BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Jason Lee

Jason Lee appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Machine Learningcond-mat.mtrl-sciArtificial IntelligenceComputation and Languagecond-mat.str-elDistributed, Parallel, and Cluster ComputingMethodologyRobotics

Catalog footprint

What is connected

12works
8topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

12 published item(s)

preprint2026arXiv

20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone

Data curation has shifted the quality-compute frontier for language-model and contrastive image-text pretraining, but its role for vision-language models (VLMs) is far less established. We ask how far data curation alone can take VLM performance, holding architecture, training recipe, and compute fixed and varying only the training data. Our pipeline, applied to the MAmmoTH-VL single-image subset, lifts performance by +11.7pp on average across 20 public VLM benchmarks (spanning grounding, VQA, OCR/documents, captioning, spatial/3D, counting, charts, math, brand-ID, and multi-image reasoning) and by +11.3pp on average across all nine capability axes of DatBench, our high-fidelity VLM eval suite. At 2B, our curated model surpasses InternVL3.5-2B by 9.9pp at ~17x less training compute and closes the gap to Qwen3-VL-2B to within 1.8pp at ~87x less compute, from pretraining alone. Beyond accuracy, curation delivers four further properties: (1) Reliability: per-capability std across training seeds drops by ~67% and the lift survives a 4k-to-16k context-length sweep; (2) OOD generalization: the 9-eval OOD average rises by +7.2pp, and multi-image BLINK rises by +3.09pp despite single-image-only training, with Visual Correspondence gaining +11.8pp; (3) Behavioral gains beyond benchmarks: across ~1,100 open-ended queries the curated 2B is more honest and more specific than the matched-compute baseline, and more concise and less refusal-prone than a frontier 2B reference; (4) Pareto-dominance on inference cost: at every scale (1B, 2B, 4B) the curated model raises accuracy while lowering response FLOPs vs. the matched-compute baseline, and the curated 4B matches near-frontier accuracy at 3.3x lower response FLOPs than Qwen3-VL-4B. Data curation is a high-leverage tool for building better VLMs, reaching near-frontier accuracy at up to ~150x less training compute.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

DatBench: Discriminative, Faithful, and Efficient VLM Evaluations

Empirical evaluation serves as the primary compass guiding research progress in foundation models. Despite a large body of work focused on training frontier vision-language models (VLMs), approaches to their evaluation remain nascent. To guide their maturation, we propose three desiderata that evaluations should satisfy: (1) faithfulness to the modality and application, (2) discriminability between models of varying quality, and (3) efficiency in compute. Through this lens, we identify critical failure modes that violate faithfulness and discriminability, misrepresenting model capabilities: (i) multiple-choice formats reward guessing, poorly reflect downstream use cases, and saturate early as models improve; (ii) blindly solvable questions, which can be answered without images, constitute up to 70% of some evaluations; and (iii) mislabeled or ambiguous samples compromise up to 42% of examples in certain datasets. Regarding efficiency, the computational burden of evaluating frontier models has become prohibitive: by some accounts, nearly 20% of development compute is devoted to evaluation alone. Rather than discarding existing benchmarks, we curate them via transformation and filtering to maximize fidelity and discriminability. We find that converting multiple-choice questions to generative tasks reveals sharp capability drops of up to 35%. In addition, filtering blindly solvable and mislabeled samples improves discriminative power while simultaneously reducing computational cost. We release DatBench-Full, a cleaned evaluation suite of 33 datasets spanning nine VLM capabilities, and DatBench, a discriminative subset that achieves 13x average speedup (up to 50x) while closely matching the discriminative power of the original datasets. Our work outlines a path toward evaluation practices that are both rigorous and sustainable as VLMs continue to scale.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

The LBNL Superfacility Project Report

The Superfacility model is designed to leverage HPC for experimental science. It is more than simply a model of connected experiment, network, and HPC facilities; it encompasses the full ecosystem of infrastructure, software, tools, and expertise needed to make connected facilities easy to use. The three-year Lawrence Berkeley National Laboratory (LBNL) Superfacility project was initiated in 2019 to coordinate work being performed at LBNL to support this model, and to provide a coherent and comprehensive set of science requirements to drive existing and new work. A key component of the project was the in-depth engagements with eight science teams that represent challenging use cases across the DOE Office of Science. By the close of the project, we met our project goal by enabling our science application engagements to demonstrate automated pipelines that analyze data from remote facilities at large scale, without routine human intervention. In several cases, we have gone beyond demonstrations and now provide production-level services. To achieve this goal, the Superfacility team developed tools, infrastructure, and policies for near-real-time computing support, dynamic high-performance networking, data management and movement tools, API-driven automation, HPC-scale notebooks via Jupyter, authentication using Federated Identity and container-based edge services supported. The lessons we learned during this project provide a valuable model for future large, complex, cross-disciplinary collaborations. There is a pressing need for a coherent computing infrastructure across national facilities, and LBNL's Superfacility project is a unique model for success in tackling the challenges that will be faced in hardware, software, policies, and services across multiple science domains.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Characterizing Implicit Bias in Terms of Optimization Geometry

We study the implicit bias of generic optimization methods, such as mirror descent, natural gradient descent, and steepest descent with respect to different potentials and norms, when optimizing underdetermined linear regression or separable linear classification problems. We explore the question of whether the specific global minimum (among the many possible global minima) reached by an algorithm can be characterized in terms of the potential or norm of the optimization geometry, and independently of hyperparameter choices such as step-size and momentum.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation

We propose an efficient inference procedure for non-autoregressive machine translation that iteratively refines translation purely in the continuous space. Given a continuous latent variable model for machine translation (Shu et al., 2020), we train an inference network to approximate the gradient of the marginal log probability of the target sentence, using only the latent variable as input. This allows us to use gradient-based optimization to find the target sentence at inference time that approximately maximizes its marginal probability. As each refinement step only involves computation in the latent space of low dimensionality (we use 8 in our experiments), we avoid computational overhead incurred by existing non-autoregressive inference procedures that often refine in token space. We compare our approach to a recently proposed EM-like inference procedure (Shu et al., 2020) that optimizes in a hybrid space, consisting of both discrete and continuous variables. We evaluate our approach on WMT'14 En-De, WMT'16 Ro-En and IWSLT'16 De-En, and observe two advantages over the EM-like inference: (1) it is computationally efficient, i.e. each refinement step is twice as fast, and (2) it is more effective, resulting in higher marginal probabilities and BLEU scores with the same number of refinement steps. On WMT'14 En-De, for instance, our approach is able to decode 6.2 times faster than the autoregressive model with minimal degradation to translation quality (0.9 BLEU).

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Kernel and Rich Regimes in Overparametrized Models

A recent line of work studies overparametrized neural networks in the "kernel regime," i.e. when the network behaves during training as a kernelized linear predictor, and thus training with gradient descent has the effect of finding the minimum RKHS norm solution. This stands in contrast to other studies which demonstrate how gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms. Building on an observation by Chizat and Bach, we show how the scale of the initialization controls the transition between the "kernel" (aka lazy) and "rich" (aka active) regimes and affects generalization properties in multilayer homogeneous models. We provide a complete and detailed analysis for a simple two-layer model that already exhibits an interesting and meaningful transition between the kernel and rich regimes, and we demonstrate the transition for more complex matrix factorization models and multilayer non-linear networks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

On the Discrepancy between Density Estimation and Sequence Generation

Many sequence-to-sequence generation tasks, including machine translation and text-to-speech, can be posed as estimating the density of the output y given the input x: p(y|x). Given this interpretation, it is natural to evaluate sequence-to-sequence models using conditional log-likelihood on a test set. However, the goal of sequence-to-sequence generation (or structured prediction) is to find the best output y^ given an input x, and each task has its own downstream metric R that scores a model output by comparing against a set of references y*: R(y^, y* | x). While we hope that a model that excels in density estimation also performs well on the downstream metric, the exact correlation has not been studied for sequence generation tasks. In this paper, by comparing several density estimators on five machine translation tasks, we find that the correlation between rankings of models based on log-likelihood and BLEU varies significantly depending on the range of the model families being compared. First, log-likelihood is highly correlated with BLEU when we consider models within the same family (e.g. autoregressive models, or latent variable models with the same parameterization of the prior). However, we observe no correlation between rankings of models across different families: (1) among non-autoregressive latent variable models, a flexible prior distribution is better at density estimation but gives worse generation quality than a simple prior, and (2) autoregressive models offer the best translation performance overall, while latent variable models with a normalizing flow prior give the highest held-out log-likelihood across all datasets. Therefore, we recommend using a simple prior for the latent variable non-autoregressive model when fast generation speed is desired.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Deploying the NASA Valkyrie Humanoid for IED Response: An Initial Approach and Evaluation Summary

As part of a feasibility study, this paper shows the NASA Valkyrie humanoid robot performing an end-to-end improvised explosive device (IED) response task. To demonstrate and evaluate robot capabilities, sub-tasks highlight different locomotion, manipulation, and perception requirements: traversing uneven terrain, passing through a narrow passageway, opening a car door, retrieving a suspected IED, and securing the IED in a total containment vessel (TCV). For each sub-task, a description of the technical approach and the hidden challenges that were overcome during development are presented. The discussion of results, which explicitly includes existing limitations, is aimed at motivating continued research and development to enable practical deployment of humanoid robots for IED response. For instance, the data shows that operator pauses contribute to 50\% of the total completion time, which implies that further work is needed on user interfaces for increasing task completion efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Two-Dimensional Honeycomb Monolayer of Nitrogen Group Elements and the Related Nano-Structure: A First-Principle Study

Because of its novel physical properties, two-dimensional materials have attracted great attention. From first-principle calculations and vibration frequenceis analysis, we predict a new family of two-dimensional materials based on the idea of octet stability: honeycomb lattices of pnictogens (N, P, As, Sb, Bi). The buckled structures of materials come from the sp3 hybridization. These materials have indirect band gap ranging from 0.43eV to 3.7eV. From the analysis of projected density of states, we argue that the s and p orbitals together are sufficient to describe the electronic structure under tight-binding model, and the tight-binding parameters are obtained by fitting the band structures to first-principle results. Surprisingly large on-site spin-orbit coupling is found for all the pnictogen lattices except nitrogen. Investigation on the electronic structures of both zigzag and armchair nanoribbons reveals the possible existence of spin-polarized ferromagnetic edge states in some cases, which are rare in one-dimensional systems. These edge states and magnetism may exist under the condition of high vaccum and low temperature. This new family of materials would have promising applications in electronics, optics, sensors, and solar cells.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Two-dimensional octagon-structure monolayer of nitrogen group elements and the related nano-structures

In the purpose of expanding the family of two-dimensional materials, we predict the existence of two-dimensional octa-structure of nitrogen group elements that are composed of squares and octagons in first-principle method based on density functional theory (DFT). From our calculations, electronic structures of all monolayers show that they are semiconductors with indirect (N, P, Bi) and direct (As, Sb) band gaps (0.57-2.61eV). Nano-ribbons of three different unpassivated edges and their band structures are also investigated. Because of the reconstruction on the edges and dangling bonds, there exist ferromagnetic edge states in P, As, Sb nano-ribbons with different edges, and a Dirac point near π is found in the band structure of one specific N nano-ribbon. These structures may be useful in future applications, such as semiconductor devices, spintronics, hydrogen storage and quantum computation.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Matrix Completion and Low-Rank SVD via Fast Alternating Least Squares

The matrix-completion problem has attracted a lot of attention, largely as a result of the celebrated Netflix competition. Two popular approaches for solving the problem are nuclear-norm-regularized matrix approximation (Candes and Tao, 2009, Mazumder, Hastie and Tibshirani, 2010), and maximum-margin matrix factorization (Srebro, Rennie and Jaakkola, 2005). These two procedures are in some cases solving equivalent problems, but with quite different algorithms. In this article we bring the two approaches together, leading to an efficient algorithm for large matrix factorization and completion that outperforms both of these. We develop a software package "softImpute" in R for implementing our approaches, and a distributed version for very large matrices using the "Spark" cluster programming environment.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

Quantum computation with two-dimensional graphene quantum dots

We study an array of graphene nano sheets that form a two-dimensional S = 1/2 Kagome spin lattice used for quantum computation. The edge states of the graphene nano sheets are used to form quantum dots to confine electrons and perform the computation. We propose two schemes of bang-bang control to combat decoherence and realize gate operations on this array of quantum dots. It is shown that both schemes contain a great amount of information for quantum computation. The corresponding gate operations are also proposed.

0 citations0 reviewsNo code linkedOpen access