Publications (17)
Learning Deep Parameterized Skills from Demonstration for Re-targetable Visuomotor Control
Jonathan Chang, Nishanth Kumar, Sean Hastings +6
Robots need to learn skills that can not only generalize across similar problems but also be directed to a specific goal. Previous methods either train a new skill for every differ…
A State-of-the-Art SQL Reasoning Model using RLVR
Alnur Ali, Ashutosh Baheti, Jonathan Chang +13
Developing custom reasoning models via Reinforcement Learning (RL) that can incorporate organization-specific knowledge has great potential to address problems faced by enterprise…
Laguna M.1/XS.2 Technical Report
Julien Abadji, Marah Abdin, Connor Adams +93
We present Laguna M.1 and Laguna XS.2, two Mixture-of-Experts foundation models built for long-horizon, agentic coding: M.1 has B total parameters (B activated per tok…
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
BigScience Workshop, :, Teven Le Scao +391
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to wi…
Multitask Prompted Training Enables Zero-Shot Task Generalization
Victor Sanh, Albert Webson, Colin Raffel +38
Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., 2020). It has been hypothesized that this is a…
LLMs Can Learn to Reason Via Off-Policy RL
Daniel Ritter, Owen Oertell, Bradley Guo +3
Reinforcement learning (RL) approaches for Large Language Models (LLMs) frequently use on-policy algorithms, such as PPO or GRPO. However, policy lag from distributed training arch…
: Provably Optimal Distributional RL for LLM Post-Training
Jin Peng Zhou, Kaiwen Wang, Jonathan Chang +5
Reinforcement learning (RL) post-training is crucial for LLM alignment and reasoning, but existing policy-based methods, such as PPO and DPO, can fall short of fixing shortcuts inh…
Learning Representations of Emotional Speech with Deep Convolutional Generative Adversarial Networks
Jonathan Chang, Stefan Scherer
Automatically assessing emotional valence in human speech has historically been a difficult task for machine learning algorithms. The subtle changes in the voice of the speaker tha…
Joint Inference of Multiple Label Types in Large Networks
Deepayan Chakrabarti, Stanislav Funiak, Jonathan Chang +1
We tackle the problem of inferring node labels in a partially labeled graph where each node in the graph has multiple label types and each label type has a large number of possible…
Value-Guided Search for Efficient Chain-of-Thought Reasoning
Kaiwen Wang, Jin Peng Zhou, Jonathan Chang +4
In this paper, we propose a simple and efficient method for value model training on long-context reasoning traces. Compared to existing process reward models (PRMs), our method doe…
TAPIR enables high-throughput estimation and comparison of phylogenetic informativeness using locus-specific substitution models
Brant C. Faircloth, Jonathan Chang, Michael E. Alfaro
Massively parallel DNA sequencing techniques are rapidly changing the dynamics of phylogenetic study design by exponentially increasing the discovery of phylogenetically useful loc…
Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
Yiran Shen, Yu Xia, Jonathan Chang +1
Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single objective. We seek to answer wha…
Application of an attention-based CNN-BiLSTM framework for in vivo two-photon calcium imaging of neuronal ensembles: decoding complex bilateral forelimb movements from unilateral M1
Ghazal Mirzaee, Jonathan Chang, Shahrzad Latifi
Decoding behavior, such as movement, from multiscale brain networks remains a central objective in neuroscience. Over the past decades, artificial intelligence and machine learning…
Competition and extinction explain the evolution of diversity in American automobiles
Erik Gjesfjeld, Jonathan Chang, Daniele Silvestro +2
One of the most remarkable aspects of our species is that while we show surprisingly little genetic diversity, we demonstrate astonishing amounts of cultural diversity. Perhaps mos…
MobILE: Model-Based Imitation Learning From Observation Alone
Rahul Kidambi, Jonathan Chang, Wen Sun
This paper studies Imitation Learning from Observations alone (ILFO) where the learner is presented with expert demonstrations that consist only of states visited by an expert (wit…
2-adjoint equivalences in homotopy type theory
Daniel Carranza, Jonathan Chang, Chris Kapulkin +1
We introduce the notion of (half) 2-adjoint equivalences in Homotopy Type Theory and prove their expected properties. We formalized these results in the Lean Theorem Prover.
Hierarchical relational models for document networks
Jonathan Chang, David M. Blei
We develop the relational topic model (RTM), a hierarchical model of both network structure and node attributes. We focus on document networks, where the attributes of each documen…