Position Description: The Hantman Lab is seeking an undergraduate graphic designer to create and/or refine visualizations for presentations and written communications. This Graphic Design position will involve designing static 3D graphics, graphic templates (in illustrator), which may be easily manipulated for future requirements, animations, and presentation slides on an as needed basis. Effective communication of scientific concepts is crucial for sharing ideas, rationale, and findings. While familiarity with biology concepts is beneficial, it is not required, as many of the required graphics are conceptual or metaphorical in nature.

Lab Area of Study: The Hantman Lab is a systems neuroscience lab that studies how complex patterns of neural activity generate skilled behaviors.

Required Skills:
– Adobe Illustrator
– High attention to detail
– Highly communicative
– Collaborative

Application: If you are interested, please fill out the following google form, https://forms.gle/xZG81Ust1xBqvXVe6.

We look forward to hearing from you!

Projects are available to investigate the function of genes that regulate excitatory and inhibitory synapses in cortical circuits relevant to autism. One project focuses on defining novel molecular mechanisms of the high confidence autism spectrum gene Ankyrin2 (Ank2) using mouse genetic models. Training will involve biochemical/cell biological analysis of protein-protein interactions by Western blotting, site directed mutagenesis of autism-related cDNAs, and cultures of mouse cortical neurons. A key focus of the lab is understanding the molecular mechanism by which Neural Cell Adhesion Molecules regulate dendritic spines and synapses during the adolescent to adult transition. Genes encoding Neuron-Glial related CAM (NrCAM), L1, and NCAM are linked to autism, schizophrenia, and bipolar disorder. These CAMs reversibly engage the spectrin-actin adaptor protein AnkyrinB, which encoded by the autism-linked Ank2 gene but the function of these interactions remain to be elucidated.

Advisor: Prof. Mohit Bansal (https://www.cs.unc.edu/~mbansal/)
Mentor: Elias Stengel-Eskin (https://esteng.github.io)
Group: Murge Lab UNC-CH (https://murgelab.cs.unc.edu/)
Duration (Flexible): Apr 15th – Sep 15th, 2024 (5 months), at least 20 hours per week commitment.
Role: Research Assistant (with RAship stipend)
Contact: Elias Stengel-Eskin (esteng@cs.unc.edu) with some basic information about yourself, your transcripts, your CV, and any discussion about any prior Machine Learning / Programming experience you have.

Requirements from Candidates (Good to Haves):
– Undergrads or Masters students from Computer Science, Mathematics/Statistics, or Linguistics/Cognitive Science background.
– Strong foundation in machine learning and deep learning techniques. Familiarity with model architectures like transformers, etc.
– Familiarity with deep learning programming frameworks like Pytorch and Huggingface libraries.
– Preferred: experience with code generation (semantic parsing, text-to-code) or vision-language tasks.
– Strong analytical abilities to ask the right questions to come up with a hypothesis and then design experiments to test it.
– Candidates who are possibly interested in a research career or grad school (Master/PhD) or Machine Learning jobs in the future.

Project Description:

Large language models allow people to interact with digital systems using natural language. However, language is inherently ambiguous and underspecified, and can lead to high uncertainty. This project will focus on enabling safe and robust interactions that allow people to make informed choices on when to trust model outputs. Core topics include: how to better model uncertainty, how to leverage multiple models to address ambiguity, how to intelligently obtain information to reduce uncertainty, and how to produce outputs that help users form their own uncertainty estimates. Topics may also include: multimodality and multimodal generation, vision-language tasks.

Research Areas:
– Multi-agent interactions and collaboration.
– Acquiring information for uncertainty reduction.
– Calibration and confidence estimation in LLM reasoning.
– Attributable and interpretable text generation.
– Multimodal reasoning and generation.

Some recent and representative papers in the direction:
1. Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models, ICLR 2024 (https://arxiv.org/abs/2310.05861)
2. ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs (https://arxiv.org/pdf/2309.13007)
3. MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models (https://arxiv.org/abs/2402.01620)
4. Soft Self-Consistency Improves Language Model Agents (https://arxiv.org/abs/2402.13212)
5. Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training (https://arxiv.org/abs/2403.02325)
6. Did You Mean…? Confidence-based Trade-offs in Semantic Parsing, EMNLP 2023 (https://arxiv.org/abs/2303.16857)
7. Zero and Few-shot Semantic Parsing with Ambiguous Inputs, ICLR 2024 (https://arxiv.org/abs/2306.00824)
8. ReGAL: Refactoring Programs to Discover Generalizable Abstractions (https://arxiv.org/abs/2401.16467)
9. GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations (https://arxiv.org/abs/2402.12348)
10. VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning (https://arxiv.org/abs/2309.15091)
11. Any-to-Any Generation via Composable Diffusion (https://arxiv.org/abs/2305.11846)

For inquiries or to express your interest, please send an email to esteng@cs.unc.edu

Advisor: Prof. Mohit Bansal (https://www.cs.unc.edu/~mbansal/)
Mentor: Prateek Yadav (https://prateeky2806.github.io/)
Group: Murge Lab UNC-CH (https://murgelab.cs.unc.edu/)
Duration (Flexible): Apr 15th – Sep 15th, 2024 (5 months), at least 20 hours per week commitment.
Role: Research Assistant (with RAship stipend)
Contact: Prateek Yadav (praty@cs.unc.edu) with some basic information about yourself, your transcripts, your CV, and any discussion about any prior Machine Learning / Programming experience you have.

Requirements from Candidates (Good to Haves):
– Undergrads or Masters students from Computer Science, Mathematics or Statistics background.
– Strong foundation in machine learning and deep learning techniques. Familiarity with Model architectures like transformers, etc.
– Familiarity with deep learning programming frameworks like Pytorch and Huggingface libraries.
– Strong analytical abilities to ask the right questions to come up with a hypothesis and then design experiments to test it.
– Candidates who are possibly interested in a research career or grad school (Master/PhD) or Machine Learning jobs in the future.

Project Description:
Machine Learning has been evolving very rapidly and often people specialize models like LLama, and LLava to their specific applications to create domain-specialized models. The projects would revolve around the goal of recycling these existing models to create better modular models that are capable of solving unseen tasks and generalizing them to new datasets/domains in a zero/few-shot manner. Moreover, these models need to be continually adapted to new domains. The techniques involved would be around ideas related to Parameter Efficient finetuning, a Mixture of Expert models, Model Merging, and Composition.
Research Areas:
1. Enabling decentralized collaborative development of models, including modular architectures, cheaply-communicable updates, and merging methods
2. Developing generalist models by creating Mixture of Expert Models system.
3. Continual Model Adaptation and Learning
4. Parameter and Compute efficiency.

Some recent and representative papers in the direction;

1. TIES-Merging: Resolving Interference When Merging Models, NeurIPS’23 (https://arxiv.org/abs/2306.01708)
2. Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy, ICLR’24 (https://arxiv.org/abs/2310.01334)
3. ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization (https://arxiv.org/abs/2311.13171)
4. Loramoe: Revolutionizing Mixture of Experts for Maintaining World Knowledge In Language Model Alignment (https://arxiv.org/pdf2312.09979.pdf)
5. Modular Deep Learning (https://arxiv.org/abs/2302.11529)
6. Learning to Route Among Specialized Experts for Zero-Shot Generalization (https://arxiv.org/abs/2402.05859)
7. Model Stock: All we need is just a few fine-tuned models (https://arxiv.org/abs/2403.19522)

For inquiries or to express your interest, please send me an email at praty@cs.unc.edu

Dr. Can Chen, a faculty member of the School of Data Science and Society, is seeking undergraduate research assistants to join his research team in the field of data science. The research focuses on developing and applying artificial intelligence and dynamical systems techniques to solve problems in the field of data science. Dr. Chen’s research interests span a diverse range of fields, including control theory, network science, tensor algebra, numerical analysis, data science, machine learning, deep learning, hypergraph learning, data analysis, and computational biology.

The Physical Mathematics Lab (PML) (Intro Video) offers a wide range of interdisciplinary problems that find motivation in very diverse fields, including soft matter, fluid mechanics, biophysics and quantum mechanics. One of PML’s themes is the study of new Hydrodynamic Quantum Analogs (HQAs) with walking drops (Video). Millimetric liquid drops can walk across the surface of a vibrating fluid bath, self-propelled through a resonant interaction with their own guiding or ‘pilot’ wave fields. These walking drops exhibit features previously thought to be exclusive to the quantum realm. This system has attracted a great deal of attention as it constitutes the first known and directly observable pilot-wave system of the form proposed by de Broglie in 1926 as a rational, realist alternative to the Copenhagen Interpretation (Video & Read). At PML, we work to unveil and rationalize new HQAs, thus challenging the limits between the quantum & classical worlds. Our investigations blend experiments & mathematical modeling (theory & simulations), we can thus tailor your project according to your interests & skills. Prior research experience is not necessary, you just need to be eager to learn!

The Motion Science Institute is currently recruiting healthy women between the ages of 18-30 to participate in a research study examining performance fatigability in women. Participants must have a BMI of ≥ 30 kg/m2 and not currently be on hormonal contraception.

Participants will receive free body composition analysis and $50 for taking part in this study.

If you are interested, please visit our website or contact Amber Schmitz by email at amberns@unc.edu.