164 citations · 210 across the 5 of their papers we have counts for
9 papers
gpt-oss-120b & gpt-oss-20b Model Card
OpenAI, :, Sandhini Agarwal +124
We present gpt-oss-120b and gpt-oss-20b, two open-weight reasoning models that push the frontier of accuracy and inference cost. The models use an efficient mixture-of-expert trans…
Balancing Knowledge Delivery and Emotional Comfort in Healthcare Conversational Systems
Shang-Chi Tsai, Yun-Nung Chen
With the advancement of large language models, many dialogue systems are now capable of providing reasonable and informative responses to patients' medical conditions. However, whe…
GPT-4o System Card
OpenAI, :, Aaron Hurst +416
GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's…
The Two-Pass Softmax Algorithm
Marat Dukhan, Artsiom Ablavatski
The softmax (also called softargmax) function is widely used in machine learning models to normalize real-valued scores into a probability distribution. To avoid floating-point ove…
Fast Sparse ConvNets
Erich Elsen, Marat Dukhan, Trevor Gale +1
Historically, the pursuit of efficient inference has been one of the driving forces behind research into new deep learning architectures and building blocks. Some recent examples i…
The Indirect Convolution Algorithm
Marat Dukhan
Deep learning frameworks commonly implement convolution operators with GEMM-based algorithms. In these algorithms, convolution is implemented on top of matrix-matrix multiplication…
ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation
Xiaoliang Dai, Peizhao Zhang, Bichen Wu +10
This paper proposes an efficient neural network (NN) architecture design methodology called Chameleon that honors given resource constraints. Instead of developing new building blo…
Wanted: Floating-Point Add Round-off Error instruction
Marat Dukhan, Richard Vuduc, Jason Riedy
We propose a new instruction (FPADDRE) that computes the round-off error in floating-point addition. We explain how this instruction benefits high-precision arithmetic operations i…
Branch-Avoiding Graph Algorithms
Oded Green, Marat Dukhan, Richard Vuduc
This paper quantifies the impact of branches and branch mispredictions on the single-core performance for two classes of graph problems. Specifically, we consider classical algorit…