1.6k citations · 2.5k across the 19 of their papers we have counts for
22 papers
On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents
Aaron Wang, Neelabh Madan, Vlad Sobal +5
We study whether small LLM agents can operate effectively under explicit wall-clock time budgets by both respecting the allocated runtime and using available time productively. We…
DREAM: Deep Research Evaluation with Agentic Metrics
Elad Ben Avraham, Changhao Li, Ron Dorfman +8
Deep Research Agents generate analyst-grade reports, yet evaluating them remains challenging due to the absence of a single ground truth and the multidimensional nature of research…
A Study on Leveraging Search and Self-Feedback for Agent Reasoning
Karthikeyan K, Michelle Yuan, Elman Mansimov +6
Recent works have demonstrated that incorporating search during inference can significantly improve reasoning capabilities of language agents. Some approaches may make use of the g…
Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk
Dennis Ulmer, Elman Mansimov, Kaixiang Lin +3
Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be challenging. Instructing tuning, i.e. tuning models o…
Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification
Mujeen Sung, James Gung, Elman Mansimov +5
Intent classification (IC) plays an important role in task-oriented dialogue systems. However, IC models often generalize poorly when training without sufficient annotated examples…
Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion
Yi-An Lai, Elman Mansimov, Yuqing Xie +1
When upgrading neural models to a newer version, new errors that were not encountered in the legacy version can be introduced, known as regression errors. This inconsistent behavio…
Conversation Style Transfer using Few-Shot Learning
Shamik Roy, Raphael Shu, Nikolaos Pappas +4
Conventional text style transfer approaches focus on sentence-level style transfer without considering contextual information, and the style is described with attributes (e.g., for…
Backward Compatibility During Data Updates by Weight Interpolation
Raphael Schumann, Elman Mansimov, Yi-An Lai +3
Backward compatibility of model predictions is a desired property when updating a machine learning driven application. It allows to seamlessly improve the underlying model without…
Dialog2API: Task-Oriented Dialogue with API Description and Example Programs
Raphael Shu, Elman Mansimov, Tamer Alkhouli +6
Functionality and dialogue experience are two important factors of task-oriented dialogue systems. Conventional approaches with closed schema (e.g., conversational semantic parsing…
Label Semantic Aware Pre-training for Few-shot Text Classification
Aaron Mueller, Jason Krone, Salvatore Romeo +4
In text classification tasks, useful information is encoded in the label names. Label semantic aware systems have leveraged this information for improved text classification perfor…
Measuring and Reducing Model Update Regression in Structured Prediction for NLP
Deng Cai, Elman Mansimov, Yi-An Lai +3
Recent advance in deep learning has led to the rapid adoption of machine learning-based NLP models in a wide range of applications. Despite the continuous gain in accuracy, backwar…
Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
Yixuan Su, Lei Shu, Elman Mansimov +4
Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems. Despite their success, existing methods often formulate this task as a cascade…
Semantic Parsing in Task-Oriented Dialog with Recursive Insertion-based Encoder
Elman Mansimov, Yi Zhang
We introduce a Recursive INsertion-based Encoder (RINE), a novel approach for semantic parsing in task-oriented dialog. Our model consists of an encoder network that incrementally…
Towards End-to-End In-Image Neural Machine Translation
Elman Mansimov, Mitchell Stern, Mia Chen +3
In this paper, we offer a preliminary investigation into the task of in-image machine translation: transforming an image containing text in one language into an image containing th…
Capturing document context inside sentence-level neural machine translation models with self-training
Elman Mansimov, Gábor Melis, Lei Yu
Neural machine translation (NMT) has arguably achieved human level parity when trained and evaluated at the sentence-level. Document-level neural machine translation has received l…
A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models
Elman Mansimov, Alex Wang, Sean Welleck +1
Undirected neural sequence models such as BERT (Devlin et al., 2019) have received renewed interest due to their success on discriminative natural language understanding tasks such…
Molecular geometry prediction using a deep generative graph neural network
Elman Mansimov, Omar Mahmood, Seokho Kang +1
A molecule's geometry, also known as conformation, is one of a molecule's most important properties, determining the reactions it participates in, the bonds it forms, and the inter…
Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement
Jason Lee, Elman Mansimov, Kyunghyun Cho
We propose a conditional non-autoregressive neural sequence model based on iterative refinement. The proposed model is designed based on the principles of latent variable models an…
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
Yuhuai Wu, Elman Mansimov, Shun Liao +2
In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature. We extend th…
Generating Images from Captions with Attention
Elman Mansimov, Emilio Parisotto, Jimmy Lei Ba +1
Motivated by the recent progress in generative models, we introduce a model that generates images from natural language descriptions. The proposed model iteratively draws patches o…
Initialization Strategies of Spatio-Temporal Convolutional Neural Networks
Elman Mansimov, Nitish Srivastava, Ruslan Salakhutdinov
We propose a new way of incorporating temporal information present in videos into Spatial Convolutional Neural Networks (ConvNets) trained on images, that avoids training Spatio-Te…
Unsupervised Learning of Video Representations using LSTMs
Nitish Srivastava, Elman Mansimov, Ruslan Salakhutdinov
We use multilayer Long Short Term Memory (LSTM) networks to learn representations of video sequences. Our model uses an encoder LSTM to map an input sequence into a fixed length re…