Author

H. Le

h-index 2 View on Semantic Scholar

We have 4 of 10 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Feb 2026

SOCKET: SOft Collision Kernel EsTimator for Sparse Attention

This work revisits Locality-Sensitive Hashing (LSH) and introduces SOCKET, a SOft Collision Kernel EsTimator that replaces hard bucket matches with probabilistic, similarity-aware aggregation, and reframes LSH from a candidate-generation mechanism into a principled scoring kernel for sparse attention.

Sahil Joshi, Agniva Chowdhury, W. Bellinger et al. · 3 citations

#machine learning Jul 2026

When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning

Tail-Aware Credit calibratiOn (TACO), a method that calibrates uniform credit assignment to suppress undesirable positive updates in RL, and improves training stability, supporting sustained performance gains in long-horizon RL.

Xiuyi Lou, Zi-Cheng Xu, Yu-Neng Chuang et al. · arXiv.org · 1 citation

Jul 2026

HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models

HiF4 is established as the enabling format for end-to-end FP4 RL post-training, and Rollout Residual Quantization (Rollout-ResQ) is established as the activation-side mechanism that makes the gap to BF16 closable.

H. Mak, Shadan Golestan, H. Le et al. · arXiv.org · 0 citations

Preprint Aug 2026

Activation Outliers Matter: Robust Recovery for Quantized Multimodal LLMs

This work proposes Residual Fallback Quantization (RFQ), a lightweight activation reconstruction framework that supplements the primary ulta-low-bit activation representation with an auxiliary quantized residual pathway that improves activation fidelity while preserving the efficiency advantages of ultra-low-bit comput...

Tanzila Rahman, Mehran Taghian Jazi, Yunke Peng et al. · 0 citations