1 citations · 1 across the 4 of their papers we have counts for
6 papers
Same molecule, Different Knowledge: Cross-Identifier Binding Failures in LLMs For chemistry
Khouloud Saadi, Di Wang
Chemical AI workflows routinely represent the same molecule through multiple co-referring identifiers, including trivial names, IUPAC names, and SMILES, implicitly assuming that th…
One Teacher, Many Views: Reducing Reference Sensitivity in On-Policy Self-Distillation
Khouloud Saadi, Di Wang
On-policy self-distillation (OPSD) improves reasoning by training a model on its own trajectories with dense token-level supervision from a privileged copy conditioned on a referen…
Validity-Calibrated Reasoning Distillation
Khouloud Saadi, Di Wang
Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent methods have shown promising gain…
What Should Feature Distillation Transfer in LLMs? A Task-Tangent Geometry View
Khouloud Saadi, Di Wang
Feature-based knowledge distillation aims to transfer intermediate representations from a teacher LLM model to a student. Existing approaches typically rely on direct feature match…
Dissecting Representation Misalignment in Contrastive Learning via Influence Function
Lijie Hu, Chenyang Ren, Huanyi Xie +5
Contrastive learning, commonly applied in large-scale multimodal models, often relies on data from diverse and often unreliable sources, which can include misaligned or mislabeled…
Effective prevention of semantic drift as angular distance in memory-less continual deep neural networks
Khouloud Saadi, Muhammad Taimoor Khan
Lifelong machine learning or continual learning models attempt to learn incrementally by accumulating knowledge across a sequence of tasks. Therefore, these models learn better and…