8 papers
HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning
Weiqi Wang, Xin Liu, Binxuan Huang +13
RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts…
END: Early Noise Dropping for Efficient and Effective Context Denoising
Hongye Jin, Pei Chen, Jingfeng Yang +11
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, they are often distracted by irrelevant or…
Guard: Scalable Straggler Detection and Node Health Management for Large-Scale Training
Guanliang Liu, Abhinandan Patni, Congzhu Lin +14
Training frontier-scale foundation models involves coordinating tens of thousands of GPUs over multi-month runs, where even minor performance degradations can accumulate into subst…
Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts
Chaitanya Dwivedi, Binxuan Huang, Himanshu Gupta +3
Mixture-of-Experts (MoE) has become the dominant architecture for scaling large language models: frontier models routinely decouple total parameters from per-token computation thro…
BackPlay: Head-Only Look-Back Self-Correction for Diffusion Language Models
Liming Liu, Binxuan Huang, Zixuan Zhang +3
Diffusion Language Models (DLMs) decode multiple tokens in parallel, but aggressive multi-token decoding amplifies cross-token dependency errors and can sharply degrade generation…
DocTalk: Scalable Graph-based Dialogue Synthesis for Enhancing LLM Conversational Capabilities
Jing Yang Lee, Hamed Bonab, Nasser Zalmout +6
Large Language Models (LLMs) are increasingly employed in multi-turn conversational tasks, yet their pre-training data predominantly consists of continuous prose, creating a potent…