Takeaways/Observations/Advice from my #NeurIPS2018 experience (thread):
❄️(1): deep learning seems stagnant in terms of impactful and new ideas
❄️(2): on the flip side, deep learning is providing tremendous opportunities for building powerful applications (could be seen from the amount of creativity and value of works presented in workshops such as ML for Health and Creativity)
❄️(3): the rise of deep learning applications is all thanks to the continued integration of software tools (open source) and hardware (GPUs and TPUs)
❄️(4): Conversational AI is important because it encompasses most subfields in NLP... also, embedding social capabilities into these type of AI systems is a challenging task but very important one going forward
❄️(5): it's important to start to think about how to transition from supervised learning to problems involving semi-supervised learning and beyond. Reinforcement learning seems to be the next frontier. BTW, Bayesian deep learning is a thing!?
❄️(6): we should not avoid the questions or the thoughts of inspiring our AI algorithms based on biological systems just because people are saying this is bad... there is still a whole lot to learn from neuroscience
❄️(7): when we use the word "algorithms" to refer to AI systems it seems to be used in negative ways by the media... what if we use the term "models" instead? (rephrased from Hanna Wallach)
❄️(8): we can embrace the gains of deep learning and revise our traditional learning systems based on what we have learned from modern deep learning techniques (this was my favorite piece of advice)
❄️(9): the ease of applying machine learning to different problems has sparked leaderboard chasing... let's all be careful of those short-term rewards
❄️(10): there is a ton of noise in the field of AI... when you read about AI papers, systems and technologies just be aware of that
❄️(11): causal reasoning needs to be paid close attention... especially as we begin to heavily use AI systems to make important decisions in our lives
❄️(12): efforts in diversification seems to have amplified healthy interactions between young and prominent members of the AI community
❄️(13): we can expect to see more multimodal systems and environments being used and leveraged to help with learning in various settings (e.g., conversation, simulations, etc.)
❄️(14): let's get serious about reproducibility... this goes for all sub-disciplines in the field of AI
❄️(15): more efforts need to be invested in finding ways to properly evaluate different types of machine learning systems... this was a resonant theme at the conference...from the NLP people to the statisticians to the reinforcement learning people... it's a serious problem
I will formalize and expound on all of these observations, takeaways, and advice learned from my NeurIPS experience in a future post (will be posted directly at @dair_ai)... at the moment, I am still trying to put together the resources (links, slides, papers, etc.)
• • •
Missing some Tweet in this thread? You can try to
force a refresh
Reasoning Models Thinking Slow and Fast at Test Time
Another super cool work on improving reasoning efficiency in LLMs.
They show that slow-then-fast reasoning outperforms other strategies.
Here are my notes:
What's the high level?
Introduces a universal framework, AlphaOne (α1), for modulating the reasoning progress of large reasoning models (LRMs) during inference.
Rather than relying on rigid or automatic schedules, α1 explicitly controls when and how models engage in “slow thinking” using a tunable parameter α.
Token magic
The method dynamically inserts “wait” tokens to encourage deeper reasoning & then deterministically ends slow thinking with a “</think>” token to prompt efficient answer generation.
This yields better accuracy & efficiency than previous test-time scaling methods.
This work shows the potential of self-improving AI, inspired by biological evolution and open-ended exploration.
This is a must-read!
Here are my notes:
What's the high level?
This work presents the Darwin Gödel Machine (DGM), a system that advances the vision of self-improving AI by combining self-referential code modification with open-ended evolutionary search...
Unlike the original Gödel machine, which requires provable benefits for code changes (a practically intractable constraint), the DGM adopts an empirical approach: it modifies its own codebase and evaluates improvements on coding benchmarks.
Building Production-Grade Conversational Agents with Workflow Graphs
Uses DAG to design robust and complex agentic systems.
If you're building AI agents, this is worth a read.
Here are my notes:
Quick overview
This paper presents a pragmatic, production-ready framework for building LLM-powered conversational agents using workflow graphs, with a specific focus on e-commerce scenarios.
Instead of relying solely on end-to-end generation, the authors design agents using a directed acyclic graph (DAG), enabling flexible yet controllable interactions that adhere to strict business rules and format constraints.
Multi-State DAG Framework
Each node in the graph corresponds to a conversational state with its own system prompt, tool access, and execution rules.
This structure enables robust constraint handling (e.g., avoiding hallucinated responses or non-compliant suggestions) by localizing logic and formatting within specific graph nodes.
An Operating System for Memory-Augmented Generation in LLMs
Lots of great ideas on how to think about memory and better manage it in LLM-based agents.
Must read!
Here are my notes:
It introduces a unified operating system for managing memory in LLMs, addressing a key limitation in current architectures: their lack of structured, persistent, and governable memory...
While today's LLMs rely primarily on parametric memory (model weights) and limited short-term context, MemOS proposes a comprehensive memory lifecycle and management infrastructure designed to support continual learning, behavioral consistency, and knowledge evolution.
RAG systems are more brittle than you think, even when provided sufficient context.
Great work from Google and collaborators.
Good tips for devs included.
Here are my notes:
What is the paper about?
It introduces a new empirical framework for analyzing RAG systems through the lens of sufficient context, whether the retrieved content alone enables answering a query.
This notion helps decouple retrieval failures from generation errors in LLMs.
New definition and classifier for sufficient context
The authors formalize “sufficient context” as context that plausibly allows answering a query, without requiring ground truth.
They develop a high-accuracy LLM-based autorater (Gemini 1.5 Pro, 93% accuracy) to label instances as having sufficient or insufficient context, enabling large-scale evaluation without needing ground-truth answers.