Reasoning Models

Feeds to Scour
SubscribedAll
Scoured 27 posts in 17.7 ms

A Comprehensive Anatomy of Human and DeepSeek-R1 LLM Mathematical Reasoning

 🇨🇳Chinese AI  Content type: Academic
arxiv.org·
Less-relevant results

AIchain Skill: A Prompt as a Reusable Object

 🤖AI  Content type: Code
github.com··DEV

Instruction Finetuning DeepSeek-R1-8B Model Using LoRA and NEFTune

 🇨🇳Chinese AI  Content type: Academic
arxiv.org·

Show HN: One API Key for 45 AI Models – Pay per Token, OpenAI Compatible

 🇨🇳Chinese AI
modelhub-api.com··Hacker News

ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models

 🤖AI  Content type: Academic
arxiv.org·

LLM Research Papers: The 2026 List (January to May)

 🎓Advanced content  Content type: News
magazine.sebastianraschka.com
··Hacker News

Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning

 🪄Prompt Engineering  Content type: Academic
arxiv.org·

ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning

 🤖LLM  Content type: Academic
arxiv.org·

Hint Tuning: Less Data Makes Better Reasoners

 🪄Prompt Engineering  Content type: Academic
arxiv.org·

Aspen: Own your intelligence

 🤖AI  Content type: Discussion  Content type: Tutorial
runonaspen.com··Hacker News

Knowledge Graphs and Reasoning LLMs for Finding Simple Yet Effective Transcriptomic Perturbation Predictors

 🗂️Information Architecture  Content type: Academic
arxiv.org·

Test-Time Compute Scaling for ASR with Depth-Conditioned Looped Transformers

 🔓Hacking  Content type: Academic
arxiv.org·

SugaC-275/ToTra: Open-source AI gateway for enterprises — quota, PII protection, cost tracking, and compliance

 🤖AI  Content type: Code
github.com··Hacker News

Contemporary AI lacks the imagination to diverge or negate in science

 📋Text Quality  Content type: Academic
arxiv.org·

Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation

 📱Edge AI Optimization  Content type: Academic
arxiv.org·

The OnlyFans Economy of American AI

 🤖AI  Content type: Blog
leoveanu.com··Hacker News

Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese

 🇨🇳Chinese AI  Content type: Academic
arxiv.org·

ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces

 🇨🇳Chinese AI  Content type: Academic
arxiv.org·

GRPO Does Not Close the Multi-Agent Coordination Gap

 🤖AI  Content type: Academic
arxiv.org·

Rollout-Level Advantage-Prioritized Experience Replay for GRPO

 🔐Cryptography  Content type: Academic
arxiv.org·

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