9 citations · 12 across the 10 of their papers we have counts for
8 papers · 1 filter
Activation Outliers Matter: Robust Recovery for Quantized Multimodal LLMs
Tanzila Rahman, Mehran Taghian Jazi, Yunke Peng +10
Low-bit quantization offers a promising avenue for reducing the computational and memory demands of Multimodal Large Language Models (MLLMs). Recent hardware support for low-precis…
HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models
Hei Yi Mak, Shadan Golestan, Hoang Le +10
We present, to our knowledge, the first end-to-end FP4 RL post-training, in which both the rollout and training policies, including their forward and backward passes, operate at 4-…
HiFloat4 Format for Language Model Pre-training on Ascend NPUs
Mehran Taghian, Yunke Peng, Xing Huang +22
Training large foundation models at low numerical precision is one of the most promising directions for reducing the compute and memory cost of modern AI. Recent 4-bit floating-poi…
WINFlowNets: Warm-up Integrated Networks Training of Generative Flow Networks for Robotics and Machine Fault Adaptation
Zahin Sufiyan, Shadan Golestan, Yoshihiro Mitsuka +2
Generative Flow Networks for continuous scenarios (CFlowNets) have shown promise in solving sequential decision-making tasks by learning stochastic policies using a flow and a retr…
The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning
Sheila Schoepp, Masoud Jafaripour, Yingyue Cao +6
Reinforcement learning (RL) has shown impressive results in sequential decision-making tasks. Meanwhile, Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged…
TLXML: Task-Level Explanation of Meta-Learning via Influence Functions
Yoshihiro Mitsuka, Shadan Golestan, Zahin Sufiyan +2
Meta-learning enables models to rapidly adapt to new tasks by leveraging prior experience, but its adaptation mechanisms remain opaque, especially regarding how past training tasks…
Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms
Sheila Schoepp, Mehran Taghian, Shotaro Miwa +3
Industry is moving toward autonomous, network-connected machines that detect and adapt to changing conditions, including hardware faults. Conventional fault-tolerant design duplica…
Grey-box Bayesian Optimization for Sensor Placement in Assisted Living Environments
Shadan Golestan, Omid Ardakanian, Pierre Boulanger
Optimizing the configuration and placement of sensors is crucial for reliable fall detection, indoor localization, and activity recognition in assisted living spaces. We propose a…