Lilian Weng

New short course: DSPy: Build and Optimize Agentic Apps DSPy is a powerful open-source framework for automatically tuning prompts for GenAI applications. In this course, you'll learn to use DSPy, together with MLflow. This is built in partnership with Databricks and taught by Chen Qian, co-lead of the DSPy framework. Many AI builders spend hours hand-tuning prompts. When given a set of evals, DSPy automates this process. It’s especially useful for optimizing prompts, including few-shot prompts, in complex agentic AI workflows. Further, if you switch an application to a newer LLM, performance can degrade if your prompts were optimized to the previous model. DSPy automatically optimizes the entire system for the new LLM as well, using just a few evaluation examples. This course teaches DSPy works, and best practices for using it. You’ll write programs using DSPy’s signature-based programming model, debug them with MLflow tracing -- to gain visibility into how different parts of a pipeline, as well as how the overall system, are performing -- and automatically improve their accuracy with DSPy Optimizer. Please sign up here: https://lnkd.in/gdjae8AX

4,672

190 Comments

I’ve been leaning on Claude Code a lot lately (I especially like the new Claude Opus 4.1) and this new short course from DeepLearning.AI crystalized a bunch of “do this, not that” habits for agentic coding. Claude Code: A Highly Agentic Coding Assistant (built with Anthropic) is clear, hands-on, and only 90 minutes or so long.  https://lnkd.in/guvsDnBg My big takeaway: Claude Code shines when you give it context + constraints and let it work in small, testable steps.  First reading the repo, then proposing a plan, then shipping diffs (not walls of code). The course walks through exactly that across three concrete projects (RAG chatbot, refactoring a notebook into a dashboard, and a Figma-to-web app build), plus GitHub hooks. If you are not already doing it, here were a few tips that can level up your usage: Use CLAUDE.md at the repo root (and even per-package in a monorepo) so Claude automatically pulls project norms, commands, and “gotchas” into context. It’s like a living, machine-readable onboarding doc. Create custom /slash commands by dropping prompt templates into .claude/commands.  This is great for repeatable workflows like “fix PR comments and push” or “triage Issue #1234.” Team-shareable via git. Headless mode for CI: run Claude Code non-interactively to label issues, do subjective linting (naming, clarity), or fan out codebase migrations. It’s an automation surface, not just a chat. MCP servers as power-ups: wire in tools (e.g., Puppeteer, Sentry) via .mcp.json so everyone on the repo gets the same agentic capabilities out of the box. Git + GitHub ergonomics: install gh and let Claude draft commit messages, open PRs, or resolve rebases—surprisingly effective when scoped to small diffs. Why I liked the course: it doesn’t just demo “AI writes code.” It teaches the workflow: have Claude summarize the codebase, set success criteria, ship incremental changes, and keep tests close. The GitHub hooks + notebook-to-dashboard refactor were especially practical. If you’re experimenting with agentic coding or trying to make it stick across a team, this is a crisp starting point. #AI #ClaudeCode #AgenticCoding #DeveloperExperience #MLOps #Productivity

18

1 Comment

Model training on TPUs just got way easier! A completely reimagined vLLM TPU for LLM inference 👉 for PyTorch and JAX developers, this means more flexibility to run PyTorch model definitions performantly on TPU without any additional code changes, while also extending native support to JAX. read: https://lnkd.in/gW7476Hs #GoogleCloud #TPUs #LLMs

14

In collaborative machine learning (CML), early contributors take on more risk and encourage participation from wait-and-see parties, but existing CML frameworks treat every party as if they join simultaneously. The #NeurIPS2025 paper of Jiangwei Chen, Nguyen Pham, Rachael Sim, Arun Verma, Zhaoxuan Wu, Chuan Sheng Foo, and Bryan Kian Hsiang Low proposes a time-aware CML framework that rewards parties not just for what they contribute, but when they contribute: •⁠ ⁠8 incentives extending fairness with time-aware notions that incentivize early participation while preventing low-quality early submissions. •⁠ ⁠2 reward distribution methods that theoretically satisfy all incentives and recover the #ShapleyValue in time-agnostic cases. •⁠ ⁠A practical recipe for constructing valuation functions and reward realization, with empirical validation on synthetic and real-world data. Find our more at our posters! #NeurIPS2025 Thu, Dec 4, Exhibit Hall C, D, E #1104 #EurIPS2025 Wed, Dec 3, Poster Stand #56 Paper: https://lnkd.in/g_yM6j39 #FederatedLearning

50

Among other things, my team has been focusing on AI research for agents. We just blogged about a recent project: the Test-Time Diffusion Deep Researcher (TTD-DR). This framework uses a Deep Research agent to draft and revise its own drafts using high-quality retrieved information. This approach achieves new state-of-the-art results in writing long-form research reports and completing complex reasoning tasks. The work achieves better results than any other deep research agent we compared to. It also shows that self-evaluation and self-improvement are must-have components of a successful agent. https://lnkd.in/gBZpVMQy

297

8 Comments

📑 New Survey: The Landscape of Agentic Reinforcement Learning for LLMs A comprehensive survey has just been released, synthesizing 500+ recent works on how reinforcement learning is transforming large language models from passive text generators into agentic decision-makers. 🔑 Key highlights from the paper: - Formalizes the shift from LLM-RL (single-step MDPs) to Agentic RL (long-horizon POMDPs) - Proposes a twofold taxonomy: By capabilities: planning, reasoning, tool use, memory, self-improvement, perception By applications: code agents, math agents, GUI agents, vision/embodied agents, multi-agent systems, and more - Consolidates open-source environments, frameworks, and benchmarks into a practical compendium for researchers - Discusses open challenges: trustworthiness, scaling agentic training, and scaling environments

113

4 Comments

RQ-VAE models naturally discover taxonomic hierarchies for semantic IDs but lack interpretability. I'm exploring LLMs as interpreters using them to analyze and label entity groups within codebook levels to make the learned structure human-readable. What potential issues should I watch out for with this approach or are there better way to evaluate generated semantic ids are meaningful?

6

1 Comment

Many of our users have been asking for stronger guarantees around structured outputs and less prompt drift as projects grow. We listened. Today we’re shipping BAML (by Boundary (YC W23)) support in cognee: type-safe, schema-aligned LLM calls with dynamic Pydantic→BAML mapping and validation, without having to change the design of your cognee pipelines. Flip a flag to switch between BAML and Instructor. With BAML in cognee, you get production hygiene: fewer parsing errors, clearer versioning, safer changes, faster iteration, and more. Read the full benefits from the link below. Huge thanks to the Boundary (YC W23) team for their support during integration. We deeply appreciate their work and we’re excited about what this update unlocks for cognee users worldwide.

62

12 Comments

Positional encoding and persistent homology have been powerful tools for graph neural networks. This very recent ICML paper combines the two methodologies to leverage both algorithm strengths. It's an interesting new direction for TDA + neural network architectures. https://lnkd.in/eskZZfsW

92

2 Comments

Speeding up PyTorch performance usually requires the use of intermediate optimization frameworks, or writing low-level optimized kernels. This can be burdensome, especially when supporting multiple target devices. Taras Sereda led research to evaluate if frontier models could automatically generate low-level kernels from pure PyTorch. Our technique sped up inference on Apple by 1.87X on average! Check out the details here: https://lnkd.in/g4tdEXEi

89

5 Comments

Forge delivers 2.4–5.2× faster inference than torch.compile on NVIDIA B200 We benchmarked Forge against torch.compile(mode='max-autotune-no-cudagraphs') the strongest PyTorch baseline available across 7 production models Now publicly available with a free trial: https://lnkd.in/dnw_XmJH

35

2 Comments

I’m excited to attend NeurIPS workshop sessions at San Diego and present two papers authored by the applied research team: 1. GraphMatch: Fusing Language and Graph Representations in a Dynamic Two-Sided Work Marketplace. Mikołaj Sacha et al. - NeurIPS Workshop on Unifying Representations in Neural Models (UniReps) 2. Towards Real-World Evaluation of Agentic Work in Freelance Marketplaces. Mattie Terzolo et al. - NeurIPS Workshop on LLM Evaluation Over the next couple of days, I’ll be sharing insights and some behind-the-scenes perspectives on how we think about these models, how they’re shaping Upwork today, and the opportunities we see ahead. For attendees already onsite at the main conference, please stop by the Upwork booth #722 to learn more about the efforts the ML & AI team is driving - from research to real product impact. Feels great to be again publishing at NeurIPS after a hiatus and looking forward to great conversations and inspiration ahead!

50

2 Comments

I just published Vol. 108 of "Top Information Retrieval Papers of the Week" on Substack. My Substack newsletter features the 7-10 most notable research papers on information retrieval (including recommender systems, search & ranking, etc.) from each week, with a brief summary, and links to the paper/codebase. This week’s newsletter highlights the following research work: 📚 The Case for Implicit Semantics in Text Embedding Research, from Sun et al. 📚 Understanding Contrastive Learning Through Embedding Similarities, from Yonsei University 📚 A Systematic Analysis of GraphRAG vs. Traditional RAG, from Xiang et al. 📚 Improving Visual Question Answering with Reasoning Context Re-ranking, from Yang et al. 📚 Adaptive Context Window Selection for RAG Systems via Similarity Score Distribution Analysis, from Megagon Labs 📚 Joint Optimization of Recall and Semantic Relevance in Large-Scale Item Retrieval, from Meta 📚 Video-ColBERT: Fine-Grained Late Interaction for Text-to-Video Retrieval, from Reddy et al. 📚 A Comprehensive Survey of Reasoning-Enhanced RAG Systems, from Liang et al. 📚 Efficient Long Semantic ID Generation for Large-Scale Recommendation, from Meta 📚 RecGPT: A Text-Driven Foundation Model for Cross-Domain Sequential Recommendation, from Jiang et al. #InformationRetrieval #ResearchPapers #CuratedContent #Newsletter  #substack

23

1 Comment

🔬 Granite Docling 258M: Efficient Document AI for Structured Extraction IBM Research released Granite Docling 258M—a compact vision-language model optimized for high-precision document understanding with layout preservation. Key Technical Specs: → 258M parameters (lightweight, inference-efficient) → Vision encoder + autoregressive decoder architecture → Multi-stage training: synthetic + real-world document datasets → Output formats: Markdown, JSON with preserved structure → CPU-friendly inference, production-ready Performance: → Competitive accuracy vs larger models on DocLayNet & PubLayNet → Maintains layout fidelity: tables, headers, reading order intact → Fast processing for enterprise-scale document pipelines Practical Applications: → RAG systems requiring structured context → Legal/financial document parsing with layout integrity → Research paper extraction for knowledge graphs → Multi-format document processing workflows Why It Matters: Balances efficiency with accuracy—critical for production Document AI where compute cost and latency matter. Open-source availability (Hugging Face + GitHub) accelerates adoption. Ideal for teams building document-heavy AI systems without overprovisioning infrastructure. Links are in the comments.

86

1 Comment