7 papers
HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models
Hei Yi Mak, Shadan Golestan, Hoang Le +10
The paper introduces HiFloat4, a 4-bit floating-point format and a Rollout Residual Quantization technique that enable end-to-end reinforcement learning post‑training of large lang…
When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning
Xiuyi Lou, Zicheng Xu, Yu-Neng Chuang +4
Reinforcement learning (RL) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, widely used critic-free RL methods rel…
Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets
Duc Duong, Hoang Anh Duy Le, Jianwen Xie +2
Long-context and agentic LLM workloads push the KV cache past any fixed memory budget, forcing the inference stack to permanently evict tokens at every step of a continuous-inferen…
Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning
Zicheng Xu, Ruixuan Zhang, Yu-Neng Chuang +7
Large Language Models (LLMs) achieve remarkable reasoning capabilities through reinforcement learning (RL) post-training. However, existing RL post-training commonly relies on unif…
A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data
Kaituo Zhang, Mingzhi Hu, Hoang Anh Duy Le +9
Large Language Models (LLMs) have emerged as powerful tools for generating data across various modalities. By transforming data from a scarce resource into a controllable asset, LL…
SOCKET: SOft Collision Kernel EsTimator for Sparse Attention
Sahil Joshi, Agniva Chowdhury, Wyatt Bellinger +5
Exploiting sparsity during long-context inference is key to scaling large language models, as attention dominates the cost of autoregressive decoding. Sparse attention reduces this…