Note: I sent out the last stack yesterday morning (EST), so some publications from the 28th weren't included. Here are the ones missing from the 28th, followed by the complete list for February 29th.

28th February 2024

1. Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness

2. FedHCA: Towards Hetero-Client Federated Multi-Task Learning

3. Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing

4. Protein Multimer Structure Prediction via Prompt Learning

5. Less is More: Fewer Interpretable Region via Submodular Subset Selection

6. When does word order matter and when doesn't it?

7. How do Large Language Models Handle Multilingualism?

8. On the Decision-Making Abilities in Role-Playing using Large Language Models

9. FlexLLM: A System for Co-Serving Large Language Model Inference and Parameter-Efficient Finetuning

10. How Much Annotation is Needed to Compare Summarization Models?

11. Learning to Compress Prompt in Natural Language Formats

12. Grounding Language Models for Visual Entity Recognition

13. Simple linear attention language models balance the recall-throughput tradeoff

14. FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability

15. Tokenization Is More Than Compression

16. Evaluating Quantized Large Language Models

17. BFRFormer: Transformer-based generator for Real-World Blind Face Restoration

18. Cooperative Open-ended Learning Framework for Zero-shot Coordination

29th February 2024

1. Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers

2. SeMoLi: What Moves Together Belongs Together

3. ManiFPT: Defining and Analyzing Fingerprints of Generative Models

4. OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

5. Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models

6. ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL

7. Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Process

8. PRSA: Prompt Reverse Stealing Attacks against Large Language Models

9. Teaching Large Language Models an Unseen Language on the Fly

10. Typographic Attacks in Large Multimodal Models Can be Alleviated by More Informative Prompts

11. Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models

12. Exploring the Efficacy of Large Language Models in Summarizing Mental Health Counseling Sessions: A Benchmark Study

13. Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models

14. PopALM: Popularity-Aligned Language Models for Social Media Trendy Response Prediction

15. Syntactic Ghost: An Imperceptible General-purpose Backdoor Attacks on Pre-trained Language Models

16. AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging

17. Reducing Hallucinations in Entity Abstract Summarization with Facts-Template Decomposition

18. Language Models Represent Beliefs of Self and Others

19. End-to-End Quantum Vision Transformer: Towards Practical Quantum Speedup in Large-Scale Models

Language-specific LLM research

1. Advancing Generative AI for Portuguese with Open Decoder Gervásio PT*

2. Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark

3. PeLLE: Encoder-based language models for Brazilian Portuguese based on open data

4. Improving Legal Judgement Prediction in Romanian with Long Text Encoders

Dataset

1. WanJuan-CC: A Safe and High-Quality Open-sourced English Webtext Dataset