7 papers
CTA-Pipelining: A Latency-Oriented Spatial Scaling Method for Multi-GPU Systems
Tingkai Liu, Muralidhar Andoorveedu, Sanjoy Das +2
The evolution of compute infrastructure has transformed multi-GPU systems into tightly integrated shared-memory structures. However, current software still mostly treats these cohe…
A cross-species neural foundation model for end-to-end speech decoding
Yizi Zhang, Linyang He, Chaofei Fan +9
Speech brain-computer interfaces (BCIs) aim to restore communication for people with paralysis by translating neural activity into text. Most systems use cascaded frameworks that d…
NdLinear: Preserving Multi-Dimensional Structure for Parameter-Efficient Neural Networks
Alex Reneau, Jerry Yao-Chieh Hu, Zhongfang Zhuang +6
In deep learning, processing multidimensional inputs (e.g., images, medical scans, and time series) is an important task that often requires flattening the inputs. We introduce $\m…
FullStack Bench: Evaluating LLMs as Full Stack Coders
Bytedance-Seed-Foundation-Code-Team, :, Yao Cheng +53
As the capabilities of code large language models (LLMs) continue to expand, their applications across diverse code intelligence domains are rapidly increasing. However, most exist…
Token-Level Uncertainty-Aware Objective for Language Model Post-Training
Tingkai Liu, Ari S. Benjamin, Anthony M. Zador
In the current work, we connect token-level uncertainty in causal language modeling to two types of training objectives: 1) masked maximum likelihood (MLE), 2) self-distillation. W…
DavIR: Data Selection via Implicit Reward for Large Language Models
Haotian Zhou, Tingkai Liu, Qianli Ma +5
We introduce DavIR, a model-based data selection method for post-training Large Language Models. DavIR generalizes Reducible Holdout Loss to core-set selection problem of causal la…