arXiv subjects

Michael Hu

Publications and source records attributed to Michael Hu.

9 recordsLinked to original sources

arXiv2026

Simulating Human Memory with Language Models

Language models are increasingly being deployed as user simulators, but their memory is far more reliable than that of real users. To measure this gap, we run a series of classic memory experiments from psychology on both humans and language models. Across tasks, we find that out-of-the-box language models exhibit better memory than humans, even when prompted to imitate human behavior. We then show that better prompting strategies and the use of a compactor can cause language models to forget content in a more human-like way. Using these methods, we show preliminary evidence that language models with human-like memory constraints can function as more effective user simulators in a downstream education task. Finally, we release human reference data and benchmarks to support future work on simulating human memory with language models.

cs.CL↗

arXiv2025

BabyLM Turns 3: Call for papers for the 2025 BabyLM workshop

BabyLM aims to dissolve the boundaries between cognitive modeling and language modeling. We call for both workshop papers and for researchers to join the 3rd BabyLM competition. As in previous years, we call for participants in the data-efficient pretraining challenge in the general track. This year, we also offer a new track: INTERACTION. This new track encourages interactive behavior, learning from a teacher, and adapting the teaching material to the student. We also call for papers outside the competition in any relevant areas. These include training efficiency, cognitively plausible research, weak model evaluation, and more.

cs.CL↗

arXiv2024

Pruning the Path to Optimal Care: Identifying Systematically Suboptimal Medical Decision-Making with Inverse Reinforcement Learning

In aims to uncover insights into medical decision-making embedded within observational data from clinical settings, we present a novel application of Inverse Reinforcement Learning (IRL) that identifies suboptimal clinician actions based on the actions of their peers. This approach centers two stages of IRL with an intermediate step to prune trajectories displaying behavior that deviates significantly from the consensus. This enables us to effectively identify clinical priorities and values from ICU data containing both optimal and suboptimal clinician decisions. We observe that the benefits of removing suboptimal actions vary by disease and differentially impact certain demographic groups.

cs.LG↗

arXiv2024

Kirillov's conjecture on Hecke-Grothendieck polynomials

We use algebraic methods in statistical mechanics to represent a multi-parameter class of polynomials in several variables as partition functions of a new family of solvable lattice models. The class of polynomials, defined by A. N. Kirillov, is derived from the largest class of divided difference operators satisfying the braid relations of Cartan type $A$. It includes as specializations Schubert, Grothendieck, and dual-Grothendieck polynomials, among others. In particular, our results prove positivity conjectures of Kirillov for the subfamily of Hecke-Grothendieck polynomials, while the larger family is shown to exhibit rare instances of negative coefficients.

math.CO↗

arXiv2022

Imaging gate-induced molecular melting on a graphene field-effect transistor

Solid-liquid phase transitions are fundamental physical processes, but atomically-resolved microscopy has yet to capture both the solid and liquid dynamics for such a transition. We have developed a new technique for controlling the melting and freezing of 2D molecular layers on a graphene field-effect transistor (FET) that allows us to image phase transition dynamics via atomically-resolved scanning tunneling microscopy. Back-gate voltages applied to a F4TCNQ-decorated graphene FET induce reversible transitions between a charge-neutral solid phase and a negatively charged liquid phase. Nonequilibrium molecular melting dynamics are visualized by rapidly heating the graphene surface with electrical current and imaging the resulting evolution toward new equilibrium states. An analytical model has been developed that explains the observed equilibrium mixed-state phases based on spectroscopic measurement of both solid and liquid molecular energy levels. Observed non-equilibrium melting dynamics are consistent with Monte Carlo simulations.

cond-mat.mes-hall↗

arXiv2022

End-to-End Multimodal Representation Learning for Video Dialog

Video-based dialog task is a challenging multimodal learning task that has received increasing attention over the past few years with state-of-the-art obtaining new performance records. This progress is largely powered by the adaptation of the more powerful transformer-based language encoders. Despite this progress, existing approaches do not effectively utilize visual features to help solve tasks. Recent studies show that state-of-the-art models are biased toward textual information rather than visual cues. In order to better leverage the available visual information, this study proposes a new framework that combines 3D-CNN network and transformer-based networks into a single visual encoder to extract more robust semantic representations from videos. The visual encoder is jointly trained end-to-end with other input modalities such as text and audio. Experiments on the AVSD task show significant improvement over baselines in both generative and retrieval tasks.

cs.CV↗

arXiv2022

Self-Supervised Representation Learning for CAD

The design of man-made objects is dominated by computer aided design (CAD) tools. Assisting design with data-driven machine learning methods is hampered by lack of labeled data in CAD's native format; the parametric boundary representation (B-Rep). Several data sets of mechanical parts in B-Rep format have recently been released for machine learning research. However, large scale databases are largely unlabeled, and labeled datasets are small. Additionally, task specific label sets are rare, and costly to annotate. This work proposes to leverage unlabeled CAD geometry on supervised learning tasks. We learn a novel, hybrid implicit/explicit surface representation for B-Rep geometry, and show that this pre-training significantly improves few-shot learning performance and also achieves state-of-the-art performance on several existing B-Rep benchmarks.

cs.CV↗

arXiv2020

Safe Reinforcement Learning with Natural Language Constraints

While safe reinforcement learning (RL) holds great promise for many practical applications like robotics or autonomous cars, current approaches require specifying constraints in mathematical form. Such specifications demand domain expertise, limiting the adoption of safe RL. In this paper, we propose learning to interpret natural language constraints for safe RL. To this end, we first introduce HazardWorld, a new multi-task benchmark that requires an agent to optimize reward while not violating constraints specified in free-form text. We then develop an agent with a modular architecture that can interpret and adhere to such textual constraints while learning new tasks. Our model consists of (1) a constraint interpreter that encodes textual constraints into spatial and temporal representations of forbidden states, and (2) a policy network that uses these representations to produce a policy achieving minimal constraint violations during training. Across different domains in HazardWorld, we show that our method achieves higher rewards (up to11x) and fewer constraint violations (by 1.8x) compared to existing approaches. However, in terms of absolute performance, HazardWorld still poses significant challenges for agents to learn efficiently, motivating the need for future work.

cs.CL↗

arXiv2011

Integrated Photonic Sensing

Loss is a critical roadblock to achieving photonic quantum-enhanced technologies. We explore a modular platform for implementing integrated photonics experiments and consider the effects of loss at different stages of these experiments, including state preparation, manipulation and measurement. We frame our discussion mainly in the context of quantum sensing and focus particularly on the use of loss-tolerant Holland-Burnett states for optical phase estimation. In particular, we discuss spontaneous four-wave mixing in standard birefringent fibre as a source of pure, heralded single photons and present methods of optimising such sources. We also outline a route to programmable circuits which allow the control of photonic interactions even in the presence of fabrication imperfections and describe a ratiometric characterisation method for beam splitters which allows the characterisation of complex circuits without the need for full process tomography. Finally, we present a framework for performing state tomography on heralded states using lossy measurement devices. This is motivated by a calculation of the effects of fabrication imperfections on precision measurement using Holland-Burnett states.

quant-ph↗