Accepted Papers

The papers are publicly available on OpenReview: https://openreview.net/group?id=NeurIPS.cc/2023/Workshop/R0-FoMo

1. (Oral) [Best Paper Award] The Consensus Game: Language Model Generation via Equilibrium Search

2. (Oral) [Best Paper Award] Mindstorms in Natural Language-Based Societies of Mind

3. (Oral) [Honorable Mention for Best Paper] Teaching language models with canonical examples

4. (Oral) [Honorable Mention for Best Paper] Foundation Models Can Robustify Themselves, For Free

5. (Spotlight) LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

6. (Spotlight) Learning Through Consistency for Prompt Tuning

7. (Spotlight) Towards General-Purpose In-Context Learning Agents

8. (Spotlight) Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions

9. (Spotlight) Effective Data Augmentation With Diffusion Models

10. (Spotlight) Evaluating Adversarial Defense in the Era of Large Language Models

11. (Spotlight) Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering

12. (Spotlight) TART: A plug-and-play Transformer module for task-agnostic reasoning

13. (Spotlight) Efficient Online Data Mixing For Language Model Pre-Training

14. (Spotlight) Estimating Uncertainty in Multimodal Foundation Models using Public Internet Data

15. (Spotlight) Trained Transformers Learn Linear Models In-Context

16. (Spotlight) InstructEval: Systematic Evaluation of Instruction Selection Methods

17. (Spotlight) Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game

18. (Spotlight) Quantifying Uncertainty in Natural Language Explanations of Large Language Models

19. (Spotlight) A Universal Prompt Generator for Large Language Models

20. On the Relationship between Skill Neurons and Robustness in Prompt Tuning

21. Enhancing Large Language Models with Ensemble of Critics for Mitigating Toxicity and Hallucination

22. SAD: Segment Any RGBD

23. Deep Embedded Clustering in Few-shot Representations (DECiFR)

24. PATHFINDER: Guided Search over Multi-Step Reasoning Paths

25. Function-constrained Program Synthesis

26. How Robust is Google's Bard to Adversarial Image Attacks?

27. AutoVP: An Automated Visual Prompting Framework and Benchmark

28. Can LLM-Generated Misinformation Be Detected?

29. Selective Prediction For Open-Ended Question Answering in Black-Box Vision-Language Models

30. Dissecting In-Context Learning of Translations

31. Extra Training Provides a Strong Baseline for CLIP

32. Context is Environment

33. Fewshot learning on global multimodal embeddings for earth observation tasks

34. Meta- (out-of-context) learning in neural networks

35. SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

36. FedJETs: Efficient Just-In-Time Personalization with Federated Mixture of Experts

37. Cross-Modal Learning for Chemistry Property Prediction: Large Language Models Meet Graph Machine Learning

38. Crossing New Frontiers: Knowledge-Augmented Large Language Model Prompting for Zero-Shot Text-Based De Novo Molecule Design

39. Hierarchical Network Fusion for Multi-Modal Electron Micrograph Representation Learning with Foundational Large Language Models

40. Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification

41. Why Larger Language Models Do In-context Learning Differently?

42. Are Large Language Models Post Hoc Explainers?

43. READ: Recurrent Adaptation of Large Transformers

44. Think before you speak: Training Language Models With Pause Tokens

45. LOVM: Language-Only Vision Model Selection

46. Trainable Transformer in Transformer

47. ICL-Markup: Structuring In-Context Learning using Soft-Token Tags

48. LOWA: Localize Objects in the Wild with Attributes

49. HePCo: Data-Free Heterogeneous Prompt Consolidation for Continual Federated Learning

50. On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation

51. Dr.ICL: Demonstration-Retrieved In-context Learning

52. Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning

53. SELF-EXPLAIN: Teaching Large Language Models to Reason Complex Questions by Themselves

54. Automatic Hallucination Assessment for Aligned Large Language Models via Transferable Adversarial Attacks

55. Predicting the Performance of Foundation Models via Agreement-on-the-line

56. JAB: Joint Adversarial Prompting and Belief Augmentation

57. Benchmarking Robustness of Text-Image Composed Retrieval

58. Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data

59. Jailbreaking Black Box Large Language Models in Twenty Queries

60. Latent Skill Discovery for Chain-of-Thought Reasoning

61. HART: Efficient Adaptation via Regularized Autoregressive Parameter Generation

62. One shot localization and segmentation of medical images with Foundation Models

63. Task Arithmetic with LoRA for Continual Learning

64. How does fine-tuning affect your model? Mechanistic analysis on procedural tasks

65. Image Clustering Conditioned on Text Criteria

66. Lag-Llama: Towards Foundation Models for Time Series Forecasting

67. Zero-shot Conversational Summarization Evaluations with small Large Language Models

68. Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks

69. How Capable Can a Transformer Become? A Study on Synthetic, Interpretable Tasks

70. Flexible visual prompts for in context learning in computer vision

71. What’s important here?: Opportunities and Challenges of LLM in retrieving information from Web Interface

72. Zero-shot Clustering of Embeddings with Pretrained and Self-Supervised Learnt Encoders

73. OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning

74. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

75. Stepwise Inference in Transformers: Exploring a Synthetic Graph Navigation Task

76. Fooling GPT with adversarial in-context examples for text classification

77. Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing

78. Understanding the Vulnerability of CLIP to Image Compression

79. How Do Large Multimodal Models Really Fare in Classical Vision Few-Shot Challenges? A Deep Dive

80. Coded Prompts for Large Language Models

81. Zero-shot Improvement of Object Counting with CLIP

82. Analyzing ChatGPT’s Behavior Shifts Over Time

83. Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation

84. CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a $10,000 Budget

85. Provable Robust Watermarking for AI-Generated Text

86. Neural Sandbox Framework for Classification: A Concept Based Method of Leveraging LLMs for Text Classification

87. Divide and Conquer: Two-Level Problem Remodeling for Large-Scale Few-Shot Learning

88. Visual Cropping Improves Zero-Shot Question Answering of Multimodal Large Language Models

89. Group Preference Optimization: Few-Shot Alignment of Large Language Models

90. Investigating Hiring Bias in Large Language Models

91. In-Context Learning and Bayesian Inference

92. AutoMix: Mixing Models with Few-shot Self and Meta Verification