I might not be most university researchers, but the vast majority of my publications are open access, the ones that aren't you can either find a preprint for on my webpage or email me for a copy. >>
RESEARCH
-
Differential Privacy Deployment: Real-World Applications and Best Practices
By
–
This blog post on deployments by @TedOnPrivacy may help: https://
desfontain.es/blog/real-worl
d-differential-privacy.html
… -
AI Represents a Revolutionary Force, Not a Commercial Product
By
–
AI is a revolution, not a product.
-
Citation Practices in AI Research: arXiv vs Peer Review
By
–
PSA: Every time you cite the arXiv version of something instead of the peer reviewed version, you're lending legitimacy to nonsense like this: Source: https://
arxiv.org/html/2404.0722
1v1#S6
… -
Table-LLaVa 7B: Multimodal Table Understanding Competing with GPT-4V
By
–
9/ Multimodal Table Understanding – introduces Table-LLaVa 7B, a multimodal LLM for multimodal table understanding; it’s competitive with GPT-4V and significantly outperforms existing MLLMs on multiple benchmarks.
-
LLM Context Window Enhancement: Extending to 256K Tokens
By
–
10/ Consistent Middle Enhancement in LLMs – proposes an approach to tune an LLM to effectively utilize information from the middle part of the context; it first proposes a training-efficient method to extend LLMs to longer context lengths (e.g., 4K -> 256K).
-
Mixture of Memory Experts Reduces LLM Hallucination Tenfold
By
–
8/ Mixture of Memory Experts – proposes an approach to significantly reduce hallucination (10x) by tuning millions of expert adapters (e.g., LoRAs) to learn exact facts and retrieve them from an index at inference time.
-
Transformers Meet Neural Algorithmic Reasoners Hybrid Architecture
By
–
5/ Transformers Meet Neural Algorithmic Reasoners – a new hybrid architecture that enables tokens in the LLM to cross-attend to node embeddings from a GNN-based neural algorithmic reasoner (NAR).
-
Self-Tuning LLMs Improve Knowledge Acquisition from Raw Documents
By
–
6/ Self-Tuning with LLMs – improves an LLM’s ability to effectively acquire new knowledge from raw documents through self-teaching.
-
SelfGoal: LLM Agent Framework for Hierarchical Goal Achievement
By
–
3/ SelfGoal – a framework to enhance an LLM-based agent's capabilities to achieve high-level goals; adaptively breaks down a high-level goal into a tree structure of practical subgoals during interaction with the environment.