ML News
new
|
past
|
best
|
rss
|
submit
about
91.
Collaborative AI agents for autonomous experimental research
(
arxiv.org
)
3 points
by
Betelbuddy
17 days ago
|
hide
|
past
|
pdf
|
1 comment
92.
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
(
arxiv.org
)
5 points
by
olalonde
17 days ago
|
hide
|
past
|
pdf
|
1 comment
93.
LLMs recognize dropout and Gaussian noise applied to their activations
(
arxiv.org
)
3 points
by
gone35
18 days ago
|
hide
|
past
|
pdf
|
discuss
94.
The Hitchhiker's Guide to System One Models
(
arxiv.org
)
2 points
by
saikatsg
18 days ago
|
hide
|
past
|
pdf
|
discuss
95.
The Illusion of Thinking: Models Don't Actually Reason
(
arxiv.org
)
14 points
by
CGMthrowaway
19 days ago
|
hide
|
past
|
pdf
|
1 comment
96.
Cross-species representation learning aligns mouse and human neural dynamics
(
arxiv.org
)
1 point
by
gmays
19 days ago
|
hide
|
past
|
pdf
|
discuss
97.
What Drives AI Citations? FAQ isn't what drives ChatGPT citations
(
arxiv.org
)
2 points
by
aidotguru
19 days ago
|
hide
|
past
|
pdf
|
discuss
98.
The Trinity: Capability-Driven Recursive Self-Improvement for Multimodal Agents
(
arxiv.org
)
1 point
by
frozenseven
19 days ago
|
hide
|
past
|
pdf
|
1 comment
99.
LLMs Love Python: A Study of LLMs' Bias
(
arxiv.org
)
2 points
by
codehead
20 days ago
|
hide
|
past
|
pdf
|
discuss
100.
DeepSeek-v4.1-Flash: Pushing the Limits of KV Cache Compression
(
arxiv.org
)
6 points
by
jonbaer
20 days ago
|
hide
|
past
|
pdf
|
discuss
101.
RSI-Anything: Unlocking Recursive Self-Improvement with World Models
(
arxiv.org
)
2 points
by
jonbaer
20 days ago
|
hide
|
past
|
pdf
|
discuss
102.
A Fix for Softmax and Cross-Entropy
(
arxiv.org
)
4 points
by
theanonymousone
20 days ago
|
hide
|
past
|
pdf
|
discuss
103.
StreamVibe: Proactive Video Agents for Evolving User Intent
(
arxiv.org
)
1 point
by
gmays
20 days ago
|
hide
|
past
|
pdf
|
discuss
104.
Why are all LLMs obsessed with Japanese culture?
(
arxiv.org
)
2 points
by
surprisetalk
20 days ago
|
hide
|
past
|
pdf
|
discuss
105.
A Mathematical Theory of the Jacobian Lens
(
arxiv.org
)
1 point
by
krackers
21 days ago
|
hide
|
past
|
pdf
|
1 comment
106.
MathMixup: Boosting LLM Mathematical Reasoning via Curriculum and Decomposition
(
arxiv.org
)
1 point
by
wslh
21 days ago
|
hide
|
past
|
pdf
|
discuss
107.
Token-Efficient Logical Supervision for Mathematical Reasoning
(
arxiv.org
)
1 point
by
wslh
21 days ago
|
hide
|
past
|
pdf
|
discuss
108.
Omega: Can LLMs Reason Outside the Box in Math? (2025)
(
arxiv.org
)
2 points
by
wslh
21 days ago
|
hide
|
past
|
pdf
|
discuss
109.
On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models
(
arxiv.org
)
1 point
by
gmays
21 days ago
|
hide
|
past
|
pdf
|
discuss
110.
Ring-0 by Default: Agents as Operating Systems
(
arxiv.org
)
1 point
by
ersinesen
21 days ago
|
hide
|
past
|
pdf
|
discuss
111.
Cost-Efficient Pareto Recommendation for LLM Agentic Workflows
(
arxiv.org
)
1 point
by
saikatsg
21 days ago
|
hide
|
past
|
pdf
|
discuss
112.
Repairing Broken Access Control in Web Applications with LLMs
(
arxiv.org
)
2 points
by
50kIters
21 days ago
|
hide
|
past
|
pdf
|
discuss
113.
Toolflation: Seller Agents Distort Tool Markets
(
arxiv.org
)
2 points
by
diautonofinz
22 days ago
|
hide
|
past
|
pdf
|
1 comment
114.
Compaction Laundering: Provenance Destruction in Context-Compacting Coding Agent
(
arxiv.org
)
9 points
by
nahsra
22 days ago
|
hide
|
past
|
pdf
|
2 comments
115.
Parallel Language Models via Variational Decoding [pdf]
(
arxiv.org
)
1 point
by
simonpure
22 days ago
|
hide
|
past
|
pdf
|
discuss
116.
Unintended Disclosure Through Revision Traces of LLM Deliverables
(
arxiv.org
)
1 point
by
hasley
22 days ago
|
hide
|
past
|
pdf
|
1 comment
117.
Model Equality Testing: Which Model Is This API Serving?
(
arxiv.org
)
1 point
by
ogous
22 days ago
|
hide
|
past
|
pdf
|
discuss
118.
Attention Is Not What You Need (2025)
(
arxiv.org
)
197 points
by
westurner
23 days ago
|
hide
|
past
|
pdf
|
72 comments
119.
What the Specification Did Not Say: Gaps in Test-Graded Coding-Agent Benchmarks
(
arxiv.org
)
2 points
by
mehdizare
23 days ago
|
hide
|
past
|
pdf
|
discuss
120.
How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
(
arxiv.org
)
2 points
by
tchalla
23 days ago
|
hide
|
past
|
pdf
|
discuss
More
About
|
RSS
|
RSS (all)
|
HN arXiv