7 citations · 36 across the 17 of their papers we have counts for
8 papers · 1 filter
Rate or Fate? RLVR: Reinforcement Learning with Verifiable Noisy Rewards
Ali Rad, Khashayar Filom, Darioush Keivan +2
Reinforcement learning with verifiable rewards (RLVR) is a simple but powerful paradigm for training LLMs: sample a completion, verify it, and update. In practice, however, the ver…
TB or Not TB: Coverage-Driven Direct Preference Optimization for Verilog Stimulus Generation
Bardia Nadimi, Khashayar Filom, Deming Chen +1
With the rapid advancement of Large Language Models (LLMs), there is growing interest in applying them to hardware design and verification. Among these stages, design verification…
MBExplainer: Multilevel bandit-based explanations for downstream models with augmented graph embeddings
Ashkan Golgoon, Ryan Franks, Khashayar Filom +1
In many industrial applications, it is common that the graph embeddings generated from training GNNs are used in an ensemble model where the embeddings are combined with other tabu…
Mechanistic interpretability of large language models with applications to the financial services industry
Ashkan Golgoon, Khashayar Filom, Arjun Ravi Kannan
Large Language Models such as GPTs (Generative Pre-trained Transformers) exhibit remarkable capabilities across a broad spectrum of applications. Nevertheless, due to their intrins…
Approximation of group explainers with coalition structure using Monte Carlo sampling on the product space of coalitions and features
Konstandinos Kotsiopoulos, Alexey Miroshnikov, Khashayar Filom +1
In recent years, many Machine Learning (ML) explanation techniques have been designed using ideas from cooperative game theory. These game-theoretic explainers suffer from high com…
On marginal feature attributions of tree-based models
Khashayar Filom, Alexey Miroshnikov, Konstandinos Kotsiopoulos +1
Due to their power and ease of use, tree-based machine learning models, such as random forests and gradient-boosted tree ensembles, have become very popular. To interpret them, loc…
PDE constraints on smooth hierarchical functions computed by neural networks
Khashayar Filom, Konrad Paul Kording, Roozbeh Farhoodi
Neural networks are versatile tools for computation, having the ability to approximate a broad range of functions. An important problem in the theory of deep neural networks is exp…
On functions computed on trees
Roozbeh Farhoodi, Khashayar Filom, Ilenna Simone Jones +1
Any function can be constructed using a hierarchy of simpler functions through compositions. Such a hierarchy can be characterized by a binary rooted tree. Each node of this tree i…