collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2026

SAGE-OPD: Selective Agent-Guided Intervention for Multi-Turn On-Policy Distillation

Yuhang Zhou, Lizhu Zhang, Yifan Wu +5

On-policy distillation (OPD) improves student models by training them on trajectories induced by their own policy, making it a promising approach for mitigating exposure bias in ag…

cs.CL2026

Efficient Pre-Training with Token Superposition

Bowen Peng, Théo Gigant, Jeffrey Quesnelle

Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughp…

cs.CL2026

Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation

Théo Gigant, Bowen Peng, Jeffrey Quesnelle

Subword tokenization is an essential part of modern large language models (LLMs), yet its specific contributions to training efficiency and model performance remain poorly understo…

cs.CL2026

Topology-Enhanced Alignment for Large Language Models: Trajectory Topology Loss and Topological Preference Optimization

Yurui Pan, Ke Xu, Bo Peng

Alignment of large language models (LLMs) via SFT and RLHF/DPO typically ignores the global geometry of the representation space, relying instead on local token likelihoods or scal…

cs.CL2026

Long Context Pre-Training with Lighthouse Attention

Bowen Peng, Subho Ghosh, Jeffrey Quesnelle

Training causal transformers at extreme sequence lengths is bottlenecked by the quadratic time and memory of scaled dot-product attention (SDPA). In this work, we propose Lighthous…