activity
20152026
most citeddeltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets

95 citations · 313 across the 30 of their papers we have counts for

collaborators
Showing cs.LGShow all

21 papers · 1 filter

cs.LG2026

Test-Time Learning with an Evolving Library

Weijia Xu, Alessandro Sordoni, Chandan Singh +4

We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates…

cs.LG2026

Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient Experts

Sanae Lotfi, Lucas Caccia, Alessandro Sordoni +2

While large language models (LLMs) fine-tuned with lightweight adapters achieve strong performance across diverse tasks, their performance on individual tasks depends on the fine-t…

cs.LG2026

Learning to Solve Complex Problems via Dataset Decomposition

Wanru Zhao, Lucas Caccia, Zhengyan Shi +3

Curriculum learning is a class of training strategies that organizes the data being exposed to a model by difficulty, gradually from simpler to more complex examples. This research…

cs.LG2025

Learning to Extract Context for Context-Aware LLM Inference

Minseon Kim, Lucas Caccia, Zhengyan Shi +4

User prompts to large language models (LLMs) are often ambiguous or under-specified, and subtle contextual cues shaped by user intentions, prior knowledge, and risk factors strongl…

cs.LG2025

The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning

Milad Aghajohari, Kamran Chitsaz, Amirhossein Kazemnejad +4

Reinforcement learning (RL) has recently become a strong recipe for training reasoning LLMs that produce long chains of thought (LongCoT). Yet the standard RL "thinking environment…

cs.LG2025

Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts

Samin Yeasar Arnob, Zhan Su, Minseon Kim +6

Merging parameter-efficient task experts has recently gained growing attention as a way to build modular architectures that can be rapidly adapted on the fly for specific downstrea…