Next >
1
A vision researcher's guide to some RL stuff: PPO and GRPO (yugeten.github.io)
5 hours ago | fzliu | github.io | newest
2
Benchmark for Evaluating Text Embeddings (huggingface.co)
a day ago | fzliu | huggingface.co | newest
90
Biomolecular shifts occur in our 40s and 60s (2024) (stanford.edu)
3 days ago | fzliu | stanford.edu | best
1
Text Embedding Benchmark (huggingface.co)
5 days ago | fzliu | huggingface.co | newest
2
Watermarking Autoregressive Image Generation (arxiv.org)
6 days ago | fzliu | arxiv.org | newest
2
Agentic Search for Dummies (benanderson.work)
a week ago | fzliu | benanderson.work | newest
1
Benchmark for Evaluating Text Embeddings (huggingface.co)
a week ago | fzliu | huggingface.co | newest
1
Does RL Incentivize Reasoning Capacity in LLMs Beyond the Base Model? (lesswrong.com)
a week ago | fzliu | lesswrong.com | newest
2
Emergence of Diffusion Models from Associative Memory (arxiv.org)
a week ago | fzliu | arxiv.org | frontpage
2
Benchmark for Evaluating Text Embeddings (huggingface.co)
a week ago | fzliu | huggingface.co | newest
1
MAIR: A Benchmark for Evaluating Instructed Retrieval (github.com/sunnweiwei)
a week ago | fzliu | github.com | newest
1
Wanting to Be Understood Explains the Meta-Problem of Consciousness (arxiv.org)
a week ago | fzliu | arxiv.org | newest
3
The Gumbel-Softmax Distribution (sassafras13.github.io)
a week ago | fzliu | github.io | frontpage
5
The Value of Chess Pieces (lichess.org)
a week ago | fzliu | lichess.org | newest
1
AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions (arxiv.org)
a week ago | fzliu | arxiv.org | newest
1
CURE: A Dataset for Clinical Understanding and Retrieval Evaluation (arxiv.org)
a week ago | fzliu | arxiv.org | newest
1
Benchmark for Evaluating Text Embeddings (huggingface.co)
a week ago | fzliu | huggingface.co | newest
19
Extracting memorized pieces of books from open-weight language models (arxiv.org)
a week ago | fzliu | arxiv.org | best
3
The FCC Builds a Firewall Around US-Bound Electronics (eetimes.com)
2 weeks ago | fzliu | eetimes.com | newest
4
Towards Understanding Sycophancy in Language Models (arxiv.org)
2 weeks ago | fzliu | arxiv.org | frontpage
1
Extended Thinking Tips (anthropic.com)
2 weeks ago | fzliu | anthropic.com | newest
1
Embedding Benchmark for Retrieval (huggingface.co)
2 weeks ago | fzliu | huggingface.co | newest
1
Torch Backends (pytorch.org)
2 weeks ago | fzliu | pytorch.org | newest
2
Hideo Kojima's Boss Fight with Time (gq.com)
2 weeks ago | fzliu | gq.com | newest
2
AI Risk Repository (airisk.mit.edu)
2 weeks ago | fzliu | mit.edu | newest
1
RAG for Contract Analysis (robinai.com)
2 weeks ago | fzliu | robinai.com | newest
1
Embedding Benchmark for Retrieval (huggingface.co)
2 weeks ago | fzliu | huggingface.co | newest
1
tau²-bench (sierra.ai)
2 weeks ago | fzliu | sierra.ai | newest
1
Video Search with Multimodal AI (kx.com)
2 weeks ago | fzliu | kx.com | newest
1
Untether AI Shuts Down, Engineering Team Joins AMD (eetimes.com)
3 weeks ago | fzliu | eetimes.com | newest
1
Norway Chess 2025 in 7 Graphs (lichess.org)
3 weeks ago | fzliu | lichess.org | newest
1
Retrieval Embedding Benchmark (huggingface.co)
3 weeks ago | fzliu | huggingface.co | newest
1
General-Purpose vs. Domain-Specific Embedding Models (timescale.com)
3 weeks ago | fzliu | timescale.com | newest
2
Quantifying Volatility of Chess Games (lichess.org)
3 weeks ago | fzliu | lichess.org | newest
2
Maillard Reaction (wikipedia.org)
3 weeks ago | fzliu | wikipedia.org | newest
1
Retrieval Embedding Benchmark (huggingface.co)
3 weeks ago | fzliu | huggingface.co | newest
1
Evaluating the Best Search Engine (exa.ai)
3 weeks ago | fzliu | exa.ai | newest
1
Optimization by unifying stochastic gradient and quasi-Newton methods (2013) (arxiv.org)
a month ago | fzliu | arxiv.org | newest
4
voyage-3.5 and voyage-3.5-lite: improved quality for a new retrieval frontier (voyageai.com)
a month ago | fzliu | voyageai.com | frontpage
3
Perplexity builds AI Search at scale on Vespa.ai (vespa.ai)
2 months ago | fzliu | vespa.ai | newest
6
X-Ray Defence (lichess.org)
2 months ago | fzliu | lichess.org | frontpage
1
D&D Retreat Costs 10x a Chess Tournament (lichess.org)
2 months ago | fzliu | lichess.org | newest
2
Wanting to Be Understood (arxiv.org)
2 months ago | fzliu | arxiv.org | newest
8
When it comes to tariffs, China is a special case (twitter.com/stevesi)
2 months ago | fzliu | twitter.com | frontpage
1
voyage-3-Large (voyageai.com)
2 months ago | fzliu | voyageai.com | newest
43
Multi-Token Attention (arxiv.org)
2 months ago | fzliu | arxiv.org | best
1
Attack or Be Attacked (lichess.org)
3 months ago | fzliu | lichess.org | newest
1
Inato Patient Pre-Screening (inato.com)
3 months ago | fzliu | inato.com | newest
10
Fuckarounditis (2011) (leangains.com)
3 months ago | fzliu | leangains.com | frontpage
1
Drowning in Documents: Consequences of Scaling Reranker Inference (arxiv.org)
3 months ago | fzliu | arxiv.org | newest
2
voyage-3-large (voyageai.com)
3 months ago | fzliu | voyageai.com | frontpage
2
Transformers Without Normalization (arxiv.org)
3 months ago | fzliu | arxiv.org | newest
2
Is muscle and protein loss relevant in long-term fasting in healthy men? (buchinger-wilhelmi.com)
3 months ago | fzliu | buchinger-wilhelmi.com | newest
2
Acetaminophen improves cognitive and repeated high intensity maximal performance (springer.com)
3 months ago | fzliu | springer.com | newest
1
The Model Is the Product (vintagedata.org)
3 months ago | fzliu | vintagedata.org | newest
1
Life as an Immigrant (learnerncoffee.wordpress.com)
3 months ago | fzliu | wordpress.com | newest
1
TabDiff: A Mixed-Type Diffusion Model for Tabular Data Generation (github.com/minkaixu)
4 months ago | fzliu | github.com | newest
1
So You Want to Make Marginal Progress (lesswrong.com)
4 months ago | fzliu | lesswrong.com | newest
4
Voyage AI Joins MongoDB (voyageai.com)
4 months ago | fzliu | voyageai.com | newest
1
ZeroBench (zerobench.github.io)
4 months ago | fzliu | github.io | newest
1
General-Purpose vs. Domain-Specific Embedding Models (timescale.com)
4 months ago | fzliu | timescale.com | newest
1
SPIRE: Semantic Prompt-Driven Image Restoration (2024) (arxiv.org)
4 months ago | fzliu | arxiv.org | newest
1
Scaling Test-Time Compute Can Be More Effective Than Scaling Parameters (2024) (arxiv.org)
4 months ago | fzliu | arxiv.org | newest
1
Overfitting to Theories of Overfitting (argmin.net)
4 months ago | fzliu | argmin.net | newest
1
Does Fasting cause (or cure) Hunger? (freedium.cfd)
4 months ago | fzliu | freedium.cfd | newest
1
DeepSearcher (github.com/zilliztech)
4 months ago | fzliu | github.com | newest
2
voyage-3-large: embedding model with Matryoshka and quantization awareness (voyageai.com)
4 months ago | fzliu | voyageai.com | newest
1
King Marches (lichess.org)
4 months ago | fzliu | lichess.org | newest
32
LM2: Large Memory Models (arxiv.org)
4 months ago | fzliu | arxiv.org | frontpage
1
Reviving Old Hardware with Batocera Linux and NVMe Workarounds (tsak.dev)
4 months ago | fzliu | tsak.dev | newest
2
Distillation Scaling Laws (arxiv.org)
4 months ago | fzliu | arxiv.org | newest
2
Elasticsearch vs. Vespa Performance Comparison (vespa.ai)
4 months ago | fzliu | vespa.ai | newest
38
Basis of the Kalman Filter [pdf] (github.com/tpn)
4 months ago | fzliu | github.com | best
2
voyage-3-large (voyageai.com)
4 months ago | fzliu | voyageai.com | newest
3
My New Reading Workflow (seankilleen.com)
4 months ago | fzliu | seankilleen.com | newest
2
Matryoshka Quantization (arxiv.org)
4 months ago | fzliu | arxiv.org | newest
2
Learn Haskell by building a blog generator (learn-haskell.blog)
4 months ago | fzliu | learn-haskell.blog | newest
2
Open Source Deep Research (milvus.io)
4 months ago | fzliu | milvus.io | newest
1
voyage-3-large (voyageai.com)
4 months ago | fzliu | voyageai.com | newest
1
DocVLM: Make Your VLM an Efficient Reader (arxiv.org)
4 months ago | fzliu | arxiv.org | newest
3
10x Professionals (deeplearning.ai)
4 months ago | fzliu | deeplearning.ai | newest
1
voyage-3-large (voyageai.com)
4 months ago | fzliu | voyageai.com | newest
1
From ML Teams to API Calls: The Illusion of Simplicity (twitter.com/jobergum)
4 months ago | fzliu | twitter.com | newest
1
Harmonic Loss Trains Interpretable AI Models (arxiv.org)
4 months ago | fzliu | arxiv.org | newest
1
Transformer Circuits Thread (transformer-circuits.pub)
4 months ago | fzliu | transformer-circuits.pub | newest
2
Elasticsearch vs. Vespa Performance Comparison (vespa.ai)
4 months ago | fzliu | vespa.ai | newest
2
voyage-3-large (voyageai.com)
4 months ago | fzliu | voyageai.com | newest
1
Tik-Tok Wins the Social Media Recommendation System War (2020) (leehanchung.github.io)
4 months ago | fzliu | github.io | newest
1
Why do humans have earlobes? (popsci.com)
4 months ago | fzliu | popsci.com | newest
4
How do we evaluate vector-based code retrieval? (voyageai.com)
4 months ago | fzliu | voyageai.com | frontpage
1
voyage-3-large: general-purpose embedding model (voyageai.com)
4 months ago | fzliu | voyageai.com | newest
14
Shades of Blunders (lichess.org)
4 months ago | fzliu | lichess.org | frontpage
2
Evaluating Code Embedding Models (voyageai.com)
4 months ago | fzliu | voyageai.com | frontpage
2
voyage-3-large: state-of-the-art general-purpose embedding model (voyageai.com)
5 months ago | fzliu | voyageai.com | newest
1
Guide to Multimodal RAG for Images and Text (medium.com/kx-systems)
5 months ago | fzliu | medium.com | newest
1
Memory Snapshots (modal.com)
5 months ago | fzliu | modal.com | newest
1
voyage-3-large (voyageai.com)
5 months ago | fzliu | voyageai.com | newest
1
End To End testing for Prometheus (2023) (squiggly.dev)
5 months ago | fzliu | squiggly.dev | newest
2
First Principles Thinking (2023) (principles.dev)
5 months ago | fzliu | principles.dev | newest
2
The Art of Interference (lichess.org)
5 months ago | fzliu | lichess.org | newest
Next >