curius graph

all pages

showing 133351-133400 of 160880 pages (sorted by popularity)
[2212.03827] Discovering Latent Knowledge in Language Models Without Supervision
Discover 1X | A Gearless Future
Choosing the right GPU for deep learning on AWS | by Shashank Prasanna | Towards Data Science
Why Nvidia’s AI Supremacy is Only Temporary « Pete Warden's blog
[2202.11233] Retrieval Augmented Classification for Long-Tail Visual Recognition
HQQ quantization
Quantization
Quantization for Neural Networks - Lei Mao's Log Book
[2212.08045] CLIPPO: Image-and-Language Understanding from Pixels Only
[2403.03163] Design2Code: How Far Are We From Automating Front-End Engineering?
How I Learned to Concentrate | The New Yorker
How to Build a GPT-3 for Science | Future
Command-R: Retrieval Augmented Generation at Production Scale
How to ML Paper - A brief Guide - Google Docs
Timo Schick | Toolformer: Language Models Can Teach Themselves to Use Tools - YouTube
Steering Llama-2 with contrastive activation additions — LessWrong
[2402.02622] DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging
[2402.15449] Repetition Improves Language Model Embeddings
2403.17919.pdf
2308.14711.pdf
arxiv.org/pdf/2301.03598.pdf
TrueSkill Through Time: Revisiting the History of Chess - Microsoft Research
Rachel Thomas, PhD - Making Peace with Personal Branding
Erik Demaine
[2305.19452] Bigger, Better, Faster: Human-level Atari with human-level efficiency
2310.15421.pdf
More Agents Is All You Need
2311.04930.pdf
Min P style sampling - an alternative to Top P/TopK · Issue #27670 · huggingface/transformers
Can tech save us from worst of climate change effects? Doesn’t look good — Harvard Gazette
Answer.AI - SB-1047 will stifle open-source AI and decrease safety
What is memory safety and why does it matter? - Prossimo
Critics Says Harvard’s Endowment Is Underperforming and Overly Secretive. Is It? | News | The Harvard Crimson
Let's reproduce GPT-2 (124M) - YouTube
dlc-handout-13-2-attention-mechanisms.pdf
uncertain_ground_truth/monte_carlo.py at main · google-deepmind/uncertain_ground_truth
Contributions QX
[2410.06508] Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
[2501.06252] $\text{Transformer}^2$: Self-adaptive LLMs
Introduction to Poker Theory - YouTube
[2104.03113] Scaling Scaling Laws with Board Games
Model Merging, Mixtures of Experts, and Towards Smaller LLMs
Exclusive | The Secrets and Misdirection Behind Sam Altman’s Firing From OpenAI - WSJ
Advanced Web Scraping With Python: Extract Data From Any Site
Simple Alpha Zero
Rich's Top 10 Readings - Google Docs
Random Network Distillation: a new take on Curiosity-Driven Learning | by Thomas Simonini | data from the trenches | Medium
The Lean FRO Year 2 Roadmap — Lean FRO
synthetic-data-kit/use-cases/awesome-synthetic-data-papers at main · meta-llama/synthetic-data-kit
werner-duvaud/muzero-general: MuZero