Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks9 from public data
- 40
- A General Framework for Producing Interpretable Semantic Text Embeddings15
This work introduces \algo{CQG-MBQA} (Contrastive Question Generation - Multi-task Binary Question Answering), a general framework for producing interpretable semantic text embeddings across diverse tasks and demonstrates that it delivers embedding quality comparable to many advanced black-box models while maintaining inherently interpretability.
- One Swallow Does Not Make a Summer: Understanding Semantic Structures in Embedding Spaces7
The Semantic Field Subspace (SFS), a geometry-preserving, context-aware representation that captures local semantic neighborhoods within the embedding space, is introduced, and an efficient approximation of Semantic Shift is developed that replaces costly SVD computations, achieving a 15~30x speedup with average errors below 0.01.
- Can Reasoning Power Significantly Improve the Knowledge of Large Language Models for Chemistry?─Based on Conversations with LLMs7
It is demonstrated that reasoning-enabled LLMs achieve significant performance improvements in fundamental tasks and that, in most cases, overly complex prompts are not beneficial for these models, and the necessity of developing domain-optimized training paradigms to bridge the gap between general reasoning capabilities and specialized chemical applications.
- Adversarial Mixup Unlearning6
This work introduces a novel approach that regularizes the unlearning process by utilizing synthesized mixup samples, which simulate the data susceptible to catastrophic effects, and lays the foundation for effective machine unlearning with mixup augmentation.
- 2
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.