Library · Machine learning & AI
What Zero-Shot Learning got wrong, from 76 theses
Summary written by a model from the records below: Across various applications, zero-shot models often suffer from severe domain shifts, label biases, and performance drops when deployed without task-specific supervision. As a result, unadapted zero-shot approaches frequently fail on specialized reasoning, physiological signals, and subjective tasks while falling behind trained baselines. These records come from graduate theses, 2021 to 2026, each labeled with its degree where the repository states it, and each links to its thesis. They were extracted by language models reading the full text, so treat each as a lead to read, not a verdict.
Plus 10 problems the authors left open, listed at the end.
Failure modes, by theses reporting them
Select a mode to jump to its records.
Zero-shot models underperform supervised and fine-tuned baselines
Pretrained zero-shot approaches across language, speech, and vision tasks consistently achieve lower accuracy and higher error rates than supervised classifiers or few-shot prompts. In several benchmarks, zero-shot methods also lag behind traditional modular pipelines and simple rule-based baselines.
Lost to a baseline
On Multi30K German-to-image search, thesis English-only zero-shot model (31.4% R@1) lost to supervised MHA-D (40.3% R@1)
Learning and interpreting deep representations from multi-modal data · Oxford · PhD
Lost to a baseline
All zero-shot models achieved lower raw Recall@K across all cutoffs compared to fully trained models (IMP, GPSNet, Motifs, VCTree, OpenPSG)
Zero-Shot Scene Graph Relationship Prediction using VLMs · Virginia Tech · Master's
Lost to a baseline
UnifiedQA zero-shot answering on StrategyQA scored 58.95% accuracy, heavily underperforming GPT-3 zero-shot prompting (58.08% / 63.32% few-shot) and other reasoning baselines when not given gold supporting facts.
Incidental Supervision for Natural Language Understanding · Penn · PhD
Lost to a baseline
Zero-shot foundation model mPLUG-Owl achieved inferior or comparable precision/recall (0.20 precision / 0.20 recall on multiple groundings) compared to naive single/multiple baselines on the Single Answer Grounding Challenge.
Visual question answering : representing authentic use cases and ambiguity · UT Austin · PhD
Lost to a baseline
In-domain zero-shot German question formation for mBART failed to correctly transform the full sequence (0% sequence accuracy), underperforming mT5.
Emergent Syntactic Behaviors and Mechanisms in Neural Language Models · Johns Hopkins · PhD
Lost to a baseline
Zero-shot CLIP OOD methods (MCM and Cosine) achieved 67.1% to 79.8% FPR on NINCO, failing to beat standard IN-1K fine-tuned classifiers
Out-of-Distribution Detection, Sharpness, and Unlearning: Advancing Robust and Trustworthy Deep Learning · Tübingen · PhD
Lost to a baseline
Direct zero-shot Seq2Seq transfer yielded near or exceeding 100% WER, severely underperforming modular hybrid DNN-HMM systems.
Automatic Speech Recognition without Transcribed Speech or Pronunciation Lexicons · Johns Hopkins · PhD
Tried and failed
zero-shot sequence-to-sequence pretrained model classification applied to claim verification verdict classification. Outcome: worse than baseline. Reason: lack of task-specific fine-tuning severely limited classification capability compared to fine-tuned alternatives
Explainable Neural Claim Verification Using Rationalization · Virginia Tech · Master's
Lost to a baseline
In conversational Turing tests, zero-shot ChatGPT performed poorly as an AI judge and was outperformed by one-shot prompted ChatGPT and trained SVM classifiers.
Finding Structure in Human Cognition: From Temporal Order Codes in Memory to Behavioral Signatures in Vision and Language · Harvard · PhD
Lost to a baseline
Zero-shot and few-shot Llama 3 in-context learning achieved F1-scores of only 0.29–0.40, falling well behind the non-LLM BiLSTM baseline F1 of 0.67.
Surgical Site Infection (SSI) Identification Across Multiple Facilities and Surgery Types Using Multimodal Data and Deep Learning · University of Washington · PhD
Lost to a baseline
Zero-shot prompting on several LLMs (including Llama3 8B and Mistral 7B) achieved lower accuracy than the rule-based VADER sentiment analysis baseline
Lost to a baseline
On ActivityNet-QA VQA, supervised finetuned JustAsk (FT) achieved 64.667% vs this method's zero-shot 61.168%.
Learning Generalizable Systems by Learning Composable Energy Landscapes · MIT · PhD
Lost to a baseline
In zero-shot multilingual SLU intent classification, the proposed zero-shot Speech-LLM (16.24%–47.38%) lost to the text NLU baseline (70%–80%) and cascaded SLU across all evaluated languages.
Multilingual Spoken Language Understanding: Efficient Speech Dataset Collection, Architectural Exploration, and Zero-Shot SLU · University of Trento · PhD
Lost to a baseline
Generic zero-shot AudioSet transfer learning achieved only 51.1% accuracy on self-talk, performing barely above chance
Lost to a baseline
Zero-shot BLINK achieved 54.4% accuracy on NLM-Chem, missing domain-specific performance
Entity Linking in Low-Annotation Data Settings · Johns Hopkins · PhD
Lost to a baseline
DiffuCOMET-Fact (RA-F1 43.51) lost to Beam-COMET baseline (RA-F1 45.88) on out-of-domain MovieSummaries zero-shot testing.
Understanding Implicit Schemas of Reasoning · EPFL · PhD
Lost to a baseline
Zero-shot Kaleido 3B achieved 71.5% on ETHICS Commonsense, losing to few-shot ChatGPT (80.3%).
Steps Towards the Pluralistic Alignment of Language Models · University of Washington · PhD
Tried and failed
pretrained vision-language and self-supervised models for keypoint detection applied to deformable object semantic keypoint localization. Outcome: worse than baseline. Reason: zero-shot VLM and DINOv2 backbones lacked fine spatial localization precision compared to supervised ResNets
Deformable Object Manipulation with a Tactile Reactive Gripper · MIT · PhD
Lost to a baseline
On few-shot HICO classification (Few@1, Few@5, Few@10), zero-shot HTS ViT-B/32 (33.6, 36.3, 37.2 mAP) was beaten by supervised HTS* ViT-B/32 (49.6, 52.6, 52.9 mAP).
Crossing the Chasm: Bridging Perception and Generative Models for Enhanced Vision-Language Understanding · University of Washington · PhD
Lost to a baseline
Zero-shot and decoder-fit DNNs achieved lower accuracy (barely above 8.33% chance at 35% fragments) compared to humans (~50% accuracy).
Differences in Visual Perception in Humans and Deep Neural Networks · EPFL · PhD
Zero-shot models fail under visual and physical distribution shifts
Models pretrained on standard visual or synthetic data fail to generalize when deployed on out-of-distribution domains like satellite imagery, histopathology, and synthetic simulations. These environmental and sensor discrepancies cause extreme false negative rates, unstable segmentations, and collapsed feature matching.
Tried and failed
zero-shot segmentation using pre-trained network applied to out-of-distribution histopathology images. Outcome: did not generalise. Reason: produced unstable nuclear segmentations and unreliable classification without fine-tuning and threshold calibration
Integrated Molecular and Histopathological Studies of Testicular Germ Cell Tumor Biology · Harvard · PhD
Tried and failed
zero-shot vision-language model classification applied to satellite imagery object detection. Outcome: no signal. Reason: poor zero-shot alignment on domain-specific satellite imagery led to zero true positives
Adaptive Learning for AI Systems: AI Methods for Scientific Domains under Limited Supervision · Cornell · PhD
Tried and failed
deep learning PDE solver direct zero-shot inference applied to out-of-distribution physical scattering fields. Outcome: did not generalise. Reason: test inputs had structures completely uncorrelated with the synthetic training distribution
Exploring Novel Modalities for Optical Diffraction Tomography · EPFL · PhD
Tried and failed
zero-shot transfer of task-finetuned conditional adapters applied to unseen visual generation tasks. Outcome: did not generalise. Reason: specialized finetuning destroyed zero-shot generalization capability on out-of-distribution conditioning tasks
Enhancing generative model efficiency and control for data generation, reinforcement learning, and robotics · UT Austin · PhD
Tried and failed
unprompted zero-shot foundation model segmentation applied to complex morphology cell microscopy images. Outcome: did not generalise. Reason: zero-shot segmentation failed on complex star-shaped developmental morphologies without task-specific prompting or fine-tuning
IDCC-SAM: Automated cell counting in immunocytochemistry using the segment anything model · Iowa State · Master's
Tried and failed
zero-shot pretrained cell segmentation model applied to unseen tissue histopathology classification. Outcome: did not generalise. Reason: the specific target cancer type was underrepresented in the pretraining dataset
Spatially aware deep learning for clear cell renal cell carcinoma characterization and discovery · Harvard · PhD
Tried and failed
zero-shot object detection using off-the-shelf models applied to floating aquatic debris identification. Outcome: did not generalise. Reason: Domain shift between standard training imagery and aquatic surface imagery caused near-zero detection accuracy.
Autonomous System for Identifying and Capturing Floating Waste · Georgia Tech · PhD
Tried and failed
zero-shot transfer of real-trained segmentation models applied to synthetic simulation environments. Outcome: did not generalise. Reason: Domain shift between real-world training imagery and synthetic rendering distributions.
Perception Enabled Planning for Autonomous Systems · Cornell · PhD
Tried and failed
zero-shot pre-trained instance segmentation applied to indoor robotic object detection. Outcome: did not generalise. Reason: distribution shift between pre-training dataset and deployment environment caused significant false negatives on visible objects
Autonomous exploration and object reconstruction with an MAV · Imperial · PhD
Tried and failed
zero-shot transfer of self-supervised image clustering applied to satellite imagery across geographic regions. Outcome: did not generalise. Reason: domain shift between geographic locations caused semantic confusion across visually distinct feature clusters
Characterising urban environments in Sub-Saharan Africa with satellite imagery and unsupervised deep learning · Imperial · PhD
Tried and failed
direct zero-shot cross-dataset transfer of object detectors applied to multi-object tracking benchmark evaluation. Outcome: did not generalise. Reason: domain shift between source and target datasets degraded detection accuracy without target fine-tuning
Improved 2D Camera-Based Multi-Object Tracking for Autonomous Vehicles · Virginia Tech · Master's
Tried and failed
zero-shot image-to-image translation GAN applied to cross-sensor aerial imagery. Outcome: did not generalise. Reason: sensor and domain distribution shifts between satellite training data and aerial test imagery
Deep Learning Emulators for Accessible Climate Projections · MIT · PhD
Tried and failed
Pre-trained video moment retrieval model applied to cross-domain video moment queries. Outcome: did not generalise. Reason: Severe zero-shot domain mismatch between pre-training distribution and evaluation moment queries.
User-centered Programmatic Data Labeling · Georgia Tech · PhD
Tried and failed
zero-shot transfer of pre-trained document layout models applied to long-form academic dissertations. Outcome: did not generalise. Reason: Distribution shift between short research paper training sets and complex long-form dissertation formats.
Analyzing and Navigating Electronic Theses and Dissertations · Virginia Tech · Doctorate
Tried and failed
pretrained cross-modal feature matching networks applied to zero-shot airborne 2D-3D data. Outcome: did not generalise. Reason: extreme domain shift between ground training data and airborne perspectives yielding negligible inlier ratios
Concurrent adjustment of active and passive optical sensors with GNSS and raw inertial data · EPFL · PhD
Tried and failed
zero-shot policy transfer across network topologies applied to optimization algorithm parameter tuning. Outcome: did not generalise. Reason: policies trained on one graph structure fail on differently sized or structured graphs without retraining
Designing policy optimization algorithms for multi-agent reinforcement learning · Georgia Tech · PhD
Zero-shot methods break down on complex reasoning and domain-specific structures
Unsupervised zero-shot prompting fails when tasks require structured multi-step logic, temporal planning, chemical transformation mechanisms, or clinical extraction. Without dedicated fine-tuning or concrete exemplars, models over-rely on generic priors and produce imprecise outputs or high false alarm rates.
Tried and failed
zero-shot autoregressive language model generation and classification applied to logical fallacy prediction. Outcome: did not generalise. Reason: models fail to identify and distinguish unseen fallacy categories in zero-shot settings
Extending Provenance for Understanding Claims and Data Analyses · Penn · PhD
Tried and failed
zero-shot vision-language contrastive classification applied to fine-grained multi-class pathology subtyping. Outcome: did not generalise. Reason: lack of supervision causes zero-shot models to fail on complex, fine-grained multi-class classification tasks
Data-Driven General Purpose Foundation Models for Computational Pathology · MIT · PhD
Tried and failed
zero-shot text-prompted segmentation models applied to medical image finding grounding. Outcome: no signal. Reason: pretrained models failed completely on complex free-text clinical finding descriptions
AI Systems for Understanding and Grounding Radiology Reports · Harvard · Master's
Tried and failed
direct zero-shot prompting of large language models applied to clinical note information extraction. Outcome: did not generalise. Reason: failed to adapt and performed poorly on advanced reasoning models without structured reasoning or fine-tuning
Machine Learning Approaches for Drug Combination Discovery · Cornell · PhD
Tried and failed
domain fine-tuned zero-shot language model applied to time series forecasting. Outcome: worse than baseline. Reason: exhibited performance degradation across all horizons and metrics compared to standard deep learning models
Deep Learning Methods for Built Environment Operational Management · Virginia Tech · Doctorate
Tried and failed
zero-shot prompting with abstract category definitions applied to program semantic reasoning. Outcome: worse than baseline. Reason: lacking concrete few-shot examples degraded performance relative to direct prediction
CodeSense: A real-world benchmark and dataset for code semantic reasoning · Iowa State · Master's
Tried and failed
zero-shot prompting of large language models applied to time series anomaly detection. Outcome: worse than baseline. Reason: produced high false alarm rates or generic text and code instead of precise anomaly intervals
Machine Learning Systems for Unsupervised Time Series Anomaly Detection · MIT · PhD
Tried and failed
zero-shot transformer reranker on beam search candidates applied to neural code generation candidates. Outcome: worse than baseline. Reason: compounded overfitting from using an un-finetuned reranker
Neuro-symbolic program generation and execution for hybrid reasoning · Iowa State · PhD
Tried and failed
Adding predicate confidence score to scoring function applied to parse tree simplification for event extraction. Outcome: worse than baseline. Reason: Model over-relied on learned language priors rather than generalising in the zero-shot setting
Towards Explainable Event Detection and Extraction · Virginia Tech · Doctorate
Tried and failed
zero-shot vision-language models applied to robot trajectory planning and motion reasoning. Outcome: did not generalise. Reason: models exhibit severe forward-motion and deceleration biases and fail at temporal motion reasoning
Building Intelligence that can Interact with the Physical World · MIT · PhD
Tried and failed
zero-shot large language model generation without exemplars applied to generating software vulnerability exploits. Outcome: no signal. Reason: the model lacked domain-specific context and test patterns needed to synthesize functional exploit payloads
Secure Coding Practice in Java: Automatic Detection, Repair, and Vulnerability Demonstration · Virginia Tech · Doctorate
Tried and failed
zero-shot direct prompting of large language models applied to resolving semantic ambiguities in text. Reason: Failed to resolve complex relational and temporal dependencies without intermediate feedback or attributes
Transforming Free-Form Sentences into Sequence of Unambiguous Sentences with Large Language Model · Virginia Tech · Master's
Tried and failed
zero-shot large language model reasoning applied to temporal knowledge graph link prediction. Outcome: did not generalise. Reason: models fail to understand structured graph entities and temporal relations without specialized fine-tuning
Temporal link prediction in the wild · Imperial · PhD
Zero-shot inference produces worse-than-random or invalid outputs
In several specialized prediction settings, zero-shot language and vision models produce negative correlations, excessive error, or scores worse than random chance. Other unadapted zero-shot setups completely fail to generate valid responses or produce code that cannot execute reliably.
Lost to a baseline
Vanilla zero-shot style transfer failed to return a valid response 25.4% of the time, compared to 0.6% for augmented zero-shot learning.
Understanding the Limitations of Using Large Language Models for Text Generation · Penn · PhD
Tried and failed
prompt-based zero-shot large language model classification applied to student text behavior classification. Outcome: worse than baseline. Reason: produced substantially lower AUC and more than double the false positives compared to embedding-based classifiers
MEASURING AND UNDERSTANDING STUDENTS’ SELF-REGULATED LEARNING IN TEXTUAL DATA IN COMPUTER-BASED LEARNING ENVIRONMENTS · Penn · PhD
Lost to a baseline
Zero-shot persona gpt-4o-mini performed worse than the theoretical random baseline (Qini -0.167 vs 0.000).
Language Models as Opinion Models: Techniques and Applications · MIT · PhD
Lost to a baseline
Hierarchical inference with DistilBERT+RLHR achieved lower Macro-F1 (63.61% vs 74.56%), Micro-F1 (64.21% vs 72.44%), and Example-based F1 (53.39% vs 61.06%) on WOS zero-shot compared to flat prediction DistilBERT+RLHR.
Deep Learning Models for Topic Classification and Disentanglement · Queen's University · PhD
Lost to a baseline
Zero-shot text2text gpt-4o-mini produced worse-than-random HTE prediction (Qini -0.052 vs baseline 0.183).
Language Models as Opinion Models: Techniques and Applications · MIT · PhD
Tried and failed
zero-shot multimodal large language models applied to audio event extraction. Outcome: no signal. Reason: Models completely failed to extract audio events, resulting in zero F1 performance across all tests
M3EC: A Multimodal Multidocument Benchmark for Event Extraction and Coreference Resolution · Virginia Tech · Master's
Tried and failed
LLM zero-shot reward function code generation applied to dexterous robotic hand manipulation tasks. Reason: Generated reward code failed to execute consistently across multiple random seeds.
Personalized, Safe, and Interactive Robot Programming via Human Demonstrations · Georgia Tech · PhD
Tried and failed
zero-shot co-training with soft prompting applied to weakly supervised question answering. Outcome: worse than baseline. Reason: extremely high label noise rate prevented pseudo-label refinement from improving over the initial zero-shot model
Learning from Weak Supervision: Theory, Methods, and Applications · MIT · PhD
Lost to a baseline
Zero-shot text2text Pythia-410m (untrained) produced an individual-dataset Qini (-0.063) that was worse than the ensemble baseline (0.183).
Language Models as Opinion Models: Techniques and Applications · MIT · PhD
Lost to a baseline
Unsupervised SimCSEbase and supervised FlanT5large achieved negative Spearman correlation (-3.0 and -0.43) on zero-shot Conditional Semantic Text Similarity.
Methods and Challenges In Inference Across Textual Sources · Penn · PhD
Tried and failed
evaluating unadapted dense models under activation sparsity applied to sparse neural network performance estimation. Outcome: no signal. Reason: unadapted zero-shot sparse evaluation produces unreliable accuracy rankings that do not correlate with fine-tuned performance
Efficient Deep Learning with Sparsity: Algorithms, Systems, and Applications · MIT · PhD
Zero-shot prompting struggles with subjective and nuanced human annotations
Zero-shot models exhibit near-random alignment when tasked with scoring subjective rhetorical attributes, customer sentiment, or qualitative thematic analysis. The lack of communicative context and exemplars prevents models from matching human judgment on nuanced or ambiguous categories.
Tried and failed
Zero-shot prompting of large language models applied to thematic analysis across study groups. Outcome: did not generalise. Reason: Prompts alone struggled to synthesize generalized themes and perform cross-group comparisons across qualitative data.
Embodied Virtual Reality: The Impacts of Human-Nature Connection During Engineering Design · Virginia Tech · Doctorate
Tried and failed
zero-shot large language model classification applied to persona relation extraction. Outcome: worse than baseline. Reason: Individual model predictions were unreliable compared to aggregated human majority voting.
Understanding Implicit Schemas of Reasoning · EPFL · PhD
Tried and failed
zero-shot large language model generation applied to automated customer review responses. Outcome: worse than baseline. Reason: generated text significantly impaired customer perceived helpfulness across varied sampling temperatures
Strategizing in Response to Environmental Uncertainty in the Hospitality Industry: A Data-Analytical Approach · Virginia Tech · Doctorate
Tried and failed
zero-shot prompt classification of isolated short phrases applied to narrative frame identification. Outcome: no signal. Reason: isolated phrases lacked sufficient context, making direct frame elicitation too vague and unreliable
ON THE NARRATIVE CONSTRUCTION OF REALITY IN POLITICAL DISCOURSE: A THEORY, A METHOD, AND EMPIRICAL STUDY · Penn · PhD
Tried and failed
zero-shot LLM classification on rare classes applied to noisy text transcript classification. Outcome: data insufficient. Reason: low prevalence and high semantic ambiguity resulted in poor F1 scores
Local Television News in a Changing Media Environment · Penn · PhD
Tried and failed
zero-shot large language model prompting applied to nuanced text annotation tasks. Outcome: no signal. Reason: models achieved near-random performance on subjective constructs
More Than a Sum of Its Parts: Teamwork Through a Multidimensional Lens · Penn · PhD
Lost to a baseline
Zero-shot GPT-4 achieved only 44% accuracy matching human ratings across rating constructs.
Procedural Justice for CS Hiring: Towards Fair and Equitable Resume Matching in AI Era · Virginia Tech · Doctorate
Zero-shot classifiers exhibit severe label bias and prediction collapse
Natural language inference and prompt-based zero-shot classifiers frequently suffer from extreme prediction skew by allocating most samples into a single category or favoring brief outputs. Abstract keyword prompts also cause semantic leakage and false positive over-assignment across unrelated target labels.
Tried and failed
NLI-based zero-shot classification applied to thematic categorization of domain-specific text. Outcome: did not generalise. Reason: the model exhibited severe label bias, classifying the vast majority of samples into a single category
Capturing Elusive Metrics in Economics · University of Nevada, Reno · PhD
Considered and rejected
Considered and rejected: Using purely zero-shot NLP classification without deterministic adjustments; rejected because models favored brief answers and scored unrelated phrases.
Weaving AI into Society: The Co-Evolution of Artificial Intelligence and the social fabric of organizations · LUISS · PhD
Tried and failed
instruction-tuned vision-language model applied to zero-shot visual question answering. Outcome: worse than baseline. Reason: prior instruction tuning biased the model toward coarse-grained answers rather than fine-grained predictions
Extracting Knowledge with Multimodal and Multilingual Intelligent Systems · Georgia Tech · PhD
Considered and rejected
Considered and rejected: Rejected relying solely on in-context prompting (zero-shot, few-shot, and Chain-of-Thought) for specialized legal construct classification due to poor performance and severe class imbalance errors.
Modeling Legal Constructs · Cornell · PhD
Tried and failed
zero-shot NLI for text classification applied to domain-specific technical requirements classification. Outcome: did not generalise. Reason: severe class prediction bias caused poor performance on specialized domain text
Standardization of Engineering Requirements using Large Language Models · Georgia Tech · PhD
Zero-shot transfer fails across individuals and physiological variations
Generic representations fail to transfer across subjects in biological, acoustic, and neurological tasks due to inter-individual signal variability. Without personalized calibration or target language phonetic distinctions, zero-shot models cannot capture user-specific or clinical vocal patterns.
Tried and failed
zero-shot cross-subject classification from decomposed signals applied to dexterous movement intent decoding. Outcome: did not generalise. Reason: inter-individual variability in physiological signal representations degraded generalization performance across subjects
Decoding peripheral neural correlates of dexterous movements · Imperial · PhD
Tried and failed
zero-shot cross-subject transfer of neural networks applied to fMRI brain response prediction. Outcome: did not generalise. Reason: models trained exclusively on other individuals failed to capture subject-specific functional representations without individualized readouts
Characterizing human vision through large-scale brain imaging and computational models · MIT · PhD
Considered and rejected
Considered and rejected: Rejected evaluating zero-shot generalisation across morphologies without limb dimension features (weights and lengths), recognizing that morphological topological differences alone make transfer dependent on random gait similarities.
A minimalist approach to deep multi-task learning · Oxford · PhD
Tried and failed
zero-shot transfer learning with pretrained audio embeddings applied to idiosyncratic atypical vocalization classification. Outcome: no signal. Reason: generic pretrained representations failed to capture idiosyncratic acoustic patterns of atypical vocalizations
Foundations of Cognitive, Affective, and Communicative Systems for Neurodiverse Individuals · MIT · PhD
Tried and failed
zero-shot cross-lingual transfer of sub-phonetic representations applied to unseen target language speech recognition. Outcome: did not generalise. Reason: source language lacked phonetic distinctions (like voicing contrasts) required to resolve target language syllables
Modeling of Language-Universal Speech Attributes for Multilingual Speech Recognition and Processing · Georgia Tech · PhD
Considered and rejected
Considered and rejected: Decided against using zero-shot automatic phoneme recognition models (e.g. XLS-R FAIR) because they learn surface-level acoustics without linguistic/phonemic contrasts.
Investigating the Corpus Phonetics Pipeline Applied to Diverse Speech Data · University of Washington · PhD
Lost to a baseline
In zero-shot gaze prediction on whole signals, high-privacy autoencoder signals (AE-0.1, AE-0.2) achieved worse prediction error (2.27°, 2.52°) than the baseline no-prediction approach.
Toward Privacy-Preserving Eye Tracking with Applications in Cross-Platform and Extended Reality Environments · Texas State University · PhD
Left open by the authors
Problems the authors named and did not get to.
Left open
Develop zero-shot or transfer learning AI prognostic systems for newly deployed engineering assets lacking operational or failure data. Blocker: The task is an open-ended research direction without specific target metrics, assets, or concrete methodologies proposed.
Advanced data-driven methods for prognostics and life extension of assets using condition monitoring and sensor data. · Cranfield · PhD
Left open
Evaluate generalized zero-shot learning for cross-modal IMU activity recognition by classifying both seen and unseen classes at test time. Blocker: None
Cross-modal learning from visual information for activity recognition on inertial sensors · Oxford · PhD
Left open
Develop and evaluate methods to resolve zero-shot classification failure of BioTrove-CLIP models on the Confounding-Species benchmark. Blocker: None
Curating the world’s largest biodiversity dataset for AI · Iowa State · Master's
Left open
Reduce the zero-shot scene graph relationship prediction performance gap between small and large vision-language models for resource-constrained environments. Blocker: None
Zero-Shot Scene Graph Relationship Prediction using VLMs · Virginia Tech · Master's
Left open
Improve zero-shot vision-language models for scene graph generation to match or exceed supervised recall benchmarks while preserving generalization. Blocker: None
Zero-Shot Scene Graph Relationship Prediction using VLMs · Virginia Tech · Master's
Left open
Evaluate the effect of representation dimension and dataset coverage on Proto-Successor Measure zero-shot RL performance. Blocker: None
Reinforcement learning beyond rewards : decision-making in the language of visitation distributions · UT Austin · PhD
Left open
Evaluate zero-shot, one-shot, and few-shot prompting on LLM annotation performance for pedagogical discourse moves in classroom transcripts. Blocker: Access to the annotated elementary classroom transcript dataset.
Comparing human and generative AI annotation performance: Understanding linguistic features of teacher talk in classroom discussions · Iowa State · Master's
Left open
Evaluate the zero-shot stance detection pipeline across additional domains and distinct NLP task settings beyond climate change. Blocker: None
Advancing stance detection and fine-grained content analysis for socially relevant domains · Leibniz Universität Hannover · PhD
Left open
Evaluate alternative distance metrics, prototype encodings, and transductive zero-shot learning settings in Logic Tensor Networks with vision backbones. Blocker: None
Robust machine learning models for high dimensional data interpretation · Politecnico di Torino · PhD
Left open
Apply few-shot, zero-shot, and one-shot learning methods to improve classification performance on tail classes in NSL-KDD, UNSW-NB15, and CIC-IDS-2018. Blocker: None
Modeling the Abnormality: Machine Learning-based Anomaly and Intrusion Detection in Software-defined Networks · University of Nevada, Reno · PhD
Who has worked on this
Authors of the public theses cited on this page, most-cited first.
- William Brannon · MIT · PhD · 2025
Language Models as Opinion Models: Techniques and Applications - Amartya Dutta · Virginia Tech · Master's · 2025
Zero-Shot Scene Graph Relationship Prediction using VLMs - Silin Gao · EPFL · PhD · 2026
Understanding Implicit Schemas of Reasoning - Mohammed Baharoon · Harvard · Master's · 2026
AI Systems for Understanding and Grounding Radiology Reports - Elisa Catherine Pavarino · Harvard · PhD · 2026
Finding Structure in Human Cognition: From Temporal Order Codes in Memory to Behavioral Signatures in Vision and Language - Luis Felipe Wolf Batista · Georgia Tech · PhD · 2026
Autonomous System for Identifying and Capturing Floating Waste - Maximilian Peter Müller · Tübingen · PhD · 2026
Out-of-Distribution Detection, Sharpness, and Unlearning: Advancing Robust and Trustworthy Deep Learning - Beomseok Lee · University of Trento · PhD · 2026
Multilingual Spoken Language Understanding: Efficient Speech Dataset Collection, Architectural Exploration, and Zero-Shot SLU - Ying Jin · University of Washington · PhD · 2026
Crossing the Chasm: Bridging Perception and Generative Models for Enhanced Vision-Language Understanding - Monoshi Kumar Roy · Iowa State · Master's · 2026
CodeSense: A real-world benchmark and dataset for code semantic reasoning - Zaber Ibn Abdul Hakim · Virginia Tech · Master's · 2026
M3EC: A Multimodal Multidocument Benchmark for Event Extraction and Coreference Resolution - Swanand Suhas Vaishampayan · Virginia Tech · Doctorate · 2026
Procedural Justice for CS Hiring: Towards Fair and Equitable Resume Matching in AI Era
Checking a claim in this area?
We can run the same search on any method or claim. If nothing turns up, we will say so, and that proves nothing on its own.