Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
ML Research
📊 ML Research
machine learning papers, deep learning, model training, benchmarks
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
295
posts in
6.5
ms
ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs
🤖
AI Models
Content type:
Academic
arxiv.org
·
21h
21 hours ago
Actions for ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs
Gram
Newton-Schulz: A Fast, Hardware-Aware Newton-Schulz Algorithm for Muon
📏
Model Evaluation
Content type:
Blog
tridao.me
·
1d
1 day ago
·
Hacker News
Actions for Gram Newton-Schulz: A Fast, Hardware-Aware Newton-Schulz Algorithm for Muon
Unpacking AI: The Hardware Behind AI
🤖
AI Models
Content type:
News
pathtostaff.com
·
4d
4 days ago
·
Hacker News
Actions for Unpacking AI: The Hardware Behind AI
meleantonio forked meleantonio/DEQN_Galo_03_2026 from sischei/DEQN_Galo_03_2026
📏
Model Evaluation
Content type:
Code
github.com
·
6d
6 days ago
Actions for meleantonio forked meleantonio/DEQN_Galo_03_2026 from sischei/DEQN_Galo_03_2026
RKSC: Reasoning-Aware KV Cache Sharing and Confident Early Exit for Multi-Step LLM
Inference
📝
Prompt Engineering
Content type:
Academic
arxiv.org
·
21h
21 hours ago
Actions for RKSC: Reasoning-Aware KV Cache Sharing and Confident Early Exit for Multi-Step LLM Inference
Less-relevant results
Designing Loops That Prompt
Coding
Agents: The Six I Actually Run
📝
Prompt Engineering
cameronwestland.com
·
2d
2 days ago
·
Hacker News
Actions for Designing Loops That Prompt Coding Agents: The Six I Actually Run
UniSVQ: 2-bit Unified Scalar-Vector Quantization
📝
Prompt Engineering
Content type:
Academic
arxiv.org
·
21h
21 hours ago
Actions for UniSVQ: 2-bit Unified Scalar-Vector Quantization
Growing Pains of Starting a Secret Society
📝
Prompt Engineering
Content type:
Blog
mrmarket.bearblog.dev
·
1d
1 day ago
·
Hacker News
Actions for Growing Pains of Starting a Secret Society
Tampa Bay tech, entrepreneur, and nerd events list (Monday, June 8 – Sunday, June 14)
📋
Event Sourcing
globalnerdy.com
·
5d
5 days ago
Actions for Tampa Bay tech, entrepreneur, and nerd events list (Monday, June 8 – Sunday, June 14)
Fast and Highly Expressive Policy
Learning
for Offline Reinforcement
Learning
via Bootstrapped Flow
Q-Learning
🔒
AI Safety
Content type:
Academic
arxiv.org
·
21h
21 hours ago
Actions for Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning
Diverse binding poses of agonistic neurotoxins on human Na v 1.6
🤖
AI Models
Content type:
Academic
nature.com
·
1d
1 day ago
Actions for Diverse binding poses of agonistic neurotoxins on human Na v 1.6
AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic
Inference
🧠
LLMs
Content type:
Academic
arxiv.org
·
21h
21 hours ago
Actions for AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic Inference
The Exploit Always Wins
🤖
LLM Agents
Content type:
Blog
abhishek-shankar.com
·
5d
5 days ago
Actions for The Exploit Always Wins
KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.
✅
TLA+
Content type:
Code
github.com
·
9h
9 hours ago
·
Hacker News
Actions for KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.
Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs
📝
Prompt Engineering
lesswrong.com
·
5d
5 days ago
Actions for Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs
A Theory on Flow Matching with Neural Networks
🤖
AI Models
Content type:
Academic
arxiv.org
·
21h
21 hours ago
Actions for A Theory on Flow Matching with Neural Networks
Meta's smart glasses companion app ships a complete, dormant face-recognition pipeline on a stock account.
✅
TLA+
buchodi.com
·
6d
6 days ago
·
Hacker News
Actions for Meta's smart glasses companion app ships a complete, dormant face-recognition pipeline on a stock account.
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs
📝
Prompt Engineering
Content type:
Academic
arxiv.org
·
21h
21 hours ago
Actions for How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs
princezuda/-RequiemGPT-: Fully open source and open weights built and
trained
by fable five with one prompt. An experience in how AI actually works
🤖
AI Models
Content type:
Code
github.com
·
1d
1 day ago
·
Hacker News
Actions for princezuda/-RequiemGPT-: Fully open source and open weights built and trained by fable five with one prompt. An experience in how AI actually works
Dynamic Linear Attention
🧠
LLMs
Content type:
Academic
arxiv.org
·
21h
21 hours ago
Actions for Dynamic Linear Attention
Sign up or log in to see more results
Sign Up
Login
« Page 2
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
j
/
k
Open post
o
or
Enter
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
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Browse
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help