Hacker News headlines

1

Evaluating Embedding Models for Code (voyageai.com)

4 months ago | fzliu | voyageai.com | newest

1

To Save C, We Must Save ABI (2022) (thephd.dev)

4 months ago | fzliu | thephd.dev | newest

2

Write code with your Alphabet Radio on (vickiboykis.com)

4 months ago | fzliu | vickiboykis.com | newest

2

voyage-code-3: Code embedding model with Matryoshka learning and quantization (voyageai.com)

4 months ago | fzliu | voyageai.com | newest

4

voyage-3-large (twitter.com/voyageai)

4 months ago | fzliu | twitter.com | frontpage

1

Embedding model with Matryoshka learning and quantization-aware training (voyageai.com)

4 months ago | fzliu | voyageai.com | newest

1

Embrace the SICK (2018) (ibiblio.org)

4 months ago | fzliu | ibiblio.org | newest

1

General-Purpose vs. Domain-Specific Embedding Models (timescale.com)

4 months ago | fzliu | timescale.com | newest

2

Evaluating Embedding Models for Code (voyageai.com)

4 months ago | fzliu | voyageai.com | newest

1

Code embedding model with Matryoshka learning and quantization-aware training (voyageai.com)

4 months ago | fzliu | voyageai.com | newest

2

Pocketstox: Semantic search between news articles and earnings transcripts (andresvolosyanko.com)

4 months ago | fzliu | andresvolosyanko.com | newest

2

Aging in Chess (lichess.org)

4 months ago | fzliu | lichess.org | newest

2

Powering AI RAG Applications with Vector Embeddings (sambanova.ai)

4 months ago | fzliu | sambanova.ai | frontpage

1

Evaluating Code Embedding Models (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

2

The Upside of the Pentium Bug (1995) [pdf] (uci.edu)

5 months ago | fzliu | uci.edu | frontpage

1

Evaluating Code Embeddings (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

2

Code embedding model with Matryoshka learning and quantization-aware training (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

2

Evaluating Code Embeddings (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

1

Code embeddings with Matryoshka learning and quantization awareness (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

2

Leanness combined with healthy lifestyle protective against early death (2016) (hsph.harvard.edu)

5 months ago | fzliu | harvard.edu | newest

2

Beating Arc the Hard Way (nonint.com)

5 months ago | fzliu | nonint.com | newest

3

Why are we using LLMs as calculators? (vickiboykis.com)

5 months ago | fzliu | vickiboykis.com | frontpage

1

Code embedding model with Matryoshka learning and quantization-aware training (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

2

Evaluating Code Embeddings (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

2

[dupe] ModernBERT (arxiv.org)

5 months ago | fzliu | arxiv.org | newest

2

Code embedding model with Matryoshka learning and quantization-aware training (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

1

Evaluating Code Embeddings (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

1

Head-to-head benchmarking tool for embedding models (github.com/voyage-ai)

5 months ago | fzliu | github.com | newest

1

voyage-code-3 (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

1

How do we evaluate vector-based code retrieval? (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

1

Are You a Peacetime CEO or a Wartime CEO? (2011) (hbr.org)

5 months ago | fzliu | hbr.org | newest

2

Arctic-Embed 2.0: Multilingual Retrieval Without Compromise (arxiv.org)

5 months ago | fzliu | arxiv.org | newest

1

Evaluating Code Embeddings (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

1

Head-to-head benchmarking tool for embedding models (github.com/voyage-ai)

5 months ago | fzliu | github.com | newest

1

Code embedding model with Matryoshka learning and quantization-aware training (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

1

A Better Way to Measure Progress in Semiconductors (2020) (ieee.org)

5 months ago | fzliu | ieee.org | newest

1

Global AI Power Rankings (stanford.edu)

5 months ago | fzliu | stanford.edu | newest

2

Evaluating Code Embeddings (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

1

Head-to-head benchmarking tool for embedding models (github.com/voyage-ai)

5 months ago | fzliu | github.com | newest

1

Code embedding model with Matryoshka learning and quantization-aware training (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

2

How do we evaluate vector-based code retrieval? (voyageai.com)

5 months ago | fzliu | voyageai.com | newest

1

Do LLMs Perform Latent Multi-Hop Reasoning Without Exploiting Shortcuts? (arxiv.org)

5 months ago | fzliu | arxiv.org | newest

1

Multimodal RAG (github.com/fzliu)

6 months ago | fzliu | github.com | newest

1

CS229 Lecture Notes (2023) [pdf] (stanford.edu)

6 months ago | fzliu | stanford.edu | newest

2

Head-to-head benchmarking tool for embedding models (github.com/voyage-ai)

6 months ago | fzliu | github.com | newest

1

Embeddings Drive the Quality of RAG (2023) (voyageai.com)

6 months ago | fzliu | voyageai.com | newest

3

The PhD Application from a Faculty's Perspective (eugenewu.net)

6 months ago | fzliu | eugenewu.net | newest

1

Voyage Multilingual Rerankers (voyageai.com)

6 months ago | fzliu | voyageai.com | newest

2

A statistical approach to model evaluations (anthropic.com)

6 months ago | fzliu | anthropic.com | newest

27

32k context length text embedding models (voyageai.com)

6 months ago | fzliu | voyageai.com | best

9

Samurai: Adapting Segment Anything Model for Zero-Shot Visual Tracking (arxiv.org)

6 months ago | fzliu | arxiv.org | frontpage

2

Embedding Model Benchmark Tool (github.com/voyage-ai)

6 months ago | fzliu | github.com | newest

2

Voyage Multilingual Rerankers (voyageai.com)

6 months ago | fzliu | voyageai.com | newest

1

The next generation of Voyage multilingual rerankers (voyageai.com)

6 months ago | fzliu | voyageai.com | newest

63

All-in-one embedding model for interleaved text, images, and screenshots (voyageai.com)

6 months ago | fzliu | voyageai.com | best

1

Multimodal embedding model for interleaved text, images, and screenshots (voyageai.com)

6 months ago | fzliu | voyageai.com | newest

32

BERTs Are Generative In-Context Learners (arxiv.org)

6 months ago | fzliu | arxiv.org | best

1

In Search of Forgotten Domain Generalization (arxiv.org)

6 months ago | fzliu | arxiv.org | newest

2

All-in-one embedding model for interleaved text, images, and screenshots (voyageai.com)

6 months ago | fzliu | voyageai.com | newest

1

All-in-one embedding model for interleaved text, images, and screenshots (voyageai.com)

6 months ago | fzliu | voyageai.com | newest

1

Age Normalized Testosterone Peaks at Series B for Male Startup Founders (arxiv.org)

6 months ago | fzliu | arxiv.org | newest

1

Elasticsearch vs. Vespa Performance Comparison (vespa.ai)

6 months ago | fzliu | vespa.ai | newest

1

Getting started with Voyage multimodal embeddings (colab.research.google.com)

6 months ago | fzliu | google.com | newest

1

Multimodal embeddings for interleaved text and images (voyageai.com)

6 months ago | fzliu | voyageai.com | newest

1

Adaptive Length Image Tokenization via Recurrent Allocation (arxiv.org)

6 months ago | fzliu | arxiv.org | newest

1

An Empirical Model of Large-Batch Training (2018) (arxiv.org)

6 months ago | fzliu | arxiv.org | newest

3

Elasticsearch vs. Vespa Performance Comparison (vespa.ai)

6 months ago | fzliu | vespa.ai | newest

2

Embedding Model Benchmark Tool (github.com/voyage-ai)

6 months ago | fzliu | github.com | newest

1

How Does a Reranker Work? (voyageai.com)

6 months ago | fzliu | voyageai.com | newest

2

Prejudice and China (gavekal.com)

6 months ago | fzliu | gavekal.com | newest

1

Rerank-2 and rerank-2-lite: the next generation of Voyage multilingual rerankers (voyageai.com)

6 months ago | fzliu | voyageai.com | newest

1

Multimodal embeddings for interleaved text and images (voyageai.com)

6 months ago | fzliu | voyageai.com | newest

3

Double Delusion (lichess.org)

6 months ago | fzliu | lichess.org | newest

1

Understanding Warmup-Stable-Decay Learning Rates (arxiv.org)

6 months ago | fzliu | arxiv.org | newest

3

Multimodal embeddings for interleaved text and images (voyageai.com)

6 months ago | fzliu | voyageai.com | newest

1

What the Hype and Reality of Agents (leehanchung.github.io)

6 months ago | fzliu | github.io | newest

2

Multimodal RAG (github.com/fzliu)

7 months ago | fzliu | github.com | newest

1

32K-token context length embedding models (voyageai.com)

7 months ago | fzliu | voyageai.com | newest

1

How to win Equalized/Worst positions? (lichess.org)

7 months ago | fzliu | lichess.org | newest

2

The Modern RAG Stack (adamkhakhar.substack.com)

7 months ago | fzliu | substack.com | newest

35

OmniParser for Pure Vision Based GUI Agent (microsoft.github.io)

7 months ago | fzliu | github.io | best

1

Improving Generalization Performance by Switching from Adam to SGD (2017) (arxiv.org)

7 months ago | fzliu | arxiv.org | newest

1

Embeddings Drive the Quality of RAG: A Case Study of Chat.LangChain (voyageai.com)

7 months ago | fzliu | voyageai.com | newest

1

Rerank-2 and rerank-2-lite: the next generation of Voyage multilingual rerankers (voyageai.com)

7 months ago | fzliu | voyageai.com | newest

1

32K-token context length embedding models (voyageai.com)

7 months ago | fzliu | voyageai.com | newest

1

Voyage-3 and voyage-3-lite: small yet mighty general-purpose embedding models (voyageai.com)

7 months ago | fzliu | voyageai.com | newest

1

Why opening statistics are hard (lichess.org)

7 months ago | fzliu | lichess.org | newest

2

Does Refusal Training in LLMs Generalize to the Past Tense? (arxiv.org)

7 months ago | fzliu | arxiv.org | newest

1

TxT360 (huggingface.co)

7 months ago | fzliu | huggingface.co | newest

1

Rerank-2 and rerank-2-lite: the next generation of Voyage multilingual rerankers (voyageai.com)

7 months ago | fzliu | voyageai.com | newest

2

32K-token context length embedding models (voyageai.com)

7 months ago | fzliu | voyageai.com | newest

1

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence (arxiv.org)

7 months ago | fzliu | arxiv.org | newest

1

How Does a Reranker Work? (voyageai.com)

7 months ago | fzliu | voyageai.com | newest

1

Robust (Structured) Text Generation (github.com/dottxt-ai)

7 months ago | fzliu | github.com | newest

71

Project Euler #912: Where are the Odds? (projecteuler.net)

7 months ago | fzliu | projecteuler.net | best

2

Updating Your Priors in the Age of Scaling Compute (leehanchung.github.io)

7 months ago | fzliu | github.io | newest

1

Semantic Search with Milvus Lite and Voyage AI (voyageai.com)

7 months ago | fzliu | voyageai.com | newest

1

How Does a Reranker Work? (voyageai.com)

7 months ago | fzliu | voyageai.com | newest

35

AI Winter Is Coming (leehanchung.github.io)

7 months ago | fzliu | github.io | best

1

32K-token context length embedding models (voyageai.com)

7 months ago | fzliu | voyageai.com | newest