG2025

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning

Changsheng Wang, Yihua Zhang, Jinghan Jia +6

Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. H…