aidevblogs
⌘K
BlogsVideosTweets
AllLLMsComputer VisionMLOpsAgentsData EngineeringResearchSafety
langchain-classic==1.0.1
LangChain Releases·github.com·2 days ago·LLMs
Google's year in review: 8 areas with research breakthroughs in 2025
Google AI Blog·blog.google·3 days ago·LLMs
langchain-core==0.3.81
LangChain Releases·github.com·3 days ago·LLMs
langchain-core==1.2.5
LangChain Releases·github.com·3 days ago·LLMs
v0.13.0
vLLM Releases·github.com·4 days ago·LLMs
One in a million: celebrating the customers shaping AI’s future
OpenAI Blog·openai.com·4 days ago·LLMs
Continuously hardening ChatGPT Atlas against prompt injection
OpenAI Blog·openai.com·4 days ago·LLMs
The Shape of AI: Jaggedness, Bottlenecks and Salients
One Useful Thing (Ethan Mollick)·oneusefulthing.org·5 days ago·LLMs
v0.13.5
Ollama Releases·github.com·6 days ago·LLMs
2025 LLM Year in Review
Andrej Karpathy·karpathy.bearblog.dev·6 days ago·LLMs
v0.14.0rc0
vLLM Releases·github.com·7 days ago·LLMs
langchain-core==1.2.3
LangChain Releases·github.com·7 days ago·LLMs
Chemical hygiene
Andrej Karpathy·karpathy.bearblog.dev·7 days ago·LLMs
langchain-openai==1.1.6
LangChain Releases·github.com·7 days ago·LLMs
You can now verify Google AI-generated videos in the Gemini app.
Google AI Blog·blog.google·8 days ago·LLMs
v0.13.5-rc1
Ollama Releases·github.com·8 days ago·LLMs
2025 Interconnects year in review
Interconnects (Nathan Lambert)·interconnects.ai·8 days ago·LLMs
Evaluating chain-of-thought monitorability
OpenAI Blog·openai.com·8 days ago·LLMs
AI literacy resources for teens and parents
OpenAI Blog·openai.com·8 days ago·LLMs
Updating our Model Spec with teen protections
OpenAI Blog·openai.com·8 days ago·LLMs
v0.13.0rc4: [v1] Add PrefixLM support to TritonAttention backend (#30386)
vLLM Releases·github.com·8 days ago·LLMs
Addendum to GPT-5.2 System Card: GPT-5.2-Codex
OpenAI Blog·openai.com·8 days ago·LLMs
Introducing GPT-5.2-Codex
OpenAI Blog·openai.com·8 days ago·LLMs
Watch a podcast discussion about Gemini 3 and the future of Search.
Google AI Blog·blog.google·8 days ago·LLMs
Introducing GPT-5.2-Codex
OpenAI Blog·openai.com·8 days ago·LLMs
v0.13.5-rc0: GGML update to ec98e2002 (#13451)
Ollama Releases·github.com·8 days ago·LLMs
langchain-openai==1.1.5
LangChain Releases·github.com·8 days ago·LLMs
Gemini 3 Flash: frontier intelligence built for speed
Google AI Blog·blog.google·9 days ago·LLMs
v0.13.0rc3: [XPU] fix broken fp8 online quantization for XPU platform (#30831)
vLLM Releases·github.com·9 days ago·LLMs
v0.13.0rc2: [ROCm] [Bugfix] Fix torch sdpa hallucination (#30789)
vLLM Releases·github.com·9 days ago·LLMs
Developers can now submit apps to ChatGPT
OpenAI Blog·openai.com·9 days ago·LLMs
langchain-tests==1.1.1
LangChain Releases·github.com·9 days ago·LLMs
langchain-core==1.2.2
LangChain Releases·github.com·9 days ago·LLMs
langchain-openai==1.1.4
LangChain Releases·github.com·9 days ago·LLMs
v0.13.4
Ollama Releases·github.com·9 days ago·LLMs
Measuring AI’s capability to accelerate biological research
OpenAI Blog·openai.com·10 days ago·LLMs
v0.13.4-rc2
Ollama Releases·github.com·10 days ago·LLMs
The new ChatGPT Images is here
OpenAI Blog·openai.com·10 days ago·LLMs
Olmo 3 and the Open LLM Renaissance
Cameron Wolfe·cameronrwolfe.substack.com·11 days ago·LLMs
2025 Open Models Year in Review
Interconnects (Nathan Lambert)·interconnects.ai·11 days ago·LLMs
2025 Year in Review
Eugene Yan·eugeneyan.com·12 days ago·LLMs
v0.13.4-rc1
Ollama Releases·github.com·13 days ago·LLMs
v0.13.4-rc0
Ollama Releases·github.com·13 days ago·LLMs
Bringing state-of-the-art Gemini translation capabilities to Google Translate
Google AI Blog·blog.google·14 days ago·LLMs
Transformers v5.0.0rc0
Transformers Releases·github.com·14 days ago·LLMs
v0.13.3
Ollama Releases·github.com·14 days ago·LLMs
How We Used Codex to Ship Sora for Android in 28 Days
OpenAI Blog·openai.com·14 days ago·LLMs
BBVA and OpenAI collaborate to transform global banking
OpenAI Blog·openai.com·14 days ago·LLMs
Gradient Canvas: Celebrating over a decade of artistic collaborations with AI
Google AI Blog·blog.google·14 days ago·LLMs
v5.0.0rc1
Transformers Releases·github.com·15 days ago·LLMs
Advancing science and math with GPT-5.2
OpenAI Blog·openai.com·15 days ago·LLMs
Increasing revenue 300% by bringing AI to SMBs
OpenAI Blog·openai.com·15 days ago·LLMs
Update to GPT-5 System Card: GPT-5.2
OpenAI Blog·openai.com·15 days ago·LLMs
v0.13.3-rc1: feat: llama.cpp bump (17f7f4) for SSM performance improvements (#13408)
Ollama Releases·github.com·15 days ago·LLMs
New Talk: Building Olmo 3 Think
Interconnects (Nathan Lambert)·interconnects.ai·15 days ago·LLMs
These developers are changing lives with Gemma 3n
Google AI Blog·blog.google·16 days ago·LLMs
Why AGI Will Not Happen
Tim Dettmers·timdettmers.com·16 days ago·LLMs
Auto-grading decade-old Hacker News discussions with hindsight
Andrej Karpathy·karpathy.bearblog.dev·16 days ago·LLMs
v0.13.0rc1
vLLM Releases·github.com·16 days ago·LLMs
v0.13.3-rc0
Ollama Releases·github.com·17 days ago·LLMs
Transforming Nordic classrooms through responsible AI partnerships
Google AI Blog·blog.google·18 days ago·LLMs
v0.12.0
vLLM Releases·github.com·20 days ago·LLMs
The latest AI news we announced in November
Google AI Blog·blog.google·20 days ago·LLMs
v0.14.10
LlamaIndex Releases·github.com·21 days ago·LLMs
From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates
Sebastian Raschka·magazine.sebastianraschka.com·23 days ago·LLMs
v0.14.9
LlamaIndex Releases·github.com·23 days ago·LLMs
The space of minds
Andrej Karpathy·karpathy.bearblog.dev·26 days ago·LLMs
[Subscribers only] Dev Writers Retreat 2025: WRITING FOR HUMANS — 10 Fellowship spots left!
Latent Space·latent.space·28 days ago·LLMs
Patch release v4.57.3
Transformers Releases·github.com·about 1 month ago·LLMs
Patch Release v4.57.2
Transformers Releases·github.com·about 1 month ago·LLMs
Group Relative Policy Optimization (GRPO)
Cameron Wolfe·cameronrwolfe.substack.com·about 1 month ago·LLMs
Latest open artifacts (#16): Who's building models in the U.S., China's model release playbook, and a resurgence of truly open models
Interconnects (Nathan Lambert)·interconnects.ai·about 1 month ago·LLMs
Product Evals in Three Simple Steps
Eugene Yan·eugeneyan.com·about 1 month ago·LLMs
Olmo 3: America’s truly open reasoning models
Interconnects (Nathan Lambert)·interconnects.ai·about 1 month ago·LLMs
v0.11.2
vLLM Releases·github.com·about 1 month ago·LLMs
v0.11.1
vLLM Releases·github.com·about 1 month ago·LLMs
Three Years from GPT-3 to Gemini 3
One Useful Thing (Ethan Mollick)·oneusefulthing.org·about 1 month ago·LLMs
The Agent Labs Thesis
Latent Space·latent.space·about 1 month ago·LLMs
Verifiability
Andrej Karpathy·karpathy.bearblog.dev·about 1 month ago·LLMs
Why AI writing is mid
Interconnects (Nathan Lambert)·interconnects.ai·about 1 month ago·LLMs
v0.11.1rc7
vLLM Releases·github.com·about 1 month ago·LLMs
Interview: Ant Group's open model ambitions
Interconnects (Nathan Lambert)·interconnects.ai·about 1 month ago·LLMs
Giving your AI a Job Interview
One Useful Thing (Ethan Mollick)·oneusefulthing.org·about 1 month ago·LLMs
v0.14.8
LlamaIndex Releases·github.com·about 2 months ago·LLMs
5 Thoughts on Kimi K2 Thinking
Interconnects (Nathan Lambert)·interconnects.ai·about 2 months ago·LLMs
Beyond Standard LLMs
Sebastian Raschka·magazine.sebastianraschka.com·about 2 months ago·LLMs
RL without TD learning
Berkeley AI Research (BAIR)·bair.berkeley.edu·about 2 months ago·LLMs
v0.14.7
LlamaIndex Releases·github.com·about 2 months ago·LLMs
PPO for LLMs: A Guide for Normal People
Cameron Wolfe·cameronrwolfe.substack.com·about 2 months ago·LLMs
v0.14.6
LlamaIndex Releases·github.com·2 months ago·LLMs
Burning out
Interconnects (Nathan Lambert)·interconnects.ai·2 months ago·LLMs
An Opinionated Guide to Using AI Right Now
One Useful Thing (Ethan Mollick)·oneusefulthing.org·2 months ago·LLMs
Advice for New Principal Tech ICs (i.e., Notes to Myself)
Eugene Yan·eugeneyan.com·2 months ago·LLMs
Latest open artifacts (#15): It’s Qwen's world and we get to live in it, on CAISI's report, & GPT-OSS update
Interconnects (Nathan Lambert)·interconnects.ai·2 months ago·LLMs
The State of Open Models
Interconnects (Nathan Lambert)·interconnects.ai·2 months ago·LLMs
v0.14.5
LlamaIndex Releases·github.com·2 months ago·LLMs
Patch release v4.57.1
Transformers Releases·github.com·2 months ago·LLMs
Thoughts on The Curve
Interconnects (Nathan Lambert)·interconnects.ai·3 months ago·LLMs
Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)
Sebastian Raschka·magazine.sebastianraschka.com·3 months ago·LLMs
v0.14.4
LlamaIndex Releases·github.com·3 months ago·LLMs
v4.57.0: Qwen3-Next, Vault Gemma, Qwen3 VL, LongCat Flash, Flex OLMO, LFM2 VL, BLT, Qwen3 OMNI MoE, Parakeet, EdgeTAM, OLMO3
Transformers Releases·github.com·3 months ago·LLMs
Taste is your moat — with Dylan Field, Figma
Latent Space·latent.space·3 months ago·LLMs
Animals vs Ghosts
Andrej Karpathy·karpathy.bearblog.dev·3 months ago·LLMs
ChatGPT: The Agentic App
Interconnects (Nathan Lambert)·interconnects.ai·3 months ago·LLMs
REINFORCE: Easy Online RL for LLMs
Cameron Wolfe·cameronrwolfe.substack.com·3 months ago·LLMs
v0.14.3
LlamaIndex Releases·github.com·3 months ago·LLMs
Thinking, Searching, and Acting
Interconnects (Nathan Lambert)·interconnects.ai·3 months ago·LLMs
Coding as the epicenter of AI progress and the path to general agents
Interconnects (Nathan Lambert)·interconnects.ai·3 months ago·LLMs
Patch release v4.56.2
Transformers Releases·github.com·3 months ago·LLMs
v0.14.2
LlamaIndex Releases·github.com·3 months ago·LLMs
How GPT5 + Codex took over Agentic Coding — ft. Greg Brockman, OpenAI
Latent Space·latent.space·3 months ago·LLMs
v0.14.1
LlamaIndex Releases·github.com·3 months ago·LLMs
Training an LLM-RecSys Hybrid for Steerable Recs with Semantic IDs
Eugene Yan·eugeneyan.com·3 months ago·LLMs
Vault-Gemma (based on v4.56.1)
Transformers Releases·github.com·3 months ago·LLMs
On Working with Wizards
One Useful Thing (Ethan Mollick)·oneusefulthing.org·4 months ago·LLMs
On China's open source AI trajectory
Interconnects (Nathan Lambert)·interconnects.ai·4 months ago·LLMs
Huawei Ascend Production Ramp: Die Banks, TSMC Continued Production, HBM is The Bottleneck
SemiAnalysis·semianalysis.com·4 months ago·LLMs
Online versus Offline RL for LLMs
Cameron Wolfe·cameronrwolfe.substack.com·4 months ago·LLMs
Understanding and Implementing Qwen3 From Scratch
Sebastian Raschka·magazine.sebastianraschka.com·4 months ago·LLMs
A Technical History of Generative Media — with Gorkem and Batuhan from Fal.ai
Latent Space·latent.space·4 months ago·LLMs
Patch release v4.56.1
Transformers Releases·github.com·4 months ago·LLMs
Amazon’s AI Resurgence: AWS & Anthropic’s Multi-Gigawatt Trainium Expansion
SemiAnalysis·semianalysis.com·4 months ago·LLMs
What exactly does word2vec learn?
Berkeley AI Research (BAIR)·bair.berkeley.edu·4 months ago·LLMs
Mass Intelligence
One Useful Thing (Ethan Mollick)·oneusefulthing.org·4 months ago·LLMs
The Illustrated GPT-OSS
Language Models Newsletter·newsletter.languagemodels.co·4 months ago·LLMs
GPT-oss from the Ground Up
Cameron Wolfe·cameronrwolfe.substack.com·4 months ago·LLMs
GPT-5 Set the Stage for Ad Monetization and the SuperApp
SemiAnalysis·semianalysis.com·5 months ago·LLMs
Scaling the Memory Wall: The Rise and Roadmap of HBM
SemiAnalysis·semianalysis.com·5 months ago·LLMs
Can coding agents self-improve?
Latent Space·latent.space·5 months ago·LLMs
From GPT-2 to gpt-oss: Analyzing the Architectural Advances
Sebastian Raschka·magazine.sebastianraschka.com·5 months ago·LLMs
GPT-5's Vision Checkup: a frontier VLM, but not a new SOTA
Latent Space·latent.space·5 months ago·LLMs
GPT-5's Router: how it works and why Frontier Labs are now targeting the Pareto Frontier
Latent Space·latent.space·5 months ago·LLMs
GPT-5 Hands-On: Welcome to the Stone Age
Latent Space·latent.space·5 months ago·LLMs
GPT-5: It Just Does Stuff
One Useful Thing (Ethan Mollick)·oneusefulthing.org·5 months ago·LLMs
The Bitter Lesson versus The Garbage Can
One Useful Thing (Ethan Mollick)·oneusefulthing.org·5 months ago·LLMs
Direct Preference Optimization (DPO)
Cameron Wolfe·cameronrwolfe.substack.com·5 months ago·LLMs
The Big LLM Architecture Comparison
Sebastian Raschka·magazine.sebastianraschka.com·5 months ago·LLMs
The Tiny Teams Playbook
Latent Space·latent.space·5 months ago·LLMs
The Hyperstitions of Moloch
Latent Space·latent.space·6 months ago·LLMs
Against "Brain Damage"
One Useful Thing (Ethan Mollick)·oneusefulthing.org·6 months ago·LLMs
LLM Research Papers: The 2025 List (January to June)
Sebastian Raschka·magazine.sebastianraschka.com·6 months ago·LLMs
Reward Models
Cameron Wolfe·cameronrwolfe.substack.com·6 months ago·LLMs
Using AI Right Now: A Quick Guide
One Useful Thing (Ethan Mollick)·oneusefulthing.org·6 months ago·LLMs
Andrej Karpathy on Software 3.0: Software in the Age of AI (UPDATED with Full Transcript)
Latent Space·latent.space·6 months ago·LLMs
Understanding and Coding the KV Cache in LLMs from Scratch
Sebastian Raschka·magazine.sebastianraschka.com·6 months ago·LLMs
The Shape of Compute — with Chris Lattner for Modular
Latent Space·latent.space·7 months ago·LLMs
AI Engineering Goes Mainstream
Latent Space·latent.space·7 months ago·LLMs
AI Agents from First Principles
Cameron Wolfe·cameronrwolfe.substack.com·7 months ago·LLMs
AI Engineer 2025 - Improving RecSys & Search with LLM techniques
Eugene Yan·eugeneyan.com·7 months ago·LLMs
The recent history of AI in 32 otters
One Useful Thing (Ethan Mollick)·oneusefulthing.org·7 months ago·LLMs
Making AI Work: Leadership, Lab, and Crowd
One Useful Thing (Ethan Mollick)·oneusefulthing.org·7 months ago·LLMs
A Guide for Debugging LLM Training Data
Cameron Wolfe·cameronrwolfe.substack.com·7 months ago·LLMs
Exceptional Leadership: Some Qualities, Behaviors, and Styles
Eugene Yan·eugeneyan.com·7 months ago·LLMs
Coding LLMs from the Ground Up: A Complete Course
Sebastian Raschka·magazine.sebastianraschka.com·8 months ago·LLMs
Personality and Persuasion
One Useful Thing (Ethan Mollick)·oneusefulthing.org·8 months ago·LLMs
Llama 4: The Challenges of Creating a Frontier-Level LLM
Cameron Wolfe·cameronrwolfe.substack.com·8 months ago·LLMs
Vibe coding MenuGen
Andrej Karpathy·karpathy.bearblog.dev·8 months ago·LLMs
On Jagged AGI: o3, Gemini 2.5, and everything after
One Useful Thing (Ethan Mollick)·oneusefulthing.org·8 months ago·LLMs
An LLM-as-Judge Won't Save The Product—Fixing Your Process Will
Eugene Yan·eugeneyan.com·8 months ago·LLMs
The State of Reinforcement Learning for LLM Reasoning
Sebastian Raschka·magazine.sebastianraschka.com·8 months ago·LLMs
Defending against Prompt Injection with Structured Queries (StruQ) and Preference Optimization (SecAlign)
Berkeley AI Research (BAIR)·bair.berkeley.edu·9 months ago·LLMs
Repurposing Protein Folding Models for Generation with Latent Diffusion
Berkeley AI Research (BAIR)·bair.berkeley.edu·9 months ago·LLMs
Power to the people: How LLMs flip the script on technology diffusion
Andrej Karpathy·karpathy.bearblog.dev·9 months ago·LLMs
Vision Large Language Models (vLLMs)
Cameron Wolfe·cameronrwolfe.substack.com·9 months ago·LLMs
No elephants: Breakthroughs in image generation
One Useful Thing (Ethan Mollick)·oneusefulthing.org·9 months ago·LLMs
Frequently Asked Questions about My Writing Process
Eugene Yan·eugeneyan.com·9 months ago·LLMs
First Look at Reasoning From Scratch: Chapter 1
Sebastian Raschka·magazine.sebastianraschka.com·9 months ago·LLMs
The Cybernetic Teammate
One Useful Thing (Ethan Mollick)·oneusefulthing.org·9 months ago·LLMs
The append-and-review note
Andrej Karpathy·karpathy.bearblog.dev·9 months ago·LLMs
NVIDIA GTC 2025 - Building LLM-Powered Applications
Eugene Yan·eugeneyan.com·9 months ago·LLMs
Improving Recommendation Systems & Search in the Age of LLMs
Eugene Yan·eugeneyan.com·10 months ago·LLMs
Speaking things into existence
One Useful Thing (Ethan Mollick)·oneusefulthing.org·10 months ago·LLMs
nanoMoE: Mixture-of-Experts (MoE) LLMs from Scratch in PyTorch
Cameron Wolfe·cameronrwolfe.substack.com·10 months ago·LLMs
The State of LLM Reasoning Model Inference
Sebastian Raschka·magazine.sebastianraschka.com·10 months ago·LLMs
A new generation of AIs: Claude 3.7 and Grok 3
One Useful Thing (Ethan Mollick)·oneusefulthing.org·10 months ago·LLMs
Demystifying Reasoning Models
Cameron Wolfe·cameronrwolfe.substack.com·10 months ago·LLMs
How Transformer LLMs Work [Free Course]
Language Models Newsletter·newsletter.languagemodels.co·11 months ago·LLMs
Understanding Reasoning LLMs
Sebastian Raschka·magazine.sebastianraschka.com·11 months ago·LLMs
The Illustrated DeepSeek-R1
Language Models Newsletter·newsletter.languagemodels.co·11 months ago·LLMs
Mixture-of-Experts (MoE) LLMs
Cameron Wolfe·cameronrwolfe.substack.com·11 months ago·LLMs
Launching Version 14.2 of Wolfram Language & Mathematica: Big Data Meets Computation & AI
Stephen Wolfram·writings.stephenwolfram.com·11 months ago·LLMs
SWE-Bench authors reflect on the state of LLM agents at Neurips 2024
Language Models Newsletter·newsletter.languagemodels.co·12 months ago·LLMs
Scaling Laws for LLMs: From GPT-3 to o3
Cameron Wolfe·cameronrwolfe.substack.com·12 months ago·LLMs
2024 Year in Review
Eugene Yan·eugeneyan.com·about 1 year ago·LLMs
Useful to the Point of Being Revolutionary: Introducing Wolfram Notebook Assistant
Stephen Wolfram·writings.stephenwolfram.com·about 1 year ago·LLMs
LLM Research Papers: The 2024 List
Sebastian Raschka·magazine.sebastianraschka.com·about 1 year ago·LLMs
Finetuning LLM Judges for Evaluation
Cameron Wolfe·cameronrwolfe.substack.com·about 1 year ago·LLMs
Seemingly Paradoxical Rules of Writing
Eugene Yan·eugeneyan.com·about 1 year ago·LLMs
My Minimal MacBook Pro Setup Guide
Eugene Yan·eugeneyan.com·about 1 year ago·LLMs
Virtual Personas for Language Models via an Anthology of Backstories
Berkeley AI Research (BAIR)·bair.berkeley.edu·about 1 year ago·LLMs
Automatic Prompt Optimization
Cameron Wolfe·cameronrwolfe.substack.com·about 1 year ago·LLMs
Understanding Multimodal LLMs
Sebastian Raschka·magazine.sebastianraschka.com·about 1 year ago·LLMs
39 Lessons on Building ML Systems, Scaling, Execution, and More
Eugene Yan·eugeneyan.com·about 1 year ago·LLMs
AlignEval: Building an App to Make Evals Easy, Fun, and Automated
Eugene Yan·eugeneyan.com·about 1 year ago·LLMs
Our book, Hands-On Large Language Models, Is Now Out!
Language Models Newsletter·newsletter.languagemodels.co·about 1 year ago·LLMs
Weights & Biases LLM-Evaluator Hackathon - Hackathon Judge
Eugene Yan·eugeneyan.com·over 1 year ago·LLMs
Building A GPT-Style LLM Classifier From Scratch
Sebastian Raschka·magazine.sebastianraschka.com·over 1 year ago·LLMs
Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination
Berkeley AI Research (BAIR)·bair.berkeley.edu·over 1 year ago·LLMs
Model Merging: A Survey
Cameron Wolfe·cameronrwolfe.substack.com·over 1 year ago·LLMs
Building LLMs from the Ground Up: A 3-hour Coding Workshop
Sebastian Raschka·magazine.sebastianraschka.com·over 1 year ago·LLMs
How to Evaluate Jailbreak Methods: A Case Study with the StrongREJECT Benchmark
Berkeley AI Research (BAIR)·bair.berkeley.edu·over 1 year ago·LLMs
New LLM Pre-training and Post-training Paradigms
Sebastian Raschka·magazine.sebastianraschka.com·over 1 year ago·LLMs
Using LLMs for Evaluation
Cameron Wolfe·cameronrwolfe.substack.com·over 1 year ago·LLMs
Are We Ready for Multi-Image Reasoning? Launching VHs: The Visual Haystacks Benchmark!
Berkeley AI Research (BAIR)·bair.berkeley.edu·over 1 year ago·LLMs
LLM Tokenizers, Semantic Search Course, And book update #2
Language Models Newsletter·newsletter.languagemodels.co·about 2 years ago·LLMs
We're Writing a Book! "Hands-On Large Language Models"
Language Models Newsletter·newsletter.languagemodels.co·over 2 years ago·LLMs
LLM University, Generative AI, AI Product Moats
Language Models Newsletter·newsletter.languagemodels.co·over 2 years ago·LLMs
What a Time for Language Models
Language Models Newsletter·newsletter.languagemodels.co·over 2 years ago·LLMs
Coming soon
Language Models Newsletter·newsletter.languagemodels.co·almost 3 years ago·LLMs
Which GPU(s) to Get for Deep Learning: My Experience and Advice for Using GPUs in Deep Learning
Tim Dettmers·timdettmers.com·almost 3 years ago·LLMs
LLM.int8() and Emergent Features
Tim Dettmers·timdettmers.com·over 3 years ago·LLMs
How to Choose Your Grad School
Tim Dettmers·timdettmers.com·almost 4 years ago·LLMs
On Creativity in Academia
Tim Dettmers·timdettmers.com·over 6 years ago·LLMs
A Full Hardware Guide to Deep Learning
Tim Dettmers·timdettmers.com·about 7 years ago·LLMs
Machine Learning PhD Applications — Everything You Need to Know
Tim Dettmers·timdettmers.com·about 7 years ago·LLMs
TPUs vs GPUs for Transformers (BERT)
Tim Dettmers·timdettmers.com·about 7 years ago·LLMs
Deep Learning Hardware Limbo
Tim Dettmers·timdettmers.com·about 8 years ago·LLMs
Understanding LSTM Networks
Chris Olah·colah.github.io·about 5 hours ago·LLMs
Neural Networks, Types, and Functional Programming
Chris Olah·colah.github.io·about 5 hours ago·LLMs
A new way to extract detailed transcripts from Claude Code
Simon Willison·simonwillison.net·about 6 hours ago·LLMs
LWiAI Podcast #229 - Gemini 3 Flash, ChatGPT Apps, Nemotron 3
Last Week in AI·lastweekin.ai·about 8 hours ago·LLMs
Last Week in AI #330 - Groq->Nvidia , ChatGPT Apps, US AI Genesis Mission
Last Week in AI·lastweekin.ai·about 21 hours ago·LLMs
uv-init-demos
Simon Willison·simonwillison.net·1 day ago·LLMs
Quoting Salvatore Sanfilippo
Simon Willison·simonwillison.net·2 days ago·LLMs
MicroQuickJS
Simon Willison·simonwillison.net·2 days ago·LLMs
AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems
Hugging Face Blog·huggingface.co·3 days ago·LLMs
Cooking with Claude
Simon Willison·simonwillison.net·3 days ago·LLMs
Using Claude in Chrome to navigate out the Cloudflare dashboard
Simon Willison·simonwillison.net·4 days ago·LLMs
Import AI 438: Silent sirens, flashing for us all
Import AI·importai.substack.com·4 days ago·LLMs
Quoting Shriram Krishnamurthi
Simon Willison·simonwillison.net·5 days ago·LLMs
Quoting Andrej Karpathy
Simon Willison·simonwillison.net·6 days ago·LLMs
Sam Rose explains how LLMs work with a visual essay
Simon Willison·simonwillison.net·6 days ago·LLMs
Introducing GPT-5.2-Codex
Simon Willison·simonwillison.net·7 days ago·LLMs
Agent Skills
Simon Willison·simonwillison.net·7 days ago·LLMs
swift-justhtml
Simon Willison·simonwillison.net·7 days ago·LLMs
Your job is to deliver code you have proven to work
Simon Willison·simonwillison.net·8 days ago·LLMs
Inside PostHog: How SSRF, a ClickHouse SQL Escaping 0day, and Default PostgreSQL Credentials Formed an RCE Chain
Simon Willison·simonwillison.net·8 days ago·LLMs
Tokenization in Transformers v5: Simpler, Clearer, and More Modular
Hugging Face Blog·huggingface.co·8 days ago·LLMs
AoAH Day 15: Porting a complete HTML5 parser and browser test suite
Simon Willison·simonwillison.net·8 days ago·LLMs
Gemini 3 Flash
Simon Willison·simonwillison.net·8 days ago·LLMs
LWiAI Podcast #228 - GPT 5.2, Scaling Agents, Weird Generalization
Last Week in AI·lastweekin.ai·8 days ago·LLMs
The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator
Hugging Face Blog·huggingface.co·9 days ago·LLMs
firefox parser/html/java/README.txt
Simon Willison·simonwillison.net·9 days ago·LLMs
The new ChatGPT Images is here
Simon Willison·simonwillison.net·9 days ago·LLMs
s3-credentials 0.17
Simon Willison·simonwillison.net·9 days ago·LLMs
Last Week in AI #329 - GPT 5.2, GenAI.mil, Disney in Sora
Last Week in AI·lastweekin.ai·10 days ago·LLMs
New in llama.cpp: Model Management
Hugging Face Blog·huggingface.co·15 days ago·LLMs
Codex is Open Sourcing AI models
Hugging Face Blog·huggingface.co·15 days ago·LLMs
LWiAI Podcast #227 - Jeremie is back! DeepSeek 3.2, TPUs, Nested Learning
Last Week in AI·lastweekin.ai·17 days ago·LLMs
Import AI 437: Co-improving AI; RL dreams; AI labels might be annoying
Import AI·importai.substack.com·18 days ago·LLMs
Last Week in AI #328 - DeepSeek 3.2, Mistral 3, Trainium3, Runway Gen-4.5
Last Week in AI·lastweekin.ai·18 days ago·LLMs
Introducing swift-huggingface: The Complete Swift Client for Hugging Face
Hugging Face Blog·huggingface.co·21 days ago·LLMs
We Got Claude to Fine-Tune an Open Source LLM
Hugging Face Blog·huggingface.co·22 days ago·LLMs
Transformers v5: Simple model definitions powering the AI ecosystem
Hugging Face Blog·huggingface.co·25 days ago·LLMs
LWiAI Podcast #226 - Gemini 3, Claude Opus 4.5, Nano Banana Pro, LeJEPA
Last Week in AI·lastweekin.ai·26 days ago·LLMs
Taming LLMs with NeMo Guardrails
MLOps Community·mlops.community·30 days ago·LLMs
Last Week in AI #327 - Gemini 3, Opus 4.5, Nano Banana Pro, GPT-5.1-Codex-Max
Last Week in AI·lastweekin.ai·about 1 month ago·LLMs
Continuous batching from first principles
Hugging Face Blog·huggingface.co·about 1 month ago·LLMs
Diffusers welcomes FLUX-2
Hugging Face Blog·huggingface.co·about 1 month ago·LLMs
LWiAI Podcast #225 - GPT 5.1, Kimi K2 Thinking, Remote Labor Index
Last Week in AI·lastweekin.ai·about 1 month ago·LLMs
Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks
Hugging Face Blog·huggingface.co·about 1 month ago·LLMs
20x Faster TRL Fine-tuning with RapidFire AI
Hugging Face Blog·huggingface.co·about 1 month ago·LLMs
Introducing AnyLanguageModel: One API for Local and Remote LLMs on Apple Platforms
Hugging Face Blog·huggingface.co·about 1 month ago·LLMs
Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models
Hugging Face Blog·huggingface.co·about 1 month ago·LLMs
Easily Build and Share ROCm Kernels with Hugging Face
Hugging Face Blog·huggingface.co·about 1 month ago·LLMs
Authentic Imperfection
Alex Irpan·alexirpan.com·about 1 month ago·LLMs
Join the AMD Open Robotics Hackathon
Hugging Face Blog·huggingface.co·about 1 month ago·LLMs
Import AI 434: Pragmatic AI personhood; SPACE COMPUTERS; and global government or human extinction;
Import AI·importai.substack.com·about 2 months ago·LLMs
Last Week in AI #326 - Qualcomm AI Chips, MiniMax M2, Kimi K2 Thinking
Last Week in AI·lastweekin.ai·about 2 months ago·LLMs
Last Week in AI #325 - OpenAI is for-profit, ChatGPT Atlas, Copilot Mico
Last Week in AI·lastweekin.ai·about 2 months ago·LLMs
Pretraining: Breaking Down the Modern LLM Training Pipeline
MLOps Community·mlops.community·about 2 months ago·LLMs
Import AI 433: AI auditors; robot dreams; and software for helping an AI run a lab
Import AI·importai.substack.com·about 2 months ago·LLMs
LWiAI Podcast #223 - Haiku 4.5, OpenAI DevDay, SB 243
Last Week in AI·lastweekin.ai·2 months ago·LLMs
Import AI 432: AI malware; frankencomputing; and Poolside's big cluster
Import AI·importai.substack.com·2 months ago·LLMs
Last Week in AI #324: OpenAI Deals and DevDay, Haiku 4.5, Veo 3.1
Last Week in AI·lastweekin.ai·2 months ago·LLMs
Import AI 431: Technological Optimism and Appropriate Fear
Import AI·importai.substack.com·2 months ago·LLMs
LWiAI Podcast #222 - Sora 2, Sonnet 4.5, Vibes, Thinking Machines
Last Week in AI·lastweekin.ai·3 months ago·LLMs
Last Week in AI #323 - Sonnet 4.5, Sora 2, Vibes, SB 53
Last Week in AI·lastweekin.ai·3 months ago·LLMs
LWiAI Podcast #221 - OpenAI Codex, Gemini in Chrome, K2-Think, SB 53
Last Week in AI·lastweekin.ai·3 months ago·LLMs
Last Week in AI #322 - Robotaxi progress, OpenAI Business, Gemini in Chrome
Last Week in AI·lastweekin.ai·3 months ago·LLMs
Sometimes you want to skip that CGI Status header
Rachel by the Bay·rachelbythebay.com·3 months ago·LLMs
A guide to understanding AI as normal technology
AI Snake Oil·normaltech.ai·4 months ago·LLMs
LWiAI Podcast #220 - Gemini 2.5 Flash Image, Claude for Chrome
Last Week in AI·lastweekin.ai·4 months ago·LLMs
Making the most of a dumb fax switcher box in the old days
Rachel by the Bay·rachelbythebay.com·4 months ago·LLMs
Import AI 426: Playable world models; circuit design AI; and ivory smuggling analysis
Import AI·importai.substack.com·4 months ago·LLMs
Ten Years Later
Alex Irpan·alexirpan.com·4 months ago·LLMs
Import AI 424: Facebook improves ads with RL; LLM and human brain similarities; and mental health and chatbots
Import AI·importai.substack.com·5 months ago·LLMs
Import AI 423: Multilingual CLIP; anti-drone tracking; and Huawei kernel design
Import AI·importai.substack.com·5 months ago·LLMs
Import AI 422: LLM bias; China cares about the same safety risks as us; AI persuasion
Import AI·importai.substack.com·5 months ago·LLMs
Brony Musicians Seize The Means of Production: My Eyewitness Account to BABSCon 2025
Alex Irpan·alexirpan.com·5 months ago·LLMs
Import AI 421: Kimi 2 - a great Chinese open weight model; giving AI systems rights and what it means; and how to pause AI progress
Import AI·importai.substack.com·5 months ago·LLMs
Could AI slow science?
AI Snake Oil·normaltech.ai·5 months ago·LLMs
Life lessons from reinforcement learning
Jason Wei·jasonwei.net·5 months ago·LLMs
Asymmetry of verification and verifier’s rule
Jason Wei·jasonwei.net·5 months ago·LLMs
Import AI 420: Prisoner Dilemma AI; FrontierMath Tier 4; and how to regulate AI companies
Import AI·importai.substack.com·5 months ago·LLMs
Documenting what you're willing to support (and not)
Rachel by the Bay·rachelbythebay.com·6 months ago·LLMs
Import AI 419: Amazon's millionth robot; CrowdTrack; and infinite games
Import AI·importai.substack.com·6 months ago·LLMs
Calculating rollovers
Rachel by the Bay·rachelbythebay.com·6 months ago·LLMs
AGI is not a milestone
AI Snake Oil·normaltech.ai·8 months ago·LLMs
[AINews] Grok 3 & 3-mini now API Available
AI News (Buttondown)·buttondown.com·8 months ago·LLMs
[AINews] Gemini 2.5 Flash completes the total domination of the Pareto Frontier
AI News (Buttondown)·buttondown.com·8 months ago·LLMs
[AINews] OpenAI o3, o4-mini, and Codex CLI
AI News (Buttondown)·buttondown.com·8 months ago·LLMs
[AINews] SOTA Video Gen: Veo 2 and Kling 2 are GA for developers
AI News (Buttondown)·buttondown.com·8 months ago·LLMs
[AINews] GPT 4.1: The New OpenAI Workhorse
AI News (Buttondown)·buttondown.com·9 months ago·LLMs
[AINews] not much happened today
AI News (Buttondown)·buttondown.com·9 months ago·LLMs
[AINews] not much happened today
AI News (Buttondown)·buttondown.com·9 months ago·LLMs
[AINews] Google's Agent2Agent Protocol (A2A)
AI News (Buttondown)·buttondown.com·9 months ago·LLMs
Problems with the heap
Rachel by the Bay·rachelbythebay.com·9 months ago·LLMs
Moving To Substack
Jay Alammar·jalammar.github.io·9 months ago·LLMs
You might want to stop running atop
Rachel by the Bay·rachelbythebay.com·9 months ago·LLMs
A Visual Guide to LLM Agents
Maarten Grootendorst·newsletter.maartengrootendorst.com·9 months ago·LLMs
More thoughts on the 1670 modem's weird noises
Rachel by the Bay·rachelbythebay.com·10 months ago·LLMs
Two modems, a length of line cord, and no battery
Rachel by the Bay·rachelbythebay.com·10 months ago·LLMs
A Visual Guide to Reasoning LLMs
Maarten Grootendorst·newsletter.maartengrootendorst.com·11 months ago·LLMs
MIT Mystery Hunt 2025
Alex Irpan·alexirpan.com·11 months ago·LLMs
Common pitfalls when building generative AI applications
Chip Huyen·huyenchip.com·11 months ago·LLMs
Using AI to Get the Neopets Destruct-o-Match Avatar
Alex Irpan·alexirpan.com·12 months ago·LLMs
Agents
Chip Huyen·huyenchip.com·12 months ago·LLMs
Is AI progress slowing down?
AI Snake Oil·normaltech.ai·about 1 year ago·LLMs
We Looked at 78 Election Deepfakes. Political Misinformation is not an AI Problem.
AI Snake Oil·normaltech.ai·about 1 year ago·LLMs
Late Takes on OpenAI o1
Alex Irpan·alexirpan.com·about 1 year ago·LLMs
Reward Hacking in Reinforcement Learning
Lilian Weng·lilianweng.github.io·about 1 year ago·LLMs
Does the UK’s liver transplant matching algorithm systematically exclude younger patients?
AI Snake Oil·normaltech.ai·about 1 year ago·LLMs
A Visual Guide to Mixture of Experts (MoE)
Maarten Grootendorst·newsletter.maartengrootendorst.com·about 1 year ago·LLMs
FAQ about the book and our writing process
AI Snake Oil·normaltech.ai·about 1 year ago·LLMs
Can AI automate computational reproducibility?
AI Snake Oil·normaltech.ai·over 1 year ago·LLMs
Start reading the AI Snake Oil book online
AI Snake Oil·normaltech.ai·over 1 year ago·LLMs
What's Missing From LLM Chatbots: A Sense of Purpose
The Gradient·thegradient.pub·over 1 year ago·LLMs
AI companies are pivoting from creating gods to building products. Good.
AI Snake Oil·normaltech.ai·over 1 year ago·LLMs
Nine Years Later
Alex Irpan·alexirpan.com·over 1 year ago·LLMs
AI existential risk probabilities are too unreliable to inform policy
AI Snake Oil·normaltech.ai·over 1 year ago·LLMs
Building A Generative AI Platform
Chip Huyen·huyenchip.com·over 1 year ago·LLMs
A Visual Guide to Quantization
Maarten Grootendorst·newsletter.maartengrootendorst.com·over 1 year ago·LLMs
The Tragedies of Reality Are Coming for You
Alex Irpan·alexirpan.com·over 1 year ago·LLMs
Extrinsic Hallucinations in LLMs
Lilian Weng·lilianweng.github.io·over 1 year ago·LLMs
AI scaling myths
AI Snake Oil·normaltech.ai·over 1 year ago·LLMs
Successful language model evals
Jason Wei·jasonwei.net·over 1 year ago·LLMs
Financial Market Applications of LLMs
The Gradient·thegradient.pub·over 1 year ago·LLMs
AI Snake Oil is now available to preorder
AI Snake Oil·normaltech.ai·over 1 year ago·LLMs
Tech policy is only frustrating 90% of the time
AI Snake Oil·normaltech.ai·over 1 year ago·LLMs
Mamba Explained
The Gradient·thegradient.pub·over 1 year ago·LLMs
What I learned from looking at 900 most popular open source AI tools
Chip Huyen·huyenchip.com·almost 2 years ago·LLMs
Car-GPT: Could LLMs finally make self-driving cars happen?
The Gradient·thegradient.pub·almost 2 years ago·LLMs
Predictive Human Preference: From Model Ranking to Model Routing
Chip Huyen·huyenchip.com·almost 2 years ago·LLMs
A Visual Guide to Mamba and State Space Models
Maarten Grootendorst·newsletter.maartengrootendorst.com·almost 2 years ago·LLMs
Thinking about High-Quality Human Data
Lilian Weng·lilianweng.github.io·almost 2 years ago·LLMs
Generation configurations: temperature, top-k, top-p, and test time compute
Chip Huyen·huyenchip.com·almost 2 years ago·LLMs
Deep learning for single-cell sequencing: a microscope to see the diversity of cells
The Gradient·thegradient.pub·almost 2 years ago·LLMs
Book Update #2 - Hands-On Large Language Models
Maarten Grootendorst·newsletter.maartengrootendorst.com·about 2 years ago·LLMs
Salmon in the Loop
The Gradient·thegradient.pub·about 2 years ago·LLMs
BERTopic: What Is So Special About v0.16?
Maarten Grootendorst·newsletter.maartengrootendorst.com·about 2 years ago·LLMs
Six intuitions about large language models
Jason Wei·jasonwei.net·about 2 years ago·LLMs
Which Quantization Method is Right for You? (GPTQ vs. GGUF vs. AWQ)
Maarten Grootendorst·newsletter.maartengrootendorst.com·about 2 years ago·LLMs
Adversarial Attacks on LLMs
Lilian Weng·lilianweng.github.io·about 2 years ago·LLMs
Multimodality and Large Multimodal Models (LMMs)
Chip Huyen·huyenchip.com·about 2 years ago·LLMs
Introducing KeyLLM — Keyword Extraction with LLMs
Maarten Grootendorst·newsletter.maartengrootendorst.com·about 2 years ago·LLMs
An Introduction to the Problems of AI Consciousness
The Gradient·thegradient.pub·about 2 years ago·LLMs
3 Ways To Improve Your Large Language Model
Maarten Grootendorst·newsletter.maartengrootendorst.com·over 2 years ago·LLMs
Topic Modeling with Llama 2
Maarten Grootendorst·newsletter.maartengrootendorst.com·over 2 years ago·LLMs
Open challenges in LLM research
Chip Huyen·huyenchip.com·over 2 years ago·LLMs
Decoding Auto-GPT
Maarten Grootendorst·newsletter.maartengrootendorst.com·over 2 years ago·LLMs
LLM Powered Autonomous Agents
Lilian Weng·lilianweng.github.io·over 2 years ago·LLMs
Welcome!
Maarten Grootendorst·newsletter.maartengrootendorst.com·over 2 years ago·LLMs
Generative AI Strategy
Chip Huyen·huyenchip.com·over 2 years ago·LLMs
Common arguments regarding emergent abilities
Jason Wei·jasonwei.net·over 2 years ago·LLMs
Prompt Engineering
Lilian Weng·lilianweng.github.io·almost 3 years ago·LLMs
The Transformer Family Version 2.0
Lilian Weng·lilianweng.github.io·almost 3 years ago·LLMs
Research I enjoy
Jason Wei·jasonwei.net·almost 3 years ago·LLMs
137 emergent abilities of large language models
Jason Wei·jasonwei.net·about 3 years ago·LLMs
Generalized Visual Language Models
Lilian Weng·lilianweng.github.io·over 3 years ago·LLMs
Learning with not Enough Data Part 3: Data Generation
Lilian Weng·lilianweng.github.io·over 3 years ago·LLMs
Applying massive language models in the real world with Cohere
Jay Alammar·jalammar.github.io·almost 4 years ago·LLMs
The Illustrated Retrieval Transformer
Jay Alammar·jalammar.github.io·almost 4 years ago·LLMs
Reducing Toxicity in Language Models
Lilian Weng·lilianweng.github.io·almost 5 years ago·LLMs
Finding the Words to Say: Hidden State Visualizations for Language Models
Jay Alammar·jalammar.github.io·almost 5 years ago·LLMs
Controllable Neural Text Generation
Lilian Weng·lilianweng.github.io·almost 5 years ago·LLMs
Interfaces for Explaining Transformer Language Models
Jay Alammar·jalammar.github.io·about 5 years ago·LLMs
How GPT3 Works - Visualizations and Animations
Jay Alammar·jalammar.github.io·over 5 years ago·LLMs
A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents
arXiv CS.AI·arxiv.org·1 day ago·LLMs
Safety Alignment of LMs via Non-cooperative Games
arXiv CS.AI·arxiv.org·1 day ago·LLMs
Uncovering Competency Gaps in Large Language Models and Their Benchmarks
arXiv CS.CL·arxiv.org·1 day ago·LLMs
TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior
arXiv CS.CL·arxiv.org·1 day ago·LLMs
Large Language Models Approach Expert Pedagogical Quality in Math Tutoring but Differ in Instructional and Linguistic Profiles
arXiv CS.CL·arxiv.org·1 day ago·LLMs
Investigating Model Editing for Unlearning in Large Language Models
arXiv CS.CL·arxiv.org·1 day ago·LLMs
Measuring Mechanistic Independence: Can Bias Be Removed Without Erasing Demographics?
arXiv CS.CL·arxiv.org·1 day ago·LLMs
Semantic Deception: When Reasoning Models Can't Compute an Addition
arXiv CS.CL·arxiv.org·1 day ago·LLMs
EssayCBM: Rubric-Aligned Concept Bottleneck Models for Transparent Essay Grading
arXiv CS.CL·arxiv.org·1 day ago·LLMs
MediEval: A Unified Medical Benchmark for Patient-Contextual and Knowledge-Grounded Reasoning in LLMs
arXiv CS.CL·arxiv.org·1 day ago·LLMs
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
arXiv CS.CL·arxiv.org·1 day ago·LLMs
How important is Recall for Measuring Retrieval Quality?
arXiv CS.CL·arxiv.org·1 day ago·LLMs
Architectural Trade-offs in Small Language Models Under Compute Constraints
arXiv CS.CL·arxiv.org·1 day ago·LLMs
Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation
arXiv CS.CL·arxiv.org·1 day ago·LLMs
Neural Probe-Based Hallucination Detection for Large Language Models
arXiv CS.CL·arxiv.org·1 day ago·LLMs
MultiMind at SemEval-2025 Task 7: Crosslingual Fact-Checked Claim Retrieval via Multi-Source Alignment
arXiv CS.CL·arxiv.org·1 day ago·LLMs
Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models
arXiv CS.CL·arxiv.org·1 day ago·LLMs
Automatic Replication of LLM Mistakes in Medical Conversations
arXiv CS.CL·arxiv.org·1 day ago·LLMs
Learning Evolving Latent Strategies for Multi-Agent Language Systems without Model Fine-Tuning
arXiv CS.LG·arxiv.org·1 day ago·LLMs
Enhancing Lung Cancer Treatment Outcome Prediction through Semantic Feature Engineering Using Large Language Models
arXiv CS.LG·arxiv.org·1 day ago·LLMs
Real Time Detection and Quantitative Analysis of Spurious Forgetting in Continual Learning
arXiv CS.LG·arxiv.org·1 day ago·LLMs
Data-Free Pruning of Self-Attention Layers in LLMs
arXiv CS.LG·arxiv.org·1 day ago·LLMs
Managing the Stochastic: Foundations of Learning in Neuro-Symbolic Systems for Software Engineering
arXiv CS.LG·arxiv.org·1 day ago·LLMs
HyDRA: Hierarchical and Dynamic Rank Adaptation for Mobile Vision Language Model
arXiv CS.LG·arxiv.org·1 day ago·LLMs
Revisiting the Learning Objectives of Vision-Language Reward Models
arXiv CS.LG·arxiv.org·1 day ago·LLMs
PHOTON: Hierarchical Autoregressive Modeling for Lightspeed and Memory-Efficient Language Generation
arXiv CS.LG·arxiv.org·1 day ago·LLMs
FEM-Bench: A Structured Scientific Reasoning Benchmark for Evaluating Code-Generating LLMs
arXiv CS.LG·arxiv.org·1 day ago·LLMs
BitRL-Light: 1-bit LLM Agents with Deep Reinforcement Learning for Energy-Efficient Smart Home Lighting Optimization
arXiv CS.AI·arxiv.org·1 day ago·LLMs
MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation
arXiv CS.AI·arxiv.org·1 day ago·LLMs
MicroProbe: Efficient Reliability Assessment for Foundation Models with Minimal Data
arXiv CS.AI·arxiv.org·1 day ago·LLMs
Erkang-Diagnosis-1.1 Technical Report
arXiv CS.AI·arxiv.org·1 day ago·LLMs
Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning
arXiv CS.AI·arxiv.org·1 day ago·LLMs
AIAuditTrack: A Framework for AI Security system
arXiv CS.AI·arxiv.org·1 day ago·LLMs
Memory Bear AI A Breakthrough from Memory to Cognition Toward Artificial General Intelligence
arXiv CS.AI·arxiv.org·1 day ago·LLMs
AI-Driven Decision-Making System for Hiring Process
arXiv CS.AI·arxiv.org·1 day ago·LLMs
From Fake Focus to Real Precision: Confusion-Driven Adversarial Attention Learning in Transformers
arXiv CS.AI·arxiv.org·1 day ago·LLMs
Quantifying Laziness, Decoding Suboptimality, and Context Degradation in Large Language Models
arXiv CS.AI·arxiv.org·1 day ago·LLMs
Eidoku: A Neuro-Symbolic Verification Gate for LLM Reasoning via Structural Constraint Satisfaction
arXiv CS.AI·arxiv.org·1 day ago·LLMs
AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent
arXiv CS.AI·arxiv.org·1 day ago·LLMs