Resultados de búsqueda - Boxing An

Batch-Max: Higher LLM Throughput using Larger Batch Sizes and KV Cache Compression por Metel, Michael R., Chen, Boxing, Rezagholizadeh, Mehdi

Enlace del recurso

On the importance of Data Scale in Pretraining Arabic Language Models por Ghaddar, Abbas, Langlais, Philippe, Rezagholizadeh, Mehdi, Chen, Boxing

Enlace del recurso

Integral Transformer: Denoising Attention, Not Too Much Not Too Little por Kobyzev, Ivan, Ghaddar, Abbas, Hu, Dingtao, Chen, Boxing

Enlace del recurso

BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs por Ghaddar, Abbas, Kobyzev, Ivan, Chen, Boxing, Cui, Yufei

Enlace del recurso

A High‐Performance User‐Defined XFEM‐Based Cohesive Zone Modeling Method for Mixed‐Mode Fracture Problems por Haoran Zhu, Longgang Tian, Jiacheng Yu, Boxing Zhang

Enlace del recurso

Thinking Long, but Short: Stable Sequential Test-Time Scaling for Large Reasoning Models por Metel, Michael R., Cui, Yufei, Chen, Boxing, Parthasarathi, Prasanna

Enlace del recurso

Order-lifted data inversion/retrieval method of neighbor cells to implement general high-order schemes in unstructured-mesh-based finite-volume solution framework por Guo, Hao, Jiang, Peixue, Ma, Xiaofeng, Hu, Boxing, Zhu, Yinhai

Enlace del recurso

Single Parent Family: A Spectrum of Family Members from a Single Pre-Trained Foundation Model por Hajimolahoseini, Habib, Hassanpour, Mohammad, Ataiefard, Foozhan, Chen, Boxing, Liu, Yang

Enlace del recurso

DPEC: Dual-Path Error Compensation Method for Enhanced Low-Light Image Clarity por Wang, Shuang, Lu, Qianwen, Peng, Boxing, Nie, Yihe, Tao, Qingchuan

Enlace del recurso

Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination por Huang, Jerry, Parthasarathi, Prasanna, Rezagholizadeh, Mehdi, Chen, Boxing, Chandar, Sarath

Enlace del recurso

ReGLA: Refining Gated Linear Attention por Lu, Peng, Kobyzev, Ivan, Rezagholizadeh, Mehdi, Chen, Boxing, Langlais, Philippe

Enlace del recurso

Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts por Heuillet, Maxime, Cui, Yufei, Chen, Boxing, Durand, Audrey, Parthasarathi, Prasanna

Enlace del recurso

GRPO-$λ$: Credit Assignment improves LLM Reasoning por Parthasarathi, Prasanna, Reymond, Mathieu, Chen, Boxing, Cui, Yufei, Chandar, Sarath

Enlace del recurso

EPAS: Efficient Training with Progressive Activation Sharing por Karim, Rezaul, Dialameh, Maryam, Liu, Yang, Chen, Boxing, Ahmed, Walid

Enlace del recurso

Exploring the compactness of $α$ cluster in $^{16}$O nuclei with relativistic $^{16}$O+$^{16}$O collisions por Wang, Yuanyuan, Zhao, Shujun, Cao, Boxing, Xu, Hao-jie, Song, Huichao

Enlace del recurso

AdpQ: A Zero-shot Calibration Free Adaptive Post Training Quantization Method for LLMs por Ghaffari, Alireza, Younesian, Sharareh, Nia, Vahid Partovi, Chen, Boxing, Asgharian, Masoud

Enlace del recurso

Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity por Metel, Michael R., Lu, Peng, Chen, Boxing, Rezagholizadeh, Mehdi, Kobyzev, Ivan

Enlace del recurso

Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach por Ghaffari, Alireza, Younesian, Sharareh, Chen, Boxing, Nia, Vahid Partovi, Asgharian, Masoud

Enlace del recurso

Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference por Kavehzadeh, Parsa, Valipour, Mojtaba, Tahaei, Marzieh, Ghodsi, Ali, Chen, Boxing, Rezagholizadeh, Mehdi

Enlace del recurso

SCOUT: Toward Sub-Quadratic Attention via Segment Compression for Optimized Utility in Transformers por Jafari, Aref, Fan, Yuhe, Jamialahmadi, Benyamin, Farinneya, Parsa, Chen, Boxing, Tahaei, Marzieh S.

Enlace del recurso