activity
20242026
collaborators

6 papers

cs.LG2026

PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks

Srijith Nair, Atilla Eryilmaz, Jia Liu

In the literature, many continual learning (CL) algorithms have been proposed to address the issue of catastrophic forgetting in ML models (i.e., learning new tasks leads to the lo…

cs.CL2026

SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling

Quanen Sun, Changxin Tian, Ke Shi +5

Scaling laws guide large language model training by relating compute to cross-entropy loss, and recent work further extends them to predict downstream benchmark performance. Howeve…

cs.CL2026

PowLU: An Activation Function for Stable Pre-Training of LLMs

Peijie Jiang, Yuqi Feng, Cunyin Peng +5

In contemporary large language models (LLMs), the swish-gated linear unit (SwiGLU) activation function is widely adopted to regulate the information flow and introduce non-linearit…

cs.CL2026

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

Liujie Zhang, Benzhe Ning, Rui Yang +8

Reinforcement learning (RL) post-training has proven effective at unlocking reasoning, self-reflection, and tool-use capabilities in large language models. As models extend to omni…

cs.LG2025

FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation

Srijith Nair, Michael Lin, Peizhong Ju +3

Collaborative training methods like Federated Learning (FL) and Split Learning (SL) enable distributed machine learning without sharing raw data. However, FL assumes clients can tr…

cs.LG2024

PSMGD: Periodic Stochastic Multi-Gradient Descent for Fast Multi-Objective Optimization

Mingjing Xu, Peizhong Ju, Jia Liu +1

Multi-objective optimization (MOO) lies at the core of many machine learning (ML) applications that involve multiple, potentially conflicting objectives (e.g., multi-task learning,…