most citedTask-Level Contrastiveness for Cross-Domain Few-Shot Learning

1 citations · 1 across the 8 of their papers we have counts for

collaborators

8 papers

cs.LG2026

Outer-Momentum Restarting in High-Dimensional Two-Phase Optimization

Kristi Topollai, Allan Ma, Tolga Dimlioglu +2

Communication-efficient distributed optimizers such as DiLoCo reduce synchronization costs by letting workers perform many local updates before aggregating their progress with an o…

cs.LG2026

Worker Disagreement Reveals Sharp Directions in Local SGD

Tolga Dimlioglu, Kristi Topollai, Anna Choromanska

Deep neural network training often exhibits highly anisotropic loss geometry, where a few sharp dominant Hessian directions coexist with a large flatter bulk. Gradients tend to ali…

cs.LG2026

Understanding Quantization of Optimizer States in LLM Pre-training: Dynamics of State Staleness and Effectiveness of State Resets

Kristi Topollai, Anna Choromanska

Quantizing optimizer states is becoming an important ingredient of memory-efficient large-scale pre-training, but the resulting optimizer dynamics remain only partially understood.…

cs.CL2025

Streamlining Industrial Contract Management with Retrieval-Augmented LLMs

Kristi Topollai, Tolga Dimlioglu, Anna Choromanska +2

Contract management involves reviewing and negotiating provisions, individual clauses that define rights, obligations, and terms of agreement. During this process, revisions to pro…

cs.LG2025★ 1 cited

Task-Level Contrastiveness for Cross-Domain Few-Shot Learning

Kristi Topollai, Anna Choromanska

Few-shot classification and meta-learning methods typically struggle to generalize across diverse domains, as most approaches focus on a single dataset, failing to transfer knowled…

cs.CL2025

OncoReason: Structuring Clinical Reasoning in LLMs for Robust and Interpretable Survival Prediction

Raghu Vamshi Hemadri, Geetha Krishna Guruju, Kristi Topollai +1

Predicting cancer treatment outcomes requires models that are both accurate and interpretable, particularly in the presence of heterogeneous clinical data. While large language mod…