Accepted Papers
The papers are publicly available on OpenReview: https://openreview.net/group?id=NeurIPS.cc/2023/Workshop/R0-FoMo
(Oral) [Best Paper Award] The Consensus Game: Language Model Generation via Equilibrium Search
(Oral) [Best Paper Award] Mindstorms in Natural Language-Based Societies of Mind
(Oral) [Honorable Mention for Best Paper] Teaching language models with canonical examples
(Oral) [Honorable Mention for Best Paper] Foundation Models Can Robustify Themselves, For Free
(Spotlight) LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
(Spotlight) Learning Through Consistency for Prompt Tuning
(Spotlight) Towards General-Purpose In-Context Learning Agents
(Spotlight) Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions
(Spotlight) Effective Data Augmentation With Diffusion Models
(Spotlight) Evaluating Adversarial Defense in the Era of Large Language Models
(Spotlight) Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering
(Spotlight) TART: A plug-and-play Transformer module for task-agnostic reasoning
(Spotlight) Efficient Online Data Mixing For Language Model Pre-Training
(Spotlight) Estimating Uncertainty in Multimodal Foundation Models using Public Internet Data
(Spotlight) Trained Transformers Learn Linear Models In-Context
(Spotlight) InstructEval: Systematic Evaluation of Instruction Selection Methods
(Spotlight) Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
(Spotlight) Quantifying Uncertainty in Natural Language Explanations of Large Language Models
(Spotlight) A Universal Prompt Generator for Large Language Models
On the Relationship between Skill Neurons and Robustness in Prompt Tuning
Enhancing Large Language Models with Ensemble of Critics for Mitigating Toxicity and Hallucination
SAD: Segment Any RGBD
Deep Embedded Clustering in Few-shot Representations (DECiFR)
PATHFINDER: Guided Search over Multi-Step Reasoning Paths
Function-constrained Program Synthesis
How Robust is Google's Bard to Adversarial Image Attacks?
AutoVP: An Automated Visual Prompting Framework and Benchmark
Can LLM-Generated Misinformation Be Detected?
Selective Prediction For Open-Ended Question Answering in Black-Box Vision-Language Models
Dissecting In-Context Learning of Translations
Extra Training Provides a Strong Baseline for CLIP
Context is Environment
Fewshot learning on global multimodal embeddings for earth observation tasks
Meta- (out-of-context) learning in neural networks
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
FedJETs: Efficient Just-In-Time Personalization with Federated Mixture of Experts
Cross-Modal Learning for Chemistry Property Prediction: Large Language Models Meet Graph Machine Learning
Crossing New Frontiers: Knowledge-Augmented Large Language Model Prompting for Zero-Shot Text-Based De Novo Molecule Design
Hierarchical Network Fusion for Multi-Modal Electron Micrograph Representation Learning with Foundational Large Language Models
Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification
Why Larger Language Models Do In-context Learning Differently?
Are Large Language Models Post Hoc Explainers?
READ: Recurrent Adaptation of Large Transformers
Think before you speak: Training Language Models With Pause Tokens
LOVM: Language-Only Vision Model Selection
Trainable Transformer in Transformer
ICL-Markup: Structuring In-Context Learning using Soft-Token Tags
LOWA: Localize Objects in the Wild with Attributes
HePCo: Data-Free Heterogeneous Prompt Consolidation for Continual Federated Learning
On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation
Dr.ICL: Demonstration-Retrieved In-context Learning
Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning
SELF-EXPLAIN: Teaching Large Language Models to Reason Complex Questions by Themselves
Automatic Hallucination Assessment for Aligned Large Language Models via Transferable Adversarial Attacks
Predicting the Performance of Foundation Models via Agreement-on-the-line
JAB: Joint Adversarial Prompting and Belief Augmentation
Benchmarking Robustness of Text-Image Composed Retrieval
Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data
Jailbreaking Black Box Large Language Models in Twenty Queries
Latent Skill Discovery for Chain-of-Thought Reasoning
HART: Efficient Adaptation via Regularized Autoregressive Parameter Generation
One shot localization and segmentation of medical images with Foundation Models
Task Arithmetic with LoRA for Continual Learning
How does fine-tuning affect your model? Mechanistic analysis on procedural tasks
Image Clustering Conditioned on Text Criteria
Lag-Llama: Towards Foundation Models for Time Series Forecasting
Zero-shot Conversational Summarization Evaluations with small Large Language Models
Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks
How Capable Can a Transformer Become? A Study on Synthetic, Interpretable Tasks
Flexible visual prompts for in context learning in computer vision
What’s important here?: Opportunities and Challenges of LLM in retrieving information from Web Interface
Zero-shot Clustering of Embeddings with Pretrained and Self-Supervised Learnt Encoders
OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning
DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
Stepwise Inference in Transformers: Exploring a Synthetic Graph Navigation Task
Fooling GPT with adversarial in-context examples for text classification
Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing
Understanding the Vulnerability of CLIP to Image Compression
How Do Large Multimodal Models Really Fare in Classical Vision Few-Shot Challenges? A Deep Dive
Coded Prompts for Large Language Models
Zero-shot Improvement of Object Counting with CLIP
Analyzing ChatGPT’s Behavior Shifts Over Time
Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation
CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a $10,000 Budget
Provable Robust Watermarking for AI-Generated Text
Neural Sandbox Framework for Classification: A Concept Based Method of Leveraging LLMs for Text Classification
Divide and Conquer: Two-Level Problem Remodeling for Large-Scale Few-Shot Learning
Visual Cropping Improves Zero-Shot Question Answering of Multimodal Large Language Models
Group Preference Optimization: Few-Shot Alignment of Large Language Models
Investigating Hiring Bias in Large Language Models
In-Context Learning and Bayesian Inference
AutoMix: Mixing Models with Few-shot Self and Meta Verification