ML News
new
|
past
|
best
|
rss
|
submit
about
Stories from November 18, 2025 (UTC)
Go back a
day
,
month
, or
year
. Go forward a
day
.
1.
Solving a million-step LLM task with zero errors
(
arxiv.org
)
222 points
by
Anon84
320 days ago
|
hide
|
past
|
pdf
|
95 comments
2.
LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
(
arxiv.org
)
68 points
by
nothrowaways
320 days ago
|
hide
|
past
|
pdf
|
18 comments
3.
Out-of-Distribution Generalization in Transformers via Latent Space Reasoning
(
arxiv.org
)
9 points
by
marojejian
320 days ago
|
hide
|
past
|
pdf
|
1 comment
4.
The Fundamental Limits of LLMs at Scale
(
arxiv.org
)
6 points
by
Hard_Space
320 days ago
|
hide
|
past
|
pdf
|
discuss
5.
AA-Omniscience: Evaluating Cross-Domain Knowledge Reliability in Language Models
(
arxiv.org
)
6 points
by
declanjackson
320 days ago
|
hide
|
past
|
pdf
|
1 comment
6.
Back to Basics: Let Denoising Generative Models Denoise
(
arxiv.org
)
4 points
by
dvrp
320 days ago
|
hide
|
past
|
pdf
|
discuss
7.
VRScout: Towards Real-Time, Autonomous Testing of Virtual Reality Games
(
arxiv.org
)
2 points
by
PaulHoule
320 days ago
|
hide
|
past
|
pdf
|
discuss
8.
SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing
(
arxiv.org
)
2 points
by
PaulHoule
320 days ago
|
hide
|
past
|
pdf
|
discuss
9.
Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
(
arxiv.org
)
2 points
by
fzliu
320 days ago
|
hide
|
past
|
pdf
|
discuss
10.
Reliable Confidence Intervals for Information Retrieval Evaluation
(
arxiv.org
)
1 point
by
matesz
320 days ago
|
hide
|
past
|
pdf
|
discuss
About
|
RSS
|
RSS (all)
|
HN arXiv