96 citations · 351 across the 28 of their papers we have counts for
29 papers
Muse Glimmer 30B: An On-Device Agentic Model
Arash Ebrahim Abtahizadeh, Muna Aghamelu, Adil Ahmed +327
We introduce Muse Glimmer, an open-source 30B parameter causal language model with perception encoder, purpose-built for autonomous agentic tasks on consumer hardware. Muse Glimmer…
Autodata: An agentic data scientist to create high quality synthetic data
Ilia Kulikov, Chenxi Whitehouse, Tianhao Wu +12
We introduce Autodata, a general method that enables AI agents to act as data scientists who build high quality training and evaluation data. We show how to train (meta-optimize) s…
Reasoning over mathematical objects: on-policy reward modeling and test time aggregation
Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim +18
The ability to precisely derive mathematical objects is a core requirement for downstream STEM applications, including mathematics, physics, and chemistry, where reasoning must cul…
SPICE: Self-Play In Corpus Environments Improves Reasoning
Bo Liu, Chuanyang Jin, Seungone Kim +7
Self-improving systems require environmental interaction for continuous adaptation. We introduce SPICE (Self-Play In Corpus Environments), a reinforcement learning framework where…
Jointly Reinforcing Diversity and Quality in Language Model Generations
Tianjian Li, Yiming Zhang, Ping Yu +5
Post-training of Large Language Models (LMs) often prioritizes accuracy and helpfulness at the expense of diversity. This creates a tension: while post-training improves response q…
Task-Dependent Evaluation of LLM Output Homogenization: A Taxonomy-Guided Framework
Shomik Jain, Jack Lanchantin, Maximilian Nickel +4
Large language models often generate homogeneous outputs, but whether this is problematic depends on the specific task. For objective math tasks, responses may vary in terms of pro…
OptimalThinkingBench: Evaluating Over and Underthinking in LLMs
Pranjal Aggarwal, Seungone Kim, Jack Lanchantin +4
Thinking LLMs solve complex tasks at the expense of increased compute and overthinking on simpler problems, while non-thinking LLMs are faster and cheaper but underthink on harder…
NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks
Yang Li, Youssef Emad, Karthik Padthe +8
Recent work has shown that distilling reasoning traces from a larger teacher model via supervised finetuning outperforms reinforcement learning with the smaller student model alone…
CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks
Ping Yu, Jack Lanchantin, Tianlu Wang +6
We propose CoT-Self-Instruct, a synthetic data generation method that instructs LLMs to first reason and plan via Chain-of-Thought (CoT) based on given seed tasks, and then generat…
Bridging Offline and Online Reinforcement Learning for LLMs
Jack Lanchantin, Angelica Chen, Janice Lan +9
We investigate the effectiveness of reinforcement learning methods for finetuning large language models when transitioning from offline to semi-online to fully online regimes for b…
LLM Pretraining with Continuous Concepts
Jihoon Tack, Jack Lanchantin, Jane Yu +7
Next token prediction has been the standard training objective used in large language model pretraining. Representations are learned as a result of optimizing for token-level perpl…
Diverse Preference Optimization
Jack Lanchantin, Angelica Chen, Shehzaad Dhuliawala +4
Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and…
Adaptive Decoding via Latent Preference Optimization
Shehzaad Dhuliawala, Ilia Kulikov, Ping Yu +4
During language model decoding, it is known that using higher temperature sampling gives more creative responses, while lower temperatures are more factually accurate. However, suc…
TOOLVERIFIER: Generalization to New Tools via Self-Verification
Dheeraj Mekala, Jason Weston, Jack Lanchantin +4
Teaching language models to use tools is an important milestone towards building general assistants, but remains an open problem. While there has been significant progress on learn…
A Data Source for Reasoning Embodied Agents
Jack Lanchantin, Sainbayar Sukhbaatar, Gabriel Synnaeve +3
Recent progress in using machine learning models for reasoning tasks has been driven by novel model architectures, large-scale pre-training protocols, and dedicated reasoning datas…
Learning to Reason and Memorize with Self-Notes
Jack Lanchantin, Shubham Toshniwal, Jason Weston +2
Large language models have been shown to struggle with multi-step reasoning, and do not retain previous reasoning steps for future use. We propose a simple method for solving both…
General Multi-label Image Classification with Transformers
Jack Lanchantin, Tianlu Wang, Vicente Ordonez +1
Multi-label image classification is the task of predicting a set of labels corresponding to objects, attributes or other entities present in an image. In this work we propose the C…
Reevaluating Adversarial Examples in Natural Language
John X. Morris, Eli Lifland, Jack Lanchantin +2
State-of-the-art attacks on NLP models lack a shared definition of a what constitutes a successful attack. We distill ideas from past work into a unified framework: a successful na…
Neural Message Passing for Multi-Label Classification
Jack Lanchantin, Arshdeep Sekhon, Yanjun Qi
Multi-label classification (MLC) is the task of assigning a set of target labels for a given sample. Modeling the combinatorial label interactions in MLC has been a long-haul chall…
Exploring the Naturalness of Buggy Code with Recurrent Neural Networks
Jack Lanchantin, Ji Gao
Statistical language models are powerful tools which have been used for many tasks within natural language processing. Recently, they have been used for other sequential data such…
Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers
Ji Gao, Jack Lanchantin, Mary Lou Soffa +1
Although various techniques have been proposed to generate adversarial samples for white-box attacks on text, little attention has been paid to black-box attacks, which are more re…
Prototype Matching Networks for Large-Scale Multi-label Genomic Sequence Classification
Jack Lanchantin, Arshdeep Sekhon, Ritambhara Singh +1
One of the fundamental tasks in understanding genomics is the problem of predicting Transcription Factor Binding Sites (TFBSs). With more than hundreds of Transcription Factors (TF…
Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin
Ritambhara Singh, Jack Lanchantin, Arshdeep Sekhon +1
The past decade has seen a revolution in genomic technologies that enable a flood of genome-wide profiling of chromatin marks. Recent literature tried to understand gene regulation…
GaKCo: a Fast GApped k-mer string Kernel using COunting
Ritambhara Singh, Arshdeep Sekhon, Kamran Kowsari +3
String Kernel (SK) techniques, especially those using gapped -mers as features (gk), have obtained great success in classifying sequences like DNA, protein, and text. However, t…