ML News
new
|
past
|
best
|
rss
|
submit
about
Stories from October 19, 2026 (UTC)
Go back a
day
,
month
, or
year
. Go forward a
day
.
1.
Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories
(
arxiv.org
)
3 points
by
gradus_ad
29 days ago
|
hide
|
past
|
pdf
|
discuss
2.
A team of Gemini 4 Argon agents beats Minecraft
(
arxiv.org
)
3 points
by
DeepLogin
29 days ago
|
hide
|
past
|
pdf
|
1 comment
3.
Architecting for HW Diversity: Meta's E2E Co-Design for AI Training on AMD GPUs
(
arxiv.org
)
3 points
by
matt_d
30 days ago
|
hide
|
past
|
pdf
|
discuss
4.
AI Discovery in Combinatorics: From Problems to Solutions and Back
(
arxiv.org
)
2 points
by
JohnHammersley
29 days ago
|
hide
|
past
|
pdf
|
discuss
5.
T0: A Time-Series Foundation Model for Forecasting with Context
(
arxiv.org
)
2 points
by
GeoffNN
29 days ago
|
hide
|
past
|
pdf
|
discuss
6.
A New Lens on Multi-GPU Comms: API-Level Memory Models for Portable Optimization
(
arxiv.org
)
2 points
by
matt_d
29 days ago
|
hide
|
past
|
pdf
|
discuss
7.
Understanding Nvidia Grace-Blackwell Unified Memory Through Microbenchmarks
(
arxiv.org
)
2 points
by
matt_d
29 days ago
|
hide
|
past
|
pdf
|
discuss
8.
Profiling the Attack Surface of AI Agent Skills
(
arxiv.org
)
1 point
by
ratneshiiita
29 days ago
|
hide
|
past
|
pdf
|
discuss
9.
FloatDoor: Platform-Triggered Backdoors in LLMs
(
arxiv.org
)
1 point
by
mcyc
29 days ago
|
hide
|
past
|
pdf
|
discuss
10.
Better and Faster Large Language Models via Multi-Token Prediction (2024)
(
arxiv.org
)
1 point
by
peter_d_sherman
29 days ago
|
hide
|
past
|
pdf
|
discuss
11.
Harness²: Recursive Agent Harnessing for an Open World (Google Research)
(
arxiv.org
)
1 point
by
aljazfarkas
29 days ago
|
hide
|
past
|
pdf
|
discuss
12.
From Memory Hits to Answerable Evidence
(
arxiv.org
)
1 point
by
axis_official
29 days ago
|
hide
|
past
|
pdf
|
discuss
About
|
RSS
|
RSS (all)
|
HN arXiv