ML News
new
|
past
|
best
|
rss
|
submit
about
Stories from October 5, 2026 (UTC)
Go back a
day
,
month
, or
year
. Go forward a
day
.
1.
New Flash Attention
(
arxiv.org
)
2 points
by
sashko1
43 days ago
|
hide
|
past
|
pdf
|
discuss
2.
LLMs Learn to Evade Latent Monitors from Prior Feedback Alone
(
arxiv.org
)
2 points
by
Betelbuddy
43 days ago
|
hide
|
past
|
pdf
|
discuss
3.
Securing Computer-Use Agents Against Branch Steering Attacks
(
arxiv.org
)
2 points
by
sbulaev
43 days ago
|
hide
|
past
|
pdf
|
discuss
4.
Scalable, Efficient Optical Architecture for Muxed Deepfake Video Detection
(
arxiv.org
)
2 points
by
rbanffy
43 days ago
|
hide
|
past
|
pdf
|
discuss
5.
The Output-Space Hypothesis:Enumerative Equivalence Checking for Tensor Programs
(
arxiv.org
)
1 point
by
matt_d
43 days ago
|
hide
|
past
|
pdf
|
discuss
6.
Evaluating Memory Structure in LLM Agents
(
arxiv.org
)
1 point
by
matt_d
43 days ago
|
hide
|
past
|
pdf
|
discuss
7.
CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering
(
arxiv.org
)
1 point
by
pykello
44 days ago
|
hide
|
past
|
pdf
|
discuss
About
|
RSS
|
RSS (all)
|
HN arXiv