Tokenization

Feeds to Scour
SubscribedAll
Scoured 39 posts in 7.9 ms

Show HN: SupXML, modern memory-safe XML parser replacement for libxml2

 📡RSS
supso.org··Hacker News

ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding

 🤖LLM  Content type: Academic
arxiv.org·

lbj96347/nemotron-3.5-asr-ios: On-device, offline speech recognition for iPhone/iPad using NVIDIA's Nemotron-3.5-ASR Streaming 0.6B (multilingual) via CoreML.SwiftUI app with mic capture + audio file import, RNN-Tdecoding, and live benchmark metrics (latency, RTF, memory).

 🤖Data science  Content type: Code
github.com··Hacker News

Open source building blocks for computational design. Est. 2006

 🕸️Knowledge Graphs
thi.ng··Hacker News

Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models

 🪟Context Windows  Content type: Academic
arxiv.org·

SIDInspector: A Mapping-First Diagnostic Resource for Semantic-ID Tokenizers

 🪟Context Windows  Content type: Academic
arxiv.org·

inflightsec/agent-vault-proxy: Just-in-time API keys for AI agents - and any other process you route through it: the caller only ever sees a placeholder.

 🏠Self-hosting  Content type: Code
github.com··Hacker News

UniDexTok: A Unified Dexterous Hand Tokenizer from Real Data

 💬Natural Language Processing  Content type: Academic
arxiv.org·

Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models

 🤖LLM  Content type: Academic
arxiv.org·

apple/coreai-models: Model export recipes, Python primitives, and Swift runtime utilities for on-device AI

 🔬Deep Learning  Content type: Code
github.com··Hacker News

F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation

 🤖LLM  Content type: Academic
arxiv.org·

Balancing Image Compression and Generation with Bootstrapped Tokenization

 💬Natural Language Processing  Content type: Academic
arxiv.org·

tigerless-labs/cost-xray: See what Claude Code and Codex actually send to the API — and what each part costs.

 🏠Self-Hosting  Content type: Code
github.com··Hacker News

HybridCodec: Fast Dual-Stream, Semantically Enhanced Neural Audio Codec

 🔢Embeddings  Content type: Academic
arxiv.org·

DREAM: Dynamic Refinement of Early Assignment Mappings

 💬Natural Language Processing  Content type: Academic
arxiv.org·

Show HN: ARouter – drop-in OpenAI/Anthropic proxy that cuts cost and fails over

 🖥️Homelab  Content type: Code
github.com··Hacker News

Reversible Foundations: Training a 120B Sparse MoE through State-Preserving Scaling

 🤖LLM  Content type: Academic
arxiv.org·

BioVid: Autoregressive Video Generation with Biological Behavior Semantic Comprehension

 💬Natural Language Processing  Content type: Academic
arxiv.org·

DotFox/transit.c: A data interchange format and set of libraries for conveying values between applications written in different programming languages.

 📡RSS  Content type: Code
github.com··Lobsters

No more posts from saeedesmaili's subscribed feeds.

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help