Stephen Bach
24 papers · 2010–2026 · 9 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (62) π Conference Polyglot Β· Silver π Academic Marathon Β· Full π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π₯
Mega-Team Β· Squad
π§¬
Topic Evolution
π
Grand Slam
π
Keyword Champion
π§
Keyword Pioneer
π
Renaissance Researcher
(7)
π₯
Unstoppable Β· Bronze
β
The Questioner
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(126)
Top co-authors
Research topics
Machine Learning
(18)
Artificial Intelligence
(16)
Learning Types Β· Machine Learning
(12)
Core AI
(10)
Natural Language Processing
(9)
Deep Learning
(8)
Learning Paradigms
(7)
Learning Types Β· Deep Learning
(7)
Optimization & Theory
(7)
Core Methods
(6)
Resources & Methods
(6)
Applications
(3)
Computer Vision
(2)
Bayesian & Probabilistic
(2)
Data Science & Analytics
(1)
Keywords
vision-language model
(5)
large language model
(5)
zero-shot learning
(4)
probabilistic graphical model
(3)
weak supervision
(3)
semi-supervised learning
(2)
markov random field
(2)
information retrieval
(2)
image classification
(2)
instruction tuning
(2)
map inference
(2)
graphical model
(2)
structured prediction
(2)
weakly supervised learning
(2)
named entity recognition
(2)
synthetic data generation
(2)
label aggregation
(2)
transfer learning
(1)
variational inference
(1)
reinforcement learning
(1)
Papers
Revisiting Generalization Across Difficulty Levels: Itβs Not So Easy
EACL 2026
Trove: A Flexible Toolkit for Dense Retrieval
EACL 2026
An Adaptive Method for Weak Supervision with Drifting Data
AISTATS 2025
Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance
EMNLP 2025
Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages
NAACL 2025
The State of Multilingual LLM Safety Research: From Measuring The Language Gap To Mitigating It
EMNLP 2025
Does CLIP Bind Concepts? Probing Compositionality in Large Image Models
EACL 2024
Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification
ICLR 2024
If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions
EMNLP 2024
Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation
ACL 2024
LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons
EMNLP 2024
Preference Tuning For Toxicity Mitigation Generalizes Across Languages
EMNLP 2024
Alfred: A System for Prompted Weak Supervision
ACL 2023
Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning
NeurIPS 2023
Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
ICLR 2023
BigBio: A Framework for Data-Centric Biomedical Natural Language Processing
NeurIPS 2022
Multitask Prompted Training Enables Zero-Shot Task Generalization
ICLR 2022
Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes
NeurIPS 2022
Semi-Supervised Aggregation of Dependent Weak Supervision Sources With Performance Guarantees
AISTATS 2021
Weakly Supervised Sequence Tagging from Noisy Rules
AAAI 2020
Paired-Dual Learning for Fast Training of Latent Variable Hinge-Loss MRFs
ICML 2015
Unifying Local Consistency and MAX SAT Relaxations for Scalable Inference with Rounding Guarantees
AISTATS 2015
Scaling MPE Inference for Constrained Continuous Markov Random Fields with Consensus Optimization
NeurIPS 2012
A Bayesian Approach to Concept Drift
NeurIPS 2010